add barriers to buffer_uptodate and set_buffer_uptodate

Let's have a look at this piece of code in __bread_slow:

get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
submit_bh(REQ_OP_READ, 0, bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;

Neither wait_on_buffer nor buffer_uptodate contain any memory barrier.
Consequently, if someone calls sb_bread and then reads the buffer data,
the read of buffer data may be executed before wait_on_buffer(bh) on
architectures with weak memory ordering and it may return invalid data.

Fix this bug by adding a memory barrier to set_buffer_uptodate and an
acquire barrier to buffer_uptodate (in a similar way as
folio_test_uptodate and folio_mark_uptodate).

Signed-off-by: Mikulas Patocka <[e-mail]>
Reviewed-by: Matthew Wilcox (Oracle) <[e-mail]>
Cc: [e-mail]
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/buffer_head.h

···
  * of the form "mark_buffer_foo()".  These are higher-level functions which
  * do something in addition to setting a b_state bit.
  */
-BUFFER_FNS(Uptodate, uptodate)
 BUFFER_FNS(Dirty, dirty)
 TAS_BUFFER_FNS(Dirty, dirty)
 BUFFER_FNS(Lock, locked)
···
 BUFFER_FNS(Meta, meta)
 BUFFER_FNS(Prio, prio)
 BUFFER_FNS(Defer_Completion, defer_completion)
+
+static __always_inline void set_buffer_uptodate(struct buffer_head *bh)
+{
+	/*
+	 * make it consistent with folio_mark_uptodate
+	 * pairs with smp_load_acquire in buffer_uptodate
+	 */
+	smp_mb__before_atomic();
+	set_bit(BH_Uptodate, &bh->b_state);
+}
+
+static __always_inline void clear_buffer_uptodate(struct buffer_head *bh)
+{
+	clear_bit(BH_Uptodate, &bh->b_state);
+}
+
+static __always_inline int buffer_uptodate(const struct buffer_head *bh)
+{
+	/*
+	 * make it consistent with folio_test_uptodate
+	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
+	 */
+	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+}
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)