[PATCH v7 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs

[PATCH v7 1/7] i40e/i40evf: Eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel(). writel() already has a barrier
on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c   | 14 ++++++++++----
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c |  4 ++--
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c6972bd..d970350 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -186,7 +186,13 @@ static int i40e_program_fdir_filter(struct i40e_fdir_filter *fdir_data,
 	/* Mark the data descriptor to be watched */
 	first->next_to_watch = tx_desc;
 
-	writel(tx_ring->next_to_use, tx_ring->tail);
+	writel_relaxed(tx_ring->next_to_use, tx_ring->tail);
+
+	/* We need this if more than one processor can write to our tail
+	 * at a time, it synchronizes IO on IA64/Altix systems
+	 */
+	mmiowb();
+
 	return 0;
 
 dma_fail:
@@ -1529,7 +1535,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 	 * such as IA-64).
 	 */
 	wmb();
-	writel(val, rx_ring->tail);
+	writel_relaxed(val, rx_ring->tail);
 }
 
 /**
@@ -2412,7 +2418,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		 */
 		wmb();
 
-		writel(xdp_ring->next_to_use, xdp_ring->tail);
+		writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
 	}
 
 	rx_ring->skb = skb;
@@ -3437,7 +3443,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
-		writel(i, tx_ring->tail);
+		writel_relaxed(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
 		 * at a time, it synchronizes IO on IA64/Altix systems
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index 1ae112f..5db5c50c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -810,7 +810,7 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val)
 	 * such as IA-64).
 	 */
 	wmb();
-	writel(val, rx_ring->tail);
+	writel_relaxed(val, rx_ring->tail);
 }
 
 /**
@@ -2379,7 +2379,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
-		writel(i, tx_ring->tail);
+		writel_relaxed(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
 		 * at a time, it synchronizes IO on IA64/Altix systems
-- 
2.7.4

[PATCH v7 2/7] ixgbe: eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel() in multiple places. writel()
already has a barrier on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e3b32ea..fb80edb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1701,7 +1701,7 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 		 * such as IA-64).
 		 */
 		wmb();
-		writel(i, rx_ring->tail);
+		writel_relaxed(i, rx_ring->tail);
 	}
 }
 
@@ -2470,7 +2470,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 * know there are new descriptors to fetch.
 		 */
 		wmb();
-		writel(ring->next_to_use, ring->tail);
+		writel_relaxed(ring->next_to_use, ring->tail);
 
 		xdp_do_flush_map();
 	}
@@ -8101,7 +8101,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 	ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
-		writel(i, tx_ring->tail);
+		writel_relaxed(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
 		 * at a time, it synchronizes IO on IA64/Altix systems
@@ -10038,7 +10038,7 @@ static void ixgbe_xdp_flush(struct net_device *dev)
 	 * are new descriptors to fetch.
 	 */
 	wmb();
-	writel(ring->next_to_use, ring->tail);
+	writel_relaxed(ring->next_to_use, ring->tail);
 
 	return;
 }
-- 
2.7.4

[PATCH v7 3/7] igbvf: eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel(). writel() already has a barrier
on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/igbvf/netdev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index fa07876..df2283b 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -252,7 +252,7 @@ static void igbvf_alloc_rx_buffers(struct igbvf_ring *rx_ring,
 		 * such as IA-64).
 		*/
 		wmb();
-		writel(i, adapter->hw.hw_addr + rx_ring->tail);
+		writel_relaxed(i, adapter->hw.hw_addr + rx_ring->tail);
 	}
 }
 
@@ -2298,7 +2298,7 @@ static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter,
 
 	tx_ring->buffer_info[first].next_to_watch = tx_desc;
 	tx_ring->next_to_use = i;
-	writel(i, adapter->hw.hw_addr + tx_ring->tail);
+	writel_relaxed(i, adapter->hw.hw_addr + tx_ring->tail);
 	/* we need this if more than one processor can write to our tail
 	 * at a time, it synchronizes IO on IA64/Altix systems
 	 */
-- 
2.7.4

[PATCH v7 4/7] igb: eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel(). writel() already has a barrier
on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 3d4ff3c..c501378 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5674,7 +5674,7 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
-		writel(i, tx_ring->tail);
+		writel_relaxed(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
 		 * at a time, it synchronizes IO on IA64/Altix systems
@@ -8079,7 +8079,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		 * such as IA-64).
 		 */
 		wmb();
-		writel(i, rx_ring->tail);
+		writel_relaxed(i, rx_ring->tail);
 	}
 }
 
-- 
2.7.4

[PATCH v7 5/7] fm10k: Eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel(). writel() already has a
barrier on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing
the register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/fm10k/fm10k_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 409554d..bb94f04 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -180,7 +180,7 @@ void fm10k_alloc_rx_buffers(struct fm10k_ring *rx_ring, u16 cleaned_count)
 		wmb();
 
 		/* notify hardware of new descriptors */
-		writel(i, rx_ring->tail);
+		writel_relaxed(i, rx_ring->tail);
 	}
 }
 
@@ -1055,7 +1055,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
-		writel(i, tx_ring->tail);
+		writel_relaxed(i, tx_ring->tail);
 
 		/* we need this if more than one processor can write to our tail
 		 * at a time, it synchronizes IO on IA64/Altix systems
-- 
2.7.4

[PATCH v7 6/7] ixgbevf: keep writel() closer to wmb()

[Sinan Kaya]

Remove ixgbevf_write_tail() in favor of moving writel() close to
wmb().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf.h      | 5 -----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 6 +++---
 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
index f712646..f97091d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h
@@ -312,11 +312,6 @@ static inline u16 ixgbevf_desc_unused(struct ixgbevf_ring *ring)
 	return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1;
 }
 
-static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32 value)
-{
-	writel(value, ring->tail);
-}
-
 #define IXGBEVF_RX_DESC(R, i)	\
 	(&(((union ixgbe_adv_rx_desc *)((R)->desc))[i]))
 #define IXGBEVF_TX_DESC(R, i)	\
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 3d9033f..815cb1a 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -725,7 +725,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring,
 		 * such as IA-64).
 		 */
 		wmb();
-		ixgbevf_write_tail(rx_ring, i);
+		writel(i, rx_ring->tail);
 	}
 }
 
@@ -1232,7 +1232,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		 * know there are new descriptors to fetch.
 		 */
 		wmb();
-		ixgbevf_write_tail(xdp_ring, xdp_ring->next_to_use);
+		writel(xdp_ring->next_to_use, xdp_ring->tail);
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
@@ -4004,7 +4004,7 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
 	tx_ring->next_to_use = i;
 
 	/* notify HW of packet */
-	ixgbevf_write_tail(tx_ring, i);
+	writel(i, tx_ring->tail);
 
 	return;
 dma_error:
-- 
2.7.4

[PATCH v7 7/7] ixgbevf: eliminate duplicate barriers on weakly-ordered archs

[Sinan Kaya]

Code includes wmb() followed by writel() in multiple places. writel()
already has a barrier on some architectures like arm64.

This ends up CPU observing two barriers back to back before executing the
register write.

Since code already has an explicit barrier call, changing writel() to
writel_relaxed().

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
---
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 815cb1a..7277647 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -725,7 +725,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring,
 		 * such as IA-64).
 		 */
 		wmb();
-		writel(i, rx_ring->tail);
+		writel_relaxed(i, rx_ring->tail);
 	}
 }
 
@@ -1232,7 +1232,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector,
 		 * know there are new descriptors to fetch.
 		 */
 		wmb();
-		writel(xdp_ring->next_to_use, xdp_ring->tail);
+		writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail);
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
@@ -4004,7 +4004,12 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
 	tx_ring->next_to_use = i;
 
 	/* notify HW of packet */
-	writel(i, tx_ring->tail);
+	writel_relaxed(i, tx_ring->tail);
+
+	/* We need this if more than one processor can write to our tail
+	 * at a time, it synchronizes IO on IA64/Altix systems
+	 */
+	mmiowb();
 
 	return;
 dma_error:
-- 
2.7.4