* [PATCH rdma-next v1 12/13] IB/mlx5: Add flow counters read support
From: Leon Romanovsky @ 2018-05-27 10:23 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Boris Pismenny, Matan Barak,
Raed Salem, Yishai Hadas, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527102346.15149-1-leon@kernel.org>
From: Raed Salem <raeds@mellanox.com>
Implements the flow counters read wrapper.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 16 ++++++++++++++++
drivers/infiniband/hw/mlx5/mlx5_ib.h | 11 +++++++++++
2 files changed, 27 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3f1e957946e6..2044d9f69a83 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3150,7 +3150,21 @@ static void set_underlay_qp(struct mlx5_ib_dev *dev,
}
}
+static int read_flow_counters(struct ib_device *ibdev,
+ struct mlx5_read_counters_attr *read_attr)
+{
+ struct mlx5_fc *fc = (struct mlx5_fc *)(read_attr->hw_cntrs_hndl);
+ struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+ return mlx5_fc_query(dev->mdev, fc->id,
+ &read_attr->out[IB_COUNTER_PACKETS],
+ &read_attr->out[IB_COUNTER_BYTES]);
+}
+
#define MAX_COUNTERS_NUM (USHRT_MAX / (sizeof(u32) * 2))
+/* flow counters currently expose two counters packets and bytes */
+#define FLOW_COUNTERS_NUM 2
+
static int counters_set_description(struct ib_counters *counters,
enum mlx5_ib_counters_type counters_type,
const void __user *cntrs_data,
@@ -3182,6 +3196,8 @@ static int counters_set_description(struct ib_counters *counters,
/* init the fields for the object */
mcounters->type = counters_type;
+ mcounters->read_counters = read_flow_counters;
+ mcounters->counters_num = FLOW_COUNTERS_NUM;
mcounters->ncounters = ncounters;
desc = mcounters->counters_data;
for (i = 0; i < ncounters * 2; i += 2) {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 7313d3cd04f0..1baee579d84b 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -814,6 +814,12 @@ struct mlx5_memic {
DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES);
};
+struct mlx5_read_counters_attr {
+ void *hw_cntrs_hndl;
+ u64 *out;
+ u32 flags;
+};
+
enum mlx5_ib_counters_type {
MLX5_IB_COUNTERS_FLOW,
};
@@ -821,7 +827,12 @@ enum mlx5_ib_counters_type {
struct mlx5_ib_mcounters {
struct ib_counters ibcntrs;
enum mlx5_ib_counters_type type;
+ /* number of counters supported for this counters type */
+ u32 counters_num;
void *hw_cntrs_hndl;
+ /* read function for this counters type */
+ int (*read_counters)(struct ib_device *ibdev,
+ struct mlx5_read_counters_attr *read_attr);
/* max index set as part of create_flow */
u32 cntrs_max_index;
/* number of counters data entries (<description,index> pair) */
--
2.14.3
^ permalink raw reply related
* [PATCH rdma-next v1 13/13] IB/mlx5: Add counters read support
From: Leon Romanovsky @ 2018-05-27 10:23 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Boris Pismenny, Matan Barak,
Raed Salem, Yishai Hadas, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527102346.15149-1-leon@kernel.org>
From: Raed Salem <raeds@mellanox.com>
This patch implements the uverbs counters read API, it will use the
specific read counters function to the given type to accomplish its
task.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 44 +++++++++++++++++++++++++++++++++++++++
1 file changed, 44 insertions(+)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2044d9f69a83..ef688a265d47 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -5316,6 +5316,49 @@ static void depopulate_specs_root(struct mlx5_ib_dev *dev)
uverbs_free_spec_tree(dev->ib_dev.specs_root);
}
+static int mlx5_ib_read_counters(struct ib_counters *counters,
+ struct ib_counters_read_attr *read_attr,
+ struct uverbs_attr_bundle *attrs)
+{
+ struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
+ struct mlx5_read_counters_attr mread_attr = {};
+ u32 *desc;
+ int ret, i;
+
+ mutex_lock(&mcounters->mcntrs_mutex);
+ if (mcounters->cntrs_max_index > read_attr->ncounters) {
+ ret = -EINVAL;
+ goto err_bound;
+ }
+
+ mread_attr.out = kcalloc(mcounters->counters_num, sizeof(u64),
+ GFP_KERNEL);
+ if (!mread_attr.out) {
+ ret = -ENOMEM;
+ goto err_bound;
+ }
+
+ mread_attr.hw_cntrs_hndl = mcounters->hw_cntrs_hndl;
+ mread_attr.flags = read_attr->flags;
+ ret = mcounters->read_counters(counters->device, &mread_attr);
+ if (ret)
+ goto err_read;
+
+ /*
+ * We pass over the counters data array to assign according
+ * to the descriptions and indexing pairs.
+ */
+ desc = mcounters->counters_data;
+ for (i = 0; i < mcounters->ncounters * 2; i += 2)
+ read_attr->counters_buff[desc[i+1]] += mread_attr.out[desc[i]];
+
+err_read:
+ kfree(mread_attr.out);
+err_bound:
+ mutex_unlock(&mcounters->mcntrs_mutex);
+ return ret;
+}
+
static int mlx5_ib_destroy_counters(struct ib_counters *counters)
{
struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
@@ -5589,6 +5632,7 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
dev->ib_dev.driver_id = RDMA_DRIVER_MLX5;
dev->ib_dev.create_counters = mlx5_ib_create_counters;
dev->ib_dev.destroy_counters = mlx5_ib_destroy_counters;
+ dev->ib_dev.read_counters = mlx5_ib_read_counters;
err = init_node_data(dev);
if (err)
--
2.14.3
^ permalink raw reply related
* [PATCH rdma-next v1 08/13] IB/core: Add support for flow counters
From: Leon Romanovsky @ 2018-05-27 10:23 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Boris Pismenny, Matan Barak,
Raed Salem, Yishai Hadas, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527102346.15149-1-leon@kernel.org>
From: Raed Salem <raeds@mellanox.com>
A counters object could be attached to flow on creation
by providing the counter specification action.
General counters description which count packets and bytes are
introduced, downstream patches from this series will use them
as part of flow counters binding.
In addition, increase number of flow specifications supported
layers to 10 upon adding count specification and for the
previously added drop specification.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Raed Salem <raeds@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
include/rdma/ib_verbs.h | 15 ++++++++++++++-
1 file changed, 14 insertions(+), 1 deletion(-)
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 80956b1c9f4d..3acf7a9fa452 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1859,9 +1859,10 @@ enum ib_flow_spec_type {
IB_FLOW_SPEC_ACTION_TAG = 0x1000,
IB_FLOW_SPEC_ACTION_DROP = 0x1001,
IB_FLOW_SPEC_ACTION_HANDLE = 0x1002,
+ IB_FLOW_SPEC_ACTION_COUNT = 0x1003,
};
#define IB_FLOW_SPEC_LAYER_MASK 0xF0
-#define IB_FLOW_SPEC_SUPPORT_LAYERS 8
+#define IB_FLOW_SPEC_SUPPORT_LAYERS 10
/* Flow steering rule priority is set according to it's domain.
* Lower domain value means higher priority.
@@ -2041,6 +2042,17 @@ struct ib_flow_spec_action_handle {
struct ib_flow_action *act;
};
+enum ib_counters_description {
+ IB_COUNTER_PACKETS,
+ IB_COUNTER_BYTES,
+};
+
+struct ib_flow_spec_action_count {
+ enum ib_flow_spec_type type;
+ u16 size;
+ struct ib_counters *counters;
+};
+
union ib_flow_spec {
struct {
u32 type;
@@ -2058,6 +2070,7 @@ union ib_flow_spec {
struct ib_flow_spec_action_tag flow_tag;
struct ib_flow_spec_action_drop drop;
struct ib_flow_spec_action_handle action;
+ struct ib_flow_spec_action_count flow_count;
};
struct ib_flow_attr {
--
2.14.3
^ permalink raw reply related
* [PATCH rdma-next 0/3] Introduce new mlx5 CQE format
From: Leon Romanovsky @ 2018-05-27 10:42 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Guy Levi, Yishai Hadas,
Yonatan Cohen, Saeed Mahameed, linux-netdev
From: Leon Romanovsky <leonro@mellanox.com>
Introduce new internal to mlx5 CQE format - mini-CQE. It is a CQE in
compressed form that holds data needed to extra a single full CQE.
It stride index, byte count and packet checksum.
Thanks
Yonatan Cohen (3):
net/mlx5: Exposing a new mini-CQE format
IB/mlx5: Refactor CQE compression response
IB/mlx5: Introduce a new mini-CQE format
drivers/infiniband/hw/mlx5/cq.c | 42 +++++++++++++++++++++++++++++----------
drivers/infiniband/hw/mlx5/main.c | 20 +++++++++++++------
include/linux/mlx5/mlx5_ifc.h | 3 ++-
include/uapi/rdma/mlx5-abi.h | 2 +-
4 files changed, 49 insertions(+), 18 deletions(-)
^ permalink raw reply
* [PATCH mlx5-next 1/3] net/mlx5: Exposing a new mini-CQE format
From: Leon Romanovsky @ 2018-05-27 10:42 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Guy Levi, Yishai Hadas,
Yonatan Cohen, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527104234.17261-1-leon@kernel.org>
From: Yonatan Cohen <yonatanc@mellanox.com>
The new mini-CQE format includes byte-count, checksum
and stride index.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
include/linux/mlx5/mlx5_ifc.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ee8e5a0d0acf..1ea2827e94be 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1160,7 +1160,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
u8 flex_parser_protocols[0x20];
u8 reserved_at_560[0x20];
- u8 reserved_at_580[0x3d];
+ u8 reserved_at_580[0x3c];
+ u8 mini_cqe_resp_stride_index[0x1];
u8 cqe_128_always[0x1];
u8 cqe_compression_128[0x1];
u8 cqe_compression[0x1];
--
2.14.3
^ permalink raw reply related
* [PATCH rdma-next 2/3] IB/mlx5: Refactor CQE compression response
From: Leon Romanovsky @ 2018-05-27 10:42 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Guy Levi, Yishai Hadas,
Yonatan Cohen, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527104234.17261-1-leon@kernel.org>
From: Yonatan Cohen <yonatanc@mellanox.com>
Refactor CQE compression response to be fully set only
when it`s really supported. There is no change from user
perspective because anyway resp.cqe_comp_caps.max_num was
set to zero.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>W
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/hw/mlx5/main.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 59e080da32aa..95e67a85078c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -982,13 +982,17 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
}
if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
- resp.cqe_comp_caps.max_num =
- MLX5_CAP_GEN(dev->mdev, cqe_compression) ?
- MLX5_CAP_GEN(dev->mdev, cqe_compression_max_num) : 0;
- resp.cqe_comp_caps.supported_format =
- MLX5_IB_CQE_RES_FORMAT_HASH |
- MLX5_IB_CQE_RES_FORMAT_CSUM;
resp.response_length += sizeof(resp.cqe_comp_caps);
+
+ if (MLX5_CAP_GEN(dev->mdev, cqe_compression)) {
+ resp.cqe_comp_caps.max_num =
+ MLX5_CAP_GEN(dev->mdev,
+ cqe_compression_max_num);
+
+ resp.cqe_comp_caps.supported_format =
+ MLX5_IB_CQE_RES_FORMAT_HASH |
+ MLX5_IB_CQE_RES_FORMAT_CSUM;
+ }
}
if (field_avail(typeof(resp), packet_pacing_caps, uhw->outlen) &&
--
2.14.3
^ permalink raw reply related
* [PATCH rdma-next 3/3] IB/mlx5: Introduce a new mini-CQE format
From: Leon Romanovsky @ 2018-05-27 10:42 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Guy Levi, Yishai Hadas,
Yonatan Cohen, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527104234.17261-1-leon@kernel.org>
From: Yonatan Cohen <yonatanc@mellanox.com>
The new mini-CQE format includes the stride index, byte count and
packet checksum.
Stride index is needed for striding WQ feature.
This patch exposes this capability and enables its setting
via mlx5 UHW data as part of query device and cq creation.
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Guy Levi <guyle@mellanox.com>
Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/hw/mlx5/cq.c | 42 +++++++++++++++++++++++++++++----------
drivers/infiniband/hw/mlx5/main.c | 4 ++++
include/uapi/rdma/mlx5-abi.h | 2 +-
3 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 7b4ce1a19de0..ad39d64b8108 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -751,6 +751,28 @@ static int alloc_cq_frag_buf(struct mlx5_ib_dev *dev,
return 0;
}
+enum {
+ MLX5_CQE_RES_FORMAT_HASH = 0,
+ MLX5_CQE_RES_FORMAT_CSUM = 1,
+ MLX5_CQE_RES_FORMAT_CSUM_STRIDX = 3,
+};
+
+static int mini_cqe_res_format_to_hw(struct mlx5_ib_dev *dev, u8 format)
+{
+ switch (format) {
+ case MLX5_IB_CQE_RES_FORMAT_HASH:
+ return MLX5_CQE_RES_FORMAT_HASH;
+ case MLX5_IB_CQE_RES_FORMAT_CSUM:
+ return MLX5_CQE_RES_FORMAT_CSUM;
+ case MLX5_IB_CQE_RES_FORMAT_CSUM_STRIDX:
+ if (MLX5_CAP_GEN(dev->mdev, mini_cqe_resp_stride_index))
+ return MLX5_CQE_RES_FORMAT_CSUM_STRIDX;
+ return -EOPNOTSUPP;
+ default:
+ return -EINVAL;
+ }
+}
+
static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
struct ib_ucontext *context, struct mlx5_ib_cq *cq,
int entries, u32 **cqb,
@@ -816,6 +838,8 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
*index = to_mucontext(context)->bfregi.sys_pages[0];
if (ucmd.cqe_comp_en == 1) {
+ int mini_cqe_format;
+
if (!((*cqe_size == 128 &&
MLX5_CAP_GEN(dev->mdev, cqe_compression_128)) ||
(*cqe_size == 64 &&
@@ -826,20 +850,18 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
goto err_cqb;
}
- if (unlikely(!ucmd.cqe_comp_res_format ||
- !(ucmd.cqe_comp_res_format <
- MLX5_IB_CQE_RES_RESERVED) ||
- (ucmd.cqe_comp_res_format &
- (ucmd.cqe_comp_res_format - 1)))) {
- err = -EOPNOTSUPP;
- mlx5_ib_warn(dev, "CQE compression res format %d is not supported!\n",
- ucmd.cqe_comp_res_format);
+ mini_cqe_format =
+ mini_cqe_res_format_to_hw(dev,
+ ucmd.cqe_comp_res_format);
+ if (mini_cqe_format < 0) {
+ err = mini_cqe_format;
+ mlx5_ib_dbg(dev, "CQE compression res format %d error: %d\n",
+ ucmd.cqe_comp_res_format, err);
goto err_cqb;
}
MLX5_SET(cqc, cqc, cqe_comp_en, 1);
- MLX5_SET(cqc, cqc, mini_cqe_res_format,
- ilog2(ucmd.cqe_comp_res_format));
+ MLX5_SET(cqc, cqc, mini_cqe_res_format, mini_cqe_format);
}
if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_CQE_128B_PAD) {
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 95e67a85078c..238f1eed714c 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -992,6 +992,10 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
resp.cqe_comp_caps.supported_format =
MLX5_IB_CQE_RES_FORMAT_HASH |
MLX5_IB_CQE_RES_FORMAT_CSUM;
+
+ if (MLX5_CAP_GEN(dev->mdev, mini_cqe_resp_stride_index))
+ resp.cqe_comp_caps.supported_format |=
+ MLX5_IB_CQE_RES_FORMAT_CSUM_STRIDX;
}
}
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index beec971effef..a03b68b3e26c 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -166,7 +166,7 @@ struct mlx5_ib_rss_caps {
enum mlx5_ib_cqe_comp_res_format {
MLX5_IB_CQE_RES_FORMAT_HASH = 1 << 0,
MLX5_IB_CQE_RES_FORMAT_CSUM = 1 << 1,
- MLX5_IB_CQE_RES_RESERVED = 1 << 2,
+ MLX5_IB_CQE_RES_FORMAT_CSUM_STRIDX = 1 << 2,
};
struct mlx5_ib_cqe_comp_caps {
--
2.14.3
^ permalink raw reply related
* [PATCH v5 0/3] IR decoding using BPF
From: Sean Young @ 2018-05-27 11:24 UTC (permalink / raw)
To: linux-media, linux-kernel, Alexei Starovoitov,
Mauro Carvalho Chehab, Daniel Borkmann, netdev, Matthias Reichl,
Devin Heitmueller, Y Song, Quentin Monnet
The kernel IR decoders (drivers/media/rc/ir-*-decoder.c) support the most
widely used IR protocols, but there are many protocols which are not
supported[1]. For example, the lirc-remotes[2] repo has over 2700 remotes,
many of which are not supported by rc-core. There is a "long tail" of
unsupported IR protocols, for which lircd is need to decode the IR .
IR encoding is done in such a way that some simple circuit can decode it;
therefore, bpf is ideal.
In order to support all these protocols, here we have bpf based IR decoding.
The idea is that user-space can define a decoder in bpf, attach it to
the rc device through the lirc chardev.
Separate work is underway to extend ir-keytable to have an extensive library
of bpf-based decoders, and a much expanded library of rc keymaps.
Another future application would be to compile IRP[3] to a IR BPF program, and
so support virtually every remote without having to write a decoder for each.
It might also be possible to support non-button devices such as analog
directional pads or air conditioning remote controls and decode the target
temperature in bpf, and pass that to an input device.
Thanks,
Sean Young
[1] http://www.hifi-remote.com/wiki/index.php?title=DecodeIR
[2] https://sourceforge.net/p/lirc-remotes/code/ci/master/tree/remotes/
[3] http://www.hifi-remote.com/wiki/index.php?title=IRP_Notation
Changes since v4:
- Renamed rc_dev_bpf_{attach,detach,query} to lirc_bpf_{attach,detach,query}
- Fixed error path in lirc_bpf_query
- Rebased on bpf-next
Changes since v3:
- Implemented review comments from Quentin Monnet and Y Song (thanks!)
- More helpful and better formatted bpf helper documentation
- Changed back to bpf_prog_array rather than open-coded implementation
- scancodes can be 64 bit
- bpf gets passed values in microseconds, not nanoseconds.
microseconds is more than than enough (IR receivers support carriers upto
70kHz, at which point a single period is already 14 microseconds). Also,
this makes it much more consistent with lirc mode2.
- Since it looks much more like lirc mode2, rename the program type to
BPF_PROG_TYPE_LIRC_MODE2.
- Rebased on bpf-next
Changes since v2:
- Fixed locking issues
- Improved self-test to cover more cases
- Rebased on bpf-next again
Changes since v1:
- Code review comments from Y Song <ys114321@gmail.com> and
Randy Dunlap <rdunlap@infradead.org>
- Re-wrote sample bpf to be selftest
- Renamed RAWIR_DECODER -> RAWIR_EVENT (Kconfig, context, bpf prog type)
- Rebase on bpf-next
- Introduced bpf_rawir_event context structure with simpler access checking
Sean Young (3):
bpf: bpf_prog_array_copy() should return -ENOENT if exclude_prog not
found
media: rc: introduce BPF_PROG_LIRC_MODE2
bpf: add selftest for lirc_mode2 type program
drivers/media/rc/Kconfig | 13 +
drivers/media/rc/Makefile | 1 +
drivers/media/rc/bpf-lirc.c | 313 ++++++++++++++++++
drivers/media/rc/lirc_dev.c | 30 ++
drivers/media/rc/rc-core-priv.h | 21 ++
drivers/media/rc/rc-ir-raw.c | 12 +-
include/linux/bpf_lirc.h | 29 ++
include/linux/bpf_types.h | 3 +
include/uapi/linux/bpf.h | 53 ++-
kernel/bpf/core.c | 11 +-
kernel/bpf/syscall.c | 7 +
kernel/trace/bpf_trace.c | 2 +
tools/bpf/bpftool/prog.c | 1 +
tools/include/uapi/linux/bpf.h | 53 ++-
tools/include/uapi/linux/lirc.h | 217 ++++++++++++
tools/lib/bpf/libbpf.c | 1 +
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 7 +-
tools/testing/selftests/bpf/bpf_helpers.h | 5 +
.../testing/selftests/bpf/test_lirc_mode2.sh | 28 ++
.../selftests/bpf/test_lirc_mode2_kern.c | 23 ++
.../selftests/bpf/test_lirc_mode2_user.c | 149 +++++++++
22 files changed, 971 insertions(+), 9 deletions(-)
create mode 100644 drivers/media/rc/bpf-lirc.c
create mode 100644 include/linux/bpf_lirc.h
create mode 100644 tools/include/uapi/linux/lirc.h
create mode 100755 tools/testing/selftests/bpf/test_lirc_mode2.sh
create mode 100644 tools/testing/selftests/bpf/test_lirc_mode2_kern.c
create mode 100644 tools/testing/selftests/bpf/test_lirc_mode2_user.c
--
2.17.0
^ permalink raw reply
* [PATCH v5 1/3] bpf: bpf_prog_array_copy() should return -ENOENT if exclude_prog not found
From: Sean Young @ 2018-05-27 11:24 UTC (permalink / raw)
To: linux-media, linux-kernel, Alexei Starovoitov,
Mauro Carvalho Chehab, Daniel Borkmann, netdev, Matthias Reichl,
Devin Heitmueller, Y Song, Quentin Monnet
In-Reply-To: <cover.1527419762.git.sean@mess.org>
This makes is it possible for bpf prog detach to return -ENOENT.
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Sean Young <sean@mess.org>
---
kernel/bpf/core.c | 11 +++++++++--
kernel/trace/bpf_trace.c | 2 ++
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b574dddc05b8..527587de8a67 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1616,6 +1616,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
int new_prog_cnt, carry_prog_cnt = 0;
struct bpf_prog **existing_prog;
struct bpf_prog_array *array;
+ bool found_exclude = false;
int new_prog_idx = 0;
/* Figure out how many existing progs we need to carry over to
@@ -1624,14 +1625,20 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
if (old_array) {
existing_prog = old_array->progs;
for (; *existing_prog; existing_prog++) {
- if (*existing_prog != exclude_prog &&
- *existing_prog != &dummy_bpf_prog.prog)
+ if (*existing_prog == exclude_prog) {
+ found_exclude = true;
+ continue;
+ }
+ if (*existing_prog != &dummy_bpf_prog.prog)
carry_prog_cnt++;
if (*existing_prog == include_prog)
return -EEXIST;
}
}
+ if (exclude_prog && !found_exclude)
+ return -ENOENT;
+
/* How many progs (not NULL) will be in the new array? */
new_prog_cnt = carry_prog_cnt;
if (include_prog)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 81fdf2fc94ac..af1486d9a0ed 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1006,6 +1006,8 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
old_array = event->tp_event->prog_array;
ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
+ if (ret == -ENOENT)
+ goto unlock;
if (ret < 0) {
bpf_prog_array_delete_safe(old_array, event->prog);
} else {
--
2.17.0
^ permalink raw reply related
* [PATCH v5 2/3] media: rc: introduce BPF_PROG_LIRC_MODE2
From: Sean Young @ 2018-05-27 11:24 UTC (permalink / raw)
To: linux-media, linux-kernel, Alexei Starovoitov,
Mauro Carvalho Chehab, Daniel Borkmann, netdev, Matthias Reichl,
Devin Heitmueller, Y Song, Quentin Monnet
In-Reply-To: <cover.1527419762.git.sean@mess.org>
Add support for BPF_PROG_LIRC_MODE2. This type of BPF program can call
rc_keydown() to reported decoded IR scancodes, or rc_repeat() to report
that the last key should be repeated.
The bpf program can be attached to using the bpf(BPF_PROG_ATTACH) syscall;
the target_fd must be the /dev/lircN device.
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Sean Young <sean@mess.org>
---
drivers/media/rc/Kconfig | 13 ++
drivers/media/rc/Makefile | 1 +
drivers/media/rc/bpf-lirc.c | 313 ++++++++++++++++++++++++++++++++
drivers/media/rc/lirc_dev.c | 30 +++
drivers/media/rc/rc-core-priv.h | 21 +++
drivers/media/rc/rc-ir-raw.c | 12 +-
include/linux/bpf_lirc.h | 29 +++
include/linux/bpf_types.h | 3 +
include/uapi/linux/bpf.h | 53 +++++-
kernel/bpf/syscall.c | 7 +
10 files changed, 479 insertions(+), 3 deletions(-)
create mode 100644 drivers/media/rc/bpf-lirc.c
create mode 100644 include/linux/bpf_lirc.h
diff --git a/drivers/media/rc/Kconfig b/drivers/media/rc/Kconfig
index eb2c3b6eca7f..d5b35a6ba899 100644
--- a/drivers/media/rc/Kconfig
+++ b/drivers/media/rc/Kconfig
@@ -25,6 +25,19 @@ config LIRC
passes raw IR to and from userspace, which is needed for
IR transmitting (aka "blasting") and for the lirc daemon.
+config BPF_LIRC_MODE2
+ bool "Support for eBPF programs attached to lirc devices"
+ depends on BPF_SYSCALL
+ depends on RC_CORE=y
+ depends on LIRC
+ help
+ Allow attaching eBPF programs to a lirc device using the bpf(2)
+ syscall command BPF_PROG_ATTACH. This is supported for raw IR
+ receivers.
+
+ These eBPF programs can be used to decode IR into scancodes, for
+ IR protocols not supported by the kernel decoders.
+
menuconfig RC_DECODERS
bool "Remote controller decoders"
depends on RC_CORE
diff --git a/drivers/media/rc/Makefile b/drivers/media/rc/Makefile
index 2e1c87066f6c..e0340d043fe8 100644
--- a/drivers/media/rc/Makefile
+++ b/drivers/media/rc/Makefile
@@ -5,6 +5,7 @@ obj-y += keymaps/
obj-$(CONFIG_RC_CORE) += rc-core.o
rc-core-y := rc-main.o rc-ir-raw.o
rc-core-$(CONFIG_LIRC) += lirc_dev.o
+rc-core-$(CONFIG_BPF_LIRC_MODE2) += bpf-lirc.o
obj-$(CONFIG_IR_NEC_DECODER) += ir-nec-decoder.o
obj-$(CONFIG_IR_RC5_DECODER) += ir-rc5-decoder.o
obj-$(CONFIG_IR_RC6_DECODER) += ir-rc6-decoder.o
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
new file mode 100644
index 000000000000..40826bba06b6
--- /dev/null
+++ b/drivers/media/rc/bpf-lirc.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0
+// bpf-lirc.c - handles bpf
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/bpf_lirc.h>
+#include "rc-core-priv.h"
+
+/*
+ * BPF interface for raw IR
+ */
+const struct bpf_prog_ops lirc_mode2_prog_ops = {
+};
+
+BPF_CALL_1(bpf_rc_repeat, u32*, sample)
+{
+ struct ir_raw_event_ctrl *ctrl;
+
+ ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+ rc_repeat(ctrl->dev);
+
+ return 0;
+}
+
+static const struct bpf_func_proto rc_repeat_proto = {
+ .func = bpf_rc_repeat,
+ .gpl_only = true, /* rc_repeat is EXPORT_SYMBOL_GPL */
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
+/*
+ * Currently rc-core does not support 64-bit scancodes, but there are many
+ * known protocols with more than 32 bits. So, define the interface as u64
+ * as a future-proof.
+ */
+BPF_CALL_4(bpf_rc_keydown, u32*, sample, u32, protocol, u64, scancode,
+ u32, toggle)
+{
+ struct ir_raw_event_ctrl *ctrl;
+
+ ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample);
+
+ rc_keydown(ctrl->dev, protocol, scancode, toggle != 0);
+
+ return 0;
+}
+
+static const struct bpf_func_proto rc_keydown_proto = {
+ .func = bpf_rc_keydown,
+ .gpl_only = true, /* rc_keydown is EXPORT_SYMBOL_GPL */
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+ .arg3_type = ARG_ANYTHING,
+ .arg4_type = ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+ switch (func_id) {
+ case BPF_FUNC_rc_repeat:
+ return &rc_repeat_proto;
+ case BPF_FUNC_rc_keydown:
+ return &rc_keydown_proto;
+ case BPF_FUNC_map_lookup_elem:
+ return &bpf_map_lookup_elem_proto;
+ case BPF_FUNC_map_update_elem:
+ return &bpf_map_update_elem_proto;
+ case BPF_FUNC_map_delete_elem:
+ return &bpf_map_delete_elem_proto;
+ case BPF_FUNC_ktime_get_ns:
+ return &bpf_ktime_get_ns_proto;
+ case BPF_FUNC_tail_call:
+ return &bpf_tail_call_proto;
+ case BPF_FUNC_get_prandom_u32:
+ return &bpf_get_prandom_u32_proto;
+ case BPF_FUNC_trace_printk:
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
+ /* fall through */
+ default:
+ return NULL;
+ }
+}
+
+static bool lirc_mode2_is_valid_access(int off, int size,
+ enum bpf_access_type type,
+ const struct bpf_prog *prog,
+ struct bpf_insn_access_aux *info)
+{
+ /* We have one field of u32 */
+ return type == BPF_READ && off == 0 && size == sizeof(u32);
+}
+
+const struct bpf_verifier_ops lirc_mode2_verifier_ops = {
+ .get_func_proto = lirc_mode2_func_proto,
+ .is_valid_access = lirc_mode2_is_valid_access
+};
+
+#define BPF_MAX_PROGS 64
+
+static int lirc_bpf_attach(struct rc_dev *rcdev, struct bpf_prog *prog)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ struct ir_raw_event_ctrl *raw;
+ int ret;
+
+ if (rcdev->driver_type != RC_DRIVER_IR_RAW)
+ return -EINVAL;
+
+ ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+ if (ret)
+ return ret;
+
+ raw = rcdev->raw;
+ if (!raw) {
+ ret = -ENODEV;
+ goto unlock;
+ }
+
+ if (raw->progs && bpf_prog_array_length(raw->progs) >= BPF_MAX_PROGS) {
+ ret = -E2BIG;
+ goto unlock;
+ }
+
+ old_array = raw->progs;
+ ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array);
+ if (ret < 0)
+ goto unlock;
+
+ rcu_assign_pointer(raw->progs, new_array);
+ bpf_prog_array_free(old_array);
+
+unlock:
+ mutex_unlock(&ir_raw_handler_lock);
+ return ret;
+}
+
+static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog)
+{
+ struct bpf_prog_array __rcu *old_array;
+ struct bpf_prog_array *new_array;
+ struct ir_raw_event_ctrl *raw;
+ int ret;
+
+ if (rcdev->driver_type != RC_DRIVER_IR_RAW)
+ return -EINVAL;
+
+ ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+ if (ret)
+ return ret;
+
+ raw = rcdev->raw;
+ if (!raw) {
+ ret = -ENODEV;
+ goto unlock;
+ }
+
+ old_array = raw->progs;
+ ret = bpf_prog_array_copy(old_array, prog, NULL, &new_array);
+ /*
+ * Do not use bpf_prog_array_delete_safe() as we would end up
+ * with a dummy entry in the array, and the we would free the
+ * dummy in lirc_bpf_free()
+ */
+ if (ret)
+ goto unlock;
+
+ rcu_assign_pointer(raw->progs, new_array);
+ bpf_prog_array_free(old_array);
+unlock:
+ mutex_unlock(&ir_raw_handler_lock);
+ return ret;
+}
+
+void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
+{
+ struct ir_raw_event_ctrl *raw = rcdev->raw;
+
+ raw->bpf_sample = sample;
+
+ if (raw->progs)
+ BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, BPF_PROG_RUN);
+}
+
+/*
+ * This should be called once the rc thread has been stopped, so there can be
+ * no concurrent bpf execution.
+ */
+void lirc_bpf_free(struct rc_dev *rcdev)
+{
+ struct bpf_prog **progs;
+
+ if (!rcdev->raw->progs)
+ return;
+
+ progs = rcu_dereference(rcdev->raw->progs)->progs;
+ while (*progs)
+ bpf_prog_put(*progs++);
+
+ bpf_prog_array_free(rcdev->raw->progs);
+}
+
+int lirc_prog_attach(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ struct rc_dev *rcdev;
+ int ret;
+
+ if (attr->attach_flags)
+ return -EINVAL;
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd,
+ BPF_PROG_TYPE_LIRC_MODE2);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ rcdev = rc_dev_get_from_fd(attr->target_fd);
+ if (IS_ERR(rcdev)) {
+ bpf_prog_put(prog);
+ return PTR_ERR(rcdev);
+ }
+
+ ret = lirc_bpf_attach(rcdev, prog);
+ if (ret)
+ bpf_prog_put(prog);
+
+ put_device(&rcdev->dev);
+
+ return ret;
+}
+
+int lirc_prog_detach(const union bpf_attr *attr)
+{
+ struct bpf_prog *prog;
+ struct rc_dev *rcdev;
+ int ret;
+
+ if (attr->attach_flags)
+ return -EINVAL;
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd,
+ BPF_PROG_TYPE_LIRC_MODE2);
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
+
+ rcdev = rc_dev_get_from_fd(attr->target_fd);
+ if (IS_ERR(rcdev)) {
+ bpf_prog_put(prog);
+ return PTR_ERR(rcdev);
+ }
+
+ ret = lirc_bpf_detach(rcdev, prog);
+
+ bpf_prog_put(prog);
+ put_device(&rcdev->dev);
+
+ return ret;
+}
+
+int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
+{
+ __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+ struct bpf_prog_array __rcu *progs;
+ struct rc_dev *rcdev;
+ u32 cnt, flags = 0;
+ int ret;
+
+ if (attr->query.query_flags)
+ return -EINVAL;
+
+ rcdev = rc_dev_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(rcdev))
+ return PTR_ERR(rcdev);
+
+ if (rcdev->driver_type != RC_DRIVER_IR_RAW) {
+ ret = -EINVAL;
+ goto put;
+ }
+
+ ret = mutex_lock_interruptible(&ir_raw_handler_lock);
+ if (ret)
+ goto put;
+
+ progs = rcdev->raw->progs;
+ cnt = progs ? bpf_prog_array_length(progs) : 0;
+
+ if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) {
+ ret = -EFAULT;
+ goto unlock;
+ }
+
+ if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) {
+ ret = -EFAULT;
+ goto unlock;
+ }
+
+ if (attr->query.prog_cnt != 0 && prog_ids && cnt)
+ ret = bpf_prog_array_copy_to_user(progs, prog_ids, cnt);
+
+unlock:
+ mutex_unlock(&ir_raw_handler_lock);
+put:
+ put_device(&rcdev->dev);
+
+ return ret;
+}
diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
index 24e9fbb80e81..da7013a12a58 100644
--- a/drivers/media/rc/lirc_dev.c
+++ b/drivers/media/rc/lirc_dev.c
@@ -20,6 +20,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/device.h>
+#include <linux/file.h>
#include <linux/idr.h>
#include <linux/poll.h>
#include <linux/sched.h>
@@ -104,6 +105,12 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev)
TO_US(ev.duration), TO_STR(ev.pulse));
}
+ /*
+ * bpf does not care about the gap generated above; that exists
+ * for backwards compatibility
+ */
+ lirc_bpf_run(dev, sample);
+
spin_lock_irqsave(&dev->lirc_fh_lock, flags);
list_for_each_entry(fh, &dev->lirc_fh, list) {
if (LIRC_IS_TIMEOUT(sample) && !fh->send_timeout_reports)
@@ -816,4 +823,27 @@ void __exit lirc_dev_exit(void)
unregister_chrdev_region(lirc_base_dev, RC_DEV_MAX);
}
+struct rc_dev *rc_dev_get_from_fd(int fd)
+{
+ struct fd f = fdget(fd);
+ struct lirc_fh *fh;
+ struct rc_dev *dev;
+
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+
+ if (f.file->f_op != &lirc_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ fh = f.file->private_data;
+ dev = fh->rc;
+
+ get_device(&dev->dev);
+ fdput(f);
+
+ return dev;
+}
+
MODULE_ALIAS("lirc_dev");
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index e0e6a17460f6..eb004757038b 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -13,6 +13,7 @@
#define MAX_IR_EVENT_SIZE 512
#include <linux/slab.h>
+#include <uapi/linux/bpf.h>
#include <media/rc-core.h>
/**
@@ -57,6 +58,11 @@ struct ir_raw_event_ctrl {
/* raw decoder state follows */
struct ir_raw_event prev_ev;
struct ir_raw_event this_ev;
+
+#ifdef CONFIG_BPF_LIRC_MODE2
+ u32 bpf_sample;
+ struct bpf_prog_array __rcu *progs;
+#endif
struct nec_dec {
int state;
unsigned count;
@@ -126,6 +132,9 @@ struct ir_raw_event_ctrl {
} imon;
};
+/* Mutex for locking raw IR processing and handler change */
+extern struct mutex ir_raw_handler_lock;
+
/* macros for IR decoders */
static inline bool geq_margin(unsigned d1, unsigned d2, unsigned margin)
{
@@ -288,6 +297,7 @@ void ir_lirc_raw_event(struct rc_dev *dev, struct ir_raw_event ev);
void ir_lirc_scancode_event(struct rc_dev *dev, struct lirc_scancode *lsc);
int ir_lirc_register(struct rc_dev *dev);
void ir_lirc_unregister(struct rc_dev *dev);
+struct rc_dev *rc_dev_get_from_fd(int fd);
#else
static inline int lirc_dev_init(void) { return 0; }
static inline void lirc_dev_exit(void) {}
@@ -299,4 +309,15 @@ static inline int ir_lirc_register(struct rc_dev *dev) { return 0; }
static inline void ir_lirc_unregister(struct rc_dev *dev) { }
#endif
+/*
+ * bpf interface
+ */
+#ifdef CONFIG_BPF_LIRC_MODE2
+void lirc_bpf_free(struct rc_dev *dev);
+void lirc_bpf_run(struct rc_dev *dev, u32 sample);
+#else
+static inline void lirc_bpf_free(struct rc_dev *dev) { }
+static inline void lirc_bpf_run(struct rc_dev *dev, u32 sample) { }
+#endif
+
#endif /* _RC_CORE_PRIV */
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index 374f83105a23..7675b7ee5bc7 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -14,7 +14,7 @@
static LIST_HEAD(ir_raw_client_list);
/* Used to handle IR raw handler extensions */
-static DEFINE_MUTEX(ir_raw_handler_lock);
+DEFINE_MUTEX(ir_raw_handler_lock);
static LIST_HEAD(ir_raw_handler_list);
static atomic64_t available_protocols = ATOMIC64_INIT(0);
@@ -621,9 +621,17 @@ void ir_raw_event_unregister(struct rc_dev *dev)
list_for_each_entry(handler, &ir_raw_handler_list, list)
if (handler->raw_unregister)
handler->raw_unregister(dev);
- mutex_unlock(&ir_raw_handler_lock);
+
+ lirc_bpf_free(dev);
ir_raw_event_free(dev);
+
+ /*
+ * A user can be calling bpf(BPF_PROG_{QUERY|ATTACH|DETACH}), so
+ * ensure that the raw member is null on unlock; this is how
+ * "device gone" is checked.
+ */
+ mutex_unlock(&ir_raw_handler_lock);
}
/*
diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h
new file mode 100644
index 000000000000..5f8a4283092d
--- /dev/null
+++ b/include/linux/bpf_lirc.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _BPF_LIRC_H
+#define _BPF_LIRC_H
+
+#include <uapi/linux/bpf.h>
+
+#ifdef CONFIG_BPF_LIRC_MODE2
+int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_detach(const union bpf_attr *attr);
+int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
+#else
+static inline int lirc_prog_attach(const union bpf_attr *attr)
+{
+ return -EINVAL;
+}
+
+static inline int lirc_prog_detach(const union bpf_attr *attr)
+{
+ return -EINVAL;
+}
+
+static inline int lirc_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ return -EINVAL;
+}
+#endif
+
+#endif /* _BPF_LIRC_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index b161e506dcfc..c5700c2d5549 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -26,6 +26,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
#ifdef CONFIG_CGROUP_BPF
BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
#endif
+#ifdef CONFIG_BPF_LIRC_MODE2
+BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
+#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9b8c6e310e9a..4636c596096d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -143,6 +143,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT,
BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_PROG_TYPE_LWT_SEG6LOCAL,
+ BPF_PROG_TYPE_LIRC_MODE2,
};
enum bpf_attach_type {
@@ -160,6 +161,7 @@ enum bpf_attach_type {
BPF_CGROUP_INET6_CONNECT,
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
+ BPF_LIRC_MODE2,
__MAX_BPF_ATTACH_TYPE
};
@@ -2004,6 +2006,53 @@ union bpf_attr {
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown** () again with the same values, or calling
+ * **bpf_rc_repeat** ().
+ *
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ *
+ * Return
+ * 0
+ *
+ * int bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ *
+ * Return
+ * 0
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2082,7 +2131,9 @@ union bpf_attr {
FN(lwt_push_encap), \
FN(lwt_seg6_store_bytes), \
FN(lwt_seg6_adjust_srh), \
- FN(lwt_seg6_action),
+ FN(lwt_seg6_action), \
+ FN(rc_repeat), \
+ FN(rc_keydown),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 388d4feda348..3c104113d040 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -11,6 +11,7 @@
*/
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
+#include <linux/bpf_lirc.h>
#include <linux/btf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
@@ -1578,6 +1579,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ case BPF_LIRC_MODE2:
+ return lirc_prog_attach(attr);
default:
return -EINVAL;
}
@@ -1648,6 +1651,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ case BPF_LIRC_MODE2:
+ return lirc_prog_detach(attr);
default:
return -EINVAL;
}
@@ -1695,6 +1700,8 @@ static int bpf_prog_query(const union bpf_attr *attr,
case BPF_CGROUP_SOCK_OPS:
case BPF_CGROUP_DEVICE:
break;
+ case BPF_LIRC_MODE2:
+ return lirc_prog_query(attr, uattr);
default:
return -EINVAL;
}
--
2.17.0
^ permalink raw reply related
* [PATCH v5 3/3] bpf: add selftest for lirc_mode2 type program
From: Sean Young @ 2018-05-27 11:24 UTC (permalink / raw)
To: linux-media, linux-kernel, Alexei Starovoitov,
Mauro Carvalho Chehab, Daniel Borkmann, netdev, Matthias Reichl,
Devin Heitmueller, Y Song, Quentin Monnet
In-Reply-To: <cover.1527419762.git.sean@mess.org>
This is simple test over rc-loopback.
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Sean Young <sean@mess.org>
---
tools/bpf/bpftool/prog.c | 1 +
tools/include/uapi/linux/bpf.h | 53 ++++-
tools/include/uapi/linux/lirc.h | 217 ++++++++++++++++++
tools/lib/bpf/libbpf.c | 1 +
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 7 +-
tools/testing/selftests/bpf/bpf_helpers.h | 5 +
.../testing/selftests/bpf/test_lirc_mode2.sh | 28 +++
.../selftests/bpf/test_lirc_mode2_kern.c | 23 ++
.../selftests/bpf/test_lirc_mode2_user.c | 149 ++++++++++++
10 files changed, 481 insertions(+), 4 deletions(-)
create mode 100644 tools/include/uapi/linux/lirc.h
create mode 100755 tools/testing/selftests/bpf/test_lirc_mode2.sh
create mode 100644 tools/testing/selftests/bpf/test_lirc_mode2_kern.c
create mode 100644 tools/testing/selftests/bpf/test_lirc_mode2_user.c
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 39b88e760367..a4f435203fef 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -71,6 +71,7 @@ static const char * const prog_type_name[] = {
[BPF_PROG_TYPE_SK_MSG] = "sk_msg",
[BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint",
[BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr",
+ [BPF_PROG_TYPE_LIRC_MODE2] = "lirc_mode2",
};
static void print_boot_time(__u64 nsecs, char *buf, unsigned int size)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9b8c6e310e9a..4636c596096d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -143,6 +143,7 @@ enum bpf_prog_type {
BPF_PROG_TYPE_RAW_TRACEPOINT,
BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
BPF_PROG_TYPE_LWT_SEG6LOCAL,
+ BPF_PROG_TYPE_LIRC_MODE2,
};
enum bpf_attach_type {
@@ -160,6 +161,7 @@ enum bpf_attach_type {
BPF_CGROUP_INET6_CONNECT,
BPF_CGROUP_INET4_POST_BIND,
BPF_CGROUP_INET6_POST_BIND,
+ BPF_LIRC_MODE2,
__MAX_BPF_ATTACH_TYPE
};
@@ -2004,6 +2006,53 @@ union bpf_attr {
* direct packet access.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded key press with *scancode*,
+ * *toggle* value in the given *protocol*. The scancode will be
+ * translated to a keycode using the rc keymap, and reported as
+ * an input key down event. After a period a key up event is
+ * generated. This period can be extended by calling either
+ * **bpf_rc_keydown** () again with the same values, or calling
+ * **bpf_rc_repeat** ().
+ *
+ * Some protocols include a toggle bit, in case the button was
+ * released and pressed again between consecutive scancodes.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * The *protocol* is the decoded protocol number (see
+ * **enum rc_proto** for some predefined values).
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ *
+ * Return
+ * 0
+ *
+ * int bpf_rc_repeat(void *ctx)
+ * Description
+ * This helper is used in programs implementing IR decoding, to
+ * report a successfully decoded repeat key message. This delays
+ * the generation of a key up event for previously generated
+ * key down event.
+ *
+ * Some IR protocols like NEC have a special IR message for
+ * repeating last button, for when a button is held down.
+ *
+ * The *ctx* should point to the lirc sample as passed into
+ * the program.
+ *
+ * This helper is only available is the kernel was compiled with
+ * the **CONFIG_BPF_LIRC_MODE2** configuration option set to
+ * "**y**".
+ *
+ * Return
+ * 0
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -2082,7 +2131,9 @@ union bpf_attr {
FN(lwt_push_encap), \
FN(lwt_seg6_store_bytes), \
FN(lwt_seg6_adjust_srh), \
- FN(lwt_seg6_action),
+ FN(lwt_seg6_action), \
+ FN(rc_repeat), \
+ FN(rc_keydown),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
diff --git a/tools/include/uapi/linux/lirc.h b/tools/include/uapi/linux/lirc.h
new file mode 100644
index 000000000000..f189931042a7
--- /dev/null
+++ b/tools/include/uapi/linux/lirc.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * lirc.h - linux infrared remote control header file
+ * last modified 2010/07/13 by Jarod Wilson
+ */
+
+#ifndef _LINUX_LIRC_H
+#define _LINUX_LIRC_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define PULSE_BIT 0x01000000
+#define PULSE_MASK 0x00FFFFFF
+
+#define LIRC_MODE2_SPACE 0x00000000
+#define LIRC_MODE2_PULSE 0x01000000
+#define LIRC_MODE2_FREQUENCY 0x02000000
+#define LIRC_MODE2_TIMEOUT 0x03000000
+
+#define LIRC_VALUE_MASK 0x00FFFFFF
+#define LIRC_MODE2_MASK 0xFF000000
+
+#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE)
+#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE)
+#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY)
+#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT)
+
+#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK)
+#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK)
+
+#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE)
+#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE)
+#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY)
+#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT)
+
+/* used heavily by lirc userspace */
+#define lirc_t int
+
+/*** lirc compatible hardware features ***/
+
+#define LIRC_MODE2SEND(x) (x)
+#define LIRC_SEND2MODE(x) (x)
+#define LIRC_MODE2REC(x) ((x) << 16)
+#define LIRC_REC2MODE(x) ((x) >> 16)
+
+#define LIRC_MODE_RAW 0x00000001
+#define LIRC_MODE_PULSE 0x00000002
+#define LIRC_MODE_MODE2 0x00000004
+#define LIRC_MODE_SCANCODE 0x00000008
+#define LIRC_MODE_LIRCCODE 0x00000010
+
+
+#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW)
+#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE)
+#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2)
+#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_SEND_MASK 0x0000003f
+
+#define LIRC_CAN_SET_SEND_CARRIER 0x00000100
+#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200
+#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400
+
+#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW)
+#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE)
+#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2)
+#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE)
+#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE)
+
+#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK)
+
+#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16)
+#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16)
+
+#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000
+#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000
+#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000
+#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000
+#define LIRC_CAN_SET_REC_FILTER 0x08000000
+
+#define LIRC_CAN_MEASURE_CARRIER 0x02000000
+#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000
+
+#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK)
+#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK)
+
+#define LIRC_CAN_NOTIFY_DECODE 0x01000000
+
+/*** IOCTL commands for lirc driver ***/
+
+#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32)
+
+#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32)
+#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32)
+#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32)
+
+#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32)
+#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32)
+
+/* code length in bits, currently only for LIRC_MODE_LIRCCODE */
+#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32)
+
+#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32)
+#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32)
+/* Note: these can reset the according pulse_width */
+#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32)
+#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32)
+#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32)
+#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32)
+
+/*
+ * when a timeout != 0 is set the driver will send a
+ * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is
+ * never sent, timeout is disabled by default
+ */
+#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32)
+
+/* 1 enables, 0 disables timeout reports in MODE2 */
+#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32)
+
+/*
+ * if enabled from the next key press on the driver will send
+ * LIRC_MODE2_FREQUENCY packets
+ */
+#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32)
+
+/*
+ * to set a range use LIRC_SET_REC_CARRIER_RANGE with the
+ * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound
+ */
+#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32)
+
+#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32)
+
+/*
+ * struct lirc_scancode - decoded scancode with protocol for use with
+ * LIRC_MODE_SCANCODE
+ *
+ * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR
+ * was decoded.
+ * @flags: should be 0 for transmit. When receiving scancodes,
+ * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set
+ * depending on the protocol
+ * @rc_proto: see enum rc_proto
+ * @keycode: the translated keycode. Set to 0 for transmit.
+ * @scancode: the scancode received or to be sent
+ */
+struct lirc_scancode {
+ __u64 timestamp;
+ __u16 flags;
+ __u16 rc_proto;
+ __u32 keycode;
+ __u64 scancode;
+};
+
+/* Set if the toggle bit of rc-5 or rc-6 is enabled */
+#define LIRC_SCANCODE_FLAG_TOGGLE 1
+/* Set if this is a nec or sanyo repeat */
+#define LIRC_SCANCODE_FLAG_REPEAT 2
+
+/**
+ * enum rc_proto - the Remote Controller protocol
+ *
+ * @RC_PROTO_UNKNOWN: Protocol not known
+ * @RC_PROTO_OTHER: Protocol known but proprietary
+ * @RC_PROTO_RC5: Philips RC5 protocol
+ * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol
+ * @RC_PROTO_RC5_SZ: StreamZap variant of RC5
+ * @RC_PROTO_JVC: JVC protocol
+ * @RC_PROTO_SONY12: Sony 12 bit protocol
+ * @RC_PROTO_SONY15: Sony 15 bit protocol
+ * @RC_PROTO_SONY20: Sony 20 bit protocol
+ * @RC_PROTO_NEC: NEC protocol
+ * @RC_PROTO_NECX: Extended NEC protocol
+ * @RC_PROTO_NEC32: NEC 32 bit protocol
+ * @RC_PROTO_SANYO: Sanyo protocol
+ * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard
+ * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse
+ * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol
+ * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol
+ * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol
+ * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol
+ * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol
+ * @RC_PROTO_SHARP: Sharp protocol
+ * @RC_PROTO_XMP: XMP protocol
+ * @RC_PROTO_CEC: CEC protocol
+ * @RC_PROTO_IMON: iMon Pad protocol
+ */
+enum rc_proto {
+ RC_PROTO_UNKNOWN = 0,
+ RC_PROTO_OTHER = 1,
+ RC_PROTO_RC5 = 2,
+ RC_PROTO_RC5X_20 = 3,
+ RC_PROTO_RC5_SZ = 4,
+ RC_PROTO_JVC = 5,
+ RC_PROTO_SONY12 = 6,
+ RC_PROTO_SONY15 = 7,
+ RC_PROTO_SONY20 = 8,
+ RC_PROTO_NEC = 9,
+ RC_PROTO_NECX = 10,
+ RC_PROTO_NEC32 = 11,
+ RC_PROTO_SANYO = 12,
+ RC_PROTO_MCIR2_KBD = 13,
+ RC_PROTO_MCIR2_MSE = 14,
+ RC_PROTO_RC6_0 = 15,
+ RC_PROTO_RC6_6A_20 = 16,
+ RC_PROTO_RC6_6A_24 = 17,
+ RC_PROTO_RC6_6A_32 = 18,
+ RC_PROTO_RC6_MCE = 19,
+ RC_PROTO_SHARP = 20,
+ RC_PROTO_XMP = 21,
+ RC_PROTO_CEC = 22,
+ RC_PROTO_IMON = 23,
+};
+
+#endif
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d20411ebfa2f..6cb45898afa7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1462,6 +1462,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_SK_MSG:
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_LIRC_MODE2:
return false;
case BPF_PROG_TYPE_UNSPEC:
case BPF_PROG_TYPE_KPROBE:
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index adc8e5474b66..6ea835982464 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -17,3 +17,4 @@ test_sock_addr
urandom_read
test_btf
test_sockmap
+test_lirc_mode2_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 85044448bbc7..06400291e6e2 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -24,7 +24,7 @@ urandom_read: urandom_read.c
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
- test_sock test_btf test_sockmap
+ test_sock test_btf test_sockmap test_lirc_mode2_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
@@ -34,7 +34,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
- test_lwt_seg6local.o
+ test_lwt_seg6local.o test_lirc_mode2_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -44,7 +44,8 @@ TEST_PROGS := test_kmod.sh \
test_offload.py \
test_sock_addr.sh \
test_tunnel.sh \
- test_lwt_seg6local.sh
+ test_lwt_seg6local.sh \
+ test_lirc_mode2.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 334d3e8c5e89..a66a9d91acf4 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -126,6 +126,11 @@ static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param,
static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset,
unsigned int len) =
(void *) BPF_FUNC_lwt_seg6_adjust_srh;
+static int (*bpf_rc_repeat)(void *ctx) =
+ (void *) BPF_FUNC_rc_repeat;
+static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
+ unsigned long long scancode, unsigned int toggle) =
+ (void *) BPF_FUNC_rc_keydown;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
new file mode 100755
index 000000000000..ce2e15e4f976
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+GREEN='\033[0;92m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+modprobe rc-loopback
+
+for i in /sys/class/rc/rc*
+do
+ if grep -q DRV_NAME=rc-loopback $i/uevent
+ then
+ LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
+ fi
+done
+
+if [ -n $LIRCDEV ];
+then
+ TYPE=lirc_mode2
+ ./test_lirc_mode2_user $LIRCDEV
+ ret=$?
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ else
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+ fi
+fi
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
new file mode 100644
index 000000000000..ba26855563a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+#include <linux/bpf.h>
+#include <linux/lirc.h>
+#include "bpf_helpers.h"
+
+SEC("lirc_mode2")
+int bpf_decoder(unsigned int *sample)
+{
+ if (LIRC_IS_PULSE(*sample)) {
+ unsigned int duration = LIRC_VALUE(*sample);
+
+ if (duration & 0x10000)
+ bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
+ }
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
new file mode 100644
index 000000000000..d470d63c33db
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+// A lirc chardev is a device representing a consumer IR (cir) device which
+// can receive infrared signals from remote control and/or transmit IR.
+//
+// IR is sent as a series of pulses and space somewhat like morse code. The
+// BPF program can decode this into scancodes so that rc-core can translate
+// this into input key codes using the rc keymap.
+//
+// This test works by sending IR over rc-loopback, so the IR is processed by
+// BPF and then decoded into scancodes. The lirc chardev must be the one
+// associated with rc-loopback, see the output of ir-keytable(1).
+//
+// The following CONFIG options must be enabled for the test to succeed:
+// CONFIG_RC_CORE=y
+// CONFIG_BPF_RAWIR_EVENT=y
+// CONFIG_RC_LOOPBACK=y
+
+// Steps:
+// 1. Open the /dev/lircN device for rc-loopback (given on command line)
+// 2. Attach bpf_lirc_mode2 program which decodes some IR.
+// 3. Send some IR to the same IR device; since it is loopback, this will
+// end up in the bpf program
+// 4. bpf program should decode IR and report keycode
+// 5. We can read keycode from same /dev/lirc device
+
+#include <linux/bpf.h>
+#include <linux/lirc.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+int main(int argc, char **argv)
+{
+ struct bpf_object *obj;
+ int ret, lircfd, progfd, mode;
+ int testir = 0x1dead;
+ u32 prog_ids[10], prog_flags[10], prog_cnt;
+
+ if (argc != 2) {
+ printf("Usage: %s /dev/lircN\n", argv[0]);
+ return 2;
+ }
+
+ ret = bpf_prog_load("test_lirc_mode2_kern.o",
+ BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd);
+ if (ret) {
+ printf("Failed to load bpf program\n");
+ return 1;
+ }
+
+ lircfd = open(argv[1], O_RDWR | O_NONBLOCK);
+ if (lircfd == -1) {
+ printf("failed to open lirc device %s: %m\n", argv[1]);
+ return 1;
+ }
+
+ /* Let's try detach it before it was ever attached */
+ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+ if (ret != -1 || errno != ENOENT) {
+ printf("bpf_prog_detach2 not attached should fail: %m\n");
+ return 1;
+ }
+
+ mode = LIRC_MODE_SCANCODE;
+ if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) {
+ printf("failed to set rec mode: %m\n");
+ return 1;
+ }
+
+ prog_cnt = 10;
+ ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+ &prog_cnt);
+ if (ret) {
+ printf("Failed to query bpf programs on lirc device: %m\n");
+ return 1;
+ }
+
+ if (prog_cnt != 0) {
+ printf("Expected nothing to be attached\n");
+ return 1;
+ }
+
+ ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0);
+ if (ret) {
+ printf("Failed to attach bpf to lirc device: %m\n");
+ return 1;
+ }
+
+ /* Write raw IR */
+ ret = write(lircfd, &testir, sizeof(testir));
+ if (ret != sizeof(testir)) {
+ printf("Failed to send test IR message: %m\n");
+ return 1;
+ }
+
+ struct pollfd pfd = { .fd = lircfd, .events = POLLIN };
+ struct lirc_scancode lsc;
+
+ poll(&pfd, 1, 100);
+
+ /* Read decoded IR */
+ ret = read(lircfd, &lsc, sizeof(lsc));
+ if (ret != sizeof(lsc)) {
+ printf("Failed to read decoded IR: %m\n");
+ return 1;
+ }
+
+ if (lsc.scancode != 0xdead || lsc.rc_proto != 64) {
+ printf("Incorrect scancode decoded\n");
+ return 1;
+ }
+
+ prog_cnt = 10;
+ ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+ &prog_cnt);
+ if (ret) {
+ printf("Failed to query bpf programs on lirc device: %m\n");
+ return 1;
+ }
+
+ if (prog_cnt != 1) {
+ printf("Expected one program to be attached\n");
+ return 1;
+ }
+
+ /* Let's try detaching it now it is actually attached */
+ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+ if (ret) {
+ printf("bpf_prog_detach2: returned %m\n");
+ return 1;
+ }
+
+ return 0;
+}
--
2.17.0
^ permalink raw reply related
* [PATCH bpf 0/2] Use __aligned_u64 in UAPI fields
From: Eugene Syromiatnikov @ 2018-05-27 11:28 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, Martin KaFai Lau, Daniel Borkmann,
Alexei Starovoitov, David S. Miller, Jiri Olsa, Ingo Molnar,
Lawrence Brakmo, Andrey Ignatov, Jakub Kicinski, John Fastabend,
Dmitry V. Levin
Hello.
It was discovered during strace development that struct bpf_map_info and
struct bpf_prog_info now have different layouts of i386/compat and x86_64.
Since it's already broken and bpf syscall has no separate compat (as
far as I can see), and the affecting change was introduced recently (in
Linux 4.16), it's proposed to change the layout of these structures
on 32-bit architectures by using __aligned_u64.
In order to somewhat future-proof from this problem in future, an
approach similar to the one implemented in RDMA subsystem recently
is proposed: use __aligned_u64 consistently throughout the UAPI header.
Eugene Syromiatnikov (2):
bpf: fix alignment of netns_dev/netns_ino fields in
bpf_{map,prog}_info
bpf: enforce usage of __aligned_u64 in the UAPI header
include/uapi/linux/bpf.h | 30 +++++++++++++++---------------
tools/include/uapi/linux/bpf.h | 30 +++++++++++++++---------------
2 files changed, 30 insertions(+), 30 deletions(-)
--
2.1.4
^ permalink raw reply
* [PATCH bpf 1/2] bpf: fix alignment of netns_dev/netns_ino fields in bpf_{map,prog}_info
From: Eugene Syromiatnikov @ 2018-05-27 11:28 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, Martin KaFai Lau, Daniel Borkmann,
Alexei Starovoitov, David S. Miller, Jiri Olsa, Ingo Molnar,
Lawrence Brakmo, Andrey Ignatov, Jakub Kicinski, John Fastabend,
Dmitry V. Levin
Recent introduction of netns_dev/netns_ino to bpf_map_info/bpf_prog info
has broken compat, as offsets of these fields are different in 32-bit
and 64-bit ABIs. One fix (other than implementing compat support in
syscall in order to handle this discrepancy) is to use __aligned_u64
instead of __u64 for these fields.
Reported-by: Dmitry V. Levin <ldv@altlinux.org>
Fixes: 52775b33bb507 ("bpf: offload: report device information about
offloaded maps")
Fixes: 675fc275a3a2d ("bpf: offload: report device information for
offloaded programs")
Signed-off-by: Eugene Syromiatnikov <esyr@redhat.com>
---
include/uapi/linux/bpf.h | 8 ++++----
tools/include/uapi/linux/bpf.h | 8 ++++----
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index c5ec897..903010a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1017,8 +1017,8 @@ struct bpf_prog_info {
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u64 netns_dev;
- __u64 netns_ino;
+ __aligned_u64 netns_dev;
+ __aligned_u64 netns_ino;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -1030,8 +1030,8 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u64 netns_dev;
- __u64 netns_ino;
+ __aligned_u64 netns_dev;
+ __aligned_u64 netns_ino;
} __attribute__((aligned(8)));
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c5ec897..903010a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1017,8 +1017,8 @@ struct bpf_prog_info {
__aligned_u64 map_ids;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u64 netns_dev;
- __u64 netns_ino;
+ __aligned_u64 netns_dev;
+ __aligned_u64 netns_ino;
} __attribute__((aligned(8)));
struct bpf_map_info {
@@ -1030,8 +1030,8 @@ struct bpf_map_info {
__u32 map_flags;
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
- __u64 netns_dev;
- __u64 netns_ino;
+ __aligned_u64 netns_dev;
+ __aligned_u64 netns_ino;
} __attribute__((aligned(8)));
/* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
--
2.1.4
^ permalink raw reply related
* [PATCH bpf 2/2] bpf: enforce usage of __aligned_u64 in the UAPI header
From: Eugene Syromiatnikov @ 2018-05-27 11:28 UTC (permalink / raw)
To: netdev
Cc: linux-kernel, Martin KaFai Lau, Daniel Borkmann,
Alexei Starovoitov, David S. Miller, Jiri Olsa, Ingo Molnar,
Lawrence Brakmo, Andrey Ignatov, Jakub Kicinski, John Fastabend,
Dmitry V. Levin
Use __aligned_u64 instead of __u64 everywhere in the UAPI header,
similarly to v4.17-rc1~94^2~58^2 "RDMA: Change all uapi headers to use
__aligned_u64 instead of __u64".
This commit doesn't change structure layouts, but imposes additional
alignment requirements on struct bpf_stack_build_id, struct
bpf_sock_ops, struct bpf_perf_event_value, and struct
bpf_raw_tracepoint_args; of them only struct bpf_sock_ops and struct
bpf_perf_event_value have 64-bit fields that were present in a released
kernel without this additional alignment requirement (bytes_received
and bytes_acked were added to struct bpf_sock_ops in commit
v4.16-rc1~123^2~33^2~5^2~4, struct bpf_perf_event_value was added
in commit v4.15-rc1~84^2~532^2~3).
Signed-off-by: Eugene Syromiatnikov <esyr@redhat.com>
---
include/uapi/linux/bpf.h | 22 +++++++++++-----------
tools/include/uapi/linux/bpf.h | 22 +++++++++++-----------
2 files changed, 22 insertions(+), 22 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 903010a..174e99a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -259,8 +259,8 @@ struct bpf_stack_build_id {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
- __u64 offset;
- __u64 ip;
+ __aligned_u64 offset;
+ __aligned_u64 ip;
};
};
@@ -288,7 +288,7 @@ union bpf_attr {
__aligned_u64 value;
__aligned_u64 next_key;
};
- __u64 flags;
+ __aligned_u64 flags;
};
struct { /* anonymous struct used by BPF_PROG_LOAD command */
@@ -360,7 +360,7 @@ union bpf_attr {
} query;
struct {
- __u64 name;
+ __aligned_u64 name;
__u32 prog_fd;
} raw_tracepoint;
} __attribute__((aligned(8)));
@@ -1011,7 +1011,7 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
- __u64 load_time; /* ns since boottime */
+ __aligned_u64 load_time; /* ns since boottime */
__u32 created_by_uid;
__u32 nr_map_ids;
__aligned_u64 map_ids;
@@ -1101,8 +1101,8 @@ struct bpf_sock_ops {
__u32 lost_out;
__u32 sacked_out;
__u32 sk_txhash;
- __u64 bytes_received;
- __u64 bytes_acked;
+ __aligned_u64 bytes_received;
+ __aligned_u64 bytes_acked;
};
/* Definitions for bpf_sock_ops_cb_flags */
@@ -1189,9 +1189,9 @@ enum {
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
struct bpf_perf_event_value {
- __u64 counter;
- __u64 enabled;
- __u64 running;
+ __aligned_u64 counter;
+ __aligned_u64 enabled;
+ __aligned_u64 running;
};
#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
@@ -1209,7 +1209,7 @@ struct bpf_cgroup_dev_ctx {
};
struct bpf_raw_tracepoint_args {
- __u64 args[0];
+ __aligned_u64 args[0];
};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 903010a..174e99a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -259,8 +259,8 @@ struct bpf_stack_build_id {
__s32 status;
unsigned char build_id[BPF_BUILD_ID_SIZE];
union {
- __u64 offset;
- __u64 ip;
+ __aligned_u64 offset;
+ __aligned_u64 ip;
};
};
@@ -288,7 +288,7 @@ union bpf_attr {
__aligned_u64 value;
__aligned_u64 next_key;
};
- __u64 flags;
+ __aligned_u64 flags;
};
struct { /* anonymous struct used by BPF_PROG_LOAD command */
@@ -360,7 +360,7 @@ union bpf_attr {
} query;
struct {
- __u64 name;
+ __aligned_u64 name;
__u32 prog_fd;
} raw_tracepoint;
} __attribute__((aligned(8)));
@@ -1011,7 +1011,7 @@ struct bpf_prog_info {
__u32 xlated_prog_len;
__aligned_u64 jited_prog_insns;
__aligned_u64 xlated_prog_insns;
- __u64 load_time; /* ns since boottime */
+ __aligned_u64 load_time; /* ns since boottime */
__u32 created_by_uid;
__u32 nr_map_ids;
__aligned_u64 map_ids;
@@ -1101,8 +1101,8 @@ struct bpf_sock_ops {
__u32 lost_out;
__u32 sacked_out;
__u32 sk_txhash;
- __u64 bytes_received;
- __u64 bytes_acked;
+ __aligned_u64 bytes_received;
+ __aligned_u64 bytes_acked;
};
/* Definitions for bpf_sock_ops_cb_flags */
@@ -1189,9 +1189,9 @@ enum {
#define TCP_BPF_SNDCWND_CLAMP 1002 /* Set sndcwnd_clamp */
struct bpf_perf_event_value {
- __u64 counter;
- __u64 enabled;
- __u64 running;
+ __aligned_u64 counter;
+ __aligned_u64 enabled;
+ __aligned_u64 running;
};
#define BPF_DEVCG_ACC_MKNOD (1ULL << 0)
@@ -1209,7 +1209,7 @@ struct bpf_cgroup_dev_ctx {
};
struct bpf_raw_tracepoint_args {
- __u64 args[0];
+ __aligned_u64 args[0];
};
#endif /* _UAPI__LINUX_BPF_H__ */
--
2.1.4
^ permalink raw reply related
* Re: [PATCH net] mlxsw: spectrum: Forbid creation of VLAN 1 over port/LAG
From: Jiri Pirko @ 2018-05-27 12:26 UTC (permalink / raw)
To: Ido Schimmel; +Cc: netdev, davem, jiri, petrm, mlxsw
In-Reply-To: <20180527064841.32199-1-idosch@mellanox.com>
Sun, May 27, 2018 at 08:48:41AM CEST, idosch@mellanox.com wrote:
>From: Petr Machata <petrm@mellanox.com>
>
>VLAN 1 is internally used for untagged traffic. Prevent creation of
>explicit netdevice for that VLAN, because that currently isn't supported
>and leads to the NULL pointer dereference cited below.
>
>Fix by preventing creation of VLAN devices with VID of 1 over mlxsw
>devices or LAG devices that involve mlxsw devices.
>
>[ 327.175816] ================================================================================
>[ 327.184544] UBSAN: Undefined behaviour in drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c:200:12
>[ 327.193667] member access within null pointer of type 'const struct mlxsw_sp_fid'
>[ 327.201226] CPU: 0 PID: 8983 Comm: ip Not tainted 4.17.0-rc4-petrm_net_ip6gre_headroom-custom-140 #11
>[ 327.210496] Hardware name: Mellanox Technologies Ltd. "MSN2410-CB2F"/"SA000874", BIOS 4.6.5 03/08/2016
>[ 327.219872] Call Trace:
>[ 327.222384] dump_stack+0xc3/0x12b
>[ 327.234007] ubsan_epilogue+0x9/0x49
>[ 327.237638] ubsan_type_mismatch_common+0x1f9/0x2d0
>[ 327.255769] __ubsan_handle_type_mismatch+0x90/0xa7
>[ 327.264716] mlxsw_sp_fid_type+0x35/0x50 [mlxsw_spectrum]
>[ 327.270255] mlxsw_sp_port_vlan_router_leave+0x46/0xc0 [mlxsw_spectrum]
>[ 327.277019] mlxsw_sp_inetaddr_port_vlan_event+0xe1/0x340 [mlxsw_spectrum]
>[ 327.315031] mlxsw_sp_netdevice_vrf_event+0xa8/0x100 [mlxsw_spectrum]
>[ 327.321626] mlxsw_sp_netdevice_event+0x276/0x430 [mlxsw_spectrum]
>[ 327.367863] notifier_call_chain+0x4c/0x150
>[ 327.372128] __netdev_upper_dev_link+0x1b3/0x260
>[ 327.399450] vrf_add_slave+0xce/0x170 [vrf]
>[ 327.403703] do_setlink+0x658/0x1d70
>[ 327.508998] rtnl_newlink+0x908/0xf20
>[ 327.559128] rtnetlink_rcv_msg+0x50c/0x720
>[ 327.571720] netlink_rcv_skb+0x16a/0x1f0
>[ 327.583450] netlink_unicast+0x2ca/0x3e0
>[ 327.599305] netlink_sendmsg+0x3e2/0x7f0
>[ 327.616655] sock_sendmsg+0x76/0xc0
>[ 327.620207] ___sys_sendmsg+0x494/0x5d0
>[ 327.666117] __sys_sendmsg+0xc2/0x130
>[ 327.690953] do_syscall_64+0x66/0x370
>[ 327.694677] entry_SYSCALL_64_after_hwframe+0x49/0xbe
>[ 327.699782] RIP: 0033:0x7f4c2f3f8037
>[ 327.703393] RSP: 002b:00007ffe8c389708 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
>[ 327.711035] RAX: ffffffffffffffda RBX: 000000005b03f53e RCX: 00007f4c2f3f8037
>[ 327.718229] RDX: 0000000000000000 RSI: 00007ffe8c389760 RDI: 0000000000000003
>[ 327.725431] RBP: 00007ffe8c389760 R08: 0000000000000000 R09: 00007f4c2f443630
>[ 327.732632] R10: 00000000000005eb R11: 0000000000000246 R12: 0000000000000000
>[ 327.739833] R13: 00000000006774e0 R14: 00007ffe8c3897e8 R15: 0000000000000000
>[ 327.747096] ================================================================================
>
>Fixes: 9589a7b5d7d9 ("mlxsw: spectrum: Handle VLAN devices linking / unlinking")
>Suggested-by: Ido Schimmel <idosch@mellanox.com>
>Signed-off-by: Petr Machata <petrm@mellanox.com>
>Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
^ permalink raw reply
* Congratulations,
From: Mikhail Fridman @ 2018-05-27 12:39 UTC (permalink / raw)
--
Hello,
I Mikhail Fridman. has selected you specially as one of my beneficiaries
for my Charitable Donation, Just as I have declared on May 23, 2016 to
give my fortune as charity.
Check the link below for confirmation:
https://www.ibtimes.co.uk/russias-second-wealthiest-man-mikhail-fridman-plans-leaving-14-2bn-fortune-charity-1561604
Reply as soon as possible with further directives.
Best Regards,
Mikhail Fridman.
^ permalink raw reply
* [PATCH] iptables-compat: homogenize error message
From: Arushi Singhal @ 2018-05-27 13:09 UTC (permalink / raw)
To: pablo; +Cc: netfilter-devel, coreteam, netdev, linux-kernel
There is a difference between error messages in iptables and
iptables-compat:
#sudo iptables-compat -D INPUT 4
iptables: No chain/target/match by that name.
#sudo iptables -D INPUT 4
iptables: Index of deletion too big.
Now, will show same error message.
Signed-off-by: Arushi Singhal <arushisinghal19971997@gmail.com>
---
iptables/nft.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/iptables/nft.c b/iptables/nft.c
index e33d00f..40646f4 100644
--- a/iptables/nft.c
+++ b/iptables/nft.c
@@ -2603,7 +2603,7 @@ const char *nft_strerror(int err)
{ nft_rule_add, E2BIG, "Index of insertion too big" },
{ nft_rule_check, ENOENT, "Bad rule (does a matching rule exist in that chain?)" },
{ nft_rule_replace, ENOENT, "Index of replacement too big" },
- { nft_rule_delete_num, E2BIG, "Index of deletion too big" },
+ { nft_rule_delete_num, ENOENT, "Index of deletion too big" },
/* { TC_READ_COUNTER, E2BIG, "Index of counter too big" },
{ TC_ZERO_COUNTER, E2BIG, "Index of counter too big" }, */
{ nft_rule_add, ELOOP, "Loop found in table" },
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 0/7] net: Add address attribute to control metric of prefix route
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
From: David Ahern <dsahern@gmail.com>
For use cases such as VRR (Virtual Router Redundancy) interface managers
want efficient control over the order of prefix routes when multiple
interfaces have addresses with overlapping/duplicate subnets.
Currently, if two interfaces have addresses in the same subnet, the order
of the prefix route entries is determined by the order in which the
addresses are assigned or the links brought up. Any actions like cycling
an interface up and down changes that order. This set adds a new attribute
for addresses to allow a user to specify the metric of the prefix route
associated with an address giving interface managers better and more
efficient control of the order of prefix routes.
Patches 1-3 refactor IPv6 address add functions to pass an ifa6_config
struct. The functions currently have a long list of arguments and adding
the metric just makes it worse. Because of the overall diff size in
moving the arguments to a struct, the change is done in stages to make
it easier to review starting with the bottom function and pushing the
struct up to callers in each successive patch.
Patch 4 introduces the new attribute.
Patches 5 and 6 add support for the new attribute to IPv4 and IPv6
addresses.
Patch 7 adds a set of test cases.
Patch 8 adds support to iproute2
Changes since RFC
- collapsed patches 1 and 3 into patch 2
- simplified stack variables in fib_modify_prefix_metric in patch 5
David Ahern (7):
net/ipv6: Convert ipv6_add_addr to struct ifa6_config
net/ipv6: Pass ifa6_config struct to inet6_addr_add
net/ipv6: Pass ifa6_config struct to inet6_addr_modify
net: Add IFA_RT_PRIORITY address attribute
net/ipv4: Add support for specifying metric of connected routes
net/ipv6: Add support for specifying metric of connected routes
selftests: fib_tests: Add prefix route tests with metric
include/linux/inetdevice.h | 1 +
include/net/addrconf.h | 13 ++
include/net/if_inet6.h | 1 +
include/net/route.h | 1 +
include/uapi/linux/if_addr.h | 1 +
net/ipv4/devinet.c | 15 ++
net/ipv4/fib_frontend.c | 53 ++++-
net/ipv6/addrconf.c | 359 +++++++++++++++++++------------
tools/testing/selftests/net/fib_tests.sh | 181 +++++++++++++++-
9 files changed, 472 insertions(+), 153 deletions(-)
mode change 100755 => 100644 tools/testing/selftests/net/fib_tests.sh
--
2.11.0
^ permalink raw reply
* [PATCH net-next 1/7] net/ipv6: Convert ipv6_add_addr to struct ifa6_config
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Move config parameters for adding an ipv6 address to a struct. struct
names stem from inet6_rtm_newaddr which is the modern handler for
adding an address.
Start the conversion to ifa6_config with ipv6_add_addr. This is an argument
move only; no functional change intended. Mapping of variable changes:
addr --> cfg->pfx
peer_addr --> cfg->peer_pfx
pfxlen --> cfg->plen
flags --> cfg->ifa_flags
scope, valid_lft, prefered_lft have the same names within cfg
(with corrected spelling).
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/addrconf.h | 12 +++++
net/ipv6/addrconf.c | 134 +++++++++++++++++++++++++++----------------------
2 files changed, 87 insertions(+), 59 deletions(-)
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index c07d4dd09361..f766af2cd1a4 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -59,6 +59,18 @@ struct in6_validator_info {
struct netlink_ext_ack *extack;
};
+struct ifa6_config {
+ const struct in6_addr *pfx;
+ unsigned int plen;
+
+ const struct in6_addr *peer_pfx;
+
+ u32 ifa_flags;
+ u32 preferred_lft;
+ u32 valid_lft;
+ u16 scope;
+};
+
int addrconf_init(void);
void addrconf_cleanup(void);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index fbfd71a2d9c8..4988f2265882 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -986,17 +986,15 @@ static int ipv6_add_addr_hash(struct net_device *dev, struct inet6_ifaddr *ifa)
/* On success it returns ifp with increased reference count */
static struct inet6_ifaddr *
-ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
- const struct in6_addr *peer_addr, int pfxlen,
- int scope, u32 flags, u32 valid_lft, u32 prefered_lft,
+ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
bool can_block, struct netlink_ext_ack *extack)
{
gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC;
+ int addr_type = ipv6_addr_type(cfg->pfx);
struct net *net = dev_net(idev->dev);
struct inet6_ifaddr *ifa = NULL;
struct fib6_info *f6i = NULL;
int err = 0;
- int addr_type = ipv6_addr_type(addr);
if (addr_type == IPV6_ADDR_ANY ||
addr_type & IPV6_ADDR_MULTICAST ||
@@ -1019,7 +1017,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
*/
if (can_block) {
struct in6_validator_info i6vi = {
- .i6vi_addr = *addr,
+ .i6vi_addr = *cfg->pfx,
.i6vi_dev = idev,
.extack = extack,
};
@@ -1036,7 +1034,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
goto out;
}
- f6i = addrconf_f6i_alloc(net, idev, addr, false, gfp_flags);
+ f6i = addrconf_f6i_alloc(net, idev, cfg->pfx, false, gfp_flags);
if (IS_ERR(f6i)) {
err = PTR_ERR(f6i);
f6i = NULL;
@@ -1049,21 +1047,21 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
neigh_parms_data_state_setall(idev->nd_parms);
- ifa->addr = *addr;
- if (peer_addr)
- ifa->peer_addr = *peer_addr;
+ ifa->addr = *cfg->pfx;
+ if (cfg->peer_pfx)
+ ifa->peer_addr = *cfg->peer_pfx;
spin_lock_init(&ifa->lock);
INIT_DELAYED_WORK(&ifa->dad_work, addrconf_dad_work);
INIT_HLIST_NODE(&ifa->addr_lst);
- ifa->scope = scope;
- ifa->prefix_len = pfxlen;
- ifa->flags = flags;
+ ifa->scope = cfg->scope;
+ ifa->prefix_len = cfg->plen;
+ ifa->flags = cfg->ifa_flags;
/* No need to add the TENTATIVE flag for addresses with NODAD */
- if (!(flags & IFA_F_NODAD))
+ if (!(cfg->ifa_flags & IFA_F_NODAD))
ifa->flags |= IFA_F_TENTATIVE;
- ifa->valid_lft = valid_lft;
- ifa->prefered_lft = prefered_lft;
+ ifa->valid_lft = cfg->valid_lft;
+ ifa->prefered_lft = cfg->preferred_lft;
ifa->cstamp = ifa->tstamp = jiffies;
ifa->tokenized = false;
@@ -1260,11 +1258,10 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
{
struct inet6_dev *idev = ifp->idev;
struct in6_addr addr, *tmpaddr;
- unsigned long tmp_prefered_lft, tmp_valid_lft, tmp_tstamp, age;
+ unsigned long tmp_tstamp, age;
unsigned long regen_advance;
- int tmp_plen;
+ struct ifa6_config cfg;
int ret = 0;
- u32 addr_flags;
unsigned long now = jiffies;
long max_desync_factor;
s32 cnf_temp_preferred_lft;
@@ -1326,13 +1323,12 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
}
}
- tmp_valid_lft = min_t(__u32,
- ifp->valid_lft,
+ cfg.valid_lft = min_t(__u32, ifp->valid_lft,
idev->cnf.temp_valid_lft + age);
- tmp_prefered_lft = cnf_temp_preferred_lft + age -
- idev->desync_factor;
- tmp_prefered_lft = min_t(__u32, ifp->prefered_lft, tmp_prefered_lft);
- tmp_plen = ifp->prefix_len;
+ cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor;
+ cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft);
+
+ cfg.plen = ifp->prefix_len;
tmp_tstamp = ifp->tstamp;
spin_unlock_bh(&ifp->lock);
@@ -1346,21 +1342,22 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
* temporary addresses being generated.
*/
age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ;
- if (tmp_prefered_lft <= regen_advance + age) {
+ if (cfg.preferred_lft <= regen_advance + age) {
in6_ifa_put(ifp);
in6_dev_put(idev);
ret = -1;
goto out;
}
- addr_flags = IFA_F_TEMPORARY;
+ cfg.ifa_flags = IFA_F_TEMPORARY;
/* set in addrconf_prefix_rcv() */
if (ifp->flags & IFA_F_OPTIMISTIC)
- addr_flags |= IFA_F_OPTIMISTIC;
+ cfg.ifa_flags |= IFA_F_OPTIMISTIC;
+
+ cfg.pfx = &addr;
+ cfg.scope = ipv6_addr_scope(cfg.pfx);
- ift = ipv6_add_addr(idev, &addr, NULL, tmp_plen,
- ipv6_addr_scope(&addr), addr_flags,
- tmp_valid_lft, tmp_prefered_lft, block, NULL);
+ ift = ipv6_add_addr(idev, &cfg, block, NULL);
if (IS_ERR(ift)) {
in6_ifa_put(ifp);
in6_dev_put(idev);
@@ -2031,13 +2028,17 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
spin_lock_bh(&ifp->lock);
if (ifp->flags & IFA_F_STABLE_PRIVACY) {
- int scope = ifp->scope;
- u32 flags = ifp->flags;
struct in6_addr new_addr;
struct inet6_ifaddr *ifp2;
- u32 valid_lft, preferred_lft;
- int pfxlen = ifp->prefix_len;
int retries = ifp->stable_privacy_retry + 1;
+ struct ifa6_config cfg = {
+ .pfx = &new_addr,
+ .plen = ifp->prefix_len,
+ .ifa_flags = ifp->flags,
+ .valid_lft = ifp->valid_lft,
+ .preferred_lft = ifp->prefered_lft,
+ .scope = ifp->scope,
+ };
if (retries > net->ipv6.sysctl.idgen_retries) {
net_info_ratelimited("%s: privacy stable address generation failed because of DAD conflicts!\n",
@@ -2050,9 +2051,6 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
idev))
goto errdad;
- valid_lft = ifp->valid_lft;
- preferred_lft = ifp->prefered_lft;
-
spin_unlock_bh(&ifp->lock);
if (idev->cnf.max_addresses &&
@@ -2063,9 +2061,7 @@ void addrconf_dad_failure(struct sk_buff *skb, struct inet6_ifaddr *ifp)
net_info_ratelimited("%s: generating new stable privacy address because of DAD conflict\n",
ifp->idev->dev->name);
- ifp2 = ipv6_add_addr(idev, &new_addr, NULL, pfxlen,
- scope, flags, valid_lft,
- preferred_lft, false, NULL);
+ ifp2 = ipv6_add_addr(idev, &cfg, false, NULL);
if (IS_ERR(ifp2))
goto lock_errdad;
@@ -2507,12 +2503,20 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
if (!ifp && valid_lft) {
int max_addresses = in6_dev->cnf.max_addresses;
+ struct ifa6_config cfg = {
+ .pfx = addr,
+ .plen = pinfo->prefix_len,
+ .ifa_flags = addr_flags,
+ .valid_lft = valid_lft,
+ .preferred_lft = prefered_lft,
+ .scope = addr_type & IPV6_ADDR_SCOPE_MASK,
+ };
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
if ((net->ipv6.devconf_all->optimistic_dad ||
in6_dev->cnf.optimistic_dad) &&
!net->ipv6.devconf_all->forwarding && sllao)
- addr_flags |= IFA_F_OPTIMISTIC;
+ cfg.ifa_flags |= IFA_F_OPTIMISTIC;
#endif
/* Do not allow to create too much of autoconfigured
@@ -2520,11 +2524,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev,
*/
if (!max_addresses ||
ipv6_count_addresses(in6_dev) < max_addresses)
- ifp = ipv6_add_addr(in6_dev, addr, NULL,
- pinfo->prefix_len,
- addr_type&IPV6_ADDR_SCOPE_MASK,
- addr_flags, valid_lft,
- prefered_lft, false, NULL);
+ ifp = ipv6_add_addr(in6_dev, &cfg, false, NULL);
if (IS_ERR_OR_NULL(ifp))
return -1;
@@ -2836,12 +2836,19 @@ static int inet6_addr_add(struct net *net, int ifindex,
__u32 prefered_lft, __u32 valid_lft,
struct netlink_ext_ack *extack)
{
+ struct ifa6_config cfg = {
+ .pfx = pfx,
+ .plen = plen,
+ .peer_pfx = peer_pfx,
+ .ifa_flags = ifa_flags,
+ .preferred_lft = prefered_lft,
+ .valid_lft = valid_lft,
+ };
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
unsigned long timeout;
clock_t expires;
- int scope;
u32 flags;
ASSERT_RTNL();
@@ -2872,7 +2879,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
return ret;
}
- scope = ipv6_addr_scope(pfx);
+ cfg.scope = ipv6_addr_scope(pfx);
timeout = addrconf_timeout_fixup(valid_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
@@ -2892,9 +2899,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
prefered_lft = timeout;
}
- ifp = ipv6_add_addr(idev, pfx, peer_pfx, plen, scope, ifa_flags,
- valid_lft, prefered_lft, true, extack);
-
+ ifp = ipv6_add_addr(idev, &cfg, true, extack);
if (!IS_ERR(ifp)) {
if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
@@ -3010,11 +3015,16 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
int plen, int scope)
{
struct inet6_ifaddr *ifp;
+ struct ifa6_config cfg = {
+ .pfx = addr,
+ .plen = plen,
+ .ifa_flags = IFA_F_PERMANENT,
+ .valid_lft = INFINITY_LIFE_TIME,
+ .preferred_lft = INFINITY_LIFE_TIME,
+ .scope = scope
+ };
- ifp = ipv6_add_addr(idev, addr, NULL, plen,
- scope, IFA_F_PERMANENT,
- INFINITY_LIFE_TIME, INFINITY_LIFE_TIME,
- true, NULL);
+ ifp = ipv6_add_addr(idev, &cfg, true, NULL);
if (!IS_ERR(ifp)) {
spin_lock_bh(&ifp->lock);
ifp->flags &= ~IFA_F_TENTATIVE;
@@ -3104,18 +3114,24 @@ static void init_loopback(struct net_device *dev)
void addrconf_add_linklocal(struct inet6_dev *idev,
const struct in6_addr *addr, u32 flags)
{
+ struct ifa6_config cfg = {
+ .pfx = addr,
+ .plen = 64,
+ .ifa_flags = flags | IFA_F_PERMANENT,
+ .valid_lft = INFINITY_LIFE_TIME,
+ .preferred_lft = INFINITY_LIFE_TIME,
+ .scope = IFA_LINK
+ };
struct inet6_ifaddr *ifp;
- u32 addr_flags = flags | IFA_F_PERMANENT;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad ||
idev->cnf.optimistic_dad) &&
!dev_net(idev->dev)->ipv6.devconf_all->forwarding)
- addr_flags |= IFA_F_OPTIMISTIC;
+ cfg.ifa_flags |= IFA_F_OPTIMISTIC;
#endif
- ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
- INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL);
+ ifp = ipv6_add_addr(idev, &cfg, true, NULL);
if (!IS_ERR(ifp)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev,
0, 0, GFP_ATOMIC);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 2/7] net/ipv6: Pass ifa6_config struct to inet6_addr_add
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Move the creation of struct ifa6_config up to callers of inet6_addr_add.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/addrconf.c | 112 ++++++++++++++++++++++++++--------------------------
1 file changed, 57 insertions(+), 55 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4988f2265882..2db1acf70610 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2830,20 +2830,9 @@ static int ipv6_mc_config(struct sock *sk, bool join,
* Manual configuration of address on an interface
*/
static int inet6_addr_add(struct net *net, int ifindex,
- const struct in6_addr *pfx,
- const struct in6_addr *peer_pfx,
- unsigned int plen, __u32 ifa_flags,
- __u32 prefered_lft, __u32 valid_lft,
+ struct ifa6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct ifa6_config cfg = {
- .pfx = pfx,
- .plen = plen,
- .peer_pfx = peer_pfx,
- .ifa_flags = ifa_flags,
- .preferred_lft = prefered_lft,
- .valid_lft = valid_lft,
- };
struct inet6_ifaddr *ifp;
struct inet6_dev *idev;
struct net_device *dev;
@@ -2853,14 +2842,14 @@ static int inet6_addr_add(struct net *net, int ifindex,
ASSERT_RTNL();
- if (plen > 128)
+ if (cfg->plen > 128)
return -EINVAL;
/* check the lifetime */
- if (!valid_lft || prefered_lft > valid_lft)
+ if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft)
return -EINVAL;
- if (ifa_flags & IFA_F_MANAGETEMPADDR && plen != 64)
+ if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR && cfg->plen != 64)
return -EINVAL;
dev = __dev_get_by_index(net, ifindex);
@@ -2871,37 +2860,37 @@ static int inet6_addr_add(struct net *net, int ifindex,
if (IS_ERR(idev))
return PTR_ERR(idev);
- if (ifa_flags & IFA_F_MCAUTOJOIN) {
+ if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
int ret = ipv6_mc_config(net->ipv6.mc_autojoin_sk,
- true, pfx, ifindex);
+ true, cfg->pfx, ifindex);
if (ret < 0)
return ret;
}
- cfg.scope = ipv6_addr_scope(pfx);
+ cfg->scope = ipv6_addr_scope(cfg->pfx);
- timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
expires = jiffies_to_clock_t(timeout * HZ);
- valid_lft = timeout;
+ cfg->valid_lft = timeout;
flags = RTF_EXPIRES;
} else {
expires = 0;
flags = 0;
- ifa_flags |= IFA_F_PERMANENT;
+ cfg->ifa_flags |= IFA_F_PERMANENT;
}
- timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
if (timeout == 0)
- ifa_flags |= IFA_F_DEPRECATED;
- prefered_lft = timeout;
+ cfg->ifa_flags |= IFA_F_DEPRECATED;
+ cfg->preferred_lft = timeout;
}
- ifp = ipv6_add_addr(idev, &cfg, true, extack);
+ ifp = ipv6_add_addr(idev, cfg, true, extack);
if (!IS_ERR(ifp)) {
- if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+ if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
expires, flags, GFP_KERNEL);
}
@@ -2917,15 +2906,15 @@ static int inet6_addr_add(struct net *net, int ifindex,
* manually configured addresses
*/
addrconf_dad_start(ifp);
- if (ifa_flags & IFA_F_MANAGETEMPADDR)
- manage_tempaddrs(idev, ifp, valid_lft, prefered_lft,
- true, jiffies);
+ if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR)
+ manage_tempaddrs(idev, ifp, cfg->valid_lft,
+ cfg->preferred_lft, true, jiffies);
in6_ifa_put(ifp);
addrconf_verify_rtnl();
return 0;
- } else if (ifa_flags & IFA_F_MCAUTOJOIN) {
- ipv6_mc_config(net->ipv6.mc_autojoin_sk,
- false, pfx, ifindex);
+ } else if (cfg->ifa_flags & IFA_F_MCAUTOJOIN) {
+ ipv6_mc_config(net->ipv6.mc_autojoin_sk, false,
+ cfg->pfx, ifindex);
}
return PTR_ERR(ifp);
@@ -2976,6 +2965,11 @@ static int inet6_addr_del(struct net *net, int ifindex, u32 ifa_flags,
int addrconf_add_ifaddr(struct net *net, void __user *arg)
{
+ struct ifa6_config cfg = {
+ .ifa_flags = IFA_F_PERMANENT,
+ .preferred_lft = INFINITY_LIFE_TIME,
+ .valid_lft = INFINITY_LIFE_TIME,
+ };
struct in6_ifreq ireq;
int err;
@@ -2985,10 +2979,11 @@ int addrconf_add_ifaddr(struct net *net, void __user *arg)
if (copy_from_user(&ireq, arg, sizeof(struct in6_ifreq)))
return -EFAULT;
+ cfg.pfx = &ireq.ifr6_addr;
+ cfg.plen = ireq.ifr6_prefixlen;
+
rtnl_lock();
- err = inet6_addr_add(net, ireq.ifr6_ifindex, &ireq.ifr6_addr, NULL,
- ireq.ifr6_prefixlen, IFA_F_PERMANENT,
- INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, NULL);
+ err = inet6_addr_add(net, ireq.ifr6_ifindex, &cfg, NULL);
rtnl_unlock();
return err;
}
@@ -4624,12 +4619,11 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct ifaddrmsg *ifm;
struct nlattr *tb[IFA_MAX+1];
- struct in6_addr *pfx, *peer_pfx;
+ struct in6_addr *peer_pfx;
struct inet6_ifaddr *ifa;
struct net_device *dev;
struct inet6_dev *idev;
- u32 valid_lft = INFINITY_LIFE_TIME, preferred_lft = INFINITY_LIFE_TIME;
- u32 ifa_flags;
+ struct ifa6_config cfg;
int err;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy,
@@ -4637,60 +4631,68 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ memset(&cfg, 0, sizeof(cfg));
+
ifm = nlmsg_data(nlh);
- pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
- if (!pfx)
+ cfg.pfx = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer_pfx);
+ if (!cfg.pfx)
return -EINVAL;
+ cfg.peer_pfx = peer_pfx;
+ cfg.plen = ifm->ifa_prefixlen;
+ cfg.valid_lft = INFINITY_LIFE_TIME;
+ cfg.preferred_lft = INFINITY_LIFE_TIME;
+
if (tb[IFA_CACHEINFO]) {
struct ifa_cacheinfo *ci;
ci = nla_data(tb[IFA_CACHEINFO]);
- valid_lft = ci->ifa_valid;
- preferred_lft = ci->ifa_prefered;
- } else {
- preferred_lft = INFINITY_LIFE_TIME;
- valid_lft = INFINITY_LIFE_TIME;
+ cfg.valid_lft = ci->ifa_valid;
+ cfg.preferred_lft = ci->ifa_prefered;
}
dev = __dev_get_by_index(net, ifm->ifa_index);
if (!dev)
return -ENODEV;
- ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags;
+ if (tb[IFA_FLAGS])
+ cfg.ifa_flags = nla_get_u32(tb[IFA_FLAGS]);
+ else
+ cfg.ifa_flags = ifm->ifa_flags;
/* We ignore other flags so far. */
- ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
- IFA_F_NOPREFIXROUTE | IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC;
+ cfg.ifa_flags &= IFA_F_NODAD | IFA_F_HOMEADDRESS |
+ IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE |
+ IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC;
idev = ipv6_find_idev(dev);
if (IS_ERR(idev))
return PTR_ERR(idev);
if (!ipv6_allow_optimistic_dad(net, idev))
- ifa_flags &= ~IFA_F_OPTIMISTIC;
+ cfg.ifa_flags &= ~IFA_F_OPTIMISTIC;
- if (ifa_flags & IFA_F_NODAD && ifa_flags & IFA_F_OPTIMISTIC) {
+ if (cfg.ifa_flags & IFA_F_NODAD &&
+ cfg.ifa_flags & IFA_F_OPTIMISTIC) {
NL_SET_ERR_MSG(extack, "IFA_F_NODAD and IFA_F_OPTIMISTIC are mutually exclusive");
return -EINVAL;
}
- ifa = ipv6_get_ifaddr(net, pfx, dev, 1);
+ ifa = ipv6_get_ifaddr(net, cfg.pfx, dev, 1);
if (!ifa) {
/*
* It would be best to check for !NLM_F_CREATE here but
* userspace already relies on not having to provide this.
*/
- return inet6_addr_add(net, ifm->ifa_index, pfx, peer_pfx,
- ifm->ifa_prefixlen, ifa_flags,
- preferred_lft, valid_lft, extack);
+ return inet6_addr_add(net, ifm->ifa_index, &cfg, extack);
}
if (nlh->nlmsg_flags & NLM_F_EXCL ||
!(nlh->nlmsg_flags & NLM_F_REPLACE))
err = -EEXIST;
else
- err = inet6_addr_modify(ifa, ifa_flags, preferred_lft, valid_lft);
+ err = inet6_addr_modify(ifa, cfg.ifa_flags, cfg.preferred_lft,
+ cfg.valid_lft);
in6_ifa_put(ifa);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 3/7] net/ipv6: Pass ifa6_config struct to inet6_addr_modify
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update inet6_addr_modify to take ifa6_config argument versus a parameter
list. This is an argument move only; no functional change intended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/addrconf.c | 44 +++++++++++++++++++++++---------------------
1 file changed, 23 insertions(+), 21 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2db1acf70610..1b1e63a4520b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4527,8 +4527,7 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm->ifa_prefixlen);
}
-static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
- u32 prefered_lft, u32 valid_lft)
+static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
{
u32 flags;
clock_t expires;
@@ -4538,32 +4537,32 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
ASSERT_RTNL();
- if (!valid_lft || (prefered_lft > valid_lft))
+ if (!cfg->valid_lft || cfg->preferred_lft > cfg->valid_lft)
return -EINVAL;
- if (ifa_flags & IFA_F_MANAGETEMPADDR &&
+ if (cfg->ifa_flags & IFA_F_MANAGETEMPADDR &&
(ifp->flags & IFA_F_TEMPORARY || ifp->prefix_len != 64))
return -EINVAL;
if (!(ifp->flags & IFA_F_TENTATIVE) || ifp->flags & IFA_F_DADFAILED)
- ifa_flags &= ~IFA_F_OPTIMISTIC;
+ cfg->ifa_flags &= ~IFA_F_OPTIMISTIC;
- timeout = addrconf_timeout_fixup(valid_lft, HZ);
+ timeout = addrconf_timeout_fixup(cfg->valid_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
expires = jiffies_to_clock_t(timeout * HZ);
- valid_lft = timeout;
+ cfg->valid_lft = timeout;
flags = RTF_EXPIRES;
} else {
expires = 0;
flags = 0;
- ifa_flags |= IFA_F_PERMANENT;
+ cfg->ifa_flags |= IFA_F_PERMANENT;
}
- timeout = addrconf_timeout_fixup(prefered_lft, HZ);
+ timeout = addrconf_timeout_fixup(cfg->preferred_lft, HZ);
if (addrconf_finite_timeout(timeout)) {
if (timeout == 0)
- ifa_flags |= IFA_F_DEPRECATED;
- prefered_lft = timeout;
+ cfg->ifa_flags |= IFA_F_DEPRECATED;
+ cfg->preferred_lft = timeout;
}
spin_lock_bh(&ifp->lock);
@@ -4573,16 +4572,16 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
ifp->flags &= ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD |
IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR |
IFA_F_NOPREFIXROUTE);
- ifp->flags |= ifa_flags;
+ ifp->flags |= cfg->ifa_flags;
ifp->tstamp = jiffies;
- ifp->valid_lft = valid_lft;
- ifp->prefered_lft = prefered_lft;
+ ifp->valid_lft = cfg->valid_lft;
+ ifp->prefered_lft = cfg->preferred_lft;
spin_unlock_bh(&ifp->lock);
if (!(ifp->flags&IFA_F_TENTATIVE))
ipv6_ifa_notify(0, ifp);
- if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
+ if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->idev->dev, expires, flags,
GFP_KERNEL);
@@ -4601,10 +4600,14 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
}
if (was_managetempaddr || ifp->flags & IFA_F_MANAGETEMPADDR) {
- if (was_managetempaddr && !(ifp->flags & IFA_F_MANAGETEMPADDR))
- valid_lft = prefered_lft = 0;
- manage_tempaddrs(ifp->idev, ifp, valid_lft, prefered_lft,
- !was_managetempaddr, jiffies);
+ if (was_managetempaddr &&
+ !(ifp->flags & IFA_F_MANAGETEMPADDR)) {
+ cfg->valid_lft = 0;
+ cfg->preferred_lft = 0;
+ }
+ manage_tempaddrs(ifp->idev, ifp, cfg->valid_lft,
+ cfg->preferred_lft, !was_managetempaddr,
+ jiffies);
}
addrconf_verify_rtnl();
@@ -4691,8 +4694,7 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
!(nlh->nlmsg_flags & NLM_F_REPLACE))
err = -EEXIST;
else
- err = inet6_addr_modify(ifa, cfg.ifa_flags, cfg.preferred_lft,
- cfg.valid_lft);
+ err = inet6_addr_modify(ifa, &cfg);
in6_ifa_put(ifa);
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 4/7] net: Add IFA_RT_PRIORITY address attribute
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Currently, if two interfaces have addresses in the same connected route,
then the order of the prefix route entries is determined by the order in
which the addresses are assigned or the links brought up.
Add IFA_RT_PRIORITY to allow user to specify the metric of the prefix
route associated with an address giving interface managers better
control of the order of prefix routes.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/uapi/linux/if_addr.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index 2ef053d265de..ebaf5701c9db 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -33,6 +33,7 @@ enum {
IFA_CACHEINFO,
IFA_MULTICAST,
IFA_FLAGS,
+ IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */
__IFA_MAX,
};
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 6/7] net/ipv6: Add support for specifying metric of connected routes
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add support for IFA_RT_PRIORITY to ipv6 addresses.
If the metric is changed on an existing address then the new route
is inserted before removing the old one. Since the metric is one
of the route keys, the prefix route can not be atomically replaced.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/addrconf.h | 1 +
include/net/if_inet6.h | 1 +
net/ipv6/addrconf.c | 93 ++++++++++++++++++++++++++++++++++++++++----------
3 files changed, 77 insertions(+), 18 deletions(-)
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f766af2cd1a4..5f43f7a70fe6 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -65,6 +65,7 @@ struct ifa6_config {
const struct in6_addr *peer_pfx;
+ u32 rt_priority;
u32 ifa_flags;
u32 preferred_lft;
u32 valid_lft;
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index db389253dc2a..d7578cf49c3a 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -42,6 +42,7 @@ enum {
struct inet6_ifaddr {
struct in6_addr addr;
__u32 prefix_len;
+ __u32 rt_priority;
/* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */
__u32 valid_lft;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 1b1e63a4520b..f09afc232da4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1056,6 +1056,7 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = cfg->scope;
ifa->prefix_len = cfg->plen;
+ ifa->rt_priority = cfg->rt_priority;
ifa->flags = cfg->ifa_flags;
/* No need to add the TENTATIVE flag for addresses with NODAD */
if (!(cfg->ifa_flags & IFA_F_NODAD))
@@ -1356,6 +1357,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp,
cfg.pfx = &addr;
cfg.scope = ipv6_addr_scope(cfg.pfx);
+ cfg.rt_priority = 0;
ift = ipv6_add_addr(idev, &cfg, block, NULL);
if (IS_ERR(ift)) {
@@ -2314,12 +2316,13 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad
*/
static void
-addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
- unsigned long expires, u32 flags, gfp_t gfp_flags)
+addrconf_prefix_route(struct in6_addr *pfx, int plen, u32 metric,
+ struct net_device *dev, unsigned long expires,
+ u32 flags, gfp_t gfp_flags)
{
struct fib6_config cfg = {
.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
- .fc_metric = IP6_RT_PRIO_ADDRCONF,
+ .fc_metric = metric ? : IP6_RT_PRIO_ADDRCONF,
.fc_ifindex = dev->ifindex,
.fc_expires = expires,
.fc_dst_len = plen,
@@ -2683,7 +2686,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
expires = jiffies_to_clock_t(rt_expires);
}
addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
- dev, expires, flags, GFP_ATOMIC);
+ 0, dev, expires, flags,
+ GFP_ATOMIC);
}
fib6_info_release(rt);
}
@@ -2891,8 +2895,9 @@ static int inet6_addr_add(struct net *net, int ifindex,
ifp = ipv6_add_addr(idev, cfg, true, extack);
if (!IS_ERR(ifp)) {
if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) {
- addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
- expires, flags, GFP_KERNEL);
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+ ifp->rt_priority, dev, expires,
+ flags, GFP_KERNEL);
}
/* Send a netlink notification if DAD is enabled and
@@ -3056,7 +3061,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
if (addr.s6_addr32[3]) {
add_addr(idev, &addr, plen, scope);
- addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags,
+ addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags,
GFP_ATOMIC);
return;
}
@@ -3081,8 +3086,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
}
add_addr(idev, &addr, plen, flag);
- addrconf_prefix_route(&addr, plen, idev->dev, 0,
- pflags, GFP_ATOMIC);
+ addrconf_prefix_route(&addr, plen, 0, idev->dev,
+ 0, pflags, GFP_ATOMIC);
}
}
}
@@ -3128,7 +3133,7 @@ void addrconf_add_linklocal(struct inet6_dev *idev,
ifp = ipv6_add_addr(idev, &cfg, true, NULL);
if (!IS_ERR(ifp)) {
- addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev,
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len, 0, idev->dev,
0, 0, GFP_ATOMIC);
addrconf_dad_start(ifp);
in6_ifa_put(ifp);
@@ -3244,7 +3249,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
addrconf_add_linklocal(idev, &addr,
IFA_F_STABLE_PRIVACY);
else if (prefix_route)
- addrconf_prefix_route(&addr, 64, idev->dev,
+ addrconf_prefix_route(&addr, 64, 0, idev->dev,
0, 0, GFP_KERNEL);
break;
case IN6_ADDR_GEN_MODE_EUI64:
@@ -3255,7 +3260,7 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0)
addrconf_add_linklocal(idev, &addr, 0);
else if (prefix_route)
- addrconf_prefix_route(&addr, 64, idev->dev,
+ addrconf_prefix_route(&addr, 64, 0, idev->dev,
0, 0, GFP_KERNEL);
break;
case IN6_ADDR_GEN_MODE_NONE:
@@ -3375,7 +3380,8 @@ static int fixup_permanent_addr(struct net *net,
if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
- idev->dev, 0, 0, GFP_ATOMIC);
+ ifp->rt_priority, idev->dev, 0, 0,
+ GFP_ATOMIC);
}
if (ifp->state == INET6_IFADDR_STATE_PREDAD)
@@ -4495,6 +4501,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = {
[IFA_LOCAL] = { .len = sizeof(struct in6_addr) },
[IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
[IFA_FLAGS] = { .len = sizeof(u32) },
+ [IFA_RT_PRIORITY] = { .len = sizeof(u32) },
};
static int
@@ -4527,6 +4534,37 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
ifm->ifa_prefixlen);
}
+static int modify_prefix_route(struct inet6_ifaddr *ifp,
+ unsigned long expires, u32 flags)
+{
+ struct fib6_info *f6i;
+
+ f6i = addrconf_get_prefix_route(&ifp->addr,
+ ifp->prefix_len,
+ ifp->idev->dev,
+ 0, RTF_GATEWAY | RTF_DEFAULT);
+ if (!f6i)
+ return -ENOENT;
+
+ if (f6i->fib6_metric != ifp->rt_priority) {
+ /* add new one */
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+ ifp->rt_priority, ifp->idev->dev,
+ expires, flags, GFP_KERNEL);
+ /* delete old one */
+ ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+ } else {
+ if (!expires)
+ fib6_clean_expires(f6i);
+ else
+ fib6_set_expires(f6i, expires);
+
+ fib6_info_release(f6i);
+ }
+
+ return 0;
+}
+
static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
{
u32 flags;
@@ -4577,14 +4615,25 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg)
ifp->valid_lft = cfg->valid_lft;
ifp->prefered_lft = cfg->preferred_lft;
+ if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority)
+ ifp->rt_priority = cfg->rt_priority;
+
spin_unlock_bh(&ifp->lock);
if (!(ifp->flags&IFA_F_TENTATIVE))
ipv6_ifa_notify(0, ifp);
if (!(cfg->ifa_flags & IFA_F_NOPREFIXROUTE)) {
- addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
- ifp->idev->dev, expires, flags,
- GFP_KERNEL);
+ int rc = -ENOENT;
+
+ if (had_prefixroute)
+ rc = modify_prefix_route(ifp, expires, flags);
+
+ /* prefix route could have been deleted; if so restore it */
+ if (rc == -ENOENT) {
+ addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
+ ifp->rt_priority, ifp->idev->dev,
+ expires, flags, GFP_KERNEL);
+ }
} else if (had_prefixroute) {
enum cleanup_prefix_rt_t action;
unsigned long rt_expires;
@@ -4643,6 +4692,9 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg.peer_pfx = peer_pfx;
cfg.plen = ifm->ifa_prefixlen;
+ if (tb[IFA_RT_PRIORITY])
+ cfg.rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]);
+
cfg.valid_lft = INFINITY_LIFE_TIME;
cfg.preferred_lft = INFINITY_LIFE_TIME;
@@ -4745,7 +4797,8 @@ static inline int inet6_ifaddr_msgsize(void)
+ nla_total_size(16) /* IFA_LOCAL */
+ nla_total_size(16) /* IFA_ADDRESS */
+ nla_total_size(sizeof(struct ifa_cacheinfo))
- + nla_total_size(4) /* IFA_FLAGS */;
+ + nla_total_size(4) /* IFA_FLAGS */
+ + nla_total_size(4) /* IFA_RT_PRIORITY */;
}
static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
@@ -4791,6 +4844,10 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0)
goto error;
+ if (ifa->rt_priority &&
+ nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority))
+ goto error;
+
if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0)
goto error;
@@ -5635,7 +5692,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
if (!ipv6_addr_any(&ifp->peer_addr))
- addrconf_prefix_route(&ifp->peer_addr, 128,
+ addrconf_prefix_route(&ifp->peer_addr, 128, 0,
ifp->idev->dev, 0, 0,
GFP_ATOMIC);
break;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 5/7] net/ipv4: Add support for specifying metric of connected routes
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add support for IFA_RT_PRIORITY to ipv4 addresses.
If the metric is changed on an existing address then the new route
is inserted before removing the old one. Since the metric is one
of the route keys, the prefix route can not be replaced.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/linux/inetdevice.h | 1 +
include/net/route.h | 1 +
net/ipv4/devinet.c | 15 +++++++++++++
net/ipv4/fib_frontend.c | 53 ++++++++++++++++++++++++++++++++++++----------
4 files changed, 59 insertions(+), 11 deletions(-)
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index e16fe7d44a71..27650f1bff3d 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -139,6 +139,7 @@ struct in_ifaddr {
__be32 ifa_local;
__be32 ifa_address;
__be32 ifa_mask;
+ __u32 ifa_rt_priority;
__be32 ifa_broadcast;
unsigned char ifa_scope;
unsigned char ifa_prefixlen;
diff --git a/include/net/route.h b/include/net/route.h
index dbb032d5921b..bb53cdba38dc 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -225,6 +225,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
struct in_ifaddr;
void fib_add_ifaddr(struct in_ifaddr *);
void fib_del_ifaddr(struct in_ifaddr *, struct in_ifaddr *);
+void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric);
void rt_add_uncached_list(struct rtable *rt);
void rt_del_uncached_list(struct rtable *rt);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 40f001782c1b..d7585ab1a77a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -99,6 +99,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
[IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
[IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) },
[IFA_FLAGS] = { .type = NLA_U32 },
+ [IFA_RT_PRIORITY] = { .type = NLA_U32 },
};
#define IN4_ADDR_HSIZE_SHIFT 8
@@ -835,6 +836,9 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
+ if (tb[IFA_RT_PRIORITY])
+ ifa->ifa_rt_priority = nla_get_u32(tb[IFA_RT_PRIORITY]);
+
if (tb[IFA_CACHEINFO]) {
struct ifa_cacheinfo *ci;
@@ -906,12 +910,20 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid,
extack);
} else {
+ u32 new_metric = ifa->ifa_rt_priority;
+
inet_free_ifa(ifa);
if (nlh->nlmsg_flags & NLM_F_EXCL ||
!(nlh->nlmsg_flags & NLM_F_REPLACE))
return -EEXIST;
ifa = ifa_existing;
+
+ if (ifa->ifa_rt_priority != new_metric) {
+ fib_modify_prefix_metric(ifa, new_metric);
+ ifa->ifa_rt_priority = new_metric;
+ }
+
set_ifa_lifetime(ifa, valid_lft, prefered_lft);
cancel_delayed_work(&check_lifetime_work);
queue_delayed_work(system_power_efficient_wq,
@@ -1549,6 +1561,7 @@ static size_t inet_nlmsg_size(void)
+ nla_total_size(4) /* IFA_BROADCAST */
+ nla_total_size(IFNAMSIZ) /* IFA_LABEL */
+ nla_total_size(4) /* IFA_FLAGS */
+ + nla_total_size(4) /* IFA_RT_PRIORITY */
+ nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */
}
@@ -1618,6 +1631,8 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
(ifa->ifa_label[0] &&
nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) ||
nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) ||
+ (ifa->ifa_rt_priority &&
+ nla_put_u32(skb, IFA_RT_PRIORITY, ifa->ifa_rt_priority)) ||
put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp,
preferred, valid))
goto nla_put_failure;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 045c43a27c12..07989d9ab2f2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -846,7 +846,8 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
* to fib engine. It is legal, because all events occur
* only when netlink is already locked.
*/
-static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
+static void fib_magic(int cmd, int type, __be32 dst, int dst_len,
+ struct in_ifaddr *ifa, u32 rt_priority)
{
struct net *net = dev_net(ifa->ifa_dev->dev);
u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev);
@@ -856,6 +857,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
.fc_type = type,
.fc_dst = dst,
.fc_dst_len = dst_len,
+ .fc_priority = rt_priority,
.fc_prefsrc = ifa->ifa_local,
.fc_oif = ifa->ifa_dev->dev->ifindex,
.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
@@ -901,31 +903,57 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
}
}
- fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim);
+ fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0);
if (!(dev->flags & IFF_UP))
return;
/* Add broadcast address, if it is explicitly assigned. */
if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
- fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
+ fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
+ prim, 0);
if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
fib_magic(RTM_NEWROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
- prefix, ifa->ifa_prefixlen, prim);
+ prefix, ifa->ifa_prefixlen, prim,
+ ifa->ifa_rt_priority);
/* Add network specific broadcasts, when it takes a sense */
if (ifa->ifa_prefixlen < 31) {
- fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim);
+ fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32,
+ prim, 0);
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
- 32, prim);
+ 32, prim, 0);
}
}
}
+void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric)
+{
+ __be32 prefix = ifa->ifa_address & ifa->ifa_mask;
+ struct in_device *in_dev = ifa->ifa_dev;
+ struct net_device *dev = in_dev->dev;
+
+ if (!(dev->flags & IFF_UP) ||
+ ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) ||
+ ipv4_is_zeronet(prefix) ||
+ prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32)
+ return;
+
+ /* add the new */
+ fib_magic(RTM_NEWROUTE,
+ dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+ prefix, ifa->ifa_prefixlen, ifa, new_metric);
+
+ /* delete the old */
+ fib_magic(RTM_DELROUTE,
+ dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+ prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority);
+}
+
/* Delete primary or secondary address.
* Optionally, on secondary address promotion consider the addresses
* from subnet iprim as deleted, even if they are in device list.
@@ -967,7 +995,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
fib_magic(RTM_DELROUTE,
dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
- any, ifa->ifa_prefixlen, prim);
+ any, ifa->ifa_prefixlen, prim, 0);
subnet = 1;
}
@@ -1051,17 +1079,20 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
no_promotions:
if (!(ok & BRD_OK))
- fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
+ fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
+ prim, 0);
if (subnet && ifa->ifa_prefixlen < 31) {
if (!(ok & BRD1_OK))
- fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
+ fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32,
+ prim, 0);
if (!(ok & BRD0_OK))
- fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
+ fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32,
+ prim, 0);
}
if (!(ok & LOCAL_OK)) {
unsigned int addr_type;
- fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
+ fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0);
/* Check, that this local address finally disappeared. */
addr_type = inet_addr_type_dev_table(dev_net(dev), dev,
--
2.11.0
^ permalink raw reply related
* [PATCH iproute2-next] ipaddress: Add support for address metric
From: dsahern @ 2018-05-27 15:10 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add support for IFA_RT_PRIORITY using the same keywords as iproute for
RTA_PRIORITY.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/uapi/linux/if_addr.h | 1 +
ip/ipaddress.c | 15 ++++++++++++++-
man/man8/ip-address.8.in | 6 ++++++
3 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index c4899e22cdaa..a924606f36e5 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -33,6 +33,7 @@ enum {
IFA_CACHEINFO,
IFA_MULTICAST,
IFA_FLAGS,
+ IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */
__IFA_MAX,
};
diff --git a/ip/ipaddress.c b/ip/ipaddress.c
index 75539e057f6a..6b53b753ead9 100644
--- a/ip/ipaddress.c
+++ b/ip/ipaddress.c
@@ -63,7 +63,7 @@ static void usage(void)
fprintf(stderr, " ip address {showdump|restore}\n");
fprintf(stderr, "IFADDR := PREFIX | ADDR peer PREFIX\n");
fprintf(stderr, " [ broadcast ADDR ] [ anycast ADDR ]\n");
- fprintf(stderr, " [ label IFNAME ] [ scope SCOPE-ID ]\n");
+ fprintf(stderr, " [ label IFNAME ] [ scope SCOPE-ID ] [ metric METRIC ]\n");
fprintf(stderr, "SCOPE-ID := [ host | link | global | NUMBER ]\n");
fprintf(stderr, "FLAG-LIST := [ FLAG-LIST ] FLAG\n");
fprintf(stderr, "FLAG := [ permanent | dynamic | secondary | primary |\n");
@@ -1328,6 +1328,10 @@ int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
rta_tb[IFA_ADDRESS]));
}
print_int(PRINT_ANY, "prefixlen", "/%d ", ifa->ifa_prefixlen);
+
+ if (rta_tb[IFA_RT_PRIORITY])
+ print_uint(PRINT_ANY, "metric", "metric %u ",
+ rta_getattr_u32(rta_tb[IFA_RT_PRIORITY]));
}
if (brief)
@@ -2119,6 +2123,15 @@ static int ipaddr_modify(int cmd, int flags, int argc, char **argv)
NEXT_ARG();
l = *argv;
addattr_l(&req.n, sizeof(req), IFA_LABEL, l, strlen(l)+1);
+ } else if (matches(*argv, "metric") == 0 ||
+ matches(*argv, "priority") == 0 ||
+ matches(*argv, "preference") == 0) {
+ __u32 metric;
+
+ NEXT_ARG();
+ if (get_u32(&metric, *argv, 0))
+ invarg("\"metric\" value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), IFA_RT_PRIORITY, metric);
} else if (matches(*argv, "valid_lft") == 0) {
if (valid_lftp)
duparg("valid_lft", *argv);
diff --git a/man/man8/ip-address.8.in b/man/man8/ip-address.8.in
index 7ebf0bc98dcd..c3861b3725cc 100644
--- a/man/man8/ip-address.8.in
+++ b/man/man8/ip-address.8.in
@@ -27,6 +27,8 @@ ip-address \- protocol address management
.IR IFNAME " ] [ "
.B scope
.IR SCOPE-ID " ] [ "
+.B metric
+.IR METRIC " ] [ "
.B to
.IR PREFIX " ] [ " FLAG-LIST " ] [ "
.B label
@@ -215,6 +217,10 @@ valid inside this site.
.in -8
.TP
+.BI metric " NUMBER"
+priority of prefix route associated with address.
+
+.TP
.BI valid_lft " LFT"
the valid lifetime of this address; see section 5.5.4 of
RFC 4862. When it expires, the address is removed by the kernel.
--
2.11.0
^ 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