[PATCH v6 3/6] mm: drop per-VMA lock when returning VM_FAULT_RETRY or VM_FAULT_COMPLETED

[Suren Baghdasaryan <surenb@xxxxxxxxxx>]

handle_mm_fault returning VM_FAULT_RETRY or VM_FAULT_COMPLETED means
mmap_lock has been released. However with per-VMA locks behavior is
different and the caller should still release it. To make the
rules consistent for the caller, drop the per-VMA lock when returning
VM_FAULT_RETRY or VM_FAULT_COMPLETED. Currently the only path returning
VM_FAULT_RETRY under per-VMA locks is do_swap_page and no path returns
VM_FAULT_COMPLETED for now.

Signed-off-by: Suren Baghdasaryan <surenb@xxxxxxxxxx>
Acked-by: Peter Xu <peterx@xxxxxxxxxx>
---
 arch/arm64/mm/fault.c   |  3 ++-
 arch/powerpc/mm/fault.c |  3 ++-
 arch/s390/mm/fault.c    |  3 ++-
 arch/x86/mm/fault.c     |  3 ++-
 mm/memory.c             | 12 ++++++++++++
 5 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 935f0a8911f9..9d78ff78b0e3 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -602,7 +602,8 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		goto lock_mmap;
 	}
 	fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs);
-	vma_end_read(vma);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 
 	if (!(fault & VM_FAULT_RETRY)) {
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 5bfdf6ecfa96..82954d0e6906 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -489,7 +489,8 @@ static int ___do_page_fault(struct pt_regs *regs, unsigned long address,
 	}
 
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
-	vma_end_read(vma);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 
 	if (!(fault & VM_FAULT_RETRY)) {
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index dbe8394234e2..40a71063949b 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -418,7 +418,8 @@ static inline vm_fault_t do_exception(struct pt_regs *regs, int access)
 		goto lock_mmap;
 	}
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
-	vma_end_read(vma);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 	if (!(fault & VM_FAULT_RETRY)) {
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
 		goto out;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e8711b2cafaf..56b4f9faf8c4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1341,7 +1341,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto lock_mmap;
 	}
 	fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs);
-	vma_end_read(vma);
+	if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED)))
+		vma_end_read(vma);
 
 	if (!(fault & VM_FAULT_RETRY)) {
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
diff --git a/mm/memory.c b/mm/memory.c
index 0ae594703021..5f26c56ce979 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3730,6 +3730,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 
 	if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
 		ret = VM_FAULT_RETRY;
+		vma_end_read(vma);
 		goto out;
 	}
 
@@ -5182,6 +5183,17 @@ static vm_fault_t sanitize_fault_flags(struct vm_area_struct *vma,
 				 !is_cow_mapping(vma->vm_flags)))
 			return VM_FAULT_SIGSEGV;
 	}
+#ifdef CONFIG_PER_VMA_LOCK
+	/*
+	 * Per-VMA locks can't be used with FAULT_FLAG_RETRY_NOWAIT because of
+	 * the assumption that lock is dropped on VM_FAULT_RETRY.
+	 */
+	if (WARN_ON_ONCE((*flags &
+			(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)) ==
+			(FAULT_FLAG_VMA_LOCK | FAULT_FLAG_RETRY_NOWAIT)))
+		return VM_FAULT_SIGSEGV;
+#endif
+
 	return 0;
 }
 
-- 
2.41.0.255.g8b1d071c50-goog