diff options
author | Claudio Imbrenda <imbrenda@linux.ibm.com> | 2020-03-12 15:29:05 +1100 |
---|---|---|
committer | Christian Borntraeger <borntraeger@de.ibm.com> | 2020-03-12 08:19:51 -0400 |
commit | cb89195caf34ddf14dc688ae062bbed4f236230f (patch) | |
tree | f8e84441ce23e87b829cd29f0b4f6f188280d338 | |
parent | 79f83c54416e741da744f66396b2f813f6a808c5 (diff) | |
download | linux-53_pv.tar.gz |
mm/gup/writeback: add callbacks for inaccessible pages53_pv
With the introduction of protected KVM guests on s390 there is now a
concept of inaccessible pages. These pages need to be made accessible
before the host can access them.
While cpu accesses will trigger a fault that can be resolved, I/O accesses
will just fail. We need to add a callback into architecture code for
places that will do I/O, namely when writeback is started or when a page
reference is taken.
This is not only to enable paging, file backing etc, it is also necessary
to protect the host against a malicious user space. For example a bad
QEMU could simply start direct I/O on such protected memory. We do not
want userspace to be able to trigger I/O errors and thus the logic is
"whenever somebody accesses that page (gup) or does I/O, make sure that
this page can be accessed". When the guest tries to access that page we
will wait in the page fault handler for writeback to have finished and for
the page_ref to be the expected value.
On s390x the function is not supposed to fail, so it is ok to use a
WARN_ON on failure. If we ever need some more finegrained handling we can
tackle this when we know the details.
Link: http://lkml.kernel.org/r/20200306132537.783769-3-imbrenda@linux.ibm.com
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
[borntraeger@de.ibm.com: backport]
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
-rw-r--r-- | include/linux/gfp.h | 6 | ||||
-rw-r--r-- | mm/gup.c | 27 | ||||
-rw-r--r-- | mm/page-writeback.c | 9 |
3 files changed, 38 insertions, 4 deletions
diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ff1c96b8ae927c..047d40b26ffe0d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -485,6 +485,12 @@ static inline void arch_free_page(struct page *page, int order) { } #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif +#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE +static inline int arch_make_page_accessible(struct page *page) +{ + return 0; +} +#endif struct page * __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, diff --git a/mm/gup.c b/mm/gup.c index 98f13ab37bacc1..7dc19e30360e70 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -193,6 +193,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, struct page *page; spinlock_t *ptl; pte_t *ptep, pte; + int ret; retry: if (unlikely(pmd_bad(*pmd))) @@ -246,8 +247,6 @@ retry: if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { - int ret; - ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; @@ -255,7 +254,6 @@ retry: } if (flags & FOLL_SPLIT && PageTransCompound(page)) { - int ret; get_page(page); pte_unmap_unlock(ptep, ptl); lock_page(page); @@ -273,6 +271,18 @@ retry: goto out; } } + /* + * We need to make the page accessible if and only if we are going + * to access its content (the FOLL_GET case). + */ + if (flags & FOLL_GET) { + ret = arch_make_page_accessible(page); + if (ret) { + put_page(page); + page = ERR_PTR(ret); + goto out; + } + } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -1863,6 +1873,17 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, VM_BUG_ON_PAGE(compound_head(page) != head, page); + /* + * We need to make the page accessible if and only if we are + * going to access its content (the FOLL_GET case). + */ + if (flags & FOLL_GET) { + ret = arch_make_page_accessible(page); + if (ret) { + put_page(page); + goto pte_unmap; + } + } SetPageReferenced(page); pages[*nr] = page; (*nr)++; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 1804f64ff43c1c..88c775bbad61c8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2760,7 +2760,7 @@ int test_clear_page_writeback(struct page *page) int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); - int ret; + int ret, access_ret; lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { @@ -2803,6 +2803,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write) inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); } unlock_page_memcg(page); + access_ret = arch_make_page_accessible(page); + /* + * If writeback has been triggered on a page that cannot be made + * accessible, it is too late to recover here. + */ + VM_BUG_ON_PAGE(access_ret != 0, page); + return ret; } |