* [PATCH bpf-next 2/4] bpf: Sync bpf.h to tools/
From: Andrey Ignatov @ 2018-08-11 5:35 UTC (permalink / raw)
To: netdev; +Cc: Andrey Ignatov, ast, daniel, tj, guro, kernel-team
In-Reply-To: <cover.1533965421.git.rdna@fb.com>
Sync skb_ancestor_cgroup_id() related bpf UAPI changes to tools/.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
---
tools/include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3102a2a23c31..66917a4eba27 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2093,6 +2093,24 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
@@ -2207,7 +2225,8 @@ union bpf_attr {
FN(skb_cgroup_id), \
FN(get_current_cgroup_id), \
FN(get_local_storage), \
- FN(sk_select_reuseport),
+ FN(sk_select_reuseport), \
+ FN(skb_ancestor_cgroup_id),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next 3/4] selftests/bpf: Add cgroup id helpers to bpf_helpers.h
From: Andrey Ignatov @ 2018-08-11 5:35 UTC (permalink / raw)
To: netdev; +Cc: Andrey Ignatov, ast, daniel, tj, guro, kernel-team
In-Reply-To: <cover.1533965421.git.rdna@fb.com>
Add bpf_skb_cgroup_id and bpf_skb_ancestor_cgroup_id helpers to
bpf_helpers.h to use them in tests and samples.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
---
tools/testing/selftests/bpf/bpf_helpers.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5c32266c2c38..e4be7730222d 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -139,6 +139,10 @@ static unsigned long long (*bpf_get_current_cgroup_id)(void) =
(void *) BPF_FUNC_get_current_cgroup_id;
static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
(void *) BPF_FUNC_get_local_storage;
+static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
+ (void *) BPF_FUNC_skb_cgroup_id;
+static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
+ (void *) BPF_FUNC_skb_ancestor_cgroup_id;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next 1/4] bpf: Introduce bpf_skb_ancestor_cgroup_id helper
From: Andrey Ignatov @ 2018-08-11 5:35 UTC (permalink / raw)
To: netdev; +Cc: Andrey Ignatov, ast, daniel, tj, guro, kernel-team
In-Reply-To: <cover.1533965421.git.rdna@fb.com>
== Problem description ==
It's useful to be able to identify cgroup associated with skb in TC so
that a policy can be applied to this skb, and existing bpf_skb_cgroup_id
helper can help with this.
Though in real life cgroup hierarchy and hierarchy to apply a policy to
don't map 1:1.
It's often the case that there is a container and corresponding cgroup,
but there are many more sub-cgroups inside container, e.g. because it's
delegated to containerized application to control resources for its
subsystems, or to separate application inside container from infra that
belongs to containerization system (e.g. sshd).
At the same time it may be useful to apply a policy to container as a
whole.
If multiple containers like this are run on a host (what is often the
case) and many of them have sub-cgroups, it may not be possible to apply
per-container policy in TC with existing helpers such as
bpf_skb_under_cgroup or bpf_skb_cgroup_id:
* bpf_skb_cgroup_id will return id of immediate cgroup associated with
skb, i.e. if it's a sub-cgroup inside container, it can't be used to
identify container's cgroup;
* bpf_skb_under_cgroup can work only with one cgroup and doesn't scale,
i.e. if there are N containers on a host and a policy has to be
applied to M of them (0 <= M <= N), it'd require M calls to
bpf_skb_under_cgroup, and, if M changes, it'd require to rebuild &
load new BPF program.
== Solution ==
The patch introduces new helper bpf_skb_ancestor_cgroup_id that can be
used to get id of cgroup v2 that is an ancestor of cgroup associated
with skb at specified level of cgroup hierarchy.
That way admin can place all containers on one level of cgroup hierarchy
(what is a good practice in general and already used in many
configurations) and identify specific cgroup on this level no matter
what sub-cgroup skb is associated with.
E.g. if there is a cgroup hierarchy:
root/
root/container1/
root/container1/app11/
root/container1/app11/sub-app-a/
root/container1/app12/
root/container2/
root/container2/app21/
root/container2/app22/
root/container2/app22/sub-app-b/
, then having skb associated with root/container1/app11/sub-app-a/ it's
possible to get ancestor at level 1, what is container1 and apply policy
for this container, or apply another policy if it's container2.
Policies can be kept e.g. in a hash map where key is a container cgroup
id and value is an action.
Levels where container cgroups are created are usually known in advance
whether cgroup hierarchy inside container may be hard to predict
especially in case when its creation is delegated to containerized
application.
== Implementation details ==
The helper gets ancestor by walking parents up to specified level.
Another option would be to get different kind of "id" from
cgroup->ancestor_ids[level] and use it with idr_find() to get struct
cgroup for ancestor. But that would require radix lookup what doesn't
seem to be better (at least it's not obviously better).
Format of return value of the new helper is same as that of
bpf_skb_cgroup_id.
Signed-off-by: Andrey Ignatov <rdna@fb.com>
---
include/linux/cgroup.h | 30 ++++++++++++++++++++++++++++++
include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
net/core/filter.c | 28 ++++++++++++++++++++++++++++
3 files changed, 78 insertions(+), 1 deletion(-)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c9fdf6f57913..32c553556bbd 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -553,6 +553,36 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
}
+/**
+ * cgroup_ancestor - find ancestor of cgroup
+ * @cgrp: cgroup to find ancestor of
+ * @ancestor_level: level of ancestor to find starting from root
+ *
+ * Find ancestor of cgroup at specified level starting from root if it exists
+ * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
+ * @ancestor_level.
+ *
+ * This function is safe to call as long as @cgrp is accessible.
+ */
+static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
+ int ancestor_level)
+{
+ struct cgroup *ptr;
+
+ if (cgrp->level < ancestor_level)
+ return NULL;
+
+ for (ptr = cgrp;
+ ptr && ptr->level > ancestor_level;
+ ptr = cgroup_parent(ptr))
+ ;
+
+ if (ptr && ptr->level == ancestor_level)
+ return ptr;
+
+ return NULL;
+}
+
/**
* task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
* @task: the task to be tested
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3102a2a23c31..66917a4eba27 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2093,6 +2093,24 @@ union bpf_attr {
* Return
* The id is returned or 0 in case the id could not be retrieved.
*
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ * Description
+ * Return id of cgroup v2 that is ancestor of cgroup associated
+ * with the *skb* at the *ancestor_level*. The root cgroup is at
+ * *ancestor_level* zero and each step down the hierarchy
+ * increments the level. If *ancestor_level* == level of cgroup
+ * associated with *skb*, then return value will be same as that
+ * of **bpf_skb_cgroup_id**\ ().
+ *
+ * The helper is useful to implement policies based on cgroups
+ * that are upper in hierarchy than immediate cgroup associated
+ * with *skb*.
+ *
+ * The format of returned id and helper limitations are same as in
+ * **bpf_skb_cgroup_id**\ ().
+ * Return
+ * The id is returned or 0 in case the id could not be retrieved.
+ *
* u64 bpf_get_current_cgroup_id(void)
* Return
* A 64-bit integer containing the current cgroup id based
@@ -2207,7 +2225,8 @@ union bpf_attr {
FN(skb_cgroup_id), \
FN(get_current_cgroup_id), \
FN(get_local_storage), \
- FN(sk_select_reuseport),
+ FN(sk_select_reuseport), \
+ FN(skb_ancestor_cgroup_id),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index 22906b31d43f..15b9d2df92ca 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3778,6 +3778,32 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
};
+
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+ ancestor_level)
+{
+ struct sock *sk = skb_to_full_sk(skb);
+ struct cgroup *ancestor;
+ struct cgroup *cgrp;
+
+ if (!sk || !sk_fullsock(sk))
+ return 0;
+
+ cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+ ancestor = cgroup_ancestor(cgrp, ancestor_level);
+ if (!ancestor)
+ return 0;
+
+ return ancestor->kn->id.id;
+}
+
+static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
+ .func = bpf_skb_ancestor_cgroup_id,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+};
#endif
static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -4966,6 +4992,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
#ifdef CONFIG_SOCK_CGROUP_DATA
case BPF_FUNC_skb_cgroup_id:
return &bpf_skb_cgroup_id_proto;
+ case BPF_FUNC_skb_ancestor_cgroup_id:
+ return &bpf_skb_ancestor_cgroup_id_proto;
#endif
default:
return bpf_base_func_proto(func_id);
--
2.17.1
^ permalink raw reply related
* [PATCH bpf-next 0/4] bpf_skb_ancestor_cgroup_id helper
From: Andrey Ignatov @ 2018-08-11 5:35 UTC (permalink / raw)
To: netdev; +Cc: Andrey Ignatov, ast, daniel, tj, guro, kernel-team
This patch set adds new BPF helper bpf_skb_ancestor_cgroup_id that returns
id of cgroup v2 that is ancestor of cgroup associated with the skb at the
ancestor_level.
The helper is useful to implement policies in TC based on cgroups that are
upper in hierarchy than immediate cgroup associated with skb.
Patch 0001 provides more details and describes use-cases.
Patch 0002 syncs UAPI changes to tools/.
Patch 0003 adds skb*cgroup_id helpers to bpf_helper.h header.
Patch 0004 adds selftest for the new helper and is an example of usage.
Andrey Ignatov (4):
bpf: Introduce bpf_skb_ancestor_cgroup_id helper
bpf: Sync bpf.h to tools/
selftests/bpf: Add cgroup id helpers to bpf_helpers.h
selftests/bpf: Selftest for bpf_skb_ancestor_cgroup_id
include/linux/cgroup.h | 30 +++
include/uapi/linux/bpf.h | 21 +-
net/core/filter.c | 28 +++
tools/include/uapi/linux/bpf.h | 21 +-
tools/testing/selftests/bpf/Makefile | 9 +-
tools/testing/selftests/bpf/bpf_helpers.h | 4 +
.../selftests/bpf/test_skb_cgroup_id.sh | 61 ++++++
.../selftests/bpf/test_skb_cgroup_id_kern.c | 47 +++++
.../selftests/bpf/test_skb_cgroup_id_user.c | 187 ++++++++++++++++++
9 files changed, 403 insertions(+), 5 deletions(-)
create mode 100755 tools/testing/selftests/bpf/test_skb_cgroup_id.sh
create mode 100644 tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
create mode 100644 tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
--
2.17.1
^ permalink raw reply
* Re: [BUG] bpf: syscall: a possible sleep-in-atomic-context bug in map_update_elem()
From: Y Song @ 2018-08-11 5:01 UTC (permalink / raw)
To: Jia-Ju Bai
Cc: Daniel Borkmann, Alexei Starovoitov, netdev,
Linux Kernel Mailing List, Jesper Dangaard Brouer
In-Reply-To: <4f9a083d-1498-8cfb-b54c-614abccb193e@gmail.com>
On Fri, Aug 10, 2018 at 6:57 PM, Jia-Ju Bai <baijiaju1990@gmail.com> wrote:
>
>
> On 2018/8/10 22:22, Daniel Borkmann wrote:
>>
>> On 08/10/2018 04:07 PM, Jia-Ju Bai wrote:
>>>
>>> The kernel may sleep with holding a rcu read lock.
>>>
>>> The function call paths (from bottom to top) in Linux-4.16 are:
>>>
>>> [FUNC] kmalloc(GFP_KERNEL)
>>> kernel/kthread.c, 283: kmalloc in __kthread_create_on_node
>>> kernel/kthread.c, 365: __kthread_create_on_node in kthread_create_on_node
>>> kernel/bpf/cpumap.c, 368: kthread_create_on_node in __cpu_map_entry_alloc
>>> kernel/bpf/cpumap.c, 490: __cpu_map_entry_alloc in cpu_map_update_elem
>>> kernel/bpf/syscall.c, 724: [FUNC_PTR]cpu_map_update_elem in
>>> map_update_elem
>>> kernel/bpf/syscall.c, 723: rcu_read_lock in map_update_elem
>>>
>>> Note that [FUNC_PTR] means a function pointer call is used.
>>>
>>> I do not find a good way to fix it, so I only report.
>>> This is found by my static analysis tool (DSAC).
Maybe your static analysis tool have false positives in this case?
>>
>> Thanks for the report Jia-Ju! In the map_update_elem() from syscall
>> path there's a check map->map_type == BPF_MAP_TYPE_CPUMAP, where we
>> call the cpumap's map->ops->map_update_elem() while /not/ being under
>> rcu_read_lock() as in other cases, so looks okay to me. Could you point
>> out the case for being under rcu_read_lock() more specifically which
>> the tool found?
>
>
> Thanks for your reply :)
> My tool cannot accurately track the case of map->map_type at present...
>
> According to my code review, there is a indeed check on line 697 in
> Linux-4.16:
> else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
> err = map->ops->map_update_elem(map, key, value, attr->flags);
> goto out;
> }
> But there is a call to map->ops->map_update_elem() that is under
> rcu_read_lock on line 724:
> rcu_read_lock();
> err = map->ops->map_update_elem(map, key, value, attr->flags);
> rcu_read_unlock();
>
> So I think if map->map_type is not equal to BPF_MAP_TYPE_CPUMAP,
> map->ops->map_update_elem() can still be called under rcu_read_lock, is it
> right?
map->ops->map_update_elem() can be called under rcu_read_lock(), but
since it is not type cpumap, the function should not be cpu_map_update_elem().
Could you double check your static analysis tool?
>
>
> Best wishes,
> Jia-Ju Bai
^ permalink raw reply
* Re: [net-next 03/12] net/mlx5e: Ethtool steering, ip6 support
From: David Miller @ 2018-08-11 2:25 UTC (permalink / raw)
To: saeedm; +Cc: netdev
In-Reply-To: <20180810222630.11688-4-saeedm@mellanox.com>
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 10 Aug 2018 15:26:21 -0700
> +static bool is_zero_ip6(__be32 ip6[4])
> +{
> + int i;
> +
> + for (i = 0; i < 4; i++)
> + if (ip6[i] != 0)
> + return false;
> + return true;
> +}
This is ipv6_addr_any().
^ permalink raw reply
* Re: [net-next 01/12] net/mlx5e: Ethtool steering flow validation refactoring
From: David Miller @ 2018-08-11 2:22 UTC (permalink / raw)
To: saeedm; +Cc: netdev
In-Reply-To: <20180810222630.11688-2-saeedm@mellanox.com>
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 10 Aug 2018 15:26:19 -0700
> +static int validate_tcpudp4(struct ethtool_rx_flow_spec *fs)
> +{
> + struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
> + int ntuples = 0;
> +
> + if (fs->m_u.tcp_ip4_spec.tos)
^^^^^^^^^^^^^^^^^^^^^^^^
Since you've gone to the trouble of loading this object into
l4_mask before this statement, please use "if (l4_mask->tos)"
I know you're just moving existing code into a function, but it
looks silly now.
^ permalink raw reply
* Re: [PATCH net-next v2] bnxt_en: Fix strcpy() warnings in bnxt_ethtool.c
From: David Miller @ 2018-08-11 2:13 UTC (permalink / raw)
To: michael.chan; +Cc: netdev, dan.carpenter, vasundhara-v.volam
In-Reply-To: <1533939883-23768-1-git-send-email-michael.chan@broadcom.com>
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 10 Aug 2018 18:24:43 -0400
> From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
>
> This patch fixes following smatch warnings:
>
> drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2826 bnxt_fill_coredump_seg_hdr() error: strcpy() '"sEgM"' too large for 'seg_hdr->signature' (5 vs 4)
> drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2858 bnxt_fill_coredump_record() error: strcpy() '"cOrE"' too large for 'record->signature' (5 vs 4)
> drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2879 bnxt_fill_coredump_record() error: strcpy() 'utsname()->sysname' too large for 'record->os_name' (65 vs 32)
>
> Fixes: 6c5657d085ae ("bnxt_en: Add support for ethtool get dump.")
> Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
> Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
> Signed-off-by: Michael Chan <michael.chan@broadcom.com>
That seems to make them all go away, applied, thanks!
^ permalink raw reply
* [PATCH 2/2] net: nixge: Don't store skb in app4 field of descriptor
From: Moritz Fischer @ 2018-08-11 1:19 UTC (permalink / raw)
To: davem; +Cc: keescook, netdev, linux-kernel, alex.williams, Moritz Fischer
In-Reply-To: <20180811011941.6187-1-mdf@kernel.org>
Don't store skb in app4 field of descriptor since it is
not being used anywhere (including hardware).
Signed-off-by: Moritz Fischer <mdf@kernel.org>
---
drivers/net/ethernet/ni/nixge.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index ac31b0d30415..76efed058f33 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -503,7 +503,6 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
tx_skb->skb = skb;
cur_p->cntrl |= XAXIDMA_BD_CTRL_TXEOF_MASK;
- cur_p->app4 = (unsigned long)skb;
tail_p = priv->tx_bd_p + sizeof(*priv->tx_bd_v) * priv->tx_bd_tail;
/* Start the transfer */
--
2.18.0
^ permalink raw reply related
* Re: [PATCH bpf-next 0/9] Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY and BPF_PROG_TYPE_SK_REUSEPORT
From: Daniel Borkmann @ 2018-08-11 0:32 UTC (permalink / raw)
To: Martin KaFai Lau, netdev; +Cc: Alexei Starovoitov, kernel-team
In-Reply-To: <20180808075917.3009181-1-kafai@fb.com>
On 08/08/2018 09:59 AM, Martin KaFai Lau wrote:
> This series introduces a new map type "BPF_MAP_TYPE_REUSEPORT_SOCKARRAY"
> and a new prog type BPF_PROG_TYPE_SK_REUSEPORT.
>
> Here is a snippet from a commit message:
>
> "To unleash the full potential of a bpf prog, it is essential for the
> userspace to be capable of directly setting up a bpf map which can then
> be consumed by the bpf prog to make decision. In this case, decide which
> SO_REUSEPORT sk to serve the incoming request.
>
> By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control
> and visibility on where a SO_REUSEPORT sk should be located in a bpf map.
> The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that
> the bpf prog can directly select a sk from the bpf map. That will
> raise the programmability of the bpf prog attached to a reuseport
> group (a group of sk serving the same IP:PORT).
>
> For example, in UDP, the bpf prog can peek into the payload (e.g.
> through the "data" pointer introduced in the later patch) to learn
> the application level's connection information and then decide which sk
> to pick from a bpf map. The userspace can tightly couple the sk's location
> in a bpf map with the application logic in generating the UDP payload's
> connection information. This connection info contact/API stays within the
> userspace.
>
> Also, when used with map-in-map, the userspace can switch the
> old-server-process's inner map to a new-server-process's inner map
> in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)".
> The bpf prog will then direct incoming requests to the new process instead
> of the old process. The old process can finish draining the pending
> requests (e.g. by "accept()") before closing the old-fds. [Note that
> deleting a fd from a bpf map does not necessary mean the fd is closed]"
>
> Please see individual patch for details
>
> Martin KaFai Lau (9):
> tcp: Avoid TCP syncookie rejected by SO_REUSEPORT socket
> net: Add ID (if needed) to sock_reuseport and expose reuseport_lock
> bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY
> bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT
> bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport selection
> bpf: Refactor ARRAY_SIZE macro to bpf_util.h
> bpf: Sync bpf.h uapi to tools/
> bpf: test BPF_MAP_TYPE_REUSEPORT_SOCKARRAY
> bpf: Test BPF_PROG_TYPE_SK_REUSEPORT
Applied to bpf-next, thanks Martin!
^ permalink raw reply
* Re: [PATCH net-next] net: mvneta: fix mvneta_config_rss on armada 3700
From: David Miller @ 2018-08-11 2:11 UTC (permalink / raw)
To: andrew
Cc: Jisheng.Zhang, thomas.petazzoni, linux-arm-kernel, netdev,
linux-kernel
In-Reply-To: <20180810222335.GD11955@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Sat, 11 Aug 2018 00:23:35 +0200
> On Fri, Aug 10, 2018 at 02:40:31PM -0700, David Miller wrote:
>> From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
>> Date: Fri, 10 Aug 2018 11:36:27 +0800
>>
>> > The mvneta Ethernet driver is used on a few different Marvell SoCs.
>> > Some SoCs have per cpu interrupts for Ethernet events, the driver uses
>> > a per CPU napi structure for this case. Some SoCs such as armada 3700
>> > have a single interrupt for Ethernet events, the driver uses a global
>> > napi structure for this case.
>> >
>> > Current mvneta_config_rss() always operates the per cpu napi structure.
>> > Fix it by operating a global napi for "single interrupt" case, and per
>> > cpu napi structure for remaining cases.
>> >
>> > Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
>> > Fixes: 2636ac3cc2b4 ("net: mvneta: Add network support for Armada 3700 SoC")
>>
>> Applied, thanks.
>
> Hi David
>
> Please can you queue up:
>
> Fixes: 7a86f05faf11 ("net: ethernet: mvneta: Fix napi structure mixup on armada 3700")
>
> and this patch for stable.
If you want things to go to -stable, don't mark them for net-next as this
patch was.
If it isn't appropriate for 'net' it isn't appropriate for -stable either.
^ permalink raw reply
* Re: [PATCH bpf-next 0/3] bpf: add bpffs pretty print for hash/lru_hash maps
From: Daniel Borkmann @ 2018-08-10 23:32 UTC (permalink / raw)
To: Yonghong Song, ast, netdev; +Cc: kernel-team
In-Reply-To: <20180809155521.1544888-1-yhs@fb.com>
On 08/09/2018 05:55 PM, Yonghong Song wrote:
> Commit a26ca7c982cb ("bpf: btf: Add pretty print support to
> the basic arraymap") added pretty print support to array map.
> This patch adds pretty print for hash and lru_hash maps.
>
> The following example shows the pretty-print result of a pinned hashmap.
> Without this patch set, user will get an error instead.
>
> struct map_value {
> int count_a;
> int count_b;
> };
>
> cat /sys/fs/bpf/pinned_hash_map:
>
> 87907: {87907,87908}
> 57354: {37354,57355}
> 76625: {76625,76626}
> ...
>
> Patch #1 fixed a bug in bpffs map_seq_next() function so that
> all elements in the hash table will be traversed.
> Patch #2 implemented map_seq_show_elem() and map_check_btf()
> callback functions for hash and lru hash maps.
> Patch #3 enhanced tools/testing/selftests/bpf/test_btf.c to
> test bpffs hash and lru hash map pretty print.
>
> Yonghong Song (3):
> bpf: fix bpffs non-array map seq_show issue
> bpf: btf: add pretty print for hash/lru_hash maps
> tools/bpf: add bpffs pretty print btf test for hash/lru_hash maps
>
> kernel/bpf/hashtab.c | 44 +++++++++++++++++
> kernel/bpf/inode.c | 8 ++--
> tools/testing/selftests/bpf/test_btf.c | 87 ++++++++++++++++++++++++++++------
> 3 files changed, 121 insertions(+), 18 deletions(-)
Applied to bpf-next, thanks Yonghong!
^ permalink raw reply
* Re: [BUG] bpf: syscall: a possible sleep-in-atomic-context bug in map_update_elem()
From: Jia-Ju Bai @ 2018-08-11 1:57 UTC (permalink / raw)
To: Daniel Borkmann, ast; +Cc: netdev, Linux Kernel Mailing List, brouer
In-Reply-To: <97aa2e6b-1863-f123-af2c-24a2e6333ba5@iogearbox.net>
On 2018/8/10 22:22, Daniel Borkmann wrote:
> On 08/10/2018 04:07 PM, Jia-Ju Bai wrote:
>> The kernel may sleep with holding a rcu read lock.
>>
>> The function call paths (from bottom to top) in Linux-4.16 are:
>>
>> [FUNC] kmalloc(GFP_KERNEL)
>> kernel/kthread.c, 283: kmalloc in __kthread_create_on_node
>> kernel/kthread.c, 365: __kthread_create_on_node in kthread_create_on_node
>> kernel/bpf/cpumap.c, 368: kthread_create_on_node in __cpu_map_entry_alloc
>> kernel/bpf/cpumap.c, 490: __cpu_map_entry_alloc in cpu_map_update_elem
>> kernel/bpf/syscall.c, 724: [FUNC_PTR]cpu_map_update_elem in map_update_elem
>> kernel/bpf/syscall.c, 723: rcu_read_lock in map_update_elem
>>
>> Note that [FUNC_PTR] means a function pointer call is used.
>>
>> I do not find a good way to fix it, so I only report.
>> This is found by my static analysis tool (DSAC).
> Thanks for the report Jia-Ju! In the map_update_elem() from syscall
> path there's a check map->map_type == BPF_MAP_TYPE_CPUMAP, where we
> call the cpumap's map->ops->map_update_elem() while /not/ being under
> rcu_read_lock() as in other cases, so looks okay to me. Could you point
> out the case for being under rcu_read_lock() more specifically which
> the tool found?
Thanks for your reply :)
My tool cannot accurately track the case of map->map_type at present...
According to my code review, there is a indeed check on line 697 in
Linux-4.16:
else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
But there is a call to map->ops->map_update_elem() that is under
rcu_read_lock on line 724:
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
rcu_read_unlock();
So I think if map->map_type is not equal to BPF_MAP_TYPE_CPUMAP,
map->ops->map_update_elem() can still be called under rcu_read_lock, is
it right?
Best wishes,
Jia-Ju Bai
^ permalink raw reply
* Re: [PATCH v2 bpf-next] BPF: helpers: New helper to obtain namespace data from current task
From: Alexei Starovoitov @ 2018-08-10 23:07 UTC (permalink / raw)
To: Carlos Neira; +Cc: netdev, ebiederm, quentin.monnet, ys114321, brouer
In-Reply-To: <20180810124104.1207-1-cneirabustos@gmail.com>
On Fri, Aug 10, 2018 at 08:41:04AM -0400, Carlos Neira wrote:
> This helper obtains the active namespace from current and returns pid, tgid,
> device and namespace id as seen from that namespace, allowing to instrument
> a process inside a container.
> Device is read from /proc/self/ns/pid, as in the future it's possible that
> different pid_ns files may belong to different devices, according
> to the discussion between Eric Biederman and Yonghong in 2017 linux plumbers
> conference.
>
> Currently bpf_get_current_pid_tgid(), is used to do pid filtering in bcc's
> scripts but this helper returns the pid as seen by the root namespace which is
> fine when a bcc script is not executed inside a container.
> When the process of interest is inside a container, pid filtering will not work
> if bpf_get_current_pid_tgid() is used. This helper addresses this limitation
> returning the pid as it's seen by the current namespace where the script is
> executing.
>
> This helper has the same use cases as bpf_get_current_pid_tgid() as it can be
> used to do pid filtering even inside a container.
>
> For example a bcc script using bpf_get_current_pid_tgid() (tools/funccount.py):
>
> u32 pid = bpf_get_current_pid_tgid() >> 32;
> if (pid != <pid_arg_passed_in>)
> return 0;
>
> Could be modified to use bpf_get_current_pidns_info() as follows:
>
> struct bpf_pidns pidns;
> bpf_get_current_pidns_info(&pidns, sizeof(struct bpf_pidns));
> u32 pid = pidns.tgid;
> u32 nsid = pidns.nsid;
> if ((pid != <pid_arg_passed_in>) && (nsid != <nsid_arg_passed_in>))
> return 0;
>
> To find out the name PID namespace id of a process, you could use this command:
>
> $ ps -h -o pidns -p <pid_of_interest>
>
> Or this other command:
>
> $ ls -Li /proc/<pid_of_interest>/ns/pid
>
> Signed-off-by: Carlos Antonio Neira Bustos <cneirabustos@gmail.com>
> ---
> include/linux/bpf.h | 1 +
> include/uapi/linux/bpf.h | 24 +++++++++++-
> kernel/bpf/core.c | 1 +
> kernel/bpf/helpers.c | 64 +++++++++++++++++++++++++++++++
> kernel/trace/bpf_trace.c | 2 +
> samples/bpf/Makefile | 3 ++
> samples/bpf/trace_ns_info_user.c | 35 +++++++++++++++++
> samples/bpf/trace_ns_info_user_kern.c | 45 ++++++++++++++++++++++
> tools/include/uapi/linux/bpf.h | 24 +++++++++++-
> tools/testing/selftests/bpf/bpf_helpers.h | 3 ++
> 10 files changed, 200 insertions(+), 2 deletions(-)
> create mode 100644 samples/bpf/trace_ns_info_user.c
> create mode 100644 samples/bpf/trace_ns_info_user_kern.c
>
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index cd8790d2c6ed..3f4b999f7c99 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -787,6 +787,7 @@ extern const struct bpf_func_proto bpf_get_stack_proto;
> extern const struct bpf_func_proto bpf_sock_map_update_proto;
> extern const struct bpf_func_proto bpf_sock_hash_update_proto;
> extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
> +extern const struct bpf_func_proto bpf_get_current_pidns_info_proto;
>
> extern const struct bpf_func_proto bpf_get_local_storage_proto;
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index dd5758dc35d3..8462f9881465 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2113,6 +2113,18 @@ union bpf_attr {
> * the shared data.
> * Return
> * Pointer to the local storage area.
> + *
> + * int bpf_get_current_pidns_info(struct bpf_pidns_info *pidns, u32 size_of_pidns)
> + * Description
> + * Copies into *pidns* pid, namespace id and tgid as seen by the
> + * current namespace and also device from /proc/self/ns/pid.
> + * *size_of_pidns* must be the size of *pidns*
> + *
> + * This helper is used when pid filtering is needed inside a
> + * container as bpf_get_current_tgid() helper returns always the
> + * pid id as seen by the root namespace.
> + * Return
> + * 0 on success -EINVAL on error.
> */
> #define __BPF_FUNC_MAPPER(FN) \
> FN(unspec), \
> @@ -2196,7 +2208,8 @@ union bpf_attr {
> FN(rc_keydown), \
> FN(skb_cgroup_id), \
> FN(get_current_cgroup_id), \
> - FN(get_local_storage),
> + FN(get_local_storage), \
> + FN(get_current_pidns_info),
>
> /* integer value in 'imm' field of BPF_CALL instruction selects which helper
> * function eBPF program intends to call
> @@ -2724,4 +2737,13 @@ enum bpf_task_fd_type {
> BPF_FD_TYPE_URETPROBE, /* filename + offset */
> };
>
> +/* helper bpf_get_current_pidns_info will store the following
> + * data, dev will contain major/minor from /proc/self/ns/pid.
> + */
> +struct bpf_pidns_info {
> + __u32 dev;
> + __u32 nsid;
> + __u32 tgid;
> + __u32 pid;
> +};
> #endif /* _UAPI__LINUX_BPF_H__ */
> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> index 4d09e610777f..98ce53ce2ea6 100644
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
> @@ -1796,6 +1796,7 @@ const struct bpf_func_proto bpf_sock_map_update_proto __weak;
> const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
> const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
> const struct bpf_func_proto bpf_get_local_storage_proto __weak;
> +const struct bpf_func_proto bpf_get_current_pidns_info __weak;
>
> const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
> {
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
> index 1991466b8327..d06d723b9cff 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -18,6 +18,9 @@
> #include <linux/sched.h>
> #include <linux/uidgid.h>
> #include <linux/filter.h>
> +#include <linux/pid_namespace.h>
> +#include <linux/major.h>
> +#include <linux/stat.h>
>
> /* If kernel subsystem is allowing eBPF programs to call this function,
> * inside its own verifier_ops->get_func_proto() callback it should return
> @@ -214,3 +217,64 @@ const struct bpf_func_proto bpf_get_local_storage_proto = {
> .arg2_type = ARG_ANYTHING,
> };
> #endif
> +
> +BPF_CALL_2(bpf_get_current_pidns_info, struct bpf_pidns_info *, pidns_info, u32,
> + size)
> +{
> + const char *ppath = "/proc/self/ns/pid";
> + struct pid_namespace *pidns = NULL;
> + mm_segment_t oldsegfs;
> + struct kstat stat;
> + pid_t tgid = 0;
> + pid_t pid = 0;
> + int res = 0;
> +
> + if (unlikely(size != sizeof(struct bpf_pidns_info)))
> + goto clear;
> +
> + pidns = task_active_pid_ns(current);
> +
> + if (unlikely(!pidns))
> + goto clear;
> +
> + pidns_info->nsid = pidns->ns.inum;
> + pid = task_pid_nr_ns(current, pidns);
> +
> + if (unlikely(!pid))
> + goto clear;
> +
> + tgid = task_tgid_nr_ns(current, pidns);
> +
> + if (unlikely(!tgid))
> + goto clear;
> +
> + pidns_info->tgid = (u32) tgid;
> + pidns_info->pid = (u32) pid;
> +
> + oldsegfs = get_fs();
> + set_fs(KERNEL_DS);
> + res = vfs_stat((const char __user *)ppath, &stat);
> + set_fs(oldsegfs);
such fs magic cannot be done from the helper.
please find a way to retrieve device differently.
> +
> + if (unlikely(res))
> + goto clear;
> +
> + pidns_info->dev = stat.dev;
> +
> + return 0;
> +
> +clear:
> + if (pidns_info)
> + memset((void *)pidns, 0, (size_t) size);
> +
> + return -EINVAL;
> +}
> +
> +const struct bpf_func_proto bpf_get_current_pidns_info_proto = {
> + .func = bpf_get_current_pidns_info,
> + .gpl_only = false,
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_UNINIT_MEM,
> + .arg2_type = ARG_CONST_SIZE,
> +};
> +
> diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
> index 0ae6829804bc..f70be29e49ab 100644
> --- a/kernel/trace/bpf_trace.c
> +++ b/kernel/trace/bpf_trace.c
> @@ -568,6 +568,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
> case BPF_FUNC_get_current_cgroup_id:
> return &bpf_get_current_cgroup_id_proto;
> #endif
> + case BPF_FUNC_get_current_pidns_info:
> + return &bpf_get_current_pidns_info_proto;
> default:
> return NULL;
> }
> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> index f88d5683d6ee..fdcde00554ce 100644
> --- a/samples/bpf/Makefile
> +++ b/samples/bpf/Makefile
> @@ -53,6 +53,7 @@ hostprogs-y += xdpsock
> hostprogs-y += xdp_fwd
> hostprogs-y += task_fd_query
> hostprogs-y += xdp_sample_pkts
> +hostprogs-y += trace_ns_info
>
> # Libbpf dependencies
> LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
> @@ -109,6 +110,7 @@ xdpsock-objs := xdpsock_user.o
> xdp_fwd-objs := xdp_fwd_user.o
> task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
> xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
> +trace_ns_info-objs := bpf_load.o trace_ns_info_user.o
>
> # Tell kbuild to always build the programs
> always := $(hostprogs-y)
> @@ -166,6 +168,7 @@ always += xdpsock_kern.o
> always += xdp_fwd_kern.o
> always += task_fd_query_kern.o
> always += xdp_sample_pkts_kern.o
> +always += trace_ns_info_user_kern.o
>
> HOSTCFLAGS += -I$(objtree)/usr/include
> HOSTCFLAGS += -I$(srctree)/tools/lib/
> diff --git a/samples/bpf/trace_ns_info_user.c b/samples/bpf/trace_ns_info_user.c
> new file mode 100644
> index 000000000000..e06d08db6f30
> --- /dev/null
> +++ b/samples/bpf/trace_ns_info_user.c
please split addition of sample code into separate patch
and convert it into selftests.
> @@ -0,0 +1,35 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright (c) 2018 Carlos Neira cneirabustos@gmail.com
> + *
> + * 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.
> + */
> +
> +#include <stdio.h>
> +#include <linux/bpf.h>
> +#include <unistd.h>
> +#include "bpf/libbpf.h"
> +#include "bpf_load.h"
> +
> +/* This code was taken verbatim from tracex1_user.c, it's used
> + * to exercize bpf_get_current_pidns_info() helper call.
> + */
> +int main(int ac, char **argv)
> +{
> + FILE *f;
> + char filename[256];
> +
> + snprintf(filename, sizeof(filename), "%s_user_kern.o", argv[0]);
> + printf("loading %s\n", filename);
> +
> + if (load_bpf_file(filename)) {
> + printf("%s", bpf_log_buf);
> + return 1;
> + }
> +
> + f = popen("taskset 1 ping localhost", "r");
> + (void) f;
> + read_trace_pipe();
> + return 0;
> +}
> diff --git a/samples/bpf/trace_ns_info_user_kern.c b/samples/bpf/trace_ns_info_user_kern.c
> new file mode 100644
> index 000000000000..ceaf3e83c8e7
> --- /dev/null
> +++ b/samples/bpf/trace_ns_info_user_kern.c
> @@ -0,0 +1,45 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright (c) 2018 Carlos Neira cneirabustos@gmail.com
> + *
> + * 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.
> + */
> +#include <linux/skbuff.h>
> +#include <linux/netdevice.h>
> +#include <linux/version.h>
> +#include <uapi/linux/bpf.h>
> +#include "bpf_helpers.h"
> +
> +typedef __u64 u64;
> +typedef __u32 u32;
> +
> +
> +/* kprobe is NOT a stable ABI
> + * kernel functions can be removed, renamed or completely change semantics.
> + * Number of arguments and their positions can change, etc.
> + * In such case this bpf+kprobe example will no longer be meaningful
> + */
> +
> +/* This will call bpf_get_current_pidns_info() to display pid and ns values
> + * as seen by the current namespace, on the far left you will see the pid as
> + * seen as by the root namespace.
> + */
> +
> +SEC("kprobe/__netif_receive_skb_core")
> +int bpf_prog1(struct pt_regs *ctx)
> +{
> + char fmt[] = "nsid:%u, dev: %u, pid:%u\n";
> + struct bpf_pidns_info nsinfo;
> + int ok = 0;
> +
> + ok = bpf_get_current_pidns_info(&nsinfo, sizeof(nsinfo));
> + if (ok == 0)
> + bpf_trace_printk(fmt, sizeof(fmt), (u32)nsinfo.nsid,
> + (u32) nsinfo.dev, (u32)nsinfo.pid);
> +
> + return 0;
> +}
> +
> +char _license[] SEC("license") = "GPL";
> +u32 _version SEC("version") = LINUX_VERSION_CODE;
> diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
> index dd5758dc35d3..8462f9881465 100644
> --- a/tools/include/uapi/linux/bpf.h
> +++ b/tools/include/uapi/linux/bpf.h
update to tools/../bpf.h should be separate patch as well.
At the end it should be:
p1 - feature introduction
p2 - update tools/.../bpf.h
p3 - selftest
^ permalink raw reply
* [PATCH 1/2] net: nixge: Do not zero application specific fields in desc
From: Moritz Fischer @ 2018-08-11 1:19 UTC (permalink / raw)
To: davem; +Cc: keescook, netdev, linux-kernel, alex.williams, Moritz Fischer
In-Reply-To: <20180811011941.6187-1-mdf@kernel.org>
Do not zero application specific fields in DMA descriptors.
The hardware does ignore them, so should software.
Signed-off-by: Moritz Fischer <mdf@kernel.org>
---
drivers/net/ethernet/ni/nixge.c | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 9ae4fcef725e..ac31b0d30415 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -739,22 +739,12 @@ static void nixge_dma_err_handler(unsigned long data)
cur_p->phys = 0;
cur_p->cntrl = 0;
cur_p->status = 0;
- cur_p->app0 = 0;
- cur_p->app1 = 0;
- cur_p->app2 = 0;
- cur_p->app3 = 0;
- cur_p->app4 = 0;
cur_p->sw_id_offset = 0;
}
for (i = 0; i < RX_BD_NUM; i++) {
cur_p = &lp->rx_bd_v[i];
cur_p->status = 0;
- cur_p->app0 = 0;
- cur_p->app1 = 0;
- cur_p->app2 = 0;
- cur_p->app3 = 0;
- cur_p->app4 = 0;
}
lp->tx_bd_ci = 0;
--
2.18.0
^ permalink raw reply related
* [PATCH 0/2] net: nixge: Minor cleanups
From: Moritz Fischer @ 2018-08-11 1:19 UTC (permalink / raw)
To: davem; +Cc: keescook, netdev, linux-kernel, alex.williams, Moritz Fischer
Hi Dave,
in preparation of my 64-bit support series, here's some
minor cleanup in preparation that gets rid of unneccesary
accesses to the descriptor application fields.
I've confirmed that the hardware does not access the fields
in all our configurations.
Thanks,
Moritz
Moritz Fischer (2):
net: nixge: Do not zero application specific fields in desc
net: nixge: Don't store skb in app4 field of descriptor
drivers/net/ethernet/ni/nixge.c | 11 -----------
1 file changed, 11 deletions(-)
--
2.18.0
^ permalink raw reply
* [net-next 12/12] net/mlx5: Improve argument name for add flow API
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Eli Cohen, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
From: Eli Cohen <eli@mellanox.com>
The last argument to mlx5_add_flow_rules passes the number of
destinations in the struct pointed to by the dest arg. Change the name
to better reflect this fact.
Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++----
include/linux/mlx5/fs.h | 2 +-
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a21df24b695e..261cb6aacf12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1876,7 +1876,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
struct mlx5_flow_spec *spec,
struct mlx5_flow_act *flow_act,
struct mlx5_flow_destination *dest,
- int dest_num)
+ int num_dest)
{
struct mlx5_flow_root_namespace *root = find_root(&ft->node);
struct mlx5_flow_destination gen_dest = {};
@@ -1889,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
if (!fwd_next_prio_supported(ft))
return ERR_PTR(-EOPNOTSUPP);
- if (dest_num)
+ if (num_dest)
return ERR_PTR(-EINVAL);
mutex_lock(&root->chain_lock);
next_ft = find_next_chained_ft(prio);
@@ -1897,7 +1897,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
gen_dest.ft = next_ft;
dest = &gen_dest;
- dest_num = 1;
+ num_dest = 1;
flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
} else {
mutex_unlock(&root->chain_lock);
@@ -1905,7 +1905,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
}
}
- handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num);
+ handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
if (!IS_ERR_OR_NULL(handle) &&
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index c40f2fc68655..71fb503b2b52 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -177,7 +177,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
struct mlx5_flow_spec *spec,
struct mlx5_flow_act *flow_act,
struct mlx5_flow_destination *dest,
- int dest_num);
+ int num_dest);
void mlx5_del_flow_rules(struct mlx5_flow_handle *fr);
int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
--
2.17.0
^ permalink raw reply related
* [net-next 11/12] net/mlx5: Reorganize the makefile
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Reorganize the Makefile and group files together according to their
functionality and importance.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 57 +++++++++++++------
1 file changed, 40 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9e78c48b22dd..d324a3884462 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -1,38 +1,61 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
+#
+# Makefile for Mellanox 5th generation network adapters
+# (ConnectX series) core & netdev driver
+#
+
subdir-ccflags-y += -I$(src)
+obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
+
+#
+# mlx5 core basic
+#
mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \
diag/fs_tracepoint.o diag/fw_tracer.o
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
-
-mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
- fpga/ipsec.o fpga/tls.o
-
-mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
-mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
-mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
-
+#
+# Netdev basic
+#
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
en_selftest.o en/port.o
-mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o
-mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
+#
+# Netdev extra
+#
+mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o
+
+#
+# Core extra
+#
+mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
+#
+# Ipoib netdev
+#
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
-mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
+#
+# Accelerations & FPGA
+#
+mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
-mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
+mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
+ fpga/ipsec.o fpga/tls.o
mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
- en_accel/ipsec_stats.o
+ en_accel/ipsec_stats.o
-mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
CFLAGS_tracepoint.o := -I$(src)
--
2.17.0
^ permalink raw reply related
* [net-next 10/12] net/mlx5e: clock.c depends on CONFIG_PTP_1588_CLOCK
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Moshe Shemesh, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
From: Moshe Shemesh <moshe@mellanox.com>
lib/clock.c includes clock related functions which require ptp support.
Thus compile out lib/clock.c and add the needed function stubs in case
kconfig CONFIG_PTP_1588_CLOCK is off.
Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Makefile | 3 ++-
.../ethernet/mellanox/mlx5/core/en_ethtool.c | 7 +++---
.../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +++-
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 1 +
.../ethernet/mellanox/mlx5/core/lib/clock.h | 24 +++++++++++++++++++
.../ethernet/mellanox/mlx5/core/mlx5_core.h | 1 -
6 files changed, 34 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 09b5e235527b..9e78c48b22dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -5,7 +5,7 @@ subdir-ccflags-y += -I$(src)
mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
- fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
+ fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o \
diag/fs_tracepoint.o diag/fw_tracer.o
mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
@@ -15,6 +15,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 7787cc3a2c84..98dd3e0ada72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
#include "en.h"
#include "en/port.h"
+#include "lib/clock.h"
void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
struct ethtool_drvinfo *drvinfo)
@@ -1106,10 +1107,10 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
if (ret)
return ret;
- info->phc_index = mdev->clock.ptp ?
- ptp_clock_index(mdev->clock.ptp) : -1;
+ info->phc_index = mlx5_clock_get_ptp_index(mdev);
- if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+ if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+ info->phc_index == -1)
return 0;
info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e09086f41365..5a7939e70190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -46,6 +46,7 @@
#include "accel/ipsec.h"
#include "accel/tls.h"
#include "lib/vxlan.h"
+#include "lib/clock.h"
#include "en/port.h"
#include "en/xdp.h"
@@ -3782,7 +3783,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
struct hwtstamp_config config;
int err;
- if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+ if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+ (mlx5_clock_get_ptp_index(priv->mdev) == -1))
return -EOPNOTSUPP;
if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 7669b4380779..48864f4988a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -40,6 +40,7 @@
#include "mlx5_core.h"
#include "fpga/core.h"
#include "eswitch.h"
+#include "lib/clock.h"
#include "diag/fw_tracer.h"
enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index a8eecedd46c2..02e2e4575e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,8 +33,15 @@
#ifndef __LIB_CLOCK_H__
#define __LIB_CLOCK_H__
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
void mlx5_init_clock(struct mlx5_core_dev *mdev);
void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+ return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+}
static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
u64 timestamp)
@@ -48,4 +55,21 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
return ns_to_ktime(nsec);
}
+#else
+static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+ return -1;
+}
+
+static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
+ u64 timestamp)
+{
+ return 0;
+}
+#endif
+
#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 49955117ae36..b4134fa0bba3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -99,7 +99,6 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
unsigned long param);
void mlx5_core_page_fault(struct mlx5_core_dev *dev,
struct mlx5_pagefault *pfault);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
void mlx5_disable_device(struct mlx5_core_dev *dev);
--
2.17.0
^ permalink raw reply related
* [net-next 08/12] net/mlx5e: Move flow steering declarations into en/fs.h
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Move flow steering declarations and definitions into the dedicated
en/fs.h header file
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 126 -----------------
.../net/ethernet/mellanox/mlx5/core/en/fs.h | 129 ++++++++++++++++++
2 files changed, 129 insertions(+), 126 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8743bbe1baa2..db2cfcd21d43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -627,112 +627,12 @@ struct mlx5e_channel_stats {
struct mlx5e_xdpsq_stats xdpsq;
} ____cacheline_aligned_in_smp;
-enum mlx5e_traffic_types {
- MLX5E_TT_IPV4_TCP,
- MLX5E_TT_IPV6_TCP,
- MLX5E_TT_IPV4_UDP,
- MLX5E_TT_IPV6_UDP,
- MLX5E_TT_IPV4_IPSEC_AH,
- MLX5E_TT_IPV6_IPSEC_AH,
- MLX5E_TT_IPV4_IPSEC_ESP,
- MLX5E_TT_IPV6_IPSEC_ESP,
- MLX5E_TT_IPV4,
- MLX5E_TT_IPV6,
- MLX5E_TT_ANY,
- MLX5E_NUM_TT,
- MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
-};
-
-enum mlx5e_tunnel_types {
- MLX5E_TT_IPV4_GRE,
- MLX5E_TT_IPV6_GRE,
- MLX5E_NUM_TUNNEL_TT,
-};
-
enum {
MLX5E_STATE_ASYNC_EVENTS_ENABLED,
MLX5E_STATE_OPENED,
MLX5E_STATE_DESTROYING,
};
-struct mlx5e_l2_rule {
- u8 addr[ETH_ALEN + 2];
- struct mlx5_flow_handle *rule;
-};
-
-#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
-
-struct mlx5e_tc_table {
- struct mlx5_flow_table *t;
-
- struct rhashtable ht;
-
- DECLARE_HASHTABLE(mod_hdr_tbl, 8);
- DECLARE_HASHTABLE(hairpin_tbl, 8);
-};
-
-struct mlx5e_vlan_table {
- struct mlx5e_flow_table ft;
- DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
- DECLARE_BITMAP(active_svlans, VLAN_N_VID);
- struct mlx5_flow_handle *active_cvlans_rule[VLAN_N_VID];
- struct mlx5_flow_handle *active_svlans_rule[VLAN_N_VID];
- struct mlx5_flow_handle *untagged_rule;
- struct mlx5_flow_handle *any_cvlan_rule;
- struct mlx5_flow_handle *any_svlan_rule;
- bool cvlan_filter_disabled;
-};
-
-struct mlx5e_l2_table {
- struct mlx5e_flow_table ft;
- struct hlist_head netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
- struct hlist_head netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
- struct mlx5e_l2_rule broadcast;
- struct mlx5e_l2_rule allmulti;
- struct mlx5e_l2_rule promisc;
- bool broadcast_enabled;
- bool allmulti_enabled;
- bool promisc_enabled;
-};
-
-/* L3/L4 traffic type classifier */
-struct mlx5e_ttc_table {
- struct mlx5e_flow_table ft;
- struct mlx5_flow_handle *rules[MLX5E_NUM_TT];
- struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
-};
-
-/* NIC prio FTS */
-enum {
- MLX5E_VLAN_FT_LEVEL = 0,
- MLX5E_L2_FT_LEVEL,
- MLX5E_TTC_FT_LEVEL,
- MLX5E_INNER_TTC_FT_LEVEL,
-#ifdef CONFIG_MLX5_EN_ARFS
- MLX5E_ARFS_FT_LEVEL
-#endif
-};
-
-enum {
- MLX5E_TC_FT_LEVEL = 0,
- MLX5E_TC_TTC_FT_LEVEL,
-};
-
-struct mlx5e_flow_steering {
- struct mlx5_flow_namespace *ns;
-#ifdef CONFIG_MLX5_EN_RXNFC
- struct mlx5e_ethtool_steering ethtool;
-#endif
- struct mlx5e_tc_table tc;
- struct mlx5e_vlan_table vlan;
- struct mlx5e_l2_table l2;
- struct mlx5e_ttc_table ttc;
- struct mlx5e_ttc_table inner_ttc;
-#ifdef CONFIG_MLX5_EN_ARFS
- struct mlx5e_arfs_tables arfs;
-#endif
-};
-
struct mlx5e_rqt {
u32 rqtn;
bool enabled;
@@ -866,10 +766,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
void mlx5e_update_stats(struct mlx5e_priv *priv);
-int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
int mlx5e_self_test_num(struct mlx5e_priv *priv);
void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
u64 *buf);
@@ -883,8 +780,6 @@ int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
u16 vid);
int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
u16 vid);
-void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
-void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
void mlx5e_timestamp_init(struct mlx5e_priv *priv);
struct mlx5e_redirect_rqt_param {
@@ -1021,27 +916,6 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
-struct ttc_params {
- struct mlx5_flow_table_attr ft_attr;
- u32 any_tt_tirn;
- u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
- struct mlx5e_ttc_table *inner_ttc;
-};
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
- struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
- struct mlx5e_ttc_table *ttc);
-
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
- struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
- struct mlx5e_ttc_table *ttc);
-
int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
u32 underlay_qpn, u32 *tisn);
void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index adc00ae7e9e9..bbf69e859b78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -4,12 +4,97 @@
#ifndef __MLX5E_FLOW_STEER_H__
#define __MLX5E_FLOW_STEER_H__
+enum {
+ MLX5E_TC_FT_LEVEL = 0,
+ MLX5E_TC_TTC_FT_LEVEL,
+};
+
+struct mlx5e_tc_table {
+ struct mlx5_flow_table *t;
+
+ struct rhashtable ht;
+
+ DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+ DECLARE_HASHTABLE(hairpin_tbl, 8);
+};
+
struct mlx5e_flow_table {
int num_groups;
struct mlx5_flow_table *t;
struct mlx5_flow_group **g;
};
+struct mlx5e_l2_rule {
+ u8 addr[ETH_ALEN + 2];
+ struct mlx5_flow_handle *rule;
+};
+
+#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct mlx5e_vlan_table {
+ struct mlx5e_flow_table ft;
+ DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
+ DECLARE_BITMAP(active_svlans, VLAN_N_VID);
+ struct mlx5_flow_handle *active_cvlans_rule[VLAN_N_VID];
+ struct mlx5_flow_handle *active_svlans_rule[VLAN_N_VID];
+ struct mlx5_flow_handle *untagged_rule;
+ struct mlx5_flow_handle *any_cvlan_rule;
+ struct mlx5_flow_handle *any_svlan_rule;
+ bool cvlan_filter_disabled;
+};
+
+struct mlx5e_l2_table {
+ struct mlx5e_flow_table ft;
+ struct hlist_head netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
+ struct hlist_head netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
+ struct mlx5e_l2_rule broadcast;
+ struct mlx5e_l2_rule allmulti;
+ struct mlx5e_l2_rule promisc;
+ bool broadcast_enabled;
+ bool allmulti_enabled;
+ bool promisc_enabled;
+};
+
+enum mlx5e_traffic_types {
+ MLX5E_TT_IPV4_TCP,
+ MLX5E_TT_IPV6_TCP,
+ MLX5E_TT_IPV4_UDP,
+ MLX5E_TT_IPV6_UDP,
+ MLX5E_TT_IPV4_IPSEC_AH,
+ MLX5E_TT_IPV6_IPSEC_AH,
+ MLX5E_TT_IPV4_IPSEC_ESP,
+ MLX5E_TT_IPV6_IPSEC_ESP,
+ MLX5E_TT_IPV4,
+ MLX5E_TT_IPV6,
+ MLX5E_TT_ANY,
+ MLX5E_NUM_TT,
+ MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
+};
+
+enum mlx5e_tunnel_types {
+ MLX5E_TT_IPV4_GRE,
+ MLX5E_TT_IPV6_GRE,
+ MLX5E_NUM_TUNNEL_TT,
+};
+
+/* L3/L4 traffic type classifier */
+struct mlx5e_ttc_table {
+ struct mlx5e_flow_table ft;
+ struct mlx5_flow_handle *rules[MLX5E_NUM_TT];
+ struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
+};
+
+/* NIC prio FTS */
+enum {
+ MLX5E_VLAN_FT_LEVEL = 0,
+ MLX5E_L2_FT_LEVEL,
+ MLX5E_TTC_FT_LEVEL,
+ MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
+ MLX5E_ARFS_FT_LEVEL
+#endif
+};
+
#ifdef CONFIG_MLX5_EN_RXNFC
struct mlx5e_ethtool_table {
@@ -77,5 +162,49 @@ static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUP
static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
#endif
+struct mlx5e_flow_steering {
+ struct mlx5_flow_namespace *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
+ struct mlx5e_ethtool_steering ethtool;
+#endif
+ struct mlx5e_tc_table tc;
+ struct mlx5e_vlan_table vlan;
+ struct mlx5e_l2_table l2;
+ struct mlx5e_ttc_table ttc;
+ struct mlx5e_ttc_table inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
+ struct mlx5e_arfs_tables arfs;
+#endif
+};
+
+struct ttc_params {
+ struct mlx5_flow_table_attr ft_attr;
+ u32 any_tt_tirn;
+ u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
+ struct mlx5e_ttc_table *inner_ttc;
+};
+
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+ struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+ struct mlx5e_ttc_table *ttc);
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+ struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+ struct mlx5e_ttc_table *ttc);
+
+void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
+
+void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
+void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
+
+int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
+void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
+
#endif /* __MLX5E_FLOW_STEER_H__ */
--
2.17.0
^ permalink raw reply related
* [net-next 09/12] net/mlx5e: vxlan.c depends on CONFIG_VXLAN
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
When vxlan is not enabled by kernel, no need to enable it in mlx5.
Compile out lib/vxlan.c if CONFIG_VXLAN is not selected.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 1 +
drivers/net/ethernet/mellanox/mlx5/core/Makefile | 7 ++++---
drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h | 12 ++++++------
3 files changed, 11 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 01f9ba1a2098..37a551436e4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -7,6 +7,7 @@ config MLX5_CORE
depends on MAY_USE_DEVLINK
depends on PCI
imply PTP_1588_CLOCK
+ imply VXLAN
default n
---help---
Core driver for low level functionality of the ConnectX-4 and
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ae9da4b51487..09b5e235527b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -13,15 +13,16 @@ mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
fpga/ipsec.o fpga/tls.o
+mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
+
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
- en_selftest.o en/port.o lib/vxlan.o
+ en_selftest.o en/port.o
mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o
mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
-mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
-
mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index fd874a30c4d0..8fb0eb08fa6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -37,8 +37,6 @@
struct mlx5_vxlan;
struct mlx5_vxlan_port;
-#ifdef CONFIG_MLX5_CORE_EN
-
static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
{
/* not allowed reason is encoded in vxlan pointer as error,
@@ -47,18 +45,20 @@ static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
return !IS_ERR_OR_NULL(vxlan);
}
+#if IS_ENABLED(CONFIG_VXLAN)
struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
-
#else
-
static inline struct mlx5_vxlan*
-mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); }
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
-
+static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline struct mx5_vxlan_port*
+mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return NULL; }
#endif
#endif /* __MLX5_VXLAN_H__ */
--
2.17.0
^ permalink raw reply related
* [net-next 07/12] net/mlx5e: Add CONFIG_MLX5_EN_ARFS for accelerated flow steering support
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Add new mlx5 Kconfig flag to allow selecting accelerated flow steering
support, and compile out en_arfs.c if not selected.
Move arfs declarations and definitions to en/fs.h header file.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Kconfig | 8 +++
.../net/ethernet/mellanox/mlx5/core/Makefile | 3 +-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 61 ++-----------------
.../net/ethernet/mellanox/mlx5/core/en/fs.h | 46 ++++++++++++++
.../net/ethernet/mellanox/mlx5/core/en_arfs.c | 4 +-
.../net/ethernet/mellanox/mlx5/core/en_main.c | 14 ++---
6 files changed, 68 insertions(+), 68 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 1ff5f12ab12d..01f9ba1a2098 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -35,6 +35,14 @@ config MLX5_CORE_EN
---help---
Ethernet support in Mellanox Technologies ConnectX-4 NIC.
+config MLX5_EN_ARFS
+ bool "Mellanox MLX5 ethernet accelerated receive flow steering (ARFS) support"
+ depends on MLX5_CORE_EN && RFS_ACCEL
+ default y
+ ---help---
+ Mellanox MLX5 ethernet hardware-accelerated receive flow steering support,
+ Enables ethernet netdevice arfs support and ntuple filtering.
+
config MLX5_EN_RXNFC
bool "Mellanox MLX5 ethernet rx nfc flow steering support"
depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 7b6f9d2c32c9..ae9da4b51487 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,8 +15,9 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
- en_arfs.o en_selftest.o en/port.o lib/vxlan.o
+ en_selftest.o en/port.o lib/vxlan.o
+mlx5_core-$(CONFIG_MLX5_EN_ARFS) += en_arfs.o
mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 19728f9f25e7..8743bbe1baa2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -660,12 +660,6 @@ struct mlx5e_l2_rule {
struct mlx5_flow_handle *rule;
};
-struct mlx5e_flow_table {
- int num_groups;
- struct mlx5_flow_table *t;
- struct mlx5_flow_group **g;
-};
-
#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
struct mlx5e_tc_table {
@@ -708,38 +702,15 @@ struct mlx5e_ttc_table {
struct mlx5_flow_handle *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
};
-#define ARFS_HASH_SHIFT BITS_PER_BYTE
-#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
-struct arfs_table {
- struct mlx5e_flow_table ft;
- struct mlx5_flow_handle *default_rule;
- struct hlist_head rules_hash[ARFS_HASH_SIZE];
-};
-
-enum arfs_type {
- ARFS_IPV4_TCP,
- ARFS_IPV6_TCP,
- ARFS_IPV4_UDP,
- ARFS_IPV6_UDP,
- ARFS_NUM_TYPES,
-};
-
-struct mlx5e_arfs_tables {
- struct arfs_table arfs_tables[ARFS_NUM_TYPES];
- /* Protect aRFS rules list */
- spinlock_t arfs_lock;
- struct list_head rules;
- int last_filter_id;
- struct workqueue_struct *wq;
-};
-
/* NIC prio FTS */
enum {
MLX5E_VLAN_FT_LEVEL = 0,
MLX5E_L2_FT_LEVEL,
MLX5E_TTC_FT_LEVEL,
MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
MLX5E_ARFS_FT_LEVEL
+#endif
};
enum {
@@ -757,7 +728,9 @@ struct mlx5e_flow_steering {
struct mlx5e_l2_table l2;
struct mlx5e_ttc_table ttc;
struct mlx5e_ttc_table inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
struct mlx5e_arfs_tables arfs;
+#endif
};
struct mlx5e_rqt {
@@ -1028,32 +1001,6 @@ void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
#endif
-#ifndef CONFIG_RFS_ACCEL
-static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
-{
- return 0;
-}
-
-static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
-
-static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
-{
- return -EOPNOTSUPP;
-}
-
-static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
-{
- return -EOPNOTSUPP;
-}
-#else
-int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
-void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
-int mlx5e_arfs_enable(struct mlx5e_priv *priv);
-int mlx5e_arfs_disable(struct mlx5e_priv *priv);
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
- u16 rxq_index, u32 flow_id);
-#endif
-
int mlx5e_create_tir(struct mlx5_core_dev *mdev,
struct mlx5e_tir *tir, u32 *in, int inlen);
void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 50b0784787bc..adc00ae7e9e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -4,6 +4,12 @@
#ifndef __MLX5E_FLOW_STEER_H__
#define __MLX5E_FLOW_STEER_H__
+struct mlx5e_flow_table {
+ int num_groups;
+ struct mlx5_flow_table *t;
+ struct mlx5_flow_group **g;
+};
+
#ifdef CONFIG_MLX5_EN_RXNFC
struct mlx5e_ethtool_table {
@@ -31,5 +37,45 @@ static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { }
static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
#endif /* CONFIG_MLX5_EN_RXNFC */
+#ifdef CONFIG_MLX5_EN_ARFS
+#define ARFS_HASH_SHIFT BITS_PER_BYTE
+#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct arfs_table {
+ struct mlx5e_flow_table ft;
+ struct mlx5_flow_handle *default_rule;
+ struct hlist_head rules_hash[ARFS_HASH_SIZE];
+};
+
+enum arfs_type {
+ ARFS_IPV4_TCP,
+ ARFS_IPV6_TCP,
+ ARFS_IPV4_UDP,
+ ARFS_IPV6_UDP,
+ ARFS_NUM_TYPES,
+};
+
+struct mlx5e_arfs_tables {
+ struct arfs_table arfs_tables[ARFS_NUM_TYPES];
+ /* Protect aRFS rules list */
+ spinlock_t arfs_lock;
+ struct list_head rules;
+ int last_filter_id;
+ struct workqueue_struct *wq;
+};
+
+int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
+void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
+int mlx5e_arfs_enable(struct mlx5e_priv *priv);
+int mlx5e_arfs_disable(struct mlx5e_priv *priv);
+int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+ u16 rxq_index, u32 flow_id);
+#else
+static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
+static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
+static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
+#endif
+
#endif /* __MLX5E_FLOW_STEER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index d258bb679271..45cdde694d20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -30,8 +30,6 @@
* SOFTWARE.
*/
-#ifdef CONFIG_RFS_ACCEL
-
#include <linux/hash.h>
#include <linux/mlx5/fs.h>
#include <linux/ip.h>
@@ -738,4 +736,4 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
spin_unlock_bh(&arfs->arfs_lock);
return arfs_rule->filter_id;
}
-#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2731ba2d8049..e09086f41365 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3624,7 +3624,7 @@ static int set_feature_rx_vlan(struct net_device *netdev, bool enable)
return err;
}
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
static int set_feature_arfs(struct net_device *netdev, bool enable)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3679,7 +3679,7 @@ static int mlx5e_set_features(struct net_device *netdev,
err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
#endif
@@ -4348,12 +4348,12 @@ static const struct net_device_ops mlx5e_netdev_ops = {
.ndo_udp_tunnel_add = mlx5e_add_vxlan_port,
.ndo_udp_tunnel_del = mlx5e_del_vxlan_port,
.ndo_features_check = mlx5e_features_check,
-#ifdef CONFIG_RFS_ACCEL
- .ndo_rx_flow_steer = mlx5e_rx_flow_steer,
-#endif
.ndo_tx_timeout = mlx5e_tx_timeout,
.ndo_bpf = mlx5e_xdp,
.ndo_xdp_xmit = mlx5e_xdp_xmit,
+#ifdef CONFIG_MLX5_EN_ARFS
+ .ndo_rx_flow_steer = mlx5e_rx_flow_steer,
+#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = mlx5e_netpoll,
#endif
@@ -4703,7 +4703,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
FT_CAP(identified_miss_table_mode) &&
FT_CAP(flow_table_modify)) {
netdev->hw_features |= NETIF_F_HW_TC;
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
netdev->hw_features |= NETIF_F_NTUPLE;
#endif
}
@@ -4947,7 +4947,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
return NULL;
}
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
netdev->rx_cpu_rmap = mdev->rmap;
#endif
--
2.17.0
^ permalink raw reply related
* [net-next 05/12] net/mlx5e: Ethtool steering, move ethtool callbacks
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Move ethool rxnfc callback into en_fs_etthool file where they belong.
This will allow us to make many ethtool fs related helper functions
static.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 11 +--
.../ethernet/mellanox/mlx5/core/en_ethtool.c | 48 -------------
.../mellanox/mlx5/core/en_fs_ethtool.c | 67 ++++++++++++++++---
3 files changed, 62 insertions(+), 64 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index dddd29a3be97..31a29b73f558 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -912,16 +912,11 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
int mlx5e_self_test_num(struct mlx5e_priv *priv);
void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
u64 *buf);
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
- int location);
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
- struct ethtool_rxnfc *info, u32 *rule_locs);
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
- struct ethtool_rx_flow_spec *fs);
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
- int location);
void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *info, u32 *rule_locs);
void mlx5e_set_rx_mode_work(struct work_struct *work);
int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fffe514ba855..cde1a0bb9c4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -969,33 +969,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
return 0;
}
-static int mlx5e_get_rxnfc(struct net_device *netdev,
- struct ethtool_rxnfc *info, u32 *rule_locs)
-{
- struct mlx5e_priv *priv = netdev_priv(netdev);
- int err = 0;
-
- switch (info->cmd) {
- case ETHTOOL_GRXRINGS:
- info->data = priv->channels.params.num_channels;
- break;
- case ETHTOOL_GRXCLSRLCNT:
- info->rule_cnt = priv->fs.ethtool.tot_num_rules;
- break;
- case ETHTOOL_GRXCLSRULE:
- err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
- break;
- case ETHTOOL_GRXCLSRLALL:
- err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
- break;
- default:
- err = -EOPNOTSUPP;
- break;
- }
-
- return err;
-}
-
#define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC 100
#define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC 8000
#define MLX5E_PFC_PREVEN_MINOR_PRECENT 85
@@ -1606,26 +1579,6 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
return priv->channels.params.pflags;
}
-static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
- int err = 0;
- struct mlx5e_priv *priv = netdev_priv(dev);
-
- switch (cmd->cmd) {
- case ETHTOOL_SRXCLSRLINS:
- err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
- break;
- case ETHTOOL_SRXCLSRLDEL:
- err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
- break;
- default:
- err = -EOPNOTSUPP;
- break;
- }
-
- return err;
-}
-
int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
struct ethtool_flash *flash)
{
@@ -1696,5 +1649,4 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
.self_test = mlx5e_self_test,
.get_msglevel = mlx5e_get_msglevel,
.set_msglevel = mlx5e_set_msglevel,
-
};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index c0abcf48dfe5..881cb2475c18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -684,8 +684,9 @@ static int validate_flow(struct mlx5e_priv *priv,
return num_tuples;
}
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
- struct ethtool_rx_flow_spec *fs)
+static int
+mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+ struct ethtool_rx_flow_spec *fs)
{
struct mlx5e_ethtool_table *eth_ft;
struct mlx5e_ethtool_rule *eth_rule;
@@ -732,8 +733,8 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
return err;
}
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
- int location)
+static int
+mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv, int location)
{
struct mlx5e_ethtool_rule *eth_rule;
int err = 0;
@@ -752,8 +753,9 @@ int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
return err;
}
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
- int location)
+static int
+mlx5e_ethtool_get_flow(struct mlx5e_priv *priv,
+ struct ethtool_rxnfc *info, int location)
{
struct mlx5e_ethtool_rule *eth_rule;
@@ -770,8 +772,9 @@ int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
return -ENOENT;
}
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
- u32 *rule_locs)
+static int
+mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
+ struct ethtool_rxnfc *info, u32 *rule_locs)
{
int location = 0;
int idx = 0;
@@ -800,3 +803,51 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
{
INIT_LIST_HEAD(&priv->fs.ethtool.rules);
}
+
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+ int err = 0;
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ switch (cmd->cmd) {
+ case ETHTOOL_SRXCLSRLINS:
+ err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+ break;
+ case ETHTOOL_SRXCLSRLDEL:
+ err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
+int mlx5e_get_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+ int err = 0;
+
+ switch (info->cmd) {
+ case ETHTOOL_GRXRINGS:
+ info->data = priv->channels.params.num_channels;
+ break;
+ case ETHTOOL_GRXCLSRLCNT:
+ info->rule_cnt = priv->fs.ethtool.tot_num_rules;
+ break;
+ case ETHTOOL_GRXCLSRULE:
+ err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
+ break;
+ case ETHTOOL_GRXCLSRLALL:
+ err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ return err;
+}
+
--
2.17.0
^ permalink raw reply related
* [net-next 06/12] net/mlx5e: Add CONFIG_MLX5_EN_RXNFC for ethtool rx nfc
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Add new mlx5 Kconfig flag to allow selecting ethtool rx nfc support,
and compile out en_fs_ehtool.c if not selected.
Add en/fs.h header file to host all steering declarations and
definitions.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/Kconfig | 10 ++++++
.../net/ethernet/mellanox/mlx5/core/Makefile | 4 ++-
drivers/net/ethernet/mellanox/mlx5/core/en.h | 23 ++----------
.../net/ethernet/mellanox/mlx5/core/en/fs.h | 35 +++++++++++++++++++
.../ethernet/mellanox/mlx5/core/en_ethtool.c | 2 ++
5 files changed, 53 insertions(+), 21 deletions(-)
create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 7a84dd07ced2..1ff5f12ab12d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -35,6 +35,16 @@ config MLX5_CORE_EN
---help---
Ethernet support in Mellanox Technologies ConnectX-4 NIC.
+config MLX5_EN_RXNFC
+ bool "Mellanox MLX5 ethernet rx nfc flow steering support"
+ depends on MLX5_CORE_EN
+ default y
+ ---help---
+ Mellanox MLX5 ethernet rx nfc flow steering support
+ Enables ethtool receive network flow classification, which allows user defined
+ flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc
+ API.
+
config MLX5_MPFS
bool "Mellanox Technologies MLX5 MPFS support"
depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index f20fda1ced4f..7b6f9d2c32c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,7 +15,9 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
- en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o lib/vxlan.o
+ en_arfs.o en_selftest.o en/port.o lib/vxlan.o
+
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 31a29b73f558..19728f9f25e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
#include "wq.h"
#include "mlx5_core.h"
#include "en_stats.h"
+#include "en/fs.h"
struct page_pool;
@@ -746,24 +747,11 @@ enum {
MLX5E_TC_TTC_FT_LEVEL,
};
-struct mlx5e_ethtool_table {
- struct mlx5_flow_table *ft;
- int num_rules;
-};
-
-#define ETHTOOL_NUM_L3_L4_FTS 7
-#define ETHTOOL_NUM_L2_FTS 4
-
-struct mlx5e_ethtool_steering {
- struct mlx5e_ethtool_table l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
- struct mlx5e_ethtool_table l2_ft[ETHTOOL_NUM_L2_FTS];
- struct list_head rules;
- int tot_num_rules;
-};
-
struct mlx5e_flow_steering {
struct mlx5_flow_namespace *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
struct mlx5e_ethtool_steering ethtool;
+#endif
struct mlx5e_tc_table tc;
struct mlx5e_vlan_table vlan;
struct mlx5e_l2_table l2;
@@ -912,11 +900,6 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
int mlx5e_self_test_num(struct mlx5e_priv *priv);
void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
u64 *buf);
-void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
-void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
-int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
-int mlx5e_get_rxnfc(struct net_device *dev,
- struct ethtool_rxnfc *info, u32 *rule_locs);
void mlx5e_set_rx_mode_work(struct work_struct *work);
int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
new file mode 100644
index 000000000000..50b0784787bc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5E_FLOW_STEER_H__
+#define __MLX5E_FLOW_STEER_H__
+
+#ifdef CONFIG_MLX5_EN_RXNFC
+
+struct mlx5e_ethtool_table {
+ struct mlx5_flow_table *ft;
+ int num_rules;
+};
+
+#define ETHTOOL_NUM_L3_L4_FTS 7
+#define ETHTOOL_NUM_L2_FTS 4
+
+struct mlx5e_ethtool_steering {
+ struct mlx5e_ethtool_table l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
+ struct mlx5e_ethtool_table l2_ft[ETHTOOL_NUM_L2_FTS];
+ struct list_head rules;
+ int tot_num_rules;
+};
+
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+ struct ethtool_rxnfc *info, u32 *rule_locs);
+#else
+static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { }
+static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
+#endif /* CONFIG_MLX5_EN_RXNFC */
+
+#endif /* __MLX5E_FLOW_STEER_H__ */
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cde1a0bb9c4a..7787cc3a2c84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1631,8 +1631,10 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
.get_rxfh = mlx5e_get_rxfh,
.set_rxfh = mlx5e_set_rxfh,
+#ifdef CONFIG_MLX5_EN_RXNFC
.get_rxnfc = mlx5e_get_rxnfc,
.set_rxnfc = mlx5e_set_rxnfc,
+#endif
.flash_device = mlx5e_flash_device,
.get_tunable = mlx5e_get_tunable,
.set_tunable = mlx5e_set_tunable,
--
2.17.0
^ permalink raw reply related
* [net-next 03/12] net/mlx5e: Ethtool steering, ip6 support
From: Saeed Mahameed @ 2018-08-10 22:26 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Saeed Mahameed
In-Reply-To: <20180810222630.11688-1-saeedm@mellanox.com>
Add ip6 support for ethtool flow steering.
New supported flow types: ip6|tcp6|udp6|
Supported fields: src-ip|dst-ip|src-port|dst-port
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../mellanox/mlx5/core/en_fs_ethtool.c | 138 ++++++++++++++++++
1 file changed, 138 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index f2fa189adc4f..646b659fe805 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -66,11 +66,14 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
case TCP_V4_FLOW:
case UDP_V4_FLOW:
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
max_tuples = ETHTOOL_NUM_L3_L4_FTS;
prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
break;
case IP_USER_FLOW:
+ case IPV6_USER_FLOW:
max_tuples = ETHTOOL_NUM_L3_L4_FTS;
prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
@@ -142,6 +145,39 @@ set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m,
MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IP);
}
+static bool is_zero_ip6(__be32 ip6[4])
+{
+ int i;
+
+ for (i = 0; i < 4; i++)
+ if (ip6[i] != 0)
+ return false;
+ return true;
+}
+
+static void
+set_ip6(void *headers_c, void *headers_v, __be32 ip6src_m[4],
+ __be32 ip6src_v[4], __be32 ip6dst_m[4], __be32 ip6dst_v[4])
+{
+ u8 ip6_sz = MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6);
+
+ if (!is_zero_ip6(ip6src_m)) {
+ memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+ ip6src_v, ip6_sz);
+ memset(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+ 0xff, ip6_sz);
+ }
+ if (!is_zero_ip6(ip6dst_m)) {
+ memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+ ip6dst_v, ip6_sz);
+ memset(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+ 0xff, ip6_sz);
+ }
+
+ MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+ MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IPV6);
+}
+
static void
set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
__be16 pdst_m, __be16 pdst_v)
@@ -213,6 +249,42 @@ parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
l3_mask->ip4dst, l3_val->ip4dst);
}
+static void
+parse_ip6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+ struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+ struct ethtool_usrip6_spec *l3_val = &fs->h_u.usr_ip6_spec;
+
+ set_ip6(headers_c, headers_v, l3_mask->ip6src,
+ l3_val->ip6src, l3_mask->ip6dst, l3_val->ip6dst);
+}
+
+static void
+parse_tcp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+ struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+ struct ethtool_tcpip6_spec *l4_val = &fs->h_u.tcp_ip6_spec;
+
+ set_ip6(headers_c, headers_v, l4_mask->ip6src,
+ l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+ set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+ l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+ struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.udp_ip6_spec;
+ struct ethtool_tcpip6_spec *l4_val = &fs->h_u.udp_ip6_spec;
+
+ set_ip6(headers_c, headers_v, l4_mask->ip6src,
+ l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+ set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+ l4_mask->pdst, l4_val->pdst);
+}
+
static void
parse_ether(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
{
@@ -264,6 +336,15 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
case IP_USER_FLOW:
parse_ip4(outer_headers_c, outer_headers_v, fs);
break;
+ case TCP_V6_FLOW:
+ parse_tcp6(outer_headers_c, outer_headers_v, fs);
+ break;
+ case UDP_V6_FLOW:
+ parse_udp6(outer_headers_c, outer_headers_v, fs);
+ break;
+ case IPV6_USER_FLOW:
+ parse_ip6(outer_headers_c, outer_headers_v, fs);
+ break;
case ETHER_FLOW:
parse_ether(outer_headers_c, outer_headers_v, fs);
break;
@@ -473,6 +554,50 @@ static int validate_ip4(struct ethtool_rx_flow_spec *fs)
return ++ntuples;
}
+static int validate_ip6(struct ethtool_rx_flow_spec *fs)
+{
+ struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+ int ntuples = 0;
+
+ if (l3_mask->l4_4_bytes || l3_mask->tclass || l3_mask->l4_proto)
+ return -EINVAL;
+ if (!is_zero_ip6(l3_mask->ip6src))
+ ntuples++;
+ if (!is_zero_ip6(l3_mask->ip6dst))
+ ntuples++;
+
+ /* Flow is IPv6 */
+ return ++ntuples;
+}
+
+static int validate_tcpudp6(struct ethtool_rx_flow_spec *fs)
+{
+ struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+ int ntuples = 0;
+
+ if (l4_mask->tclass)
+ return -EINVAL;
+
+ if (!is_zero_ip6(l4_mask->ip6src))
+ ntuples++;
+
+ if (!is_zero_ip6(l4_mask->ip6dst))
+ ntuples++;
+
+ if (l4_mask->psrc) {
+ if (!all_ones(l4_mask->psrc))
+ return -EINVAL;
+ ntuples++;
+ }
+ if (l4_mask->pdst) {
+ if (!all_ones(l4_mask->pdst))
+ return -EINVAL;
+ ntuples++;
+ }
+ /* Flow is TCP/UDP */
+ return ++ntuples;
+}
+
static int validate_vlan(struct ethtool_rx_flow_spec *fs)
{
if (fs->m_ext.vlan_etype ||
@@ -516,6 +641,19 @@ static int validate_flow(struct mlx5e_priv *priv,
return ret;
num_tuples += ret;
break;
+ case TCP_V6_FLOW:
+ case UDP_V6_FLOW:
+ ret = validate_tcpudp6(fs);
+ if (ret < 0)
+ return ret;
+ num_tuples += ret;
+ break;
+ case IPV6_USER_FLOW:
+ ret = validate_ip6(fs);
+ if (ret < 0)
+ return ret;
+ num_tuples += ret;
+ break;
default:
return -ENOTSUPP;
}
--
2.17.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox