From 743edc0cad80722bdaaf025cbd98bd869d11dd6e Mon Sep 17 00:00:00 2001 From: kram Date: Thu, 2 Nov 2017 17:11:14 -0700 Subject: [PATCH] initial barefoot checkin october 2017 --- .gitmodules | 6 +- .../installer.conf | 1 + .../minigraph.xml | 1079 ++++++++ .../montara/port_config.ini | 33 + .../installer.conf | 1 + .../mavericks/port_config.ini | 66 + .../minigraph.xml | 1079 ++++++++ dockers/docker-bfn-sswsyncd-rpc/Dockerfile | 38 + dockers/docker-bfn-sswsyncd/Dockerfile | 17 + dockers/docker-orchagent-bfn | 1 + dockers/docker-orchagent/orchagent.sh | 2 + dockers/docker-saiserver-bfn/Dockerfile | 38 + dockers/docker-saiserver-bfn/portmap.ini | 33 + dockers/docker-saiserver-bfn/profile.ini | 1 + dockers/docker-saiserver-bfn/sai_tofino.xml | 2 + dockers/docker-saiserver-bfn/start.sh | 16 + dockers/docker-saiserver-bfn/supervisord.conf | 29 + files/image_config/interfaces/interfaces.j2 | 5 + platform/barefoot/bfn-sai.mk | 6 + platform/barefoot/docker-orchagent-bfn.mk | 18 + platform/barefoot/docker-ptf-bfn.mk | 5 + platform/barefoot/docker-syncd-bfn-rpc.mk | 15 + .../docker-syncd-bfn-rpc/Dockerfile.j2 | 52 + .../docker-syncd-bfn-rpc/ptf_nn_agent.conf | 10 + platform/barefoot/docker-syncd-bfn.mk | 15 + .../barefoot/docker-syncd-bfn/Dockerfile.j2 | 29 + platform/barefoot/docker-syncd-bfn/start.sh | 9 + .../docker-syncd-bfn/supervisord.conf | 29 + platform/barefoot/libsaithrift-dev.mk | 7 + platform/barefoot/one-image.mk | 11 + .../barefoot/platform-modules-bfn-montara.mk | 11 + platform/barefoot/platform-modules-bfn.mk | 11 + platform/barefoot/platform.conf | 0 platform/barefoot/python-saithrift.mk | 6 + platform/barefoot/rules.mk | 19 + .../LICENSE | 15 + .../MAINTAINERS | 7 + .../README.md | 2 + .../debian/changelog | 5 + .../debian/compat | 1 + .../debian/control | 12 + .../debian/copyright | 15 + .../debian/files | 1 + .../debian/rules | 32 + .../modules/Makefile | 1 + .../modules/bf_kdrv.c | 1 + .../modules/bf_tun.c | 1 + .../scripts/test | 1 + .../sonic-platform-modules-bfn/LICENSE | 15 + .../sonic-platform-modules-bfn/MAINTAINERS | 7 + .../sonic-platform-modules-bfn/README.md | 2 + .../debian/changelog | 5 + .../sonic-platform-modules-bfn/debian/compat | 1 + .../sonic-platform-modules-bfn/debian/control | 12 + .../debian/copyright | 15 + .../sonic-platform-modules-bfn/debian/files | 1 + .../sonic-platform-modules-bfn/debian/rules | 32 + .../modules/Makefile | 2 + .../modules/bf_kdrv.c | 1152 ++++++++ .../modules/bf_tun.c | 2396 +++++++++++++++++ .../sonic-platform-modules-bfn/scripts/test | 1 + sonic-slave/Dockerfile | 3 + .../tests/sample_output/interfaces | 5 + src/sonic-sairedis | 2 +- src/sonic-swss | 2 +- 65 files changed, 6442 insertions(+), 5 deletions(-) create mode 100644 device/barefoot/x86_64-accton_wedge100bf_32x-r0/installer.conf create mode 100644 device/barefoot/x86_64-accton_wedge100bf_32x-r0/minigraph.xml create mode 100644 device/barefoot/x86_64-accton_wedge100bf_32x-r0/montara/port_config.ini create mode 100644 device/barefoot/x86_64-accton_wedge100bf_65x-r0/installer.conf create mode 100644 device/barefoot/x86_64-accton_wedge100bf_65x-r0/mavericks/port_config.ini create mode 100644 device/barefoot/x86_64-accton_wedge100bf_65x-r0/minigraph.xml create mode 100644 dockers/docker-bfn-sswsyncd-rpc/Dockerfile create mode 100755 dockers/docker-bfn-sswsyncd/Dockerfile create mode 120000 dockers/docker-orchagent-bfn create mode 100755 dockers/docker-saiserver-bfn/Dockerfile create mode 100644 dockers/docker-saiserver-bfn/portmap.ini create mode 100644 dockers/docker-saiserver-bfn/profile.ini create mode 100644 dockers/docker-saiserver-bfn/sai_tofino.xml create mode 100755 dockers/docker-saiserver-bfn/start.sh create mode 100644 dockers/docker-saiserver-bfn/supervisord.conf create mode 100644 platform/barefoot/bfn-sai.mk create mode 100644 platform/barefoot/docker-orchagent-bfn.mk create mode 100644 platform/barefoot/docker-ptf-bfn.mk create mode 100644 platform/barefoot/docker-syncd-bfn-rpc.mk create mode 100644 platform/barefoot/docker-syncd-bfn-rpc/Dockerfile.j2 create mode 100644 platform/barefoot/docker-syncd-bfn-rpc/ptf_nn_agent.conf create mode 100644 platform/barefoot/docker-syncd-bfn.mk create mode 100755 platform/barefoot/docker-syncd-bfn/Dockerfile.j2 create mode 100755 platform/barefoot/docker-syncd-bfn/start.sh create mode 100644 platform/barefoot/docker-syncd-bfn/supervisord.conf create mode 100644 platform/barefoot/libsaithrift-dev.mk create mode 100644 platform/barefoot/one-image.mk create mode 100644 platform/barefoot/platform-modules-bfn-montara.mk create mode 100644 platform/barefoot/platform-modules-bfn.mk create mode 100644 platform/barefoot/platform.conf create mode 100644 platform/barefoot/python-saithrift.mk create mode 100644 platform/barefoot/rules.mk create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/LICENSE create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/MAINTAINERS create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/README.md create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/debian/changelog create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/debian/compat create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/debian/control create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/debian/copyright create mode 100644 platform/barefoot/sonic-platform-modules-bfn-montara/debian/files create mode 100755 platform/barefoot/sonic-platform-modules-bfn-montara/debian/rules create mode 120000 platform/barefoot/sonic-platform-modules-bfn-montara/modules/Makefile create mode 120000 platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_kdrv.c create mode 120000 platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_tun.c create mode 100755 platform/barefoot/sonic-platform-modules-bfn-montara/scripts/test create mode 100644 platform/barefoot/sonic-platform-modules-bfn/LICENSE create mode 100644 platform/barefoot/sonic-platform-modules-bfn/MAINTAINERS create mode 100644 platform/barefoot/sonic-platform-modules-bfn/README.md create mode 100644 platform/barefoot/sonic-platform-modules-bfn/debian/changelog create mode 100644 platform/barefoot/sonic-platform-modules-bfn/debian/compat create mode 100644 platform/barefoot/sonic-platform-modules-bfn/debian/control create mode 100644 platform/barefoot/sonic-platform-modules-bfn/debian/copyright create mode 100644 platform/barefoot/sonic-platform-modules-bfn/debian/files create mode 100755 platform/barefoot/sonic-platform-modules-bfn/debian/rules create mode 100644 platform/barefoot/sonic-platform-modules-bfn/modules/Makefile create mode 100644 platform/barefoot/sonic-platform-modules-bfn/modules/bf_kdrv.c create mode 100644 platform/barefoot/sonic-platform-modules-bfn/modules/bf_tun.c create mode 100755 platform/barefoot/sonic-platform-modules-bfn/scripts/test diff --git a/.gitmodules b/.gitmodules index c837451c94..bbd7722d15 100644 --- a/.gitmodules +++ b/.gitmodules @@ -1,15 +1,15 @@ [submodule "sonic-swss-common"] path = src/sonic-swss-common - url = https://github.com/Azure/sonic-swss-common + url = https://github.com/barefootnetworks/sonic-swss-common [submodule "sonic-linux-kernel"] path = src/sonic-linux-kernel url = https://github.com/Azure/sonic-linux-kernel [submodule "sonic-sairedis"] path = src/sonic-sairedis - url = https://github.com/Azure/sonic-sairedis + url = https://github.com/barefootnetworks/sonic-sairedis [submodule "sonic-swss"] path = src/sonic-swss - url = https://github.com/Azure/sonic-swss + url = https://github.com/barefootnetworks/sonic-swss [submodule "src/p4-switch/switch"] path = platform/p4/p4-switch/switch url = https://github.com/krambn/switch diff --git a/device/barefoot/x86_64-accton_wedge100bf_32x-r0/installer.conf b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/installer.conf new file mode 100644 index 0000000000..3714ff053b --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/installer.conf @@ -0,0 +1 @@ +CONSOLE_SPEED=57600 diff --git a/device/barefoot/x86_64-accton_wedge100bf_32x-r0/minigraph.xml b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/minigraph.xml new file mode 100644 index 0000000000..20637fc434 --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/minigraph.xml @@ -0,0 +1,1079 @@ + + + + + + ARISTA01T0 + 10.0.0.33 + switch2 + 10.0.0.32 + 1 + 180 + 60 + + + switch2 + 10.0.0.0 + ARISTA01T2 + 10.0.0.1 + 1 + 180 + 60 + + + ARISTA02T0 + 10.0.0.35 + switch2 + 10.0.0.34 + 1 + 180 + 60 + + + switch2 + 10.0.0.2 + ARISTA02T2 + 10.0.0.3 + 1 + 180 + 60 + + + ARISTA03T0 + 10.0.0.37 + switch2 + 10.0.0.36 + 1 + 180 + 60 + + + switch2 + 10.0.0.4 + ARISTA03T2 + 10.0.0.5 + 1 + 180 + 60 + + + ARISTA04T0 + 10.0.0.39 + switch2 + 10.0.0.38 + 1 + 180 + 60 + + + switch2 + 10.0.0.6 + ARISTA04T2 + 10.0.0.7 + 1 + 180 + 60 + + + ARISTA05T0 + 10.0.0.41 + switch2 + 10.0.0.40 + 1 + 180 + 60 + + + switch2 + 10.0.0.8 + ARISTA05T2 + 10.0.0.9 + 1 + 180 + 60 + + + ARISTA06T0 + 10.0.0.43 + switch2 + 10.0.0.42 + 1 + 180 + 60 + + + switch2 + 10.0.0.10 + ARISTA06T2 + 10.0.0.11 + 1 + 180 + 60 + + + ARISTA07T0 + 10.0.0.45 + switch2 + 10.0.0.44 + 1 + 180 + 60 + + + switch2 + 10.0.0.12 + ARISTA07T2 + 10.0.0.13 + 1 + 180 + 60 + + + ARISTA08T0 + 10.0.0.47 + switch2 + 10.0.0.46 + 1 + 180 + 60 + + + switch2 + 10.0.0.14 + ARISTA08T2 + 10.0.0.15 + 1 + 180 + 60 + + + ARISTA09T0 + 10.0.0.49 + switch2 + 10.0.0.48 + 1 + 180 + 60 + + + switch2 + 10.0.0.16 + ARISTA09T2 + 10.0.0.17 + 1 + 180 + 60 + + + ARISTA10T0 + 10.0.0.51 + switch2 + 10.0.0.50 + 1 + 180 + 60 + + + switch2 + 10.0.0.18 + ARISTA10T2 + 10.0.0.19 + 1 + 180 + 60 + + + ARISTA11T0 + 10.0.0.53 + switch2 + 10.0.0.52 + 1 + 180 + 60 + + + switch2 + 10.0.0.20 + ARISTA11T2 + 10.0.0.21 + 1 + 180 + 60 + + + ARISTA12T0 + 10.0.0.55 + switch2 + 10.0.0.54 + 1 + 180 + 60 + + + switch2 + 10.0.0.22 + ARISTA12T2 + 10.0.0.23 + 1 + 180 + 60 + + + ARISTA13T0 + 10.0.0.57 + switch2 + 10.0.0.56 + 1 + 180 + 60 + + + switch2 + 10.0.0.24 + ARISTA13T2 + 10.0.0.25 + 1 + 180 + 60 + + + ARISTA14T0 + 10.0.0.59 + switch2 + 10.0.0.58 + 1 + 180 + 60 + + + switch2 + 10.0.0.26 + ARISTA14T2 + 10.0.0.27 + 1 + 180 + 60 + + + ARISTA15T0 + 10.0.0.61 + switch2 + 10.0.0.60 + 1 + 180 + 60 + + + switch2 + 10.0.0.28 + ARISTA15T2 + 10.0.0.29 + 1 + 180 + 60 + + + ARISTA16T0 + 10.0.0.63 + switch2 + 10.0.0.62 + 1 + 180 + 60 + + + switch2 + 10.0.0.30 + ARISTA16T2 + 10.0.0.31 + 1 + 180 + 60 + + + + + 65100 + switch2 + + +
10.0.0.33
+ + + + +
10.0.0.1
+ + + + +
10.0.0.35
+ + + + +
10.0.0.3
+ + + + +
10.0.0.37
+ + + + +
10.0.0.5
+ + + + +
10.0.0.39
+ + + + +
10.0.0.7
+ + + + +
10.0.0.41
+ + + + +
10.0.0.9
+ + + + +
10.0.0.43
+ + + + +
10.0.0.11
+ + + + +
10.0.0.45
+ + + + +
10.0.0.13
+ + + + +
10.0.0.47
+ + + + +
10.0.0.15
+ + + + +
10.0.0.49
+ + + + +
10.0.0.17
+ + + + +
10.0.0.51
+ + + + +
10.0.0.19
+ + + + +
10.0.0.53
+ + + + +
10.0.0.21
+ + + + +
10.0.0.55
+ + + + +
10.0.0.23
+ + + + +
10.0.0.57
+ + + + +
10.0.0.25
+ + + + +
10.0.0.59
+ + + + +
10.0.0.27
+ + + + +
10.0.0.61
+ + + + +
10.0.0.29
+ + + + +
10.0.0.63
+ + + + +
10.0.0.31
+ + + + + + + + 64001 + ARISTA01T0 + + + + 65200 + ARISTA01T2 + + + + 64002 + ARISTA02T0 + + + + 65200 + ARISTA02T2 + + + + 64003 + ARISTA03T0 + + + + 65200 + ARISTA03T2 + + + + 64004 + ARISTA04T0 + + + + 65200 + ARISTA04T2 + + + + 64005 + ARISTA05T0 + + + + 65200 + ARISTA05T2 + + + + 64006 + ARISTA06T0 + + + + 65200 + ARISTA06T2 + + + + 64007 + ARISTA07T0 + + + + 65200 + ARISTA07T2 + + + + 64008 + ARISTA08T0 + + + + 65200 + ARISTA08T2 + + + + 64009 + ARISTA09T0 + + + + 65200 + ARISTA09T2 + + + + 64010 + ARISTA10T0 + + + + 65200 + ARISTA10T2 + + + + 64011 + ARISTA11T0 + + + + 65200 + ARISTA11T2 + + + + 64012 + ARISTA12T0 + + + + 65200 + ARISTA12T2 + + + + 64013 + ARISTA13T0 + + + + 65200 + ARISTA13T2 + + + + 64014 + ARISTA14T0 + + + + 65200 + ARISTA14T2 + + + + 64015 + ARISTA15T0 + + + + 65200 + ARISTA15T2 + + + + 64016 + ARISTA16T0 + + + + 65200 + ARISTA16T2 + + + + + + + + + + HostIP + Loopback0 + + 10.1.0.32/32 + + 10.1.0.32/32 + + + + + + + + switch2 + + + + + + Ethernet0 + 10.0.0.0/31 + + + + Ethernet4 + 10.0.0.2/31 + + + + Ethernet8 + 10.0.0.4/31 + + + + Ethernet12 + 10.0.0.6/31 + + + + Ethernet16 + 10.0.0.8/31 + + + + Ethernet20 + 10.0.0.10/31 + + + + Ethernet24 + 10.0.0.12/31 + + + + Ethernet28 + 10.0.0.14/31 + + + + Ethernet32 + 10.0.0.16/31 + + + + Ethernet36 + 10.0.0.18/31 + + + + Ethernet40 + 10.0.0.20/31 + + + + Ethernet44 + 10.0.0.22/31 + + + + Ethernet48 + 10.0.0.24/31 + + + + Ethernet52 + 10.0.0.26/31 + + + + Ethernet56 + 10.0.0.28/31 + + + + Ethernet60 + 10.0.0.30/31 + + + + Ethernet64 + 10.0.0.32/31 + + + + Ethernet68 + 10.0.0.34/31 + + + + Ethernet72 + 10.0.0.36/31 + + + + Ethernet76 + 10.0.0.38/31 + + + + Ethernet80 + 10.0.0.40/31 + + + + Ethernet84 + 10.0.0.42/31 + + + + Ethernet88 + 10.0.0.44/31 + + + + Ethernet92 + 10.0.0.46/31 + + + + Ethernet96 + 10.0.0.48/31 + + + + Ethernet100 + 10.0.0.50/31 + + + + Ethernet104 + 10.0.0.52/31 + + + + Ethernet108 + 10.0.0.54/31 + + + + Ethernet112 + 10.0.0.56/31 + + + + Ethernet116 + 10.0.0.58/31 + + + + Ethernet120 + 10.0.0.60/31 + + + + Ethernet124 + 10.0.0.62/31 + + + + + + + + + + + + DeviceInterfaceLink + switch2 + Ethernet0 + ARISTA01T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet4 + ARISTA02T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet8 + ARISTA03T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet12 + ARISTA04T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet16 + ARISTA05T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet20 + ARISTA06T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet24 + ARISTA07T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet28 + ARISTA08T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet32 + ARISTA09T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet36 + ARISTA10T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet40 + ARISTA11T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet44 + ARISTA12T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet48 + ARISTA13T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet52 + ARISTA14T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet56 + ARISTA15T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet60 + ARISTA16T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet64 + ARISTA01T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet68 + ARISTA02T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet72 + ARISTA03T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet76 + ARISTA04T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet80 + ARISTA05T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet84 + ARISTA06T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet88 + ARISTA07T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet92 + ARISTA08T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet96 + ARISTA09T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet100 + ARISTA10T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet104 + ARISTA11T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet108 + ARISTA12T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet112 + ARISTA13T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet116 + ARISTA14T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet120 + ARISTA15T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet124 + ARISTA16T0 + Ethernet1 + + + + + switch2 + montara + + ` + + + + + switch2 + + + DhcpResources + + + + + NtpResources + + 0.debian.pool.ntp.org;1.debian.pool.ntp.org;2.debian.pool.ntp.org;3.debian.pool.ntp.org + + + SyslogResources + + + + + ErspanDestinationIpv4 + + 2.2.2.2 + + + + + + + switch2 + montara + diff --git a/device/barefoot/x86_64-accton_wedge100bf_32x-r0/montara/port_config.ini b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/montara/port_config.ini new file mode 100644 index 0000000000..816bb0e94a --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_32x-r0/montara/port_config.ini @@ -0,0 +1,33 @@ +# name lanes +Ethernet0 0,1,2,3 +Ethernet4 4,5,6,7 +Ethernet8 8,9,10,11 +Ethernet12 12,13,14,15 +Ethernet16 16,17,18,19 +Ethernet20 20,21,22,23 +Ethernet24 24,25,26,27 +Ethernet28 28,29,30,31 +Ethernet32 32,33,34,35 +Ethernet36 36,37,38,39 +Ethernet40 40,41,42,43 +Ethernet44 44,45,46,47 +Ethernet48 48,49,50,51 +Ethernet52 52,53,54,55 +Ethernet56 56,57,58,59 +Ethernet60 60,61,62,63 +Ethernet64 64,65,66,67 +Ethernet68 68,69,70,71 +Ethernet72 72,73,74,75 +Ethernet76 76,77,78,79 +Ethernet80 80,81,82,83 +Ethernet84 84,85,86,87 +Ethernet88 88,89,90,91 +Ethernet92 92,93,94,95 +Ethernet96 96,97,98,99 +Ethernet100 100,101,102,103 +Ethernet104 104,105,106,107 +Ethernet108 108,109,110,111 +Ethernet112 112,113,114,115 +Ethernet116 116,117,118,119 +Ethernet120 120,121,122,123 +Ethernet124 124,125,126,127 diff --git a/device/barefoot/x86_64-accton_wedge100bf_65x-r0/installer.conf b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/installer.conf new file mode 100644 index 0000000000..3714ff053b --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/installer.conf @@ -0,0 +1 @@ +CONSOLE_SPEED=57600 diff --git a/device/barefoot/x86_64-accton_wedge100bf_65x-r0/mavericks/port_config.ini b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/mavericks/port_config.ini new file mode 100644 index 0000000000..c1001741d2 --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/mavericks/port_config.ini @@ -0,0 +1,66 @@ +# name lanes +Ethernet0 0,1,2,3 +Ethernet4 4,5,6,7 +Ethernet8 8,9,10,11 +Ethernet12 12,13,14,15 +Ethernet16 16,17,18,19 +Ethernet20 20,21,22,23 +Ethernet24 24,25,26,27 +Ethernet28 28,29,30,31 +Ethernet32 32,33,34,35 +Ethernet36 36,37,38,39 +Ethernet40 40,41,42,43 +Ethernet44 44,45,46,47 +Ethernet48 48,49,50,51 +Ethernet52 52,53,54,55 +Ethernet56 56,57,58,59 +Ethernet60 60,61,62,63 +Ethernet64 64,65,66,67 +Ethernet68 68,69,70,71 +Ethernet72 72,73,74,75 +Ethernet76 76,77,78,79 +Ethernet80 80,81,82,83 +Ethernet84 84,85,86,87 +Ethernet88 88,89,90,91 +Ethernet92 92,93,94,95 +Ethernet96 96,97,98,99 +Ethernet100 100,101,102,103 +Ethernet104 104,105,106,107 +Ethernet108 108,109,110,111 +Ethernet112 112,113,114,115 +Ethernet116 116,117,118,119 +Ethernet120 120,121,122,123 +Ethernet124 124,125,126,127 +Ethernet128 128,129,130,131 +Ethernet132 132,133,134,135 +Ethernet136 136,137,138,139 +Ethernet140 140,141,142,143 +Ethernet144 144,145,146,147 +Ethernet148 148,149,150,151 +Ethernet152 152,153,154,155 +Ethernet156 156,157,158,159 +Ethernet160 160,161,162,163 +Ethernet164 164,165,166,167 +Ethernet168 168,169,170,171 +Ethernet172 172,173,174,175 +Ethernet176 176,177,178,179 +Ethernet180 180,181,182,183 +Ethernet184 184,185,186,187 +Ethernet188 188,189,190,191 +Ethernet192 192,193,194,195 +Ethernet196 196,197,198,199 +Ethernet200 200,201,202,203 +Ethernet204 204,205,206,207 +Ethernet208 208,209,210,211 +Ethernet212 212,213,214,215 +Ethernet216 216,217,218,219 +Ethernet220 220,221,222,223 +Ethernet224 224,225,226,227 +Ethernet228 228,229,230,231 +Ethernet232 232,233,234,235 +Ethernet236 236,237,238,239 +Ethernet240 240,241,242,243 +Ethernet244 244,245,246,247 +Ethernet248 248,249,250,251 +Ethernet252 252,253,254,255 +Ethernet256 256,257,258,259 diff --git a/device/barefoot/x86_64-accton_wedge100bf_65x-r0/minigraph.xml b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/minigraph.xml new file mode 100644 index 0000000000..61f7b9c85a --- /dev/null +++ b/device/barefoot/x86_64-accton_wedge100bf_65x-r0/minigraph.xml @@ -0,0 +1,1079 @@ + + + + + + ARISTA01T0 + 10.0.0.33 + switch2 + 10.0.0.32 + 1 + 180 + 60 + + + switch2 + 10.0.0.0 + ARISTA01T2 + 10.0.0.1 + 1 + 180 + 60 + + + ARISTA02T0 + 10.0.0.35 + switch2 + 10.0.0.34 + 1 + 180 + 60 + + + switch2 + 10.0.0.2 + ARISTA02T2 + 10.0.0.3 + 1 + 180 + 60 + + + ARISTA03T0 + 10.0.0.37 + switch2 + 10.0.0.36 + 1 + 180 + 60 + + + switch2 + 10.0.0.4 + ARISTA03T2 + 10.0.0.5 + 1 + 180 + 60 + + + ARISTA04T0 + 10.0.0.39 + switch2 + 10.0.0.38 + 1 + 180 + 60 + + + switch2 + 10.0.0.6 + ARISTA04T2 + 10.0.0.7 + 1 + 180 + 60 + + + ARISTA05T0 + 10.0.0.41 + switch2 + 10.0.0.40 + 1 + 180 + 60 + + + switch2 + 10.0.0.8 + ARISTA05T2 + 10.0.0.9 + 1 + 180 + 60 + + + ARISTA06T0 + 10.0.0.43 + switch2 + 10.0.0.42 + 1 + 180 + 60 + + + switch2 + 10.0.0.10 + ARISTA06T2 + 10.0.0.11 + 1 + 180 + 60 + + + ARISTA07T0 + 10.0.0.45 + switch2 + 10.0.0.44 + 1 + 180 + 60 + + + switch2 + 10.0.0.12 + ARISTA07T2 + 10.0.0.13 + 1 + 180 + 60 + + + ARISTA08T0 + 10.0.0.47 + switch2 + 10.0.0.46 + 1 + 180 + 60 + + + switch2 + 10.0.0.14 + ARISTA08T2 + 10.0.0.15 + 1 + 180 + 60 + + + ARISTA09T0 + 10.0.0.49 + switch2 + 10.0.0.48 + 1 + 180 + 60 + + + switch2 + 10.0.0.16 + ARISTA09T2 + 10.0.0.17 + 1 + 180 + 60 + + + ARISTA10T0 + 10.0.0.51 + switch2 + 10.0.0.50 + 1 + 180 + 60 + + + switch2 + 10.0.0.18 + ARISTA10T2 + 10.0.0.19 + 1 + 180 + 60 + + + ARISTA11T0 + 10.0.0.53 + switch2 + 10.0.0.52 + 1 + 180 + 60 + + + switch2 + 10.0.0.20 + ARISTA11T2 + 10.0.0.21 + 1 + 180 + 60 + + + ARISTA12T0 + 10.0.0.55 + switch2 + 10.0.0.54 + 1 + 180 + 60 + + + switch2 + 10.0.0.22 + ARISTA12T2 + 10.0.0.23 + 1 + 180 + 60 + + + ARISTA13T0 + 10.0.0.57 + switch2 + 10.0.0.56 + 1 + 180 + 60 + + + switch2 + 10.0.0.24 + ARISTA13T2 + 10.0.0.25 + 1 + 180 + 60 + + + ARISTA14T0 + 10.0.0.59 + switch2 + 10.0.0.58 + 1 + 180 + 60 + + + switch2 + 10.0.0.26 + ARISTA14T2 + 10.0.0.27 + 1 + 180 + 60 + + + ARISTA15T0 + 10.0.0.61 + switch2 + 10.0.0.60 + 1 + 180 + 60 + + + switch2 + 10.0.0.28 + ARISTA15T2 + 10.0.0.29 + 1 + 180 + 60 + + + ARISTA16T0 + 10.0.0.63 + switch2 + 10.0.0.62 + 1 + 180 + 60 + + + switch2 + 10.0.0.30 + ARISTA16T2 + 10.0.0.31 + 1 + 180 + 60 + + + + + 65100 + switch2 + + +
10.0.0.33
+ + + + +
10.0.0.1
+ + + + +
10.0.0.35
+ + + + +
10.0.0.3
+ + + + +
10.0.0.37
+ + + + +
10.0.0.5
+ + + + +
10.0.0.39
+ + + + +
10.0.0.7
+ + + + +
10.0.0.41
+ + + + +
10.0.0.9
+ + + + +
10.0.0.43
+ + + + +
10.0.0.11
+ + + + +
10.0.0.45
+ + + + +
10.0.0.13
+ + + + +
10.0.0.47
+ + + + +
10.0.0.15
+ + + + +
10.0.0.49
+ + + + +
10.0.0.17
+ + + + +
10.0.0.51
+ + + + +
10.0.0.19
+ + + + +
10.0.0.53
+ + + + +
10.0.0.21
+ + + + +
10.0.0.55
+ + + + +
10.0.0.23
+ + + + +
10.0.0.57
+ + + + +
10.0.0.25
+ + + + +
10.0.0.59
+ + + + +
10.0.0.27
+ + + + +
10.0.0.61
+ + + + +
10.0.0.29
+ + + + +
10.0.0.63
+ + + + +
10.0.0.31
+ + + + + + + + 64001 + ARISTA01T0 + + + + 65200 + ARISTA01T2 + + + + 64002 + ARISTA02T0 + + + + 65200 + ARISTA02T2 + + + + 64003 + ARISTA03T0 + + + + 65200 + ARISTA03T2 + + + + 64004 + ARISTA04T0 + + + + 65200 + ARISTA04T2 + + + + 64005 + ARISTA05T0 + + + + 65200 + ARISTA05T2 + + + + 64006 + ARISTA06T0 + + + + 65200 + ARISTA06T2 + + + + 64007 + ARISTA07T0 + + + + 65200 + ARISTA07T2 + + + + 64008 + ARISTA08T0 + + + + 65200 + ARISTA08T2 + + + + 64009 + ARISTA09T0 + + + + 65200 + ARISTA09T2 + + + + 64010 + ARISTA10T0 + + + + 65200 + ARISTA10T2 + + + + 64011 + ARISTA11T0 + + + + 65200 + ARISTA11T2 + + + + 64012 + ARISTA12T0 + + + + 65200 + ARISTA12T2 + + + + 64013 + ARISTA13T0 + + + + 65200 + ARISTA13T2 + + + + 64014 + ARISTA14T0 + + + + 65200 + ARISTA14T2 + + + + 64015 + ARISTA15T0 + + + + 65200 + ARISTA15T2 + + + + 64016 + ARISTA16T0 + + + + 65200 + ARISTA16T2 + + + + + + + + + + HostIP + Loopback0 + + 10.1.0.32/32 + + 10.1.0.32/32 + + + + + + + + switch2 + + + + + + Ethernet0 + 10.0.0.0/31 + + + + Ethernet4 + 10.0.0.2/31 + + + + Ethernet8 + 10.0.0.4/31 + + + + Ethernet12 + 10.0.0.6/31 + + + + Ethernet16 + 10.0.0.8/31 + + + + Ethernet20 + 10.0.0.10/31 + + + + Ethernet24 + 10.0.0.12/31 + + + + Ethernet28 + 10.0.0.14/31 + + + + Ethernet32 + 10.0.0.16/31 + + + + Ethernet36 + 10.0.0.18/31 + + + + Ethernet40 + 10.0.0.20/31 + + + + Ethernet44 + 10.0.0.22/31 + + + + Ethernet48 + 10.0.0.24/31 + + + + Ethernet52 + 10.0.0.26/31 + + + + Ethernet56 + 10.0.0.28/31 + + + + Ethernet60 + 10.0.0.30/31 + + + + Ethernet64 + 10.0.0.32/31 + + + + Ethernet68 + 10.0.0.34/31 + + + + Ethernet72 + 10.0.0.36/31 + + + + Ethernet76 + 10.0.0.38/31 + + + + Ethernet80 + 10.0.0.40/31 + + + + Ethernet84 + 10.0.0.42/31 + + + + Ethernet88 + 10.0.0.44/31 + + + + Ethernet92 + 10.0.0.46/31 + + + + Ethernet96 + 10.0.0.48/31 + + + + Ethernet100 + 10.0.0.50/31 + + + + Ethernet104 + 10.0.0.52/31 + + + + Ethernet108 + 10.0.0.54/31 + + + + Ethernet112 + 10.0.0.56/31 + + + + Ethernet116 + 10.0.0.58/31 + + + + Ethernet120 + 10.0.0.60/31 + + + + Ethernet124 + 10.0.0.62/31 + + + + + + + + + + + + DeviceInterfaceLink + switch2 + Ethernet0 + ARISTA01T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet4 + ARISTA02T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet8 + ARISTA03T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet12 + ARISTA04T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet16 + ARISTA05T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet20 + ARISTA06T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet24 + ARISTA07T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet28 + ARISTA08T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet32 + ARISTA09T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet36 + ARISTA10T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet40 + ARISTA11T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet44 + ARISTA12T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet48 + ARISTA13T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet52 + ARISTA14T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet56 + ARISTA15T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet60 + ARISTA16T2 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet64 + ARISTA01T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet68 + ARISTA02T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet72 + ARISTA03T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet76 + ARISTA04T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet80 + ARISTA05T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet84 + ARISTA06T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet88 + ARISTA07T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet92 + ARISTA08T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet96 + ARISTA09T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet100 + ARISTA10T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet104 + ARISTA11T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet108 + ARISTA12T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet112 + ARISTA13T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet116 + ARISTA14T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet120 + ARISTA15T0 + Ethernet1 + + + DeviceInterfaceLink + switch2 + Ethernet124 + ARISTA16T0 + Ethernet1 + + + + + switch2 + mavericks + + ` + + + + + switch2 + + + DhcpResources + + + + + NtpResources + + 0.debian.pool.ntp.org;1.debian.pool.ntp.org;2.debian.pool.ntp.org;3.debian.pool.ntp.org + + + SyslogResources + + + + + ErspanDestinationIpv4 + + 2.2.2.2 + + + + + + + switch2 + mavericks + diff --git a/dockers/docker-bfn-sswsyncd-rpc/Dockerfile b/dockers/docker-bfn-sswsyncd-rpc/Dockerfile new file mode 100644 index 0000000000..4d1b3e49bc --- /dev/null +++ b/dockers/docker-bfn-sswsyncd-rpc/Dockerfile @@ -0,0 +1,38 @@ +FROM docker-base + +## Make apt-get non-interactive +ENV DEBIAN_FRONTEND=noninteractive + +## Pre-install the fundamental packages +RUN apt-get update \ + && apt-get -y install \ + net-tools + +COPY deps /deps +RUN dpkg_apt() { [ -f $1 ] && { dpkg -i $1 || apt-get -y install -f; } || return 1; }; \ + dpkg_apt /deps/python-tabulate_*.deb \ + && dpkg_apt /deps/applibs_*.deb \ + && dpkg_apt /deps/applibs-dev_*.deb \ + && dpkg_apt /deps/sx-complib_*.deb \ + && dpkg_apt /deps/sxd-libs_*.deb \ + && dpkg_apt /deps/sx-scew_*.deb \ + && dpkg_apt /deps/sx-examples_*.deb \ + && dpkg_apt /deps/sx-gen-utils_*.deb \ + && dpkg_apt /deps/python-sdk-api_*.deb \ + && dpkg_apt /deps/sx-libnl_*.deb \ + && dpkg_apt /deps/iproute2_*.deb \ + && dpkg_apt /deps/libsswsdk_*.deb \ + && dpkg_apt /deps/libthrift-0.9.3_*.deb \ + && dpkg_apt /deps/libthrift-dev_*.deb + +RUN dpkg_apt() { [ -f $1 ] && { dpkg -i $1 || apt-get -y install -f; } || return 1; }; \ + dpkg_apt /deps/mlnx-sai_*.deb \ + && dpkg_apt /deps/sswsyncd-saithrift_*.deb + +## Clean up +RUN apt-get clean -y ; apt-get autoclean -y ; apt-get autoremove -y ; rm -rf /deps + +ENTRYPOINT service rsyslog start \ + && mkdir -p /dev/sxdevs && ( [ -e /dev/sxdevs/sxcdev ] || mknod /dev/sxdevs/sxcdev c 231 193 ) \ + && service sswsyncd start \ + && /bin/bash diff --git a/dockers/docker-bfn-sswsyncd/Dockerfile b/dockers/docker-bfn-sswsyncd/Dockerfile new file mode 100755 index 0000000000..9bb6c71e87 --- /dev/null +++ b/dockers/docker-bfn-sswsyncd/Dockerfile @@ -0,0 +1,17 @@ +FROM docker-base + +## Make apt-get non-interactive +ENV DEBIAN_FRONTEND=noninteractive + +RUN apt-get update + +## Pre-install the fundamental packages +RUN apt-get update \ + && apt-get -y install \ + net-tools + +COPY deps /deps + +ENTRYPOINT service rsyslog start \ + && sleep 5 && service sswsyncd start \ + && /bin/bash diff --git a/dockers/docker-orchagent-bfn b/dockers/docker-orchagent-bfn new file mode 120000 index 0000000000..8d52609c56 --- /dev/null +++ b/dockers/docker-orchagent-bfn @@ -0,0 +1 @@ +docker-orchagent \ No newline at end of file diff --git a/dockers/docker-orchagent/orchagent.sh b/dockers/docker-orchagent/orchagent.sh index f92dfe5fd5..b11a202230 100755 --- a/dockers/docker-orchagent/orchagent.sh +++ b/dockers/docker-orchagent/orchagent.sh @@ -18,6 +18,8 @@ if [ "$platform" == "broadcom" ]; then ORCHAGENT_ARGS+="-m $MAC_ADDRESS" elif [ "$platform" == "cavium" ]; then ORCHAGENT_ARGS+="-m $MAC_ADDRESS" +elif [ "$ASIC" == "barefoot" ]; then + ORCHAGENT_ARGS+="-m $MAC_ADDRESS" fi exec /usr/bin/orchagent ${ORCHAGENT_ARGS} diff --git a/dockers/docker-saiserver-bfn/Dockerfile b/dockers/docker-saiserver-bfn/Dockerfile new file mode 100755 index 0000000000..427a551e00 --- /dev/null +++ b/dockers/docker-saiserver-bfn/Dockerfile @@ -0,0 +1,38 @@ +FROM docker-base + +## Make apt-get non-interactive +ENV DEBIAN_FRONTEND=noninteractive + +RUN apt-get update + +COPY ["deps/applibs_*.deb", "/deps/applibs-dev_*.deb", "/deps/sx-complib_*.deb", "/deps/sxd-libs_*.deb", "/deps/sx-scew_*.deb", "/deps/sx-examples_*.deb", "/deps/sx-gen-utils_*.deb", "/deps/python-sdk-api_*.deb", "/deps/iproute2_*.deb", "/deps/mlnx-sai_*.deb", "/deps/libthrift-0.9.3_*.deb", "/deps/libnl-3-200_*.deb", "/deps/libnl-genl-3-200_*.deb", "/deps/libnl-route-3-200_*.deb", "/deps/"] + +RUN dpkg_apt() { [ -f $1 ] && { dpkg -i $1 || apt-get -y install -f; } || return 1; }; \ + dpkg_apt /deps/applibs_*.deb \ + && dpkg_apt /deps/applibs-dev_*.deb \ + && dpkg_apt /deps/sx-complib_*.deb \ + && dpkg_apt /deps/sxd-libs_*.deb \ + && dpkg_apt /deps/sx-scew_*.deb \ + && dpkg_apt /deps/sx-examples_*.deb \ + && dpkg_apt /deps/sx-gen-utils_*.deb \ + && dpkg_apt /deps/python-sdk-api_*.deb \ + && dpkg_apt /deps/iproute2_*.deb \ + && dpkg_apt /deps/mlnx-sai_*.deb \ + && dpkg_apt /deps/libthrift-0.9.3_*.deb \ + && dpkg_apt /deps/libnl-3-200_*.deb \ + && dpkg_apt /deps/libnl-genl-3-200_*.deb \ + && dpkg_apt /deps/libnl-route-3-200_*.deb + +COPY ["deps/saiserver", "start.sh", "/usr/bin/"] + +COPY ["supervisord.conf", "/etc/supervisor/conf.d/"] + +COPY ["profile.ini", "portmap.ini", "/etc/sai/"] + + +## Clean up +RUN apt-get clean -y; apt-get autoclean -y; apt-get autoremove -y +RUN rm -rf /deps + +ENTRYPOINT ["/usr/bin/supervisord"] + diff --git a/dockers/docker-saiserver-bfn/portmap.ini b/dockers/docker-saiserver-bfn/portmap.ini new file mode 100644 index 0000000000..4d3be08ce5 --- /dev/null +++ b/dockers/docker-saiserver-bfn/portmap.ini @@ -0,0 +1,33 @@ +# alias lanes +Ethernet1 0,1,2,3 +Ethernet2 4,5,6,7 +Ethernet3 8,9,10,11 +Ethernet4 12,13,14,15 +Ethernet5 16,17,18,19 +Ethernet6 20,21,22,23 +Ethernet7 24,25,26,27 +Ethernet8 28,29,30,31 +Ethernet9 32,33,34,35 +Ethernet10 36,37,38,39 +Ethernet11 40,41,42,43 +Ethernet12 44,45,46,47 +Ethernet13 48,49,50,51 +Ethernet14 52,53,54,55 +Ethernet15 56,57,58,59 +Ethernet16 60,61,62,63 +Ethernet17 64,65,66,67 +Ethernet18 68,69,70,71 +Ethernet19 72,73,74,75 +Ethernet20 76,77,78,79 +Ethernet21 80,81,82,83 +Ethernet22 84,85,86,87 +Ethernet23 88,89,90,91 +Ethernet24 92,93,94,95 +Ethernet25 96,97,98,99 +Ethernet26 100,101,102,103 +Ethernet27 104,105,106,107 +Ethernet28 108,109,110,111 +Ethernet29 112,113,114,115 +Ethernet30 116,117,118,119 +Ethernet31 120,121,122,123 +Ethernet32 124,125,126,127 \ No newline at end of file diff --git a/dockers/docker-saiserver-bfn/profile.ini b/dockers/docker-saiserver-bfn/profile.ini new file mode 100644 index 0000000000..b20b2c6f0e --- /dev/null +++ b/dockers/docker-saiserver-bfn/profile.ini @@ -0,0 +1 @@ +SAI_INIT_CONFIG_FILE=/usr/share/sai_tofino.xml diff --git a/dockers/docker-saiserver-bfn/sai_tofino.xml b/dockers/docker-saiserver-bfn/sai_tofino.xml new file mode 100644 index 0000000000..139597f9cb --- /dev/null +++ b/dockers/docker-saiserver-bfn/sai_tofino.xml @@ -0,0 +1,2 @@ + + diff --git a/dockers/docker-saiserver-bfn/start.sh b/dockers/docker-saiserver-bfn/start.sh new file mode 100755 index 0000000000..57ee5036de --- /dev/null +++ b/dockers/docker-saiserver-bfn/start.sh @@ -0,0 +1,16 @@ +#!/usr/bin/env bash + +start_mlnx() +{ + [ -e /dev/sxdevs/sxcdev ] || ( mkdir -p /dev/sxdevs && mknod /dev/sxdevs/sxcdev c 231 193 ) +} + + +rm -f /var/run/rsyslogd.pid + +supervisorctl start rsyslogd + +start_mlnx + +supervisorctl start saiserver + diff --git a/dockers/docker-saiserver-bfn/supervisord.conf b/dockers/docker-saiserver-bfn/supervisord.conf new file mode 100644 index 0000000000..e09ac3cbb4 --- /dev/null +++ b/dockers/docker-saiserver-bfn/supervisord.conf @@ -0,0 +1,29 @@ +[supervisord] +logfile_maxbytes=1MB +logfile_backups=2 +nodaemon=true + +[program:start.sh] +command=/usr/bin/start.sh +priority=1 +autostart=true +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + +[program:rsyslogd] +command=/usr/sbin/rsyslogd -n +priority=2 +autostart=false +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + +[program:saiserver] +command=/usr/bin/saiserver -p /etc/sai/profile.ini -f /etc/sai/portmap.ini +priority=3 +autostart=false +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + diff --git a/files/image_config/interfaces/interfaces.j2 b/files/image_config/interfaces/interfaces.j2 index 2fdd04804c..7822858ca0 100644 --- a/files/image_config/interfaces/interfaces.j2 +++ b/files/image_config/interfaces/interfaces.j2 @@ -18,6 +18,11 @@ iface lo {{ 'inet' if prefix | ipv4 else 'inet6' }} static {% endfor %} {% endblock loopback %} {% block mgmt_interface %} +# BMC interface +auto usb0 +iface usb0 inet static + address 192.168.0.2 + netmask 255.255.255.0 # The management network interface auto eth0 {% if MGMT_INTERFACE %} diff --git a/platform/barefoot/bfn-sai.mk b/platform/barefoot/bfn-sai.mk new file mode 100644 index 0000000000..4f27a7ae18 --- /dev/null +++ b/platform/barefoot/bfn-sai.mk @@ -0,0 +1,6 @@ +BFN_SAI = bfnsdk_1.0.0_amd64.deb +$(BFN_SAI)_URL = "https://www.dropbox.com/s/4ljk6hzw82rudsr/bfnsdk_1.0.0_amd64.deb?dl=0" +# $(BFN_SAI_DEV)_URL = "https://www.dropbox.com/s/4ljk6hzw82rudsr/bfnsdk_1.0.0_amd64.deb?dl=0" + +SONIC_ONLINE_DEBS += $(BFN_SAI) # $(BFN_SAI_DEV) +$(BFN_SAI_DEV)_DEPENDS += $(BFN_SAI) diff --git a/platform/barefoot/docker-orchagent-bfn.mk b/platform/barefoot/docker-orchagent-bfn.mk new file mode 100644 index 0000000000..ac338f2ba7 --- /dev/null +++ b/platform/barefoot/docker-orchagent-bfn.mk @@ -0,0 +1,18 @@ +# docker image for orchagent + +DOCKER_ORCHAGENT_BFN = docker-orchagent-bfn.gz +$(DOCKER_ORCHAGENT_BFN)_PATH = $(DOCKERS_PATH)/docker-orchagent +$(DOCKER_ORCHAGENT_BFN)_DEPENDS += $(SWSS) $(REDIS_TOOLS) +$(DOCKER_ORCHAGENT_BFN)_LOAD_DOCKERS += $(DOCKER_CONFIG_ENGINE) +SONIC_DOCKER_IMAGES += $(DOCKER_ORCHAGENT_BFN) +SONIC_INSTALL_DOCKER_IMAGES += $(DOCKER_ORCHAGENT_BFN) + +$(DOCKER_ORCHAGENT_BFN)_CONTAINER_NAME = swss +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += --net=host --privileged -t +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += -v /etc/network/interfaces:/etc/network/interfaces:ro +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += -v /etc/network/interfaces.d/:/etc/network/interfaces.d/:ro +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += -v /host/machine.conf:/host/machine.conf:ro +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += -v /etc/sonic:/etc/sonic:ro +$(DOCKER_ORCHAGENT_BFN)_RUN_OPT += -v /var/log/swss:/var/log/swss:rw + +$(DOCKER_ORCHAGENT_BFN)_BASE_IMAGE_FILES += swssloglevel:/usr/bin/swssloglevel diff --git a/platform/barefoot/docker-ptf-bfn.mk b/platform/barefoot/docker-ptf-bfn.mk new file mode 100644 index 0000000000..573e9cd9cf --- /dev/null +++ b/platform/barefoot/docker-ptf-bfn.mk @@ -0,0 +1,5 @@ +# docker image for docker-ptf + +DOCKER_PTF_BFN = docker-ptf-bfn.gz +$(DOCKER_PTF_BFN)_PATH = $(DOCKERS_PATH)/docker-ptf-saithrift +$(DOCKER_PTF_BFN)_LOAD_DOCKERS += $(DOCKER_PTF) diff --git a/platform/barefoot/docker-syncd-bfn-rpc.mk b/platform/barefoot/docker-syncd-bfn-rpc.mk new file mode 100644 index 0000000000..61f5570c16 --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn-rpc.mk @@ -0,0 +1,15 @@ +# docker image for syncd with rpc + +DOCKER_SYNCD_BFN_RPC = docker-syncd-bfn-rpc.gz +$(DOCKER_SYNCD_BFN_RPC)_PATH = $(PLATFORM_PATH)/docker-syncd-bfn-rpc +$(DOCKER_SYNCD_BFN_RPC)_DEPENDS += $(SYNCD_RPC) $(LIBTHRIFT) +$(DOCKER_SYNCD_BFN_RPC)_LOAD_DOCKERS += $(DOCKER_SYNCD_BFN) +SONIC_DOCKER_IMAGES += $(DOCKER_SYNCD_BFN_RPC) +ifeq ($(ENABLE_SYNCD_RPC),y) +SONIC_INSTALL_DOCKER_IMAGES += $(DOCKER_SYNCD_BFN_RPC) +endif + +$(DOCKER_SYNCD_BFN_RPC)_CONTAINER_NAME = syncd +$(DOCKER_SYNCD_BFN_RPC)_RUN_OPT += --net=host --privileged -t +$(DOCKER_SYNCD_BFN_RPC)_RUN_OPT += -v /host/machine.conf:/etc/machine.conf +$(DOCKER_SYNCD_BFN_RPC)_RUN_OPT += -v /etc/sonic:/etc/sonic:ro diff --git a/platform/barefoot/docker-syncd-bfn-rpc/Dockerfile.j2 b/platform/barefoot/docker-syncd-bfn-rpc/Dockerfile.j2 new file mode 100644 index 0000000000..590f80aacd --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn-rpc/Dockerfile.j2 @@ -0,0 +1,52 @@ +FROM docker-syncd-bfn + +## Make apt-get non-interactive +ENV DEBIAN_FRONTEND=noninteractive + +COPY \ +{% for deb in docker_syncd_bfn.split(' ') -%} +debs/{{ deb }}{{' '}} +{%- endfor -%} +debs/ + +RUN dpkg -P syncd + +RUN dpkg_apt() { [ -f $1 ] && { dpkg -i $1 || apt-get -y install -f; } || return 1; } ; \ +{% for deb in docker_syncd_bfn.split(' ') -%} +dpkg_apt debs/{{ deb }}{{'; '}} +{%- endfor %} + +## Pre-install the fundamental packages +RUN apt-get update \ + && apt-get -y install \ + net-tools \ + python-pip \ + build-essential \ + libssl-dev \ + libffi-dev \ + python-dev \ + wget \ + cmake \ + && wget https://github.com/nanomsg/nanomsg/archive/1.0.0.tar.gz \ + && tar xvfz 1.0.0.tar.gz \ + && cd nanomsg-1.0.0 \ + && mkdir -p build \ + && cmake . \ + && make install \ + && ldconfig \ + && cd .. \ + && rm -fr nanomsg-1.0.0 \ + && rm -f 1.0.0.tar.gz \ + && pip install cffi==1.7.0 \ + && pip install --upgrade cffi==1.7.0 \ + && pip install nnpy \ + && mkdir -p /opt \ + && cd /opt \ + && wget https://raw.githubusercontent.com/p4lang/ptf/master/ptf_nn/ptf_nn_agent.py \ + && apt-get clean -y; apt-get autoclean -y; apt-get autoremove -y \ + && rm -rf /root/deps + +COPY ["ptf_nn_agent.conf", "/etc/supervisor/conf.d/"] + +ENTRYPOINT ["/usr/bin/supervisord"] + diff --git a/platform/barefoot/docker-syncd-bfn-rpc/ptf_nn_agent.conf b/platform/barefoot/docker-syncd-bfn-rpc/ptf_nn_agent.conf new file mode 100644 index 0000000000..fa1ed0eb16 --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn-rpc/ptf_nn_agent.conf @@ -0,0 +1,10 @@ +[program:ptf_nn_agent] +command=/usr/bin/python /opt/ptf_nn_agent.py --device-socket 1@tcp://0.0.0.0:10900 -i 1-3@Ethernet12 --set-iface-rcv-buffer=109430400 +process_name=ptf_nn_agent +stdout_logfile=/tmp/ptf_nn_agent.out.log +stderr_logfile=/tmp/ptf_nn_agent.err.log +redirect_stderr=false +autostart=true +autorestart=true +startsecs=1 +numprocs=1 diff --git a/platform/barefoot/docker-syncd-bfn.mk b/platform/barefoot/docker-syncd-bfn.mk new file mode 100644 index 0000000000..22bb10763e --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn.mk @@ -0,0 +1,15 @@ +# docker image for syncd + +DOCKER_SYNCD_BFN = docker-syncd-bfn.gz +$(DOCKER_SYNCD_BFN)_PATH = $(PLATFORM_PATH)/docker-syncd-bfn +$(DOCKER_SYNCD_BFN)_DEPENDS += $(SYNCD) +$(DOCKER_SYNCD_BFN)_LOAD_DOCKERS += $(DOCKER_CONFIG_ENGINE) +SONIC_DOCKER_IMAGES += $(DOCKER_SYNCD_BFN) +ifneq ($(ENABLE_SYNCD_RPC),y) +SONIC_INSTALL_DOCKER_IMAGES += $(DOCKER_SYNCD_BFN) +endif + +$(DOCKER_SYNCD_BFN)_CONTAINER_NAME = syncd +$(DOCKER_SYNCD_BFN)_RUN_OPT += --net=host --privileged -t +$(DOCKER_SYNCD_BFN)_RUN_OPT += -v /host/machine.conf:/etc/machine.conf +$(DOCKER_SYNCD_BFN)_RUN_OPT += -v /etc/sonic:/etc/sonic:ro diff --git a/platform/barefoot/docker-syncd-bfn/Dockerfile.j2 b/platform/barefoot/docker-syncd-bfn/Dockerfile.j2 new file mode 100755 index 0000000000..54e55e1108 --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn/Dockerfile.j2 @@ -0,0 +1,29 @@ +FROM docker-config-engine + +## Make apt-get non-interactive +ENV DEBIAN_FRONTEND=noninteractive + +RUN apt-get update + +COPY \ +{% for deb in docker_syncd_bfn_debs.split(' ') -%} +debs/{{ deb }}{{' '}} +{%- endfor -%} +debs/ + +RUN apt-get install -y libxml2 libpcap-dev libusb-1.0-0-dev libcurl3 libcurl4-gnutls-dev + +RUN dpkg -i \ +{% for deb in docker_syncd_bfn_debs.split(' ') -%} +debs/{{ deb }}{{' '}} +{%- endfor %} + +COPY ["start.sh", "/usr/bin/"] +COPY ["supervisord.conf", "/etc/supervisor/conf.d/"] + +## Clean up +RUN apt-get clean -y; apt-get autoclean -y; apt-get autoremove -y +RUN rm -rf /debs + +ENTRYPOINT ["/usr/bin/supervisord"] + diff --git a/platform/barefoot/docker-syncd-bfn/start.sh b/platform/barefoot/docker-syncd-bfn/start.sh new file mode 100755 index 0000000000..1a39db4a9d --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn/start.sh @@ -0,0 +1,9 @@ +#!/usr/bin/env bash + +rm -f /var/run/rsyslogd.pid + +supervisorctl start rsyslogd + +. /opt/bfn/install/bin/dma_setup.sh +# . /opt/bfn/install/bin/bf_kdrv_mod_load /opt/bfn/install +LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/bfn/install/lib supervisorctl start syncd diff --git a/platform/barefoot/docker-syncd-bfn/supervisord.conf b/platform/barefoot/docker-syncd-bfn/supervisord.conf new file mode 100644 index 0000000000..1e015fef93 --- /dev/null +++ b/platform/barefoot/docker-syncd-bfn/supervisord.conf @@ -0,0 +1,29 @@ +[supervisord] +logfile_maxbytes=1MB +logfile_backups=2 +nodaemon=true + +[program:start.sh] +command=/usr/bin/start.sh +priority=1 +autostart=true +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + +[program:rsyslogd] +command=/usr/sbin/rsyslogd -n +priority=2 +autostart=false +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + +[program:syncd] +command=/usr/bin/syncd_start.sh +priority=3 +autostart=false +autorestart=false +stdout_logfile=syslog +stderr_logfile=syslog + diff --git a/platform/barefoot/libsaithrift-dev.mk b/platform/barefoot/libsaithrift-dev.mk new file mode 100644 index 0000000000..c9c8cbb3ad --- /dev/null +++ b/platform/barefoot/libsaithrift-dev.mk @@ -0,0 +1,7 @@ +# libsaithrift-dev package + +LIBSAITHRIFT_DEV_BFN = libsaithrift-dev_0.9.4_amd64.deb +$(LIBSAITHRIFT_DEV_BFN)_SRC_PATH = $(SRC_PATH)/SAI +$(LIBSAITHRIFT_DEV_BFN)_DEPENDS += $(LIBTHRIFT) $(LIBTHRIFT_DEV) $(THRIFT_COMPILER) $(BFN_SAI) $(BFN_SAI_DEV) +$(LIBSAITHRIFT_DEV_BFN)_RDEPENDS += $(LIBTHRIFT) $(BFN_SAI) +#SONIC_DPKG_DEBS += $(LIBSAITHRIFT_DEV_BFN) diff --git a/platform/barefoot/one-image.mk b/platform/barefoot/one-image.mk new file mode 100644 index 0000000000..52cc9ba369 --- /dev/null +++ b/platform/barefoot/one-image.mk @@ -0,0 +1,11 @@ +# sonic one image installer + +SONIC_ONE_IMAGE = sonic-barefoot.bin +$(SONIC_ONE_IMAGE)_MACHINE = barefoot +$(SONIC_ONE_IMAGE)_IMAGE_TYPE = onie +$(SONIC_ONE_IMAGE)_INSTALLS += $(BFN_PLATFORM_MODULE) +$(SONIC_ONE_IMAGE)_INSTALLS += $(BFN_MONTARA_PLATFORM_MODULE) +$(SONIC_ONE_IMAGE)_DEPENDS += $(BFN_PLATFORM_MODULE) +$(SONIC_ONE_IMAGE)_DEPENDS += $(BFN_MONTARA_PLATFORM_MODULE) +$(SONIC_ONE_IMAGE)_DOCKERS += $(SONIC_INSTALL_DOCKER_IMAGES) +SONIC_INSTALLERS += $(SONIC_ONE_IMAGE) diff --git a/platform/barefoot/platform-modules-bfn-montara.mk b/platform/barefoot/platform-modules-bfn-montara.mk new file mode 100644 index 0000000000..113faf201e --- /dev/null +++ b/platform/barefoot/platform-modules-bfn-montara.mk @@ -0,0 +1,11 @@ +# BFN Platform modules + +BFN_MONTARA_PLATFORM_MODULE_VERSION = 1.0 + +export BFN_MONTARA_PLATFORM_MODULE_VERSION + +BFN_MONTARA_PLATFORM_MODULE = platform-modules-bfn-montara_$(BFN_MONTARA_PLATFORM_MODULE_VERSION)_amd64.deb +$(BFN_MONTARA_PLATFORM_MODULE)_SRC_PATH = $(PLATFORM_PATH)/sonic-platform-modules-bfn-montara +$(BFN_MONTARA_PLATFORM_MODULE)_DEPENDS += $(LINUX_HEADERS) $(LINUX_HEADERS_COMMON) +$(BFN_MONTARA_PLATFORM_MODULE)_PLATFORM = x86_64-accton_wedge100bf_32x-r0 +SONIC_DPKG_DEBS += $(BFN_MONTARA_PLATFORM_MODULE) diff --git a/platform/barefoot/platform-modules-bfn.mk b/platform/barefoot/platform-modules-bfn.mk new file mode 100644 index 0000000000..3f76e94aa0 --- /dev/null +++ b/platform/barefoot/platform-modules-bfn.mk @@ -0,0 +1,11 @@ +# BFN Platform modules + +BFN_PLATFORM_MODULE_VERSION = 1.0 + +export BFN_PLATFORM_MODULE_VERSION + +BFN_PLATFORM_MODULE = platform-modules-bfn_$(BFN_PLATFORM_MODULE_VERSION)_amd64.deb +$(BFN_PLATFORM_MODULE)_SRC_PATH = $(PLATFORM_PATH)/sonic-platform-modules-bfn +$(BFN_PLATFORM_MODULE)_DEPENDS += $(LINUX_HEADERS) $(LINUX_HEADERS_COMMON) +$(BFN_PLATFORM_MODULE)_PLATFORM = x86_64-accton_wedge100bf_65x-r0 +SONIC_DPKG_DEBS += $(BFN_PLATFORM_MODULE) diff --git a/platform/barefoot/platform.conf b/platform/barefoot/platform.conf new file mode 100644 index 0000000000..e69de29bb2 diff --git a/platform/barefoot/python-saithrift.mk b/platform/barefoot/python-saithrift.mk new file mode 100644 index 0000000000..ba4846402f --- /dev/null +++ b/platform/barefoot/python-saithrift.mk @@ -0,0 +1,6 @@ +# python-saithrift package + +PYTHON_SAITHRIFT_BFN = python-saithrift_0.9.4_amd64.deb +$(PYTHON_SAITHRIFT_BFN)_SRC_PATH = $(SRC_PATH)/SAI +$(PYTHON_SAITHRIFT_BFN)_DEPENDS += $(BFN_SAI_DEV) $(BFN_SAI) $(THRIFT_COMPILER) $(PYTHON_THRIFT) $(LIBTHRIFT_DEV) +#SONIC_DPKG_DEBS += $(PYTHON_SAITHRIFT_BFN) diff --git a/platform/barefoot/rules.mk b/platform/barefoot/rules.mk new file mode 100644 index 0000000000..507e6b7dae --- /dev/null +++ b/platform/barefoot/rules.mk @@ -0,0 +1,19 @@ +include $(PLATFORM_PATH)/platform-modules-bfn.mk +include $(PLATFORM_PATH)/platform-modules-bfn-montara.mk +include $(PLATFORM_PATH)/bfn-sai.mk +include $(PLATFORM_PATH)/docker-syncd-bfn.mk +include $(PLATFORM_PATH)/docker-syncd-bfn-rpc.mk +include $(PLATFORM_PATH)/docker-orchagent-bfn.mk +include $(PLATFORM_PATH)/one-image.mk +include $(PLATFORM_PATH)/libsaithrift-dev.mk +include $(PLATFORM_PATH)/python-saithrift.mk +include $(PLATFORM_PATH)/docker-ptf-bfn.mk + +SONIC_ALL += $(SONIC_ONE_IMAGE) \ + $(DOCKER_FPM) + +# Inject sai into sairedis +$(LIBSAIREDIS)_DEPENDS += $(BFN_SAI) #$(LIBSAITHRIFT_DEV_BFN) + +# Runtime dependency on sai is set only for syncd +$(SYNCD)_RDEPENDS += $(BFN_SAI) diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/LICENSE b/platform/barefoot/sonic-platform-modules-bfn-montara/LICENSE new file mode 100644 index 0000000000..676cdeec72 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/LICENSE @@ -0,0 +1,15 @@ +Copyright (C) 2016 Microsoft, Inc + +This program is free software; you can redistribute it and/or +modify it under the terms of the GNU General Public License +as published by the Free Software Foundation; either version 2 +of the License, or (at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/MAINTAINERS b/platform/barefoot/sonic-platform-modules-bfn-montara/MAINTAINERS new file mode 100644 index 0000000000..05b0cea082 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/MAINTAINERS @@ -0,0 +1,7 @@ +# This file describes the maintainers for sonic-platform-modules-bfn +# See the SONiC project governance document for more information + +Name = "Daxay" +Email = "support@barefootnetworks.com" +Github = barefootnetworks +Mailinglist = sonicproject@googlegroups.com diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/README.md b/platform/barefoot/sonic-platform-modules-bfn-montara/README.md new file mode 100644 index 0000000000..5dc055a1d9 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/README.md @@ -0,0 +1,2 @@ +# sonic-platform-modules-bfn +Device drivers for support of BFN platform for the SONiC project diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/changelog b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/changelog new file mode 100644 index 0000000000..070927fd78 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/changelog @@ -0,0 +1,5 @@ +platform-modules-bfn-montara (1.0) unstable; urgency=low + + * Initial release + + -- Shuotian Cheng Mon, 11 Nov 2015 11:11:11 -0800 diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/compat b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/compat new file mode 100644 index 0000000000..45a4fb75db --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/compat @@ -0,0 +1 @@ +8 diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/control b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/control new file mode 100644 index 0000000000..1281dffd3f --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/control @@ -0,0 +1,12 @@ +Source: platform-modules-bfn-montara +Section: main +Priority: extra +Maintainer: Shuotian Cheng +Build-Depends: debhelper (>= 8.0.0), bzip2 +Standards-Version: 3.9.3 + +Package: platform-modules-bfn-montara +Architecture: amd64 +Depends: linux-image-3.16.0-4-amd64 +Description: kernel modules for platform devices such as fan, led, sfp + diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/copyright b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/copyright new file mode 100644 index 0000000000..ade42b7aa7 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/copyright @@ -0,0 +1,15 @@ +Provides linux kernel driver for BF PCIe devices + +This program is free software; you can redistribute it and/or +modify it under the terms of the GNU General Public License +as published by the Free Software Foundation; either version 2 +of the License, or (at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/files b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/files new file mode 100644 index 0000000000..73e4715522 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/files @@ -0,0 +1 @@ +platform-modules-bfn-montara_1.0_amd64.deb main extra diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/debian/rules b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/rules new file mode 100755 index 0000000000..e48edc3049 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/debian/rules @@ -0,0 +1,32 @@ +#!/usr/bin/make -f + +export INSTALL_MOD_DIR:=extra + +PACKAGE_NAME := platform-modules-bfn-montara +KVERSION ?= $(shell uname -r) +KERNEL_SRC := /lib/modules/$(KVERSION) +MODULE_SRC := $(shell pwd)/modules +SCRIPT_SRC := $(shell pwd)/scripts + +%: + dh $@ + +override_dh_auto_build: + make -C $(KERNEL_SRC)/build M=$(MODULE_SRC) + +override_dh_auto_install: + dh_installdirs -p$(PACKAGE_NAME) $(KERNEL_SRC)/$(INSTALL_MOD_DIR) + cp $(MODULE_SRC)/*.ko debian/$(PACKAGE_NAME)/$(KERNEL_SRC)/$(INSTALL_MOD_DIR) + dh_installdirs -p$(PACKAGE_NAME) usr/local/bin + cp -r $(SCRIPT_SRC)/* debian/$(PACKAGE_NAME)/usr/local/bin + +override_dh_usrlocal: + +override_dh_pysupport: + +override_dh_clean: + dh_clean + rm -f $(MODULE_SRC)/*.o $(MODULE_SRC)/*.ko $(MODULE_SRC)/*.mod.c $(MODULE_SRC)/.*.cmd + rm -f $(MODULE_SRC)/Module.markers $(MODULE_SRC)/Module.symvers $(MODULE_SRC)/modules.order + rm -rf $(MODULE_SRC)/.tmp_versions + diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/modules/Makefile b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/Makefile new file mode 120000 index 0000000000..d394585dd2 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/Makefile @@ -0,0 +1 @@ +../../sonic-platform-modules-bfn/modules/Makefile \ No newline at end of file diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_kdrv.c b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_kdrv.c new file mode 120000 index 0000000000..959d811823 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_kdrv.c @@ -0,0 +1 @@ +../../sonic-platform-modules-bfn/modules/bf_kdrv.c \ No newline at end of file diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_tun.c b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_tun.c new file mode 120000 index 0000000000..ea380c3075 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/modules/bf_tun.c @@ -0,0 +1 @@ +../../sonic-platform-modules-bfn/modules/bf_tun.c \ No newline at end of file diff --git a/platform/barefoot/sonic-platform-modules-bfn-montara/scripts/test b/platform/barefoot/sonic-platform-modules-bfn-montara/scripts/test new file mode 100755 index 0000000000..38327722c9 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn-montara/scripts/test @@ -0,0 +1 @@ +echo "test" diff --git a/platform/barefoot/sonic-platform-modules-bfn/LICENSE b/platform/barefoot/sonic-platform-modules-bfn/LICENSE new file mode 100644 index 0000000000..676cdeec72 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/LICENSE @@ -0,0 +1,15 @@ +Copyright (C) 2016 Microsoft, Inc + +This program is free software; you can redistribute it and/or +modify it under the terms of the GNU General Public License +as published by the Free Software Foundation; either version 2 +of the License, or (at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. diff --git a/platform/barefoot/sonic-platform-modules-bfn/MAINTAINERS b/platform/barefoot/sonic-platform-modules-bfn/MAINTAINERS new file mode 100644 index 0000000000..05b0cea082 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/MAINTAINERS @@ -0,0 +1,7 @@ +# This file describes the maintainers for sonic-platform-modules-bfn +# See the SONiC project governance document for more information + +Name = "Daxay" +Email = "support@barefootnetworks.com" +Github = barefootnetworks +Mailinglist = sonicproject@googlegroups.com diff --git a/platform/barefoot/sonic-platform-modules-bfn/README.md b/platform/barefoot/sonic-platform-modules-bfn/README.md new file mode 100644 index 0000000000..5dc055a1d9 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/README.md @@ -0,0 +1,2 @@ +# sonic-platform-modules-bfn +Device drivers for support of BFN platform for the SONiC project diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/changelog b/platform/barefoot/sonic-platform-modules-bfn/debian/changelog new file mode 100644 index 0000000000..47b18ef78f --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/changelog @@ -0,0 +1,5 @@ +platform-modules-bfn (1.0) unstable; urgency=low + + * Initial release + + -- Shuotian Cheng Mon, 11 Nov 2015 11:11:11 -0800 diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/compat b/platform/barefoot/sonic-platform-modules-bfn/debian/compat new file mode 100644 index 0000000000..45a4fb75db --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/compat @@ -0,0 +1 @@ +8 diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/control b/platform/barefoot/sonic-platform-modules-bfn/debian/control new file mode 100644 index 0000000000..5bdcd7acfc --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/control @@ -0,0 +1,12 @@ +Source: platform-modules-bfn +Section: main +Priority: extra +Maintainer: Shuotian Cheng +Build-Depends: debhelper (>= 8.0.0), bzip2 +Standards-Version: 3.9.3 + +Package: platform-modules-bfn +Architecture: amd64 +Depends: linux-image-3.16.0-4-amd64 +Description: kernel modules for platform devices such as fan, led, sfp + diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/copyright b/platform/barefoot/sonic-platform-modules-bfn/debian/copyright new file mode 100644 index 0000000000..ade42b7aa7 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/copyright @@ -0,0 +1,15 @@ +Provides linux kernel driver for BF PCIe devices + +This program is free software; you can redistribute it and/or +modify it under the terms of the GNU General Public License +as published by the Free Software Foundation; either version 2 +of the License, or (at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/files b/platform/barefoot/sonic-platform-modules-bfn/debian/files new file mode 100644 index 0000000000..1cfb92c60a --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/files @@ -0,0 +1 @@ +platform-modules-bfn_1.0_amd64.deb main extra diff --git a/platform/barefoot/sonic-platform-modules-bfn/debian/rules b/platform/barefoot/sonic-platform-modules-bfn/debian/rules new file mode 100755 index 0000000000..73aa5d84da --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/debian/rules @@ -0,0 +1,32 @@ +#!/usr/bin/make -f + +export INSTALL_MOD_DIR:=extra + +PACKAGE_NAME := platform-modules-bfn +KVERSION ?= $(shell uname -r) +KERNEL_SRC := /lib/modules/$(KVERSION) +MODULE_SRC := $(shell pwd)/modules +SCRIPT_SRC := $(shell pwd)/scripts + +%: + dh $@ + +override_dh_auto_build: + make -C $(KERNEL_SRC)/build M=$(MODULE_SRC) + +override_dh_auto_install: + dh_installdirs -p$(PACKAGE_NAME) $(KERNEL_SRC)/$(INSTALL_MOD_DIR) + cp $(MODULE_SRC)/*.ko debian/$(PACKAGE_NAME)/$(KERNEL_SRC)/$(INSTALL_MOD_DIR) + dh_installdirs -p$(PACKAGE_NAME) usr/local/bin + cp -r $(SCRIPT_SRC)/* debian/$(PACKAGE_NAME)/usr/local/bin + +override_dh_usrlocal: + +override_dh_pysupport: + +override_dh_clean: + dh_clean + rm -f $(MODULE_SRC)/*.o $(MODULE_SRC)/*.ko $(MODULE_SRC)/*.mod.c $(MODULE_SRC)/.*.cmd + rm -f $(MODULE_SRC)/Module.markers $(MODULE_SRC)/Module.symvers $(MODULE_SRC)/modules.order + rm -rf $(MODULE_SRC)/.tmp_versions + diff --git a/platform/barefoot/sonic-platform-modules-bfn/modules/Makefile b/platform/barefoot/sonic-platform-modules-bfn/modules/Makefile new file mode 100644 index 0000000000..d180b29f6a --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/modules/Makefile @@ -0,0 +1,2 @@ +obj-m := bf_kdrv.o +obj-m += bf_tun.o diff --git a/platform/barefoot/sonic-platform-modules-bfn/modules/bf_kdrv.c b/platform/barefoot/sonic-platform-modules-bfn/modules/bf_kdrv.c new file mode 100644 index 0000000000..f486a41644 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/modules/bf_kdrv.c @@ -0,0 +1,1152 @@ +/******************************************************************************* + * BAREFOOT NETWORKS CONFIDENTIAL & PROPRIETARY + * + * Copyright (c) 2015-2016 Barefoot Networks, Inc. + + * All Rights Reserved. + * + * NOTICE: All information contained herein is, and remains the property of + * Barefoot Networks, Inc. and its suppliers, if any. The intellectual and + * technical concepts contained herein are proprietary to Barefoot Networks, + * Inc. + * and its suppliers and may be covered by U.S. and Foreign Patents, patents in + * process, and are protected by trade secret or copyright law. + * Dissemination of this information or reproduction of this material is + * strictly forbidden unless prior written permission is obtained from + * Barefoot Networks, Inc. + * + * No warranty, explicit or implicit is provided, unless granted under a + * written agreement with Barefoot Networks, Inc. + * + * $Id: $ + * + ******************************************************************************/ +/** + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 Barefoot Networks. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the... + * + **/ + +/* bf_drv kernel module + * + * This is kernel mode driver for Tofino chip. + * Provides user space mmap service and user space "wait for interrupt" + * and "enable interrupt" services. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if LINUX_VERSION_CODE < KERNEL_VERSION(3, 16, 0) +//#error unsupported linux kernel version +#endif + +/* TBD: Need to build with CONFIG_PCI_MSI */ +extern int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); +extern int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec); + +#define PCI_VENDOR_ID_BF 0x1d1c +#define TOFINO_DEV_ID 1 + +#ifndef PCI_MSIX_ENTRY_SIZE +#define PCI_MSIX_ENTRY_SIZE 16 +#define PCI_MSIX_ENTRY_LOWER_ADDR 0 +#define PCI_MSIX_ENTRY_UPPER_ADDR 4 +#define PCI_MSIX_ENTRY_DATA 8 +#define PCI_MSIX_ENTRY_VECTOR_CTRL 12 +#define PCI_MSIX_ENTRY_CTRL_MASKBIT 1 +#endif + +#define BF_CLASS_NAME "bf" +#define BF_MAX_DEVICE_CNT 256 +#define BF_INTR_MODE_NONE_NAME "none" +#define BF_INTR_MODE_LEGACY_NAME "legacy" +#define BF_INTR_MODE_MSI_NAME "msi" +#define BF_INTR_MODE_MSIX_NAME "msix" +#define BF_MAX_BAR_MAPS 6 +#define BF_MSIX_ENTRY_CNT 128 /* TBD make it 512 */ +#define BF_MSI_ENTRY_CNT 2 + +/* interrupt mode */ +enum bf_intr_mode { + BF_INTR_MODE_NONE = 0, + BF_INTR_MODE_LEGACY, + BF_INTR_MODE_MSI, + BF_INTR_MODE_MSIX +}; + +/* device memory */ +struct bf_dev_mem { + const char *name; + phys_addr_t addr; + resource_size_t size; + void __iomem *internal_addr; +}; + +/* device information */ +struct bf_dev_info { + struct module *owner; + struct device *dev; + int minor; + atomic_t event[BF_MSIX_ENTRY_CNT]; + struct fasync_struct *async_queue; + wait_queue_head_t wait; + const char *version; + struct bf_dev_mem mem[BF_MAX_BAR_MAPS]; + struct msix_entry *msix_entries; + long irq; /* first irq vector */ + int num_irq; /* number of irq vectors */ + unsigned long irq_flags;/* sharable ?? */ + int pci_error_state; /* was there a pci bus error */ +}; + +/* cookie to be passed to IRQ handler, useful especially with MSIX */ +struct bf_int_vector { + struct bf_pci_dev *bf_dev; + int int_vec_offset; +}; + + +/** + * A structure describing the private information for a BF pcie device. + */ +struct bf_pci_dev { + struct bf_dev_info info; + struct pci_dev *pdev; + struct cdev cdev; + enum bf_intr_mode mode; + u8 instance; + char name[16]; + struct bf_int_vector bf_int_vec[BF_MSIX_ENTRY_CNT]; +}; + +static int bf_major; +static int bf_minor[BF_MAX_DEVICE_CNT] = {0}; +static struct class *bf_class = NULL; +static char *intr_mode = NULL; +static enum bf_intr_mode bf_intr_mode_default = BF_INTR_MODE_MSI; +static spinlock_t bf_nonisr_lock; + +/* a pool of minor numbers is maintained */ +/* return the first available minor number */ +static int bf_get_next_minor_no(int *minor) +{ + int i; + + spin_lock(&bf_nonisr_lock); + for(i = 0; i < BF_MAX_DEVICE_CNT; i++) { + if (bf_minor[i] == 0) { + *minor = i; + bf_minor[i] = 1; /* mark it as taken */ + spin_unlock(&bf_nonisr_lock); + return 0; + } + } + *minor = -1; + spin_unlock(&bf_nonisr_lock); + return -1; +} + +/* return a minor number back to the pool for recycling */ +static int bf_return_minor_no(int minor) +{ + int err; + + spin_lock(&bf_nonisr_lock); + if (bf_minor[minor] == 0) { /* was already returned */ + err = -1; /* don't change anything, but return error */ + } else { + bf_minor[minor] = 0; /* mark it as available */ + err = 0; + } + spin_unlock(&bf_nonisr_lock); + return err; +} + +static inline struct bf_pci_dev *bf_get_pci_dev(struct bf_dev_info *info) +{ + return container_of(info, struct bf_pci_dev, info); +} + +/* + * It masks the msix on/off of generating MSI-X messages. + */ +static void +bf_msix_mask_irq(struct msi_desc *desc, int32_t state) +{ + u32 mask_bits = desc->masked; + unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + + PCI_MSIX_ENTRY_VECTOR_CTRL; + + if (state != 0) + mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; + else + mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; + + if (mask_bits != desc->masked) { + writel(mask_bits, desc->mask_base + offset); + readl(desc->mask_base); + desc->masked = mask_bits; + } +} + +/** + * irqcontrol can be used to disable/enable interrupt from user space processes. + * + * @param bf_dev + * pointer to bf_pci_dev + * @param irq_state + * state value. 1 to enable interrupt, 0 to disable interrupt. + * + * @return + * - On success, 0. + * - On failure, a negative value. + */ +static int +bf_pci_irqcontrol(struct bf_pci_dev *bfdev, s32 irq_state) +{ + struct pci_dev *pdev = bfdev->pdev; + + pci_cfg_access_lock(pdev); + if (bfdev->mode == BF_INTR_MODE_LEGACY) + pci_intx(pdev, !!irq_state); + + else if (bfdev->mode == BF_INTR_MODE_MSIX) { + struct msi_desc *desc; +#if LINUX_VERSION_CODE < KERNEL_VERSION(4,2,0) + list_for_each_entry(desc, &pdev->msi_list, list) + bf_msix_mask_irq(desc, irq_state); +#else + for_each_pci_msi_entry(desc, pdev) + bf_msix_mask_irq(desc, irq_state); +#endif + } + pci_cfg_access_unlock(pdev); + + return 0; +} + +/** + * interrupt handler which will check if the interrupt is from the right + * device. If so, disable it here and will be enabled later. + */ +static irqreturn_t bf_pci_irqhandler(int irq, struct bf_pci_dev *bfdev) +{ + /* Legacy mode need to mask in hardware */ + if (bfdev->mode == BF_INTR_MODE_LEGACY && + !pci_check_and_mask_intx(bfdev->pdev)) + return IRQ_NONE; + + /* NOTE : if bfdev->info.pci_error_state == 1, then do not access the + * device and return IRQ_NOTHANDLED. + */ + /* Message signal mode, no share IRQ and automasked */ + return IRQ_HANDLED; +} + +/* Remap pci resources described by bar #pci_bar */ +static int +bf_pci_setup_iomem(struct pci_dev *dev, struct bf_dev_info *info, + int n, int pci_bar, const char *name) +{ + unsigned long addr, len; + void *internal_addr; + + if (sizeof(info->mem) / sizeof(info->mem[0]) <= n) + return -EINVAL; + + addr = pci_resource_start(dev, pci_bar); + len = pci_resource_len(dev, pci_bar); + if (addr == 0 || len == 0) + return -1; + internal_addr = pci_ioremap_bar(dev, pci_bar); + if (internal_addr == NULL) + return -1; + info->mem[n].name = name; + info->mem[n].addr = addr; + info->mem[n].internal_addr = internal_addr; + info->mem[n].size = len; + return 0; +} + +/* Unmap previously ioremap'd resources */ +static void +bf_pci_release_iomem(struct bf_dev_info *info) +{ + int i; + + for (i = 0; i < BF_MAX_BAR_MAPS; i++) { + if (info->mem[i].internal_addr) + iounmap(info->mem[i].internal_addr); + } +} + +static int +bf_setup_bars(struct pci_dev *dev, struct bf_dev_info *info) +{ + int i, iom, ret; + unsigned long flags; + static const char *bar_names[BF_MAX_BAR_MAPS] = { + "BAR0", "BAR1", "BAR2", "BAR3", "BAR4", "BAR5", + }; + + iom = 0; + + for (i = 0; i < BF_MAX_BAR_MAPS; i++) { + if (pci_resource_len(dev, i) != 0 && + pci_resource_start(dev, i) != 0) { + flags = pci_resource_flags(dev, i); + if (flags & IORESOURCE_MEM) { + ret = bf_pci_setup_iomem(dev, info, iom, i, bar_names[i]); + if (ret != 0) + return ret; + iom++; + } + } + } + return (iom != 0) ? ret : -ENOENT; +} + +static irqreturn_t bf_interrupt(int irq, void *bfdev_id) +{ + struct bf_pci_dev *bfdev = ((struct bf_int_vector *)bfdev_id)->bf_dev; + int vect_off = ((struct bf_int_vector *)bfdev_id)->int_vec_offset; + + irqreturn_t ret = bf_pci_irqhandler(irq, bfdev); + + if (ret == IRQ_HANDLED) + atomic_inc(&(bfdev->info.event[vect_off])); + + return ret; +} + +struct bf_listener { + struct bf_pci_dev *bfdev; + s32 event_count[BF_MSIX_ENTRY_CNT]; +}; + +static unsigned int bf_poll(struct file *filep, poll_table *wait) +{ + struct bf_listener *listener = (struct bf_listener *)filep->private_data; + struct bf_pci_dev *bfdev = listener->bfdev; + int i; + + if (!bfdev->info.irq) + return -EIO; + + poll_wait(filep, &bfdev->info.wait, wait); + + for (i = 0; i < BF_MSIX_ENTRY_CNT; i++) + if (listener->event_count[i] != atomic_read(&bfdev->info.event[i])) + return POLLIN | POLLRDNORM; + return 0; +} + +static int bf_find_mem_index(struct vm_area_struct *vma) +{ + struct bf_pci_dev *bfdev = vma->vm_private_data; + if (vma->vm_pgoff < BF_MAX_BAR_MAPS) { + if (bfdev->info.mem[vma->vm_pgoff].size == 0) + return -1; + return (int)vma->vm_pgoff; + } + return -1; +} + +static const struct vm_operations_struct bf_physical_vm_ops = { +#ifdef CONFIG_HAVE_IOREMAP_PROT + .access = generic_access_phys, +#endif +}; + +static int bf_mmap_physical(struct vm_area_struct *vma) +{ + struct bf_pci_dev *bfdev = vma->vm_private_data; + int bar = bf_find_mem_index(vma); + struct bf_dev_mem *mem; + if (bar < 0) + return -EINVAL; + + mem = bfdev->info.mem + bar; + + if (mem->addr & ~PAGE_MASK) + return -ENODEV; + if (vma->vm_end - vma->vm_start > mem->size) + return -EINVAL; + + vma->vm_ops = &bf_physical_vm_ops; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + + /* + * We cannot use the vm_iomap_memory() helper here, + * because vma->vm_pgoff is the map index we looked + * up above in bf_find_mem_index(), rather than an + * actual page offset into the mmap. + * + * So we just do the physical mmap without a page + * offset. + */ + return remap_pfn_range(vma, vma->vm_start, mem->addr >> PAGE_SHIFT, + vma->vm_end - vma->vm_start, vma->vm_page_prot); +} + +static int bf_mmap(struct file *filep, struct vm_area_struct *vma) +{ + struct bf_listener *listener = filep->private_data; + struct bf_pci_dev *bfdev = listener->bfdev; + int bar; + unsigned long requested_pages, actual_pages; + + if (vma->vm_end < vma->vm_start) + return -EINVAL; + + vma->vm_private_data = bfdev; + + bar = bf_find_mem_index(vma); + if (bar < 0) + return -EINVAL; + + requested_pages = vma_pages(vma); + actual_pages = ((bfdev->info.mem[bar].addr & ~PAGE_MASK) + + bfdev->info.mem[bar].size + PAGE_SIZE -1) >> PAGE_SHIFT; + if (requested_pages > actual_pages) + return -EINVAL; + + return bf_mmap_physical(vma); +} + +static int bf_fasync(int fd, struct file *filep, int mode) +{ + struct bf_pci_dev *bfdev = ((struct bf_listener *)filep->private_data)->bfdev; + + if (mode == 0 && &bfdev->info.async_queue == NULL) { + return 0; /* nothing to do */ + } + return (fasync_helper(fd, filep, mode, &bfdev->info.async_queue)); +} + +static int bf_open(struct inode *inode, struct file *filep) +{ + struct bf_pci_dev *bfdev; + struct bf_listener *listener; + int i; + + bfdev = container_of(inode->i_cdev, struct bf_pci_dev, cdev); + listener = kmalloc(sizeof(*listener), GFP_KERNEL); + if (listener) { + listener->bfdev = bfdev; + for (i = 0; i < BF_MSIX_ENTRY_CNT; i++) + listener->event_count[i] = atomic_read(&bfdev->info.event[i]); + filep->private_data = listener; + return 0; + } else { + return(-ENOMEM); + } +} + +static int bf_release(struct inode *inode, struct file *filep) +{ + struct bf_listener *listener = filep->private_data; + + bf_fasync(-1, filep, 0); /* empty any process id in the notification list */ + kfree(listener); + return 0; +} + +/* user space support: make read() system call after poll() of select() */ +static ssize_t bf_read(struct file *filep, char __user *buf, + size_t count, loff_t *ppos) +{ + struct bf_listener *listener = filep->private_data; + struct bf_pci_dev *bfdev = listener->bfdev; + int retval, event_count[BF_MSIX_ENTRY_CNT]; + int i, mismatch_found = 0; /* OR of per vector mismatch */ + unsigned char cnt_match[BF_MSIX_ENTRY_CNT]; /* per vector mismatch */ + + /* irq must be setup for read() to work */ + if (!bfdev->info.irq) + return -EIO; + + /* ensure that there is enough space on user buffer for the given interrupt + * mode */ + if (bfdev->mode == BF_INTR_MODE_MSIX) { + if (count < sizeof(s32)*BF_MSIX_ENTRY_CNT) + return -EINVAL; + count = sizeof(s32)*BF_MSIX_ENTRY_CNT; + } else if (bfdev->mode == BF_INTR_MODE_MSI) { + if (count < sizeof(s32)*BF_MSI_ENTRY_CNT) + return -EINVAL; + count = sizeof(s32)*BF_MSI_ENTRY_CNT; + } else { + if (count < sizeof(s32)) + return -EINVAL; + count = sizeof(s32); + } + count = sizeof(s32)*BF_MSIX_ENTRY_CNT; + + do { + set_current_state(TASK_INTERRUPTIBLE); + + for (i = 0; i < (count/sizeof(s32)); i++) { + event_count[i] = atomic_read(&(bfdev->info.event[i])); + if (event_count[i] != listener->event_count[i]) { + mismatch_found |= 1; + cnt_match[i] = 1; + } else { + event_count[i] = 0; + cnt_match[i] = 0; + } + } + if (mismatch_found) { + __set_current_state(TASK_RUNNING); + if (copy_to_user(buf, &event_count, count)) + retval = -EFAULT; + else { /* adjust the listener->event_count; */ + for (i = 0 ; i < BF_MSIX_ENTRY_CNT; i++) { + if (cnt_match[i]) { + listener->event_count[i] = event_count[i]; + } + } + retval = count; + } + break; + } + + if (filep->f_flags & O_NONBLOCK) { + retval = -EAGAIN; + break; + } + + if (signal_pending(current)) { + retval = -ERESTARTSYS; + break; + } + schedule(); + } while (1); + + __set_current_state(TASK_RUNNING); + + return retval; +} + +/* user space is supposed to call this after it is done with interrupt + * processing + */ +static ssize_t bf_write(struct file *filep, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct bf_listener *listener = filep->private_data; + struct bf_pci_dev *bfdev = listener->bfdev; + ssize_t ret; + s32 int_en; + + if (!bfdev || !bfdev->info.irq) + return -EIO; + + if (count != sizeof(s32)) + return -EINVAL; + + if (copy_from_user(&int_en, buf, count)) + return -EFAULT; + + /* clear pci_error_state */ + bfdev->info.pci_error_state = 0; + + ret = bf_pci_irqcontrol(bfdev, int_en); + + return ret ? ret : sizeof(s32); +} + +static const struct file_operations bf_fops = { + .owner = THIS_MODULE, + .open = bf_open, + .release = bf_release, + .read = bf_read, + .write = bf_write, + .mmap = bf_mmap, + .poll = bf_poll, + .fasync = bf_fasync, +}; + +static int bf_major_init(struct bf_pci_dev *bfdev) +{ + static const char name[] = "bf"; + dev_t bf_dev = 0; + int result; + + result = alloc_chrdev_region(&bf_dev, 0, BF_MAX_DEVICE_CNT, name); + if (result) + return result; + + result = -ENOMEM; +/* following code useful if we chose to allocate cdev here + * + *struct cdev *cdev = NULL; + * cdev = cdev_alloc(); + * if (!cdev) + * goto fail_unregister; + * cdev->ops = &bf_fops; + * cdev->owner = THIS_MODULE; + * kobject_set_name(&cdev->kobj, "%s", name); + * result = cdev_add(cdev, bf_dev, BF_MAX_DEVICE_CNT); + */ + cdev_init(&bfdev->cdev, &bf_fops); + bfdev->cdev.owner = THIS_MODULE; + bfdev->cdev.ops = &bf_fops; + + result = cdev_add(&bfdev->cdev, bf_dev, BF_MAX_DEVICE_CNT); + if (result) + goto fail_dev_add; + + bf_major = MAJOR(bf_dev); + return 0; + +fail_dev_add: + unregister_chrdev_region(bf_dev, BF_MAX_DEVICE_CNT); + return result; +} + +static void bf_major_cleanup(struct bf_pci_dev *bfdev) +{ + unregister_chrdev_region(MKDEV(bf_major, 0), BF_MAX_DEVICE_CNT); + cdev_del(&bfdev->cdev); +} + +static int bf_init_cdev(struct bf_pci_dev *bfdev) +{ + int ret; + ret = bf_major_init(bfdev); + if (ret) + return ret; + + bf_class = class_create(THIS_MODULE, BF_CLASS_NAME); + if (!bf_class) { + printk(KERN_ERR "create_class failed for bf_dev\n"); + ret = -ENODEV; + goto err_class_register; + } + return 0; + +err_class_register: + bf_major_cleanup(bfdev); + return ret; +} + +static void bf_remove_cdev(struct bf_pci_dev *bfdev) +{ + class_destroy(bf_class); + bf_major_cleanup(bfdev); +} + + +/** + * bf_register_device - register a new userspace mem device + * @parent: parent device + * @bfdev: bf pci device + * + * returns zero on success or a negative error code. + */ +int bf_register_device(struct device *parent, struct bf_pci_dev *bfdev) +{ + struct bf_dev_info *info = &bfdev->info; + int i, j, ret = 0; + int minor; + + if (!parent || !info || !info->version) + return -EINVAL; + + init_waitqueue_head(&info->wait); + + for (i = 0; i < BF_MSIX_ENTRY_CNT; i++) { + atomic_set(&info->event[i], 0); + } + + ret = bf_init_cdev(bfdev); + if (ret) { + printk(KERN_ERR "BF: device cdev creation failed\n"); + return ret; + } + + if (bf_get_next_minor_no(&minor)) { + return -EINVAL; + } + + info->dev = device_create(bf_class, parent, + MKDEV(bf_major, minor), bfdev, + "bf%d", minor); + if (!info->dev) { + printk(KERN_ERR "BF: device creation failed\n"); + return -ENODEV; + } + + info->minor = minor; + + /* bind ISRs and request interrupts */ + if (info->irq && (bfdev->mode != BF_INTR_MODE_NONE)) { + /* + * Note that we deliberately don't use devm_request_irq + * here. The parent module can unregister the UIO device + * and call pci_disable_msi, which requires that this + * irq has been freed. However, the device may have open + * FDs at the time of unregister and therefore may not be + * freed until they are released. + */ + if (bfdev->mode == BF_INTR_MODE_LEGACY) { + ret = request_irq(info->irq, bf_interrupt, + info->irq_flags, bfdev->name, + (void *)&(bfdev->bf_int_vec[0])); + if (ret) { + printk(KERN_ERR "bf failed to request legacy irq %ld error %d\n", + info->irq, ret); + return ret; + } + printk(KERN_NOTICE "BF allocating legacy int vector %ld\n", info->irq); + } else if (bfdev->mode == BF_INTR_MODE_MSIX) { + for (i = 0; i < info->num_irq; i++) { + ret = request_irq(info->msix_entries[i].vector, bf_interrupt, + info->irq_flags, bfdev->name, + (void *)&(bfdev->bf_int_vec[i])); + if (ret) { + /* undo all other previous bindings */ + printk(KERN_ERR "bf failed to request MSIX ret %d itr %d\n", ret, i); + for (j = i - 1; j >= 0; j--) { + free_irq(info->msix_entries[j].vector, + (void *)&(bfdev->bf_int_vec[j])); + } + return ret; + } + } + printk(KERN_NOTICE "BF allocating %d MSIx vectors from %ld\n", + info->num_irq, info->irq); + } else if (bfdev->mode == BF_INTR_MODE_MSI) { + for (i = 0; i < info->num_irq; i++) { + ret = request_irq(info->irq + i, bf_interrupt, + info->irq_flags, bfdev->name, + (void *)&(bfdev->bf_int_vec[i])); + if (ret) { + /* undo all other previous bindings */ + printk(KERN_ERR "bf failed to request MSI ret %d itr %d\n", ret, i); + for (j = i - 1; j >= 0; j--) { + free_irq(info->irq + j, (void *)&(bfdev->bf_int_vec[j])); + } + return ret; + } + } + printk(KERN_NOTICE "BF allocating %d MSI vectors from %ld\n", + info->num_irq, info->irq); + } + } + return 0; +} + +/** + * bf_unregister_device - register a new userspace mem device + * @bfdev: bf pci device + * + * returns none + */ +void bf_unregister_device(struct bf_pci_dev *bfdev) +{ + struct bf_dev_info *info = &bfdev->info; + int i; + + if (info->irq) { + if (bfdev->mode == BF_INTR_MODE_LEGACY) { + free_irq(info->irq, (void *)&(bfdev->bf_int_vec[0])); + } else if (bfdev->mode == BF_INTR_MODE_MSIX) { + for (i = 0; i < info->num_irq; i++) { + free_irq(info->msix_entries[i].vector, (void *)&(bfdev->bf_int_vec[i])); + } + } else if (bfdev->mode == BF_INTR_MODE_MSI) { + for (i = 0; i < info->num_irq; i++) { + free_irq(info->irq + i, (void *)&(bfdev->bf_int_vec[i])); + } + } + } + device_destroy(bf_class, MKDEV(bf_major, info->minor)); + bf_remove_cdev(bfdev); + bf_return_minor_no(info->minor); + return; +} + +static inline struct device *pci_dev_to_dev(struct pci_dev *pdev) +{ + return &pdev->dev; +} + +static int +bf_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct bf_pci_dev *bfdev; + int err, pci_use_highmem; + int i, num_irq; + + bfdev = kzalloc(sizeof(struct bf_pci_dev), GFP_KERNEL); + if (!bfdev) + return -ENOMEM; + + /* init the cookies to be passed to ISRs */ + for (i = 0; i < BF_MSIX_ENTRY_CNT; i++) { + bfdev->bf_int_vec[i].int_vec_offset = i; + bfdev->bf_int_vec[i].bf_dev = bfdev; + } + + bfdev->info.async_queue = NULL; + + /* initialize intr_mode to none */ + bfdev->mode = BF_INTR_MODE_NONE; + + /* clear pci_error_state */ + bfdev->info.pci_error_state = 0; + + /* + * enable device + */ + err = pci_enable_device(pdev); + if (err != 0) { + dev_err(&pdev->dev, "Cannot enable PCI device\n"); + goto fail_free; + } + + /* + * reserve device's PCI memory regions for use by this + * module + */ + err = pci_request_regions(pdev, "bf_umem"); + if (err != 0) { + dev_err(&pdev->dev, "Cannot request regions\n"); + goto fail_pci_disable; + } + /* remap IO memory */ + err = bf_setup_bars(pdev, &bfdev->info); + if (err != 0) + goto fail_release_iomem; + + if (!dma_set_mask(pci_dev_to_dev(pdev), DMA_BIT_MASK(64)) && + !dma_set_coherent_mask(pci_dev_to_dev(pdev), DMA_BIT_MASK(64))) { + pci_use_highmem = 1; + } else { + err = dma_set_mask(pci_dev_to_dev(pdev), DMA_BIT_MASK(32)); + if (err) { + err = dma_set_coherent_mask(pci_dev_to_dev(pdev), + DMA_BIT_MASK(32)); + if (err) { + dev_err(pci_dev_to_dev(pdev), "No usable DMA " + "configuration, aborting\n"); + goto fail_release_iomem; + } + } + pci_use_highmem = 0; + } + + /* enable pci error reporting */ + /* for the current kernel version, kernel config must have set the followings: + * CONFIG_PCIEPORTBUS=y and CONFIG_PCIEAER = y + * we have pci_error_handlers defined that gets invoked by kernel AER module + * upon detecting the pcie error on this device's addresses. + * However, there seems no way that AER would pass the offending addresses + * to the callback functions. AER logs the error messages on the console. + * This driver's calback function send the SIGIO signal to the user space + * to indicate the error condition. + */ + pci_enable_pcie_error_reporting(pdev); + + /* enable bus mastering on the device */ + pci_set_master(pdev); + + /* fill in bfdev info */ + bfdev->info.version = "0.2"; + bfdev->info.owner = THIS_MODULE; + bfdev->pdev = pdev; + + switch (bf_intr_mode_default) { +#ifdef CONFIG_PCI_MSI + case BF_INTR_MODE_MSIX: + /* Only 1 msi-x vector needed */ + bfdev->info.msix_entries = kcalloc(BF_MSIX_ENTRY_CNT, + sizeof(struct msix_entry), GFP_KERNEL); + if (!bfdev->info.msix_entries) { + err = -ENOMEM; + goto fail_clear_pci_master; + } + for (i = 0; i < BF_MSIX_ENTRY_CNT; i++) { + bfdev->info.msix_entries[i].entry= i; + } + num_irq = pci_enable_msix_range(pdev, bfdev->info.msix_entries, + BF_MSIX_ENTRY_CNT, BF_MSIX_ENTRY_CNT); + if (num_irq == BF_MSIX_ENTRY_CNT) { + dev_dbg(&pdev->dev, "using MSI-X"); + bfdev->info.num_irq = num_irq; + bfdev->info.irq = bfdev->info.msix_entries[0].vector; + bfdev->mode = BF_INTR_MODE_MSIX; + printk(KERN_DEBUG "bf using %d MSIX irq from %ld\n", num_irq, + bfdev->info.irq); + break; + } else { + if (num_irq) + pci_disable_msix(pdev); + kfree(bfdev->info.msix_entries); + bfdev->info.msix_entries = NULL; + printk(KERN_ERR "bf error allocating MSIX vectors. Trying MSI...\n"); + /* and, fall back to MSI */ + } + /* ** intentional no-break */ + case BF_INTR_MODE_MSI: + num_irq = pci_enable_msi_range(pdev, BF_MSI_ENTRY_CNT, BF_MSI_ENTRY_CNT); + if (num_irq > 0) { + dev_dbg(&pdev->dev, "using MSI"); + bfdev->info.num_irq = num_irq; + bfdev->info.irq = pdev->irq; + bfdev->mode = BF_INTR_MODE_MSI; + printk(KERN_DEBUG "bf using %d MSI irq from %ld\n", bfdev->info.num_irq, + bfdev->info.irq); + break; + } +#endif /* CONFIG_PCI_MSI */ + /* fall back to Legacy Interrupt, intentional no-break */ + + case BF_INTR_MODE_LEGACY: + if (pci_intx_mask_supported(pdev)) { + dev_dbg(&pdev->dev, "using INTX"); + bfdev->info.irq_flags = IRQF_SHARED; + bfdev->info.irq = pdev->irq; + bfdev->mode = BF_INTR_MODE_LEGACY; + printk(KERN_DEBUG "bf using LEGACY irq %ld\n", bfdev->info.irq); + break; + } + dev_notice(&pdev->dev, "PCI INTx mask not supported\n"); + /* fall back to no Interrupt, intentional no-break */ + case BF_INTR_MODE_NONE: + bfdev->info.irq = 0; + bfdev->info.num_irq = 0; + bfdev->mode = BF_INTR_MODE_NONE; + break; + + default: + dev_err(&pdev->dev, "invalid IRQ mode %u", bf_intr_mode_default); + err = -EINVAL; + goto fail_clear_pci_master; + } + + /* register bf driver */ + err = bf_register_device(&pdev->dev, bfdev); + if (err != 0) + goto fail_release_irq; + sprintf(bfdev->name, "bf_%d", bfdev->info.minor); + pci_set_drvdata(pdev, bfdev); + + dev_info(&pdev->dev, "bf device %d registered with irq %ld\n", + bfdev->instance, bfdev->info.irq); + printk(KERN_ALERT "bf probe ok\n"); + return 0; + +fail_release_irq: + if (bfdev->mode == BF_INTR_MODE_MSIX) { + pci_disable_msix(bfdev->pdev); + kfree(bfdev->info.msix_entries); + bfdev->info.msix_entries = NULL; + } + else if (bfdev->mode == BF_INTR_MODE_MSI) + pci_disable_msi(bfdev->pdev); +fail_clear_pci_master: + pci_clear_master(pdev); +fail_release_iomem: + bf_pci_release_iomem(&bfdev->info); + pci_release_regions(pdev); +fail_pci_disable: + pci_disable_device(pdev); +fail_free: + kfree(bfdev); + + printk(KERN_ERR "bf probe not ok\n"); + return err; +} + +static void +bf_pci_remove(struct pci_dev *pdev) +{ + struct bf_pci_dev *bfdev = pci_get_drvdata(pdev); + + bf_unregister_device(bfdev); + if (bfdev->mode == BF_INTR_MODE_MSIX) { + pci_disable_msix(pdev); + kfree(bfdev->info.msix_entries); + bfdev->info.msix_entries = NULL; + } + else if (bfdev->mode == BF_INTR_MODE_MSI) + pci_disable_msi(pdev); + pci_clear_master(pdev); + bf_pci_release_iomem(&bfdev->info); + pci_release_regions(pdev); + pci_disable_pcie_error_reporting(pdev); + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); + kfree(bfdev); +} + +/** + * bf_pci_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * called when root complex detects pci error associated with the device + */ +static pci_ers_result_t bf_pci_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct bf_pci_dev *bfdev = pci_get_drvdata(pdev); + + if (!bfdev) { + return PCI_ERS_RESULT_NONE; + } + printk(KERN_ERR "pci_err_detected state %d asyncQ %p\n", state, &bfdev->info.async_queue); + if (state == pci_channel_io_perm_failure || state == pci_channel_io_frozen) { + bfdev->info.pci_error_state = 1; + /* send a signal to the user space program of the error */ + if (bfdev->info.async_queue) { + kill_fasync(&bfdev->info.async_queue, SIGIO, POLL_ERR); + } + return PCI_ERS_RESULT_DISCONNECT; + } else { + return PCI_ERS_RESULT_NONE; + } +} + +/** + * bf_pci_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. + */ +static pci_ers_result_t bf_pci_slot_reset(struct pci_dev *pdev) +{ + /* nothing to do for now as we do not expect to get backto normal after + * a pcie link reset + * TBD: fill in this function if tofino can recover after an error + */ + return PCI_ERS_RESULT_DISCONNECT; +} + +/** + * bf_pci_resume - called when kernel thinks the device is up on PCIe. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. + */ +static void bf_pci_resume(struct pci_dev *pdev) +{ + /* this function should never be called for Tofinoi */ + struct bf_pci_dev *bfdev = pci_get_drvdata(pdev); + + printk(KERN_ERR "BF io_resume invoked after pci error\n"); + if (bfdev) { + bfdev->info.pci_error_state = 0; + } +} + +static int +bf_config_intr_mode(char *intr_str) +{ + if (!intr_str) { + pr_info("Use MSIX interrupt by default\n"); + return 0; + } + + if (!strcmp(intr_str, BF_INTR_MODE_MSIX_NAME)) { + bf_intr_mode_default = BF_INTR_MODE_MSIX; + pr_info("Use MSIX interrupt\n"); + } else if (!strcmp(intr_str, BF_INTR_MODE_MSI_NAME)) { + bf_intr_mode_default = BF_INTR_MODE_MSI; + pr_info("Use MSI interrupt\n"); + } else if (!strcmp(intr_str, BF_INTR_MODE_LEGACY_NAME)) { + bf_intr_mode_default = BF_INTR_MODE_LEGACY; + pr_info("Use legacy interrupt\n"); + } else { + pr_info("Error: bad parameter - %s\n", intr_str); + return -EINVAL; + } + + return 0; +} + +static const struct pci_device_id bf_pci_tbl[] = { + {PCI_VDEVICE(BF, TOFINO_DEV_ID), 0}, + /* required last entry */ + { .device = 0 } +}; + +/* PCI bus error handlers */ +static struct pci_error_handlers bf_pci_err_handler = { + .error_detected = bf_pci_error_detected, + .slot_reset = bf_pci_slot_reset, + .resume = bf_pci_resume, +}; + +static struct pci_driver bf_pci_driver = { + .name = "bf", + .id_table = bf_pci_tbl, + .probe = bf_pci_probe, + .remove = bf_pci_remove, + .err_handler = &bf_pci_err_handler +}; + +static int __init +bfdrv_init(void) +{ + int ret; + + ret = bf_config_intr_mode(intr_mode); + if (ret < 0) + return ret; + + spin_lock_init(&bf_nonisr_lock); + return pci_register_driver(&bf_pci_driver); +} + +static void __exit +bfdrv_exit(void) +{ + pci_unregister_driver(&bf_pci_driver); +} + +module_init(bfdrv_init); +module_exit(bfdrv_exit); + +module_param(intr_mode, charp, S_IRUGO); +MODULE_PARM_DESC(intr_mode, +"bf interrupt mode (default=msi):\n" +" " BF_INTR_MODE_MSIX_NAME " Use MSIX interrupt\n" +" " BF_INTR_MODE_MSI_NAME " Use MSI interrupt\n" +" " BF_INTR_MODE_LEGACY_NAME " Use Legacy interrupt\n" +"\n"); + +MODULE_DEVICE_TABLE(pci, bf_pci_tbl); +MODULE_DESCRIPTION("Barefoot Tofino PCI device"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Barefoot Networks"); diff --git a/platform/barefoot/sonic-platform-modules-bfn/modules/bf_tun.c b/platform/barefoot/sonic-platform-modules-bfn/modules/bf_tun.c new file mode 100644 index 0000000000..a1ba7047ba --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/modules/bf_tun.c @@ -0,0 +1,2396 @@ +/* + * TUN - Universal TUN/TAP device driver. + * Copyright (C) 1999-2002 Maxim Krasnyansky + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * $Id: tun.c,v 1.15 2002/03/01 02:44:24 maxk Exp $ + */ + +/* + * Changes: + * + * Mike Kershaw 2005/08/14 + * Add TUNSETLINK ioctl to set the link encapsulation + * + * Mark Smith + * Use eth_random_addr() for tap MAC address. + * + * Harald Roelle 2004/04/20 + * Fixes in packet dropping, queue length setting and queue wakeup. + * Increased default tx queue length. + * Added ethtool API. + * Minor cleanups + * + * Daniel Podlejski + * Modifications for 2.3.99-pre5 kernel. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#define DRV_NAME "bf_tun" +#define DRV_VERSION "1.6" +#define DRV_DESCRIPTION "Universal TUN/TAP device driver" +#define DRV_COPYRIGHT "(C) 1999-2004 Max Krasnyansky " + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* Uncomment to enable debugging */ +/* #define TUN_DEBUG 1 */ + +#define TUN_MINOR1 201 + +#ifdef TUN_DEBUG +static int debug; + +#define tun_debug(level, tun, fmt, args...) \ +do { \ + if (tun->debug) \ + netdev_printk(level, tun->dev, fmt, ##args); \ +} while (0) +#define DBG1(level, fmt, args...) \ +do { \ + if (debug == 2) \ + printk(level fmt, ##args); \ +} while (0) +#else +#define tun_debug(level, tun, fmt, args...) \ +do { \ + if (0) \ + netdev_printk(level, tun->dev, fmt, ##args); \ +} while (0) +#define DBG1(level, fmt, args...) \ +do { \ + if (0) \ + printk(level fmt, ##args); \ +} while (0) +#endif + +#define GOODCOPY_LEN 128 + +#define FLT_EXACT_COUNT 8 +struct tap_filter { + unsigned int count; /* Number of addrs. Zero means disabled */ + u32 mask[2]; /* Mask of the hashed addrs */ + unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN]; +}; + +/* DEFAULT_MAX_NUM_RSS_QUEUES were chosen to let the rx/tx queues allocated for + * the netdevice to be fit in one page. So we can make sure the success of + * memory allocation. TODO: increase the limit. */ +#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES +#define MAX_TAP_FLOWS 4096 + +#define TUN_FLOW_EXPIRE (3 * HZ) + +/* A tun_file connects an open character device to a tuntap netdevice. It + * also contains all socket related structures (except sock_fprog and tap_filter) + * to serve as one transmit queue for tuntap device. The sock_fprog and + * tap_filter were kept in tun_struct since they were used for filtering for the + * netdevice not for a specific queue (at least I didn't see the requirement for + * this). + * + * RCU usage: + * The tun_file and tun_struct are loosely coupled, the pointer from one to the + * other can only be read while rcu_read_lock or rtnl_lock is held. + */ +struct tun_file { + struct sock sk; + struct socket socket; + struct socket_wq wq; + struct tun_struct __rcu *tun; + struct net *net; + struct fasync_struct *fasync; + /* only used for fasnyc */ + unsigned int flags; + union { + u16 queue_index; + unsigned int ifindex; + }; + struct list_head next; + struct tun_struct *detached; +}; + +struct tun_flow_entry { + struct hlist_node hash_link; + struct rcu_head rcu; + struct tun_struct *tun; + + u32 rxhash; + u32 rps_rxhash; + int queue_index; + unsigned long updated; +}; + +#define TUN_NUM_FLOW_ENTRIES 1024 + +/* Since the socket were moved to tun_file, to preserve the behavior of persist + * device, socket filter, sndbuf and vnet header size were restore when the + * file were attached to a persist device. + */ +struct tun_struct { + struct tun_file __rcu *tfiles[MAX_TAP_QUEUES]; + unsigned int numqueues; + unsigned int flags; + kuid_t owner; + kgid_t group; + + struct net_device *dev; + netdev_features_t set_features; +#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ + NETIF_F_TSO6|NETIF_F_UFO) + + int vnet_hdr_sz; + int sndbuf; + struct tap_filter txflt; + struct sock_fprog fprog; + /* protected by rtnl lock */ + bool filter_attached; +#ifdef TUN_DEBUG + int debug; +#endif + spinlock_t lock; + struct hlist_head flows[TUN_NUM_FLOW_ENTRIES]; + struct timer_list flow_gc_timer; + unsigned long ageing_time; + unsigned int numdisabled; + struct list_head disabled; + void *security; + u32 flow_count; +}; + +static inline u32 tun_hashfn(u32 rxhash) +{ + return rxhash & 0x3ff; +} + +static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash) +{ + struct tun_flow_entry *e; + + hlist_for_each_entry_rcu(e, head, hash_link) { + if (e->rxhash == rxhash) + return e; + } + return NULL; +} + +static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun, + struct hlist_head *head, + u32 rxhash, u16 queue_index) +{ + struct tun_flow_entry *e = kmalloc(sizeof(*e), GFP_ATOMIC); + + if (e) { + tun_debug(KERN_INFO, tun, "create flow: hash %u index %u\n", + rxhash, queue_index); + e->updated = jiffies; + e->rxhash = rxhash; + e->rps_rxhash = 0; + e->queue_index = queue_index; + e->tun = tun; + hlist_add_head_rcu(&e->hash_link, head); + ++tun->flow_count; + } + return e; +} + +static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e) +{ + tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n", + e->rxhash, e->queue_index); + sock_rps_reset_flow_hash(e->rps_rxhash); + hlist_del_rcu(&e->hash_link); + kfree_rcu(e, rcu); + --tun->flow_count; +} + +static void tun_flow_flush(struct tun_struct *tun) +{ + int i; + + spin_lock_bh(&tun->lock); + for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { + struct tun_flow_entry *e; + struct hlist_node *n; + + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) + tun_flow_delete(tun, e); + } + spin_unlock_bh(&tun->lock); +} + +static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index) +{ + int i; + + spin_lock_bh(&tun->lock); + for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { + struct tun_flow_entry *e; + struct hlist_node *n; + + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { + if (e->queue_index == queue_index) + tun_flow_delete(tun, e); + } + } + spin_unlock_bh(&tun->lock); +} + +static void tun_flow_cleanup(unsigned long data) +{ + struct tun_struct *tun = (struct tun_struct *)data; + unsigned long delay = tun->ageing_time; + unsigned long next_timer = jiffies + delay; + unsigned long count = 0; + int i; + + tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n"); + + spin_lock_bh(&tun->lock); + for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) { + struct tun_flow_entry *e; + struct hlist_node *n; + + hlist_for_each_entry_safe(e, n, &tun->flows[i], hash_link) { + unsigned long this_timer; + count++; + this_timer = e->updated + delay; + if (time_before_eq(this_timer, jiffies)) + tun_flow_delete(tun, e); + else if (time_before(this_timer, next_timer)) + next_timer = this_timer; + } + } + + if (count) + mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer)); + spin_unlock_bh(&tun->lock); +} + +static void tun_flow_update(struct tun_struct *tun, u32 rxhash, + struct tun_file *tfile) +{ + struct hlist_head *head; + struct tun_flow_entry *e; + unsigned long delay = tun->ageing_time; + u16 queue_index = tfile->queue_index; + + if (!rxhash) + return; + else + head = &tun->flows[tun_hashfn(rxhash)]; + + rcu_read_lock(); + + /* We may get a very small possibility of OOO during switching, not + * worth to optimize.*/ + if (tun->numqueues == 1 || tfile->detached) + goto unlock; + + e = tun_flow_find(head, rxhash); + if (likely(e)) { + /* TODO: keep queueing to old queue until it's empty? */ + e->queue_index = queue_index; + e->updated = jiffies; + sock_rps_record_flow_hash(e->rps_rxhash); + } else { + spin_lock_bh(&tun->lock); + if (!tun_flow_find(head, rxhash) && + tun->flow_count < MAX_TAP_FLOWS) + tun_flow_create(tun, head, rxhash, queue_index); + + if (!timer_pending(&tun->flow_gc_timer)) + mod_timer(&tun->flow_gc_timer, + round_jiffies_up(jiffies + delay)); + spin_unlock_bh(&tun->lock); + } + +unlock: + rcu_read_unlock(); +} + +/** + * Save the hash received in the stack receive path and update the + * flow_hash table accordingly. + */ +static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) +{ + if (unlikely(e->rps_rxhash != hash)) { + sock_rps_reset_flow_hash(e->rps_rxhash); + e->rps_rxhash = hash; + } +} + +/* We try to identify a flow through its rxhash first. The reason that + * we do not check rxq no. is because some cards(e.g 82599), chooses + * the rxq based on the txq where the last packet of the flow comes. As + * the userspace application move between processors, we may get a + * different rxq no. here. If we could not get rxhash, then we would + * hope the rxq no. may help here. + */ +static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) +{ + struct tun_struct *tun = netdev_priv(dev); + struct tun_flow_entry *e; + u32 txq = 0; + u32 numqueues = 0; + + rcu_read_lock(); + numqueues = ACCESS_ONCE(tun->numqueues); + + txq = skb_get_hash(skb); + if (txq) { + e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq); + if (e) { + tun_flow_save_rps_rxhash(e, txq); + txq = e->queue_index; + } else + /* use multiply and shift instead of expensive divide */ + txq = ((u64)txq * numqueues) >> 32; + } else if (likely(skb_rx_queue_recorded(skb))) { + txq = skb_get_rx_queue(skb); + while (unlikely(txq >= numqueues)) + txq -= numqueues; + } + + rcu_read_unlock(); + return txq; +} + +static inline bool tun_not_capable(struct tun_struct *tun) +{ + const struct cred *cred = current_cred(); + struct net *net = dev_net(tun->dev); + + return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || + (gid_valid(tun->group) && !in_egroup_p(tun->group))) && + !ns_capable(net->user_ns, CAP_NET_ADMIN); +} + +static void tun_set_real_num_queues(struct tun_struct *tun) +{ + netif_set_real_num_tx_queues(tun->dev, tun->numqueues); + netif_set_real_num_rx_queues(tun->dev, tun->numqueues); +} + +static void tun_disable_queue(struct tun_struct *tun, struct tun_file *tfile) +{ + tfile->detached = tun; + list_add_tail(&tfile->next, &tun->disabled); + ++tun->numdisabled; +} + +static struct tun_struct *tun_enable_queue(struct tun_file *tfile) +{ + struct tun_struct *tun = tfile->detached; + + tfile->detached = NULL; + list_del_init(&tfile->next); + --tun->numdisabled; + return tun; +} + +static void tun_queue_purge(struct tun_file *tfile) +{ + skb_queue_purge(&tfile->sk.sk_receive_queue); + skb_queue_purge(&tfile->sk.sk_error_queue); +} + +static void __tun_detach(struct tun_file *tfile, bool clean) +{ + struct tun_file *ntfile; + struct tun_struct *tun; + + tun = rtnl_dereference(tfile->tun); + + if (tun && !tfile->detached) { + u16 index = tfile->queue_index; + BUG_ON(index >= tun->numqueues); + + rcu_assign_pointer(tun->tfiles[index], + tun->tfiles[tun->numqueues - 1]); + ntfile = rtnl_dereference(tun->tfiles[index]); + ntfile->queue_index = index; + + --tun->numqueues; + if (clean) { + RCU_INIT_POINTER(tfile->tun, NULL); + sock_put(&tfile->sk); + } else + tun_disable_queue(tun, tfile); + + synchronize_net(); + tun_flow_delete_by_queue(tun, tun->numqueues + 1); + /* Drop read queue */ + tun_queue_purge(tfile); + tun_set_real_num_queues(tun); + } else if (tfile->detached && clean) { + tun = tun_enable_queue(tfile); + sock_put(&tfile->sk); + } + + if (clean) { + if (tun && tun->numqueues == 0 && tun->numdisabled == 0) { + netif_carrier_off(tun->dev); + + if (!(tun->flags & TUN_PERSIST) && + tun->dev->reg_state == NETREG_REGISTERED) + unregister_netdevice(tun->dev); + } + + BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED, + &tfile->socket.flags)); + sk_release_kernel(&tfile->sk); + } +} + +static void tun_detach(struct tun_file *tfile, bool clean) +{ + rtnl_lock(); + __tun_detach(tfile, clean); + rtnl_unlock(); +} + +static void tun_detach_all(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + struct tun_file *tfile, *tmp; + int i, n = tun->numqueues; + + for (i = 0; i < n; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + BUG_ON(!tfile); + tfile->socket.sk->sk_data_ready(tfile->socket.sk); + RCU_INIT_POINTER(tfile->tun, NULL); + --tun->numqueues; + } + list_for_each_entry(tfile, &tun->disabled, next) { + tfile->socket.sk->sk_data_ready(tfile->socket.sk); + RCU_INIT_POINTER(tfile->tun, NULL); + } + BUG_ON(tun->numqueues != 0); + + synchronize_net(); + for (i = 0; i < n; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + /* Drop read queue */ + tun_queue_purge(tfile); + sock_put(&tfile->sk); + } + list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { + tun_enable_queue(tfile); + tun_queue_purge(tfile); + sock_put(&tfile->sk); + } + BUG_ON(tun->numdisabled != 0); + + if (tun->flags & TUN_PERSIST) + module_put(THIS_MODULE); +} + +static int tun_attach(struct tun_struct *tun, struct file *file, bool skip_filter) +{ + struct tun_file *tfile = file->private_data; + int err; + + err = security_tun_dev_attach(tfile->socket.sk, tun->security); + if (err < 0) + goto out; + + err = -EINVAL; + if (rtnl_dereference(tfile->tun) && !tfile->detached) + goto out; + + err = -EBUSY; + if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1) + goto out; + + err = -E2BIG; + if (!tfile->detached && + tun->numqueues + tun->numdisabled == MAX_TAP_QUEUES) + goto out; + + err = 0; + + /* Re-attach the filter to persist device */ + if (!skip_filter && (tun->filter_attached == true)) { + err = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); + if (!err) + goto out; + } + tfile->queue_index = tun->numqueues; + rcu_assign_pointer(tfile->tun, tun); + rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); + tun->numqueues++; + + if (tfile->detached) + tun_enable_queue(tfile); + else + sock_hold(&tfile->sk); + + tun_set_real_num_queues(tun); + + /* device is allowed to go away first, so no need to hold extra + * refcnt. + */ + +out: + return err; +} + +static struct tun_struct *__tun_get(struct tun_file *tfile) +{ + struct tun_struct *tun; + + rcu_read_lock(); + tun = rcu_dereference(tfile->tun); + if (tun) + dev_hold(tun->dev); + rcu_read_unlock(); + + return tun; +} + +static struct tun_struct *tun_get(struct file *file) +{ + return __tun_get(file->private_data); +} + +static void tun_put(struct tun_struct *tun) +{ + dev_put(tun->dev); +} + +/* TAP filtering */ +static void addr_hash_set(u32 *mask, const u8 *addr) +{ + int n = ether_crc(ETH_ALEN, addr) >> 26; + mask[n >> 5] |= (1 << (n & 31)); +} + +static unsigned int addr_hash_test(const u32 *mask, const u8 *addr) +{ + int n = ether_crc(ETH_ALEN, addr) >> 26; + return mask[n >> 5] & (1 << (n & 31)); +} + +static int update_filter(struct tap_filter *filter, void __user *arg) +{ + struct { u8 u[ETH_ALEN]; } *addr; + struct tun_filter uf; + int err, alen, n, nexact; + + if (copy_from_user(&uf, arg, sizeof(uf))) + return -EFAULT; + + if (!uf.count) { + /* Disabled */ + filter->count = 0; + return 0; + } + + alen = ETH_ALEN * uf.count; + addr = kmalloc(alen, GFP_KERNEL); + if (!addr) + return -ENOMEM; + + if (copy_from_user(addr, arg + sizeof(uf), alen)) { + err = -EFAULT; + goto done; + } + + /* The filter is updated without holding any locks. Which is + * perfectly safe. We disable it first and in the worst + * case we'll accept a few undesired packets. */ + filter->count = 0; + wmb(); + + /* Use first set of addresses as an exact filter */ + for (n = 0; n < uf.count && n < FLT_EXACT_COUNT; n++) + memcpy(filter->addr[n], addr[n].u, ETH_ALEN); + + nexact = n; + + /* Remaining multicast addresses are hashed, + * unicast will leave the filter disabled. */ + memset(filter->mask, 0, sizeof(filter->mask)); + for (; n < uf.count; n++) { + if (!is_multicast_ether_addr(addr[n].u)) { + err = 0; /* no filter */ + goto done; + } + addr_hash_set(filter->mask, addr[n].u); + } + + /* For ALLMULTI just set the mask to all ones. + * This overrides the mask populated above. */ + if ((uf.flags & TUN_FLT_ALLMULTI)) + memset(filter->mask, ~0, sizeof(filter->mask)); + + /* Now enable the filter */ + wmb(); + filter->count = nexact; + + /* Return the number of exact filters */ + err = nexact; + +done: + kfree(addr); + return err; +} + +/* Returns: 0 - drop, !=0 - accept */ +static int run_filter(struct tap_filter *filter, const struct sk_buff *skb) +{ + /* Cannot use eth_hdr(skb) here because skb_mac_hdr() is incorrect + * at this point. */ + struct ethhdr *eh = (struct ethhdr *) skb->data; + int i; + + /* Exact match */ + for (i = 0; i < filter->count; i++) + if (ether_addr_equal(eh->h_dest, filter->addr[i])) + return 1; + + /* Inexact match (multicast only) */ + if (is_multicast_ether_addr(eh->h_dest)) + return addr_hash_test(filter->mask, eh->h_dest); + + return 0; +} + +/* + * Checks whether the packet is accepted or not. + * Returns: 0 - drop, !=0 - accept + */ +static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) +{ + if (!filter->count) + return 1; + + return run_filter(filter, skb); +} + +/* Network device part of the driver */ + +static const struct ethtool_ops tun_ethtool_ops; + +/* Net device detach from fd. */ +static void tun_net_uninit(struct net_device *dev) +{ + tun_detach_all(dev); +} + +/* Net device open. */ +static int tun_net_open(struct net_device *dev) +{ + netif_tx_start_all_queues(dev); + return 0; +} + +/* Net device close. */ +static int tun_net_close(struct net_device *dev) +{ + netif_tx_stop_all_queues(dev); + return 0; +} + +/* Net device start xmit */ +static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + int txq = skb->queue_mapping; + struct tun_file *tfile; + u32 numqueues = 0; + + rcu_read_lock(); + tfile = rcu_dereference(tun->tfiles[txq]); + numqueues = ACCESS_ONCE(tun->numqueues); + + /* Drop packet if interface is not attached */ + if (txq >= numqueues) + goto drop; + + if (numqueues == 1) { + /* Select queue was not called for the skbuff, so we extract the + * RPS hash and save it into the flow_table here. + */ + __u32 rxhash; + + rxhash = skb_get_hash(skb); + if (rxhash) { + struct tun_flow_entry *e; + e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], + rxhash); + if (e) + tun_flow_save_rps_rxhash(e, rxhash); + } + } + + tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len); + + BUG_ON(!tfile); + + /* Drop if the filter does not like it. + * This is a noop if the filter is disabled. + * Filter can be enabled only for the TAP devices. */ + if (!check_filter(&tun->txflt, skb)) + goto drop; + + if (tfile->socket.sk->sk_filter && + sk_filter(tfile->socket.sk, skb)) + goto drop; + + /* Limit the number of packets queued by dividing txq length with the + * number of queues. + */ + if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) * numqueues + >= dev->tx_queue_len) + goto drop; + + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + + if (skb->sk) { + sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags); + sw_tx_timestamp(skb); + } + + /* Orphan the skb - required as we might hang on to it + * for indefinite time. + */ + skb_orphan(skb); + + nf_reset(skb); + + /* Enqueue packet */ + skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb); + + /* Notify and wake up reader process */ + if (tfile->flags & TUN_FASYNC) + kill_fasync(&tfile->fasync, SIGIO, POLL_IN); + tfile->socket.sk->sk_data_ready(tfile->socket.sk); + + rcu_read_unlock(); + return NETDEV_TX_OK; + +drop: + dev->stats.tx_dropped++; + skb_tx_error(skb); + kfree_skb(skb); + rcu_read_unlock(); + return NETDEV_TX_OK; +} + +static void tun_net_mclist(struct net_device *dev) +{ + /* + * This callback is supposed to deal with mc filter in + * _rx_ path and has nothing to do with the _tx_ path. + * In rx path we always accept everything userspace gives us. + */ +} + +#define MIN_MTU 68 +#define MAX_MTU 65535 + +static int +tun_net_change_mtu(struct net_device *dev, int new_mtu) +{ + if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +static netdev_features_t tun_net_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct tun_struct *tun = netdev_priv(dev); + + return (features & tun->set_features) | (features & ~TUN_USER_FEATURES); +} + +static int +tun_change_carrier(struct net_device *dev, bool new_carrier) { + if (new_carrier) + netif_carrier_on(dev); + else + netif_carrier_off(dev); + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void tun_poll_controller(struct net_device *dev) +{ + /* + * Tun only receives frames when: + * 1) the char device endpoint gets data from user space + * 2) the tun socket gets a sendmsg call from user space + * Since both of those are synchronous operations, we are guaranteed + * never to have pending data when we poll for it + * so there is nothing to do here but return. + * We need this though so netpoll recognizes us as an interface that + * supports polling, which enables bridge devices in virt setups to + * still use netconsole + */ + return; +} +#endif +static const struct net_device_ops tun_netdev_ops = { + .ndo_uninit = tun_net_uninit, + .ndo_open = tun_net_open, + .ndo_stop = tun_net_close, + .ndo_start_xmit = tun_net_xmit, + .ndo_change_mtu = tun_net_change_mtu, + .ndo_fix_features = tun_net_fix_features, + .ndo_select_queue = tun_select_queue, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif +}; + +static const struct net_device_ops tap_netdev_ops = { + .ndo_uninit = tun_net_uninit, + .ndo_open = tun_net_open, + .ndo_stop = tun_net_close, + .ndo_start_xmit = tun_net_xmit, + .ndo_change_mtu = tun_net_change_mtu, + .ndo_fix_features = tun_net_fix_features, + .ndo_set_rx_mode = tun_net_mclist, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_select_queue = tun_select_queue, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tun_poll_controller, +#endif + .ndo_change_carrier = tun_change_carrier, +}; + +static void tun_flow_init(struct tun_struct *tun) +{ + int i; + + for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) + INIT_HLIST_HEAD(&tun->flows[i]); + + tun->ageing_time = TUN_FLOW_EXPIRE; + setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun); + mod_timer(&tun->flow_gc_timer, + round_jiffies_up(jiffies + tun->ageing_time)); +} + +static void tun_flow_uninit(struct tun_struct *tun) +{ + del_timer_sync(&tun->flow_gc_timer); + tun_flow_flush(tun); +} + +/* Initialize net device. */ +static void tun_net_init(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + switch (tun->flags & TUN_TYPE_MASK) { + case TUN_TUN_DEV: + dev->netdev_ops = &tun_netdev_ops; + + /* Point-to-Point TUN Device */ + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->mtu = 1500; + + /* Zero header length */ + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->tx_queue_len = TUN_READQ_SIZE*2; /* We prefer our own queue length */ + break; + + case TUN_TAP_DEV: + dev->netdev_ops = &tap_netdev_ops; + /* Ethernet TAP Device */ + ether_setup(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + + eth_hw_addr_random(dev); + + dev->tx_queue_len = TUN_READQ_SIZE*2; /* We prefer our own queue length */ + break; + } +} + +/* Character device part */ + +/* Poll */ +static unsigned int tun_chr_poll(struct file *file, poll_table *wait) +{ + struct tun_file *tfile = file->private_data; + struct tun_struct *tun = __tun_get(tfile); + struct sock *sk; + unsigned int mask = 0; + + if (!tun) + return POLLERR; + + sk = tfile->socket.sk; + + tun_debug(KERN_INFO, tun, "tun_chr_poll\n"); + + poll_wait(file, sk_sleep(sk), wait); + + if (!skb_queue_empty(&sk->sk_receive_queue)) + mask |= POLLIN | POLLRDNORM; + + if (sock_writeable(sk) || + (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) && + sock_writeable(sk))) + mask |= POLLOUT | POLLWRNORM; + + if (tun->dev->reg_state != NETREG_REGISTERED) + mask = POLLERR; + + tun_put(tun); + return mask; +} + +/* prepad is the amount to reserve at front. len is length after that. + * linear is a hint as to how much to copy (usually headers). */ +static struct sk_buff *tun_alloc_skb(struct tun_file *tfile, + size_t prepad, size_t len, + size_t linear, int noblock) +{ + struct sock *sk = tfile->socket.sk; + struct sk_buff *skb; + int err; + + /* Under a page? Don't bother with paged skb. */ + if (prepad + len < PAGE_SIZE || !linear) + linear = len; + + skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, + &err, 0); + if (!skb) + return ERR_PTR(err); + + skb_reserve(skb, prepad); + skb_put(skb, linear); + skb->data_len = len - linear; + skb->len += len - linear; + + return skb; +} + +/* Get packet from user space buffer */ +static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, + void *msg_control, const struct iovec *iv, + size_t total_len, size_t count, int noblock) +{ + struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) }; + struct sk_buff *skb; + size_t len = total_len, align = NET_SKB_PAD, linear; + struct virtio_net_hdr gso = { 0 }; + int good_linear; + int offset = 0; + int copylen; + bool zerocopy = false; + int err; + u32 rxhash; + + if (!(tun->flags & TUN_NO_PI)) { + if (len < sizeof(pi)) + return -EINVAL; + len -= sizeof(pi); + + if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi))) + return -EFAULT; + offset += sizeof(pi); + } + + if (tun->flags & TUN_VNET_HDR) { + if (len < tun->vnet_hdr_sz) + return -EINVAL; + len -= tun->vnet_hdr_sz; + + if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso))) + return -EFAULT; + + if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && + gso.csum_start + gso.csum_offset + 2 > gso.hdr_len) + gso.hdr_len = gso.csum_start + gso.csum_offset + 2; + + if (gso.hdr_len > len) + return -EINVAL; + offset += tun->vnet_hdr_sz; + } + + if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) { + align += NET_IP_ALIGN; + if (unlikely(len < ETH_HLEN || + (gso.hdr_len && gso.hdr_len < ETH_HLEN))) + return -EINVAL; + } + + good_linear = SKB_MAX_HEAD(align); + + if (msg_control) { + /* There are 256 bytes to be copied in skb, so there is + * enough room for skb expand head in case it is used. + * The rest of the buffer is mapped from userspace. + */ + copylen = gso.hdr_len ? gso.hdr_len : GOODCOPY_LEN; + if (copylen > good_linear) + copylen = good_linear; + linear = copylen; + if (iov_pages(iv, offset + copylen, count) <= MAX_SKB_FRAGS) + zerocopy = true; + } + + if (!zerocopy) { + copylen = len; + if (gso.hdr_len > good_linear) + linear = good_linear; + else + linear = gso.hdr_len; + } + + skb = tun_alloc_skb(tfile, align, copylen, linear, noblock); + if (IS_ERR(skb)) { + if (PTR_ERR(skb) != -EAGAIN) + tun->dev->stats.rx_dropped++; + return PTR_ERR(skb); + } + + if (zerocopy) + err = zerocopy_sg_from_iovec(skb, iv, offset, count); + else { + err = skb_copy_datagram_from_iovec(skb, 0, iv, offset, len); + if (!err && msg_control) { + struct ubuf_info *uarg = msg_control; + uarg->callback(uarg, false); + } + } + + if (err) { + tun->dev->stats.rx_dropped++; + kfree_skb(skb); + return -EFAULT; + } + + if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + if (!skb_partial_csum_set(skb, gso.csum_start, + gso.csum_offset)) { + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + } + + switch (tun->flags & TUN_TYPE_MASK) { + case TUN_TUN_DEV: + if (tun->flags & TUN_NO_PI) { + switch (skb->data[0] & 0xf0) { + case 0x40: + pi.proto = htons(ETH_P_IP); + break; + case 0x60: + pi.proto = htons(ETH_P_IPV6); + break; + default: + tun->dev->stats.rx_dropped++; + kfree_skb(skb); + return -EINVAL; + } + } + + skb_reset_mac_header(skb); + skb->protocol = pi.proto; + skb->dev = tun->dev; + break; + case TUN_TAP_DEV: + skb->protocol = eth_type_trans(skb, tun->dev); + break; + } + + skb_reset_network_header(skb); + + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + pr_debug("GSO!\n"); + switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + case VIRTIO_NET_HDR_GSO_UDP: + skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); + break; + default: + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + + if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + + skb_shinfo(skb)->gso_size = gso.gso_size; + if (skb_shinfo(skb)->gso_size == 0) { + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + + /* Header must be checked, and gso_segs computed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } + + /* copy skb_ubuf_info for callback when skb has no error */ + if (zerocopy) { + skb_shinfo(skb)->destructor_arg = msg_control; + skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + } + + skb_probe_transport_header(skb, 0); + + rxhash = skb_get_hash(skb); + netif_rx_ni(skb); + + tun->dev->stats.rx_packets++; + tun->dev->stats.rx_bytes += len; + + tun_flow_update(tun, rxhash, tfile); + return total_len; +} + +static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct tun_struct *tun = tun_get(file); + struct tun_file *tfile = file->private_data; + ssize_t result; + + if (!tun) + return -EBADFD; + + tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count); + + result = tun_get_user(tun, tfile, NULL, iv, iov_length(iv, count), + count, file->f_flags & O_NONBLOCK); + + tun_put(tun); + return result; +} + +/* Put packet to the user space buffer */ +static ssize_t tun_put_user(struct tun_struct *tun, + struct tun_file *tfile, + struct sk_buff *skb, + const struct iovec *iv, int len) +{ + struct tun_pi pi = { 0, skb->protocol }; + ssize_t total = 0; + int vlan_offset = 0, copied; + int vlan_hlen = 0; + + if (vlan_tx_tag_present(skb)) + vlan_hlen = VLAN_HLEN; + + if (!(tun->flags & TUN_NO_PI)) { + if ((len -= sizeof(pi)) < 0) + return -EINVAL; + + if (len < skb->len) { + /* Packet will be striped */ + pi.flags |= TUN_PKT_STRIP; + } + + if (memcpy_toiovecend(iv, (void *) &pi, 0, sizeof(pi))) + return -EFAULT; + total += sizeof(pi); + } + + if (tun->flags & TUN_VNET_HDR) { + struct virtio_net_hdr gso = { 0 }; /* no info leak */ + if ((len -= tun->vnet_hdr_sz) < 0) + return -EINVAL; + + if (skb_is_gso(skb)) { + struct skb_shared_info *sinfo = skb_shinfo(skb); + + /* This is a hint as to how much should be linear. */ + gso.hdr_len = skb_headlen(skb); + gso.gso_size = sinfo->gso_size; + if (sinfo->gso_type & SKB_GSO_TCPV4) + gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + else if (sinfo->gso_type & SKB_GSO_TCPV6) + gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else if (sinfo->gso_type & SKB_GSO_UDP) + gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; + else { + pr_err("unexpected GSO type: " + "0x%x, gso_size %d, hdr_len %d\n", + sinfo->gso_type, gso.gso_size, + gso.hdr_len); + print_hex_dump(KERN_ERR, "tun: ", + DUMP_PREFIX_NONE, + 16, 1, skb->head, + min((int)gso.hdr_len, 64), true); + WARN_ON_ONCE(1); + return -EINVAL; + } + if (sinfo->gso_type & SKB_GSO_TCP_ECN) + gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN; + } else + gso.gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + gso.csum_start = skb_checksum_start_offset(skb) + + vlan_hlen; + gso.csum_offset = skb->csum_offset; + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + gso.flags = VIRTIO_NET_HDR_F_DATA_VALID; + } /* else everything is zero */ + + if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total, + sizeof(gso)))) + return -EFAULT; + total += tun->vnet_hdr_sz; + } + + copied = total; + len = min_t(int, skb->len + vlan_hlen, len); + total += skb->len + vlan_hlen; + if (vlan_hlen) { + int copy, ret; + struct { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + } veth; + + veth.h_vlan_proto = skb->vlan_proto; + veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); + + vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); + + copy = min_t(int, vlan_offset, len); + ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy); + len -= copy; + copied += copy; + if (ret || !len) + goto done; + + copy = min_t(int, sizeof(veth), len); + ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy); + len -= copy; + copied += copy; + if (ret || !len) + goto done; + } + + skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len); + +done: + tun->dev->stats.tx_packets++; + tun->dev->stats.tx_bytes += len; + + return total; +} + +static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, + const struct iovec *iv, ssize_t len, int noblock) +{ + struct sk_buff *skb; + ssize_t ret = 0; + int peeked, err, off = 0; + + tun_debug(KERN_INFO, tun, "tun_do_read\n"); + + if (!len) + return ret; + + if (tun->dev->reg_state != NETREG_REGISTERED) + return -EIO; + + /* Read frames from queue */ + skb = __skb_recv_datagram(tfile->socket.sk, noblock ? MSG_DONTWAIT : 0, + &peeked, &off, &err); + if (skb) { + ret = tun_put_user(tun, tfile, skb, iv, len); + kfree_skb(skb); + } else + ret = err; + + return ret; +} + +static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv, + unsigned long count, loff_t pos) +{ + struct file *file = iocb->ki_filp; + struct tun_file *tfile = file->private_data; + struct tun_struct *tun = __tun_get(tfile); + ssize_t len, ret; + + if (!tun) + return -EBADFD; + len = iov_length(iv, count); + if (len < 0) { + ret = -EINVAL; + goto out; + } + + ret = tun_do_read(tun, tfile, iv, len, + file->f_flags & O_NONBLOCK); + ret = min_t(ssize_t, ret, len); + if (ret > 0) + iocb->ki_pos = ret; +out: + tun_put(tun); + return ret; +} + +static void tun_free_netdev(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + BUG_ON(!(list_empty(&tun->disabled))); + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); + free_netdev(dev); +} + +static void tun_setup(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + + tun->owner = INVALID_UID; + tun->group = INVALID_GID; + + dev->ethtool_ops = &tun_ethtool_ops; + dev->destructor = tun_free_netdev; +} + +/* Trivial set of netlink ops to allow deleting tun or tap + * device with netlink. + */ +static int tun_validate(struct nlattr *tb[], struct nlattr *data[]) +{ + return -EINVAL; +} + +static struct rtnl_link_ops tun_link_ops __read_mostly = { + .kind = DRV_NAME, + .priv_size = sizeof(struct tun_struct), + .setup = tun_setup, + .validate = tun_validate, +}; + +static void tun_sock_write_space(struct sock *sk) +{ + struct tun_file *tfile; + wait_queue_head_t *wqueue; + + if (!sock_writeable(sk)) + return; + + if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) + return; + + wqueue = sk_sleep(sk); + if (wqueue && waitqueue_active(wqueue)) + wake_up_interruptible_sync_poll(wqueue, POLLOUT | + POLLWRNORM | POLLWRBAND); + + tfile = container_of(sk, struct tun_file, sk); + kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); +} + +static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + int ret; + struct tun_file *tfile = container_of(sock, struct tun_file, socket); + struct tun_struct *tun = __tun_get(tfile); + + if (!tun) + return -EBADFD; + ret = tun_get_user(tun, tfile, m->msg_control, m->msg_iov, total_len, + m->msg_iovlen, m->msg_flags & MSG_DONTWAIT); + tun_put(tun); + return ret; +} + +static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len, + int flags) +{ + struct tun_file *tfile = container_of(sock, struct tun_file, socket); + struct tun_struct *tun = __tun_get(tfile); + int ret; + + if (!tun) + return -EBADFD; + + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { + ret = -EINVAL; + goto out; + } + if (flags & MSG_ERRQUEUE) { + ret = sock_recv_errqueue(sock->sk, m, total_len, + SOL_PACKET, TUN_TX_TIMESTAMP); + goto out; + } + ret = tun_do_read(tun, tfile, m->msg_iov, total_len, + flags & MSG_DONTWAIT); + if (ret > total_len) { + m->msg_flags |= MSG_TRUNC; + ret = flags & MSG_TRUNC ? ret : total_len; + } +out: + tun_put(tun); + return ret; +} + +static int tun_release(struct socket *sock) +{ + if (sock->sk) + sock_put(sock->sk); + return 0; +} + +/* Ops structure to mimic raw sockets with tun */ +static const struct proto_ops tun_socket_ops = { + .sendmsg = tun_sendmsg, + .recvmsg = tun_recvmsg, + .release = tun_release, +}; + +static struct proto tun_proto = { + .name = "bf_tun", + .owner = THIS_MODULE, + .obj_size = sizeof(struct tun_file), +}; + +static int tun_flags(struct tun_struct *tun) +{ + int flags = 0; + + if (tun->flags & TUN_TUN_DEV) + flags |= IFF_TUN; + else + flags |= IFF_TAP; + + if (tun->flags & TUN_NO_PI) + flags |= IFF_NO_PI; + + /* This flag has no real effect. We track the value for backwards + * compatibility. + */ + if (tun->flags & TUN_ONE_QUEUE) + flags |= IFF_ONE_QUEUE; + + if (tun->flags & TUN_VNET_HDR) + flags |= IFF_VNET_HDR; + + if (tun->flags & TUN_TAP_MQ) + flags |= IFF_MULTI_QUEUE; + + if (tun->flags & TUN_PERSIST) + flags |= IFF_PERSIST; + + return flags; +} + +static ssize_t tun_show_flags(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tun_struct *tun = netdev_priv(to_net_dev(dev)); + return sprintf(buf, "0x%x\n", tun_flags(tun)); +} + +static ssize_t tun_show_owner(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tun_struct *tun = netdev_priv(to_net_dev(dev)); + return uid_valid(tun->owner)? + sprintf(buf, "%u\n", + from_kuid_munged(current_user_ns(), tun->owner)): + sprintf(buf, "-1\n"); +} + +static ssize_t tun_show_group(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct tun_struct *tun = netdev_priv(to_net_dev(dev)); + return gid_valid(tun->group) ? + sprintf(buf, "%u\n", + from_kgid_munged(current_user_ns(), tun->group)): + sprintf(buf, "-1\n"); +} + +static DEVICE_ATTR(tun_flags, 0444, tun_show_flags, NULL); +static DEVICE_ATTR(owner, 0444, tun_show_owner, NULL); +static DEVICE_ATTR(group, 0444, tun_show_group, NULL); + +static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) +{ + struct tun_struct *tun; + struct tun_file *tfile = file->private_data; + struct net_device *dev; + int err; + + if (tfile->detached) + return -EINVAL; + + dev = __dev_get_by_name(net, ifr->ifr_name); + if (dev) { + if (ifr->ifr_flags & IFF_TUN_EXCL) + return -EBUSY; + if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops) + tun = netdev_priv(dev); + else if ((ifr->ifr_flags & IFF_TAP) && dev->netdev_ops == &tap_netdev_ops) + tun = netdev_priv(dev); + else + return -EINVAL; + + if (!!(ifr->ifr_flags & IFF_MULTI_QUEUE) != + !!(tun->flags & TUN_TAP_MQ)) + return -EINVAL; + + if (tun_not_capable(tun)) + return -EPERM; + err = security_tun_dev_open(tun->security); + if (err < 0) + return err; + + err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER); + if (err < 0) + return err; + + if (tun->flags & TUN_TAP_MQ && + (tun->numqueues + tun->numdisabled > 1)) { + /* One or more queue has already been attached, no need + * to initialize the device again. + */ + return 0; + } + } + else { + char *name; + unsigned long flags = 0; + int queues = ifr->ifr_flags & IFF_MULTI_QUEUE ? + MAX_TAP_QUEUES : 1; + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + err = security_tun_dev_create(); + if (err < 0) + return err; + + /* Set dev type */ + if (ifr->ifr_flags & IFF_TUN) { + /* TUN device */ + flags |= TUN_TUN_DEV; + name = "tun%d"; + } else if (ifr->ifr_flags & IFF_TAP) { + /* TAP device */ + flags |= TUN_TAP_DEV; + name = "tap%d"; + } else + return -EINVAL; + + if (*ifr->ifr_name) + name = ifr->ifr_name; + + dev = alloc_netdev_mqs(sizeof(struct tun_struct), name, + tun_setup, queues, queues); + + if (!dev) + return -ENOMEM; + + dev_net_set(dev, net); + dev->rtnl_link_ops = &tun_link_ops; + dev->ifindex = tfile->ifindex; + + tun = netdev_priv(dev); + tun->dev = dev; + tun->flags = flags; + tun->txflt.count = 0; + tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr); + + tun->filter_attached = false; + tun->sndbuf = tfile->socket.sk->sk_sndbuf; + + spin_lock_init(&tun->lock); + + err = security_tun_dev_alloc_security(&tun->security); + if (err < 0) + goto err_free_dev; + + tun_net_init(dev); + tun_flow_init(tun); + + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | + TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + dev->features = dev->hw_features; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + INIT_LIST_HEAD(&tun->disabled); + err = tun_attach(tun, file, false); + if (err < 0) + goto err_free_flow; + + err = register_netdevice(tun->dev); + if (err < 0) + goto err_detach; + + if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) || + device_create_file(&tun->dev->dev, &dev_attr_owner) || + device_create_file(&tun->dev->dev, &dev_attr_group)) + pr_err("Failed to create tun sysfs files\n"); + } + + netif_carrier_on(tun->dev); + + tun_debug(KERN_INFO, tun, "tun_set_iff\n"); + + if (ifr->ifr_flags & IFF_NO_PI) + tun->flags |= TUN_NO_PI; + else + tun->flags &= ~TUN_NO_PI; + + /* This flag has no real effect. We track the value for backwards + * compatibility. + */ + if (ifr->ifr_flags & IFF_ONE_QUEUE) + tun->flags |= TUN_ONE_QUEUE; + else + tun->flags &= ~TUN_ONE_QUEUE; + + if (ifr->ifr_flags & IFF_VNET_HDR) + tun->flags |= TUN_VNET_HDR; + else + tun->flags &= ~TUN_VNET_HDR; + + if (ifr->ifr_flags & IFF_MULTI_QUEUE) + tun->flags |= TUN_TAP_MQ; + else + tun->flags &= ~TUN_TAP_MQ; + + /* Make sure persistent devices do not get stuck in + * xoff state. + */ + if (netif_running(tun->dev)) + netif_tx_wake_all_queues(tun->dev); + + strcpy(ifr->ifr_name, tun->dev->name); + return 0; + +err_detach: + tun_detach_all(dev); +err_free_flow: + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); +err_free_dev: + free_netdev(dev); + return err; +} + +static void tun_get_iff(struct net *net, struct tun_struct *tun, + struct ifreq *ifr) +{ + tun_debug(KERN_INFO, tun, "tun_get_iff\n"); + + strcpy(ifr->ifr_name, tun->dev->name); + + ifr->ifr_flags = tun_flags(tun); + +} + +/* This is like a cut-down ethtool ops, except done via tun fd so no + * privs required. */ +static int set_offload(struct tun_struct *tun, unsigned long arg) +{ + netdev_features_t features = 0; + + if (arg & TUN_F_CSUM) { + features |= NETIF_F_HW_CSUM; + arg &= ~TUN_F_CSUM; + + if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { + if (arg & TUN_F_TSO_ECN) { + features |= NETIF_F_TSO_ECN; + arg &= ~TUN_F_TSO_ECN; + } + if (arg & TUN_F_TSO4) + features |= NETIF_F_TSO; + if (arg & TUN_F_TSO6) + features |= NETIF_F_TSO6; + arg &= ~(TUN_F_TSO4|TUN_F_TSO6); + } + + if (arg & TUN_F_UFO) { + features |= NETIF_F_UFO; + arg &= ~TUN_F_UFO; + } + } + + /* This gives the user a way to test for new features in future by + * trying to set them. */ + if (arg) + return -EINVAL; + + tun->set_features = features; + netdev_update_features(tun->dev); + + return 0; +} + +static void tun_detach_filter(struct tun_struct *tun, int n) +{ + int i; + struct tun_file *tfile; + + for (i = 0; i < n; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + __sk_detach_filter(tfile->socket.sk, lockdep_rtnl_is_held()); + } + + tun->filter_attached = false; +} + +static int tun_attach_filter(struct tun_struct *tun) +{ + int i, ret = 0; + struct tun_file *tfile; + + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + ret = __sk_attach_filter(&tun->fprog, tfile->socket.sk, + lockdep_rtnl_is_held()); + if (ret) { + tun_detach_filter(tun, i); + return ret; + } + } + + tun->filter_attached = true; + return ret; +} + +static void tun_set_sndbuf(struct tun_struct *tun) +{ + struct tun_file *tfile; + int i; + + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + tfile->socket.sk->sk_sndbuf = tun->sndbuf; + } +} + +static int tun_set_queue(struct file *file, struct ifreq *ifr) +{ + struct tun_file *tfile = file->private_data; + struct tun_struct *tun; + int ret = 0; + + rtnl_lock(); + + if (ifr->ifr_flags & IFF_ATTACH_QUEUE) { + tun = tfile->detached; + if (!tun) { + ret = -EINVAL; + goto unlock; + } + ret = security_tun_dev_attach_queue(tun->security); + if (ret < 0) + goto unlock; + ret = tun_attach(tun, file, false); + } else if (ifr->ifr_flags & IFF_DETACH_QUEUE) { + tun = rtnl_dereference(tfile->tun); + if (!tun || !(tun->flags & TUN_TAP_MQ) || tfile->detached) + ret = -EINVAL; + else + __tun_detach(tfile, false); + } else + ret = -EINVAL; + +unlock: + rtnl_unlock(); + return ret; +} + +static long __tun_chr_ioctl(struct file *file, unsigned int cmd, + unsigned long arg, int ifreq_len) +{ + struct tun_file *tfile = file->private_data; + struct tun_struct *tun; + void __user* argp = (void __user*)arg; + struct ifreq ifr; + kuid_t owner; + kgid_t group; + int sndbuf; + int vnet_hdr_sz; + unsigned int ifindex; + int ret; + + if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) { + if (copy_from_user(&ifr, argp, ifreq_len)) + return -EFAULT; + } else { + memset(&ifr, 0, sizeof(ifr)); + } + if (cmd == TUNGETFEATURES) { + /* Currently this just means: "what IFF flags are valid?". + * This is needed because we never checked for invalid flags on + * TUNSETIFF. */ + return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE | + IFF_VNET_HDR | IFF_MULTI_QUEUE, + (unsigned int __user*)argp); + } else if (cmd == TUNSETQUEUE) + return tun_set_queue(file, &ifr); + + ret = 0; + rtnl_lock(); + + tun = __tun_get(tfile); + if (cmd == TUNSETIFF && !tun) { + ifr.ifr_name[IFNAMSIZ-1] = '\0'; + + ret = tun_set_iff(tfile->net, file, &ifr); + + if (ret) + goto unlock; + + if (copy_to_user(argp, &ifr, ifreq_len)) + ret = -EFAULT; + goto unlock; + } + if (cmd == TUNSETIFINDEX) { + ret = -EPERM; + if (tun) + goto unlock; + + ret = -EFAULT; + if (copy_from_user(&ifindex, argp, sizeof(ifindex))) + goto unlock; + + ret = 0; + tfile->ifindex = ifindex; + goto unlock; + } + + ret = -EBADFD; + if (!tun) + goto unlock; + + tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd); + + ret = 0; + switch (cmd) { + case TUNGETIFF: + tun_get_iff(current->nsproxy->net_ns, tun, &ifr); + + if (tfile->detached) + ifr.ifr_flags |= IFF_DETACH_QUEUE; + if (!tfile->socket.sk->sk_filter) + ifr.ifr_flags |= IFF_NOFILTER; + + if (copy_to_user(argp, &ifr, ifreq_len)) + ret = -EFAULT; + break; + + case TUNSETNOCSUM: + /* Disable/Enable checksum */ + + /* [unimplemented] */ + tun_debug(KERN_INFO, tun, "ignored: set checksum %s\n", + arg ? "disabled" : "enabled"); + break; + + case TUNSETPERSIST: + /* Disable/Enable persist mode. Keep an extra reference to the + * module to prevent the module being unprobed. + */ + if (arg && !(tun->flags & TUN_PERSIST)) { + tun->flags |= TUN_PERSIST; + __module_get(THIS_MODULE); + } + if (!arg && (tun->flags & TUN_PERSIST)) { + tun->flags &= ~TUN_PERSIST; + module_put(THIS_MODULE); + } + + tun_debug(KERN_INFO, tun, "persist %s\n", + arg ? "enabled" : "disabled"); + break; + + case TUNSETOWNER: + /* Set owner of the device */ + owner = make_kuid(current_user_ns(), arg); + if (!uid_valid(owner)) { + ret = -EINVAL; + break; + } + tun->owner = owner; + tun_debug(KERN_INFO, tun, "owner set to %u\n", + from_kuid(&init_user_ns, tun->owner)); + break; + + case TUNSETGROUP: + /* Set group of the device */ + group = make_kgid(current_user_ns(), arg); + if (!gid_valid(group)) { + ret = -EINVAL; + break; + } + tun->group = group; + tun_debug(KERN_INFO, tun, "group set to %u\n", + from_kgid(&init_user_ns, tun->group)); + break; + + case TUNSETLINK: + /* Only allow setting the type when the interface is down */ + if (tun->dev->flags & IFF_UP) { + tun_debug(KERN_INFO, tun, + "Linktype set failed because interface is up\n"); + ret = -EBUSY; + } else { + tun->dev->type = (int) arg; + tun_debug(KERN_INFO, tun, "linktype set to %d\n", + tun->dev->type); + ret = 0; + } + break; + +#ifdef TUN_DEBUG + case TUNSETDEBUG: + tun->debug = arg; + break; +#endif + case TUNSETOFFLOAD: + ret = set_offload(tun, arg); + break; + + case TUNSETTXFILTER: + /* Can be set only for TAPs */ + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = update_filter(&tun->txflt, (void __user *)arg); + break; + + case SIOCGIFHWADDR: + /* Get hw address */ + memcpy(ifr.ifr_hwaddr.sa_data, tun->dev->dev_addr, ETH_ALEN); + ifr.ifr_hwaddr.sa_family = tun->dev->type; + if (copy_to_user(argp, &ifr, ifreq_len)) + ret = -EFAULT; + break; + + case SIOCSIFHWADDR: + /* Set hw address */ + tun_debug(KERN_DEBUG, tun, "set hw address: %pM\n", + ifr.ifr_hwaddr.sa_data); + + ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr); + break; + + case TUNGETSNDBUF: + sndbuf = tfile->socket.sk->sk_sndbuf; + if (copy_to_user(argp, &sndbuf, sizeof(sndbuf))) + ret = -EFAULT; + break; + + case TUNSETSNDBUF: + if (copy_from_user(&sndbuf, argp, sizeof(sndbuf))) { + ret = -EFAULT; + break; + } + + tun->sndbuf = sndbuf; + tun_set_sndbuf(tun); + break; + + case TUNGETVNETHDRSZ: + vnet_hdr_sz = tun->vnet_hdr_sz; + if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz))) + ret = -EFAULT; + break; + + case TUNSETVNETHDRSZ: + if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) { + ret = -EFAULT; + break; + } + if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) { + ret = -EINVAL; + break; + } + + tun->vnet_hdr_sz = vnet_hdr_sz; + break; + + case TUNATTACHFILTER: + /* Can be set only for TAPs */ + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = -EFAULT; + if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog))) + break; + + ret = tun_attach_filter(tun); + break; + + case TUNDETACHFILTER: + /* Can be set only for TAPs */ + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = 0; + tun_detach_filter(tun, tun->numqueues); + break; + + case TUNGETFILTER: + ret = -EINVAL; + if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV) + break; + ret = -EFAULT; + if (copy_to_user(argp, &tun->fprog, sizeof(tun->fprog))) + break; + ret = 0; + break; + + default: + ret = -EINVAL; + break; + } + +unlock: + rtnl_unlock(); + if (tun) + tun_put(tun); + return ret; +} + +static long tun_chr_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + return __tun_chr_ioctl(file, cmd, arg, sizeof (struct ifreq)); +} + +#ifdef CONFIG_COMPAT +static long tun_chr_compat_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + case TUNSETIFF: + case TUNGETIFF: + case TUNSETTXFILTER: + case TUNGETSNDBUF: + case TUNSETSNDBUF: + case SIOCGIFHWADDR: + case SIOCSIFHWADDR: + arg = (unsigned long)compat_ptr(arg); + break; + default: + arg = (compat_ulong_t)arg; + break; + } + + /* + * compat_ifreq is shorter than ifreq, so we must not access beyond + * the end of that structure. All fields that are used in this + * driver are compatible though, we don't need to convert the + * contents. + */ + return __tun_chr_ioctl(file, cmd, arg, sizeof(struct compat_ifreq)); +} +#endif /* CONFIG_COMPAT */ + +static int tun_chr_fasync(int fd, struct file *file, int on) +{ + struct tun_file *tfile = file->private_data; + int ret; + + if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0) + goto out; + + if (on) { + ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0); + if (ret) + goto out; + tfile->flags |= TUN_FASYNC; + } else + tfile->flags &= ~TUN_FASYNC; + ret = 0; +out: + return ret; +} + +static int tun_chr_open(struct inode *inode, struct file * file) +{ + struct tun_file *tfile; + + DBG1(KERN_INFO, "tunX: tun_chr_open\n"); + + tfile = (struct tun_file *)sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL, + &tun_proto); + if (!tfile) + return -ENOMEM; + RCU_INIT_POINTER(tfile->tun, NULL); + tfile->net = get_net(current->nsproxy->net_ns); + tfile->flags = 0; + tfile->ifindex = 0; + + init_waitqueue_head(&tfile->wq.wait); + RCU_INIT_POINTER(tfile->socket.wq, &tfile->wq); + + tfile->socket.file = file; + tfile->socket.ops = &tun_socket_ops; + + sock_init_data(&tfile->socket, &tfile->sk); + sk_change_net(&tfile->sk, tfile->net); + + tfile->sk.sk_write_space = tun_sock_write_space; + tfile->sk.sk_sndbuf = INT_MAX; + + file->private_data = tfile; + set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags); + INIT_LIST_HEAD(&tfile->next); + + sock_set_flag(&tfile->sk, SOCK_ZEROCOPY); + + return 0; +} + +static int tun_chr_close(struct inode *inode, struct file *file) +{ + struct tun_file *tfile = file->private_data; + struct net *net = tfile->net; + + tun_detach(tfile, true); + put_net(net); + + return 0; +} + +#ifdef CONFIG_PROC_FS +static int tun_chr_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct tun_struct *tun; + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + rtnl_lock(); + tun = tun_get(f); + if (tun) + tun_get_iff(current->nsproxy->net_ns, tun, &ifr); + rtnl_unlock(); + + if (tun) + tun_put(tun); + + return seq_printf(m, "iff:\t%s\n", ifr.ifr_name); +} +#endif + +static const struct file_operations tun_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = do_sync_read, + .aio_read = tun_chr_aio_read, + .write = do_sync_write, + .aio_write = tun_chr_aio_write, + .poll = tun_chr_poll, + .unlocked_ioctl = tun_chr_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = tun_chr_compat_ioctl, +#endif + .open = tun_chr_open, + .release = tun_chr_close, + .fasync = tun_chr_fasync, +#ifdef CONFIG_PROC_FS + .show_fdinfo = tun_chr_show_fdinfo, +#endif +}; + +static struct miscdevice tun_miscdev = { + .minor = (TUN_MINOR1), + .name = "bf_tun", + .nodename = "net/bf_tun", + .fops = &tun_fops, +}; + +/* ethtool interface */ + +static int tun_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + cmd->supported = 0; + cmd->advertising = 0; + ethtool_cmd_speed_set(cmd, SPEED_10); + cmd->duplex = DUPLEX_FULL; + cmd->port = PORT_TP; + cmd->phy_address = 0; + cmd->transceiver = XCVR_INTERNAL; + cmd->autoneg = AUTONEG_DISABLE; + cmd->maxtxpkt = 0; + cmd->maxrxpkt = 0; + return 0; +} + +static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) +{ + struct tun_struct *tun = netdev_priv(dev); + + strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); + strlcpy(info->version, DRV_VERSION, sizeof(info->version)); + + switch (tun->flags & TUN_TYPE_MASK) { + case TUN_TUN_DEV: + strlcpy(info->bus_info, "bf_tun", sizeof(info->bus_info)); + break; + case TUN_TAP_DEV: + strlcpy(info->bus_info, "tap", sizeof(info->bus_info)); + break; + } +} + +static u32 tun_get_msglevel(struct net_device *dev) +{ +#ifdef TUN_DEBUG + struct tun_struct *tun = netdev_priv(dev); + return tun->debug; +#else + return -EOPNOTSUPP; +#endif +} + +static void tun_set_msglevel(struct net_device *dev, u32 value) +{ +#ifdef TUN_DEBUG + struct tun_struct *tun = netdev_priv(dev); + tun->debug = value; +#endif +} + +static const struct ethtool_ops tun_ethtool_ops = { + .get_settings = tun_get_settings, + .get_drvinfo = tun_get_drvinfo, + .get_msglevel = tun_get_msglevel, + .set_msglevel = tun_set_msglevel, + .get_link = ethtool_op_get_link, + .get_ts_info = ethtool_op_get_ts_info, +}; + + +static int __init tun_init(void) +{ + int ret = 0; + + pr_info("%s, %s\n", DRV_DESCRIPTION, DRV_VERSION); + pr_info("%s\n", DRV_COPYRIGHT); + + ret = rtnl_link_register(&tun_link_ops); + if (ret) { + pr_err("Can't register link_ops\n"); + goto err_linkops; + } + + ret = misc_register(&tun_miscdev); + if (ret) { + pr_err("Can't register misc device %d\n", (TUN_MINOR1)); + goto err_misc; + } + return 0; +err_misc: + rtnl_link_unregister(&tun_link_ops); +err_linkops: + return ret; +} + +static void tun_cleanup(void) +{ + misc_deregister(&tun_miscdev); + rtnl_link_unregister(&tun_link_ops); +} + +/* Get an underlying socket object from tun file. Returns error unless file is + * attached to a device. The returned object works like a packet socket, it + * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for + * holding a reference to the file for as long as the socket is in use. */ +struct socket *bf_tun_get_socket(struct file *file) +{ + struct tun_file *tfile; + if (file->f_op != &tun_fops) + return ERR_PTR(-EINVAL); + tfile = file->private_data; + if (!tfile) + return ERR_PTR(-EBADFD); + return &tfile->socket; +} +EXPORT_SYMBOL_GPL(bf_tun_get_socket); + +module_init(tun_init); +module_exit(tun_cleanup); +MODULE_DESCRIPTION(DRV_DESCRIPTION); +MODULE_AUTHOR(DRV_COPYRIGHT); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_MISCDEV(TUN_MINOR1); +MODULE_ALIAS("devname:net/bf_tun"); diff --git a/platform/barefoot/sonic-platform-modules-bfn/scripts/test b/platform/barefoot/sonic-platform-modules-bfn/scripts/test new file mode 100755 index 0000000000..38327722c9 --- /dev/null +++ b/platform/barefoot/sonic-platform-modules-bfn/scripts/test @@ -0,0 +1 @@ +echo "test" diff --git a/sonic-slave/Dockerfile b/sonic-slave/Dockerfile index f194bf604c..d1a7a8c8e5 100644 --- a/sonic-slave/Dockerfile +++ b/sonic-slave/Dockerfile @@ -114,6 +114,9 @@ RUN apt-get update && apt-get install -y \ # For mellanox sai build libtool-bin \ libxml2-dev \ +# For BFN sdk build + libusb-1.0-0-dev \ + libcurl3-nss-dev \ # For build image cpio \ squashfs-tools \ diff --git a/src/sonic-config-engine/tests/sample_output/interfaces b/src/sonic-config-engine/tests/sample_output/interfaces index 89a23471a7..5fb4738064 100644 --- a/src/sonic-config-engine/tests/sample_output/interfaces +++ b/src/sonic-config-engine/tests/sample_output/interfaces @@ -15,6 +15,11 @@ iface lo inet6 static address fc00:1::32 netmask 128 # +# BMC interface +auto usb0 +iface usb0 inet static + address 192.168.0.2 + netmask 255.255.255.0 # The management network interface auto eth0 iface eth0 inet static diff --git a/src/sonic-sairedis b/src/sonic-sairedis index f5d9c8364f..aa5bf640db 160000 --- a/src/sonic-sairedis +++ b/src/sonic-sairedis @@ -1 +1 @@ -Subproject commit f5d9c8364f5fbcc487a5f1a3e3e6203ab2293a83 +Subproject commit aa5bf640db7b7fca245c1669eeb02198a50cb5c1 diff --git a/src/sonic-swss b/src/sonic-swss index e07d86b100..475e2da081 160000 --- a/src/sonic-swss +++ b/src/sonic-swss @@ -1 +1 @@ -Subproject commit e07d86b100ccefe8b51e2c41b543cc93f33a0f13 +Subproject commit 475e2da081e600fca839a140af620a68c8206096