UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c

1734 lines
49 KiB
C
Raw Normal View History

net: mvpp2: switch to SPDX identifiers Use the appropriate SPDX license identifiers and drop the license text. This patch is only cosmetic. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:24 +08:00
// SPDX-License-Identifier: GPL-2.0
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/*
* RSS and Classifier helpers for Marvell PPv2 Network Controller
*
* Copyright (C) 2014 Marvell
*
* Marcin Wojtas <mw@semihalf.com>
*/
#include "mvpp2.h"
#include "mvpp2_cls.h"
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
#include "mvpp2_prs.h"
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
#define MVPP2_DEF_FLOW(_type, _id, _opts, _ri, _ri_mask) \
{ \
.flow_type = _type, \
.flow_id = _id, \
.supported_hash_opts = _opts, \
.prs_ri = { \
.ri = _ri, \
.ri_mask = _ri_mask \
} \
}
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
/* TCP over IPv4 flows, Not fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* TCP over IPv4 flows, Not fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
/* TCP over IPv4 flows, fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* TCP over IPv4 flows, fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP4, MVPP2_FL_IP4_TCP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
/* UDP over IPv4 flows, Not fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* UDP over IPv4 flows, Not fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
/* UDP over IPv4 flows, fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* UDP over IPv4 flows, fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP4, MVPP2_FL_IP4_UDP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
/* TCP over IPv6 flows, not fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* TCP over IPv6 flows, not fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
/* TCP over IPv6 flows, fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* TCP over IPv6 flows, fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_TCP6, MVPP2_FL_IP6_TCP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
MVPP2_PRS_RI_L4_TCP,
MVPP2_PRS_IP_MASK),
/* UDP over IPv6 flows, not fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_5T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* UDP over IPv6 flows, not fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_NF_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
/* UDP over IPv6 flows, fragmented, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
/* UDP over IPv6 flows, fragmented, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_UDP6, MVPP2_FL_IP6_UDP_FRAG_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
MVPP2_PRS_RI_L4_UDP,
MVPP2_PRS_IP_MASK),
/* IPv4 flows, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4,
MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT,
MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP4_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER,
MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
/* IPv4 flows, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4,
MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OPT,
MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP4, MVPP2_FL_IP4_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP4_OTHER,
MVPP2_PRS_RI_L3_PROTO_MASK),
/* IPv6 flows, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_IP6_2T,
MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
/* IPv6 flows, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6,
MVPP2_PRS_RI_L3_PROTO_MASK),
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_IP6, MVPP2_FL_IP6_TAG,
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_TAGGED,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP2_PRS_RI_L3_IP6,
MVPP2_PRS_RI_L3_PROTO_MASK),
/* Non IP flow, no vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_UNTAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
0,
MVPP2_PRS_RI_VLAN_NONE,
MVPP2_PRS_RI_VLAN_MASK),
/* Non IP flow, with vlan tag */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
MVPP22_CLS_HEK_OPT_VLAN,
0, 0),
};
net: mvpp2: debugfs: add classifier hit counters The classification operations that are used for RSS make use of several lookup tables. Having hit counters for these tables is really helpful to determine what flows were matched by ingress traffic, and see the path of packets among all the classifier tables. This commit adds hit counters for the 3 tables used at the moment : - The decoding table (also called lookup_id table), that links flows identified by the Header Parser to the flow table. There's one entry per flow, located at : .../mvpp2/<controller>/flows/XX/dec_hits Note that there are 21 flows in the decoding table, whereas there are 52 flows in the Header Parser. That's because there are several kind of traffic that will match a given flow. Reading the hit counter from one sub-flow will clear all hit counter that have the same flow_id. This also applies to the flow_hits. - The flow table, that contains all the different lookups to be performed by the classifier for each packet of a given flow. The match is done on the first entry of the flow sequence. - The C2 engine entries, that are used to assign the default rx queue, and enable or disable RSS for a given port. There's one entry per flow, located at: .../mvpp2/<controller>/flows/XX/flow_hits There is one C2 entry per port, so the c2 hit counter is located at : .../mvpp2/<controller>/ethX/c2_hits All hit counter values are 16-bits clear-on-read values. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:28 +08:00
u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index)
{
mvpp2_write(priv, MVPP2_CTRS_IDX, index);
return mvpp2_read(priv, MVPP2_CLS_FLOW_TBL_HIT_CTR);
}
net: mvpp2: debugfs: add entries for classifier flows The classifier configuration for RSS is quite complex, with several lookup tables being used. This commit adds useful info in debugfs to see how the different tables are configured : Added 2 new entries in the per-port directory : - .../eth0/default_rxq : The default rx queue on that port - .../eth0/rss_enable : Indicates if RSS is enabled in the C2 entry Added the 'flows' directory : It contains one entry per sub-flow. a 'sub-flow' is a unique path from Header Parser to the flow table. Multiple sub-flows can point to the same 'flow' (each flow has an id from 8 to 29, which is its index in the Lookup Id table) : - .../flows/00/... /01/... ... /51/id : The flow id. There are 21 unique flows. There's one flow per combination of the following parameters : - L4 protocol (TCP, UDP, none) - L3 protocol (IPv4, IPv6) - L3 parameters (Fragmented or not) - L2 parameters (Vlan tag presence or not) .../type : The flow type. This is an even higher level flow, that we manipulate with ethtool. It can be : "udp4" "tcp4" "udp6" "tcp6" "ipv4" "ipv6" "other". .../eth0/... .../eth1/engine : The hash generation engine used for this flow on the given port .../hash_opts : The hash generation options indicating on what data we base the hash (vlan tag, src IP, src port, etc.) Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:27 +08:00
void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
struct mvpp2_cls_flow_entry *fe)
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
{
fe->index = index;
mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
fe->data[0] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL0_REG);
fe->data[1] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL1_REG);
fe->data[2] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL2_REG);
}
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/* Update classification flow table registers */
static void mvpp2_cls_flow_write(struct mvpp2 *priv,
struct mvpp2_cls_flow_entry *fe)
{
mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, fe->index);
net: mvpp2: cls: Remove extra whitespace in mvpp2_cls_flow_write Cosmetic patch removing extra whitespaces when writing the flow_table entries Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:26 +08:00
mvpp2_write(priv, MVPP2_CLS_FLOW_TBL0_REG, fe->data[0]);
mvpp2_write(priv, MVPP2_CLS_FLOW_TBL1_REG, fe->data[1]);
mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG, fe->data[2]);
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
}
net: mvpp2: debugfs: add classifier hit counters The classification operations that are used for RSS make use of several lookup tables. Having hit counters for these tables is really helpful to determine what flows were matched by ingress traffic, and see the path of packets among all the classifier tables. This commit adds hit counters for the 3 tables used at the moment : - The decoding table (also called lookup_id table), that links flows identified by the Header Parser to the flow table. There's one entry per flow, located at : .../mvpp2/<controller>/flows/XX/dec_hits Note that there are 21 flows in the decoding table, whereas there are 52 flows in the Header Parser. That's because there are several kind of traffic that will match a given flow. Reading the hit counter from one sub-flow will clear all hit counter that have the same flow_id. This also applies to the flow_hits. - The flow table, that contains all the different lookups to be performed by the classifier for each packet of a given flow. The match is done on the first entry of the flow sequence. - The C2 engine entries, that are used to assign the default rx queue, and enable or disable RSS for a given port. There's one entry per flow, located at: .../mvpp2/<controller>/flows/XX/flow_hits There is one C2 entry per port, so the c2 hit counter is located at : .../mvpp2/<controller>/ethX/c2_hits All hit counter values are 16-bits clear-on-read values. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:28 +08:00
u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index)
{
mvpp2_write(priv, MVPP2_CTRS_IDX, index);
return mvpp2_read(priv, MVPP2_CLS_DEC_TBL_HIT_CTR);
}
net: mvpp2: debugfs: add entries for classifier flows The classifier configuration for RSS is quite complex, with several lookup tables being used. This commit adds useful info in debugfs to see how the different tables are configured : Added 2 new entries in the per-port directory : - .../eth0/default_rxq : The default rx queue on that port - .../eth0/rss_enable : Indicates if RSS is enabled in the C2 entry Added the 'flows' directory : It contains one entry per sub-flow. a 'sub-flow' is a unique path from Header Parser to the flow table. Multiple sub-flows can point to the same 'flow' (each flow has an id from 8 to 29, which is its index in the Lookup Id table) : - .../flows/00/... /01/... ... /51/id : The flow id. There are 21 unique flows. There's one flow per combination of the following parameters : - L4 protocol (TCP, UDP, none) - L3 protocol (IPv4, IPv6) - L3 parameters (Fragmented or not) - L2 parameters (Vlan tag presence or not) .../type : The flow type. This is an even higher level flow, that we manipulate with ethtool. It can be : "udp4" "tcp4" "udp6" "tcp6" "ipv4" "ipv6" "other". .../eth0/... .../eth1/engine : The hash generation engine used for this flow on the given port .../hash_opts : The hash generation options indicating on what data we base the hash (vlan tag, src IP, src port, etc.) Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:27 +08:00
void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
struct mvpp2_cls_lookup_entry *le)
{
u32 val;
val = (way << MVPP2_CLS_LKP_INDEX_WAY_OFFS) | lkpid;
mvpp2_write(priv, MVPP2_CLS_LKP_INDEX_REG, val);
le->way = way;
le->lkpid = lkpid;
le->data = mvpp2_read(priv, MVPP2_CLS_LKP_TBL_REG);
}
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/* Update classification lookup table register */
static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
struct mvpp2_cls_lookup_entry *le)
{
u32 val;
val = (le->way << MVPP2_CLS_LKP_INDEX_WAY_OFFS) | le->lkpid;
mvpp2_write(priv, MVPP2_CLS_LKP_INDEX_REG, val);
mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
}
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
/* Operations on flow entry */
static int mvpp2_cls_flow_hek_num_get(struct mvpp2_cls_flow_entry *fe)
{
return fe->data[1] & MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
}
static void mvpp2_cls_flow_hek_num_set(struct mvpp2_cls_flow_entry *fe,
int num_of_fields)
{
fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
fe->data[1] |= MVPP2_CLS_FLOW_TBL1_N_FIELDS(num_of_fields);
}
static int mvpp2_cls_flow_hek_get(struct mvpp2_cls_flow_entry *fe,
int field_index)
{
return (fe->data[2] >> MVPP2_CLS_FLOW_TBL2_FLD_OFFS(field_index)) &
MVPP2_CLS_FLOW_TBL2_FLD_MASK;
}
static void mvpp2_cls_flow_hek_set(struct mvpp2_cls_flow_entry *fe,
int field_index, int field_id)
{
fe->data[2] &= ~MVPP2_CLS_FLOW_TBL2_FLD(field_index,
MVPP2_CLS_FLOW_TBL2_FLD_MASK);
fe->data[2] |= MVPP2_CLS_FLOW_TBL2_FLD(field_index, field_id);
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
int engine)
{
fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_ENG(MVPP2_CLS_FLOW_TBL0_ENG_MASK);
fe->data[0] |= MVPP2_CLS_FLOW_TBL0_ENG(engine);
}
net: mvpp2: debugfs: add entries for classifier flows The classifier configuration for RSS is quite complex, with several lookup tables being used. This commit adds useful info in debugfs to see how the different tables are configured : Added 2 new entries in the per-port directory : - .../eth0/default_rxq : The default rx queue on that port - .../eth0/rss_enable : Indicates if RSS is enabled in the C2 entry Added the 'flows' directory : It contains one entry per sub-flow. a 'sub-flow' is a unique path from Header Parser to the flow table. Multiple sub-flows can point to the same 'flow' (each flow has an id from 8 to 29, which is its index in the Lookup Id table) : - .../flows/00/... /01/... ... /51/id : The flow id. There are 21 unique flows. There's one flow per combination of the following parameters : - L4 protocol (TCP, UDP, none) - L3 protocol (IPv4, IPv6) - L3 parameters (Fragmented or not) - L2 parameters (Vlan tag presence or not) .../type : The flow type. This is an even higher level flow, that we manipulate with ethtool. It can be : "udp4" "tcp4" "udp6" "tcp6" "ipv4" "ipv6" "other". .../eth0/... .../eth1/engine : The hash generation engine used for this flow on the given port .../hash_opts : The hash generation options indicating on what data we base the hash (vlan tag, src IP, src port, etc.) Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:27 +08:00
int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe)
{
return (fe->data[0] >> MVPP2_CLS_FLOW_TBL0_OFFS) &
MVPP2_CLS_FLOW_TBL0_ENG_MASK;
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
bool from_packet)
{
if (from_packet)
fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
else
fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
}
static void mvpp2_cls_flow_last_set(struct mvpp2_cls_flow_entry *fe,
bool is_last)
{
fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_LAST;
fe->data[0] |= !!is_last;
}
static void mvpp2_cls_flow_pri_set(struct mvpp2_cls_flow_entry *fe, int prio)
{
fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_PRIO(MVPP2_CLS_FLOW_TBL1_PRIO_MASK);
fe->data[1] |= MVPP2_CLS_FLOW_TBL1_PRIO(prio);
}
static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
u32 port)
{
fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
static void mvpp2_cls_flow_port_remove(struct mvpp2_cls_flow_entry *fe,
u32 port)
{
fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
}
net: mvpp2: cls: use Lookup Type in classification engines The PPv2 classifier allows to perform multiple lookups on the same engine when classifying a packet. These lookups can match similar parts of a packet header, but perform different actions upon matching. To differentiate these types of lookups, it's possible to specify a Lookup Type in the flow table entries, which will be part of the key for the lookup engines. This commit introduces the use of Lookup Types for C2 matches. Since for now we only perform C2 lookups to enable RSS, we only need one Lookup Type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:08 +08:00
static void mvpp2_cls_flow_lu_type_set(struct mvpp2_cls_flow_entry *fe,
u8 lu_type)
{
fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK);
fe->data[1] |= MVPP2_CLS_FLOW_TBL1_LU_TYPE(lu_type);
}
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
/* Initialize the parser entry for the given flow */
static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *flow)
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
{
mvpp2_prs_add_flow(priv, flow->flow_id, flow->prs_ri.ri,
flow->prs_ri.ri_mask);
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
/* Initialize the Lookup Id table entry for the given flow */
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *flow)
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
{
struct mvpp2_cls_lookup_entry le;
le.way = 0;
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
le.lkpid = flow->flow_id;
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
/* The default RxQ for this port is set in the C2 lookup */
le.data = 0;
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
/* We point on the first lookup in the sequence for the flow, that is
* the C2 lookup.
*/
net: mvpp2: cls: Rename the flow table macros The Flow Table dictates what lookups will be issued for each flow type. The lookup sequence for each flow is similar, and the index of each lookup is computed by some macros. There are similar mechanisms for the C2 TCAM lookups, so in order to avoid confusion, rename the flow table index computing macros with a common prefix. The only difference in behaviour is that we now use the very first entry in the flow for the RSS lookup (the first entry was previously unused). Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:19 +08:00
le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_CLS_FLT_FIRST(flow->flow_id));
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
/* CLS is always enabled, RSS is enabled/disabled in C2 lookup */
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
mvpp2_cls_lookup_write(priv, &le);
}
net: mvpp2: cls: Move C2 read/write helpers around Move C2 read/write helpers higher in the file to ease future work that rely on these helpers Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:16 +08:00
static void mvpp2_cls_c2_write(struct mvpp2 *priv,
struct mvpp2_cls_c2_entry *c2)
{
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
u32 val;
net: mvpp2: cls: Move C2 read/write helpers around Move C2 read/write helpers higher in the file to ease future work that rely on these helpers Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:16 +08:00
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
val = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_INV);
if (c2->valid)
val &= ~MVPP22_CLS_C2_TCAM_INV_BIT;
else
val |= MVPP22_CLS_C2_TCAM_INV_BIT;
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_INV, val);
net: mvpp2: cls: Move C2 read/write helpers around Move C2 read/write helpers higher in the file to ease future work that rely on these helpers Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:16 +08:00
mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
/* Writing TCAM_DATA4 flushes writes to TCAM_DATA0-4 and INV to HW */
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
}
void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
struct mvpp2_cls_c2_entry *c2)
{
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
u32 val;
net: mvpp2: cls: Move C2 read/write helpers around Move C2 read/write helpers higher in the file to ease future work that rely on these helpers Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:16 +08:00
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
c2->index = index;
c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
val = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_INV);
c2->valid = !(val & MVPP22_CLS_C2_TCAM_INV_BIT);
net: mvpp2: cls: Move C2 read/write helpers around Move C2 read/write helpers higher in the file to ease future work that rely on these helpers Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:16 +08:00
}
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
static int mvpp2_cls_ethtool_flow_to_type(int flow_type)
{
switch (flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) {
net: mvpp2: cls: Add support for ETHER_FLOW Users can specify classification actions based on the 'ether' flow type. In that case, this will apply to all ethernet traffic, superseeding flows such as 'udp4' or 'tcp6'. Add support for this flow type in the PPv2 classifier, by mapping the ETHER_FLOW value to the corresponding entries in the classifier. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-05 20:09:13 +08:00
case ETHER_FLOW:
return MVPP22_FLOW_ETHERNET;
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
case TCP_V4_FLOW:
return MVPP22_FLOW_TCP4;
case TCP_V6_FLOW:
return MVPP22_FLOW_TCP6;
case UDP_V4_FLOW:
return MVPP22_FLOW_UDP4;
case UDP_V6_FLOW:
return MVPP22_FLOW_UDP6;
case IPV4_FLOW:
return MVPP22_FLOW_IP4;
case IPV6_FLOW:
return MVPP22_FLOW_IP6;
default:
return -EOPNOTSUPP;
}
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
static int mvpp2_cls_c2_port_flow_index(struct mvpp2_port *port, int loc)
{
return MVPP22_CLS_C2_RFS_LOC(port->id, loc);
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
/* Initialize the flow table entries for the given flow */
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
static void mvpp2_cls_flow_init(struct mvpp2 *priv,
const struct mvpp2_cls_flow *flow)
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
{
struct mvpp2_cls_flow_entry fe;
net: mvpp2: cls: Initialize lookup priorities for all entries in the flow When classifying a packet pertaining to a given flow, the classifier will issue multiple lookup commands until it finds one with the 'last' bit set. It expects all prorities to be assign continuously (although not necessarily in an ordered fashion) from 0 to the number of lookups. We can initialize this once, and make sure unused lookups are given an empty port map. This avoids having to maintain priorities and the information of which lookup is the last. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:21 +08:00
int i, pri = 0;
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
net: mvpp2: cls: Initialize lookup priorities for all entries in the flow When classifying a packet pertaining to a given flow, the classifier will issue multiple lookup commands until it finds one with the 'last' bit set. It expects all prorities to be assign continuously (although not necessarily in an ordered fashion) from 0 to the number of lookups. We can initialize this once, and make sure unused lookups are given an empty port map. This avoids having to maintain priorities and the information of which lookup is the last. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:21 +08:00
/* Assign default values to all entries in the flow */
for (i = MVPP2_CLS_FLT_FIRST(flow->flow_id);
i <= MVPP2_CLS_FLT_LAST(flow->flow_id); i++) {
memset(&fe, 0, sizeof(fe));
fe.index = i;
mvpp2_cls_flow_pri_set(&fe, pri++);
if (i == MVPP2_CLS_FLT_LAST(flow->flow_id))
mvpp2_cls_flow_last_set(&fe, 1);
mvpp2_cls_flow_write(priv, &fe);
}
/* RSS config C2 lookup */
mvpp2_cls_flow_read(priv, MVPP2_CLS_FLT_C2_RSS_ENTRY(flow->flow_id),
&fe);
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
mvpp2_cls_flow_port_id_sel(&fe, true);
net: mvpp2: cls: Use a dedicated lu_type for the RSS lookup When performing a TCAM lookup in the C2 engine, it's possible that multiple entries match the packet. To make sure the correct entry match when performing a lookup, the Flow Table can set a lookup type, which will be used in the TCAM lookup, thus preventing such false-positives. We need to make sure the RSS match doesn't interfere with other classification lookups, hence we use a dedicated lookup_type for it. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:16 +08:00
mvpp2_cls_flow_lu_type_set(&fe, MVPP22_CLS_LU_TYPE_ALL);
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
/* Add all ports */
for (i = 0; i < MVPP2_MAX_PORTS; i++)
mvpp2_cls_flow_port_add(&fe, BIT(i));
mvpp2_cls_flow_write(priv, &fe);
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
/* C3Hx lookups */
for (i = 0; i < MVPP2_MAX_PORTS; i++) {
net: mvpp2: cls: Initialize lookup priorities for all entries in the flow When classifying a packet pertaining to a given flow, the classifier will issue multiple lookup commands until it finds one with the 'last' bit set. It expects all prorities to be assign continuously (although not necessarily in an ordered fashion) from 0 to the number of lookups. We can initialize this once, and make sure unused lookups are given an empty port map. This avoids having to maintain priorities and the information of which lookup is the last. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:21 +08:00
mvpp2_cls_flow_read(priv,
MVPP2_CLS_FLT_HASH_ENTRY(i, flow->flow_id),
&fe);
/* Set a default engine. Will be overwritten when setting the
* real HEK parameters
*/
mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C3HA);
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
mvpp2_cls_flow_port_id_sel(&fe, true);
mvpp2_cls_flow_port_add(&fe, BIT(i));
mvpp2_cls_flow_write(priv, &fe);
}
}
/* Adds a field to the Header Extracted Key generation parameters*/
static int mvpp2_flow_add_hek_field(struct mvpp2_cls_flow_entry *fe,
u32 field_id)
{
int nb_fields = mvpp2_cls_flow_hek_num_get(fe);
if (nb_fields == MVPP2_FLOW_N_FIELDS)
return -EINVAL;
mvpp2_cls_flow_hek_set(fe, nb_fields, field_id);
mvpp2_cls_flow_hek_num_set(fe, nb_fields + 1);
return 0;
}
static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
unsigned long hash_opts)
{
u32 field_id;
int i;
/* Clear old fields */
mvpp2_cls_flow_hek_num_set(fe, 0);
fe->data[2] = 0;
for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
switch (BIT(i)) {
net: mvpp2: cls: Add missing MAC_DA field extraction PPv2's classifier supports extracting the MAC Destination Address from the L2 header to perform RSS and flow steering. Add the missing case when setting the Header Extracted Key fields in the flow table. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:06 +08:00
case MVPP22_CLS_HEK_OPT_MAC_DA:
field_id = MVPP22_CLS_FIELD_MAC_DA;
break;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
case MVPP22_CLS_HEK_OPT_VLAN:
field_id = MVPP22_CLS_FIELD_VLAN;
break;
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
case MVPP22_CLS_HEK_OPT_VLAN_PRI:
field_id = MVPP22_CLS_FIELD_VLAN_PRI;
break;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
case MVPP22_CLS_HEK_OPT_IP4SA:
field_id = MVPP22_CLS_FIELD_IP4SA;
break;
case MVPP22_CLS_HEK_OPT_IP4DA:
field_id = MVPP22_CLS_FIELD_IP4DA;
break;
case MVPP22_CLS_HEK_OPT_IP6SA:
field_id = MVPP22_CLS_FIELD_IP6SA;
break;
case MVPP22_CLS_HEK_OPT_IP6DA:
field_id = MVPP22_CLS_FIELD_IP6DA;
break;
case MVPP22_CLS_HEK_OPT_L4SIP:
field_id = MVPP22_CLS_FIELD_L4SIP;
break;
case MVPP22_CLS_HEK_OPT_L4DIP:
field_id = MVPP22_CLS_FIELD_L4DIP;
break;
default:
return -EINVAL;
}
if (mvpp2_flow_add_hek_field(fe, field_id))
return -EINVAL;
}
return 0;
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
/* Returns the size, in bits, of the corresponding HEK field */
static int mvpp2_cls_hek_field_size(u32 field)
{
switch (field) {
case MVPP22_CLS_HEK_OPT_MAC_DA:
return 48;
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
case MVPP22_CLS_HEK_OPT_VLAN:
return 12;
case MVPP22_CLS_HEK_OPT_VLAN_PRI:
return 3;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
case MVPP22_CLS_HEK_OPT_IP4SA:
case MVPP22_CLS_HEK_OPT_IP4DA:
return 32;
case MVPP22_CLS_HEK_OPT_IP6SA:
case MVPP22_CLS_HEK_OPT_IP6DA:
return 128;
case MVPP22_CLS_HEK_OPT_L4SIP:
case MVPP22_CLS_HEK_OPT_L4DIP:
return 16;
default:
return -1;
}
}
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
{
net: mvpp2: cls: Rename MVPP2_N_FLOWS to MVPP2_N_PRS_FLOWS The macro definition MVPP2_N_FLOWS is ambiguous because it really represents the number of entries in the Header Parser that are used to identify the classification flows. Rename the macro to clearly state that we represent the number of flows in the Header Parser. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:09 +08:00
if (flow >= MVPP2_N_PRS_FLOWS)
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
return NULL;
return &cls_flows[flow];
}
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
/* Set the hash generation options for the given traffic flow.
* One traffic flow (in the ethtool sense) has multiple classification flows,
* to handle specific cases such as fragmentation, or the presence of a
* VLAN / DSA Tag.
*
* Each of these individual flows has different constraints, for example we
* can't hash fragmented packets on L4 data (else we would risk having packet
* re-ordering), so each classification flows masks the options with their
* supported ones.
*
*/
static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
u16 requested_opts)
{
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *flow;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
struct mvpp2_cls_flow_entry fe;
int i, engine, flow_index;
u16 hash_opts;
net: mvpp2: cls: Use iterators to go through the cls_table The cls_table is a global read-only table containing the different parameters that are used by various tables in the classifier. It describes the links between the Header Parser, the decoding table and the flow_table. There are several possible way we want to iterate over that table, depending on wich classifier engine we want to configure. For the Header Parser, we want to iterate over each entry. For the Decoding table, we want to iterate over each entry having a unique flow_id. Finally, when configuring an ethtool flow, we want to iterate over each entry having a unique flow_id and that has a given flow_type. This commit introduces some iterator to both provide syntactic sugar and also clarify the way we want to iterate over the table. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:14 +08:00
for_each_cls_flow_id_with_type(i, flow_type) {
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
flow = mvpp2_cls_flow_get(i);
if (!flow)
return -EINVAL;
net: mvpp2: cls: Rename the flow table macros The Flow Table dictates what lookups will be issued for each flow type. The lookup sequence for each flow is similar, and the index of each lookup is computed by some macros. There are similar mechanisms for the C2 TCAM lookups, so in order to avoid confusion, rename the flow table index computing macros with a common prefix. The only difference in behaviour is that we now use the very first entry in the flow for the RSS lookup (the first entry was previously unused). Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:19 +08:00
flow_index = MVPP2_CLS_FLT_HASH_ENTRY(port->id, flow->flow_id);
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
mvpp2_cls_flow_read(port->priv, flow_index, &fe);
hash_opts = flow->supported_hash_opts & requested_opts;
/* Use C3HB engine to access L4 infos. This adds L4 infos to the
* hash parameters
*/
if (hash_opts & MVPP22_CLS_HEK_L4_OPTS)
engine = MVPP22_CLS_ENGINE_C3HB;
else
engine = MVPP22_CLS_ENGINE_C3HA;
if (mvpp2_flow_set_hek_fields(&fe, hash_opts))
return -EINVAL;
mvpp2_cls_flow_eng_set(&fe, engine);
mvpp2_cls_flow_write(port->priv, &fe);
}
return 0;
}
u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
{
u16 hash_opts = 0;
int n_fields, i, field;
n_fields = mvpp2_cls_flow_hek_num_get(fe);
for (i = 0; i < n_fields; i++) {
field = mvpp2_cls_flow_hek_get(fe, i);
switch (field) {
case MVPP22_CLS_FIELD_MAC_DA:
hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
break;
case MVPP22_CLS_FIELD_VLAN:
hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
break;
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
case MVPP22_CLS_FIELD_VLAN_PRI:
hash_opts |= MVPP22_CLS_HEK_OPT_VLAN_PRI;
break;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
case MVPP22_CLS_FIELD_L3_PROTO:
hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
break;
case MVPP22_CLS_FIELD_IP4SA:
hash_opts |= MVPP22_CLS_HEK_OPT_IP4SA;
break;
case MVPP22_CLS_FIELD_IP4DA:
hash_opts |= MVPP22_CLS_HEK_OPT_IP4DA;
break;
case MVPP22_CLS_FIELD_IP6SA:
hash_opts |= MVPP22_CLS_HEK_OPT_IP6SA;
break;
case MVPP22_CLS_FIELD_IP6DA:
hash_opts |= MVPP22_CLS_HEK_OPT_IP6DA;
break;
case MVPP22_CLS_FIELD_L4SIP:
hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
break;
case MVPP22_CLS_FIELD_L4DIP:
hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
break;
default:
break;
}
}
return hash_opts;
}
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
/* Returns the hash opts for this flow. There are several classifier flows
* for one traffic flow, this returns an aggregation of all configurations.
*/
static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
{
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *flow;
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
struct mvpp2_cls_flow_entry fe;
int i, flow_index;
u16 hash_opts = 0;
net: mvpp2: cls: Use iterators to go through the cls_table The cls_table is a global read-only table containing the different parameters that are used by various tables in the classifier. It describes the links between the Header Parser, the decoding table and the flow_table. There are several possible way we want to iterate over that table, depending on wich classifier engine we want to configure. For the Header Parser, we want to iterate over each entry. For the Decoding table, we want to iterate over each entry having a unique flow_id. Finally, when configuring an ethtool flow, we want to iterate over each entry having a unique flow_id and that has a given flow_type. This commit introduces some iterator to both provide syntactic sugar and also clarify the way we want to iterate over the table. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:14 +08:00
for_each_cls_flow_id_with_type(i, flow_type) {
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
flow = mvpp2_cls_flow_get(i);
if (!flow)
return 0;
net: mvpp2: cls: Rename the flow table macros The Flow Table dictates what lookups will be issued for each flow type. The lookup sequence for each flow is similar, and the index of each lookup is computed by some macros. There are similar mechanisms for the C2 TCAM lookups, so in order to avoid confusion, rename the flow table index computing macros with a common prefix. The only difference in behaviour is that we now use the very first entry in the flow for the RSS lookup (the first entry was previously unused). Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:19 +08:00
flow_index = MVPP2_CLS_FLT_HASH_ENTRY(port->id, flow->flow_id);
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
mvpp2_cls_flow_read(port->priv, flow_index, &fe);
hash_opts |= mvpp2_flow_get_hek_fields(&fe);
}
return hash_opts;
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
{
net: mvpp2: cls: Make the flow definitions const The cls_flow table represent the overall configuration of the classifier, used to match the different traffic classes in the Parsing and Classification engines. This configuration is static, and applies to all PPv2 instances, we must therefore keep it const so that no modifications of this table are performed at runtime. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:10 +08:00
const struct mvpp2_cls_flow *flow;
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
int i;
net: mvpp2: cls: Rename MVPP2_N_FLOWS to MVPP2_N_PRS_FLOWS The macro definition MVPP2_N_FLOWS is ambiguous because it really represents the number of entries in the Header Parser that are used to identify the classification flows. Rename the macro to clearly state that we represent the number of flows in the Header Parser. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:09 +08:00
for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) {
net: mvpp2: split ingress traffic into multiple flows The PPv2 classifier allows to perform classification operations on each ingress packet, based on the flow the packet is assigned to. The current code uses only 1 flow per port, and the only classification action consists of assigning the rx queue to the packet, depending on the port. In preparation for adding RSS support, we have to split all incoming traffic into different flows. Since RSS assigns a rx queue depending on the hash of some header fields, we have to make sure that the hash is generated in a consistent way for all packets in the same flow. What we call a "flow" is actually a set of attributes attached to a packet that depends on various L2/L3/L4 info. This patch introduces 52 flows, wich are a combination of various L2, L3 and L4 attributes : - Whether or not the packet has a VLAN tag - Whether the packet is IPv4, IPv6 or something else - Whether the packet is TCP, UDP or something else - Whether or not the packet is fragmented at L3 level. The flow is associated to a packet by the Header Parser. Each flow corresponds to an entry in the decoding table. This entry then points to the sequence of classification lookups to be performed by the classifier, represented in the flow table. For now, the only lookup we perform is a C2 lookup to set the default rx queue. Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +------------+ +---------------------+ | To RxQ <---| Classifier |<-------| flow 0: C2 lookup |<--------+ +------------+ | flow 1: C2 lookup | | | ... | +------------+ | flow 51 : C2 lookup | | C2 engine | +---------------------+ +------------+ Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:25 +08:00
flow = mvpp2_cls_flow_get(i);
if (!flow)
break;
mvpp2_cls_flow_prs_init(priv, flow);
mvpp2_cls_flow_lkp_init(priv, flow);
mvpp2_cls_flow_init(priv, flow);
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
}
}
static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
{
struct mvpp2_cls_c2_entry c2;
u8 qh, ql, pmap;
memset(&c2, 0, sizeof(c2));
c2.index = MVPP22_CLS_C2_RSS_ENTRY(port->id);
pmap = BIT(port->id);
c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
net: mvpp2: cls: use Lookup Type in classification engines The PPv2 classifier allows to perform multiple lookups on the same engine when classifying a packet. These lookups can match similar parts of a packet header, but perform different actions upon matching. To differentiate these types of lookups, it's possible to specify a Lookup Type in the flow table entries, which will be part of the key for the lookup engines. This commit introduces the use of Lookup Types for C2 matches. Since for now we only perform C2 lookups to enable RSS, we only need one Lookup Type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:08 +08:00
/* Match on Lookup Type */
c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK));
net: mvpp2: cls: Use a dedicated lu_type for the RSS lookup When performing a TCAM lookup in the C2 engine, it's possible that multiple entries match the packet. To make sure the correct entry match when performing a lookup, the Flow Table can set a lookup type, which will be used in the TCAM lookup, thus preventing such false-positives. We need to make sure the RSS match doesn't interfere with other classification lookups, hence we use a dedicated lookup_type for it. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:16 +08:00
c2.tcam[4] |= MVPP22_CLS_C2_LU_TYPE(MVPP22_CLS_LU_TYPE_ALL);
net: mvpp2: cls: use Lookup Type in classification engines The PPv2 classifier allows to perform multiple lookups on the same engine when classifying a packet. These lookups can match similar parts of a packet header, but perform different actions upon matching. To differentiate these types of lookups, it's possible to specify a Lookup Type in the flow table entries, which will be part of the key for the lookup engines. This commit introduces the use of Lookup Types for C2 matches. Since for now we only perform C2 lookups to enable RSS, we only need one Lookup Type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:08 +08:00
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
/* Update RSS status after matching this entry */
c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
/* Mark packet as "forwarded to software", needed for RSS */
c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
/* Configure the default rx queue : Update Queue Low and Queue High, but
* don't lock, since the rx queue selection might be overridden by RSS
*/
c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD) |
MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD);
qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
MVPP22_CLS_C2_ATTR0_QLOW(ql);
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
c2.valid = true;
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
mvpp2_cls_c2_write(port->priv, &c2);
}
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/* Classifier default initialization */
void mvpp2_cls_init(struct mvpp2 *priv)
{
struct mvpp2_cls_lookup_entry le;
struct mvpp2_cls_flow_entry fe;
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
struct mvpp2_cls_c2_entry c2;
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
int index;
/* Enable classifier */
mvpp2_write(priv, MVPP2_CLS_MODE_REG, MVPP2_CLS_MODE_ACTIVE_MASK);
/* Clear classifier flow table */
memset(&fe.data, 0, sizeof(fe.data));
for (index = 0; index < MVPP2_CLS_FLOWS_TBL_SIZE; index++) {
fe.index = index;
mvpp2_cls_flow_write(priv, &fe);
}
/* Clear classifier lookup table */
le.data = 0;
for (index = 0; index < MVPP2_CLS_LKP_TBL_SIZE; index++) {
le.lkpid = index;
le.way = 0;
mvpp2_cls_lookup_write(priv, &le);
le.way = 1;
mvpp2_cls_lookup_write(priv, &le);
}
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
net: mvpp2: cls: Invalidate all C2 entries except the ones we use C2 TCAM entries can be invalidated to avoid unwanted matches. Make sure all entries are invalidated at init, then validate only the ones we use. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-27 16:44:20 +08:00
/* Clear C2 TCAM engine table */
memset(&c2, 0, sizeof(c2));
c2.valid = false;
for (index = 0; index < MVPP22_CLS_C2_N_ENTRIES; index++) {
c2.index = index;
mvpp2_cls_c2_write(priv, &c2);
}
net: mvpp2: cls: Bypass C2 internals FIFOs at init The C2 TCAM has internal FIFOs that are only useful for the built-in self-tests. Disable these FIFOS at init, as recommended in the functionnal specs. Suggested-by: Alan Winkowski <walan@marvell.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:51 +08:00
/* Disable the FIFO stages in C2 engine, which are only used in BIST
* mode
*/
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_CTRL,
MVPP22_CLS_C2_TCAM_BYPASS_FIFO);
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
mvpp2_cls_port_init_flows(priv);
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
}
void mvpp2_cls_port_config(struct mvpp2_port *port)
{
struct mvpp2_cls_lookup_entry le;
u32 val;
/* Set way for the port */
val = mvpp2_read(port->priv, MVPP2_CLS_PORT_WAY_REG);
val &= ~MVPP2_CLS_PORT_WAY_MASK(port->id);
mvpp2_write(port->priv, MVPP2_CLS_PORT_WAY_REG, val);
/* Pick the entry to be accessed in lookup ID decoding table
* according to the way and lkpid.
*/
le.lkpid = port->id;
le.way = 0;
le.data = 0;
/* Set initial CPU queue for receiving packets */
le.data &= ~MVPP2_CLS_LKP_TBL_RXQ_MASK;
le.data |= port->first_rxq;
/* Disable classification engines */
le.data &= ~MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
/* Update lookup ID table entry */
mvpp2_cls_lookup_write(port->priv, &le);
net: mvpp2: use classifier to assign default rx queue The PPv2 Controller has a classifier, that can perform multiple lookup operations for each packet, using different engines. One of these engines is the C2 engine, which performs TCAM based lookups on data extracted from the packet header. When a packet matches an entry, the engine sets various attributes, used to perform classification operations. One of these attributes is the rx queue in which the packet should be sent. The current code uses the lookup_id table (also called decoding table) to assign the rx queue. However, this only works if we use one entry per port in the decoding table, which won't be the case once we add RSS lookups. This patch uses the C2 engine to assign the rx queue to each packet. The C2 engine is used through the flow table, which dictates what classification operations are done for a given flow. Right now, we have one flow per port, which contains every ingress packet for this port. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:24 +08:00
mvpp2_port_c2_cls_init(port);
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
}
net: mvpp2: debugfs: add classifier hit counters The classification operations that are used for RSS make use of several lookup tables. Having hit counters for these tables is really helpful to determine what flows were matched by ingress traffic, and see the path of packets among all the classifier tables. This commit adds hit counters for the 3 tables used at the moment : - The decoding table (also called lookup_id table), that links flows identified by the Header Parser to the flow table. There's one entry per flow, located at : .../mvpp2/<controller>/flows/XX/dec_hits Note that there are 21 flows in the decoding table, whereas there are 52 flows in the Header Parser. That's because there are several kind of traffic that will match a given flow. Reading the hit counter from one sub-flow will clear all hit counter that have the same flow_id. This also applies to the flow_hits. - The flow table, that contains all the different lookups to be performed by the classifier for each packet of a given flow. The match is done on the first entry of the flow sequence. - The C2 engine entries, that are used to assign the default rx queue, and enable or disable RSS for a given port. There's one entry per flow, located at: .../mvpp2/<controller>/flows/XX/flow_hits There is one C2 entry per port, so the c2 hit counter is located at : .../mvpp2/<controller>/ethX/c2_hits All hit counter values are 16-bits clear-on-read values. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-14 19:29:28 +08:00
u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index)
{
mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2_index);
return mvpp2_read(priv, MVPP22_CLS_C2_HIT_CTR);
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port, u32 ctx)
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
{
struct mvpp2_cls_c2_entry c2;
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
u8 qh, ql;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
/* The RxQ number is used to select the RSS table. It that case, we set
* it to be the ctx number.
*/
qh = (ctx >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
ql = ctx & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
MVPP22_CLS_C2_ATTR0_QLOW(ql);
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
mvpp2_cls_c2_write(port->priv, &c2);
}
static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
{
struct mvpp2_cls_c2_entry c2;
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
u8 qh, ql;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
/* Reset the default destination RxQ to the port's first rx queue. */
qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
MVPP22_CLS_C2_ATTR0_QLOW(ql);
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
mvpp2_cls_c2_write(port->priv, &c2);
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
static inline int mvpp22_rss_ctx(struct mvpp2_port *port, int port_rss_ctx)
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
{
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
return port->rss_ctx[port_rss_ctx];
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
int mvpp22_port_rss_enable(struct mvpp2_port *port)
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
{
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
if (mvpp22_rss_ctx(port, 0) < 0)
return -EINVAL;
mvpp2_rss_port_c2_enable(port, mvpp22_rss_ctx(port, 0));
return 0;
}
int mvpp22_port_rss_disable(struct mvpp2_port *port)
{
if (mvpp22_rss_ctx(port, 0) < 0)
return -EINVAL;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
mvpp2_rss_port_c2_disable(port);
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
return 0;
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
static void mvpp22_port_c2_lookup_disable(struct mvpp2_port *port, int entry)
{
struct mvpp2_cls_c2_entry c2;
mvpp2_cls_c2_read(port->priv, entry, &c2);
/* Clear the port map so that the entry doesn't match anymore */
c2.tcam[4] &= ~(MVPP22_CLS_C2_PORT_ID(BIT(port->id)));
mvpp2_cls_c2_write(port->priv, &c2);
}
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/* Set CPU queue number for oversize packets */
void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
{
u32 val;
mvpp2_write(port->priv, MVPP2_CLS_OVERSIZE_RXQ_LOW_REG(port->id),
port->first_rxq & MVPP2_CLS_OVERSIZE_RXQ_LOW_MASK);
mvpp2_write(port->priv, MVPP2_CLS_SWFWD_P2HQ_REG(port->id),
(port->first_rxq >> MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS));
val = mvpp2_read(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG);
val |= MVPP2_CLS_SWFWD_PCTRL_MASK(port->id);
mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
static int mvpp2_port_c2_tcam_rule_add(struct mvpp2_port *port,
struct mvpp2_rfs_rule *rule)
{
struct flow_action_entry *act;
struct mvpp2_cls_c2_entry c2;
u8 qh, ql, pmap;
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
int index, ctx;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
memset(&c2, 0, sizeof(c2));
net: mvpp2: cls: fix less than zero check on a u32 variable The signed return from the call to mvpp2_cls_c2_port_flow_index is being assigned to the u32 variable c2.index and then checked for a negative error condition which is always going to be false. Fix this by assigning the return to the int variable index and checking this instead. Addresses-Coverity: ("Unsigned compared against 0") Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-06 05:38:14 +08:00
index = mvpp2_cls_c2_port_flow_index(port, rule->loc);
if (index < 0)
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
return -EINVAL;
net: mvpp2: cls: fix less than zero check on a u32 variable The signed return from the call to mvpp2_cls_c2_port_flow_index is being assigned to the u32 variable c2.index and then checked for a negative error condition which is always going to be false. Fix this by assigning the return to the int variable index and checking this instead. Addresses-Coverity: ("Unsigned compared against 0") Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-06 05:38:14 +08:00
c2.index = index;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
act = &rule->flow->action.entries[0];
rule->c2_index = c2.index;
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
c2.tcam[3] = (rule->c2_tcam & 0xffff) |
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
((rule->c2_tcam_mask & 0xffff) << 16);
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
c2.tcam[2] = ((rule->c2_tcam >> 16) & 0xffff) |
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
(((rule->c2_tcam_mask >> 16) & 0xffff) << 16);
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
c2.tcam[1] = ((rule->c2_tcam >> 32) & 0xffff) |
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
(((rule->c2_tcam_mask >> 32) & 0xffff) << 16);
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
c2.tcam[0] = ((rule->c2_tcam >> 48) & 0xffff) |
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
(((rule->c2_tcam_mask >> 48) & 0xffff) << 16);
pmap = BIT(port->id);
c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
/* Match on Lookup Type */
c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_LU_TYPE(MVPP2_CLS_LU_TYPE_MASK));
c2.tcam[4] |= MVPP22_CLS_C2_LU_TYPE(rule->loc);
net: mvpp2: cls: Allow dropping packets with classification offload This commit introduces support for the "Drop" action in classification offload. This corresponds to the "-1" action with ethtool -N. This is achieved using the color marking actions available in the C2 engine, which associate a color to a packet. These colors can be either Green, Yellow or Red, Red meaning that the packet should be dropped. Green and Yellow colors are interpreted by the Policer, which isn't supported yet. This method of dropping using the Classifier is different than the already existing early-drop features, such as VLAN filtering and MAC UC/MC filtering, which are performed during the Parsing step, and therefore take precedence over classification actions. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:29 +08:00
if (act->id == FLOW_ACTION_DROP) {
c2.act = MVPP22_CLS_C2_ACT_COLOR(MVPP22_C2_COL_RED_LOCK);
} else {
/* We want to keep the default color derived from the Header
* Parser drop entries, for VLAN and MAC filtering. This will
* assign a default color of Green or Red, and we want matches
* with a non-drop action to keep that color.
*/
c2.act = MVPP22_CLS_C2_ACT_COLOR(MVPP22_C2_COL_NO_UPD_LOCK);
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
/* Update RSS status after matching this entry */
if (act->queue.ctx)
c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
/* Always lock the RSS_EN decision. We might have high prio
* rules steering to an RXQ, and a lower one steering to RSS,
* we don't want the low prio RSS rule overwriting this flag.
*/
c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
net: mvpp2: cls: Allow dropping packets with classification offload This commit introduces support for the "Drop" action in classification offload. This corresponds to the "-1" action with ethtool -N. This is achieved using the color marking actions available in the C2 engine, which associate a color to a packet. These colors can be either Green, Yellow or Red, Red meaning that the packet should be dropped. Green and Yellow colors are interpreted by the Policer, which isn't supported yet. This method of dropping using the Classifier is different than the already existing early-drop features, such as VLAN filtering and MAC UC/MC filtering, which are performed during the Parsing step, and therefore take precedence over classification actions. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:29 +08:00
/* Mark packet as "forwarded to software", needed for RSS */
c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
net: mvpp2: cls: Allow dropping packets with classification offload This commit introduces support for the "Drop" action in classification offload. This corresponds to the "-1" action with ethtool -N. This is achieved using the color marking actions available in the C2 engine, which associate a color to a packet. These colors can be either Green, Yellow or Red, Red meaning that the packet should be dropped. Green and Yellow colors are interpreted by the Policer, which isn't supported yet. This method of dropping using the Classifier is different than the already existing early-drop features, such as VLAN filtering and MAC UC/MC filtering, which are performed during the Parsing step, and therefore take precedence over classification actions. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:29 +08:00
c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD_LOCK) |
MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD_LOCK);
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
if (act->queue.ctx) {
/* Get the global ctx number */
ctx = mvpp22_rss_ctx(port, act->queue.ctx);
if (ctx < 0)
return -EINVAL;
qh = (ctx >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
ql = ctx & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
} else {
qh = ((act->queue.index + port->first_rxq) >> 3) &
MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
ql = (act->queue.index + port->first_rxq) &
MVPP22_CLS_C2_ATTR0_QLOW_MASK;
}
net: mvpp2: cls: Allow dropping packets with classification offload This commit introduces support for the "Drop" action in classification offload. This corresponds to the "-1" action with ethtool -N. This is achieved using the color marking actions available in the C2 engine, which associate a color to a packet. These colors can be either Green, Yellow or Red, Red meaning that the packet should be dropped. Green and Yellow colors are interpreted by the Policer, which isn't supported yet. This method of dropping using the Classifier is different than the already existing early-drop features, such as VLAN filtering and MAC UC/MC filtering, which are performed during the Parsing step, and therefore take precedence over classification actions. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:29 +08:00
c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
MVPP22_CLS_C2_ATTR0_QLOW(ql);
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
c2.valid = true;
mvpp2_cls_c2_write(port->priv, &c2);
return 0;
}
static int mvpp2_port_c2_rfs_rule_insert(struct mvpp2_port *port,
struct mvpp2_rfs_rule *rule)
{
return mvpp2_port_c2_tcam_rule_add(port, rule);
}
static int mvpp2_port_cls_rfs_rule_remove(struct mvpp2_port *port,
struct mvpp2_rfs_rule *rule)
{
const struct mvpp2_cls_flow *flow;
struct mvpp2_cls_flow_entry fe;
int index, i;
for_each_cls_flow_id_containing_type(i, rule->flow_type) {
flow = mvpp2_cls_flow_get(i);
if (!flow)
return 0;
index = MVPP2_CLS_FLT_C2_RFS(port->id, flow->flow_id, rule->loc);
mvpp2_cls_flow_read(port->priv, index, &fe);
mvpp2_cls_flow_port_remove(&fe, BIT(port->id));
mvpp2_cls_flow_write(port->priv, &fe);
}
if (rule->c2_index >= 0)
mvpp22_port_c2_lookup_disable(port, rule->c2_index);
return 0;
}
static int mvpp2_port_flt_rfs_rule_insert(struct mvpp2_port *port,
struct mvpp2_rfs_rule *rule)
{
const struct mvpp2_cls_flow *flow;
struct mvpp2 *priv = port->priv;
struct mvpp2_cls_flow_entry fe;
int index, ret, i;
if (rule->engine != MVPP22_CLS_ENGINE_C2)
return -EOPNOTSUPP;
ret = mvpp2_port_c2_rfs_rule_insert(port, rule);
if (ret)
return ret;
for_each_cls_flow_id_containing_type(i, rule->flow_type) {
flow = mvpp2_cls_flow_get(i);
if (!flow)
return 0;
net: mvpp2: cls: Only select applicable flows of classification offload The way we currently handle classification offload and RSS is by having dedicated lookup sequences in the flow table, each being selected depending on several fields being present in the packet header. We need to make sure the classification operation we want to perform can be done in each flow we want to insert it into. As an example, classifying on VLAN tag can only be done on flows used for tagged traffic. This commit makes sure we don't insert rules in flows we aren't compatible with. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:17 +08:00
if ((rule->hek_fields & flow->supported_hash_opts) != rule->hek_fields)
continue;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
index = MVPP2_CLS_FLT_C2_RFS(port->id, flow->flow_id, rule->loc);
mvpp2_cls_flow_read(priv, index, &fe);
mvpp2_cls_flow_eng_set(&fe, rule->engine);
mvpp2_cls_flow_port_id_sel(&fe, true);
mvpp2_flow_set_hek_fields(&fe, rule->hek_fields);
mvpp2_cls_flow_lu_type_set(&fe, rule->loc);
mvpp2_cls_flow_port_add(&fe, 0xf);
mvpp2_cls_flow_write(priv, &fe);
}
return 0;
}
static int mvpp2_cls_c2_build_match(struct mvpp2_rfs_rule *rule)
{
struct flow_rule *flow = rule->flow;
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
int offs = 0;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
net: mvpp2: cls: Add steering based on vlan Id and priority. This commit allows using the vlan Id and priority as parts of the key for classification offload. These fields are extracted from the outermost tag, if multiple tags are present. Vlan Id and priority are considered as 2 different fields by the classifier, however the fields are both appended in the Header Extracted Key in the same layout as they are found in the tags. This means that when steering only based on the prio, a 16-bit slot is still taken in the HEK. The classifier doesn't allow extracting the DEI bit from the tag, so we explicitly prevent user from using this bit in the key. This commit adds the vlan priotity as a compatible HEK field for tagged traffic, meaning that we limit the possibility of extracting this field only to the flows that contain tagged traffic. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:19 +08:00
/* The order of insertion in C2 tcam must match the order in which
* the fields are found in the header
*/
if (flow_rule_match_key(flow, FLOW_DISSECTOR_KEY_VLAN)) {
struct flow_match_vlan match;
flow_rule_match_vlan(flow, &match);
if (match.mask->vlan_id) {
rule->hek_fields |= MVPP22_CLS_HEK_OPT_VLAN;
rule->c2_tcam |= ((u64)match.key->vlan_id) << offs;
rule->c2_tcam_mask |= ((u64)match.mask->vlan_id) << offs;
/* Don't update the offset yet */
}
if (match.mask->vlan_priority) {
rule->hek_fields |= MVPP22_CLS_HEK_OPT_VLAN_PRI;
/* VLAN pri is always at offset 13 relative to the
* current offset
*/
rule->c2_tcam |= ((u64)match.key->vlan_priority) <<
(offs + 13);
rule->c2_tcam_mask |= ((u64)match.mask->vlan_priority) <<
(offs + 13);
}
if (match.mask->vlan_dei)
return -EOPNOTSUPP;
/* vlan id and prio always seem to take a full 16-bit slot in
* the Header Extracted Key.
*/
offs += 16;
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
if (flow_rule_match_key(flow, FLOW_DISSECTOR_KEY_PORTS)) {
struct flow_match_ports match;
flow_rule_match_ports(flow, &match);
if (match.mask->src) {
rule->hek_fields |= MVPP22_CLS_HEK_OPT_L4SIP;
rule->c2_tcam |= ((u64)ntohs(match.key->src)) << offs;
rule->c2_tcam_mask |= ((u64)ntohs(match.mask->src)) << offs;
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
offs += mvpp2_cls_hek_field_size(MVPP22_CLS_HEK_OPT_L4SIP);
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
}
if (match.mask->dst) {
rule->hek_fields |= MVPP22_CLS_HEK_OPT_L4DIP;
rule->c2_tcam |= ((u64)ntohs(match.key->dst)) << offs;
rule->c2_tcam_mask |= ((u64)ntohs(match.mask->dst)) << offs;
net: mvpp2: cls: right-justify the C2 TCAM keys The C2 TCAM used for classification uses a key (Header Extracted Key) built by concatenating several fields extracted from the packet header. After a lot of trial-and-error and some guess work, it seems the HEK is right justified, with the first fields being stored in the MSB, then concatenated up until the LSB. Until now, this doesn't cause any issue since all HEK fields we use are full bytes. However this is an issue for the upcoming VLAN id and pri extraction, which aren't full bytes. Rework the way we built that TCAM key, by changing the order in which we append the fields. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-18 22:55:18 +08:00
offs += mvpp2_cls_hek_field_size(MVPP22_CLS_HEK_OPT_L4DIP);
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
}
}
if (hweight16(rule->hek_fields) > MVPP2_FLOW_N_FIELDS)
return -EOPNOTSUPP;
return 0;
}
static int mvpp2_cls_rfs_parse_rule(struct mvpp2_rfs_rule *rule)
{
struct flow_rule *flow = rule->flow;
struct flow_action_entry *act;
act = &flow->action.entries[0];
net: mvpp2: cls: Allow dropping packets with classification offload This commit introduces support for the "Drop" action in classification offload. This corresponds to the "-1" action with ethtool -N. This is achieved using the color marking actions available in the C2 engine, which associate a color to a packet. These colors can be either Green, Yellow or Red, Red meaning that the packet should be dropped. Green and Yellow colors are interpreted by the Policer, which isn't supported yet. This method of dropping using the Classifier is different than the already existing early-drop features, such as VLAN filtering and MAC UC/MC filtering, which are performed during the Parsing step, and therefore take precedence over classification actions. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:29 +08:00
if (act->id != FLOW_ACTION_QUEUE && act->id != FLOW_ACTION_DROP)
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
return -EOPNOTSUPP;
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
/* When both an RSS context and an queue index are set, the index
* is considered as an offset to be added to the indirection table
* entries. We don't support this, so reject this rule.
*/
if (act->queue.ctx && act->queue.index)
return -EOPNOTSUPP;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
/* For now, only use the C2 engine which has a HEK size limited to 64
* bits for TCAM matching.
*/
rule->engine = MVPP22_CLS_ENGINE_C2;
if (mvpp2_cls_c2_build_match(rule))
return -EINVAL;
return 0;
}
int mvpp2_ethtool_cls_rule_get(struct mvpp2_port *port,
struct ethtool_rxnfc *rxnfc)
{
struct mvpp2_ethtool_fs *efs;
net: mvpp2: cls: Use the correct number of rules in various places As of today, the classification offload implementation only supports 4 different rules to be offloaded. This number has been hardcoded in the rule insertion function, and the wrong define is being used elsewhere. Use the correct #define everywhere to make sure we always check for the correct number of rules. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:50 +08:00
if (rxnfc->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
return -EINVAL;
efs = port->rfs_rules[rxnfc->fs.location];
if (!efs)
return -ENOENT;
memcpy(rxnfc, &efs->rxnfc, sizeof(efs->rxnfc));
return 0;
}
int mvpp2_ethtool_cls_rule_ins(struct mvpp2_port *port,
struct ethtool_rxnfc *info)
{
struct ethtool_rx_flow_spec_input input = {};
struct ethtool_rx_flow_rule *ethtool_rule;
struct mvpp2_ethtool_fs *efs, *old_efs;
int ret = 0;
net: mvpp2: cls: Remove unnessesary check in mvpp2_ethtool_cls_rule_ins Fix smatch warning: drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c:1236 mvpp2_ethtool_cls_rule_ins() warn: unsigned 'info->fs.location' is never less than zero. 'info->fs.location' is u32 type, never less than zero. Signed-off-by: YueHaibing <yuehaibing@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-29 10:59:06 +08:00
if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW)
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
return -EINVAL;
efs = kzalloc(sizeof(*efs), GFP_KERNEL);
if (!efs)
return -ENOMEM;
input.fs = &info->fs;
net: mvpp2: cls: Extract the RSS context when parsing the ethtool rule ethtool_rx_flow_rule_create takes into parameter the ethtool flow spec, which doesn't contain the rss context id. We therefore need to extract it ourself before parsing the ethtool rule. The FLOW_RSS flag is only set in info->fs.flow_type, and not info->flow_type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:53 +08:00
/* We need to manually set the rss_ctx, since this info isn't present
* in info->fs
*/
if (info->fs.flow_type & FLOW_RSS)
input.rss_ctx = info->rss_context;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
ethtool_rule = ethtool_rx_flow_rule_create(&input);
if (IS_ERR(ethtool_rule)) {
ret = PTR_ERR(ethtool_rule);
goto clean_rule;
}
efs->rule.flow = ethtool_rule->rule;
efs->rule.flow_type = mvpp2_cls_ethtool_flow_to_type(info->fs.flow_type);
net: mvpp2: cls: Report an error for unsupported flow types Add a missing check to detect flow types that we don't support, so that user can be informed of this. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-05 20:09:12 +08:00
if (efs->rule.flow_type < 0) {
ret = efs->rule.flow_type;
goto clean_rule;
}
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
ret = mvpp2_cls_rfs_parse_rule(&efs->rule);
if (ret)
goto clean_eth_rule;
efs->rule.loc = info->fs.location;
/* Replace an already existing rule */
if (port->rfs_rules[efs->rule.loc]) {
old_efs = port->rfs_rules[efs->rule.loc];
ret = mvpp2_port_cls_rfs_rule_remove(port, &old_efs->rule);
if (ret)
goto clean_eth_rule;
kfree(old_efs);
port->n_rfs_rules--;
}
ret = mvpp2_port_flt_rfs_rule_insert(port, &efs->rule);
if (ret)
goto clean_eth_rule;
net: mvpp2: cls: Fix leaked ethtool_rx_flow_rule The flow_rule is only used when configuring the classification tables, and should be free'd once we're done using it. The current code only frees it in the error path. Fixes: 90b509b39ac9 ("net: mvpp2: cls: Add Classification offload support") Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-23 16:47:24 +08:00
ethtool_rx_flow_rule_destroy(ethtool_rule);
efs->rule.flow = NULL;
net: mvpp2: cls: Add Classification offload support This commit introduces basic classification offloading support for the PPv2 controller. The PPv2 classifier has many classification engines, for now we only use the C2 TCAM match engine. This engine allows to perform ternary lookups on 64 bits keys (called Header Extracted Key), that are built by extracting fields from the packet header and concatenating them. At most 4 fields can be extracted for a single lookup. This basic implementation allows to build the HEK from the following fields : - L4 source and destination ports (for UDP and TCP) More fields are to be added in the future. Classification flows are added through the ethtool interface, using the newly introduced flow_rule infrastructure as an internal rule representation, allowing to more easily implement tc flower rules if need be. The internal design for now allocates one range of 4 rules per port due to the internal design of the flow table, which uses 22 sub-flows. When inserting a classification rule, the rule is created in every relevant sub-flow. This low rule-count is a very simple design which reaches quickly the limitations of the flow table ordering, but guarantees that the rule ordering will always be respected. This commit only introduces support for the "steer to rxq" action. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:28 +08:00
memcpy(&efs->rxnfc, info, sizeof(*info));
port->rfs_rules[efs->rule.loc] = efs;
port->n_rfs_rules++;
return ret;
clean_eth_rule:
ethtool_rx_flow_rule_destroy(ethtool_rule);
clean_rule:
kfree(efs);
return ret;
}
int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port,
struct ethtool_rxnfc *info)
{
struct mvpp2_ethtool_fs *efs;
int ret;
efs = port->rfs_rules[info->fs.location];
if (!efs)
return -EINVAL;
/* Remove the rule from the engines. */
ret = mvpp2_port_cls_rfs_rule_remove(port, &efs->rule);
if (ret)
return ret;
port->n_rfs_rules--;
port->rfs_rules[info->fs.location] = NULL;
kfree(efs);
return 0;
}
net: mvpp2: improve the distribution of packets on CPUs when using RSS This patch adds an extra indirection when setting the indirection table into the RSS hardware table to improve the packets distribution across CPUs. For example, if 2 queues are used on a multi-core system this new indirection will choose two queues on two different CPUs instead of the two first queues which are on the same first CPU. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:21 +08:00
static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
{
net: mvpp2: make sure we don't spread load on disabled CPUs When filling the RSS table, we have to make sure that the rx queue is attached to an online CPU. This patch is not a full support for cpu_hotplug, but rather a way to make sure that we don't break network on system booted with the maxcpus parameter. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:22 +08:00
int nrxqs, cpu, cpus = num_possible_cpus();
net: mvpp2: improve the distribution of packets on CPUs when using RSS This patch adds an extra indirection when setting the indirection table into the RSS hardware table to improve the packets distribution across CPUs. For example, if 2 queues are used on a multi-core system this new indirection will choose two queues on two different CPUs instead of the two first queues which are on the same first CPU. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:21 +08:00
/* Number of RXQs per CPU */
nrxqs = port->nrxqs / cpus;
net: mvpp2: make sure we don't spread load on disabled CPUs When filling the RSS table, we have to make sure that the rx queue is attached to an online CPU. This patch is not a full support for cpu_hotplug, but rather a way to make sure that we don't break network on system booted with the maxcpus parameter. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:22 +08:00
/* CPU that will handle this rx queue */
cpu = rxq / nrxqs;
if (!cpu_online(cpu))
return port->first_rxq;
net: mvpp2: improve the distribution of packets on CPUs when using RSS This patch adds an extra indirection when setting the indirection table into the RSS hardware table to improve the packets distribution across CPUs. For example, if 2 queues are used on a multi-core system this new indirection will choose two queues on two different CPUs instead of the two first queues which are on the same first CPU. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:21 +08:00
/* Indirection to better distribute the paquets on the CPUs when
* configuring the RSS queues.
*/
return port->first_rxq + ((rxq * nrxqs + rxq / cpus) % port->nrxqs);
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
static void mvpp22_rss_fill_table(struct mvpp2_port *port,
struct mvpp2_rss_table *table,
u32 rss_ctx)
net: mvpp2: RSS indirection table support This patch adds the RSS indirection table support, allowing to use the ethtool -x and -X options to dump and set this table. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> [Maxime: Small warning fixes, use one table per port] Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:20 +08:00
{
struct mvpp2 *priv = port->priv;
int i;
for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
u32 sel = MVPP22_RSS_INDEX_TABLE(rss_ctx) |
net: mvpp2: RSS indirection table support This patch adds the RSS indirection table support, allowing to use the ethtool -x and -X options to dump and set this table. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> [Maxime: Small warning fixes, use one table per port] Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:20 +08:00
MVPP22_RSS_INDEX_TABLE_ENTRY(i);
mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
net: mvpp2: improve the distribution of packets on CPUs when using RSS This patch adds an extra indirection when setting the indirection table into the RSS hardware table to improve the packets distribution across CPUs. For example, if 2 queues are used on a multi-core system this new indirection will choose two queues on two different CPUs instead of the two first queues which are on the same first CPU. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:21 +08:00
mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY,
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
mvpp22_rxfh_indir(port, table->indir[i]));
}
}
static int mvpp22_rss_context_create(struct mvpp2_port *port, u32 *rss_ctx)
{
struct mvpp2 *priv = port->priv;
u32 ctx;
/* Find the first free RSS table */
for (ctx = 0; ctx < MVPP22_N_RSS_TABLES; ctx++) {
if (!priv->rss_tables[ctx])
break;
}
if (ctx == MVPP22_N_RSS_TABLES)
return -EINVAL;
priv->rss_tables[ctx] = kzalloc(sizeof(*priv->rss_tables[ctx]),
GFP_KERNEL);
if (!priv->rss_tables[ctx])
return -ENOMEM;
*rss_ctx = ctx;
/* Set the table width: replace the whole classifier Rx queue number
* with the ones configured in RSS table entries.
*/
mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(ctx));
mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(ctx));
mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE, MVPP22_RSS_TABLE_POINTER(ctx));
return 0;
}
int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *port_ctx)
{
u32 rss_ctx;
int ret, i;
ret = mvpp22_rss_context_create(port, &rss_ctx);
if (ret)
return ret;
/* Find the first available context number in the port, starting from 1.
* Context 0 on each port is reserved for the default context.
*/
for (i = 1; i < MVPP22_N_RSS_TABLES; i++) {
if (port->rss_ctx[i] < 0)
break;
net: mvpp2: RSS indirection table support This patch adds the RSS indirection table support, allowing to use the ethtool -x and -X options to dump and set this table. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> [Maxime: Small warning fixes, use one table per port] Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:20 +08:00
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
net: mvpp2: cls: Check RSS table index validity when creating a context Make sure we don't use an out-of-bound index for the per-port RSS context array. As of today, the global context creation in mvpp22_rss_context_create will prevent us from reaching this case, but we should still make sure we are using a sane value anyway. Reported-by: kbuild test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-27 19:52:01 +08:00
if (i == MVPP22_N_RSS_TABLES)
return -EINVAL;
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
port->rss_ctx[i] = rss_ctx;
*port_ctx = i;
return 0;
}
static struct mvpp2_rss_table *mvpp22_rss_table_get(struct mvpp2 *priv,
int rss_ctx)
{
if (rss_ctx < 0 || rss_ctx >= MVPP22_N_RSS_TABLES)
return NULL;
return priv->rss_tables[rss_ctx];
}
int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 port_ctx)
{
struct mvpp2 *priv = port->priv;
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
struct ethtool_rxnfc *rxnfc;
int i, rss_ctx, ret;
rss_ctx = mvpp22_rss_ctx(port, port_ctx);
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
if (rss_ctx < 0 || rss_ctx >= MVPP22_N_RSS_TABLES)
return -EINVAL;
net: mvpp2: cls: Support steering to RSS contexts When steering to an RXQ, we can perform an extra RSS step to assign a queue from an RSS table. This is done by setting the RSS_EN attribute in the C2 engine. In that case, the RXQ that is assigned is the global RSS context id, that is then translated to an RSS table using the RXQ2RSS table. An example using ethtool to steer to RXQ 2 and 3 would be : ethtool -X eth0 weight 0 0 1 1 context new (This would print the allocated context id, let's say it's 1) ethtool -N eth0 flow-type udp4 dst-port 1234 context 1 loc 0 The hash parameters are the ones that are globally configured for RSS : ethtool -N eth0 rx-flow-hash udp4 sdfn When an RSS context is removed while there are active classification rules using this context, these rules are removed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:54 +08:00
/* Invalidate any active classification rule that use this context */
for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
if (!port->rfs_rules[i])
continue;
rxnfc = &port->rfs_rules[i]->rxnfc;
if (!(rxnfc->fs.flow_type & FLOW_RSS) ||
rxnfc->rss_context != port_ctx)
continue;
ret = mvpp2_ethtool_cls_rule_del(port, rxnfc);
if (ret) {
netdev_warn(port->dev,
"couldn't remove classification rule %d associated to this context",
rxnfc->fs.location);
}
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
kfree(priv->rss_tables[rss_ctx]);
priv->rss_tables[rss_ctx] = NULL;
port->rss_ctx[port_ctx] = -1;
return 0;
}
int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 port_ctx,
const u32 *indir)
{
int rss_ctx = mvpp22_rss_ctx(port, port_ctx);
struct mvpp2_rss_table *rss_table = mvpp22_rss_table_get(port->priv,
rss_ctx);
if (!rss_table)
return -EINVAL;
memcpy(rss_table->indir, indir,
MVPP22_RSS_TABLE_ENTRIES * sizeof(rss_table->indir[0]));
mvpp22_rss_fill_table(port, rss_table, rss_ctx);
return 0;
}
int mvpp22_port_rss_ctx_indir_get(struct mvpp2_port *port, u32 port_ctx,
u32 *indir)
{
int rss_ctx = mvpp22_rss_ctx(port, port_ctx);
struct mvpp2_rss_table *rss_table = mvpp22_rss_table_get(port->priv,
rss_ctx);
if (!rss_table)
return -EINVAL;
memcpy(indir, rss_table->indir,
MVPP22_RSS_TABLE_ENTRIES * sizeof(rss_table->indir[0]));
return 0;
net: mvpp2: RSS indirection table support This patch adds the RSS indirection table support, allowing to use the ethtool -x and -X options to dump and set this table. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> [Maxime: Small warning fixes, use one table per port] Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:20 +08:00
}
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
{
u16 hash_opts = 0;
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
u32 flow_type;
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
flow_type = mvpp2_cls_ethtool_flow_to_type(info->flow_type);
switch (flow_type) {
case MVPP22_FLOW_TCP4:
case MVPP22_FLOW_UDP4:
case MVPP22_FLOW_TCP6:
case MVPP22_FLOW_UDP6:
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
if (info->data & RXH_L4_B_0_1)
hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
if (info->data & RXH_L4_B_2_3)
hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
/* Fallthrough */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
case MVPP22_FLOW_IP4:
case MVPP22_FLOW_IP6:
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
if (info->data & RXH_L2DA)
hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
if (info->data & RXH_VLAN)
hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
if (info->data & RXH_L3_PROTO)
hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
if (info->data & RXH_IP_SRC)
hash_opts |= (MVPP22_CLS_HEK_OPT_IP4SA |
MVPP22_CLS_HEK_OPT_IP6SA);
if (info->data & RXH_IP_DST)
hash_opts |= (MVPP22_CLS_HEK_OPT_IP4DA |
MVPP22_CLS_HEK_OPT_IP6DA);
break;
default: return -EOPNOTSUPP;
}
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
return mvpp2_port_rss_hash_opts_set(port, flow_type, hash_opts);
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
}
int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
{
unsigned long hash_opts;
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
u32 flow_type;
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
int i;
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
flow_type = mvpp2_cls_ethtool_flow_to_type(info->flow_type);
hash_opts = mvpp2_port_rss_hash_opts_get(port, flow_type);
net: mvpp2: allow setting RSS flow hash parameters with ethtool This commit allows setting the RSS hash generation parameters from ethtool. When setting parameters for a given flow type from ethtool (e.g. tcp4), all the corresponding flows in the flow table are updated, according to the supported hash parameters. For example, when configuring TCP over IPv4 hash parameters to be src/dst IP + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"), we only set the "src/dst port" hash parameters on the non-fragmented TCP over IPv4 flows. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:27 +08:00
info->data = 0;
for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
switch (BIT(i)) {
case MVPP22_CLS_HEK_OPT_MAC_DA:
info->data |= RXH_L2DA;
break;
case MVPP22_CLS_HEK_OPT_VLAN:
info->data |= RXH_VLAN;
break;
case MVPP22_CLS_HEK_OPT_L3_PROTO:
info->data |= RXH_L3_PROTO;
break;
case MVPP22_CLS_HEK_OPT_IP4SA:
case MVPP22_CLS_HEK_OPT_IP6SA:
info->data |= RXH_IP_SRC;
break;
case MVPP22_CLS_HEK_OPT_IP4DA:
case MVPP22_CLS_HEK_OPT_IP6DA:
info->data |= RXH_IP_DST;
break;
case MVPP22_CLS_HEK_OPT_L4SIP:
info->data |= RXH_L4_B_0_1;
break;
case MVPP22_CLS_HEK_OPT_L4DIP:
info->data |= RXH_L4_B_2_3;
break;
default:
return -EINVAL;
}
}
return 0;
}
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
int mvpp22_port_rss_init(struct mvpp2_port *port)
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
{
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
struct mvpp2_rss_table *table;
u32 context = 0;
int i, ret;
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
for (i = 0; i < MVPP22_N_RSS_TABLES; i++)
port->rss_ctx[i] = -1;
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
ret = mvpp22_rss_context_create(port, &context);
if (ret)
return ret;
table = mvpp22_rss_table_get(port->priv, context);
if (!table)
return -EINVAL;
port->rss_ctx[0] = context;
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
/* Configure the first table to evenly distribute the packets across
net: mvpp2: fix a typo in the RSS code Cosmetic patch fixing a typo in one of the RSS comments. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:17 +08:00
* real Rx Queues. The table entries map a hash to a port Rx Queue.
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
*/
net: mvpp2: RSS indirection table support This patch adds the RSS indirection table support, allowing to use the ethtool -x and -X options to dump and set this table. Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com> [Maxime: Small warning fixes, use one table per port] Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:20 +08:00
for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++)
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
table->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
mvpp22_rss_fill_table(port, table, mvpp22_rss_ctx(port, 0));
net: mvpp2: add an RSS classification step for each flow One of the classification action that can be performed is to compute a hash of the packet header based on some header fields, and lookup a RSS table based on this hash to determine the final RxQ. This is done by adding one lookup entry per flow per port, so that we can configure the hash generation parameters for each flow and each port. There are 2 possible engines that can be used for RSS hash generation : - C3HA, that generates a hash based on up to 4 header-extracted fields - C3HB, that does the same as c3HA, but also includes L4 info in the hash There are a lot of fields that can be extracted from the header. For now, we only use the ones that we can configure using ethtool : - DST MAC address - L3 info - Source IP - Destination IP - Source port - Destination port The C3HB engine is selected when we use L4 fields (src/dst port). Header parser Dec table Ingress pkt +-------------+ flow id +----------------------------+ ------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag | +-------------+ |TCP IPv4 w/o VLAN, not frag | |TCP IPv4 w/ VLAN, frag |--+ |etc. | | +----------------------------+ | | Flow table | +---------+ +------------+ +--------------------------+ | | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup | | +---------+ +------------+ | C3 lookup port 0 | | | | | C3 lookup port 1 | | +-----------+ +-------------+ | ... | | | C2 engine | | C3H engines | | flow 1: C2 lookup |<--+ +-----------+ +-------------+ | C3 lookup port 0 | | ... | | ... | | flow 51 : C2 lookup | | ... | +--------------------------+ The C2 engine also gains the role of enabling and disabling the RSS table lookup for this packet. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-12 19:54:26 +08:00
/* Configure default flows */
net: mvpp2: cls: Use a bitfield to represent the flow_type As of today, the classification code is used only for RSS. We split the incoming traffic into multiple flows, that correspond to the ethtool flow_type parameter. We don't want to use the ethtool flow definitions such as TCP_V4_FLOW, for several reason : - We want to decorrelate the driver code from ethtool as much as possible, so that we can easily use other interfaces such as tc flower, - We want the flow_type to be a bitfield, so that we can match flows embedded into each other, such as TCP4 which is a subset of IP4. This commit does the conversion to the newer type. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-30 21:14:27 +08:00
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_IP4, MVPP22_CLS_HEK_IP4_2T);
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_IP6, MVPP22_CLS_HEK_IP6_2T);
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_TCP4, MVPP22_CLS_HEK_IP4_5T);
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_TCP6, MVPP22_CLS_HEK_IP6_5T);
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_UDP4, MVPP22_CLS_HEK_IP4_5T);
mvpp2_port_rss_hash_opts_set(port, MVPP22_FLOW_UDP6, MVPP22_CLS_HEK_IP6_5T);
net: mvpp2: cls: Use RSS contexts to handle RSS tables The PPv2 controller has 8 RSS tables that are shared across all ports on a given PPv2 instance. The previous implementation allocated one table per port, leaving others unused. By using RSS contexts, we can make use of multiple RSS tables per port, one being the default table (always id 0), the other ones being used as destinations for flow steering, in the same way as rx rings. This commit introduces RSS contexts management in the PPv2 driver. We always reserve one table per port, allocated when the port is probed. The global table list is stored in the struct mvpp2, as it's a global resource. Each port then maintains a list of indices in that global table, that way each port can have it's own numbering scheme starting from 0. One limitation that seems unavoidable is that the hashing parameters are shared across all RSS contexts for a given port. Hashing parameters for ctx 0 will be applied to all contexts. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-24 18:05:52 +08:00
return 0;
net: mvpp2: Split the PPv2 driver to a dedicated directory As the mvpp2 driver is growing, move this driver to a dedicated directory and split it into several files. Since this driver has a lot of register defines and structure definitions, it can benefit from having all of this into a dedicated header file, named mvpp2.h. A good chunk of the mvpp2 code is dedicated to Header Parser handling, so we introduce mvpp2_prs.h where all Header Parser definitions are located, and mvpp2_prs.c containing the related code. In the same way, mvpp2_cls.h and mvpp2_cls.c are created to contain Classifier and RSS related code. The former 'mvpp2.c' file is renamed 'mvpp2_main.c' so that we can keep the driver binary named 'mvpp2'. This commit is only about spliting the driver into multiple files and doesn't introduce any new function, feature or fix besides removing 'static' keywords when needed. Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Tested-by: Antoine Tenart <antoine.tenart@bootlin.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-31 16:07:43 +08:00
}