Commit 77cffe23 authored by Tom Herbert's avatar Tom Herbert Committed by David S. Miller
Browse files

net: Clarification of CHECKSUM_UNNECESSARY 



This patch:
 - Clarifies the specific requirements of devices returning
   CHECKSUM_UNNECESSARY (comments in skbuff.h).
 - Adds csum_level field to skbuff. This is used to express how
   many checksums are covered by CHECKSUM_UNNECESSARY (stores n - 1).
   This replaces the overloading of skb->encapsulation, that field is
   is now only used to indicate inner headers are valid.
 - Change __skb_checksum_validate_needed to "consume" each checksum
   as indicated by csum_level as layers of the the packet are parsed.
 - Remove skb_pop_rcv_encapsulation, no longer needed in the new
   csum_level model.

Signed-off-by: default avatarTom Herbert <therbert@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent de20fe8e

drivers/net/vxlan.c

+0 −2
Original line number Diff line number Diff line
@@ -1158,8 +1158,6 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb) 
	if (!vs)

		goto drop;



	skb_pop_rcv_encapsulation(skb);



	vs->rcv(vs, skb, vxh->vx_vni);

	return 0;

include/linux/skbuff.h

+51 −23
Original line number Diff line number Diff line
@@ -47,11 +47,29 @@ 
 *

 *   The hardware you're dealing with doesn't calculate the full checksum

 *   (as in CHECKSUM_COMPLETE), but it does parse headers and verify checksums

 *   for specific protocols e.g. TCP/UDP/SCTP, then, for such packets it will

 *   set CHECKSUM_UNNECESSARY if their checksums are okay. skb->csum is still

 *   undefined in this case though. It is a bad option, but, unfortunately,

 *   nowadays most vendors do this. Apparently with the secret goal to sell

 *   you new devices, when you will add new protocol to your host, f.e. IPv6 8)

 *   for specific protocols. For such packets it will set CHECKSUM_UNNECESSARY

 *   if their checksums are okay. skb->csum is still undefined in this case

 *   though. It is a bad option, but, unfortunately, nowadays most vendors do

 *   this. Apparently with the secret goal to sell you new devices, when you

 *   will add new protocol to your host, f.e. IPv6 8)

 *

 *   CHECKSUM_UNNECESSARY is applicable to following protocols:

 *     TCP: IPv6 and IPv4.

 *     UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a

 *       zero UDP checksum for either IPv4 or IPv6, the networking stack

 *       may perform further validation in this case.

 *     GRE: only if the checksum is present in the header.

 *     SCTP: indicates the CRC in SCTP header has been validated.

 *

 *   skb->csum_level indicates the number of consecutive checksums found in

 *   the packet minus one that have been verified as CHECKSUM_UNNECESSARY.

 *   For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet

 *   and a device is able to verify the checksums for UDP (possibly zero),

 *   GRE (checksum flag is set), and TCP-- skb->csum_level would be set to

 *   two. If the device were only able to verify the UDP checksum and not

 *   GRE, either because it doesn't support GRE checksum of because GRE

 *   checksum is bad, skb->csum_level would be set to zero (TCP checksum is

 *   not considered in this case).

 *

 * CHECKSUM_COMPLETE:

 *
@@ -112,6 +130,9 @@ 
#define CHECKSUM_COMPLETE	2

#define CHECKSUM_PARTIAL	3



/* Maximum value in skb->csum_level */

#define SKB_MAX_CSUM_LEVEL	3



#define SKB_DATA_ALIGN(X)	ALIGN(X, SMP_CACHE_BYTES)

#define SKB_WITH_OVERHEAD(X)	\

	((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
@@ -571,11 +592,7 @@ struct sk_buff { 
	__u8			wifi_acked:1;

	__u8			no_fcs:1;

	__u8			head_frag:1;

	/* Encapsulation protocol and NIC drivers should use

	 * this flag to indicate to each other if the skb contains

	 * encapsulated packet or not and maybe use the inner packet

	 * headers if needed

	 */

	/* Indicates the inner headers are valid in the skbuff. */

	__u8			encapsulation:1;

	__u8			encap_hdr_csum:1;

	__u8			csum_valid:1;
@@ -599,7 +616,8 @@ struct sk_buff { 
	};



	kmemcheck_bitfield_begin(flags3);

	/* 16 bit hole */

	__u8			csum_level:2;

	/* 14 bit hole */

	kmemcheck_bitfield_end(flags3);



	__be16			inner_protocol;
@@ -1866,18 +1884,6 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) 
	return pskb_may_pull(skb, skb_network_offset(skb) + len);

}



static inline void skb_pop_rcv_encapsulation(struct sk_buff *skb)

{

	/* Only continue with checksum unnecessary if device indicated

	 * it is valid across encapsulation (skb->encapsulation was set).

	 */

	if (skb->ip_summed == CHECKSUM_UNNECESSARY && !skb->encapsulation)

		skb->ip_summed = CHECKSUM_NONE;



	skb->encapsulation = 0;

	skb->csum_valid = 0;

}



/*

 * CPUs often take a performance hit when accessing unaligned memory

 * locations. The actual performance hit varies, it can be small if the
@@ -2798,6 +2804,27 @@ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) 
	       0 : __skb_checksum_complete(skb);

}



static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb)

{

	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {

		if (skb->csum_level == 0)

			skb->ip_summed = CHECKSUM_NONE;

		else

			skb->csum_level--;

	}

}



static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)

{

	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {

		if (skb->csum_level < SKB_MAX_CSUM_LEVEL)

			skb->csum_level++;

	} else if (skb->ip_summed == CHECKSUM_NONE) {

		skb->ip_summed = CHECKSUM_UNNECESSARY;

		skb->csum_level = 0;

	}

}



/* Check if we need to perform checksum complete validation.

 *

 * Returns true if checksum complete is needed, false otherwise
@@ -2809,6 +2836,7 @@ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, 
{

	if (skb_csum_unnecessary(skb) || (zero_okay && !check)) {

		skb->csum_valid = 1;

		__skb_decr_checksum_unnecessary(skb);

		return false;

	}

net/ipv4/gre_demux.c

+0 −1
Original line number Diff line number Diff line
@@ -125,7 +125,6 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, 
			*csum_err = true;

			return -EINVAL;

		}

		skb_pop_rcv_encapsulation(skb);

		options++;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE