mm: move tlb_flush_pending inline helpers to mm_inline.h

linux/mm_types.h should only define structure definitions, to make it
cheap to include elsewhere.  The atomic_t helper function definitions
are particularly large, so it's better to move the helpers using those
into the existing linux/mm_inline.h and only include that where needed.

As a follow-up, we may want to go through all the indirect includes in
mm_types.h and reduce them as much as possible.

Link: https://lkml.kernel.org/r/20211207125710.2503446-2-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Colin Cross <ccross@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 86 insertions, 0 deletions

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 47d96d2647ca..b725839dfe71 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -2,6 +2,7 @@
 #ifndef LINUX_MM_INLINE_H
 #define LINUX_MM_INLINE_H
 
+#include <linux/atomic.h>
 #include <linux/huge_mm.h>
 #include <linux/swap.h>
 #include <linux/string.h>
@@ -185,4 +186,89 @@ static inline bool is_same_vma_anon_name(struct vm_area_struct *vma,
 }
 #endif  /* CONFIG_ANON_VMA_NAME */
 
+static inline void init_tlb_flush_pending(struct mm_struct *mm)
+{
+	atomic_set(&mm->tlb_flush_pending, 0);
+}
+
+static inline void inc_tlb_flush_pending(struct mm_struct *mm)
+{
+	atomic_inc(&mm->tlb_flush_pending);
+	/*
+	 * The only time this value is relevant is when there are indeed pages
+	 * to flush. And we'll only flush pages after changing them, which
+	 * requires the PTL.
+	 *
+	 * So the ordering here is:
+	 *
+	 *	atomic_inc(&mm->tlb_flush_pending);
+	 *	spin_lock(&ptl);
+	 *	...
+	 *	set_pte_at();
+	 *	spin_unlock(&ptl);
+	 *
+	 *				spin_lock(&ptl)
+	 *				mm_tlb_flush_pending();
+	 *				....
+	 *				spin_unlock(&ptl);
+	 *
+	 *	flush_tlb_range();
+	 *	atomic_dec(&mm->tlb_flush_pending);
+	 *
+	 * Where the increment if constrained by the PTL unlock, it thus
+	 * ensures that the increment is visible if the PTE modification is
+	 * visible. After all, if there is no PTE modification, nobody cares
+	 * about TLB flushes either.
+	 *
+	 * This very much relies on users (mm_tlb_flush_pending() and
+	 * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
+	 * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
+	 * locks (PPC) the unlock of one doesn't order against the lock of
+	 * another PTL.
+	 *
+	 * The decrement is ordered by the flush_tlb_range(), such that
+	 * mm_tlb_flush_pending() will not return false unless all flushes have
+	 * completed.
+	 */
+}
+
+static inline void dec_tlb_flush_pending(struct mm_struct *mm)
+{
+	/*
+	 * See inc_tlb_flush_pending().
+	 *
+	 * This cannot be smp_mb__before_atomic() because smp_mb() simply does
+	 * not order against TLB invalidate completion, which is what we need.
+	 *
+	 * Therefore we must rely on tlb_flush_*() to guarantee order.
+	 */
+	atomic_dec(&mm->tlb_flush_pending);
+}
+
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	/*
+	 * Must be called after having acquired the PTL; orders against that
+	 * PTLs release and therefore ensures that if we observe the modified
+	 * PTE we must also observe the increment from inc_tlb_flush_pending().
+	 *
+	 * That is, it only guarantees to return true if there is a flush
+	 * pending for _this_ PTL.
+	 */
+	return atomic_read(&mm->tlb_flush_pending);
+}
+
+static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+{
+	/*
+	 * Similar to mm_tlb_flush_pending(), we must have acquired the PTL
+	 * for which there is a TLB flush pending in order to guarantee
+	 * we've seen both that PTE modification and the increment.
+	 *
+	 * (no requirement on actually still holding the PTL, that is irrelevant)
+	 */
+	return atomic_read(&mm->tlb_flush_pending) > 1;
+}
+
+
 #endif