[PATCH v4 5/8] arm64: mte: Lock a page for MTE tag initialisation

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Catalin Marinas <catalin.marinas@xxxxxxx>

Initialising the tags and setting PG_mte_tagged flag for a page can race
between multiple set_pte_at() on shared pages or setting the stage 2 pte
via user_mem_abort(). Introduce a new PG_mte_lock flag as PG_arch_3 and
set it before attempting page initialisation. Given that PG_mte_tagged
is never cleared for a page, consider setting this flag to mean page
unlocked and wait on this bit with acquire semantics if the page is
locked:

- try_page_mte_tagging() - lock the page for tagging, return true if it
  can be tagged, false if already tagged. No acquire semantics if it
  returns true (PG_mte_tagged not set) as there is no serialisation with
  a previous set_page_mte_tagged().

- set_page_mte_tagged() - set PG_mte_tagged with release semantics.

The two-bit locking is based on Peter Collingbourne's idea.

Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
Signed-off-by: Peter Collingbourne <pcc@xxxxxxxxxx>
Reviewed-by: Steven Price <steven.price@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Marc Zyngier <maz@xxxxxxxxxx>
Cc: Peter Collingbourne <pcc@xxxxxxxxxx>
---
 arch/arm64/include/asm/mte.h     | 35 +++++++++++++++++++++++++++++++-
 arch/arm64/include/asm/pgtable.h |  4 ++--
 arch/arm64/kernel/cpufeature.c   |  2 +-
 arch/arm64/kernel/mte.c          | 12 +++++------
 arch/arm64/kvm/guest.c           | 16 +++++++++------
 arch/arm64/kvm/mmu.c             |  2 +-
 arch/arm64/mm/copypage.c         |  2 ++
 arch/arm64/mm/fault.c            |  2 ++
 arch/arm64/mm/mteswap.c          | 11 +++++-----
 9 files changed, 64 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 46618c575eac..be6560e1ff2b 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -25,7 +25,7 @@ unsigned long mte_copy_tags_to_user(void __user *to, void *from,
 				    unsigned long n);
 int mte_save_tags(struct page *page);
 void mte_save_page_tags(const void *page_addr, void *tag_storage);
-bool mte_restore_tags(swp_entry_t entry, struct page *page);
+void mte_restore_tags(swp_entry_t entry, struct page *page);
 void mte_restore_page_tags(void *page_addr, const void *tag_storage);
 void mte_invalidate_tags(int type, pgoff_t offset);
 void mte_invalidate_tags_area(int type);
@@ -36,6 +36,8 @@ void mte_free_tag_storage(char *storage);
 
 /* track which pages have valid allocation tags */
 #define PG_mte_tagged	PG_arch_2
+/* simple lock to avoid multiple threads tagging the same page */
+#define PG_mte_lock	PG_arch_3
 
 static inline void set_page_mte_tagged(struct page *page)
 {
@@ -60,6 +62,33 @@ static inline bool page_mte_tagged(struct page *page)
 	return ret;
 }
 
+/*
+ * Lock the page for tagging and return 'true' if the page can be tagged,
+ * 'false' if already tagged. PG_mte_tagged is never cleared and therefore the
+ * locking only happens once for page initialisation.
+ *
+ * The page MTE lock state:
+ *
+ *   Locked:	PG_mte_lock && !PG_mte_tagged
+ *   Unlocked:	!PG_mte_lock || PG_mte_tagged
+ *
+ * Acquire semantics only if the page is tagged (returning 'false').
+ */
+static inline bool try_page_mte_tagging(struct page *page)
+{
+	if (!test_and_set_bit(PG_mte_lock, &page->flags))
+		return true;
+
+	/*
+	 * The tags are either being initialised or may have been initialised
+	 * already. Check if the PG_mte_tagged flag has been set or wait
+	 * otherwise.
+	 */
+	smp_cond_load_acquire(&page->flags, VAL & (1UL << PG_mte_tagged));
+
+	return false;
+}
+
 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);
@@ -84,6 +113,10 @@ static inline bool page_mte_tagged(struct page *page)
 {
 	return false;
 }
+static inline bool try_page_mte_tagging(struct page *page)
+{
+	return false;
+}
 static inline void mte_zero_clear_page_tags(void *addr)
 {
 }
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 98b638441521..8735ac1a1e32 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1049,8 +1049,8 @@ static inline void arch_swap_invalidate_area(int type)
 #define __HAVE_ARCH_SWAP_RESTORE
 static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 {
-	if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
-		set_page_mte_tagged(&folio->page);
+	if (system_supports_mte())
+		mte_restore_tags(entry, &folio->page);
 }
 
 #endif /* CONFIG_ARM64_MTE */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index ab3312788d60..e2c0a707a941 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2049,7 +2049,7 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
 	 * Clear the tags in the zero page. This needs to be done via the
 	 * linear map which has the Tagged attribute.
 	 */
-	if (!page_mte_tagged(ZERO_PAGE(0))) {
+	if (try_page_mte_tagging(ZERO_PAGE(0))) {
 		mte_clear_page_tags(lm_alias(empty_zero_page));
 		set_page_mte_tagged(ZERO_PAGE(0));
 	}
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 2287316639f3..54ab6c4741db 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -41,17 +41,17 @@ static void mte_sync_page_tags(struct page *page, pte_t old_pte,
 	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)) {
-			set_page_mte_tagged(page);
-			return;
-		}
+		if (!non_swap_entry(entry))
+			mte_restore_tags(entry, page);
 	}
 
 	if (!pte_is_tagged)
 		return;
 
-	mte_clear_page_tags(page_address(page));
-	set_page_mte_tagged(page);
+	if (try_page_mte_tagging(page)) {
+		mte_clear_page_tags(page_address(page));
+		set_page_mte_tagged(page);
+	}
 }
 
 void mte_sync_tags(pte_t old_pte, pte_t pte)
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 817fdd1ab778..5626ddb540ce 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -1068,15 +1068,19 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
 					clear_user(tags, MTE_GRANULES_PER_PAGE);
 			kvm_release_pfn_clean(pfn);
 		} else {
+			/*
+			 * Only locking to serialise with a concurrent
+			 * set_pte_at() in the VMM but still overriding the
+			 * tags, hence ignoring the return value.
+			 */
+			try_page_mte_tagging(page);
 			num_tags = mte_copy_tags_from_user(maddr, tags,
 							MTE_GRANULES_PER_PAGE);
 
-			/*
-			 * Set the flag after checking the write
-			 * completed fully
-			 */
-			if (num_tags == MTE_GRANULES_PER_PAGE)
-				set_page_mte_tagged(page);
+			/* uaccess failed, don't leave stale tags */
+			if (num_tags != MTE_GRANULES_PER_PAGE)
+				mte_clear_page_tags(page);
+			set_page_mte_tagged(page);
 
 			kvm_release_pfn_dirty(pfn);
 		}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 5a131f009cf9..bebfd1e0bbf0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1066,7 +1066,7 @@ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
 		return;
 
 	for (i = 0; i < nr_pages; i++, page++) {
-		if (!page_mte_tagged(page)) {
+		if (try_page_mte_tagging(page)) {
 			mte_clear_page_tags(page_address(page));
 			set_page_mte_tagged(page);
 		}
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index 731d8a35701e..8dd5a8fe64b4 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -23,6 +23,8 @@ void copy_highpage(struct page *to, struct page *from)
 
 	if (system_supports_mte() && page_mte_tagged(from)) {
 		page_kasan_tag_reset(to);
+		/* It's a new page, shouldn't have been tagged yet */
+		WARN_ON_ONCE(!try_page_mte_tagging(to));
 		mte_copy_page_tags(kto, kfrom);
 		set_page_mte_tagged(to);
 	}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 629e886ceec4..b8b299d1736a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -933,6 +933,8 @@ struct page *alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma,
 
 void tag_clear_highpage(struct page *page)
 {
+	/* Newly allocated page, shouldn't have been tagged yet */
+	WARN_ON_ONCE(!try_page_mte_tagging(page));
 	mte_zero_clear_page_tags(page_address(page));
 	set_page_mte_tagged(page);
 }
diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c
index a78c1db23c68..cd508ba80ab1 100644
--- a/arch/arm64/mm/mteswap.c
+++ b/arch/arm64/mm/mteswap.c
@@ -46,16 +46,17 @@ int mte_save_tags(struct page *page)
 	return 0;
 }
 
-bool mte_restore_tags(swp_entry_t entry, struct page *page)
+void mte_restore_tags(swp_entry_t entry, struct page *page)
 {
 	void *tags = xa_load(&mte_pages, entry.val);
 
 	if (!tags)
-		return false;
+		return;
 
-	mte_restore_page_tags(page_address(page), tags);
-
-	return true;
+	if (try_page_mte_tagging(page)) {
+		mte_restore_page_tags(page_address(page), tags);
+		set_page_mte_tagged(page);
+	}
 }
 
 void mte_invalidate_tags(int type, pgoff_t offset)
-- 
2.37.3.968.ga6b4b080e4-goog

_______________________________________________
kvmarm mailing list
kvmarm@xxxxxxxxxxxxxxxxxxxxx
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm



[Index of Archives]     [Linux KVM]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux