This is a patch that enables RSS functionality for GTP packets using ethtool.
A user can include TEID and make RSS work for GTP-U over IPv4 by doing the
following:`ethtool -N ens3 rx-flow-hash gtpu4 sde`
In addition to gtpu(4|6), we now support gtpc(4|6),gtpc(4|6)t,gtpu(4|6)e,
gtpu(4|6)u, and gtpu(4|6)d.
gtpc(4|6): Used for GTP-C in IPv4 and IPv6, where the GTP header format does
not include a TEID.
gtpc(4|6)t: Used for GTP-C in IPv4 and IPv6, with a GTP header format that
includes a TEID.
gtpu(4|6): Used for GTP-U in both IPv4 and IPv6 scenarios.
gtpu(4|6)e: Used for GTP-U with extended headers in both IPv4 and IPv6.
gtpu(4|6)u: Used when the PSC (PDU session container) in the GTP-U extended
header includes Uplink, applicable to both IPv4 and IPv6.
gtpu(4|6)d: Used when the PSC in the GTP-U extended header includes Downlink,
for both IPv4 and IPv6.
GTP generates a flow that includes an ID called TEID to identify the tunnel.
This tunnel is created for each UE (User Equipment).By performing RSS based on
this flow, it is possible to apply RSS for each communication unit from the UE.
Without this, RSS would only be effective within the range of IP addresses. For
instance, the PGW can only perform RSS within the IP range of the SGW.
Problematic from a load distribution perspective, especially if there's a bias
in the terminals connected to a particular base station.This case can be
solved by using this patch.
Signed-off-by: Takeru Hayasaka <[email protected]>
Reviewed-by: Marcin Szycik <[email protected]>
---
v2->v3: Based on Harald-san's review, I added documentation and comments to
ethtool.h and ice.rst.
v3->v4: Based on Marcin-san's review, I added the missing code for GTPC and
GTPC_TEID, and revised the documentation and comments.
v4->v5: Based on Marcin-san's review, I fixed rename and wrong code regarding
GTPC
v5->v6: Based on Marcin-san's review, Undoing the addition of unnecessary
blank lines.Minor fixes.
v6->v7 Based on Jakub-san's review, Split the patch.
v7->v8: There are no code changes. I've resent the patch, including Marcin-san's
patch, because PatchWork did not interpret the patch correctly.Simon-san told
me. Thanks.
include/uapi/linux/ethtool.h | 48 ++++++++++++++++++++++++++++++++++++
1 file changed, 48 insertions(+)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 06ef6b78b7de..11fc18988bc2 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2023,6 +2023,53 @@ static inline int ethtool_validate_duplex(__u8 duplex)
#define IPV4_FLOW 0x10 /* hash only */
#define IPV6_FLOW 0x11 /* hash only */
#define ETHER_FLOW 0x12 /* spec only (ether_spec) */
+
+/* Used for GTP-U IPv4 and IPv6.
+ * The format of GTP packets only includes
+ * elements such as TEID and GTP version.
+ * It is primarily intended for data communication of the UE.
+ */
+#define GTPU_V4_FLOW 0x13 /* hash only */
+#define GTPU_V6_FLOW 0x14 /* hash only */
+
+/* Use for GTP-C IPv4 and v6.
+ * The format of these GTP packets does not include TEID.
+ * Primarily expected to be used for communication
+ * to create sessions for UE data communication,
+ * commonly referred to as CSR (Create Session Request).
+ */
+#define GTPC_V4_FLOW 0x15 /* hash only */
+#define GTPC_V6_FLOW 0x16 /* hash only */
+
+/* Use for GTP-C IPv4 and v6.
+ * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
+ * After session creation, it becomes this packet.
+ * This is mainly used for requests to realize UE handover.
+ */
+#define GTPC_TEID_V4_FLOW 0x17 /* hash only */
+#define GTPC_TEID_V6_FLOW 0x18 /* hash only */
+
+/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
+ * The format of these GTP packets includes TEID and QFI.
+ * In 5G communication using UPF (User Plane Function),
+ * data communication with this extended header is performed.
+ */
+#define GTPU_EH_V4_FLOW 0x19 /* hash only */
+#define GTPU_EH_V6_FLOW 0x1a /* hash only */
+
+/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
+ * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
+ * UL/DL included in the PSC.
+ * There are differences in the data included based on Downlink/Uplink,
+ * and can be used to distinguish packets.
+ * The functions described so far are useful when you want to
+ * handle communication from the mobile network in UPF, PGW, etc.
+ */
+#define GTPU_UL_V4_FLOW 0x1b /* hash only */
+#define GTPU_UL_V6_FLOW 0x1c /* hash only */
+#define GTPU_DL_V4_FLOW 0x1d /* hash only */
+#define GTPU_DL_V6_FLOW 0x1e /* hash only */
+
/* Flag to enable additional fields in struct ethtool_rx_flow_spec */
#define FLOW_EXT 0x80000000
#define FLOW_MAC_EXT 0x40000000
@@ -2037,6 +2084,7 @@ static inline int ethtool_validate_duplex(__u8 duplex)
#define RXH_IP_DST (1 << 5)
#define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */
#define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */
+#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */
#define RXH_DISCARD (1 << 31)
#define RX_CLS_FLOW_DISC 0xffffffffffffffffULL
--
2.34.1
Following the addition of new GTP RSS hash options to ethtool.h, this patch
implements the corresponding RSS settings for GTP packets in the Intel ice
driver. It enables users to configure RSS for GTP-U and GTP-C traffic over IPv4
and IPv6, utilizing the newly defined hash options.
The implementation covers the handling of gtpu(4|6), gtpc(4|6), gtpc(4|6)t,
gtpu(4|6)e, gtpu(4|6)u, and gtpu(4|6)d traffic, providing enhanced load
distribution for GTP traffic across multiple processing units.
Signed-off-by: Takeru Hayasaka <[email protected]>
Reviewed-by: Marcin Szycik <[email protected]>
---
.../device_drivers/ethernet/intel/ice.rst | 21 ++++-
drivers/net/ethernet/intel/ice/ice_ethtool.c | 82 +++++++++++++++++++
drivers/net/ethernet/intel/ice/ice_flow.h | 31 +++++--
drivers/net/ethernet/intel/ice/ice_lib.c | 37 +++++++++
4 files changed, 162 insertions(+), 9 deletions(-)
diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst
index 5038e54586af..934752f675ba 100644
--- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst
+++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst
@@ -368,15 +368,28 @@ more options for Receive Side Scaling (RSS) hash byte configuration.
# ethtool -N <ethX> rx-flow-hash <type> <option>
Where <type> is:
- tcp4 signifying TCP over IPv4
- udp4 signifying UDP over IPv4
- tcp6 signifying TCP over IPv6
- udp6 signifying UDP over IPv6
+ tcp4 signifying TCP over IPv4
+ udp4 signifying UDP over IPv4
+ gtpc4 signifying GTP-C over IPv4
+ gtpc4t signifying GTP-C (include TEID) over IPv4
+ gtpu4 signifying GTP-U over IPV4
+ gtpu4e signifying GTP-U and Extension Header over IPV4
+ gtpu4u signifying GTP-U PSC Uplink over IPV4
+ gtpu4d signifying GTP-U PSC Downlink over IPV4
+ tcp6 signifying TCP over IPv6
+ udp6 signifying UDP over IPv6
+ gtpc6 signifying GTP-C over IPv6
+ gtpc6t signifying GTP-C (include TEID) over IPv6
+ gtpu6 signifying GTP-U over IPV6
+ gtpu6e signifying GTP-U and Extension Header over IPV6
+ gtpu6u signifying GTP-U PSC Uplink over IPV6
+ gtpu6d signifying GTP-U PSC Downlink over IPV6
And <option> is one or more of:
s Hash on the IP source address of the Rx packet.
d Hash on the IP destination address of the Rx packet.
f Hash on bytes 0 and 1 of the Layer 4 header of the Rx packet.
n Hash on bytes 2 and 3 of the Layer 4 header of the Rx packet.
+ e Hash on GTP Packet on TEID (4bytes) of the Rx packet.
Accelerated Receive Flow Steering (aRFS)
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index a19b06f18e40..d0e05032f464 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -2486,6 +2486,24 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
case SCTP_V4_FLOW:
hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4;
break;
+ case GTPU_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case GTPC_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case GTPC_TEID_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case GTPU_EH_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case GTPU_UL_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4;
+ break;
+ case GTPU_DL_V4_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4;
+ break;
case TCP_V6_FLOW:
hdrs |= ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6;
break;
@@ -2495,6 +2513,24 @@ static u32 ice_parse_hdrs(struct ethtool_rxnfc *nfc)
case SCTP_V6_FLOW:
hdrs |= ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV6;
break;
+ case GTPU_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case GTPC_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case GTPC_TEID_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case GTPU_EH_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case GTPU_UL_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6;
+ break;
+ case GTPU_DL_V6_FLOW:
+ hdrs |= ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6;
+ break;
default:
break;
}
@@ -2518,6 +2554,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
case TCP_V4_FLOW:
case UDP_V4_FLOW:
case SCTP_V4_FLOW:
+ case GTPU_V4_FLOW:
+ case GTPC_V4_FLOW:
+ case GTPC_TEID_V4_FLOW:
+ case GTPU_EH_V4_FLOW:
+ case GTPU_UL_V4_FLOW:
+ case GTPU_DL_V4_FLOW:
if (nfc->data & RXH_IP_SRC)
hfld |= ICE_FLOW_HASH_FLD_IPV4_SA;
if (nfc->data & RXH_IP_DST)
@@ -2526,6 +2568,12 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
case TCP_V6_FLOW:
case UDP_V6_FLOW:
case SCTP_V6_FLOW:
+ case GTPU_V6_FLOW:
+ case GTPC_V6_FLOW:
+ case GTPC_TEID_V6_FLOW:
+ case GTPU_EH_V6_FLOW:
+ case GTPU_UL_V6_FLOW:
+ case GTPU_DL_V6_FLOW:
if (nfc->data & RXH_IP_SRC)
hfld |= ICE_FLOW_HASH_FLD_IPV6_SA;
if (nfc->data & RXH_IP_DST)
@@ -2564,6 +2612,33 @@ static u64 ice_parse_hash_flds(struct ethtool_rxnfc *nfc, bool symm)
}
}
+ if (nfc->data & RXH_GTP_TEID) {
+ switch (nfc->flow_type) {
+ case GTPC_TEID_V4_FLOW:
+ case GTPC_TEID_V6_FLOW:
+ hfld |= ICE_FLOW_HASH_FLD_GTPC_TEID;
+ break;
+ case GTPU_V4_FLOW:
+ case GTPU_V6_FLOW:
+ hfld |= ICE_FLOW_HASH_FLD_GTPU_IP_TEID;
+ break;
+ case GTPU_EH_V4_FLOW:
+ case GTPU_EH_V6_FLOW:
+ hfld |= ICE_FLOW_HASH_FLD_GTPU_EH_TEID;
+ break;
+ case GTPU_UL_V4_FLOW:
+ case GTPU_UL_V6_FLOW:
+ hfld |= ICE_FLOW_HASH_FLD_GTPU_UP_TEID;
+ break;
+ case GTPU_DL_V4_FLOW:
+ case GTPU_DL_V6_FLOW:
+ hfld |= ICE_FLOW_HASH_FLD_GTPU_DWN_TEID;
+ break;
+ default:
+ break;
+ }
+ }
+
return hfld;
}
@@ -2676,6 +2751,13 @@ ice_get_rss_hash_opt(struct ice_vsi *vsi, struct ethtool_rxnfc *nfc)
hash_flds & ICE_FLOW_HASH_FLD_UDP_DST_PORT ||
hash_flds & ICE_FLOW_HASH_FLD_SCTP_DST_PORT)
nfc->data |= (u64)RXH_L4_B_2_3;
+
+ if (hash_flds & ICE_FLOW_HASH_FLD_GTPC_TEID ||
+ hash_flds & ICE_FLOW_HASH_FLD_GTPU_IP_TEID ||
+ hash_flds & ICE_FLOW_HASH_FLD_GTPU_EH_TEID ||
+ hash_flds & ICE_FLOW_HASH_FLD_GTPU_UP_TEID ||
+ hash_flds & ICE_FLOW_HASH_FLD_GTPU_DWN_TEID)
+ nfc->data |= (u64)RXH_GTP_TEID;
}
/**
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index ff82915ab497..2fd2e0cb483d 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -37,13 +37,13 @@
#define ICE_HASH_SCTP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT)
#define ICE_HASH_SCTP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT)
-#define ICE_FLOW_HASH_GTP_TEID \
+#define ICE_FLOW_HASH_GTP_C_TEID \
(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID))
-#define ICE_FLOW_HASH_GTP_IPV4_TEID \
- (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID)
-#define ICE_FLOW_HASH_GTP_IPV6_TEID \
- (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID)
+#define ICE_FLOW_HASH_GTP_C_IPV4_TEID \
+ (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_C_TEID)
+#define ICE_FLOW_HASH_GTP_C_IPV6_TEID \
+ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_C_TEID)
#define ICE_FLOW_HASH_GTP_U_TEID \
(BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID))
@@ -66,6 +66,20 @@
(ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_EH_TEID | \
ICE_FLOW_HASH_GTP_U_EH_QFI)
+#define ICE_FLOW_HASH_GTP_U_UP \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID))
+#define ICE_FLOW_HASH_GTP_U_DWN \
+ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID))
+
+#define ICE_FLOW_HASH_GTP_U_IPV4_UP \
+ (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_UP)
+#define ICE_FLOW_HASH_GTP_U_IPV6_UP \
+ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_UP)
+#define ICE_FLOW_HASH_GTP_U_IPV4_DWN \
+ (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_U_DWN)
+#define ICE_FLOW_HASH_GTP_U_IPV6_DWN \
+ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_U_DWN)
+
#define ICE_FLOW_HASH_PPPOE_SESS_ID \
(BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID))
@@ -242,6 +256,13 @@ enum ice_flow_field {
#define ICE_FLOW_HASH_FLD_SCTP_DST_PORT \
BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT)
+#define ICE_FLOW_HASH_FLD_GTPC_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)
+#define ICE_FLOW_HASH_FLD_GTPU_IP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_IP_TEID)
+#define ICE_FLOW_HASH_FLD_GTPU_EH_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_EH_TEID)
+#define ICE_FLOW_HASH_FLD_GTPU_UP_TEID BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_UP_TEID)
+#define ICE_FLOW_HASH_FLD_GTPU_DWN_TEID \
+ BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID)
+
/* Flow headers and fields for AVF support */
enum ice_flow_avf_hdr_field {
/* Values 0 - 28 are reserved for future use */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 9be724291ef8..3c4282019570 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1618,6 +1618,25 @@ static const struct ice_rss_hash_cfg default_rss_cfgs[] = {
*/
{ICE_FLOW_SEG_HDR_SCTP | ICE_FLOW_SEG_HDR_IPV4,
ICE_HASH_SCTP_IPV4, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpc4 with input set IPv4 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_IPV4, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpc4t with input set IPv4 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_GTP_C_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu4 with input set IPv4 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_GTP_U_IPV4_TEID, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu4e with input set IPv4 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_GTP_U_IPV4_EH, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu4u with input set IPv4 src/dst */
+ { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_GTP_U_IPV4_UP, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu4d with input set IPv4 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV4,
+ ICE_FLOW_HASH_GTP_U_IPV4_DWN, ICE_RSS_OUTER_HEADERS, false},
+
/* configure RSS for tcp6 with input set IPv6 src/dst, TCP src/dst */
{ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_IPV6,
ICE_HASH_TCP_IPV6, ICE_RSS_ANY_HEADERS, false},
@@ -1632,6 +1651,24 @@ static const struct ice_rss_hash_cfg default_rss_cfgs[] = {
/* configure RSS for IPSEC ESP SPI with input set MAC_IPV4_SPI */
{ICE_FLOW_SEG_HDR_ESP,
ICE_FLOW_HASH_ESP_SPI, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpc6 with input set IPv6 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPC | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_IPV6, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpc6t with input set IPv6 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPC_TEID | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_GTP_C_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu6 with input set IPv6 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_IP | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_GTP_U_IPV6_TEID, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu6e with input set IPv6 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_EH | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_GTP_U_IPV6_EH, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu6u with input set IPv6 src/dst */
+ { ICE_FLOW_SEG_HDR_GTPU_UP | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_GTP_U_IPV6_UP, ICE_RSS_OUTER_HEADERS, false},
+ /* configure RSS for gtpu6d with input set IPv6 src/dst */
+ {ICE_FLOW_SEG_HDR_GTPU_DWN | ICE_FLOW_SEG_HDR_IPV6,
+ ICE_FLOW_HASH_GTP_U_IPV6_DWN, ICE_RSS_OUTER_HEADERS, false},
};
/**
--
2.34.1
Hi Jakub-san
As previously advised, the patch has been divided.
I apologize for the inconvenience, but I would appreciate it if you
could take the time to review the patch.
I understand you may be busy, but your confirmation would be greatly
appreciated.
Thanks
Takeru
2024年2月12日(月) 11:04 Takeru Hayasaka <[email protected]>:
>
> This is a patch that enables RSS functionality for GTP packets using ethtool.
>
> A user can include TEID and make RSS work for GTP-U over IPv4 by doing the
> following:`ethtool -N ens3 rx-flow-hash gtpu4 sde`
>
> In addition to gtpu(4|6), we now support gtpc(4|6),gtpc(4|6)t,gtpu(4|6)e,
> gtpu(4|6)u, and gtpu(4|6)d.
>
> gtpc(4|6): Used for GTP-C in IPv4 and IPv6, where the GTP header format does
> not include a TEID.
> gtpc(4|6)t: Used for GTP-C in IPv4 and IPv6, with a GTP header format that
> includes a TEID.
> gtpu(4|6): Used for GTP-U in both IPv4 and IPv6 scenarios.
> gtpu(4|6)e: Used for GTP-U with extended headers in both IPv4 and IPv6.
> gtpu(4|6)u: Used when the PSC (PDU session container) in the GTP-U extended
> header includes Uplink, applicable to both IPv4 and IPv6.
> gtpu(4|6)d: Used when the PSC in the GTP-U extended header includes Downlink,
> for both IPv4 and IPv6.
>
> GTP generates a flow that includes an ID called TEID to identify the tunnel.
> This tunnel is created for each UE (User Equipment).By performing RSS based on
> this flow, it is possible to apply RSS for each communication unit from the UE.
> Without this, RSS would only be effective within the range of IP addresses. For
> instance, the PGW can only perform RSS within the IP range of the SGW.
> Problematic from a load distribution perspective, especially if there's a bias
> in the terminals connected to a particular base station.This case can be
> solved by using this patch.
>
> Signed-off-by: Takeru Hayasaka <[email protected]>
> Reviewed-by: Marcin Szycik <[email protected]>
> ---
> v2->v3: Based on Harald-san's review, I added documentation and comments to
> ethtool.h and ice.rst.
> v3->v4: Based on Marcin-san's review, I added the missing code for GTPC and
> GTPC_TEID, and revised the documentation and comments.
> v4->v5: Based on Marcin-san's review, I fixed rename and wrong code regarding
> GTPC
> v5->v6: Based on Marcin-san's review, Undoing the addition of unnecessary
> blank lines.Minor fixes.
> v6->v7 Based on Jakub-san's review, Split the patch.
> v7->v8: There are no code changes. I've resent the patch, including Marcin-san's
> patch, because PatchWork did not interpret the patch correctly.Simon-san told
> me. Thanks.
> include/uapi/linux/ethtool.h | 48 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 48 insertions(+)
>
> diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
> index 06ef6b78b7de..11fc18988bc2 100644
> --- a/include/uapi/linux/ethtool.h
> +++ b/include/uapi/linux/ethtool.h
> @@ -2023,6 +2023,53 @@ static inline int ethtool_validate_duplex(__u8 duplex)
> #define IPV4_FLOW 0x10 /* hash only */
> #define IPV6_FLOW 0x11 /* hash only */
> #define ETHER_FLOW 0x12 /* spec only (ether_spec) */
> +
> +/* Used for GTP-U IPv4 and IPv6.
> + * The format of GTP packets only includes
> + * elements such as TEID and GTP version.
> + * It is primarily intended for data communication of the UE.
> + */
> +#define GTPU_V4_FLOW 0x13 /* hash only */
> +#define GTPU_V6_FLOW 0x14 /* hash only */
> +
> +/* Use for GTP-C IPv4 and v6.
> + * The format of these GTP packets does not include TEID.
> + * Primarily expected to be used for communication
> + * to create sessions for UE data communication,
> + * commonly referred to as CSR (Create Session Request).
> + */
> +#define GTPC_V4_FLOW 0x15 /* hash only */
> +#define GTPC_V6_FLOW 0x16 /* hash only */
> +
> +/* Use for GTP-C IPv4 and v6.
> + * Unlike GTPC_V4_FLOW, the format of these GTP packets includes TEID.
> + * After session creation, it becomes this packet.
> + * This is mainly used for requests to realize UE handover.
> + */
> +#define GTPC_TEID_V4_FLOW 0x17 /* hash only */
> +#define GTPC_TEID_V6_FLOW 0x18 /* hash only */
> +
> +/* Use for GTP-U and extended headers for the PSC (PDU Session Container).
> + * The format of these GTP packets includes TEID and QFI.
> + * In 5G communication using UPF (User Plane Function),
> + * data communication with this extended header is performed.
> + */
> +#define GTPU_EH_V4_FLOW 0x19 /* hash only */
> +#define GTPU_EH_V6_FLOW 0x1a /* hash only */
> +
> +/* Use for GTP-U IPv4 and v6 PSC (PDU Session Container) extended headers.
> + * This differs from GTPU_EH_V(4|6)_FLOW in that it is distinguished by
> + * UL/DL included in the PSC.
> + * There are differences in the data included based on Downlink/Uplink,
> + * and can be used to distinguish packets.
> + * The functions described so far are useful when you want to
> + * handle communication from the mobile network in UPF, PGW, etc.
> + */
> +#define GTPU_UL_V4_FLOW 0x1b /* hash only */
> +#define GTPU_UL_V6_FLOW 0x1c /* hash only */
> +#define GTPU_DL_V4_FLOW 0x1d /* hash only */
> +#define GTPU_DL_V6_FLOW 0x1e /* hash only */
> +
> /* Flag to enable additional fields in struct ethtool_rx_flow_spec */
> #define FLOW_EXT 0x80000000
> #define FLOW_MAC_EXT 0x40000000
> @@ -2037,6 +2084,7 @@ static inline int ethtool_validate_duplex(__u8 duplex)
> #define RXH_IP_DST (1 << 5)
> #define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */
> #define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */
> +#define RXH_GTP_TEID (1 << 8) /* teid in case of GTP */
> #define RXH_DISCARD (1 << 31)
>
> #define RX_CLS_FLOW_DISC 0xffffffffffffffffULL
> --
> 2.34.1
>
Hi,
On Thu, 2024-02-15 at 17:44 +0900, Takeru Hayasaka wrote:
> As previously advised, the patch has been divided.
> I apologize for the inconvenience, but I would appreciate it if you
> could take the time to review the patch.
> I understand you may be busy, but your confirmation would be greatly
> appreciated.
The series LGTM. I *think* the series should go first in the intel
tree, so it can be tested on the relevant H/W. @Tony: do you agree?
Thanks,
Paolo
On 2/15/24 2:26 AM, Paolo Abeni <[email protected]> wrote:
> Hi,
>
> On Thu, 2024-02-15 at 17:44 +0900, Takeru Hayasaka wrote:
> > As previously advised, the patch has been divided.
> > I apologize for the inconvenience, but I would appreciate it if you
> > could take the time to review the patch.
> > I understand you may be busy, but your confirmation would be greatly
> > appreciated.
>
> The series LGTM. I *think* the series should go first in the intel
> tree, so it can be tested on the relevant H/W. @Tony: do you agree?
I agree. I think it would make sense for this to go through IWL.
Thanks,
Tony
> Thanks,
>
> Paolo
>
>
Hi Tony-san and Paolo-san!
> > The series LGTM. I *think* the series should go first in the intel
Thank you both for picking up on the topic!
> I agree. I think it would make sense for this to go through IWL.
I understand. So, it means that it will go through the IWL branch and
then through net-next.
Is there any assistance I can provide to facilitate this process?
Thanks,
Takeru
On 2/16/2024 6:14 AM, Takeru Hayasaka wrote:
> Hi Tony-san and Paolo-san!
>
>>> The series LGTM. I *think* the series should go first in the intel
>
> Thank you both for picking up on the topic!
>
>> I agree. I think it would make sense for this to go through IWL.
>
> I understand. So, it means that it will go through the IWL branch and
> then through net-next.
Yes, it will go through next-queue/dev-queue and then to net-next
https://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git/
> Is there any assistance I can provide to facilitate this process?
Everything is good for now. If we have issues or questions we will reach
out to you.
Thanks,
Tony
> Thanks,
> Takeru
Hi Tony-san
Thanks for your reply!
> Everything is good for now. If we have issues or questions we will reach
> out to you.
Okay. Let me know if there's anything I can help with:)
Thanks
Takeru
> -----Original Message-----
> From: Intel-wired-lan <[email protected]> On Behalf Of Takeru Hayasaka
> Sent: Monday, February 12, 2024 7:34 AM
> To: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>
> Cc: [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; Takeru Hayasaka <hayatake396@gmailcom>; [email protected]; [email protected]
> Subject: [Intel-wired-lan] [PATCH net-next v8 2/2] ice: Implement RSS settings for GTP using ethtool
>
> Following the addition of new GTP RSS hash options to ethtool.h, this patch
> implements the corresponding RSS settings for GTP packets in the Intel ice
> driver. It enables users to configure RSS for GTP-U and GTP-C traffic over IPv4
> and IPv6, utilizing the newly defined hash options.
>
> The implementation covers the handling of gtpu(4|6), gtpc(4|6), gtpc(4|6)t,
> gtpu(4|6)e, gtpu(4|6)u, and gtpu(4|6)d traffic, providing enhanced load
> distribution for GTP traffic across multiple processing units.
>
> Signed-off-by: Takeru Hayasaka <[email protected]>
> Reviewed-by: Marcin Szycik <[email protected]>
> ---
> .../device_drivers/ethernet/intel/ice.rst | 21 ++++-
> drivers/net/ethernet/intel/ice/ice_ethtool.c | 82 +++++++++++++++++++
> drivers/net/ethernet/intel/ice/ice_flow.h | 31 +++++--
> drivers/net/ethernet/intel/ice/ice_lib.c | 37 +++++++++
> 4 files changed, 162 insertions(+), 9 deletions(-)
>
Tested-by: Pucha Himasekhar Reddy <[email protected]> (A Contingent worker at Intel)
> -----Original Message-----
> From: Intel-wired-lan <[email protected]> On Behalf Of Takeru Hayasaka
> Sent: Monday, February 12, 2024 7:34 AM
> To: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>
> Cc: [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; Takeru Hayasaka <hayatake396@gmailcom>; [email protected]; [email protected]
> Subject: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
>
> This is a patch that enables RSS functionality for GTP packets using ethtool.
>
>A user can include TEID and make RSS work for GTP-U over IPv4 by doing the
>following:`ethtool -N ens3 rx-flow-hash gtpu4 sde`
>
> In addition to gtpu(4|6), we now support gtpc(4|6),gtpc(4|6)t,gtpu(4|6)e,
> gtpu(4|6)u, and gtpu(4|6)d.
>
> gtpc(4|6): Used for GTP-C in IPv4 and IPv6, where the GTP header format does
> not include a TEID.
> gtpc(4|6)t: Used for GTP-C in IPv4 and IPv6, with a GTP header format that
> includes a TEID.
> gtpu(4|6): Used for GTP-U in both IPv4 and IPv6 scenarios.
> gtpu(4|6)e: Used for GTP-U with extended headers in both IPv4 and IPv6.
> gtpu(4|6)u: Used when the PSC (PDU session container) in the GTP-U extended
> header includes Uplink, applicable to both IPv4 and IPv6.
> gtpu(4|6)d: Used when the PSC in the GTP-U extended header includes Downlink,
> for both IPv4 and IPv6.
>
> GTP generates a flow that includes an ID called TEID to identify the tunnel.
> This tunnel is created for each UE (User Equipment).By performing RSS based on
> this flow, it is possible to apply RSS for each communication unit from the UE.
> Without this, RSS would only be effective within the range of IP addresses. For
> instance, the PGW can only perform RSS within the IP range of the SGW.
> Problematic from a load distribution perspective, especially if there's a bias
> in the terminals connected to a particular base station.This case can be
> solved by using this patch.
>
> Signed-off-by: Takeru Hayasaka <[email protected]>
> Reviewed-by: Marcin Szycik <[email protected]>
> ---
> v2->v3: Based on Harald-san's review, I added documentation and comments to
> ethtool.h and ice.rst.
> v3->v4: Based on Marcin-san's review, I added the missing code for GTPC and
> GTPC_TEID, and revised the documentation and comments.
> v4->v5: Based on Marcin-san's review, I fixed rename and wrong code regarding
> GTPC
> v5->v6: Based on Marcin-san's review, Undoing the addition of unnecessary
> blank lines.Minor fixes.
> v6->v7 Based on Jakub-san's review, Split the patch.
> v7->v8: There are no code changes. I've resent the patch, including Marcin-san's
> patch, because PatchWork did not interpret the patch correctly.Simon-san told
> me. Thanks.
> include/uapi/linux/ethtool.h | 48 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 48 insertions(+)
>
Hi Takeru Hayasaka,
Functionality wise its working fine. But the ethtool part (tab complete doesn't show GTP)
Please find below logs.
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash
ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash
ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash gtpu6e sdfn
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash gtpu6u sdfn
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash gtpu4u sdfn
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash gtpu4d sdfn
[root@os-delivery ~]# ethtool -N eth4 rx-flow-hash gtpu6d sdfn
Hi Himasekhar Reddy-san
> Functionality wise its working fine. But the ethtool part (tab complete doesn't show GTP)
I forgot to add the tab completion feature! Thank you for the good
points. I've added it again in this version's patch.
https://lore.kernel.org/all/[email protected]/
Takeru
>-----Original Message-----
> From: Takeru Hayasaka <[email protected]>
> Sent: Tuesday, March 5, 2024 9:12 AM
> To: Pucha, HimasekharX Reddy <[email protected]>
> Cc: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; [email protected]; [email protected]
> Subject: Re: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
>
> Hi Himasekhar Reddy-san
>
> > Functionality wise its working fine. But the ethtool part (tab complete doesn't show GTP)
>
> I forgot to add the tab completion feature! Thank you for the good
> points. I've added it again in this version's patch.
> https://lore.kernel.org/all/[email protected]/
>
> Takeru
>
After added the above v4 patch able to to see tab completion for flow-type but not rx-flow-hash. Please find below logs.
# ethtool -N eth4 rx-flow-hash
ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
# ethtool -N eth4 rx-flow-hash
ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
# ethtool -N eth4 flow-type
ah4 esp4 ether gtpc4t gtpc6t gtpu4d gtpu4u gtpu6d gtpu6u ip6 sctp6 tcp6 udp6
ah6 esp6 gtpc4 gtpc6 gtpu4 gtpu4e gtpu6 gtpu6e ip4 sctp4 tcp4 udp4
Hi Himasekhar Reddy-san
> After added the above v4 patch able to to see tab completion for flow-type but not rx-flow-hash. Please find below logs.
Sorry. I submitted a code with the conditions reversed. I have
resubmitted it, so could you please check it again?
https://lore.kernel.org/all/[email protected]/
Takeru
2024年3月5日(火) 13:28 Pucha, HimasekharX Reddy <[email protected]>:
>
> >-----Original Message-----
> > From: Takeru Hayasaka <[email protected]>
> > Sent: Tuesday, March 5, 2024 9:12 AM
> > To: Pucha, HimasekharX Reddy <[email protected]>
> > Cc: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; [email protected]; [email protected]
> > Subject: Re: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
> >
> > Hi Himasekhar Reddy-san
> >
> > > Functionality wise its working fine. But the ethtool part (tab complete doesn't show GTP)
> >
> > I forgot to add the tab completion feature! Thank you for the good
> > points. I've added it again in this version's patch.
> > https://lore.kernel.org/all/[email protected]/
> >
> > Takeru
> >
>
> After added the above v4 patch able to to see tab completion for flow-type but not rx-flow-hash. Please find below logs.
>
> # ethtool -N eth4 rx-flow-hash
> ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
> # ethtool -N eth4 rx-flow-hash
> ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
> # ethtool -N eth4 flow-type
> ah4 esp4 ether gtpc4t gtpc6t gtpu4d gtpu4u gtpu6d gtpu6u ip6 sctp6 tcp6 udp6
> ah6 esp6 gtpc4 gtpc6 gtpu4 gtpu4e gtpu6 gtpu6e ip4 sctp4 tcp4 udp4
>
>-----Original Message-----
> From: Takeru Hayasaka <[email protected]>
> Sent: Tuesday, March 5, 2024 1:18 PM
> To: Pucha, HimasekharX Reddy <[email protected]>
> Cc: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; [email protected]; [email protected]
> Subject: Re: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
>
> Hi Himasekhar Reddy-san
>
> > After added the above v4 patch able to to see tab completion for flow-type but not rx-flow-hash. Please find below logs.
>
> Sorry. I submitted a code with the conditions reversed. I have
> resubmitted it, so could you please check it again?
> https://lore.kernel.org/all/[email protected]/
>
> Takeru
>
Hi Takeru,
Its working fine with V5 patch.
# ./ethtool -N eth4 flow-type
ah4 ah6 esp4 esp6 ether ip4 ip6 sctp4 sctp6 tcp4 tcp6 udp4 udp6
# ./ethtool -N eth4 rx-flow-hash
ah4 esp4 ether gtpc4t gtpc6t gtpu4d gtpu4u gtpu6d gtpu6u sctp6 tcp6 udp6
ah6 esp6 gtpc4 gtpc6 gtpu4 gtpu4e gtpu6 gtpu6e sctp4 tcp4 udp4
# ./ethtool -N eth4 rx-flow-hash gtpc6t
d e f m n r s t v
# ./ethtool -N eth4 rx-flow-hash gtpc6t
d e f m n r s t v
# ./ethtool -N eth4 rx-flow-hash gtpc6t sde
# ./ethtool -N eth4 rx-flow-hash gtpc6t stv
> 2024年3月5日(火) 13:28 Pucha, HimasekharX Reddy <[email protected]>:
>
> >-----Original Message-----
> > From: Takeru Hayasaka <[email protected]>
> > Sent: Tuesday, March 5, 2024 9:12 AM
> > To: Pucha, HimasekharX Reddy <[email protected]>
> > Cc: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; [email protected]; [email protected]
> > Subject: Re: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
> >
> > Hi Himasekhar Reddy-san
> >
> > > Functionality wise its working fine. But the ethtool part (tab complete doesn't show GTP)
> >
> > I forgot to add the tab completion feature! Thank you for the good
> > points. I've added it again in this version's patch.
> > https://lore.kernel.org/all/[email protected]/
> >
> > Takeru
> >
>
> After added the above v4 patch able to to see tab completion for flow-type but not rx-flow-hash. Please find below logs.
>
> # ethtool -N eth4 rx-flow-hash
> ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
> # ethtool -N eth4 rx-flow-hash
> ah4 ah6 esp4 esp6 ether sctp4 sctp6 tcp4 tcp6 udp4 udp6
> # ethtool -N eth4 flow-type
> ah4 esp4 ether gtpc4t gtpc6t gtpu4d gtpu4u gtpu6d gtpu6u ip6 sctp6 tcp6 udp6
> ah6 esp6 gtpc4 gtpc6 gtpu4 gtpu4e gtpu6 gtpu6e ip4 sctp4 tcp4 udp4
>
> -----Original Message-----
> From: Intel-wired-lan <[email protected]> On Behalf Of Takeru Hayasaka
> Sent: Monday, February 12, 2024 7:34 AM
> To: Brandeburg, Jesse <[email protected]>; Nguyen, Anthony L <[email protected]>; David S. Miller <[email protected]>; Eric Dumazet <[email protected]>; Jakub Kicinski <[email protected]>; Paolo Abeni <[email protected]>; Jonathan Corbet <[email protected]>
> Cc: [email protected]; [email protected]; [email protected]; [email protected]; Marcin Szycik <[email protected]>; [email protected]; Takeru Hayasaka <hayatake396@gmailcom>; [email protected]; [email protected]
> Subject: [Intel-wired-lan] [PATCH net-next v8 1/2] ethtool: Add GTP RSS hash options to ethtool.h
>
> This is a patch that enables RSS functionality for GTP packets using ethtool.
>
> A user can include TEID and make RSS work for GTP-U over IPv4 by doing the
> following:`ethtool -N ens3 rx-flow-hash gtpu4 sde`
>
> In addition to gtpu(4|6), we now support gtpc(4|6),gtpc(4|6)t,gtpu(4|6)e,
> gtpu(4|6)u, and gtpu(4|6)d.
>
> gtpc(4|6): Used for GTP-C in IPv4 and IPv6, where the GTP header format does
> not include a TEID.
> gtpc(4|6)t: Used for GTP-C in IPv4 and IPv6, with a GTP header format that
> includes a TEID.
> gtpu(4|6): Used for GTP-U in both IPv4 and IPv6 scenarios.
> gtpu(4|6)e: Used for GTP-U with extended headers in both IPv4 and IPv6.
> gtpu(4|6)u: Used when the PSC (PDU session container) in the GTP-U extended
> header includes Uplink, applicable to both IPv4 and IPv6.
> gtpu(4|6)d: Used when the PSC in the GTP-U extended header includes Downlink,
> for both IPv4 and IPv6.
>
> GTP generates a flow that includes an ID called TEID to identify the tunnel.
> This tunnel is created for each UE (User Equipment).By performing RSS based on
> this flow, it is possible to apply RSS for each communication unit from the UE.
> Without this, RSS would only be effective within the range of IP addresses. For
> instance, the PGW can only perform RSS within the IP range of the SGW.
> Problematic from a load distribution perspective, especially if there's a bias
> in the terminals connected to a particular base station.This case can be
> solved by using this patch.
>
> Signed-off-by: Takeru Hayasaka <[email protected]>
> Reviewed-by: Marcin Szycik <[email protected]>
> ---
> v2->v3: Based on Harald-san's review, I added documentation and comments to
> ethtool.h and ice.rst.
> v3->v4: Based on Marcin-san's review, I added the missing code for GTPC and
> GTPC_TEID, and revised the documentation and comments.
> v4->v5: Based on Marcin-san's review, I fixed rename and wrong code regarding
> GTPC
> v5->v6: Based on Marcin-san's review, Undoing the addition of unnecessary
> blank lines.Minor fixes.
> v6->v7 Based on Jakub-san's review, Split the patch.
> v7->v8: There are no code changes. I've resent the patch, including Marcin-san's
> patch, because PatchWork did not interpret the patch correctly.Simon-san told
> me. Thanks.
> include/uapi/linux/ethtool.h | 48 ++++++++++++++++++++++++++++++++++++
> 1 file changed, 48 insertions(+)
>
Tested-by: Pucha Himasekhar Reddy <[email protected]> (A Contingent worker at Intel)