commit
8d423db527eb4384bc1087788863d09346a40c12 upstream.
Currently the PG_mte_tagged page flag mostly means the page contains
valid tags and it should be set after the tags have been cleared or
restored. However, in mte_sync_tags() it is set before setting the tags
to avoid, in theory, a race with concurrent mprotect(PROT_MTE) for
shared pages. However, a concurrent mprotect(PROT_MTE) with a copy on
write in another thread can cause the new page to have stale tags.
Similarly, tag reading via ptrace() can read stale tags if the
PG_mte_tagged flag is set before actually clearing/restoring the tags.
Fix the PG_mte_tagged semantics so that it is only set after the tags
have been cleared or restored. This is safe for swap restoring into a
MAP_SHARED or CoW page since the core code takes the page lock. Add two
functions to test and set the PG_mte_tagged flag with acquire and
release semantics. The downside is that concurrent mprotect(PROT_MTE) on
a MAP_SHARED page may cause tag loss. This is already the case for KVM
guests if a VMM changes the page protection while the guest triggers a
user_mem_abort().
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
[pcc@google.com: fix build with CONFIG_ARM64_MTE disabled]
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Peter Collingbourne <pcc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221104011041.290951-3-pcc@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
/* track which pages have valid allocation tags */
#define PG_mte_tagged PG_arch_2
+static inline void set_page_mte_tagged(struct page *page)
+{
+ /*
+ * Ensure that the tags written prior to this function are visible
+ * before the page flags update.
+ */
+ smp_wmb();
+ set_bit(PG_mte_tagged, &page->flags);
+}
+
+static inline bool page_mte_tagged(struct page *page)
+{
+ bool ret = test_bit(PG_mte_tagged, &page->flags);
+
+ /*
+ * If the page is tagged, ensure ordering with a likely subsequent
+ * read of the tags.
+ */
+ if (ret)
+ smp_rmb();
+ return ret;
+}
+
void mte_zero_clear_page_tags(void *addr);
void mte_sync_tags(pte_t old_pte, pte_t pte);
void mte_copy_page_tags(void *kto, const void *kfrom);
/* unused if !CONFIG_ARM64_MTE, silence the compiler */
#define PG_mte_tagged 0
+static inline void set_page_mte_tagged(struct page *page)
+{
+}
+static inline bool page_mte_tagged(struct page *page)
+{
+ return false;
+}
static inline void mte_zero_clear_page_tags(void *addr)
{
}
static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
{
if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
- set_bit(PG_mte_tagged, &folio->flags);
+ set_page_mte_tagged(&folio->page);
}
#endif /* CONFIG_ARM64_MTE */
* Clear the tags in the zero page. This needs to be done via the
* linear map which has the Tagged attribute.
*/
- if (!test_and_set_bit(PG_mte_tagged, &ZERO_PAGE(0)->flags))
+ if (!page_mte_tagged(ZERO_PAGE(0))) {
mte_clear_page_tags(lm_alias(empty_zero_page));
+ set_page_mte_tagged(ZERO_PAGE(0));
+ }
kasan_init_hw_tags_cpu();
}
* Pages mapped in user space as !pte_access_permitted() (e.g.
* PROT_EXEC only) may not have the PG_mte_tagged flag set.
*/
- if (!test_bit(PG_mte_tagged, &page->flags)) {
+ if (!page_mte_tagged(page)) {
put_page(page);
dump_skip(cprm, MTE_PAGE_TAG_STORAGE);
continue;
if (!page)
continue;
- if (!test_bit(PG_mte_tagged, &page->flags))
+ if (!page_mte_tagged(page))
continue;
ret = save_tags(page, pfn);
if (check_swap && is_swap_pte(old_pte)) {
swp_entry_t entry = pte_to_swp_entry(old_pte);
- if (!non_swap_entry(entry) && mte_restore_tags(entry, page))
+ if (!non_swap_entry(entry) && mte_restore_tags(entry, page)) {
+ set_page_mte_tagged(page);
return;
+ }
}
if (!pte_is_tagged)
* Test PG_mte_tagged again in case it was racing with another
* set_pte_at().
*/
- if (!test_and_set_bit(PG_mte_tagged, &page->flags))
+ if (!page_mte_tagged(page)) {
mte_clear_page_tags(page_address(page));
+ set_page_mte_tagged(page);
+ }
}
void mte_sync_tags(pte_t old_pte, pte_t pte)
/* if PG_mte_tagged is set, tags have already been initialised */
for (i = 0; i < nr_pages; i++, page++) {
- if (!test_bit(PG_mte_tagged, &page->flags))
+ if (!page_mte_tagged(page)) {
mte_sync_page_tags(page, old_pte, check_swap,
pte_is_tagged);
+ set_page_mte_tagged(page);
+ }
}
/* ensure the tags are visible before the PTE is set */
* pages is tagged, set_pte_at() may zero or change the tags of the
* other page via mte_sync_tags().
*/
- if (test_bit(PG_mte_tagged, &page1->flags) ||
- test_bit(PG_mte_tagged, &page2->flags))
+ if (page_mte_tagged(page1) || page_mte_tagged(page2))
return addr1 != addr2;
return ret;
put_page(page);
break;
}
- WARN_ON_ONCE(!test_bit(PG_mte_tagged, &page->flags));
+ WARN_ON_ONCE(!page_mte_tagged(page));
/* limit access to the end of the page */
offset = offset_in_page(addr);
maddr = page_address(page);
if (!write) {
- if (test_bit(PG_mte_tagged, &page->flags))
+ if (page_mte_tagged(page))
num_tags = mte_copy_tags_to_user(tags, maddr,
MTE_GRANULES_PER_PAGE);
else
* completed fully
*/
if (num_tags == MTE_GRANULES_PER_PAGE)
- set_bit(PG_mte_tagged, &page->flags);
+ set_page_mte_tagged(page);
kvm_release_pfn_dirty(pfn);
}
return -EFAULT;
for (i = 0; i < nr_pages; i++, page++) {
- if (!test_bit(PG_mte_tagged, &page->flags)) {
+ if (!page_mte_tagged(page)) {
mte_clear_page_tags(page_address(page));
- set_bit(PG_mte_tagged, &page->flags);
+ set_page_mte_tagged(page);
}
}
copy_page(kto, kfrom);
- if (system_supports_mte() && test_bit(PG_mte_tagged, &from->flags)) {
- set_bit(PG_mte_tagged, &to->flags);
+ if (system_supports_mte() && page_mte_tagged(from)) {
+ page_kasan_tag_reset(to);
mte_copy_page_tags(kto, kfrom);
+ set_page_mte_tagged(to);
}
}
EXPORT_SYMBOL(copy_highpage);
void tag_clear_highpage(struct page *page)
{
mte_zero_clear_page_tags(page_address(page));
- set_bit(PG_mte_tagged, &page->flags);
+ set_page_mte_tagged(page);
}
{
void *tag_storage, *ret;
- if (!test_bit(PG_mte_tagged, &page->flags))
+ if (!page_mte_tagged(page))
return 0;
tag_storage = mte_allocate_tag_storage();