drivers: Remove explicit invocations of mmiowb()

mmiowb() is now implied by spin_unlock() on architectures that require
it, so there is no reason to call it from driver code. This patch was
generated using coccinelle:

	@mmiowb@
	@@
	- mmiowb();

and invoked as:

$ for d in drivers include/linux/qed sound; do \
spatch --include-headers --sp-file mmiowb.cocci --dir $d --in-place; done

NOTE: mmiowb() has only ever guaranteed ordering in conjunction with
spin_unlock(). However, pairing each mmiowb() removal in this patch with
the corresponding call to spin_unlock() is not at all trivial, so there
is a small chance that this change may regress any drivers incorrectly
relying on mmiowb() to order MMIO writes between CPUs using lock-free
synchronisation. If you've ended up bisecting to this commit, you can
reintroduce the mmiowb() calls using wmb() instead, which should restore
the old behaviour on all architectures other than some esoteric ia64
systems.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>

7 files changed, 0 insertions, 35 deletions

diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index e23980e301b6..69e6a90edf2f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -774,18 +774,12 @@ static inline u16 qed_attn_update_idx(struct qed_hwfn *p_hwfn,
 {
 	u16 rc = 0, index;
 
-	/* Make certain HW write took affect */
-	mmiowb();
-
 	index = le16_to_cpu(p_sb_desc->sb_attn->sb_index);
 	if (p_sb_desc->index != index) {
 		p_sb_desc->index	= index;
 		rc		      = QED_SB_ATT_IDX;
 	}
 
-	/* Make certain we got a consistent view with HW */
-	mmiowb();
-
 	return rc;
 }
 
@@ -1170,7 +1164,6 @@ static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
@@ -1805,9 +1798,6 @@ static void qed_int_igu_enable_attn(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff);
 	qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0xfff);
 
-	/* Flush the writes to IGU */
-	mmiowb();
-
 	/* Unmask AEU signals toward IGU */
 	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff);
 }
@@ -1871,9 +1861,6 @@ static void qed_int_igu_cleanup_sb(struct qed_hwfn *p_hwfn,
 
 	qed_wr(p_hwfn, p_ptt, IGU_REG_COMMAND_REG_CTRL, cmd_ctrl);
 
-	/* Flush the write to IGU */
-	mmiowb();
-
 	/* calculate where to read the status bit from */
 	sb_bit = 1 << (igu_sb_id % 32);
 	sb_bit_addr = igu_sb_id / 32 * sizeof(u32);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 79b311b86f66..f5f3c03b9dd2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -341,9 +341,6 @@ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod)
 		   USTORM_EQE_CONS_OFFSET(p_hwfn->rel_pf_id);
 
 	REG_WR16(p_hwfn, addr, prod);
-
-	/* keep prod updates ordered */
-	mmiowb();
 }
 
 int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b4c8949933f1..4555c0b161ef 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1526,14 +1526,6 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	barrier();
 	writel(txq->tx_db.raw, txq->doorbell_addr);
 
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the queue lock is released and another start_xmit is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
-
 	for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
 		if (qede_txq_has_work(txq))
 			break;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 31b046e24565..6f7e3622c6b4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -580,14 +580,6 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
 
 	internal_ram_wr(rxq->hw_rxq_prod_addr, sizeof(rx_prods),
 			(u32 *)&rx_prods);
-
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the napi lock is released and another qede_poll is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
 }
 
 static void qede_get_rxhash(struct sk_buff *skb, u8 bitfields, __le32 rss_hash)
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index b61b88cbc0c7..457444894d80 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1858,7 +1858,6 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev)
 		wmb();
 		writel_relaxed(qdev->small_buf_q_producer_index,
 			       &port_regs->CommonRegs.rxSmallQProducerIndex);
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 3e71b65a9546..ad7c5eb8a3b6 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -2181,7 +2181,6 @@ static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val)
 static inline void ql_write_db_reg(u32 val, void __iomem *addr)
 {
 	writel(val, addr);
-	mmiowb();
 }
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 07e1c623048e..6cae33072496 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2695,7 +2695,6 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 
 	ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
-	mmiowb();
 	netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
 		     "tx queued, slot %d, len %d\n",
 		     tx_ring->prod_idx, skb->len);