Netdev List
 help / color / mirror / Atom feed
* [PATCH v2 net-next 12/12] net: stmmac: Remove if condition by taking advantage of hwif return code
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

We can remove the if condition and check if return code is different
than -EINVAL, meaning callback is present.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |   23 ++++++++++-----------
 1 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3ae715e..7af40e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3644,6 +3644,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	/* To handle GMAC own interrupts */
 	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
 		int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
+		int mtl_status;
 
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
@@ -3653,20 +3654,18 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 				priv->tx_path_in_lpi_mode = false;
 		}
 
-		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-			for (queue = 0; queue < queues_count; queue++) {
-				struct stmmac_rx_queue *rx_q =
-				&priv->rx_queue[queue];
+		for (queue = 0; queue < queues_count; queue++) {
+			struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 
-				status |= stmmac_host_mtl_irq_status(priv,
-						priv->hw, queue);
+			mtl_status = stmmac_host_mtl_irq_status(priv, priv->hw,
+								queue);
+			if (mtl_status != -EINVAL)
+				status |= mtl_status;
 
-				if (status & CORE_IRQ_MTL_RX_OVERFLOW)
-					stmmac_set_rx_tail_ptr(priv,
-							priv->ioaddr,
-							rx_q->rx_tail_addr,
-							queue);
-			}
+			if (status & CORE_IRQ_MTL_RX_OVERFLOW)
+				stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
+						       rx_q->rx_tail_addr,
+						       queue);
 		}
 
 		/* PCS link status */
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 11/12] net: stmmac: Let descriptor code get skbuff address
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Stop using if conditions depending on the GMAC version for getting the
descriptor skbuff address and use instead a helper implemented in the
descriptor files.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c |    6 ++++++
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     |    6 ++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    4 ++++
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    |    6 ++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |    6 +-----
 5 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 63f869c..20299f6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -424,6 +424,11 @@ static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
 	p->des3 = cpu_to_le32(TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV);
 }
 
+static void dwmac4_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+	*addr = le32_to_cpu(p->des0);
+}
+
 static void dwmac4_set_addr(struct dma_desc *p, dma_addr_t addr)
 {
 	p->des0 = cpu_to_le32(addr);
@@ -459,6 +464,7 @@ static void dwmac4_clear(struct dma_desc *p)
 	.init_tx_desc = dwmac4_rd_init_tx_desc,
 	.display_ring = dwmac4_display_ring,
 	.set_mss = dwmac4_set_mss_ctxt,
+	.get_addr = dwmac4_get_addr,
 	.set_addr = dwmac4_set_addr,
 	.clear = dwmac4_clear,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 743a60f..77914c8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -437,6 +437,11 @@ static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("\n");
 }
 
+static void enh_desc_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+	*addr = le32_to_cpu(p->des2);
+}
+
 static void enh_desc_set_addr(struct dma_desc *p, dma_addr_t addr)
 {
 	p->des2 = cpu_to_le32(addr);
@@ -467,6 +472,7 @@ static void enh_desc_clear(struct dma_desc *p)
 	.get_timestamp = enh_desc_get_timestamp,
 	.get_rx_timestamp_status = enh_desc_get_rx_timestamp_status,
 	.display_ring = enh_desc_display_ring,
+	.get_addr = enh_desc_get_addr,
 	.set_addr = enh_desc_set_addr,
 	.clear = enh_desc_clear,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 06b5e5b..f499a7f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -79,6 +79,8 @@ struct stmmac_desc_ops {
 	void (*display_ring)(void *head, unsigned int size, bool rx);
 	/* set MSS via context descriptor */
 	void (*set_mss)(struct dma_desc *p, unsigned int mss);
+	/* get descriptor skbuff address */
+	void (*get_addr)(struct dma_desc *p, unsigned int *addr);
 	/* set descriptor skbuff address */
 	void (*set_addr)(struct dma_desc *p, dma_addr_t addr);
 	/* clear descriptor */
@@ -127,6 +129,8 @@ struct stmmac_desc_ops {
 	stmmac_do_void_callback(__priv, desc, display_ring, __args)
 #define stmmac_set_mss(__priv, __args...) \
 	stmmac_do_void_callback(__priv, desc, set_mss, __args)
+#define stmmac_get_desc_addr(__priv, __args...) \
+	stmmac_do_void_callback(__priv, desc, get_addr, __args)
 #define stmmac_set_desc_addr(__priv, __args...) \
 	stmmac_do_void_callback(__priv, desc, set_addr, __args)
 #define stmmac_clear_desc(__priv, __args...) \
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 2facdb5..de65bb2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -297,6 +297,11 @@ static void ndesc_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("\n");
 }
 
+static void ndesc_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+	*addr = le32_to_cpu(p->des2);
+}
+
 static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
 {
 	p->des2 = cpu_to_le32(addr);
@@ -326,6 +331,7 @@ static void ndesc_clear(struct dma_desc *p)
 	.get_timestamp = ndesc_get_timestamp,
 	.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
 	.display_ring = ndesc_display_ring,
+	.get_addr = ndesc_get_addr,
 	.set_addr = ndesc_set_addr,
 	.clear = ndesc_clear,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cbd2638..3ae715e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3350,11 +3350,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			int frame_len;
 			unsigned int des;
 
-			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
-				des = le32_to_cpu(p->des0);
-			else
-				des = le32_to_cpu(p->des2);
-
+			stmmac_get_desc_addr(priv, p, &des);
 			frame_len = stmmac_get_rx_frame_len(priv, p, coe);
 
 			/*  If frame length is greater than skb buffer size
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 10/12] net: stmmac: Uniformize set_rx_owner()
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Currently an if condition is used to select the correct callback to set
rx_onwer in descriptor. Lets keep this simple and always use the same
callback.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c |   12 ++++++------
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     |    2 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    2 +-
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    |    2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |    5 +----
 5 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 119a2f9..63f869c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -189,9 +189,12 @@ static void dwmac4_set_tx_owner(struct dma_desc *p)
 	p->des3 |= cpu_to_le32(TDES3_OWN);
 }
 
-static void dwmac4_set_rx_owner(struct dma_desc *p)
+static void dwmac4_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
-	p->des3 |= cpu_to_le32(RDES3_OWN);
+	p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
+
+	if (!disable_rx_ic)
+		p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
 }
 
 static int dwmac4_get_tx_ls(struct dma_desc *p)
@@ -292,10 +295,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc,
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
 				   int mode, int end)
 {
-	p->des3 = cpu_to_le32(RDES3_OWN | RDES3_BUFFER1_VALID_ADDR);
-
-	if (!disable_rx_ic)
-		p->des3 |= cpu_to_le32(RDES3_INT_ON_COMPLETION_EN);
+	dwmac4_set_rx_owner(p, disable_rx_ic);
 }
 
 static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 17cd26f..743a60f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -292,7 +292,7 @@ static void enh_desc_set_tx_owner(struct dma_desc *p)
 	p->des0 |= cpu_to_le32(ETDES0_OWN);
 }
 
-static void enh_desc_set_rx_owner(struct dma_desc *p)
+static void enh_desc_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
 	p->des0 |= cpu_to_le32(RDES0_OWN);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 1c674d6..06b5e5b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -59,7 +59,7 @@ struct stmmac_desc_ops {
 	/* Get the buffer size from the descriptor */
 	int (*get_tx_len)(struct dma_desc *p);
 	/* Handle extra events on specific interrupts hw dependent */
-	void (*set_rx_owner)(struct dma_desc *p);
+	void (*set_rx_owner)(struct dma_desc *p, int disable_rx_ic);
 	/* Get the receive frame size */
 	int (*get_rx_frame_len)(struct dma_desc *p, int rx_coe_type);
 	/* Return the reception status looking at the RDES1 */
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index a7b221b..2facdb5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -168,7 +168,7 @@ static void ndesc_set_tx_owner(struct dma_desc *p)
 	p->des0 |= cpu_to_le32(TDES0_OWN);
 }
 
-static void ndesc_set_rx_owner(struct dma_desc *p)
+static void ndesc_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
 {
 	p->des0 |= cpu_to_le32(RDES0_OWN);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4d144e3..cbd2638 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3262,10 +3262,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 		}
 		dma_wmb();
 
-		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
-			stmmac_init_rx_desc(priv, p, priv->use_riwt, 0, 0);
-		else
-			stmmac_set_rx_owner(priv, p);
+		stmmac_set_rx_owner(priv, p, priv->use_riwt);
 
 		dma_wmb();
 
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 09/12] net: stmmac: Remove uneeded check for GMAC version in stmmac_xmit
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

We either have .enable_dma_transmission or .set_tx_tail_ptr in the HW
table callbacks, we can never have both so there is no need to check for
GMAC version.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h  |    1 -
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |    7 ++-----
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index 8474bf9..c63c1fe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -184,7 +184,6 @@
 #define DMA_CHAN0_DBG_STAT_RPS_SHIFT	8
 
 int dwmac4_dma_reset(void __iomem *ioaddr);
-void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
 void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
 void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
 void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0a5425c..4d144e3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3166,11 +3166,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
-	if (priv->synopsys_id < DWMAC_CORE_4_00)
-		stmmac_enable_dma_transmission(priv, priv->ioaddr);
-	else
-		stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr,
-				queue);
+	stmmac_enable_dma_transmission(priv, priv->ioaddr);
+	stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue);
 
 	return NETDEV_TX_OK;
 
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 08/12] net: stmmac: Uniformize the use of dma_init_* callbacks
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Instead of relying on the GMAC version for choosing if we need to use
dma_init or dma_init_{rx/tx}_chan callback, lets uniformize this and
always use the dma_init_{rx/tx}_chan callbacks.

While at it, fix the use of dma_init_chan callback, which shall be
called for as many channels as the max of rx/tx channels.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c    |   25 ++++++--
 drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c |   25 ++++++--
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c   |    3 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |   62 ++++++++-----------
 5 files changed, 64 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index d7447b0..aacc4aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -81,8 +81,7 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 }
 
 static void dwmac1000_dma_init(void __iomem *ioaddr,
-			       struct stmmac_dma_cfg *dma_cfg,
-			       u32 dma_tx, u32 dma_rx, int atds)
+			       struct stmmac_dma_cfg *dma_cfg, int atds)
 {
 	u32 value = readl(ioaddr + DMA_BUS_MODE);
 	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
@@ -119,12 +118,22 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
 
 	/* Mask interrupts by writing to CSR7 */
 	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
+}
 
-	/* RX/TX descriptor base address lists must be written into
-	 * DMA CSR3 and CSR4, respectively
-	 */
-	writel(dma_tx, ioaddr + DMA_TX_BASE_ADDR);
-	writel(dma_rx, ioaddr + DMA_RCV_BASE_ADDR);
+static void dwmac1000_dma_init_rx(void __iomem *ioaddr,
+				  struct stmmac_dma_cfg *dma_cfg,
+				  u32 dma_rx_phy, u32 chan)
+{
+	/* RX descriptor base address list must be written into DMA CSR3 */
+	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+}
+
+static void dwmac1000_dma_init_tx(void __iomem *ioaddr,
+				  struct stmmac_dma_cfg *dma_cfg,
+				  u32 dma_tx_phy, u32 chan)
+{
+	/* TX descriptor base address list must be written into DMA CSR4 */
+	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
 }
 
 static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
@@ -264,6 +273,8 @@ static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
 const struct stmmac_dma_ops dwmac1000_dma_ops = {
 	.reset = dwmac_dma_reset,
 	.init = dwmac1000_dma_init,
+	.init_rx_chan = dwmac1000_dma_init_rx,
+	.init_tx_chan = dwmac1000_dma_init_tx,
 	.axi = dwmac1000_dma_axi,
 	.dump_regs = dwmac1000_dump_dma_regs,
 	.dma_rx_mode = dwmac1000_dma_operation_mode_rx,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index 80339d3..21dee25 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -29,8 +29,7 @@
 #include "dwmac_dma.h"
 
 static void dwmac100_dma_init(void __iomem *ioaddr,
-			      struct stmmac_dma_cfg *dma_cfg,
-			      u32 dma_tx, u32 dma_rx, int atds)
+			      struct stmmac_dma_cfg *dma_cfg, int atds)
 {
 	/* Enable Application Access by writing to DMA CSR0 */
 	writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT),
@@ -38,12 +37,22 @@ static void dwmac100_dma_init(void __iomem *ioaddr,
 
 	/* Mask interrupts by writing to CSR7 */
 	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
+}
 
-	/* RX/TX descriptor base addr lists must be written into
-	 * DMA CSR3 and CSR4, respectively
-	 */
-	writel(dma_tx, ioaddr + DMA_TX_BASE_ADDR);
-	writel(dma_rx, ioaddr + DMA_RCV_BASE_ADDR);
+static void dwmac100_dma_init_rx(void __iomem *ioaddr,
+				 struct stmmac_dma_cfg *dma_cfg,
+				 u32 dma_rx_phy, u32 chan)
+{
+	/* RX descriptor base addr lists must be written into DMA CSR3 */
+	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+}
+
+static void dwmac100_dma_init_tx(void __iomem *ioaddr,
+				 struct stmmac_dma_cfg *dma_cfg,
+				 u32 dma_tx_phy, u32 chan)
+{
+	/* TX descriptor base addr lists must be written into DMA CSR4 */
+	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
 }
 
 /* Store and Forward capability is not used at all.
@@ -112,6 +121,8 @@ static void dwmac100_dma_diagnostic_fr(void *data, struct stmmac_extra_stats *x,
 const struct stmmac_dma_ops dwmac100_dma_ops = {
 	.reset = dwmac_dma_reset,
 	.init = dwmac100_dma_init,
+	.init_rx_chan = dwmac100_dma_init_rx,
+	.init_tx_chan = dwmac100_dma_init_tx,
 	.dump_regs = dwmac100_dump_dma_regs,
 	.dma_tx_mode = dwmac100_dma_operation_mode_tx,
 	.dma_diagnostic_fr = dwmac100_dma_diagnostic_fr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 9aab5b3..bf8e5a1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -120,8 +120,7 @@ static void dwmac4_dma_init_channel(void __iomem *ioaddr,
 }
 
 static void dwmac4_dma_init(void __iomem *ioaddr,
-			    struct stmmac_dma_cfg *dma_cfg,
-			    u32 dma_tx, u32 dma_rx, int atds)
+			    struct stmmac_dma_cfg *dma_cfg, int atds)
 {
 	u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 06fb20b..1c674d6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -140,7 +140,7 @@ struct stmmac_dma_ops {
 	/* DMA core initialization */
 	int (*reset)(void __iomem *ioaddr);
 	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
-		     u32 dma_tx, u32 dma_rx, int atds);
+		     int atds);
 	void (*init_chan)(void __iomem *ioaddr,
 			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
 	void (*init_rx_chan)(void __iomem *ioaddr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a4d6ea7..0a5425c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2138,10 +2138,9 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 {
 	u32 rx_channels_count = priv->plat->rx_queues_to_use;
 	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 dma_csr_ch = max(rx_channels_count, tx_channels_count);
 	struct stmmac_rx_queue *rx_q;
 	struct stmmac_tx_queue *tx_q;
-	u32 dummy_dma_rx_phy = 0;
-	u32 dummy_dma_tx_phy = 0;
 	u32 chan = 0;
 	int atds = 0;
 	int ret = 0;
@@ -2160,48 +2159,39 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		return ret;
 	}
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		/* DMA Configuration */
-		stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg,
-				dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
-
-		/* DMA RX Channel Configuration */
-		for (chan = 0; chan < rx_channels_count; chan++) {
-			rx_q = &priv->rx_queue[chan];
-
-			stmmac_init_rx_chan(priv, priv->ioaddr,
-					priv->plat->dma_cfg, rx_q->dma_rx_phy,
-					chan);
-
-			rx_q->rx_tail_addr = rx_q->dma_rx_phy +
-				    (DMA_RX_SIZE * sizeof(struct dma_desc));
-			stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
-					rx_q->rx_tail_addr, chan);
-		}
+	/* DMA Configuration */
+	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
 
-		/* DMA TX Channel Configuration */
-		for (chan = 0; chan < tx_channels_count; chan++) {
-			tx_q = &priv->tx_queue[chan];
+	/* DMA RX Channel Configuration */
+	for (chan = 0; chan < rx_channels_count; chan++) {
+		rx_q = &priv->rx_queue[chan];
 
-			stmmac_init_chan(priv, priv->ioaddr,
-					priv->plat->dma_cfg, chan);
+		stmmac_init_rx_chan(priv, priv->ioaddr, priv->plat->dma_cfg,
+				    rx_q->dma_rx_phy, chan);
 
-			stmmac_init_tx_chan(priv, priv->ioaddr,
-					priv->plat->dma_cfg, tx_q->dma_tx_phy,
-					chan);
+		rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+			    (DMA_RX_SIZE * sizeof(struct dma_desc));
+		stmmac_set_rx_tail_ptr(priv, priv->ioaddr,
+				       rx_q->rx_tail_addr, chan);
+	}
 
-			tx_q->tx_tail_addr = tx_q->dma_tx_phy +
-				    (DMA_TX_SIZE * sizeof(struct dma_desc));
-			stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
-					tx_q->tx_tail_addr, chan);
-		}
-	} else {
-		rx_q = &priv->rx_queue[chan];
+	/* DMA TX Channel Configuration */
+	for (chan = 0; chan < tx_channels_count; chan++) {
 		tx_q = &priv->tx_queue[chan];
-		stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg,
-				tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds);
+
+		stmmac_init_tx_chan(priv, priv->ioaddr, priv->plat->dma_cfg,
+				    tx_q->dma_tx_phy, chan);
+
+		tx_q->tx_tail_addr = tx_q->dma_tx_phy +
+			    (DMA_TX_SIZE * sizeof(struct dma_desc));
+		stmmac_set_tx_tail_ptr(priv, priv->ioaddr,
+				       tx_q->tx_tail_addr, chan);
 	}
 
+	/* DMA CSR Channel configuration */
+	for (chan = 0; chan < dma_csr_ch; chan++)
+		stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
+
 	if (priv->plat->axi)
 		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
 
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 07/12] net: stmmac: Move PTP and MMC base address calculation to hwif.c
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

PTP and MMC modules base address can depend on the GMAC version. As this
is HW specific lets move this base address calculation to hwif.c. Also,
add an entry in the HW table so that we can specify the module offset.
This can later be extended to more modules, if deemed necessary.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.c        |   34 +++++++++++++++++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h        |    5 +++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |    8 -----
 3 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 9acc8d2..23a1264 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -6,6 +6,7 @@
 
 #include "common.h"
 #include "stmmac.h"
+#include "stmmac_ptp.h"
 
 static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg)
 {
@@ -72,6 +73,7 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 	bool gmac;
 	bool gmac4;
 	u32 min_id;
+	const struct stmmac_regs_off regs;
 	const void *desc;
 	const void *dma;
 	const void *mac;
@@ -86,6 +88,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = false,
 		.gmac4 = false,
 		.min_id = 0,
+		.regs = {
+			.ptp_off = PTP_GMAC3_X_OFFSET,
+			.mmc_off = MMC_GMAC3_X_OFFSET,
+		},
 		.desc = NULL,
 		.dma = &dwmac100_dma_ops,
 		.mac = &dwmac100_ops,
@@ -98,6 +104,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = true,
 		.gmac4 = false,
 		.min_id = 0,
+		.regs = {
+			.ptp_off = PTP_GMAC3_X_OFFSET,
+			.mmc_off = MMC_GMAC3_X_OFFSET,
+		},
 		.desc = NULL,
 		.dma = &dwmac1000_dma_ops,
 		.mac = &dwmac1000_ops,
@@ -110,6 +120,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = false,
 		.gmac4 = true,
 		.min_id = 0,
+		.regs = {
+			.ptp_off = PTP_GMAC4_OFFSET,
+			.mmc_off = MMC_GMAC4_OFFSET,
+		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac4_ops,
@@ -122,6 +136,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = false,
 		.gmac4 = true,
 		.min_id = DWMAC_CORE_4_00,
+		.regs = {
+			.ptp_off = PTP_GMAC4_OFFSET,
+			.mmc_off = MMC_GMAC4_OFFSET,
+		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac4_dma_ops,
 		.mac = &dwmac410_ops,
@@ -134,6 +152,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = false,
 		.gmac4 = true,
 		.min_id = DWMAC_CORE_4_10,
+		.regs = {
+			.ptp_off = PTP_GMAC4_OFFSET,
+			.mmc_off = MMC_GMAC4_OFFSET,
+		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac410_ops,
@@ -146,6 +168,10 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 		.gmac = false,
 		.gmac4 = true,
 		.min_id = DWMAC_CORE_5_10,
+		.regs = {
+			.ptp_off = PTP_GMAC4_OFFSET,
+			.mmc_off = MMC_GMAC4_OFFSET,
+		},
 		.desc = &dwmac4_desc_ops,
 		.dma = &dwmac410_dma_ops,
 		.mac = &dwmac510_ops,
@@ -175,6 +201,12 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 	/* Save ID for later use */
 	priv->synopsys_id = id;
 
+	/* Lets assume some safe values first */
+	priv->ptpaddr = priv->ioaddr +
+		(needs_gmac4 ? PTP_GMAC4_OFFSET : PTP_GMAC3_X_OFFSET);
+	priv->mmcaddr = priv->ioaddr +
+		(needs_gmac4 ? MMC_GMAC4_OFFSET : MMC_GMAC3_X_OFFSET);
+
 	/* Check for HW specific setup first */
 	if (priv->plat->setup) {
 		priv->hw = priv->plat->setup(priv);
@@ -206,6 +238,8 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 		mac->tc = entry->tc;
 
 		priv->hw = mac;
+		priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off;
+		priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off;
 
 		/* Entry found */
 		ret = entry->setup(priv);
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 3ff4afe..06fb20b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -442,6 +442,11 @@ struct stmmac_tc_ops {
 #define stmmac_tc_setup_cls_u32(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, setup_cls_u32, __args)
 
+struct stmmac_regs_off {
+	u32 ptp_off;
+	u32 mmc_off;
+};
+
 extern const struct stmmac_ops dwmac100_ops;
 extern const struct stmmac_dma_ops dwmac100_dma_ops;
 extern const struct stmmac_ops dwmac1000_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ce6f839..a4d6ea7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2085,14 +2085,6 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
 	unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
 			    MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET;
-		priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET;
-	} else {
-		priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET;
-		priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET;
-	}
-
 	dwmac_mmc_intr_all_mask(priv->mmcaddr);
 
 	if (priv->dma_cap.rmon) {
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 06/12] net: stmmac: Remove uneeded checks for GMAC version
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

With the introducion of callbacks check in hwif.h we only call the
callback if HW supports it so there is no longer need to check for GMAC
version.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |   16 +++++-----------
 1 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index beb7ec1..ce6f839 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1973,11 +1973,8 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 
 static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv)
 {
-	int ret = false;
+	int ret;
 
-	/* Safety features are only available in cores >= 5.10 */
-	if (priv->synopsys_id < DWMAC_CORE_5_10)
-		return ret;
 	ret = stmmac_safety_feat_irq_status(priv, priv->dev,
 			priv->ioaddr, priv->dma_cap.asp, &priv->sstats);
 	if (ret && (ret != -EINVAL)) {
@@ -2495,12 +2492,10 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	stmmac_core_init(priv, priv->hw, dev);
 
 	/* Initialize MTL*/
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		stmmac_mtl_configuration(priv);
+	stmmac_mtl_configuration(priv);
 
 	/* Initialize Safety Features */
-	if (priv->synopsys_id >= DWMAC_CORE_5_10)
-		stmmac_safety_feat_configuration(priv);
+	stmmac_safety_feat_configuration(priv);
 
 	ret = stmmac_rx_ipc(priv, priv->hw);
 	if (!ret) {
@@ -3054,10 +3049,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (enh_desc)
 		is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc);
 
-	if (unlikely(is_jumbo) && likely(priv->synopsys_id <
-					 DWMAC_CORE_4_00)) {
+	if (unlikely(is_jumbo)) {
 		entry = stmmac_jumbo_frm(priv, tx_q, skb, csum_insertion);
-		if (unlikely(entry < 0))
+		if (unlikely(entry < 0) && (entry != -EINVAL))
 			goto dma_map_err;
 	}
 
-- 
1.7.1

^ permalink raw reply related

* Re: [RFC v4 3/5] virtio_ring: add packed ring support
From: Jason Wang @ 2018-05-16 12:51 UTC (permalink / raw)
  To: Tiwei Bie; +Cc: mst, virtualization, linux-kernel, netdev, wexu, jfreimann
In-Reply-To: <20180516123909.GB986@debian>



On 2018年05月16日 20:39, Tiwei Bie wrote:
> On Wed, May 16, 2018 at 07:50:16PM +0800, Jason Wang wrote:
>> On 2018年05月16日 16:37, Tiwei Bie wrote:
> [...]
>>>    struct vring_virtqueue {
>>> @@ -116,6 +117,9 @@ struct vring_virtqueue {
>>>    			/* Last written value to driver->flags in
>>>    			 * guest byte order. */
>>>    			u16 event_flags_shadow;
>>> +
>>> +			/* ID allocation. */
>>> +			struct idr buffer_id;
>> I'm not sure idr is fit for the performance critical case here. Need to
>> measure its performance impact, especially if we have few unused slots.
> I'm also not sure.. But fortunately, it should be quite easy
> to replace it with something else without changing other code.
> If it will really hurt the performance, I'll change it.

We may want to do some benchmarking/profiling to see.

>
>>>    		};
>>>    	};
> [...]
>>> +static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int head,
>>> +			      unsigned int id, void **ctx)
>>> +{
>>> +	struct vring_packed_desc *desc;
>>> +	unsigned int i, j;
>>> +
>>> +	/* Clear data ptr. */
>>> +	vq->desc_state[id].data = NULL;
>>> +
>>> +	i = head;
>>> +
>>> +	for (j = 0; j < vq->desc_state[id].num; j++) {
>>> +		desc = &vq->vring_packed.desc[i];
>>> +		vring_unmap_one_packed(vq, desc);
>> As mentioned in previous discussion, this probably won't work for the case
>> of out of order completion since it depends on the information in the
>> descriptor ring. We probably need to extend ctx to record such information.
> Above code doesn't depend on the information in the descriptor
> ring. The vq->desc_state[] is the extended ctx.
>
> Best regards,
> Tiwei Bie

Yes, but desc is a pointer to descriptor ring I think so 
vring_unmap_one_packed() still depends on the content of descriptor ring?

Thanks

^ permalink raw reply

* [PATCH v2 net-next 05/12] net: stmmac: Uniformize the use of dma_{rx/tx}_mode callbacks
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Instead of relying on the GMAC version for choosing if we need to use
dma_{rx/tx}_mode or just dma_mode callback lets uniformize this and
always use the dma_{rx/tx}_mode callbacks.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c  |   57 +++++++++-------
 .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c    |   67 +++++++++++---------
 drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c |   10 ++--
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    6 --
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |   32 +++------
 5 files changed, 86 insertions(+), 86 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index a3fa65b..4dafc6b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -398,13 +398,36 @@ static int sun8i_dwmac_dma_interrupt(void __iomem *ioaddr,
 	return ret;
 }
 
-static void sun8i_dwmac_dma_operation_mode(void __iomem *ioaddr, int txmode,
-					   int rxmode, int rxfifosz)
+static void sun8i_dwmac_dma_operation_mode_rx(void __iomem *ioaddr, int mode,
+					      u32 channel, int fifosz, u8 qmode)
+{
+	u32 v;
+
+	v = readl(ioaddr + EMAC_RX_CTL1);
+	if (mode == SF_DMA_MODE) {
+		v |= EMAC_RX_MD;
+	} else {
+		v &= ~EMAC_RX_MD;
+		v &= ~EMAC_RX_TH_MASK;
+		if (mode < 32)
+			v |= EMAC_RX_TH_32;
+		else if (mode < 64)
+			v |= EMAC_RX_TH_64;
+		else if (mode < 96)
+			v |= EMAC_RX_TH_96;
+		else if (mode < 128)
+			v |= EMAC_RX_TH_128;
+	}
+	writel(v, ioaddr + EMAC_RX_CTL1);
+}
+
+static void sun8i_dwmac_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+					      u32 channel, int fifosz, u8 qmode)
 {
 	u32 v;
 
 	v = readl(ioaddr + EMAC_TX_CTL1);
-	if (txmode == SF_DMA_MODE) {
+	if (mode == SF_DMA_MODE) {
 		v |= EMAC_TX_MD;
 		/* Undocumented bit (called TX_NEXT_FRM in BSP), the original
 		 * comment is
@@ -415,40 +438,24 @@ static void sun8i_dwmac_dma_operation_mode(void __iomem *ioaddr, int txmode,
 	} else {
 		v &= ~EMAC_TX_MD;
 		v &= ~EMAC_TX_TH_MASK;
-		if (txmode < 64)
+		if (mode < 64)
 			v |= EMAC_TX_TH_64;
-		else if (txmode < 128)
+		else if (mode < 128)
 			v |= EMAC_TX_TH_128;
-		else if (txmode < 192)
+		else if (mode < 192)
 			v |= EMAC_TX_TH_192;
-		else if (txmode < 256)
+		else if (mode < 256)
 			v |= EMAC_TX_TH_256;
 	}
 	writel(v, ioaddr + EMAC_TX_CTL1);
-
-	v = readl(ioaddr + EMAC_RX_CTL1);
-	if (rxmode == SF_DMA_MODE) {
-		v |= EMAC_RX_MD;
-	} else {
-		v &= ~EMAC_RX_MD;
-		v &= ~EMAC_RX_TH_MASK;
-		if (rxmode < 32)
-			v |= EMAC_RX_TH_32;
-		else if (rxmode < 64)
-			v |= EMAC_RX_TH_64;
-		else if (rxmode < 96)
-			v |= EMAC_RX_TH_96;
-		else if (rxmode < 128)
-			v |= EMAC_RX_TH_128;
-	}
-	writel(v, ioaddr + EMAC_RX_CTL1);
 }
 
 static const struct stmmac_dma_ops sun8i_dwmac_dma_ops = {
 	.reset = sun8i_dwmac_dma_reset,
 	.init = sun8i_dwmac_dma_init,
 	.dump_regs = sun8i_dwmac_dump_regs,
-	.dma_mode = sun8i_dwmac_dma_operation_mode,
+	.dma_rx_mode = sun8i_dwmac_dma_operation_mode_rx,
+	.dma_tx_mode = sun8i_dwmac_dma_operation_mode_tx,
 	.enable_dma_transmission = sun8i_dwmac_enable_dma_transmission,
 	.enable_dma_irq = sun8i_dwmac_enable_dma_irq,
 	.disable_dma_irq = sun8i_dwmac_disable_dma_irq,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index 7ecf549..d7447b0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -148,12 +148,40 @@ static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)
 	return csr6;
 }
 
-static void dwmac1000_dma_operation_mode(void __iomem *ioaddr, int txmode,
-					 int rxmode, int rxfifosz)
+static void dwmac1000_dma_operation_mode_rx(void __iomem *ioaddr, int mode,
+					    u32 channel, int fifosz, u8 qmode)
 {
 	u32 csr6 = readl(ioaddr + DMA_CONTROL);
 
-	if (txmode == SF_DMA_MODE) {
+	if (mode == SF_DMA_MODE) {
+		pr_debug("GMAC: enable RX store and forward mode\n");
+		csr6 |= DMA_CONTROL_RSF;
+	} else {
+		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+		csr6 &= ~DMA_CONTROL_RSF;
+		csr6 &= DMA_CONTROL_TC_RX_MASK;
+		if (mode <= 32)
+			csr6 |= DMA_CONTROL_RTC_32;
+		else if (mode <= 64)
+			csr6 |= DMA_CONTROL_RTC_64;
+		else if (mode <= 96)
+			csr6 |= DMA_CONTROL_RTC_96;
+		else
+			csr6 |= DMA_CONTROL_RTC_128;
+	}
+
+	/* Configure flow control based on rx fifo size */
+	csr6 = dwmac1000_configure_fc(csr6, fifosz);
+
+	writel(csr6, ioaddr + DMA_CONTROL);
+}
+
+static void dwmac1000_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+					    u32 channel, int fifosz, u8 qmode)
+{
+	u32 csr6 = readl(ioaddr + DMA_CONTROL);
+
+	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
 		/* Transmit COE type 2 cannot be done in cut-through mode. */
 		csr6 |= DMA_CONTROL_TSF;
@@ -162,42 +190,22 @@ static void dwmac1000_dma_operation_mode(void __iomem *ioaddr, int txmode,
 		 */
 		csr6 |= DMA_CONTROL_OSF;
 	} else {
-		pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+		pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
 		csr6 &= ~DMA_CONTROL_TSF;
 		csr6 &= DMA_CONTROL_TC_TX_MASK;
 		/* Set the transmit threshold */
-		if (txmode <= 32)
+		if (mode <= 32)
 			csr6 |= DMA_CONTROL_TTC_32;
-		else if (txmode <= 64)
+		else if (mode <= 64)
 			csr6 |= DMA_CONTROL_TTC_64;
-		else if (txmode <= 128)
+		else if (mode <= 128)
 			csr6 |= DMA_CONTROL_TTC_128;
-		else if (txmode <= 192)
+		else if (mode <= 192)
 			csr6 |= DMA_CONTROL_TTC_192;
 		else
 			csr6 |= DMA_CONTROL_TTC_256;
 	}
 
-	if (rxmode == SF_DMA_MODE) {
-		pr_debug("GMAC: enable RX store and forward mode\n");
-		csr6 |= DMA_CONTROL_RSF;
-	} else {
-		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
-		csr6 &= ~DMA_CONTROL_RSF;
-		csr6 &= DMA_CONTROL_TC_RX_MASK;
-		if (rxmode <= 32)
-			csr6 |= DMA_CONTROL_RTC_32;
-		else if (rxmode <= 64)
-			csr6 |= DMA_CONTROL_RTC_64;
-		else if (rxmode <= 96)
-			csr6 |= DMA_CONTROL_RTC_96;
-		else
-			csr6 |= DMA_CONTROL_RTC_128;
-	}
-
-	/* Configure flow control based on rx fifo size */
-	csr6 = dwmac1000_configure_fc(csr6, rxfifosz);
-
 	writel(csr6, ioaddr + DMA_CONTROL);
 }
 
@@ -258,7 +266,8 @@ static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
 	.init = dwmac1000_dma_init,
 	.axi = dwmac1000_dma_axi,
 	.dump_regs = dwmac1000_dump_dma_regs,
-	.dma_mode = dwmac1000_dma_operation_mode,
+	.dma_rx_mode = dwmac1000_dma_operation_mode_rx,
+	.dma_tx_mode = dwmac1000_dma_operation_mode_tx,
 	.enable_dma_transmission = dwmac_enable_dma_transmission,
 	.enable_dma_irq = dwmac_enable_dma_irq,
 	.disable_dma_irq = dwmac_disable_dma_irq,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index 6502b9a..80339d3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -51,14 +51,14 @@ static void dwmac100_dma_init(void __iomem *ioaddr,
  * The transmit threshold can be programmed by setting the TTC bits in the DMA
  * control register.
  */
-static void dwmac100_dma_operation_mode(void __iomem *ioaddr, int txmode,
-					int rxmode, int rxfifosz)
+static void dwmac100_dma_operation_mode_tx(void __iomem *ioaddr, int mode,
+					   u32 channel, int fifosz, u8 qmode)
 {
 	u32 csr6 = readl(ioaddr + DMA_CONTROL);
 
-	if (txmode <= 32)
+	if (mode <= 32)
 		csr6 |= DMA_CONTROL_TTC_32;
-	else if (txmode <= 64)
+	else if (mode <= 64)
 		csr6 |= DMA_CONTROL_TTC_64;
 	else
 		csr6 |= DMA_CONTROL_TTC_128;
@@ -113,7 +113,7 @@ static void dwmac100_dma_diagnostic_fr(void *data, struct stmmac_extra_stats *x,
 	.reset = dwmac_dma_reset,
 	.init = dwmac100_dma_init,
 	.dump_regs = dwmac100_dump_dma_regs,
-	.dma_mode = dwmac100_dma_operation_mode,
+	.dma_tx_mode = dwmac100_dma_operation_mode_tx,
 	.dma_diagnostic_fr = dwmac100_dma_diagnostic_fr,
 	.enable_dma_transmission = dwmac_enable_dma_transmission,
 	.enable_dma_irq = dwmac_enable_dma_irq,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index a6b9c97..3ff4afe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -153,10 +153,6 @@ struct stmmac_dma_ops {
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */
 	void (*dump_regs)(void __iomem *ioaddr, u32 *reg_space);
-	/* Set tx/rx threshold in the csr6 register
-	 * An invalid value enables the store-and-forward mode */
-	void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
-			 int rxfifosz);
 	void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
 			    int fifosz, u8 qmode);
 	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel,
@@ -199,8 +195,6 @@ struct stmmac_dma_ops {
 	stmmac_do_void_callback(__priv, dma, axi, __args)
 #define stmmac_dump_dma_regs(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, dump_regs, __args)
-#define stmmac_dma_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, dma, dma_mode, __args)
 #define stmmac_dma_rx_mode(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, dma_rx_mode, __args)
 #define stmmac_dma_tx_mode(__priv, __args...) \
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 0ccee6a..beb7ec1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1787,22 +1787,18 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 	}
 
 	/* configure all channels */
-	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		for (chan = 0; chan < rx_channels_count; chan++) {
-			qmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
+	for (chan = 0; chan < rx_channels_count; chan++) {
+		qmode = priv->plat->rx_queues_cfg[chan].mode_to_use;
 
-			stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
-					rxfifosz, qmode);
-		}
+		stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
+				rxfifosz, qmode);
+	}
 
-		for (chan = 0; chan < tx_channels_count; chan++) {
-			qmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
+	for (chan = 0; chan < tx_channels_count; chan++) {
+		qmode = priv->plat->tx_queues_cfg[chan].mode_to_use;
 
-			stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan,
-					txfifosz, qmode);
-		}
-	} else {
-		stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz);
+		stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan,
+				txfifosz, qmode);
 	}
 }
 
@@ -1971,14 +1967,8 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
 	rxfifosz /= rx_channels_count;
 	txfifosz /= tx_channels_count;
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz,
-				rxqmode);
-		stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, txfifosz,
-				txqmode);
-	} else {
-		stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz);
-	}
+	stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz, rxqmode);
+	stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, txfifosz, txqmode);
 }
 
 static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv)
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 04/12] net: stmmac: Let descriptor code clear the descriptor
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Stop using if conditions depending on the GMAC version for clearing the
descriptor and use instead a helper implemented in the descriptor files.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c |    9 +++++++++
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     |    6 ++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    4 ++++
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    |    6 ++++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |    9 +--------
 5 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index f67caa1..119a2f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -430,6 +430,14 @@ static void dwmac4_set_addr(struct dma_desc *p, dma_addr_t addr)
 	p->des1 = 0;
 }
 
+static void dwmac4_clear(struct dma_desc *p)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
 const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.tx_status = dwmac4_wrback_get_tx_status,
 	.rx_status = dwmac4_wrback_get_rx_status,
@@ -452,6 +460,7 @@ static void dwmac4_set_addr(struct dma_desc *p, dma_addr_t addr)
 	.display_ring = dwmac4_display_ring,
 	.set_mss = dwmac4_set_mss_ctxt,
 	.set_addr = dwmac4_set_addr,
+	.clear = dwmac4_clear,
 };
 
 const struct stmmac_mode_ops dwmac4_ring_mode_ops = { };
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 02749e4..17cd26f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -442,6 +442,11 @@ static void enh_desc_set_addr(struct dma_desc *p, dma_addr_t addr)
 	p->des2 = cpu_to_le32(addr);
 }
 
+static void enh_desc_clear(struct dma_desc *p)
+{
+	p->des2 = 0;
+}
+
 const struct stmmac_desc_ops enh_desc_ops = {
 	.tx_status = enh_desc_get_tx_status,
 	.rx_status = enh_desc_get_rx_status,
@@ -463,4 +468,5 @@ static void enh_desc_set_addr(struct dma_desc *p, dma_addr_t addr)
 	.get_rx_timestamp_status = enh_desc_get_rx_timestamp_status,
 	.display_ring = enh_desc_display_ring,
 	.set_addr = enh_desc_set_addr,
+	.clear = enh_desc_clear,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index d66d194..a6b9c97 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -81,6 +81,8 @@ struct stmmac_desc_ops {
 	void (*set_mss)(struct dma_desc *p, unsigned int mss);
 	/* set descriptor skbuff address */
 	void (*set_addr)(struct dma_desc *p, dma_addr_t addr);
+	/* clear descriptor */
+	void (*clear)(struct dma_desc *p);
 };
 
 #define stmmac_init_rx_desc(__priv, __args...) \
@@ -127,6 +129,8 @@ struct stmmac_desc_ops {
 	stmmac_do_void_callback(__priv, desc, set_mss, __args)
 #define stmmac_set_desc_addr(__priv, __args...) \
 	stmmac_do_void_callback(__priv, desc, set_addr, __args)
+#define stmmac_clear_desc(__priv, __args...) \
+	stmmac_do_void_callback(__priv, desc, clear, __args)
 
 struct stmmac_dma_cfg;
 struct dma_features;
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 6cf2c7c..a7b221b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -302,6 +302,11 @@ static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
 	p->des2 = cpu_to_le32(addr);
 }
 
+static void ndesc_clear(struct dma_desc *p)
+{
+	p->des2 = 0;
+}
+
 const struct stmmac_desc_ops ndesc_ops = {
 	.tx_status = ndesc_get_tx_status,
 	.rx_status = ndesc_get_rx_status,
@@ -322,4 +327,5 @@ static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
 	.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
 	.display_ring = ndesc_display_ring,
 	.set_addr = ndesc_set_addr,
+	.clear = ndesc_clear,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3f559d7..0ccee6a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1341,14 +1341,7 @@ static int init_dma_tx_desc_rings(struct net_device *dev)
 			else
 				p = tx_q->dma_tx + i;
 
-			if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-				p->des0 = 0;
-				p->des1 = 0;
-				p->des2 = 0;
-				p->des3 = 0;
-			} else {
-				p->des2 = 0;
-			}
+			stmmac_clear_desc(priv, p);
 
 			tx_q->tx_skbuff_dma[i].buf = 0;
 			tx_q->tx_skbuff_dma[i].map_as_page = false;
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 03/12] net: stmmac: Let descriptor code set skbuff address
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

Stop using if conditions depending on the GMAC version for setting the
the descriptor skbuff address and use instead a helper implemented in
the descriptor files.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c |    7 +++++
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     |    6 ++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |    4 +++
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    |    6 ++++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |   25 ++++---------------
 5 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 65ed896..f67caa1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -424,6 +424,12 @@ static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
 	p->des3 = cpu_to_le32(TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV);
 }
 
+static void dwmac4_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des0 = cpu_to_le32(addr);
+	p->des1 = 0;
+}
+
 const struct stmmac_desc_ops dwmac4_desc_ops = {
 	.tx_status = dwmac4_wrback_get_tx_status,
 	.rx_status = dwmac4_wrback_get_rx_status,
@@ -445,6 +451,7 @@ static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
 	.init_tx_desc = dwmac4_rd_init_tx_desc,
 	.display_ring = dwmac4_display_ring,
 	.set_mss = dwmac4_set_mss_ctxt,
+	.set_addr = dwmac4_set_addr,
 };
 
 const struct stmmac_mode_ops dwmac4_ring_mode_ops = { };
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 3bfb3f5..02749e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -437,6 +437,11 @@ static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("\n");
 }
 
+static void enh_desc_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des2 = cpu_to_le32(addr);
+}
+
 const struct stmmac_desc_ops enh_desc_ops = {
 	.tx_status = enh_desc_get_tx_status,
 	.rx_status = enh_desc_get_rx_status,
@@ -457,4 +462,5 @@ static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
 	.get_timestamp = enh_desc_get_timestamp,
 	.get_rx_timestamp_status = enh_desc_get_rx_timestamp_status,
 	.display_ring = enh_desc_display_ring,
+	.set_addr = enh_desc_set_addr,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index b7539a1..d66d194 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -79,6 +79,8 @@ struct stmmac_desc_ops {
 	void (*display_ring)(void *head, unsigned int size, bool rx);
 	/* set MSS via context descriptor */
 	void (*set_mss)(struct dma_desc *p, unsigned int mss);
+	/* set descriptor skbuff address */
+	void (*set_addr)(struct dma_desc *p, dma_addr_t addr);
 };
 
 #define stmmac_init_rx_desc(__priv, __args...) \
@@ -123,6 +125,8 @@ struct stmmac_desc_ops {
 	stmmac_do_void_callback(__priv, desc, display_ring, __args)
 #define stmmac_set_mss(__priv, __args...) \
 	stmmac_do_void_callback(__priv, desc, set_mss, __args)
+#define stmmac_set_desc_addr(__priv, __args...) \
+	stmmac_do_void_callback(__priv, desc, set_addr, __args)
 
 struct stmmac_dma_cfg;
 struct dma_features;
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index 7b1d901..6cf2c7c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -297,6 +297,11 @@ static void ndesc_display_ring(void *head, unsigned int size, bool rx)
 	pr_info("\n");
 }
 
+static void ndesc_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des2 = cpu_to_le32(addr);
+}
+
 const struct stmmac_desc_ops ndesc_ops = {
 	.tx_status = ndesc_get_tx_status,
 	.rx_status = ndesc_get_rx_status,
@@ -316,4 +321,5 @@ static void ndesc_display_ring(void *head, unsigned int size, bool rx)
 	.get_timestamp = ndesc_get_timestamp,
 	.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
 	.display_ring = ndesc_display_ring,
+	.set_addr = ndesc_set_addr,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 789bc22..3f559d7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1156,10 +1156,7 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 		return -EINVAL;
 	}
 
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
-	else
-		p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
+	stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[i]);
 
 	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		stmmac_init_desc3(priv, p);
@@ -3100,10 +3097,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto dma_map_err; /* should reuse desc w/o issues */
 
 		tx_q->tx_skbuff_dma[entry].buf = des;
-		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
-			desc->des0 = cpu_to_le32(des);
-		else
-			desc->des2 = cpu_to_le32(des);
+
+		stmmac_set_desc_addr(priv, desc, des);
 
 		tx_q->tx_skbuff_dma[entry].map_as_page = true;
 		tx_q->tx_skbuff_dma[entry].len = len;
@@ -3185,10 +3180,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 			goto dma_map_err;
 
 		tx_q->tx_skbuff_dma[first_entry].buf = des;
-		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
-			first->des0 = cpu_to_le32(des);
-		else
-			first->des2 = cpu_to_le32(des);
+
+		stmmac_set_desc_addr(priv, first, des);
 
 		tx_q->tx_skbuff_dma[first_entry].len = nopaged_len;
 		tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment;
@@ -3302,13 +3295,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 				break;
 			}
 
-			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-				p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
-				p->des1 = 0;
-			} else {
-				p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
-			}
-
+			stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[entry]);
 			stmmac_refill_desc3(priv, rx_q, p);
 
 			if (rx_q->rx_zeroc_thresh > 0)
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 02/12] net: stmmac: Do not keep rearming the coalesce timer in stmmac_xmit
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

This is cutting down performance. Once the timer is armed it should run
after the time expires for the first packet sent and not the last one.

After this change, running iperf, the performance gain is +/- 24%.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      |    1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |    5 ++++-
 2 files changed, 5 insertions(+), 1 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 42fc76e..4d425b1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -105,6 +105,7 @@ struct stmmac_priv {
 	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
+	bool tx_timer_armed;
 
 	int tx_coalesce;
 	int hwts_tx_en;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d9dbe13..789bc22 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3158,13 +3158,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * element in case of no SG.
 	 */
 	priv->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > priv->tx_count_frames)) {
+	if (likely(priv->tx_coal_frames > priv->tx_count_frames) &&
+	    !priv->tx_timer_armed) {
 		mod_timer(&priv->txtimer,
 			  STMMAC_COAL_TIMER(priv->tx_coal_timer));
+		priv->tx_timer_armed = true;
 	} else {
 		priv->tx_count_frames = 0;
 		stmmac_set_tx_ic(priv, desc);
 		priv->xstats.tx_set_ic_bit++;
+		priv->tx_timer_armed = false;
 	}
 
 	skb_tx_timestamp(skb);
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 01/12] net: stmmac: Enable OSP for GMAC4
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue
In-Reply-To: <cover.1526474646.git.joabreu@synopsys.com>

This enables OSP (Operate on Second Packet) for GMAC4. The feature
allows DMA to fetch second descriptor while its still processing the
first one.

Running iperf, the performance gain is +/- 38%.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index 117c3a5..9aab5b3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -94,6 +94,10 @@ static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
 
 	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 	value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
+
+	/* Enable OSP to get best performance */
+	value |= DMA_CONTROL_OSP;
+
 	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
-- 
1.7.1

^ permalink raw reply related

* [PATCH v2 net-next 00/12] net: stmmac: Clean-up and tune-up
From: Jose Abreu @ 2018-05-16 12:50 UTC (permalink / raw)
  To: netdev
  Cc: Jose Abreu, David S. Miller, Joao Pinto, Vitor Soares,
	Giuseppe Cavallaro, Alexandre Torgue

This targets to uniformize the handling of the different GMAC versions in
stmmac_main.c file and also tune-up the HW.

Currently there are some if/else conditions in the main source file which
calls different callbacks depending on the ID of GMAC.

With the introducion of a generic HW interface handling which automatically
selects the GMAC callbacks to be used, it is now unpleasant to see if
conditions in the main code because this should be completely agnostic of the
GMAC version.

This series removes most of these conditions. There are some if conditions
that remain untouched but the callbacks handling are now uniformized.

Tested in GMAC5, hope I didn't break any previous versions.

David raised some rightfull constrains about the use of indirect callbacks in
the code. I did iperf tests with and without patches 3-12 and the performance
remained equal. I guess for 1Gb/s and because my setup has a powerfull
processor these patches don't affect the performance.

Perhaps someone using a SoC with a slow CPU could test this?

Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>

Jose Abreu (12):
  net: stmmac: Enable OSP for GMAC4
  net: stmmac: Do not keep rearming the coalesce timer in stmmac_xmit
  net: stmmac: Let descriptor code set skbuff address
  net: stmmac: Let descriptor code clear the descriptor
  net: stmmac: Uniformize the use of dma_{rx/tx}_mode callbacks
  net: stmmac: Remove uneeded checks for GMAC version
  net: stmmac: Move PTP and MMC base address calculation to hwif.c
  net: stmmac: Uniformize the use of dma_init_* callbacks
  net: stmmac: Remove uneeded check for GMAC version in stmmac_xmit
  net: stmmac: Uniformize set_rx_owner()
  net: stmmac: Let descriptor code get skbuff address
  net: stmmac: Remove if condition by taking advantage of hwif return
    code

 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c  |   57 +++---
 .../net/ethernet/stmicro/stmmac/dwmac1000_dma.c    |   92 ++++++----
 drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c |   35 +++--
 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c |   34 +++-
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c   |    7 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h   |    1 -
 drivers/net/ethernet/stmicro/stmmac/enh_desc.c     |   20 ++-
 drivers/net/ethernet/stmicro/stmmac/hwif.c         |   34 ++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |   27 ++-
 drivers/net/ethernet/stmicro/stmmac/norm_desc.c    |   20 ++-
 drivers/net/ethernet/stmicro/stmmac/stmmac.h       |    1 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |  198 +++++++-------------
 12 files changed, 304 insertions(+), 222 deletions(-)

^ permalink raw reply

* Re: i.MX6S/DL and QCA8334 switch using DSA driver - CPU port not working
From: Michal Vokáč @ 2018-05-16 12:50 UTC (permalink / raw)
  To: Florian Fainelli, Andrew Lunn; +Cc: netdev, Vivien Didelot
In-Reply-To: <21fc20c7-77d2-cba0-8f58-6bacb41f0970@gmail.com>

On 15.5.2018 18:17, Florian Fainelli wrote:
>>> I would like to have confirmed that I understand it correctly and that
>>> the problem is really in the driver not handling fixed-link.
>>
>> I would actually skip fixed-link, if you don't need it. Just hardwire
>> the CPU port, like the Marvell driver does:
>>
>> https://elixir.bootlin.com/linux/latest/source/drivers/net/dsa/mv88e6xxx/chip.c#L1780
>>
>> I would do it here:
>>
>> https://elixir.bootlin.com/linux/latest/source/drivers/net/dsa/qca8k.c#L518

Thanks for the references, I will look there.
> 
> Agreed with Andrew here, though if you can implement fixed-link, this
> should be more future proof.

I do not actually need fixed-link but I agree with Florian that it is much
better to have that option. I see it a as way to override defaults that
do not work for the user. That is what I was hoping for but it did not work.

So as the fixed-link subnode is optional we still should force some sensible
defaults if it is not used. Same as Marvell drives does. Can I say that we
agreed that the current CPU port setting is not correct and the fastest link
speed and duplex supported by the chip should be set as a default?

> As far as people using this driver, John submitted it, but we have not
> see many fixes/enhancements, so I am not clear who is actually using it
> these days... glad you are though!

Thanks.

To the compatibility of the driver with the QCA8334 that I use. I am not sure
what should be the correct way to deal with that. For example Marvell binding
uses only two compatible strings for a large range of chips in one family.
While Broadcom has one compatible string for each chip. As I mentioned earlier
in this thread the QCA8334 switch has four ports while the already supported
QCA8337 has seven ports. That is the only difference. Register address space
is the same.

Should I:
  - add a new compatible string "qualcomm,qca8334" and update the docs,
  - or just update the documentation and describe the compatibility?

As I need to update the docs I understand it should go as a separate patch.
Is it enough to CC devicetree list with the whole series? Any other
list/maintainer?

Thank you for your time,
Michal

^ permalink raw reply

* [RFC PATCH] iscsit_wait_for_tag() can be static
From: kbuild test robot @ 2018-05-16 12:47 UTC (permalink / raw)
  To: Matthew Wilcox
  Cc: Juergen Gross, Jens Axboe, kvm, linux-scsi, Matthew Wilcox,
	netdev, linux-usb, linux-kernel, virtualization, target-devel,
	kbuild-all, qla2xxx-upstream, linux1394-devel, Kent Overstreet
In-Reply-To: <20180515160043.27044-2-willy@infradead.org>


Fixes: 5aff7a710f13 ("Convert target drivers to use sbitmap")
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
---
 iscsi_target_util.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 28bcffa..e147aef 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -147,7 +147,7 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd)
 	spin_unlock_bh(&cmd->r2t_lock);
 }
 
-int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup)
+static int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup)
 {
 	int tag = -1;
 	DEFINE_WAIT(wait);

------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot

^ permalink raw reply related

* Re: [PATCH 1/2] Convert target drivers to use sbitmap
From: kbuild test robot @ 2018-05-16 12:47 UTC (permalink / raw)
  To: Matthew Wilcox
  Cc: kbuild-all, linux-kernel, linux-scsi, target-devel,
	linux1394-devel, linux-usb, kvm, virtualization, netdev,
	Juergen Gross, qla2xxx-upstream, Kent Overstreet, Jens Axboe,
	Matthew Wilcox
In-Reply-To: <20180515160043.27044-2-willy@infradead.org>

Hi Matthew,

I love your patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v4.17-rc5 next-20180516]
[cannot apply to target/master]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Matthew-Wilcox/Use-sbitmap-instead-of-percpu_ida/20180516-143658
reproduce:
        # apt-get install sparse
        make ARCH=x86_64 allmodconfig
        make C=1 CF=-D__CHECK_ENDIAN__


sparse warnings: (new ones prefixed by >>)

>> drivers/target/iscsi/iscsi_target_util.c:150:5: sparse: symbol 'iscsit_wait_for_tag' was not declared. Should it be static?
   drivers/target/iscsi/iscsi_target_util.c:1174:31: sparse: expression using sizeof(void)
   drivers/target/iscsi/iscsi_target_util.c:1174:31: sparse: expression using sizeof(void)

Please review and possibly fold the followup patch.

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

^ permalink raw reply

* Re: [PATCH 12/14] net: sched: retry action check-insert on concurrent modification
From: Vlad Buslov @ 2018-05-16 12:43 UTC (permalink / raw)
  To: Jiri Pirko
  Cc: netdev, davem, jhs, xiyou.wangcong, pablo, kadlec, fw, ast,
	daniel, edumazet, keescook, linux-kernel, netfilter-devel,
	coreteam, kliteyn
In-Reply-To: <20180516122600.GM1972@nanopsycho>


On Wed 16 May 2018 at 12:26, Jiri Pirko <jiri@resnulli.us> wrote:
> Wed, May 16, 2018 at 01:55:06PM CEST, vladbu@mellanox.com wrote:
>>
>>On Wed 16 May 2018 at 09:59, Jiri Pirko <jiri@resnulli.us> wrote:
>>> Mon, May 14, 2018 at 04:27:13PM CEST, vladbu@mellanox.com wrote:
>>>>Retry check-insert sequence in action init functions if action with same
>>>>index was inserted concurrently.
>>>>
>>>>Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
>>>>---
>>>> net/sched/act_bpf.c        | 8 +++++++-
>>>> net/sched/act_connmark.c   | 8 +++++++-
>>>> net/sched/act_csum.c       | 8 +++++++-
>>>> net/sched/act_gact.c       | 8 +++++++-
>>>> net/sched/act_ife.c        | 8 +++++++-
>>>> net/sched/act_ipt.c        | 8 +++++++-
>>>> net/sched/act_mirred.c     | 8 +++++++-
>>>> net/sched/act_nat.c        | 8 +++++++-
>>>> net/sched/act_pedit.c      | 8 +++++++-
>>>> net/sched/act_police.c     | 9 ++++++++-
>>>> net/sched/act_sample.c     | 8 +++++++-
>>>> net/sched/act_simple.c     | 9 ++++++++-
>>>> net/sched/act_skbedit.c    | 8 +++++++-
>>>> net/sched/act_skbmod.c     | 8 +++++++-
>>>> net/sched/act_tunnel_key.c | 9 ++++++++-
>>>> net/sched/act_vlan.c       | 9 ++++++++-
>>>> 16 files changed, 116 insertions(+), 16 deletions(-)
>>>>
>>>>diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
>>>>index 5554bf7..7e20fdc 100644
>>>>--- a/net/sched/act_bpf.c
>>>>+++ b/net/sched/act_bpf.c
>>>>@@ -299,10 +299,16 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
>>>> 
>>>> 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
>>>> 
>>>>+replay:
>>>> 	if (!tcf_idr_check(tn, parm->index, act, bind)) {
>>>> 		ret = tcf_idr_create(tn, parm->index, est, act,
>>>> 				     &act_bpf_ops, bind, true);
>>>>-		if (ret < 0)
>>>>+		/* Action with specified index was created concurrently.
>>>>+		 * Check again.
>>>>+		 */
>>>>+		if (parm->index && ret == -ENOSPC)
>>>>+			goto replay;
>>>>+		else if (ret)
>>>
>>> Hmm, looks like you are doing the same/very similar thing in every act
>>> code. I think it would make sense to introduce a helper function for
>>> this purpose.
>>
>>This code uses goto so it can't be easily refactored into standalone
>>function. Could you specify which part of this code you suggest to
>>extract?
>
> Hmm, looking at the code, I think that what would help is to have a
> helper that would atomically check if index exists and if not, it would
> allocate one. Something like:
>
>
> int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
> 			struct tc_action **a, int bind)
> {
> 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
> 	struct tc_action *p;
> 	int err;
>
> 	spin_lock(&idrinfo->lock);
> 	if (*index) {
> 		p = idr_find(&idrinfo->action_idr, *index);
> 		if (p) {
> 			if (bind)
> 	   			p->tcfa_bindcnt++;
> 			p->tcfa_refcnt++;
> 			*a = p;
> 			err = 0;
> 		} else {
> 			*a = NULL;
> 			err = idr_alloc_u32(idr, NULL, index,
> 					    *index, GFP_ATOMIC);
> 		}
> 	} else {
> 		*index = 1;
> 		*a = NULL;
> 		err = idr_alloc_u32(idr, NULL, index, UINT_MAX, GFP_ATOMIC);
> 	}
> 	spin_unlock(&idrinfo->lock);
> 	return err;
> }
>
> The act code would just check if "a" is NULL and if so, it would call
> tcf_idr_create() with allocated index as arg.

What about multiple actions that have arbitrary code between initial
check and idr allocation that is currently inside tcf_idr_create()?

>
>
>>
>>>
>>> [...]
>>

^ permalink raw reply

* [PATCH net] tuntap: fix use after free during release
From: Jason Wang @ 2018-05-16 12:39 UTC (permalink / raw)
  To: netdev, linux-kernel; +Cc: xiyou.wangcong, avagin, mst, Jason Wang

After commit b196d88aba8a ("tun: fix use after free for ptr_ring") we
need clean up tx ring during release(). But unfortunately, it tries to
do the cleanup blindly after socket were destroyed which will lead
another use-after-free. Fix this by doing the cleanup before dropping
the last reference of the socket in __tun_detach().

Reported-by: Andrei Vagin <avagin@virtuozzo.com>
Acked-by: Andrei Vagin <avagin@virtuozzo.com>
Fixes: b196d88aba8a ("tun: fix use after free for ptr_ring")
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/net/tun.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9fbbb32..d45ac37 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -729,6 +729,7 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		}
 		if (tun)
 			xdp_rxq_info_unreg(&tfile->xdp_rxq);
+		ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
 		sock_put(&tfile->sk);
 	}
 }
@@ -3245,7 +3246,6 @@ static int tun_chr_close(struct inode *inode, struct file *file)
 	struct tun_file *tfile = file->private_data;
 
 	tun_detach(tfile, true);
-	ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
 
 	return 0;
 }
-- 
2.7.4

^ permalink raw reply related

* Re: [RFC v4 3/5] virtio_ring: add packed ring support
From: Tiwei Bie @ 2018-05-16 12:39 UTC (permalink / raw)
  To: Jason Wang; +Cc: mst, virtualization, linux-kernel, netdev, wexu, jfreimann
In-Reply-To: <2000f635-bc34-71ff-ff51-a711c2e9726d@redhat.com>

On Wed, May 16, 2018 at 07:50:16PM +0800, Jason Wang wrote:
> On 2018年05月16日 16:37, Tiwei Bie wrote:
[...]
> >   struct vring_virtqueue {
> > @@ -116,6 +117,9 @@ struct vring_virtqueue {
> >   			/* Last written value to driver->flags in
> >   			 * guest byte order. */
> >   			u16 event_flags_shadow;
> > +
> > +			/* ID allocation. */
> > +			struct idr buffer_id;
> 
> I'm not sure idr is fit for the performance critical case here. Need to
> measure its performance impact, especially if we have few unused slots.

I'm also not sure.. But fortunately, it should be quite easy
to replace it with something else without changing other code.
If it will really hurt the performance, I'll change it.

> 
> >   		};
> >   	};
[...]
> > +static void detach_buf_packed(struct vring_virtqueue *vq, unsigned int head,
> > +			      unsigned int id, void **ctx)
> > +{
> > +	struct vring_packed_desc *desc;
> > +	unsigned int i, j;
> > +
> > +	/* Clear data ptr. */
> > +	vq->desc_state[id].data = NULL;
> > +
> > +	i = head;
> > +
> > +	for (j = 0; j < vq->desc_state[id].num; j++) {
> > +		desc = &vq->vring_packed.desc[i];
> > +		vring_unmap_one_packed(vq, desc);
> 
> As mentioned in previous discussion, this probably won't work for the case
> of out of order completion since it depends on the information in the
> descriptor ring. We probably need to extend ctx to record such information.

Above code doesn't depend on the information in the descriptor
ring. The vq->desc_state[] is the extended ctx.

Best regards,
Tiwei Bie

^ permalink raw reply

* [RFC V4 PATCH 8/8] vhost: event suppression for packed ring
From: Jason Wang @ 2018-05-16 12:32 UTC (permalink / raw)
  To: mst, jasowang
  Cc: kvm, virtualization, netdev, linux-kernel, jfreimann, wexu,
	tiwei.bie
In-Reply-To: <1526473941-16199-1-git-send-email-jasowang@redhat.com>

This patch introduces basic support for event suppression aka driver
and device area.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/vhost.c            | 168 ++++++++++++++++++++++++++++++++++++---
 drivers/vhost/vhost.h            |  10 ++-
 include/uapi/linux/virtio_ring.h |  19 +++++
 3 files changed, 182 insertions(+), 15 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f2a0f5b..afdf4c1 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1108,10 +1108,15 @@ static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num,
 			       struct vring_used __user *used)
 {
 	struct vring_desc_packed *packed = (struct vring_desc_packed *)desc;
+	struct vring_packed_desc_event *driver_event =
+		(struct vring_packed_desc_event *)avail;
+	struct vring_packed_desc_event *device_event =
+		(struct vring_packed_desc_event *)used;
 
-	/* FIXME: check device area and driver area */
 	return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) &&
-	       access_ok(VERIFY_WRITE, packed, num * sizeof(*packed));
+	       access_ok(VERIFY_WRITE, packed, num * sizeof(*packed)) &&
+	       access_ok(VERIFY_READ, driver_event, sizeof(*driver_event)) &&
+	       access_ok(VERIFY_WRITE, device_event, sizeof(*device_event));
 }
 
 static int vq_access_ok_split(struct vhost_virtqueue *vq, unsigned int num,
@@ -1186,14 +1191,27 @@ static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 	return true;
 }
 
-int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
+int vq_iotlb_prefetch_packed(struct vhost_virtqueue *vq)
+{
+	int num = vq->num;
+
+	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
+			       num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
+	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->desc,
+			       num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
+	       iotlb_access_ok(vq, VHOST_ACCESS_RO,
+			       (u64)(uintptr_t)vq->driver_event,
+			       sizeof(*vq->driver_event), VHOST_ADDR_AVAIL) &&
+	       iotlb_access_ok(vq, VHOST_ACCESS_WO,
+			       (u64)(uintptr_t)vq->device_event,
+			       sizeof(*vq->device_event), VHOST_ADDR_USED);
+}
+
+int vq_iotlb_prefetch_split(struct vhost_virtqueue *vq)
 {
 	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 	unsigned int num = vq->num;
 
-	if (!vq->iotlb)
-		return 1;
-
 	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
 			       num * sizeof(*vq->desc), VHOST_ADDR_DESC) &&
 	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
@@ -1205,6 +1223,17 @@ int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
 			       num * sizeof(*vq->used->ring) + s,
 			       VHOST_ADDR_USED);
 }
+
+int vq_iotlb_prefetch(struct vhost_virtqueue *vq)
+{
+	if (!vq->iotlb)
+		return 1;
+
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vq_iotlb_prefetch_packed(vq);
+	else
+		return vq_iotlb_prefetch_split(vq);
+}
 EXPORT_SYMBOL_GPL(vq_iotlb_prefetch);
 
 /* Can we log writes? */
@@ -1724,6 +1753,29 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 	return 0;
 }
 
+static int vhost_update_device_flags(struct vhost_virtqueue *vq,
+				     __virtio16 device_flags)
+{
+	void __user *flags;
+
+	if (vhost_put_user(vq, cpu_to_vhost16(vq, device_flags),
+			   &vq->device_event->flags,
+			   VHOST_ADDR_USED) < 0)
+		return -EFAULT;
+	if (unlikely(vq->log_used)) {
+		/* Make sure the flag is seen before log. */
+		smp_wmb();
+		/* Log used flag write. */
+		flags = &vq->device_event->flags;
+		log_write(vq->log_base, vq->log_addr +
+			  (flags - (void __user *)vq->device_event),
+			  sizeof(vq->used->flags));
+		if (vq->log_ctx)
+			eventfd_signal(vq->log_ctx, 1);
+	}
+	return 0;
+}
+
 static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 {
 	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
@@ -2640,16 +2692,13 @@ int vhost_add_used_n(struct vhost_virtqueue *vq,
 }
 EXPORT_SYMBOL_GPL(vhost_add_used_n);
 
-static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify_split(struct vhost_dev *dev,
+			       struct vhost_virtqueue *vq)
 {
 	__u16 old, new;
 	__virtio16 event;
 	bool v;
 
-	/* FIXME: check driver area */
-	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
-		return false;
-
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
@@ -2682,6 +2731,78 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	return vring_need_event(vhost16_to_cpu(vq, event), new, old);
 }
 
+static bool vhost_vring_packed_need_event(struct vhost_virtqueue *vq,
+					  __u16 off_wrap, __u16 new,
+					  __u16 old)
+{
+    bool wrap = vq->used_wrap_counter;
+    int off = off_wrap & ~(1 << 15);
+
+    if (new < old) {
+	    new += vq->num;
+	    wrap ^= 1;
+    }
+
+    if (wrap != off_wrap >> 15)
+	    off += vq->num;
+
+    return vring_need_event(off, new, old);
+}
+
+static bool vhost_notify_packed(struct vhost_dev *dev,
+				struct vhost_virtqueue *vq)
+{
+	__virtio16 event_off_wrap, event_flags;
+	__u16 old, new, off_wrap;
+	bool v;
+
+	/* Flush out used descriptors updates. This is paired
+	 * with the barrier that the Guest executes when enabling
+	 * interrupts.
+	 */
+	smp_mb();
+
+	if (vhost_get_avail(vq, event_flags,
+			   &vq->driver_event->flags) < 0) {
+		vq_err(vq, "Failed to get driver desc_event_flags");
+		return true;
+	}
+
+	if (event_flags == cpu_to_vhost16(vq, RING_EVENT_FLAGS_DISABLE))
+		return false;
+	else if (event_flags == cpu_to_vhost16(vq, RING_EVENT_FLAGS_ENABLE))
+		return true;
+
+	/* Read desc event flags before event_off and event_wrap */
+	smp_rmb();
+
+	if (vhost_get_avail(vq, event_off_wrap,
+			    &vq->driver_event->off_warp) < 0) {
+		vq_err(vq, "Failed to get driver desc_event_off/wrap");
+		return true;
+	}
+
+	off_wrap = vhost16_to_cpu(vq, event_off_wrap);
+
+	old = vq->signalled_used;
+	v = vq->signalled_used_valid;
+	new = vq->signalled_used = vq->last_used_idx;
+	vq->signalled_used_valid = true;
+
+	if (unlikely(!v))
+		return true;
+
+	return vhost_vring_packed_need_event(vq, off_wrap, new, old);
+}
+
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_notify_packed(dev, vq);
+	else
+		return vhost_notify_split(dev, vq);
+}
+
 /* This actually signals the guest, using eventfd. */
 void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
@@ -2762,7 +2883,17 @@ static bool vhost_enable_notify_packed(struct vhost_dev *dev,
 	__virtio16 flags;
 	int ret;
 
-	/* FIXME: disable notification through device area */
+	if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
+		return false;
+	vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
+
+	flags = cpu_to_vhost16(vq, RING_EVENT_FLAGS_ENABLE);
+	ret = vhost_update_device_flags(vq, flags);
+	if (ret) {
+		vq_err(vq, "Failed to enable notification at %p: %d\n",
+		       &vq->device_event->flags, ret);
+		return false;
+	}
 
 	/* They could have slipped one in as we were doing that: make
 	 * sure it's written, then check again. */
@@ -2828,7 +2959,18 @@ EXPORT_SYMBOL_GPL(vhost_enable_notify);
 static void vhost_disable_notify_packed(struct vhost_dev *dev,
 					struct vhost_virtqueue *vq)
 {
-	/* FIXME: disable notification through device area */
+	__virtio16 flags;
+	int r;
+
+	if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
+		return;
+	vq->used_flags |= VRING_USED_F_NO_NOTIFY;
+
+	flags = cpu_to_vhost16(vq, RING_EVENT_FLAGS_DISABLE);
+	r = vhost_update_device_flags(vq, flags);
+	if (r)
+		vq_err(vq, "Failed to enable notification at %p: %d\n",
+		       &vq->device_event->flags, r);
 }
 
 static void vhost_disable_notify_split(struct vhost_dev *dev,
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 286b470..0750659 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -96,8 +96,14 @@ struct vhost_virtqueue {
 		struct vring_desc __user *desc;
 		struct vring_desc_packed __user *desc_packed;
 	};
-	struct vring_avail __user *avail;
-	struct vring_used __user *used;
+	union {
+		struct vring_avail __user *avail;
+		struct vring_packed_desc_event __user *driver_event;
+	};
+	union {
+		struct vring_used __user *used;
+		struct vring_packed_desc_event __user *device_event;
+	};
 	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
 	struct eventfd_ctx *call_ctx;
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index e297580..b3f4b2c 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -75,6 +75,25 @@ struct vring_desc_packed {
 	__virtio16 flags;
 };
 
+/* Enable events */
+#define RING_EVENT_FLAGS_ENABLE 0x0
+/* Disable events */
+#define RING_EVENT_FLAGS_DISABLE 0x1
+/*
+ * Enable events for a specific descriptor
+ * (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
+ * Only valid if VIRTIO_F_RING_EVENT_IDX has been negotiated.
+ */
+#define RING_EVENT_FLAGS_DESC 0x2
+/* The value 0x3 is reserved */
+
+struct vring_packed_desc_event {
+	/* Descriptor Ring Change Event Offset and Wrap Counter */
+	__virtio16 off_warp;
+	/* Descriptor Ring Change Event Flags */
+	__virtio16 flags;
+};
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
-- 
2.7.4

^ permalink raw reply related

* [RFC V4 PATCH 7/8] vhost: packed ring support
From: Jason Wang @ 2018-05-16 12:32 UTC (permalink / raw)
  To: mst, jasowang
  Cc: kvm, virtualization, netdev, linux-kernel, jfreimann, wexu,
	tiwei.bie
In-Reply-To: <1526473941-16199-1-git-send-email-jasowang@redhat.com>

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/net.c   |   3 +-
 drivers/vhost/vhost.c | 539 ++++++++++++++++++++++++++++++++++++++++++++++----
 drivers/vhost/vhost.h |   8 +-
 3 files changed, 513 insertions(+), 37 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 30273ad..f55c82f8 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -71,7 +71,8 @@ enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
+			 (1ULL << VIRTIO_F_IOMMU_PLATFORM) |
+			 (1ULL << VIRTIO_F_RING_PACKED)
 };
 
 enum {
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 8304c30..f2a0f5b 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -323,6 +323,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vhost_reset_is_le(vq);
 	vhost_disable_cross_endian(vq);
 	vq->busyloop_timeout = 0;
+	vq->used_wrap_counter = true;
+	vq->avail_wrap_counter = true;
 	vq->umem = NULL;
 	vq->iotlb = NULL;
 	__vhost_vq_meta_reset(vq);
@@ -1100,11 +1102,22 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
 	return 0;
 }
 
-static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
-			 struct vring_desc __user *desc,
-			 struct vring_avail __user *avail,
-			 struct vring_used __user *used)
+static int vq_access_ok_packed(struct vhost_virtqueue *vq, unsigned int num,
+			       struct vring_desc __user *desc,
+			       struct vring_avail __user *avail,
+			       struct vring_used __user *used)
+{
+	struct vring_desc_packed *packed = (struct vring_desc_packed *)desc;
+
+	/* FIXME: check device area and driver area */
+	return access_ok(VERIFY_READ, packed, num * sizeof(*packed)) &&
+	       access_ok(VERIFY_WRITE, packed, num * sizeof(*packed));
+}
 
+static int vq_access_ok_split(struct vhost_virtqueue *vq, unsigned int num,
+			      struct vring_desc __user *desc,
+			      struct vring_avail __user *avail,
+			      struct vring_used __user *used)
 {
 	size_t s = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
@@ -1115,6 +1128,17 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 			sizeof *used + num * sizeof *used->ring + s);
 }
 
+static int vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
+			struct vring_desc __user *desc,
+			struct vring_avail __user *avail,
+			struct vring_used __user *used)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vq_access_ok_packed(vq, num, desc, avail, used);
+	else
+		return vq_access_ok_split(vq, num, desc, avail, used);
+}
+
 static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
 				 const struct vhost_umem_node *node,
 				 int type)
@@ -1358,6 +1382,8 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 			break;
 		}
 		vq->last_avail_idx = s.num;
+		if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+			vq->avail_wrap_counter = s.num >> 31;
 		/* Forget the cached index value. */
 		vq->avail_idx = vq->last_avail_idx;
 		break;
@@ -1366,6 +1392,8 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 		s.num = vq->last_avail_idx;
 		if (copy_to_user(argp, &s, sizeof s))
 			r = -EFAULT;
+		if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+			s.num |= vq->avail_wrap_counter << 31;
 		break;
 	case VHOST_SET_VRING_ADDR:
 		if (copy_from_user(&a, argp, sizeof a)) {
@@ -1727,6 +1755,9 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq)
 
 	vhost_init_is_le(vq);
 
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return 0;
+
 	r = vhost_update_used_flags(vq);
 	if (r)
 		goto err;
@@ -1800,7 +1831,8 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 /* Each buffer in the virtqueues is actually a chain of descriptors.  This
  * function returns the next descriptor in the chain,
  * or -1U if we're at the end. */
-static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
+static unsigned next_desc_split(struct vhost_virtqueue *vq,
+				struct vring_desc *desc)
 {
 	unsigned int next;
 
@@ -1813,11 +1845,17 @@ static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
 	return next;
 }
 
-static int get_indirect(struct vhost_virtqueue *vq,
-			struct iovec iov[], unsigned int iov_size,
-			unsigned int *out_num, unsigned int *in_num,
-			struct vhost_log *log, unsigned int *log_num,
-			struct vring_desc *indirect)
+static unsigned next_desc_packed(struct vhost_virtqueue *vq,
+				 struct vring_desc_packed *desc)
+{
+	return desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT);
+}
+
+static int get_indirect_split(struct vhost_virtqueue *vq,
+			      struct iovec iov[], unsigned int iov_size,
+			      unsigned int *out_num, unsigned int *in_num,
+			      struct vhost_log *log, unsigned int *log_num,
+			      struct vring_desc *indirect)
 {
 	struct vring_desc desc;
 	unsigned int i = 0, count, found = 0;
@@ -1907,23 +1945,274 @@ static int get_indirect(struct vhost_virtqueue *vq,
 			}
 			*out_num += ret;
 		}
-	} while ((i = next_desc(vq, &desc)) != -1);
+	} while ((i = next_desc_split(vq, &desc)) != -1);
 	return 0;
 }
 
-/* This looks in the virtqueue and for the first available buffer, and converts
- * it to an iovec for convenient access.  Since descriptors consist of some
- * number of output then some number of input descriptors, it's actually two
- * iovecs, but we pack them into one and note how many of each there were.
- *
- * This function returns the descriptor number found, or vq->num (which is
- * never a valid descriptor number) if none was found.  A negative code is
- * returned on error. */
-int vhost_get_vq_desc(struct vhost_virtqueue *vq,
-		      struct vhost_used_elem *used,
-		      struct iovec iov[], unsigned int iov_size,
-		      unsigned int *out_num, unsigned int *in_num,
-		      struct vhost_log *log, unsigned int *log_num)
+static int get_indirect_packed(struct vhost_virtqueue *vq,
+			       struct iovec iov[], unsigned int iov_size,
+			       unsigned int *out_num, unsigned int *in_num,
+			       struct vhost_log *log, unsigned int *log_num,
+			       struct vring_desc_packed *indirect)
+{
+	struct vring_desc_packed desc;
+	unsigned int i = 0, count, found = 0;
+	u32 len = vhost32_to_cpu(vq, indirect->len);
+	struct iov_iter from;
+	int ret, access;
+
+	/* Sanity check */
+	if (unlikely(len % sizeof(desc))) {
+		vq_err(vq, "Invalid length in indirect descriptor: "
+		       "len 0x%llx not multiple of 0x%zx\n",
+		       (unsigned long long)len,
+		       sizeof desc);
+		return -EINVAL;
+	}
+
+	ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr),
+			     len, vq->indirect,
+			     UIO_MAXIOV, VHOST_ACCESS_RO);
+	if (unlikely(ret < 0)) {
+		if (ret != -EAGAIN)
+			vq_err(vq, "Translation failure %d in indirect.\n",
+			       ret);
+		return ret;
+	}
+	iov_iter_init(&from, READ, vq->indirect, ret, len);
+
+	/* We will use the result as an address to read from, so most
+	 * architectures only need a compiler barrier here. */
+	read_barrier_depends();
+
+	count = len / sizeof desc;
+	/* Buffers are chained via a 16 bit next field, so
+	 * we can have at most 2^16 of these. */
+	if (unlikely(count > USHRT_MAX + 1)) {
+		vq_err(vq, "Indirect buffer length too big: %d\n",
+		       indirect->len);
+		return -E2BIG;
+	}
+
+	do {
+		unsigned iov_count = *in_num + *out_num;
+		if (unlikely(++found > count)) {
+			vq_err(vq, "Loop detected: last one at %u "
+			       "indirect size %u\n",
+			       i, count);
+			return -EINVAL;
+		}
+		if (unlikely(!copy_from_iter_full(&desc, sizeof(desc),
+						  &from))) {
+			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
+			       i, (size_t)vhost64_to_cpu(vq, indirect->addr)
+				  + i * sizeof desc);
+			return -EINVAL;
+		}
+		if (unlikely(desc.flags &
+			     cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
+			vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
+			       i, (size_t)vhost64_to_cpu(vq, indirect->addr)
+				  + i * sizeof desc);
+			return -EINVAL;
+		}
+
+		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
+			access = VHOST_ACCESS_WO;
+		else
+			access = VHOST_ACCESS_RO;
+
+		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
+				     vhost32_to_cpu(vq, desc.len),
+				     iov + iov_count,
+				     iov_size - iov_count, access);
+		if (unlikely(ret < 0)) {
+			if (ret != -EAGAIN)
+				vq_err(vq, "Translation failure %d "
+					   "indirect idx %d\n",
+				       ret, i);
+			return ret;
+		}
+		/* If this is an input descriptor, increment that count. */
+		if (access == VHOST_ACCESS_WO) {
+			*in_num += ret;
+			if (unlikely(log)) {
+				log[*log_num].addr =
+					vhost64_to_cpu(vq, desc.addr);
+				log[*log_num].len =
+					vhost32_to_cpu(vq, desc.len);
+				++*log_num;
+			}
+		} else {
+			/* If it's an output descriptor, they're all supposed
+			 * to come before any input descriptors. */
+			if (unlikely(*in_num)) {
+				vq_err(vq, "Indirect descriptor "
+				       "has out after in: idx %d\n", i);
+				return -EINVAL;
+			}
+			*out_num += ret;
+		}
+		i++;
+	} while (next_desc_packed(vq, &desc));
+	return 0;
+}
+
+#define DESC_AVAIL (1 << VRING_DESC_F_AVAIL)
+#define DESC_USED  (1 << VRING_DESC_F_USED)
+static bool desc_is_avail(struct vhost_virtqueue *vq, __virtio16 flags)
+{
+	bool avail = flags & cpu_to_vhost16(vq, DESC_AVAIL);
+
+	return avail == vq->avail_wrap_counter;
+}
+
+static __virtio16 get_desc_flags(struct vhost_virtqueue *vq, bool write)
+{
+	__virtio16 flags = 0;
+
+	if (vq->used_wrap_counter) {
+		flags |= cpu_to_vhost16(vq, DESC_AVAIL);
+		flags |= cpu_to_vhost16(vq, DESC_USED);
+	} else {
+		flags &= ~cpu_to_vhost16(vq, DESC_AVAIL);
+		flags &= ~cpu_to_vhost16(vq, DESC_USED);
+	}
+
+	if (write)
+		flags |= cpu_to_vhost16(vq, VRING_DESC_F_WRITE);
+
+	return flags;
+}
+
+static int vhost_get_vq_desc_packed(struct vhost_virtqueue *vq,
+				    struct vhost_used_elem *used,
+				    struct iovec iov[], unsigned int iov_size,
+				    unsigned int *out_num, unsigned int *in_num,
+				    struct vhost_log *log,
+				    unsigned int *log_num)
+{
+	struct vring_desc_packed desc;
+	int ret, access, i;
+
+	/* When we start there are none of either input nor output. */
+	*out_num = *in_num = 0;
+	if (unlikely(log))
+		*log_num = 0;
+
+	used->count = 0;
+
+	do {
+		struct vring_desc_packed *d = vq->desc_packed +
+					      vq->last_avail_idx;
+		unsigned int iov_count = *in_num + *out_num;
+
+		ret = vhost_get_user(vq, desc.flags, &d->flags,
+				     VHOST_ADDR_DESC);
+		if (unlikely(ret)) {
+			vq_err(vq, "Failed to get flags: idx %d addr %p\n",
+			       vq->last_avail_idx, &d->flags);
+			return -EFAULT;
+		}
+
+		if (!desc_is_avail(vq, desc.flags)) {
+			/* If there's nothing new since last we looked, return
+			 * invalid.
+			 */
+			if (!used->count)
+				return -ENOSPC;
+			vq_err(vq, "Unexpected unavail descriptor: idx %d\n",
+			       vq->last_avail_idx);
+			return -EFAULT;
+		}
+
+		/* Read desc content after we're sure it was available. */
+		smp_rmb();
+
+		ret = vhost_copy_from_user(vq, &desc, d, sizeof(desc));
+		if (unlikely(ret)) {
+			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
+				vq->last_avail_idx, d);
+			return -EFAULT;
+		}
+
+		used->elem.id = desc.id;
+
+		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
+			ret = get_indirect_packed(vq, iov, iov_size,
+						  out_num, in_num, log,
+						  log_num, &desc);
+			if (unlikely(ret < 0)) {
+				if (ret != -EAGAIN)
+					vq_err(vq, "Failure detected "
+						   "in indirect descriptor "
+						   "at idx %d\n", i);
+				return ret;
+			}
+			goto next;
+		}
+
+		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
+			access = VHOST_ACCESS_WO;
+		else
+			access = VHOST_ACCESS_RO;
+		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
+				     vhost32_to_cpu(vq, desc.len),
+				     iov + iov_count, iov_size - iov_count,
+				     access);
+		if (unlikely(ret < 0)) {
+			if (ret != -EAGAIN)
+				vq_err(vq, "Translation failure %d idx %d\n",
+					ret, i);
+			return ret;
+		}
+
+		if (access == VHOST_ACCESS_WO) {
+			/* If this is an input descriptor,
+			 * increment that count.
+			 */
+			*in_num += ret;
+			if (unlikely(log)) {
+				log[*log_num].addr =
+					vhost64_to_cpu(vq, desc.addr);
+				log[*log_num].len =
+					vhost32_to_cpu(vq, desc.len);
+				++*log_num;
+			}
+		} else {
+			/* If it's an output descriptor, they're all supposed
+			 * to come before any input descriptors.
+			 */
+			if (unlikely(*in_num)) {
+				vq_err(vq, "Desc out after in: idx %d\n",
+				       i);
+				return -EINVAL;
+			}
+			*out_num += ret;
+		}
+
+next:
+		if (unlikely(++used->count > vq->num)) {
+			vq_err(vq, "Loop detected: last one at %u "
+			       "vq size %u head %u\n",
+			       i, vq->num, used->elem.id);
+			return -EINVAL;
+		}
+		if (++vq->last_avail_idx >= vq->num) {
+			vq->last_avail_idx = 0;
+			vq->avail_wrap_counter ^= 1;
+		}
+	/* If this descriptor says it doesn't chain, we're done. */
+	} while (next_desc_packed(vq, &desc));
+
+	return 0;
+}
+
+static int vhost_get_vq_desc_split(struct vhost_virtqueue *vq,
+				   struct vhost_used_elem *used,
+				   struct iovec iov[], unsigned int iov_size,
+				   unsigned int *out_num, unsigned int *in_num,
+				   struct vhost_log *log, unsigned int *log_num)
 {
 	struct vring_desc desc;
 	unsigned int i, head, found = 0;
@@ -2008,9 +2297,9 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 			return -EFAULT;
 		}
 		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
-			ret = get_indirect(vq, iov, iov_size,
-					   out_num, in_num,
-					   log, log_num, &desc);
+			ret = get_indirect_split(vq, iov, iov_size,
+						 out_num, in_num,
+						 log, log_num, &desc);
 			if (unlikely(ret < 0)) {
 				if (ret != -EAGAIN)
 					vq_err(vq, "Failure detected "
@@ -2052,7 +2341,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 			}
 			*out_num += ret;
 		}
-	} while ((i = next_desc(vq, &desc)) != -1);
+	} while ((i = next_desc_split(vq, &desc)) != -1);
 
 	/* On success, increment avail index. */
 	vq->last_avail_idx++;
@@ -2062,6 +2351,31 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
 	return 0;
 }
+
+/* This looks in the virtqueue and for the first available buffer, and converts
+ * it to an iovec for convenient access.  Since descriptors consist of some
+ * number of output then some number of input descriptors, it's actually two
+ * iovecs, but we pack them into one and note how many of each there were.
+ *
+ * This function returns the descriptor number found, or vq->num (which is
+ * never a valid descriptor number) if none was found.  A negative code is
+ * returned on error.
+ */
+int vhost_get_vq_desc(struct vhost_virtqueue *vq,
+		      struct vhost_used_elem *used,
+		      struct iovec iov[], unsigned int iov_size,
+		      unsigned int *out_num, unsigned int *in_num,
+		      struct vhost_log *log, unsigned int *log_num)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_get_vq_desc_packed(vq, used, iov, iov_size,
+						out_num, in_num,
+						log, log_num);
+	else
+		return vhost_get_vq_desc_split(vq, used, iov, iov_size,
+					       out_num, in_num,
+					       log, log_num);
+}
 EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
 
 void vhost_set_used_len(struct vhost_virtqueue *vq,
@@ -2157,6 +2471,11 @@ EXPORT_SYMBOL_GPL(vhost_get_bufs);
 void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
 {
 	vq->last_avail_idx -= n;
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED) &&
+	    vq->last_avail_idx >= vq->num) {
+		vq->avail_wrap_counter ^= 1;
+		vq->last_avail_idx += vq->num;
+	}
 }
 EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);
 
@@ -2212,10 +2531,69 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 	return 0;
 }
 
+static int vhost_add_used_n_packed(struct vhost_virtqueue *vq,
+				   struct vhost_used_elem *heads,
+				   unsigned int count)
+{
+	struct vring_desc_packed __user *desc;
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		desc = vq->desc_packed + vq->last_used_idx;
+
+		ret = vhost_put_user(vq, heads[i].elem.id, &desc->id,
+				     VHOST_ADDR_DESC);
+		if (unlikely(ret)) {
+			vq_err(vq, "Failed to update id: idx %d addr %p\n",
+			       vq->last_used_idx, desc);
+			return -EFAULT;
+		}
+		ret = vhost_put_user(vq, heads[i].elem.len, &desc->len,
+				     VHOST_ADDR_DESC);
+		if (unlikely(ret)) {
+			vq_err(vq, "Failed to update len: idx %d addr %p\n",
+			       vq->last_used_idx, desc);
+			return -EFAULT;
+		}
+
+		/* Update flags after descriptor id and len is wrote,
+		 * TODO: Update head flags at last for saving barriers */
+		smp_wmb();
+
+		ret = vhost_put_user(vq, get_desc_flags(vq, heads[i].elem.len),
+				     &desc->flags, VHOST_ADDR_DESC);
+		if (unlikely(ret)) {
+			vq_err(vq, "Failed to update flags: idx %d addr %p\n",
+			       vq->last_used_idx, desc);
+			return -EFAULT;
+		}
+
+		if (unlikely(vq->log_used)) {
+			/* Make sure desc is written before update log. */
+			smp_wmb();
+			log_write(vq->log_base, vq->log_addr +
+				  vq->last_used_idx * sizeof(*desc),
+				  sizeof(*desc));
+			if (vq->log_ctx)
+				eventfd_signal(vq->log_ctx, 1);
+		}
+
+		vq->last_used_idx += heads[i].count;
+		if (vq->last_used_idx >= vq->num) {
+			vq->used_wrap_counter ^= 1;
+			vq->last_used_idx -= vq->num;
+		}
+	}
+
+	return 0;
+}
+
 /* After we've used one of their buffers, we tell them about it.  We'll then
  * want to notify the guest, using eventfd. */
-int vhost_add_used_n(struct vhost_virtqueue *vq, struct vhost_used_elem *heads,
-		     unsigned count)
+static int vhost_add_used_n_split(struct vhost_virtqueue *vq,
+				  struct vhost_used_elem *heads,
+				  unsigned count)
+
 {
 	int start, n, r;
 
@@ -2247,6 +2625,19 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vhost_used_elem *heads,
 	}
 	return r;
 }
+
+/* After we've used one of their buffers, we tell them about it.  We'll then
+ * want to notify the guest, using eventfd.
+ */
+int vhost_add_used_n(struct vhost_virtqueue *vq,
+		     struct vhost_used_elem *heads,
+		     unsigned int count)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_add_used_n_packed(vq, heads, count);
+	else
+		return vhost_add_used_n_split(vq, heads, count);
+}
 EXPORT_SYMBOL_GPL(vhost_add_used_n);
 
 static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
@@ -2254,6 +2645,11 @@ static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 	__u16 old, new;
 	__virtio16 event;
 	bool v;
+
+	/* FIXME: check driver area */
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return false;
+
 	/* Flush out used index updates. This is paired
 	 * with the barrier that the Guest executes when enabling
 	 * interrupts. */
@@ -2316,7 +2712,8 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n);
 
 /* return true if we're sure that avaiable ring is empty */
-bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_vq_avail_empty_split(struct vhost_dev *dev,
+				       struct vhost_virtqueue *vq)
 {
 	__virtio16 avail_idx;
 	int r;
@@ -2331,10 +2728,58 @@ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 
 	return vq->avail_idx == vq->last_avail_idx;
 }
+
+static bool vhost_vq_avail_empty_packed(struct vhost_dev *dev,
+					struct vhost_virtqueue *vq)
+{
+	struct vring_desc_packed *d = vq->desc_packed + vq->last_avail_idx;
+	__virtio16 flags;
+	int ret;
+
+	ret = vhost_get_user(vq, flags, &d->flags, VHOST_ADDR_DESC);
+	if (unlikely(ret)) {
+		vq_err(vq, "Failed to get flags: idx %d addr %p\n",
+			vq->last_avail_idx, d);
+		return -EFAULT;
+	}
+
+	return !desc_is_avail(vq, flags);
+}
+
+bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_vq_avail_empty_packed(dev, vq);
+	else
+		return vhost_vq_avail_empty_split(dev, vq);
+}
 EXPORT_SYMBOL_GPL(vhost_vq_avail_empty);
 
-/* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_enable_notify_packed(struct vhost_dev *dev,
+				       struct vhost_virtqueue *vq)
+{
+	struct vring_desc_packed *d = vq->desc_packed + vq->last_avail_idx;
+	__virtio16 flags;
+	int ret;
+
+	/* FIXME: disable notification through device area */
+
+	/* They could have slipped one in as we were doing that: make
+	 * sure it's written, then check again. */
+	smp_mb();
+
+	ret = vhost_get_user(vq, flags, &d->flags, VHOST_ADDR_DESC);
+	if (unlikely(ret)) {
+		vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
+			vq->last_avail_idx, &d->flags);
+		return -EFAULT;
+	}
+
+	return desc_is_avail(vq, flags);
+}
+
+static bool vhost_enable_notify_split(struct vhost_dev *dev,
+				      struct vhost_virtqueue *vq)
 {
 	__virtio16 avail_idx;
 	int r;
@@ -2369,10 +2814,25 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 
 	return vhost16_to_cpu(vq, avail_idx) != vq->avail_idx;
 }
+
+/* OK, now we need to know about added descriptors. */
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_enable_notify_packed(dev, vq);
+	else
+		return vhost_enable_notify_split(dev, vq);
+}
 EXPORT_SYMBOL_GPL(vhost_enable_notify);
 
-/* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static void vhost_disable_notify_packed(struct vhost_dev *dev,
+					struct vhost_virtqueue *vq)
+{
+	/* FIXME: disable notification through device area */
+}
+
+static void vhost_disable_notify_split(struct vhost_dev *dev,
+				       struct vhost_virtqueue *vq)
 {
 	int r;
 
@@ -2386,6 +2846,15 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 			       &vq->used->flags, r);
 	}
 }
+
+/* We don't need to be notified again. */
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED))
+		return vhost_disable_notify_packed(dev, vq);
+	else
+		return vhost_disable_notify_split(dev, vq);
+}
 EXPORT_SYMBOL_GPL(vhost_disable_notify);
 
 /* Create a new message. */
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 604821b..286b470 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -36,6 +36,7 @@ struct vhost_poll {
 
 struct vhost_used_elem {
 	struct vring_used_elem elem;
+	int count;
 };
 
 void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn);
@@ -91,7 +92,10 @@ struct vhost_virtqueue {
 	/* The actual ring of buffers. */
 	struct mutex mutex;
 	unsigned int num;
-	struct vring_desc __user *desc;
+	union {
+		struct vring_desc __user *desc;
+		struct vring_desc_packed __user *desc_packed;
+	};
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
 	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
@@ -148,6 +152,8 @@ struct vhost_virtqueue {
 	bool user_be;
 #endif
 	u32 busyloop_timeout;
+	bool used_wrap_counter;
+	bool avail_wrap_counter;
 };
 
 struct vhost_msg_node {
-- 
2.7.4

^ permalink raw reply related

* [RFC V4 PATCH 6/8] virtio: introduce packed ring defines
From: Jason Wang @ 2018-05-16 12:32 UTC (permalink / raw)
  To: mst, jasowang
  Cc: kvm, virtualization, netdev, linux-kernel, jfreimann, wexu,
	tiwei.bie
In-Reply-To: <1526473941-16199-1-git-send-email-jasowang@redhat.com>

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 include/uapi/linux/virtio_config.h |  9 +++++++++
 include/uapi/linux/virtio_ring.h   | 13 +++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h
index 308e209..5903d51 100644
--- a/include/uapi/linux/virtio_config.h
+++ b/include/uapi/linux/virtio_config.h
@@ -71,4 +71,13 @@
  * this is for compatibility with legacy systems.
  */
 #define VIRTIO_F_IOMMU_PLATFORM		33
+
+#define VIRTIO_F_RING_PACKED		34
+
+/*
+ * This feature indicates that all buffers are used by the device in
+ * the same order in which they have been made available.
+ */
+#define VIRTIO_F_IN_ORDER		35
+
 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 6d5d5fa..e297580 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -43,6 +43,8 @@
 #define VRING_DESC_F_WRITE	2
 /* This means the buffer contains a list of buffer descriptors. */
 #define VRING_DESC_F_INDIRECT	4
+#define VRING_DESC_F_AVAIL      7
+#define VRING_DESC_F_USED	15
 
 /* The Host uses this in used->flags to advise the Guest: don't kick me when
  * you add a buffer.  It's unreliable, so it's simply an optimization.  Guest
@@ -62,6 +64,17 @@
  * at the end of the used ring. Guest should ignore the used->flags field. */
 #define VIRTIO_RING_F_EVENT_IDX		29
 
+struct vring_desc_packed {
+	/* Buffer Address. */
+	__virtio64 addr;
+	/* Buffer Length. */
+	__virtio32 len;
+	/* Buffer ID. */
+	__virtio16 id;
+	/* The flags depending on descriptor type. */
+	__virtio16 flags;
+};
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
 	/* Address (guest-physical). */
-- 
2.7.4

^ permalink raw reply related

* [RFC V4 PATCH 5/8] vhost: vhost_put_user() can accept metadata type
From: Jason Wang @ 2018-05-16 12:32 UTC (permalink / raw)
  To: mst, jasowang
  Cc: kvm, virtualization, netdev, linux-kernel, jfreimann, wexu,
	tiwei.bie
In-Reply-To: <1526473941-16199-1-git-send-email-jasowang@redhat.com>

We assumes used ring update is the only user for vhost_put_user() in
the past. This may not be the case for the incoming packed ring which
may update the descriptor ring for used. So introduce a new type
parameter.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/vhost.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2ef1859..8304c30 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -811,7 +811,7 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	return __vhost_get_user_slow(vq, addr, size, type);
 }
 
-#define vhost_put_user(vq, x, ptr)		\
+#define vhost_put_user(vq, x, ptr, type)		\
 ({ \
 	int ret = -EFAULT; \
 	if (!vq->iotlb) { \
@@ -819,7 +819,7 @@ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq,
 	} else { \
 		__typeof__(ptr) to = \
 			(__typeof__(ptr)) __vhost_get_user(vq, ptr,	\
-					  sizeof(*ptr), VHOST_ADDR_USED); \
+					  sizeof(*ptr), type); \
 		if (to != NULL) \
 			ret = __put_user(x, to); \
 		else \
@@ -1680,7 +1680,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 {
 	void __user *used;
 	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
-			   &vq->used->flags) < 0)
+			   &vq->used->flags, VHOST_ADDR_USED) < 0)
 		return -EFAULT;
 	if (unlikely(vq->log_used)) {
 		/* Make sure the flag is seen before log. */
@@ -1699,7 +1699,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
 static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
 {
 	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
-			   vhost_avail_event(vq)))
+			   vhost_avail_event(vq), VHOST_ADDR_USED))
 		return -EFAULT;
 	if (unlikely(vq->log_used)) {
 		void __user *used;
@@ -2182,12 +2182,12 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
 	used = vq->used->ring + start;
 	for (i = 0; i < count; i++) {
 		if (unlikely(vhost_put_user(vq, heads[i].elem.id,
-					    &used[i].id))) {
+					    &used[i].id, VHOST_ADDR_USED))) {
 			vq_err(vq, "Failed to write used id");
 			return -EFAULT;
 		}
 		if (unlikely(vhost_put_user(vq, heads[i].elem.len,
-					    &used[i].len))) {
+					    &used[i].len, VHOST_ADDR_USED))) {
 			vq_err(vq, "Failed to write used len");
 			return -EFAULT;
 		}
@@ -2233,7 +2233,7 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vhost_used_elem *heads,
 	/* Make sure buffer is written before we update index. */
 	smp_wmb();
 	if (vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
-			   &vq->used->idx)) {
+			   &vq->used->idx, VHOST_ADDR_USED)) {
 		vq_err(vq, "Failed to increment used idx");
 		return -EFAULT;
 	}
-- 
2.7.4

^ permalink raw reply related

* [RFC V4 PATCH 4/8] vhost_net: do not explicitly manipulate vhost_used_elem
From: Jason Wang @ 2018-05-16 12:32 UTC (permalink / raw)
  To: mst, jasowang
  Cc: kvm, virtualization, netdev, linux-kernel, jfreimann, wexu,
	tiwei.bie
In-Reply-To: <1526473941-16199-1-git-send-email-jasowang@redhat.com>

Two helpers of setting/getting used len were introduced to avoid
explicitly manipulating vhost_used_elem in zerocopy code. This will be
used to hide used_elem internals and simplify packed ring
implementation.

Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vhost/net.c   | 11 +++++------
 drivers/vhost/vhost.c | 12 ++++++++++--
 drivers/vhost/vhost.h |  5 +++++
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 3826f1f..30273ad 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -341,9 +341,10 @@ static void vhost_zerocopy_signal_used(struct vhost_net *net,
 	int j = 0;
 
 	for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
-		if (vq->heads[i].elem.len == VHOST_DMA_FAILED_LEN)
+		if (vhost_get_used_len(vq, &vq->heads[i]) ==
+		    VHOST_DMA_FAILED_LEN)
 			vhost_net_tx_err(net);
-		if (VHOST_DMA_IS_DONE(vq->heads[i].elem.len)) {
+		if (VHOST_DMA_IS_DONE(vhost_get_used_len(vq, &vq->heads[i]))) {
 			vq->heads[i].elem.len = VHOST_DMA_CLEAR_LEN;
 			++j;
 		} else
@@ -542,10 +543,8 @@ static void handle_tx(struct vhost_net *net)
 			struct ubuf_info *ubuf;
 			ubuf = nvq->ubuf_info + nvq->upend_idx;
 
-			vq->heads[nvq->upend_idx].elem.id =
-				cpu_to_vhost32(vq, used.elem.id);
-			vq->heads[nvq->upend_idx].elem.len =
-				VHOST_DMA_IN_PROGRESS;
+			vhost_set_used_len(vq, &used, VHOST_DMA_IN_PROGRESS);
+			vq->heads[nvq->upend_idx] = used;
 			ubuf->callback = vhost_zerocopy_callback;
 			ubuf->ctx = nvq->ubufs;
 			ubuf->desc = nvq->upend_idx;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index afd4119..2ef1859 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2064,11 +2064,19 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 }
 EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
 
-static void vhost_set_used_len(struct vhost_virtqueue *vq,
-			       struct vhost_used_elem *used, int len)
+void vhost_set_used_len(struct vhost_virtqueue *vq,
+			struct vhost_used_elem *used, int len)
 {
 	used->elem.len = cpu_to_vhost32(vq, len);
 }
+EXPORT_SYMBOL_GPL(vhost_set_used_len);
+
+int vhost_get_used_len(struct vhost_virtqueue *vq,
+		       struct vhost_used_elem *used)
+{
+	return vhost32_to_cpu(vq, used->elem.len);
+}
+EXPORT_SYMBOL_GPL(vhost_get_used_len);
 
 /* This is a multi-buffer version of vhost_get_desc, that works if
  *	vq has read descriptors only.
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 8dea44b..604821b 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -198,6 +198,11 @@ int vhost_get_bufs(struct vhost_virtqueue *vq,
 		   unsigned *log_num,
 		   unsigned int quota,
 		   s16 *count);
+void vhost_set_used_len(struct vhost_virtqueue *vq,
+			struct vhost_used_elem *used,
+			int len);
+int vhost_get_used_len(struct vhost_virtqueue *vq,
+		       struct vhost_used_elem *used);
 void vhost_discard_vq_desc(struct vhost_virtqueue *, int n);
 
 int vhost_vq_init_access(struct vhost_virtqueue *);
-- 
2.7.4

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox