[PATCH 1/2] net: Allow skb_recycle_check to be done in stages

[PATCH 1/2] net: Allow skb_recycle_check to be done in stages

[Andy Fleming]

skb_recycle_check resets the skb if it's eligible for recycling.
However, there are times when a driver might want to optionally
manipulate the skb data with the skb before resetting the skb,
but after it has determined eligibility.  We do this by splitting the
eligibility check from the skb reset, creating two inline functions to
accomplish that task.

Signed-off-by: Andy Fleming <afleming@freescale.com>
---

I found this useful for a driver we're working on where the device can
do different things, depending on whether the skb is recycleable.

 include/linux/skbuff.h |   21 +++++++++++++++++++
 net/core/skbuff.c      |   51 ++++++++++++++++++++++++-----------------------
 2 files changed, 47 insertions(+), 25 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ac6b05a..6b35ca1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -525,6 +525,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 	return __alloc_skb(size, priority, 1, NUMA_NO_NODE);
 }
 
+extern void skb_recycle(struct sk_buff *skb);
 extern bool skb_recycle_check(struct sk_buff *skb, int skb_size);
 
 extern struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
@@ -2459,5 +2460,25 @@ static inline void skb_checksum_none_assert(struct sk_buff *skb)
 
 bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off);
 
+static inline bool skb_is_recycleable(struct sk_buff *skb, int skb_size)
+{
+	if (irqs_disabled())
+		return false;
+
+	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY)
+		return false;
+
+	if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
+		return false;
+
+	skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD);
+	if (skb_end_pointer(skb) - skb->head < skb_size)
+		return false;
+
+	if (skb_shared(skb) || skb_cloned(skb))
+		return false;
+
+	return true;
+}
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5b2c5f1..48bee84 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -475,6 +475,30 @@ void consume_skb(struct sk_buff *skb)
 EXPORT_SYMBOL(consume_skb);
 
 /**
+ * 	skb_recycle - clean up an skb for reuse
+ * 	@skb: buffer
+ *
+ * 	Recycles the skb to be reused as a receive buffer. This
+ * 	function does any necessary reference count dropping, and
+ * 	cleans up the skbuff as if it just came from __alloc_skb().
+ */
+void skb_recycle(struct sk_buff *skb)
+{
+	struct skb_shared_info *shinfo;
+
+	skb_release_head_state(skb);
+
+	shinfo = skb_shinfo(skb);
+	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+	atomic_set(&shinfo->dataref, 1);
+
+	memset(skb, 0, offsetof(struct sk_buff, tail));
+	skb->data = skb->head + NET_SKB_PAD;
+	skb_reset_tail_pointer(skb);
+}
+EXPORT_SYMBOL(skb_recycle);
+
+/**
  *	skb_recycle_check - check if skb can be reused for receive
  *	@skb: buffer
  *	@skb_size: minimum receive buffer size
@@ -488,33 +512,10 @@ EXPORT_SYMBOL(consume_skb);
  */
 bool skb_recycle_check(struct sk_buff *skb, int skb_size)
 {
-	struct skb_shared_info *shinfo;
-
-	if (irqs_disabled())
-		return false;
-
-	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY)
-		return false;
-
-	if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
-		return false;
-
-	skb_size = SKB_DATA_ALIGN(skb_size + NET_SKB_PAD);
-	if (skb_end_pointer(skb) - skb->head < skb_size)
-		return false;
-
-	if (skb_shared(skb) || skb_cloned(skb))
+	if (!skb_is_recycleable(skb, skb_size))
 		return false;
 
-	skb_release_head_state(skb);
-
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->data = skb->head + NET_SKB_PAD;
-	skb_reset_tail_pointer(skb);
+	skb_recycle(skb);
 
 	return true;
 }
-- 
1.7.3.4

[PATCH 2/2] phylib: Modify Vitesse RGMII skew settings

[Andy Fleming]

The Vitesse driver was using the RGMII_ID interface type to determine if
skew was necessary.  However, we want to move away from using that
interface type, as it's really a property of the board's PHY connection.
However, some boards depend on it, so we want to support it, while
allowing new boards to use the more flexible "fixups" approach.  To do
this, we extract the code which adds skew into its own function, and
call that function when RGMII_ID has been selected.

Another side-effect of this change is that if your PHY has skew set
already, it doesn't clear it.  This way, the fixup code can modify the
register without config_init then clearing it.

Signed-off-by: Andy Fleming <afleming@freescale.com>
---
 drivers/net/phy/vitesse.c |   34 ++++++++++++++++++++++------------
 1 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 5d8f6e1..0ec8e09 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -3,7 +3,7 @@
  *
  * Author: Kriston Carson
  *
- * Copyright (c) 2005 Freescale Semiconductor, Inc.
+ * Copyright (c) 2005, 2009 Freescale Semiconductor, Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -61,32 +61,42 @@ MODULE_DESCRIPTION("Vitesse PHY driver");
 MODULE_AUTHOR("Kriston Carson");
 MODULE_LICENSE("GPL");
 
-static int vsc824x_config_init(struct phy_device *phydev)
+int vsc824x_add_skew(struct phy_device *phydev)
 {
-	int extcon;
 	int err;
-
-	err = phy_write(phydev, MII_VSC8244_AUX_CONSTAT,
-			MII_VSC8244_AUXCONSTAT_INIT);
-	if (err < 0)
-		return err;
+	int extcon;
 
 	extcon = phy_read(phydev, MII_VSC8244_EXT_CON1);
 
 	if (extcon < 0)
-		return err;
+		return extcon;
 
 	extcon &= ~(MII_VSC8244_EXTCON1_TX_SKEW_MASK |
 			MII_VSC8244_EXTCON1_RX_SKEW_MASK);
 
-	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
-		extcon |= (MII_VSC8244_EXTCON1_TX_SKEW |
-				MII_VSC8244_EXTCON1_RX_SKEW);
+	extcon |= (MII_VSC8244_EXTCON1_TX_SKEW |
+			MII_VSC8244_EXTCON1_RX_SKEW);
 
 	err = phy_write(phydev, MII_VSC8244_EXT_CON1, extcon);
 
 	return err;
 }
+EXPORT_SYMBOL(vsc824x_add_skew);
+
+static int vsc824x_config_init(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, MII_VSC8244_AUX_CONSTAT,
+			MII_VSC8244_AUXCONSTAT_INIT);
+	if (err < 0)
+		return err;
+
+	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)
+		err = vsc824x_add_skew(phydev);
+
+	return err;
+}
 
 static int vsc824x_ack_interrupt(struct phy_device *phydev)
 {
-- 
1.7.3.4

Re: [PATCH 1/2] net: Allow skb_recycle_check to be done in stages

[David Daney]

On 10/13/2011 07:33 AM, Andy Fleming wrote:
> skb_recycle_check resets the skb if it's eligible for recycling.
> However, there are times when a driver might want to optionally
> manipulate the skb data with the skb before resetting the skb,
> but after it has determined eligibility.  We do this by splitting the
> eligibility check from the skb reset, creating two inline functions to
> accomplish that task.
>
> Signed-off-by: Andy Fleming<afleming@freescale.com>

Acked-by: David Daney <david.daney@cavium.com>

I need this for my (Octeon) Ethernet driver as well.  Currently we have 
an ad hoc driver local implementation of this, but I would like to use 
this core code if possible.




> ---
>
> I found this useful for a driver we're working on where the device can
> do different things, depending on whether the skb is recycleable.
>
>   include/linux/skbuff.h |   21 +++++++++++++++++++
>   net/core/skbuff.c      |   51 ++++++++++++++++++++++++-----------------------
>   2 files changed, 47 insertions(+), 25 deletions(-)
>

[...]

Re: [PATCH 1/2] net: Allow skb_recycle_check to be done in stages

[David Miller]

From: Andy Fleming <afleming@freescale.com>
Date: Thu, 13 Oct 2011 09:33:54 -0500

> skb_recycle_check resets the skb if it's eligible for recycling.
> However, there are times when a driver might want to optionally
> manipulate the skb data with the skb before resetting the skb,
> but after it has determined eligibility.  We do this by splitting the
> eligibility check from the skb reset, creating two inline functions to
> accomplish that task.
> 
> Signed-off-by: Andy Fleming <afleming@freescale.com>

Applied.

Re: [PATCH 2/2] phylib: Modify Vitesse RGMII skew settings

[David Miller]

From: Andy Fleming <afleming@freescale.com>
Date: Thu, 13 Oct 2011 09:33:55 -0500

> The Vitesse driver was using the RGMII_ID interface type to determine if
> skew was necessary.  However, we want to move away from using that
> interface type, as it's really a property of the board's PHY connection.
> However, some boards depend on it, so we want to support it, while
> allowing new boards to use the more flexible "fixups" approach.  To do
> this, we extract the code which adds skew into its own function, and
> call that function when RGMII_ID has been selected.
> 
> Another side-effect of this change is that if your PHY has skew set
> already, it doesn't clear it.  This way, the fixup code can modify the
> register without config_init then clearing it.
> 
> Signed-off-by: Andy Fleming <afleming@freescale.com>

Applied.