/* * Copyright (c) 2016 Intel Corporation * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. */ #ifndef __DRM_MODESET_H__ #define __DRM_MODESET_H__ #include struct drm_object_properties; struct drm_property; struct drm_device; /** * struct drm_mode_object - base structure for modeset objects * @id: userspace visible identifier * @type: type of the object, one of DRM_MODE_OBJECT\_\* * @properties: properties attached to this object, including values * @refcount: reference count for objects which with dynamic lifetime * @free_cb: free function callback, only set for objects with dynamic lifetime * * Base structure for modeset objects visible to userspace. Objects can be * looked up using drm_mode_object_find(). Besides basic uapi interface * properties like @id and @type it provides two services: * * - It tracks attached properties and their values. This is used by &drm_crtc, * &drm_plane and &drm_connector. Properties are attached by calling * drm_object_attach_property() before the object is visible to userspace. * * - For objects with dynamic lifetimes (as indicated by a non-NULL @free_cb) it * provides reference counting through drm_mode_object_reference() and * drm_mode_object_unreference(). This is used by &drm_framebuffer, * &drm_connector and &drm_property_blob. These objects provide specialized * reference counting wrappers. */ struct drm_mode_object { uint32_t id; uint32_t type; struct drm_object_properties *properties; struct kref refcount; void (*free_cb)(struct kref *kref); }; #define DRM_OBJECT_MAX_PROPERTY 24 /** * struct drm_object_properties - property tracking for &drm_mode_object */ struct drm_object_properties { /** * @count: number of valid properties, must be less than or equal to * DRM_OBJECT_MAX_PROPERTY. */ int count; /** * @properties: Array of pointers to &drm_property. * * NOTE: if we ever start dynamically destroying properties (ie. * not at drm_mode_config_cleanup() time), then we'd have to do * a better job of detaching property from mode objects to avoid * dangling property pointers: */ struct drm_property *properties[DRM_OBJECT_MAX_PROPERTY]; /** * @values: Array to store the property values, matching @properties. Do * not read/write values directly, but use * drm_object_property_get_value() and drm_object_property_set_value(). * * Note that atomic drivers do not store mutable properties in this * array, but only the decoded values in the corresponding state * structure. The decoding is done using the ->atomic_get_property and * ->atomic_set_property hooks of the corresponding object. Hence atomic * drivers should not use drm_object_property_set_value() and * drm_object_property_get_value() on mutable objects, i.e. those * without the DRM_MODE_PROP_IMMUTABLE flag set. */ uint64_t values[DRM_OBJECT_MAX_PROPERTY]; }; /* Avoid boilerplate. I'm tired of typing. */ #define DRM_ENUM_NAME_FN(fnname, list) \ const char *fnname(int val) \ { \ int i; \ for (i = 0; i < ARRAY_SIZE(list); i++) { \ if (list[i].type == val) \ return list[i].name; \ } \ return "(unknown)"; \ } struct drm_mode_object *drm_mode_object_find(struct drm_device *dev, uint32_t id, uint32_t type); void drm_mode_object_reference(struct drm_mode_object *obj); void drm_mode_object_unreference(struct drm_mode_object *obj); int drm_object_property_set_value(struct drm_mode_object *obj, struct drm_property *property, uint64_t val); int drm_object_property_get_value(struct drm_mode_object *obj, struct drm_property *property, uint64_t *value); void drm_object_attach_property(struct drm_mode_object *obj, struct drm_property *property, uint64_t init_val); #endif today solves the per-vni netdev scalability problem in l3 networks. It expects all forwarding information to be present in dst_metadata. This patch series enhances collect metadata mode to include the case where only vni is present in dst_metadata, and the vxlan driver can then use the rest of the forwarding information datbase to make forwarding decisions. There is no change to default COLLECT_METADATA behaviour. These changes only apply to COLLECT_METADATA when used with the bridging use-case with a special dst_metadata tunnel info flag (eg: where vxlan device is part of a bridge). For all this to work, the vxlan driver will need to now support a single fdb table hashed by mac + vni. This series essentially makes this happen. use-case and workflow: vxlan collect metadata device participates in bridging vlan to vn-segments. Bridge driver above the vxlan device, sends the vni corresponding to the vlan in the dst_metadata. vxlan driver will lookup forwarding database with (mac + vni) for the required remote destination information to forward the packet. Changes introduced by this patch: - allow learning and forwarding database state in vxlan netdev in COLLECT_METADATA mode. Current behaviour is not changed by default. tunnel info flag IP_TUNNEL_INFO_BRIDGE is used to support the new bridge friendly mode. - A single fdb table hashed by (mac, vni) to allow fdb entries with multiple vnis in the same fdb table - rx path already has the vni - tx path expects a vni in the packet with dst_metadata - prior to this series, fdb remote_dsts carried remote vni and the vxlan device carrying the fdb table represented the source vni. With the vxlan device now representing multiple vnis, this patch adds a src vni attribute to the fdb entry. The remote vni already uses NDA_VNI attribute. This patch introduces NDA_SRC_VNI netlink attribute to represent the src vni in a multi vni fdb table. iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's. before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metadata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Change to use ife moduleYotam Gigi1-9/+1 Use the encode/decode functionality from the ife module instead of using implementation inside the act_ife. Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net: Introduce ife encapsulation moduleYotam Gigi2-0/+19 This module is responsible for the ife encapsulation protocol encode/decode logics. That module can: - ife_encode: encode skb and reserve space for the ife meta header - ife_decode: decode skb and extract the meta header size - ife_tlv_meta_encode - encodes one tlv entry into the reserved ife header space. - ife_tlv_meta_decode - decodes one tlv entry from the packet - ife_tlv_meta_next - advance to the next tlv Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02net: add LINUX_MIB_PFMEMALLOCDROP counterEric Dumazet1-0/+1 Debugging issues caused by pfmemalloc is often tedious. Add a new SNMP counter to more easily diagnose these problems. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Josef Bacik <jbacik@fb.com> Acked-by: Josef Bacik <jbacik@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02unix: add ioctl to open a unix socket file with O_PATHAndrey Vagin1-0/+2 This ioctl opens a file to which a socket is bound and returns a file descriptor. The caller has to have CAP_NET_ADMIN in the socket network namespace. Currently it is impossible to get a path and a mount point for a socket file. socket_diag reports address, device ID and inode number for unix sockets. An address can contain a relative path or a file may be moved somewhere. And these properties say nothing about a mount namespace and a mount point of a socket file. With the introduced ioctl, we can get a path by reading /proc/self/fd/X and get mnt_id from /proc/self/fdinfo/X. In CRIU we are going to use this ioctl to dump and restore unix socket. Here is an example how it can be used: $ strace -e socket,bind,ioctl ./test /tmp/test_sock socket(AF_UNIX, SOCK_STREAM, 0) = 3 bind(3, {sa_family=AF_UNIX, sun_path="test_sock"}, 11) = 0 ioctl(3, SIOCUNIXFILE, 0) = 4 ^Z $ ss -a | grep test_sock u_str LISTEN 0 1 test_sock 17798 * 0 $ ls -l /proc/760/fd/{3,4} lrwx------ 1 root root 64 Feb 1 09:41 3 -> 'socket:[17798]' l--------- 1 root root 64 Feb 1 09:41 4 -> /tmp/test_sock $ cat /proc/760/fdinfo/4 pos: 0 flags: 012000000 mnt_id: 40 $ cat /proc/self/mountinfo | grep "^40\s" 40 19 0:37 / /tmp rw shared:23 - tmpfs tmpfs rw Signed-off-by: Andrei Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller1-1/+3 All merge conflicts were simple overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>