mmu_notifiers: rename invalidate_range notifier

There are two main use cases for mmu notifiers.  One is by KVM which uses
mmu_notifier_invalidate_range_start()/end() to manage a software TLB.

The other is to manage hardware TLBs which need to use the
invalidate_range() callback because HW can establish new TLB entries at
any time.  Hence using start/end() can lead to memory corruption as these
callbacks happen too soon/late during page unmap.

mmu notifier users should therefore either use the start()/end() callbacks
or the invalidate_range() callbacks.  To make this usage clearer rename
the invalidate_range() callback to arch_invalidate_secondary_tlbs() and
update documention.

Link: https://lkml.kernel.org/r/6f77248cd25545c8020a54b4e567e8b72be4dca1.1690292440.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Andrew Donnellan <ajd@linux.ibm.com>
Cc: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Cc: Frederic Barrat <fbarrat@linux.ibm.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Nicolin Chen <nicolinc@nvidia.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zhi Wang <zhi.wang.linux@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

3 files changed, 22 insertions, 10 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3ece117de898..e0420de0e2e0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2120,8 +2120,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	if (is_huge_zero_pmd(*pmd)) {
 		/*
 		 * FIXME: Do we want to invalidate secondary mmu by calling
-		 * mmu_notifier_invalidate_range() see comments below inside
-		 * __split_huge_pmd() ?
+		 * mmu_notifier_arch_invalidate_secondary_tlbs() see comments below
+		 * inside __split_huge_pmd() ?
 		 *
 		 * We are going from a zero huge page write protected to zero
 		 * small page also write protected so it does not seems useful
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4672752b0b17..5ef7bccda50c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6649,8 +6649,9 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 	else
 		flush_hugetlb_tlb_range(vma, start, end);
 	/*
-	 * No need to call mmu_notifier_invalidate_range() we are downgrading
-	 * page table protection not changing it to point to a new page.
+	 * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are
+	 * downgrading page table protection not changing it to point to a new
+	 * page.
 	 *
 	 * See Documentation/mm/mmu_notifier.rst
 	 */
@@ -7294,7 +7295,7 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma,
 	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	hugetlb_vma_unlock_write(vma);
 	/*
-	 * No need to call mmu_notifier_invalidate_range(), see
+	 * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see
 	 * Documentation/mm/mmu_notifier.rst.
 	 */
 	mmu_notifier_invalidate_range_end(&range);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 453a156d93c0..ec3b068cbbe6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -585,8 +585,8 @@ void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 }
 
-void __mmu_notifier_invalidate_range(struct mm_struct *mm,
-				  unsigned long start, unsigned long end)
+void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
+					unsigned long start, unsigned long end)
 {
 	struct mmu_notifier *subscription;
 	int id;
@@ -595,9 +595,10 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 	hlist_for_each_entry_rcu(subscription,
 				 &mm->notifier_subscriptions->list, hlist,
 				 srcu_read_lock_held(&srcu)) {
-		if (subscription->ops->invalidate_range)
-			subscription->ops->invalidate_range(subscription, mm,
-							    start, end);
+		if (subscription->ops->arch_invalidate_secondary_tlbs)
+			subscription->ops->arch_invalidate_secondary_tlbs(
+				subscription, mm,
+				start, end);
 	}
 	srcu_read_unlock(&srcu, id);
 }
@@ -616,6 +617,16 @@ int __mmu_notifier_register(struct mmu_notifier *subscription,
 	mmap_assert_write_locked(mm);
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 
+	/*
+	 * Subsystems should only register for invalidate_secondary_tlbs() or
+	 * invalidate_range_start()/end() callbacks, not both.
+	 */
+	if (WARN_ON_ONCE(subscription &&
+			 (subscription->ops->arch_invalidate_secondary_tlbs &&
+			 (subscription->ops->invalidate_range_start ||
+			  subscription->ops->invalidate_range_end))))
+		return -EINVAL;
+
 	if (!mm->notifier_subscriptions) {
 		/*
 		 * kmalloc cannot be called under mm_take_all_locks(), but we