* [PATCH rdma-next v3 13/14] RDMA/rxe: Implement disassociate_ucontext callback
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Implement an empty disassociate_ucontext() callback so the RDMA core
can move rxe devices between net namespaces. The core requires this
callback to reset user contexts without waiting for userspace.
rxe needs no teardown here: its user-mapped queues live in
reference-counted vmalloc memory (see rxe_mmap.c) that stays valid
while userspace holds the mappings.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/sw/rxe/rxe_verbs.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 1ec130fee8ea..6eb10d2f0653 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -240,6 +240,10 @@ static void rxe_dealloc_ucontext(struct ib_ucontext *ibuc)
rxe_err_uc(uc, "cleanup failed, err = %d\n", err);
}
+static void rxe_disassociate_ucontext(struct ib_ucontext *ibuc)
+{
+}
+
/* pd */
static int rxe_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)
{
@@ -1478,6 +1482,7 @@ static const struct ib_device_ops rxe_dev_ops = {
.destroy_srq = rxe_destroy_srq,
.detach_mcast = rxe_detach_mcast,
.device_group = &rxe_attr_group,
+ .disassociate_ucontext = rxe_disassociate_ucontext,
.enable_driver = rxe_enable_driver,
.get_dma_mr = rxe_get_dma_mr,
.get_hw_stats = rxe_ib_get_hw_stats,
--
2.54.0
^ permalink raw reply related
* Re: [PATCH net] mac802154: llsec: reject frames shorter than the authentication tag
From: Breno Leitao @ 2026-07-16 13:23 UTC (permalink / raw)
To: Doruk Tan Ozturk
Cc: alex.aring, stefan, miquel.raynal, davem, edumazet, kuba, pabeni,
horms, phoebe.buckheister, linux-wpan, netdev, linux-kernel,
stable
In-Reply-To: <20260709131246.44517-1-doruk@0sec.ai>
On Thu, Jul 09, 2026 at 03:12:46PM +0200, Doruk Tan Ozturk wrote:
> Reported-by: Doruk Tan Ozturk <doruk@0sec.ai>
> Signed-off-by: Doruk Tan Ozturk <doruk@0sec.ai>
Usually you don't have Reported-by if you are fixing something yourself.
> ---
> net/mac802154/llsec.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c
> index 5e7cc11fab3a..364a1ac1d771 100644
> --- a/net/mac802154/llsec.c
> +++ b/net/mac802154/llsec.c
> @@ -893,6 +893,11 @@ llsec_do_decrypt_auth(struct sk_buff *skb, const struct mac802154_llsec *sec,
Why not returning here, before sg_init_one()? here you alrady have
datalen and authlen.
> sg_init_one(&sg, skb_mac_header(skb), assoclen + datalen);
>
> + if (datalen < authlen) {
> + kfree_sensitive(req);
> + return -EBADMSG;
> + }
> +
> if (!(hdr->sec.level & IEEE802154_SCF_SECLEVEL_ENC)) {
> assoclen += datalen - authlen;
> datalen = authlen;
> --
> 2.43.0
>
>
^ permalink raw reply
* [PATCH rdma-next v3 12/14] RDMA/rxe: Allow queue VMAs to outlive ucontexts
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Prepare queue mappings for asynchronous ucontext disassociation during
device disable. Rely on the VMA page references to preserve mapped
memory until the final unmap.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
v1->v2:
- new patch
---
drivers/infiniband/sw/rxe/rxe_mmap.c | 35 ++--------------------------
1 file changed, 2 insertions(+), 33 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c
index 7f723a2f3700..a4ead89ccbd3 100644
--- a/drivers/infiniband/sw/rxe/rxe_mmap.c
+++ b/drivers/infiniband/sw/rxe/rxe_mmap.c
@@ -11,7 +11,6 @@
#include "rxe.h"
#include "rxe_loc.h"
-#include "rxe_queue.h"
void rxe_mmap_release(struct kref *ref)
{
@@ -30,29 +29,6 @@ void rxe_mmap_release(struct kref *ref)
kfree(ip);
}
-/*
- * open and close keep track of how many times the memory region is mapped,
- * to avoid releasing it.
- */
-static void rxe_vma_open(struct vm_area_struct *vma)
-{
- struct rxe_mmap_info *ip = vma->vm_private_data;
-
- kref_get(&ip->ref);
-}
-
-static void rxe_vma_close(struct vm_area_struct *vma)
-{
- struct rxe_mmap_info *ip = vma->vm_private_data;
-
- kref_put(&ip->ref, rxe_mmap_release);
-}
-
-static const struct vm_operations_struct rxe_vm_ops = {
- .open = rxe_vma_open,
- .close = rxe_vma_close,
-};
-
/**
* rxe_mmap - create a new mmap region
* @context: the IB user context of the process making the mmap() call
@@ -106,17 +82,10 @@ int rxe_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
list_del_init(&ip->pending_mmaps);
spin_unlock_bh(&rxe->pending_lock);
- vma->vm_ops = &rxe_vm_ops;
- vma->vm_private_data = ip;
-
ret = remap_vmalloc_range(vma, ip->obj, 0);
- if (ret) {
- vma->vm_private_data = NULL;
- vma->vm_ops = NULL;
- kref_put(&ip->ref, rxe_mmap_release);
+ kref_put(&ip->ref, rxe_mmap_release);
+ if (ret)
rxe_dbg_dev(rxe, "err %d from remap_vmalloc_range\n", ret);
- goto done;
- }
done:
return ret;
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 11/14] RDMA/core: Make device names unique per net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Use rdma_dev_access_netns() to scope RDMA device name lookup and "%d" name
allocation to the relevant net namespace. Keep shared mode and
CONFIG_NET_NS=n behaviour system-wide.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/device.c | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index bb02640239d7..4c75078448a3 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -129,7 +129,7 @@ static DECLARE_RWSEM(rdma_nets_rwsem);
bool ib_devices_shared_netns = true;
module_param_named(netns_mode, ib_devices_shared_netns, bool, 0444);
MODULE_PARM_DESC(netns_mode,
- "Share device among net namespaces; default=1 (shared)");
+ "Share device among net namespaces; default=1 (shared). In exclusive mode device names are unique per net namespace");
/**
* rdma_dev_access_netns() - Return whether an rdma device can be accessed
* from a specified net namespace or not.
@@ -359,7 +359,8 @@ static struct ib_device *__ib_device_get_by_name(const char *name,
unsigned long index;
xa_for_each (&devices, index, device)
- if (!strcmp(name, dev_name(&device->dev)))
+ if (rdma_dev_access_netns(device, net) &&
+ !strcmp(name, dev_name(&device->dev)))
return device;
return NULL;
@@ -437,7 +438,11 @@ int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
return 0;
}
-/* Pick a free index for the '%d' style @name pattern. */
+/*
+ * Pick a free index for the '%d' style @name pattern within net namespace
+ * @net. Returns the index on success or a negative errno. The caller builds
+ * the final unique device name from the returned index.
+ */
static int __alloc_name_id(struct net *net, const char *name,
const struct ib_device *skip)
{
@@ -452,7 +457,7 @@ static int __alloc_name_id(struct net *net, const char *name,
xa_for_each (&devices, index, device) {
char buf[IB_DEVICE_NAME_MAX];
- if (device == skip)
+ if (device == skip || !rdma_dev_access_netns(device, net))
continue;
if (sscanf(dev_name(&device->dev), name, &i) != 1)
continue;
@@ -1233,7 +1238,8 @@ static __net_init int rdma_dev_init_net(struct net *net)
}
/*
- * Assign the unique string device name and the unique device index. This is
+ * Assign the unique string device name and the unique device index. The device
+ * name is unique within the net namespace the device is assigned to. This is
* undone by ib_dealloc_device.
*/
static int assign_name(struct ib_device *device, const char *name)
@@ -1416,8 +1422,9 @@ static void ib_device_notify_register(struct ib_device *device)
/**
* ib_register_device - Register an IB device with IB core
* @device: Device to register
- * @name: unique string device name. This may include a '%' which will
- * cause a unique index to be added to the passed device name.
+ * @name: device name, unique within the device's net namespace. This may
+ * include a '%' which will cause a unique index to be added to the
+ * passed device name.
* @dma_device: pointer to a DMA-capable device. If %NULL, then the IB
* device will be used. In this case the caller should fully
* setup the ibdev for DMA. This usually means using dma_virt_ops.
@@ -1708,6 +1715,7 @@ static bool rdma_dev_name_in_netns(struct ib_device *skip, struct net *net,
xa_for_each(&devices, index, device)
if (device != skip &&
+ rdma_dev_access_netns(device, net) &&
!strcmp(name, dev_name(&device->dev)))
return true;
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 10/14] RDMA/core: Document the SELinux ibendport net namespace limitation
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Document that SELinux ibendport labels use a global (device name, port)
key, so same-named RDMA devices in different net namespaces share a label.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/security.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index 9af31d1d9d70..a82c46965416 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -700,6 +700,12 @@ int ib_mad_agent_security_setup(struct ib_mad_agent *agent,
if (qp_type != IB_QPT_SMI)
return 0;
+ /*
+ * SELinux labels an endport by (device name, port) from a global
+ * policy. If devices in different net namespaces share a name, they get
+ * the same label; distinguishing them would need net namespace support
+ * in the policy language and tooling.
+ */
spin_lock(&mad_agent_list_lock);
ret = security_ib_endport_manage_subnet(agent->security,
dev_name(&agent->device->dev),
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 09/14] RDMA/cma: Document that CM configfs cannot be net namespace scoped
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Document the rdma_cm configfs limitation: configfs is global, so same-named
RDMA devices in different net namespaces cannot both be represented there.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
Documentation/ABI/testing/configfs-rdma_cm | 4 ++++
drivers/infiniband/core/cma_configfs.c | 4 ++++
2 files changed, 8 insertions(+)
diff --git a/Documentation/ABI/testing/configfs-rdma_cm b/Documentation/ABI/testing/configfs-rdma_cm
index 74f9506f42e7..739f7b6a1259 100644
--- a/Documentation/ABI/testing/configfs-rdma_cm
+++ b/Documentation/ABI/testing/configfs-rdma_cm
@@ -12,6 +12,10 @@ Description: Interface is used to configure RDMA-cable HCAs in respect to
for this HCA has to be created:
mkdir -p /config/rdma_cm/<hca>
+ Note: configfs has no network namespace support, so this
+ interface cannot represent two devices that share a name in
+ different network namespaces (possible in exclusive netns mode).
+
What: /config/rdma_cm/<hca>/ports/<port-num>/default_roce_mode
Date: November 29, 2015
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 891e52afb8f4..c389d4e37b6b 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -65,6 +65,10 @@ static struct cma_dev_port_group *to_dev_port_group(struct config_item *item)
return container_of(group, struct cma_dev_port_group, group);
}
+/*
+ * configfs is not net namespace aware, so a name shared by devices in
+ * different namespaces resolves to the first match here.
+ */
static bool filter_by_name(struct ib_device *ib_dev, void *cookie)
{
return !strcmp(dev_name(&ib_dev->dev), cookie);
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 08/14] RDMA/cgroup: Disambiguate devices across net namespaces
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
RDMA device names are unique only within a network namespace, but an
RDMA cgroup can account resources for devices from multiple namespaces.
Duplicate names therefore make cgroup output ambiguous and can cause
limit writes to select the wrong device.
Use the system-wide RDMA device index to distinguish duplicate names
while preserving the existing UAPI for unique names. Reject ambiguous
name-only writes with -ENOTUNIQ and expose a complete device view to
administrators.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
v1->v2:
- replace caller-netns filtering with global visibility and index-based
disambiguation
---
Documentation/admin-guide/cgroup-v1/rdma.rst | 8 +++
Documentation/admin-guide/cgroup-v2.rst | 15 ++++-
drivers/infiniband/core/cgroup.c | 1 +
include/linux/cgroup_rdma.h | 1 +
kernel/cgroup/rdma.c | 71 ++++++++++++++++----
5 files changed, 83 insertions(+), 13 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v1/rdma.rst b/Documentation/admin-guide/cgroup-v1/rdma.rst
index e69369b7252e..8d0c3a796ee3 100644
--- a/Documentation/admin-guide/cgroup-v1/rdma.rst
+++ b/Documentation/admin-guide/cgroup-v1/rdma.rst
@@ -90,6 +90,13 @@ Following resources can be accounted by rdma controller.
hca_object Maximum number of HCA Objects
========== =============================
+RDMA devices from all network namespaces are listed. Each line starts with
+the device name. If more than one device has the same name, ``index=N``
+follows the name, where ``N`` is the system-wide RDMA device index, unique
+among registered devices. When configuring a limit, the index is optional
+for a globally unique name and required for a duplicate name. A write without
+the required index fails with ``-ENOTUNIQ``.
+
2. Usage Examples
=================
@@ -97,6 +104,7 @@ Following resources can be accounted by rdma controller.
echo mlx4_0 hca_handle=2 hca_object=2000 > /sys/fs/cgroup/rdma/1/rdma.max
echo ocrdma1 hca_handle=3 > /sys/fs/cgroup/rdma/2/rdma.max
+ echo "rxe0 index=5 hca_handle=2" > /sys/fs/cgroup/rdma/3/rdma.max
(b) Query resource limit::
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 993446ab66d0..df74d554d2cd 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2752,6 +2752,11 @@ RDMA
The "rdma" controller regulates the distribution and accounting of
RDMA resources.
+RDMA devices from all network namespaces are listed. Each line starts with
+the device name. If more than one device has the same name, ``index=N``
+follows the name, where ``N`` is the system-wide RDMA device index, unique
+among registered devices.
+
RDMA Interface Files
~~~~~~~~~~~~~~~~~~~~
@@ -2760,7 +2765,11 @@ RDMA Interface Files
except root that describes current configured resource limit
for a RDMA/IB device.
- Lines are keyed by device name and are not ordered.
+ Lines are keyed by device name and are not ordered. A write may
+ include ``index=N`` after the device name. The index is optional
+ when the name is globally unique. If multiple devices have that
+ name, the index is required and a write without it fails with
+ ``-ENOTUNIQ``.
Each line contains space separated resource name and its configured
limit that can be distributed.
@@ -2776,6 +2785,10 @@ RDMA Interface Files
mlx4_0 hca_handle=2 hca_object=2000
ocrdma1 hca_handle=3 hca_object=max
+ For devices with duplicate names, select the device by index::
+
+ echo "rxe0 index=5 hca_handle=2" > rdma.max
+
rdma.current
A read-only file that describes current resource usage.
It exists for all the cgroup except root.
diff --git a/drivers/infiniband/core/cgroup.c b/drivers/infiniband/core/cgroup.c
index 1f037fe01450..8611b4e32cfb 100644
--- a/drivers/infiniband/core/cgroup.c
+++ b/drivers/infiniband/core/cgroup.c
@@ -17,6 +17,7 @@
void ib_device_register_rdmacg(struct ib_device *device)
{
device->cg_device.name = device->name;
+ device->cg_device.index = device->index;
rdmacg_register_device(&device->cg_device);
}
diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h
index 404e746552ca..9a5c9ee728e7 100644
--- a/include/linux/cgroup_rdma.h
+++ b/include/linux/cgroup_rdma.h
@@ -34,6 +34,7 @@ struct rdmacg_device {
struct list_head dev_node;
struct list_head rpools;
char *name;
+ u32 index;
};
/*
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index 5e82a03b3270..9489f3df0bf3 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -19,6 +19,7 @@
#define RDMACG_MAX_STR "max"
enum rdmacg_limit_tokens {
+ RDMACG_DEVICE_INDEX,
RDMACG_HCA_HANDLE_VAL,
RDMACG_HCA_HANDLE_MAX,
RDMACG_HCA_OBJECT_VAL,
@@ -27,6 +28,7 @@ enum rdmacg_limit_tokens {
};
static const match_table_t rdmacg_limit_tokens = {
+ { RDMACG_DEVICE_INDEX, "index=%u" },
{ RDMACG_HCA_HANDLE_VAL, "hca_handle=%d" },
{ RDMACG_HCA_HANDLE_MAX, "hca_handle=max" },
{ RDMACG_HCA_OBJECT_VAL, "hca_object=%d" },
@@ -464,17 +466,53 @@ void rdmacg_unregister_device(struct rdmacg_device *device)
}
EXPORT_SYMBOL(rdmacg_unregister_device);
-static struct rdmacg_device *rdmacg_get_device_locked(const char *name)
+static struct rdmacg_device *
+rdmacg_get_device_locked(const char *name, bool has_index, u32 index)
{
+ struct rdmacg_device *match = NULL;
struct rdmacg_device *device;
lockdep_assert_held(&rdmacg_mutex);
- list_for_each_entry(device, &rdmacg_devices, dev_node)
- if (!strcmp(name, device->name))
- return device;
+ list_for_each_entry(device, &rdmacg_devices, dev_node) {
+ if (strcmp(name, device->name))
+ continue;
- return NULL;
+ if (has_index) {
+ if (device->index == index)
+ return device;
+ continue;
+ }
+
+ if (match)
+ return ERR_PTR(-ENOTUNIQ);
+ match = device;
+ }
+
+ return match ?: ERR_PTR(-ENODEV);
+}
+
+static bool
+rdmacg_device_name_unique_locked(const struct rdmacg_device *device)
+{
+ struct rdmacg_device *other;
+
+ lockdep_assert_held(&rdmacg_mutex);
+
+ list_for_each_entry(other, &rdmacg_devices, dev_node)
+ if (other != device && !strcmp(other->name, device->name))
+ return false;
+
+ return true;
+}
+
+static void rdmacg_print_device_key(struct seq_file *sf,
+ const struct rdmacg_device *device)
+{
+ seq_puts(sf, device->name);
+ if (!rdmacg_device_name_unique_locked(device))
+ seq_printf(sf, " index=%u", device->index);
+ seq_putc(sf, ' ');
}
static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
@@ -488,6 +526,8 @@ static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
char *p;
int *new_limits;
unsigned long enables = 0;
+ u32 dev_index = 0;
+ bool has_index = false;
int i = 0, ret = 0;
/* extract the device name first */
@@ -503,7 +543,7 @@ static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
goto err;
}
- /* parse resource limit tokens */
+ /* parse the optional device index and resource limit tokens */
while ((p = strsep(&options, " \t\n"))) {
substring_t args[MAX_OPT_ARGS];
int tok, intval;
@@ -513,6 +553,13 @@ static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
tok = match_token(p, rdmacg_limit_tokens, args);
switch (tok) {
+ case RDMACG_DEVICE_INDEX:
+ if (has_index || match_uint(&args[0], &dev_index)) {
+ ret = -EINVAL;
+ goto parse_err;
+ }
+ has_index = true;
+ break;
case RDMACG_HCA_HANDLE_VAL:
if (match_int(&args[0], &intval) || intval < 0) {
ret = -EINVAL;
@@ -546,9 +593,9 @@ static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of,
/* acquire lock to synchronize with hot plug devices */
mutex_lock(&rdmacg_mutex);
- device = rdmacg_get_device_locked(dev_name);
- if (!device) {
- ret = -ENODEV;
+ device = rdmacg_get_device_locked(dev_name, has_index, dev_index);
+ if (IS_ERR(device)) {
+ ret = PTR_ERR(device);
goto dev_err;
}
@@ -626,7 +673,7 @@ static int rdmacg_resource_read(struct seq_file *sf, void *v)
mutex_lock(&rdmacg_mutex);
list_for_each_entry(device, &rdmacg_devices, dev_node) {
- seq_printf(sf, "%s ", device->name);
+ rdmacg_print_device_key(sf, device);
rpool = find_cg_rpool_locked(cg, device);
print_rpool_values(sf, rpool);
@@ -650,7 +697,7 @@ static int rdmacg_events_show(struct seq_file *sf, void *v)
list_for_each_entry(device, &rdmacg_devices, dev_node) {
rpool = find_cg_rpool_locked(cg, device);
- seq_printf(sf, "%s ", device->name);
+ rdmacg_print_device_key(sf, device);
for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
seq_printf(sf, "%s.max=%llu %s.alloc_fail=%llu",
rdmacg_resource_names[i],
@@ -679,7 +726,7 @@ static int rdmacg_events_local_show(struct seq_file *sf, void *v)
list_for_each_entry(device, &rdmacg_devices, dev_node) {
rpool = find_cg_rpool_locked(cg, device);
- seq_printf(sf, "%s ", device->name);
+ rdmacg_print_device_key(sf, device);
for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
seq_printf(sf, "%s.max=%llu %s.alloc_fail=%llu",
rdmacg_resource_names[i],
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 07/14] RDMA/srp: Make the SRP sysfs class net namespace aware
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Tag srp_class by the RDMA device's net namespace so SRP hosts derived from
same-named RDMA devices can coexist across namespaces.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/ulp/srp/ib_srp.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 0caebbc2810f..2fc8e133c70f 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3189,10 +3189,24 @@ static struct attribute *srp_class_attrs[];
ATTRIBUTE_GROUPS(srp_class);
+/*
+ * SRP hosts are named after their ib device, so tag the class by the ib
+ * device's net namespace.
+ */
+static const struct ns_common *srp_net_namespace(const struct device *dev)
+{
+ struct srp_host *host = container_of(dev, struct srp_host, dev);
+ struct net *net = rdma_dev_net(host->srp_dev->dev);
+
+ return net ? to_ns_common(net) : NULL;
+}
+
static struct class srp_class = {
.name = "infiniband_srp",
.dev_groups = srp_class_groups,
- .dev_release = srp_release_dev
+ .dev_release = srp_release_dev,
+ .ns_type = &net_ns_type_operations,
+ .namespace = srp_net_namespace,
};
/**
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 06/14] net/smc: Look up the pnetid ib device within the net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Scope smc_pnet_find_ib() to the caller's net namespace so pnetid setup
cannot bind to a same-named RDMA device from another namespace once names
become per-netns.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
net/smc/smc_pnet.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 63e286e2dfaa..ff9c9c35cc2f 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -304,13 +304,18 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid)
return true;
}
-/* Find an infiniband device by a given name. The device might not exist. */
-static struct smc_ib_device *smc_pnet_find_ib(char *ib_name)
+/*
+ * Find an infiniband device by a given name, restricted to the devices
+ * accessible from @net. The device might not exist.
+ */
+static struct smc_ib_device *smc_pnet_find_ib(struct net *net, char *ib_name)
{
struct smc_ib_device *ibdev;
mutex_lock(&smc_ib_devices.mutex);
list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+ if (!rdma_dev_access_netns(ibdev->ibdev, net))
+ continue;
if (!strncmp(ibdev->ibdev->name, ib_name,
sizeof(ibdev->ibdev->name)) ||
(ibdev->ibdev->dev.parent &&
@@ -408,8 +413,8 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net,
return rc;
}
-static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name,
- u8 ib_port, char *pnet_name)
+static int smc_pnet_add_ib(struct smc_pnettable *pnettable, struct net *net,
+ char *ib_name, u8 ib_port, char *pnet_name)
{
struct smc_pnetentry *tmp_pe, *new_pe;
struct smc_ib_device *ib_dev;
@@ -419,7 +424,7 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name,
bool new_ibdev;
/* try to apply the pnetid to active devices */
- ib_dev = smc_pnet_find_ib(ib_name);
+ ib_dev = smc_pnet_find_ib(net, ib_name);
if (ib_dev) {
ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name);
if (ibdev_applied)
@@ -518,7 +523,7 @@ static int smc_pnet_enter(struct net *net, struct nlattr *tb[])
if (ibport < 1 || ibport > SMC_MAX_PORTS)
goto error;
}
- rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name);
+ rc = smc_pnet_add_ib(pnettable, net, string, ibport, pnet_name);
if (!rc)
new_ibdev = true;
else if (rc != -EEXIST)
@@ -1170,6 +1175,9 @@ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port)
struct smc_net *sn;
int rc = -ENOENT;
+ if (!rdma_dev_access_netns(smcibdev->ibdev, &init_net))
+ return -ENOENT;
+
/* get pnettable for init namespace */
sn = net_generic(&init_net, smc_net_id);
pnettable = &sn->pnettable;
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 05/14] RDMA/nldev: Allow setting the device name while changing net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Accept RDMA_NLDEV_ATTR_DEV_NAME together with RDMA_NLDEV_NET_NS_FD so a
netlink move can rename the device in the destination namespace. Keep the
name semantics aligned with the existing RDMA rename path.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/device.c | 6 ++++++
drivers/infiniband/core/nldev.c | 27 ++++++++++++++++++---------
include/uapi/rdma/rdma_netlink.h | 5 ++++-
3 files changed, 28 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 366bd8463c07..bb02640239d7 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1901,6 +1901,9 @@ int ib_device_set_netns_put(struct sk_buff *skb,
if (ret == -EEXIST)
NL_SET_ERR_MSG(extack,
"Device name already exists in the target net namespace");
+ else if (ret == -EINVAL && name)
+ NL_SET_ERR_MSG(extack,
+ "Unable to use requested device name in the target net namespace");
goto ns_err;
}
@@ -1931,6 +1934,9 @@ int ib_device_set_netns_put(struct sk_buff *skb,
if (ret == -EEXIST)
NL_SET_ERR_MSG(extack,
"Device name already exists in the target net namespace");
+ else if (ret == -EINVAL && name)
+ NL_SET_ERR_MSG(extack,
+ "Unable to use requested device name in the target net namespace");
put_net(net);
return ret;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 8648e95700bf..4efa387ec1be 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1178,6 +1178,24 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!device)
return -EINVAL;
+ if (tb[RDMA_NLDEV_NET_NS_FD]) {
+ char name[IB_DEVICE_NAME_MAX] = {};
+ u32 ns_fd;
+
+ if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
+ nla_strscpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME],
+ IB_DEVICE_NAME_MAX);
+ if (strlen(name) == 0) {
+ err = -EINVAL;
+ goto done;
+ }
+ }
+ ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
+ err = ib_device_set_netns_put(skb, device, ns_fd,
+ name[0] ? name : NULL, extack);
+ goto put_done;
+ }
+
if (tb[RDMA_NLDEV_ATTR_DEV_NAME]) {
char name[IB_DEVICE_NAME_MAX] = {};
@@ -1191,15 +1209,6 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
goto done;
}
- if (tb[RDMA_NLDEV_NET_NS_FD]) {
- u32 ns_fd;
-
- ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
- err = ib_device_set_netns_put(skb, device, ns_fd, NULL,
- extack);
- goto put_done;
- }
-
if (tb[RDMA_NLDEV_ATTR_DEV_DIM]) {
u8 use_dim;
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 3af946ecbac3..ee11c3bbbae2 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -516,7 +516,10 @@ enum rdma_nldev_attr {
RDMA_NLDEV_ATTR_DEV_PROTOCOL, /* string */
/*
- * File descriptor handle of the net namespace object
+ * File descriptor handle of the net namespace object. May be combined
+ * with RDMA_NLDEV_ATTR_DEV_NAME (a literal device name) to also rename
+ * the device in the destination namespace; the move fails with -EEXIST
+ * if that name is already taken there.
*/
RDMA_NLDEV_NET_NS_FD, /* u32 */
/*
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 04/14] RDMA/nldev: Report net namespace move errors through extack
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Thread extack through the existing net namespace move helper and report the
main failure reasons from the core path. Keep the existing move UAPI shape
unchanged.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/core_priv.h | 3 ++-
drivers/infiniband/core/device.c | 24 ++++++++++++++++++++++--
drivers/infiniband/core/nldev.c | 6 ++----
3 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 3bd5bb7135a3..aaf330b0d333 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -356,7 +356,8 @@ void ib_port_unregister_client_groups(struct ib_device *ibdev, u32 port_num,
const struct attribute_group **groups);
int ib_device_set_netns_put(struct sk_buff *skb,
- struct ib_device *dev, u32 ns_fd, const char *name);
+ struct ib_device *dev, u32 ns_fd, const char *name,
+ struct netlink_ext_ack *extack);
int rdma_nl_net_init(struct rdma_dev_net *rnet);
void rdma_nl_net_exit(struct rdma_dev_net *rnet);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index c0b6613dba4c..366bd8463c07 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1871,18 +1871,22 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
}
int ib_device_set_netns_put(struct sk_buff *skb,
- struct ib_device *dev, u32 ns_fd, const char *name)
+ struct ib_device *dev, u32 ns_fd, const char *name,
+ struct netlink_ext_ack *extack)
{
struct net *net;
int ret;
net = get_net_ns_by_fd(ns_fd);
if (IS_ERR(net)) {
+ NL_SET_ERR_MSG(extack, "Invalid target net namespace fd");
ret = PTR_ERR(net);
goto net_err;
}
if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ NL_SET_ERR_MSG(extack,
+ "Missing CAP_NET_ADMIN in the target net namespace");
ret = -EPERM;
goto ns_err;
}
@@ -1893,6 +1897,10 @@ int ib_device_set_netns_put(struct sk_buff *skb,
*/
if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
ret = name ? ib_device_rename(dev, name) : 0;
+
+ if (ret == -EEXIST)
+ NL_SET_ERR_MSG(extack,
+ "Device name already exists in the target net namespace");
goto ns_err;
}
@@ -1901,7 +1909,16 @@ int ib_device_set_netns_put(struct sk_buff *skb,
* changed and this cannot be blocked waiting for userspace to do
* something, so disassociation is mandatory.
*/
- if (!dev->ops.disassociate_ucontext || ib_devices_shared_netns) {
+ if (ib_devices_shared_netns) {
+ NL_SET_ERR_MSG(extack,
+ "Cannot change net namespace of RDMA device in shared netns mode");
+ ret = -EOPNOTSUPP;
+ goto ns_err;
+ }
+
+ if (!dev->ops.disassociate_ucontext) {
+ NL_SET_ERR_MSG(extack,
+ "Device does not support namespace changes (no disassociate support)");
ret = -EOPNOTSUPP;
goto ns_err;
}
@@ -1911,6 +1928,9 @@ int ib_device_set_netns_put(struct sk_buff *skb,
ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net, name,
NULL);
put_device(&dev->dev);
+ if (ret == -EEXIST)
+ NL_SET_ERR_MSG(extack,
+ "Device name already exists in the target net namespace");
put_net(net);
return ret;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 77a758080148..8648e95700bf 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1195,10 +1195,8 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
u32 ns_fd;
ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
- err = ib_device_set_netns_put(skb, device, ns_fd, NULL);
- if (err == -EEXIST)
- NL_SET_ERR_MSG(extack,
- "Device name already exists in the target net namespace");
+ err = ib_device_set_netns_put(skb, device, ns_fd, NULL,
+ extack);
goto put_done;
}
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 03/14] RDMA/core: Support renaming a device when changing its net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Allow namespace moves to request a destination device name. Keep requested
names on the same literal-name path as the existing RDMA rename operation,
and keep teardown fallback naming on the trusted kernel-controlled path.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/core_priv.h | 2 +-
drivers/infiniband/core/device.c | 48 ++++++++++++++++++++---------
drivers/infiniband/core/nldev.c | 2 +-
3 files changed, 35 insertions(+), 17 deletions(-)
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 19104c542b27..3bd5bb7135a3 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -356,7 +356,7 @@ void ib_port_unregister_client_groups(struct ib_device *ibdev, u32 port_num,
const struct attribute_group **groups);
int ib_device_set_netns_put(struct sk_buff *skb,
- struct ib_device *dev, u32 ns_fd);
+ struct ib_device *dev, u32 ns_fd, const char *name);
int rdma_nl_net_init(struct rdma_dev_net *rnet);
void rdma_nl_net_exit(struct rdma_dev_net *rnet);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index b55fb075d0ae..c0b6613dba4c 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -268,7 +268,8 @@ static struct notifier_block ibdev_lsm_nb = {
};
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
- struct net *net, const char *fallback_pattern);
+ struct net *net, const char *requested_name,
+ const char *fallback_pattern);
/* Pointer to the RCU head at the start of the ib_port_data array */
struct ib_port_data_rcu {
@@ -1173,7 +1174,7 @@ static void rdma_dev_exit_net(struct net *net)
*/
if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
ret = rdma_dev_change_netns(dev, net, &init_net,
- "ibdev%d");
+ NULL, "ibdev%d");
if (ret && ret != -ENODEV)
WARN(1,
"Failed to move RDMA device %s to init_net on netns exit: %d\n",
@@ -1714,12 +1715,13 @@ static bool rdma_dev_name_in_netns(struct ib_device *skip, struct net *net,
}
/*
- * Choose the name @device should use in net namespace @net: keep the current
- * name when it is free, otherwise use a trusted '%d' @fallback_pattern
- * (namespace teardown) to pick a free index. The caller must hold the write
- * side of devices_rwsem.
+ * Choose the name @device should use in net namespace @net. @requested_name
+ * is used as a literal device name when set. Otherwise keep the current name
+ * when it is free, or use a trusted '%d' @fallback_pattern for teardown. The
+ * caller must hold the write side of devices_rwsem.
*/
static int rdma_dev_pick_netns_name(struct ib_device *device, struct net *net,
+ const char *requested_name,
const char *fallback_pattern,
char *buf, size_t buf_len,
const char **new_name)
@@ -1728,6 +1730,15 @@ static int rdma_dev_pick_netns_name(struct ib_device *device, struct net *net,
lockdep_assert_held_write(&devices_rwsem);
+ if (requested_name) {
+ if (!rdma_dev_name_in_netns(device, net, requested_name)) {
+ *new_name = requested_name;
+ return 0;
+ }
+
+ return -EEXIST;
+ }
+
if (!rdma_dev_name_in_netns(device, net, dev_name(&device->dev))) {
*new_name = dev_name(&device->dev);
return 0;
@@ -1758,7 +1769,8 @@ static int rdma_dev_pick_netns_name(struct ib_device *device, struct net *net,
* Naming rules are handled by rdma_dev_pick_netns_name().
*/
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
- struct net *net, const char *fallback_pattern)
+ struct net *net, const char *requested_name,
+ const char *fallback_pattern)
{
char buf[IB_DEVICE_NAME_MAX];
const char *new_name;
@@ -1784,8 +1796,9 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
* down, so a doomed user move does not disable a live device.
*/
down_write(&devices_rwsem);
- ret = rdma_dev_pick_netns_name(device, net, fallback_pattern,
- buf, sizeof(buf), &new_name);
+ ret = rdma_dev_pick_netns_name(device, net, requested_name,
+ fallback_pattern, buf,
+ sizeof(buf), &new_name);
up_write(&devices_rwsem);
if (ret)
goto out;
@@ -1801,8 +1814,9 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
* level.
*/
down_write(&devices_rwsem);
- ret = rdma_dev_pick_netns_name(device, net, fallback_pattern, buf,
- sizeof(buf), &new_name);
+ ret = rdma_dev_pick_netns_name(device, net, requested_name,
+ fallback_pattern, buf, sizeof(buf),
+ &new_name);
if (ret) {
if (fallback_pattern) {
WARN(1,
@@ -1857,7 +1871,7 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
}
int ib_device_set_netns_put(struct sk_buff *skb,
- struct ib_device *dev, u32 ns_fd)
+ struct ib_device *dev, u32 ns_fd, const char *name)
{
struct net *net;
int ret;
@@ -1873,9 +1887,12 @@ int ib_device_set_netns_put(struct sk_buff *skb,
goto ns_err;
}
- /* Moving a device to the namespace it already lives in is a no-op. */
+ /*
+ * Moving a device to the namespace it already lives in is a no-op; a
+ * supplied name still renames it in place.
+ */
if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
- ret = 0;
+ ret = name ? ib_device_rename(dev, name) : 0;
goto ns_err;
}
@@ -1891,7 +1908,8 @@ int ib_device_set_netns_put(struct sk_buff *skb,
get_device(&dev->dev);
ib_device_put(dev);
- ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net, NULL);
+ ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net, name,
+ NULL);
put_device(&dev->dev);
put_net(net);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 32b6c4d68ca0..77a758080148 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1195,7 +1195,7 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
u32 ns_fd;
ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
- err = ib_device_set_netns_put(skb, device, ns_fd);
+ err = ib_device_set_netns_put(skb, device, ns_fd, NULL);
if (err == -EEXIST)
NL_SET_ERR_MSG(extack,
"Device name already exists in the target net namespace");
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 02/14] RDMA/core: Handle device name conflicts when changing net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Prepare namespace moves for per-netns names. Check user-initiated moves for
destination-name conflicts before disabling the device, keep same-netns
moves as no-ops, and make teardown moves detach from the exiting namespace
even if fallback naming fails.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
v1->v2:
- fixed possible bogus race-triggered-WARN in rdma_dev_exit_net()
---
drivers/infiniband/core/device.c | 155 ++++++++++++++++++++++++++-----
drivers/infiniband/core/nldev.c | 3 +
2 files changed, 137 insertions(+), 21 deletions(-)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index de610f52c9b2..b55fb075d0ae 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -268,7 +268,7 @@ static struct notifier_block ibdev_lsm_nb = {
};
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
- struct net *net);
+ struct net *net, const char *fallback_pattern);
/* Pointer to the RCU head at the start of the ib_port_data array */
struct ib_port_data_rcu {
@@ -437,7 +437,8 @@ int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
}
/* Pick a free index for the '%d' style @name pattern. */
-static int alloc_name_id(struct net *net, const char *name)
+static int __alloc_name_id(struct net *net, const char *name,
+ const struct ib_device *skip)
{
struct ib_device *device;
unsigned long index;
@@ -450,6 +451,8 @@ static int alloc_name_id(struct net *net, const char *name)
xa_for_each (&devices, index, device) {
char buf[IB_DEVICE_NAME_MAX];
+ if (device == skip)
+ continue;
if (sscanf(dev_name(&device->dev), name, &i) != 1)
continue;
if (i < 0 || i >= INT_MAX)
@@ -469,6 +472,11 @@ static int alloc_name_id(struct net *net, const char *name)
return rc;
}
+static int alloc_name_id(struct net *net, const char *name)
+{
+ return __alloc_name_id(net, name, NULL);
+}
+
static int alloc_name(struct ib_device *ibdev, const char *name)
{
int id;
@@ -1160,8 +1168,17 @@ static void rdma_dev_exit_net(struct net *net)
/*
* If the real device is in the NS then move it back to init.
+ * Provide a fallback pattern so a name conflict in init_net
+ * cannot make the teardown move fail.
*/
- rdma_dev_change_netns(dev, net, &init_net);
+ if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
+ ret = rdma_dev_change_netns(dev, net, &init_net,
+ "ibdev%d");
+ if (ret && ret != -ENODEV)
+ WARN(1,
+ "Failed to move RDMA device %s to init_net on netns exit: %d\n",
+ dev_name(&dev->dev), ret);
+ }
put_device(&dev->dev);
down_read(&devices_rwsem);
@@ -1680,14 +1697,71 @@ void ib_unregister_device_queued(struct ib_device *ib_dev)
}
EXPORT_SYMBOL(ib_unregister_device_queued);
+static bool rdma_dev_name_in_netns(struct ib_device *skip, struct net *net,
+ const char *name)
+{
+ struct ib_device *device;
+ unsigned long index;
+
+ lockdep_assert_held_write(&devices_rwsem);
+
+ xa_for_each(&devices, index, device)
+ if (device != skip &&
+ !strcmp(name, dev_name(&device->dev)))
+ return true;
+
+ return false;
+}
+
+/*
+ * Choose the name @device should use in net namespace @net: keep the current
+ * name when it is free, otherwise use a trusted '%d' @fallback_pattern
+ * (namespace teardown) to pick a free index. The caller must hold the write
+ * side of devices_rwsem.
+ */
+static int rdma_dev_pick_netns_name(struct ib_device *device, struct net *net,
+ const char *fallback_pattern,
+ char *buf, size_t buf_len,
+ const char **new_name)
+{
+ int id;
+
+ lockdep_assert_held_write(&devices_rwsem);
+
+ if (!rdma_dev_name_in_netns(device, net, dev_name(&device->dev))) {
+ *new_name = dev_name(&device->dev);
+ return 0;
+ }
+
+ if (!fallback_pattern)
+ return -EEXIST;
+
+ snprintf(buf, buf_len, "ibdev%u", device->index);
+ if (!rdma_dev_name_in_netns(device, net, buf)) {
+ *new_name = buf;
+ return 0;
+ }
+
+ id = __alloc_name_id(net, fallback_pattern, device);
+ if (id < 0)
+ return id;
+ snprintf(buf, buf_len, fallback_pattern, id);
+ *new_name = buf;
+ return 0;
+}
+
/*
* The caller must pass in a device that has the kref held and the refcount
* released. If the device is in cur_net and still registered then it is moved
* into net.
+ *
+ * Naming rules are handled by rdma_dev_pick_netns_name().
*/
static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
- struct net *net)
+ struct net *net, const char *fallback_pattern)
{
+ char buf[IB_DEVICE_NAME_MAX];
+ const char *new_name;
int ret2 = -EINVAL;
int ret;
@@ -1704,30 +1778,63 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
goto out;
}
+ if (!fallback_pattern) {
+ /*
+ * Reject a predictable name conflict before tearing anything
+ * down, so a doomed user move does not disable a live device.
+ */
+ down_write(&devices_rwsem);
+ ret = rdma_dev_pick_netns_name(device, net, fallback_pattern,
+ buf, sizeof(buf), &new_name);
+ up_write(&devices_rwsem);
+ if (ret)
+ goto out;
+ }
+
kobject_uevent(&device->dev.kobj, KOBJ_REMOVE);
disable_device(device);
/*
- * At this point no one can be using the device, so it is safe to
- * change the namespace.
+ * Recompute the destination name under the write side of devices_rwsem
+ * now that the device is disabled, closing races with a concurrent
+ * registration or rename, then publish the new namespace at the sysfs
+ * level.
*/
- write_pnet(&device->coredev.rdma_net, net);
+ down_write(&devices_rwsem);
+ ret = rdma_dev_pick_netns_name(device, net, fallback_pattern, buf,
+ sizeof(buf), &new_name);
+ if (ret) {
+ if (fallback_pattern) {
+ WARN(1,
+ "%s: failed to pick device name during namespace teardown: %d\n",
+ __func__, ret);
+ write_pnet(&device->coredev.rdma_net, net);
+ ret = 0;
+ }
+ goto rename_done;
+ }
- down_read(&devices_rwsem);
- /*
- * Currently rdma devices are system wide unique. So the device name
- * is guaranteed free in the new namespace. Publish the new namespace
- * at the sysfs level.
- */
- ret = device_rename(&device->dev, dev_name(&device->dev));
- up_read(&devices_rwsem);
+ write_pnet(&device->coredev.rdma_net, net);
+ ret = device_rename(&device->dev, new_name);
if (ret) {
- dev_warn(&device->dev,
- "%s: Couldn't rename device after namespace change\n",
- __func__);
- /* Try and put things back and re-enable the device */
- write_pnet(&device->coredev.rdma_net, cur_net);
+ if (fallback_pattern) {
+ WARN(1,
+ "%s: failed to rename device during namespace teardown: %d\n",
+ __func__, ret);
+ ret = 0;
+ } else {
+ dev_warn(&device->dev,
+ "%s: Couldn't rename device after namespace change\n",
+ __func__);
+ /* Try and put things back and re-enable the device */
+ write_pnet(&device->coredev.rdma_net, cur_net);
+ }
+ } else {
+ strscpy(device->name, dev_name(&device->dev),
+ IB_DEVICE_NAME_MAX);
}
+rename_done:
+ up_write(&devices_rwsem);
ret2 = enable_device_and_get(device);
if (ret2) {
@@ -1766,6 +1873,12 @@ int ib_device_set_netns_put(struct sk_buff *skb,
goto ns_err;
}
+ /* Moving a device to the namespace it already lives in is a no-op. */
+ if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
+ ret = 0;
+ goto ns_err;
+ }
+
/*
* All the ib_clients, including uverbs, are reset when the namespace is
* changed and this cannot be blocked waiting for userspace to do
@@ -1778,7 +1891,7 @@ int ib_device_set_netns_put(struct sk_buff *skb,
get_device(&dev->dev);
ib_device_put(dev);
- ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net);
+ ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net, NULL);
put_device(&dev->dev);
put_net(net);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index aae4f3f6bcba..32b6c4d68ca0 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1196,6 +1196,9 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
err = ib_device_set_netns_put(skb, device, ns_fd);
+ if (err == -EEXIST)
+ NL_SET_ERR_MSG(extack,
+ "Device name already exists in the target net namespace");
goto put_done;
}
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 01/14] RDMA/core: Pass the net namespace to the device name lookups
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
In-Reply-To: <20260716132316.1495242-1-jiri@resnulli.us>
From: Jiri Pirko <jiri@nvidia.com>
Prepare for per-netns RDMA device names by passing the target net
namespace through the name lookup and allocation helpers. Keep current
global uniqueness behaviour.
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
drivers/infiniband/core/device.c | 26 ++++++++++++++++++--------
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index b8193e077a74..de610f52c9b2 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -351,7 +351,8 @@ void ib_device_put(struct ib_device *device)
}
EXPORT_SYMBOL(ib_device_put);
-static struct ib_device *__ib_device_get_by_name(const char *name)
+static struct ib_device *__ib_device_get_by_name(const char *name,
+ const struct net *net)
{
struct ib_device *device;
unsigned long index;
@@ -395,7 +396,7 @@ int ib_device_rename(struct ib_device *ibdev, const char *name)
return 0;
}
- if (__ib_device_get_by_name(name)) {
+ if (__ib_device_get_by_name(name, rdma_dev_net(ibdev))) {
up_write(&devices_rwsem);
return -EEXIST;
}
@@ -435,7 +436,8 @@ int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
return 0;
}
-static int alloc_name(struct ib_device *ibdev, const char *name)
+/* Pick a free index for the '%d' style @name pattern. */
+static int alloc_name_id(struct net *net, const char *name)
{
struct ib_device *device;
unsigned long index;
@@ -462,15 +464,22 @@ static int alloc_name(struct ib_device *ibdev, const char *name)
}
rc = ida_alloc(&inuse, GFP_KERNEL);
- if (rc < 0)
- goto out;
-
- rc = dev_set_name(&ibdev->dev, name, rc);
out:
ida_destroy(&inuse);
return rc;
}
+static int alloc_name(struct ib_device *ibdev, const char *name)
+{
+ int id;
+
+ id = alloc_name_id(rdma_dev_net(ibdev), name);
+ if (id < 0)
+ return id;
+
+ return dev_set_name(&ibdev->dev, name, id);
+}
+
static void ib_device_release(struct device *device)
{
struct ib_device *dev = container_of(device, struct ib_device, dev);
@@ -1223,7 +1232,8 @@ static int assign_name(struct ib_device *device, const char *name)
if (ret)
goto out;
- if (__ib_device_get_by_name(dev_name(&device->dev))) {
+ if (__ib_device_get_by_name(dev_name(&device->dev),
+ rdma_dev_net(device))) {
ret = -ENFILE;
goto out;
}
--
2.54.0
^ permalink raw reply related
* [PATCH rdma-next v3 00/14] RDMA: Make device names unique per net namespace
From: Jiri Pirko @ 2026-07-16 13:23 UTC (permalink / raw)
To: linux-rdma
Cc: cgroups, netdev, linux-s390, linux-kselftest, jgg, leon, parav,
mbloch, cmeiohas, roman.gushchin, bvanassche, zyjzyj2000, shuah,
tj, mkoutny, hannes, alibuda, dust.li, sidraya, wenjia,
yanjun.zhu, cui.tao
From: Jiri Pirko <jiri@nvidia.com>
RDMA device names are unique system-wide today:
__ib_device_get_by_name() checks a requested name against every
registered device regardless of the network namespace it lives in.
A device in one network namespace therefore cannot use a name already
taken in another, even in exclusive netns mode (netns_mode=0) where
the two are otherwise isolated. Net devices have no such restriction -
their names only need to be unique within a network namespace.
This series makes RDMA device names unique per network namespace,
matching net device semantics, and adapts the users that assumed
system-wide unique names.
Scoping reuses the existing rdma_dev_access_netns() predicate, so
behavior only changes in exclusive mode:
- shared mode (default): names stay unique system-wide, no change;
- exclusive mode: names only need to be unique within a namespace;
- CONFIG_NET_NS=n: everything is init_net, names stay system-wide
unique.
There are two users that cannot be made per-namespace and are
documented as known limitations instead of changed:
- the rdma_cm configfs tree: configfs has no network namespace
support, so it cannot represent two same-named devices;
- SELinux ibendport labelling: endports are labelled by (device
name, port) from a global policy; distinguishing same-named
devices would need net namespace support in the SELinux policy
language and tooling.
Tested with the new rxe_netns_names kselftest added in the last patch.
Jiri Pirko (14):
RDMA/core: Pass the net namespace to the device name lookups
RDMA/core: Handle device name conflicts when changing net namespace
RDMA/core: Support renaming a device when changing its net namespace
RDMA/nldev: Report net namespace move errors through extack
RDMA/nldev: Allow setting the device name while changing net namespace
net/smc: Look up the pnetid ib device within the net namespace
RDMA/srp: Make the SRP sysfs class net namespace aware
RDMA/cgroup: Disambiguate devices across net namespaces
RDMA/cma: Document that CM configfs cannot be net namespace scoped
RDMA/core: Document the SELinux ibendport net namespace limitation
RDMA/core: Make device names unique per net namespace
RDMA/rxe: Allow queue VMAs to outlive ucontexts
RDMA/rxe: Implement disassociate_ucontext callback
RDMA/selftests: Add rxe_netns_names test
Documentation/ABI/testing/configfs-rdma_cm | 4 +
Documentation/admin-guide/cgroup-v1/rdma.rst | 8 +
Documentation/admin-guide/cgroup-v2.rst | 15 +-
drivers/infiniband/core/cgroup.c | 1 +
drivers/infiniband/core/cma_configfs.c | 4 +
drivers/infiniband/core/core_priv.h | 3 +-
drivers/infiniband/core/device.c | 245 +++++++++++--
drivers/infiniband/core/nldev.c | 26 +-
drivers/infiniband/core/security.c | 6 +
drivers/infiniband/sw/rxe/rxe_mmap.c | 35 +-
drivers/infiniband/sw/rxe/rxe_verbs.c | 5 +
drivers/infiniband/ulp/srp/ib_srp.c | 16 +-
include/linux/cgroup_rdma.h | 1 +
include/uapi/rdma/rdma_netlink.h | 5 +-
kernel/cgroup/rdma.c | 71 +++-
net/smc/smc_pnet.c | 20 +-
tools/testing/selftests/rdma/Makefile | 3 +-
tools/testing/selftests/rdma/config | 2 +
.../testing/selftests/rdma/rxe_netns_names.sh | 334 ++++++++++++++++++
19 files changed, 705 insertions(+), 99 deletions(-)
create mode 100755 tools/testing/selftests/rdma/rxe_netns_names.sh
--
2.54.0
^ permalink raw reply
* Re: [PATCH net-next v3 0/9] netconsole: stop charging netpoll users for netconsole-only data
From: Simon Horman @ 2026-07-16 13:21 UTC (permalink / raw)
To: Breno Leitao
Cc: David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Andrew Lunn, netdev, asantostc, gustavold, linux-kernel,
kernel-team
In-Reply-To: <20260710-netconsole_move_more-v3-0-6f63f76b28bc@debian.org>
On Fri, Jul 10, 2026 at 04:38:52AM -0700, Breno Leitao wrote:
> This work continue to untangle netconsole and netpoll, improving
> memory usage for netpoll users that are not netconsole.
>
> struct netpoll is shared by every netpoll consumer in the tree:
> bonding, bridge, team, vlan, macvlan, dsa and netconsole. The non-
> netconsole users only need a per-port handle that lets them transmit
> SKBs.
>
> Yet struct netpoll has accumulated a pile of fields that exist only
> to serve netconsole's printk path:
>
> - skb_pool / refill_wq: the fallback skb pool find_skb() falls back
> on when alloc_skb() returns NULL, plus the workqueue that refills
> it.
> - local_port / remote_port / remote_mac: the source and destination
> UDP ports and the destination ethernet address used to build
> outgoing log packets.
>
> Every netpoll user that allocates a struct netpoll pays for all of
> these fields, even though it never queues a single skb on the pool,
> never sends a UDP frame and never looks at any of the addressing.
>
> Move this netconsole-only state out of the shared struct into struct
> netconsole_target, where its only consumer already lives.
>
> After the series every passive netpoll consumer drops
> sizeof(sk_buff_head) + sizeof(work_struct) + 2 * sizeof(u16) +
> ETH_ALEN bytes per port (plus padding), and struct netpoll keeps only
> what belongs to the generic poll/transmit abstraction or what netpoll
> core still reads itself.
>
> Follow-ups
> ----------
> local_ip, remote_ip and ipv6 are still in struct netpoll. Moving the
> addressing additionally requires relocating netpoll_setup() -- whose
> only caller is netconsole -- and its IPv4/IPv6 helpers, so it is left
> for a follow-up to keep this series focused on a single responsibility
> transfer.
>
> This is pure code motion with no functional change. The pre-existing
> target/device teardown races reported against v1 have since been fixed
> independently (as suggested by Jakub) and are already in the tree, so,
> re-posting this one.
>
> --
>
> Changes in v3:
> - Added a fix for a pre-existing cleanup-skip leak (released/joined targets).
> - Added an skb-pool init-once patch closing an init/teardown race; rebased.
> - Link to v2: https://lore.kernel.org/r/20260702-netconsole_move_more-v2-0-1ebedd921dcb@debian.org
>
> Changes in v2:
> - Rebase on net-next, now that the prerequisite netconsole
> teardown-race fixes are merged.
> - Squash the local_port and remote_port moves into a single patch.
> - v1: https://lore.kernel.org/r/20260524-netconsole_move_more-v1-0-909d1ab398b4@debian.org
For the series:
Reviewed-by: Simon Horman <horms@kernel.org>
^ permalink raw reply
* Re: [PATCH net-next] net: stmmac: dwmac-rk: enable the reference clock for output mode
From: Andrew Lunn @ 2026-07-16 13:21 UTC (permalink / raw)
To: Jiaxing Hu
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, heiko,
mcoquelin.stm32, alexandre.torgue, netdev, linux-rockchip,
linux-arm-kernel, linux-stm32, linux-kernel
In-Reply-To: <02ef3409-4078-4c3a-8c17-cb1a7f1f07e4@smtp-relay.sendinblue.com>
On Thu, Jul 16, 2026 at 06:56:06PM +1200, Jiaxing Hu wrote:
>
> rk_gmac_clk_init() only requests the refout clock group for RMII. The
> ArmSoM CM5 has an on-module YT8531 RGMII PHY with no crystal that needs
> the SoC 25 MHz reference (clk_mac_refout), so in RGMII the clock was
> never enabled and the PHY did not respond on MDIO.
Since the PHY is the consumer of the clock, it would be better if the
PHY enabled the clock.
Andrew
---
pw-bot: cr
^ permalink raw reply
* RE: [PATCH iwl-next v1 1/2] ixgbe: Refactor device operations to check whether netdev is available
From: Temerkhanov, Sergey @ 2026-07-16 13:06 UTC (permalink / raw)
To: Simon Horman; +Cc: intel-wired-lan@lists.osuosl.org, netdev@vger.kernel.org
In-Reply-To: <20260716130254.309674-2-horms@kernel.org>
> -----Original Message-----
> From: Simon Horman <horms@kernel.org>
> Sent: Thursday, July 16, 2026 3:03 PM
> To: Temerkhanov, Sergey <sergey.temerkhanov@intel.com>
> Cc: Simon Horman <horms@kernel.org>; intel-wired-lan@lists.osuosl.org;
> netdev@vger.kernel.org
> Subject: Re: [PATCH iwl-next v1 1/2] ixgbe: Refactor device operations to
> check whether netdev is available
>
> This is an AI-generated review of your patch. The human sending this email
> has considered the AI review valid, or at least plausible.
> https://netdev-ai.bots.linux.dev/sashiko/
> ---
> ixgbe: Refactor device operations to check whether netdev is available
>
> This commit refactors several ixgbe driver operations to check whether the
> netdev they operate on is enabled by introducing an ixgbe_netif_running()
> helper and adding netif_device_present() guards across the ethtool, DCB,
> FCoE and XDP code paths.
>
> > diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > index 8873a8cc4a18..12361ed58a0f 100644
> > --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> > +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
>
> [ ... ]
>
> > @@ -10954,8 +10958,10 @@ static int ixgbe_xdp_setup(struct net_device
> *dev, struct bpf_prog *prog)
> > synchronize_rcu();
> > err = ixgbe_setup_tc(dev, adapter->hw_tcs);
> >
> > - if (err)
> > + if (err) {
> > + xchg(&adapter->xdp_prog, old_prog);
> > return -EINVAL;
> > + }
> > if (!prog)
> > xdp_features_clear_redirect_target(dev);
> > } else {
>
> [Medium]
> The xchg(&adapter->xdp_prog, old_prog) rollback on the ixgbe_setup_tc()
> error path looks like a semantic fix rather than a refactor.
>
> Before this patch the error path left adapter->xdp_prog pointing at prog:
>
> old_prog = xchg(&adapter->xdp_prog, prog);
> ...
> err = ixgbe_setup_tc(dev, adapter->hw_tcs);
> if (err)
> return -EINVAL;
>
> while the ndo_bpf caller dev_xdp_install() drops its reference on prog when
> the driver returns an error:
>
> if (err) {
> if (prog)
> bpf_prog_put(prog);
> return err;
> }
>
> Can this leave adapter->xdp_prog as a dangling pointer to a freed bpf_prog on
> the pre-patch code, which is what the new xchg() restores?
>
> The commit message describes only a refactor and does not mention this
> change.
>
> Should the xdp_prog rollback be split into its own patch with a Fixes:
> tag pointing at the commit that introduced the missing rollback, per
> Documentation/process/submitting-patches.rst which asks for one logical
> change per patch?
>
> The new behavior also skips the subsequent if (old_prog)
> bpf_prog_put(old_prog) in the failure path, which is a separate semantic
> worth calling out in the commit log.
This part is going to a separate patch in v2
Regards,
Sergey
^ permalink raw reply
* Re: [BUG] vlan: skb_under_panic when toggling NETIF_F_HW_VLAN_CTAG_TX on lower device
From: Eric Dumazet @ 2026-07-16 13:06 UTC (permalink / raw)
To: xietangxin
Cc: David S . Miller, Jakub Kicinski, Paolo Abeni, Simon Horman,
netdev, linux-kernel, John Fastabend, Jesse Gross, gaoxingwang1,
huyizhen
In-Reply-To: <CANn89i+z6ECLND1o8oD10re_zGJg73JCOr3dnV9AADeG40K=_Q@mail.gmail.com>
On Thu, Jul 16, 2026 at 2:53 PM Eric Dumazet <edumazet@google.com> wrote:
>
> On Thu, Jul 16, 2026 at 2:20 PM xietangxin <xietangxin@h-partners.com> wrote:
> >
> > [BUG] vlan: skb_under_panic when toggling NETIF_F_HW_VLAN_CTAG_TX on lower device
> >
> > Hi all,
> >
> > We encountered a skb_under_panic triggered by toggling
> > NETIF_F_HW_VLAN_CTAG_TX on the lower device while a VLAN device is
> > up and sending traffic.
> >
> > Call trace
> > ==========
> >
> > skbuff: skb_under_panic: text:ffffc0d2900283d8 len:74 put:14
> > head:ffff334820249c00 data:ffff334820249bfe tail:0x48 end:0xc0 dev:vlan4
> > ------------[ cut here ]------------
> > kernel BUG at net/core/skbuff.c:116!
> > Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
> > Call trace:
> > skb_panic+0xcc/0xd0
> > __skb_checksum+0x0/0x480
> > eth_header+0x48/0x1a0
> > vlan_dev_hard_header+0xd0/0x284
> > neigh_connected_output+0x16c/0x20c
> > ip6_finish_output2+0x4b4/0xd74
> > __ip6_finish_output.part.0+0x1ac/0x3b0
> > ip6_finish_output+0x160/0x200
> > ip6_output+0x13c/0x294
> > ndisc_send_skb+0x41c/0x6f0
> > ndisc_send_rs+0xac/0x3b0
> > addrconf_rs_timer+0x42c/0x660
> > call_timer_fn+0x54/0x290
> > expire_timers+0x26c/0x420
> >
> > Reproducer
> > ==========
> >
> > # Create veth pair (NETIF_F_HW_VLAN_CTAG_TX is ON by default)
> > ip link add veth0 type veth peer name veth1
> > ip link set veth0 up
> > ip link set veth1 up
> >
> > # Turn off HW VLAN TX offload on lower device
> > ethtool -K veth0 tx-vlan-hw-insert off
> >
> > # Create VLAN device on veth0
> > # At this point: header_ops = &vlan_header_ops, hard_header_len = 18
> > ip link add link veth0 name veth0.10 type vlan id 10 reorder_hdr off
> > ip addr add 192.168.10.1/24 dev veth0.10
> > ip link set veth0.10 up
> >
> > # Turn HW VLAN TX offload back ON on lower device
> > # This triggers NETDEV_FEAT_CHANGE -> vlan_transfer_features()
> > # hard_header_len changes from 18 to 14, but header_ops is NOT updated
> > ethtool -K veth0 tx-vlan-hw-insert on
> >
> > # When a packet is sent through veth0.10
> > # - skb is allocated based on hard_header_len=14 -> ~16 bytes
> > # - vlan_dev_hard_header() pushes VLAN_HLEN(4) + ETH_HLEN(14) = 18 bytes
> > # - skb_under_panic!
> >
> >
> > Any feedback or guidance would be greatly appreciated.
>
> This rings a bell, I thought we already fixed this issue long ago :/
>
> I would suggest we always add VLAN_HLEN even if not (yet) needed.
>
> diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
> index 2b74ed56eb166d52c3351768d9dfedc7b2c8ec2d..d7f90b3b2bb3aadb2c466891720a7f407d0bc34b
> 100644
> --- a/net/8021q/vlan.c
> +++ b/net/8021q/vlan.c
> @@ -323,10 +323,7 @@ static void vlan_transfer_features(struct net_device *dev,
>
> netif_inherit_tso_max(vlandev, dev);
>
> - if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto))
> - vlandev->hard_header_len = dev->hard_header_len;
> - else
> - vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
> + vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
>
> #if IS_ENABLED(CONFIG_FCOE)
> vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
>
> A kind-of-similar change is needed in net/8021q/vlan_dev.c
The second part would be a nice cleanup, unless I am missing something.
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 7aa3af8b10ead0384bbb2e767883b63a37be5fa2..dfd907e2ede2dcb0b6120e1fa5b6bb4d30bfb28a
100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -496,26 +496,6 @@ static const struct header_ops vlan_header_ops = {
.parse_protocol = vlan_parse_protocol,
};
-static int vlan_passthru_hard_header(struct sk_buff *skb, struct
net_device *dev,
- unsigned short type,
- const void *daddr, const void *saddr,
- unsigned int len)
-{
- struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
- struct net_device *real_dev = vlan->real_dev;
-
- if (saddr == NULL)
- saddr = dev->dev_addr;
-
- return dev_hard_header(skb, real_dev, type, daddr, saddr, len);
-}
-
-static const struct header_ops vlan_passthru_header_ops = {
- .create = vlan_passthru_hard_header,
- .parse = eth_header_parse,
- .parse_protocol = vlan_parse_protocol,
-};
-
static const struct device_type vlan_type = {
.name = "vlan",
};
@@ -575,13 +555,8 @@ static int vlan_dev_init(struct net_device *dev)
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (vlan_hw_offload_capable(real_dev->features, vlan->vlan_proto)) {
- dev->header_ops = &vlan_passthru_header_ops;
- dev->hard_header_len = real_dev->hard_header_len;
- } else {
- dev->header_ops = &vlan_header_ops;
- dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
- }
+ dev->header_ops = &vlan_header_ops;
+ dev->hard_header_len = real_dev->hard_header_len + VLAN_HLEN;
dev->netdev_ops = &vlan_netdev_ops;
^ permalink raw reply
* Re: [PATCH iwl-next v1 1/2] ixgbe: Refactor device operations to check whether netdev is available
From: Simon Horman @ 2026-07-16 13:03 UTC (permalink / raw)
To: sergey.temerkhanov; +Cc: Simon Horman, intel-wired-lan, netdev
In-Reply-To: <20260710105403.1050025-2-sergey.temerkhanov@intel.com>
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
Full review at: https://sashiko.dev
---
--- Patch [1]: [PATCH iwl-next v1 1/2] ixgbe: Refactor device operations to check whether netdev is available ---
commit f7037ec91fe4185b79d89bd64ec8042f9f9b1904
Author: Sergey Temerkhanov <sergey.temerkhanov@intel.com>
ixgbe: Refactor device operations to check whether netdev is available
Refactor several ixgbe driver operations to check whether the
netdev they operate on is enabled. This will allow the system
to get synchronized, for example, during the PCI resets.
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
> index 011fda9c61939..e4cd4673f21c2 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
> @@ -836,6 +836,10 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
> {
> struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
> struct ixgbe_fcoe *fcoe = &adapter->fcoe;
> + bool running;
> +
> + if (!netif_device_present(netdev))
> + return -ENETDOWN;
>
> atomic_inc(&fcoe->refcnt);
>
> @@ -845,12 +849,14 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
> if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
> return -EINVAL;
[Severity: High]
This is a pre-existing issue, but does this leak the FCoE reference count?
If ixgbe_fcoe_enable() is called when FCoE is already enabled or the adapter
is not FCoE capable, the function returns early without decrementing the
freshly incremented fcoe->refcnt.
Later, when ixgbe_fcoe_disable() is called, atomic_dec_and_test() will not
reach zero, causing it to return -EINVAL without freeing the FCoE DDP pool or
clearing the FCoE flags.
[ ... ]
> @@ -882,6 +888,10 @@ int ixgbe_fcoe_enable(struct net_device *netdev)
> int ixgbe_fcoe_disable(struct net_device *netdev)
> {
> struct ixgbe_adapter *adapter = ixgbe_from_netdev(netdev);
> + bool running;
> +
> + if (!netif_device_present(netdev))
> + return -ENETDOWN;
[Severity: High]
Does this early return cause a memory leak of the FCoE DDP pool?
During a hardware error or device hot-unplug, ixgbe_io_error_detected() calls
netif_device_detach(), which clears the device present state. When the
driver is subsequently removed, the FCoE stack catches the unregister event
and calls ndo_fcoe_disable().
Because the device is already detached, this new early return triggers,
causing the function to skip calling ixgbe_fcoe_ddp_disable(). Will this
abandon the per-CPU DDP pool so it is never freed?
>
> if (!atomic_dec_and_test(&adapter->fcoe.refcnt))
> return -EINVAL;
[ ... ]
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index 8873a8cc4a185..12361ed58a0ff 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
[ ... ]
> @@ -10954,8 +10958,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
> synchronize_rcu();
> err = ixgbe_setup_tc(dev, adapter->hw_tcs);
>
> - if (err)
> + if (err) {
> + xchg(&adapter->xdp_prog, old_prog);
> return -EINVAL;
> + }
[Severity: Critical]
This is a pre-existing issue, but does this error path leave a freed BPF
program installed in the active Rx rings?
If DCB is enabled on the interface, ixgbe_setup_tc() returns -EINVAL.
However, before returning, it calls ixgbe_open() to restart the interface:
ixgbe_setup_tc() {
...
if (running)
return ixgbe_open(dev);
}
During this restart, the Rx rings are initialized and assigned the new BPF
program currently stored in adapter->xdp_prog.
When ixgbe_xdp_setup() sees the error, it restores old_prog and returns
-EINVAL to the network stack, which then frees the new program. The
rx_ring[i]->xdp_prog pointers still reference the freed program. Can this
lead to a use-after-free?
^ permalink raw reply
* Re: [PATCH iwl-next v1 1/2] ixgbe: Refactor device operations to check whether netdev is available
From: Simon Horman @ 2026-07-16 13:02 UTC (permalink / raw)
To: sergey.temerkhanov; +Cc: Simon Horman, intel-wired-lan, netdev
In-Reply-To: <20260710105403.1050025-2-sergey.temerkhanov@intel.com>
This is an AI-generated review of your patch. The human sending this
email has considered the AI review valid, or at least plausible.
https://netdev-ai.bots.linux.dev/sashiko/
---
ixgbe: Refactor device operations to check whether netdev is available
This commit refactors several ixgbe driver operations to check whether
the netdev they operate on is enabled by introducing an ixgbe_netif_running()
helper and adding netif_device_present() guards across the ethtool, DCB,
FCoE and XDP code paths.
> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> index 8873a8cc4a18..12361ed58a0f 100644
> --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
> +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
[ ... ]
> @@ -10954,8 +10958,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
> synchronize_rcu();
> err = ixgbe_setup_tc(dev, adapter->hw_tcs);
>
> - if (err)
> + if (err) {
> + xchg(&adapter->xdp_prog, old_prog);
> return -EINVAL;
> + }
> if (!prog)
> xdp_features_clear_redirect_target(dev);
> } else {
[Medium]
The xchg(&adapter->xdp_prog, old_prog) rollback on the ixgbe_setup_tc()
error path looks like a semantic fix rather than a refactor.
Before this patch the error path left adapter->xdp_prog pointing at prog:
old_prog = xchg(&adapter->xdp_prog, prog);
...
err = ixgbe_setup_tc(dev, adapter->hw_tcs);
if (err)
return -EINVAL;
while the ndo_bpf caller dev_xdp_install() drops its reference on prog
when the driver returns an error:
if (err) {
if (prog)
bpf_prog_put(prog);
return err;
}
Can this leave adapter->xdp_prog as a dangling pointer to a freed
bpf_prog on the pre-patch code, which is what the new xchg() restores?
The commit message describes only a refactor and does not mention this
change.
Should the xdp_prog rollback be split into its own patch with a Fixes:
tag pointing at the commit that introduced the missing rollback, per
Documentation/process/submitting-patches.rst which asks for one logical
change per patch?
The new behavior also skips the subsequent if (old_prog) bpf_prog_put(old_prog)
in the failure path, which is a separate semantic worth calling out in the
commit log.
^ permalink raw reply
* [PATCH net-next 7/7] selftests: net: getsockopt_iter: cover rawv6, ieee802154, phonet and tls
From: Breno Leitao @ 2026-07-16 13:00 UTC (permalink / raw)
To: sdf, David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Alexander Aring, Stefan Schmidt, Miquel Raynal,
Remi Denis-Courmont, Rémi Denis-Courmont, John Fastabend,
Sabrina Dubroca, Shuah Khan
Cc: netdev, linux-kernel, linux-wpan, linux-kselftest, Breno Leitao,
kernel-team
In-Reply-To: <20260716-getsockopt_phase4-v1-0-4f45cb12dce7@debian.org>
Add fixtures for the newly converted getsockopt leaves:
- rawv6: IPV6_HDRINCL / IPV6_CHECKSUM int paths + a SOL_RAW
unknown-optname case that reaches do_rawv6_getsockopt().
- ieee802154: WPAN_WANTACK dgram int path + non-SOL_IEEE802154 level
rejection.
- phonet: PNPIPE_ENCAP pep int path + non-SOL_PNPIPE level
rejection.
- tls: TLS_TX_ZEROCOPY_RO, the TLS_TX crypto_info round-trip at
the base and full cipher sizes, the NULL-optval and short
buffer EINVAL paths, and an unknown optname. It skips when
the kernel lacks TLS or AES-GCM.
Each fixture pins the returned-length / errno semantics across exact,
oversized and short buffers, an unknown optname and a bogus level. The
semantics are unchanged by the sockopt_t conversion, so the tests pass
both before and after the leaf conversions.
Signed-off-by: Breno Leitao <leitao@debian.org>
---
tools/testing/selftests/net/getsockopt_iter.c | 424 ++++++++++++++++++++++++++
1 file changed, 424 insertions(+)
diff --git a/tools/testing/selftests/net/getsockopt_iter.c b/tools/testing/selftests/net/getsockopt_iter.c
index fe5a5268bc34e..974065a23fa82 100644
--- a/tools/testing/selftests/net/getsockopt_iter.c
+++ b/tools/testing/selftests/net/getsockopt_iter.c
@@ -28,7 +28,10 @@
#include <linux/vm_sockets.h>
#include <linux/icmp.h>
#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <arpa/inet.h>
#include <sys/socket.h>
+#include <linux/tls.h>
#include "kselftest_harness.h"
#ifndef AF_VSOCK
@@ -40,6 +43,45 @@
#ifndef ICMP_FILTER
#define ICMP_FILTER 1
#endif
+#ifndef IPV6_HDRINCL
+#define IPV6_HDRINCL 36
+#endif
+#ifndef IPV6_CHECKSUM
+#define IPV6_CHECKSUM 7
+#endif
+#ifndef AF_IEEE802154
+#define AF_IEEE802154 36
+#endif
+#ifndef SOL_IEEE802154
+#define SOL_IEEE802154 0
+#endif
+#ifndef WPAN_WANTACK
+#define WPAN_WANTACK 0
+#endif
+#ifndef AF_PHONET
+#define AF_PHONET 35
+#endif
+#ifndef SOL_PNPIPE
+#define SOL_PNPIPE 275
+#endif
+#ifndef PN_PROTO_PIPE
+#define PN_PROTO_PIPE 2
+#endif
+#ifndef PNPIPE_ENCAP
+#define PNPIPE_ENCAP 1
+#endif
+#ifndef PNPIPE_ENCAP_NONE
+#define PNPIPE_ENCAP_NONE 0
+#endif
+#ifndef PNPIPE_ENCAP_IP
+#define PNPIPE_ENCAP_IP 1
+#endif
+#ifndef SOL_TLS
+#define SOL_TLS 282
+#endif
+#ifndef TCP_ULP
+#define TCP_ULP 31
+#endif
/* ---------- netlink ---------- */
@@ -394,4 +436,386 @@ TEST_F(raw, bad_optname)
ASSERT_EQ(sizeof(val), optlen);
}
+/* ---------- raw (ipv6) ---------- */
+
+FIXTURE(rawv6)
+{
+ int fd;
+};
+
+FIXTURE_SETUP(rawv6)
+{
+ self->fd = socket(AF_INET6, SOCK_RAW, IPPROTO_UDP);
+ if (self->fd < 0)
+ SKIP(return, "SOCK_RAW/IPv6 socket: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(rawv6)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+}
+
+TEST_F(rawv6, hdrincl_exact)
+{
+ socklen_t optlen;
+ int val = -1;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(0, getsockopt(self->fd, IPPROTO_IPV6, IPV6_HDRINCL,
+ &val, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+ ASSERT_TRUE(val == 0 || val == 1);
+}
+
+TEST_F(rawv6, hdrincl_oversize_clamped)
+{
+ char buf[16] = {};
+ socklen_t optlen = sizeof(buf);
+
+ ASSERT_EQ(0, getsockopt(self->fd, IPPROTO_IPV6, IPV6_HDRINCL,
+ buf, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+}
+
+/* Raw int options clamp the reported length down to the user buffer
+ * instead of returning EINVAL on a short buffer.
+ */
+TEST_F(rawv6, hdrincl_undersize_clamped)
+{
+ socklen_t optlen = 2;
+ int val = 0;
+
+ ASSERT_EQ(0, getsockopt(self->fd, IPPROTO_IPV6, IPV6_HDRINCL,
+ &val, &optlen));
+ ASSERT_EQ(2, optlen);
+}
+
+TEST_F(rawv6, checksum_default)
+{
+ socklen_t optlen;
+ int val = 0;
+
+ optlen = sizeof(val);
+
+ /* A non-ICMPv6 raw socket has the checksum disabled, reported as -1. */
+ ASSERT_EQ(0, getsockopt(self->fd, IPPROTO_IPV6, IPV6_CHECKSUM,
+ &val, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+ ASSERT_EQ(-1, val);
+}
+
+TEST_F(rawv6, bad_optname)
+{
+ socklen_t optlen;
+ int val;
+
+ optlen = sizeof(val);
+
+ /* SOL_RAW reaches do_rawv6_getsockopt() directly. */
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_RAW, 0x7fff, &val, &optlen));
+ ASSERT_EQ(ENOPROTOOPT, errno);
+ ASSERT_EQ(sizeof(val), optlen);
+}
+
+/* ---------- ieee802154 (dgram) ---------- */
+
+FIXTURE(ieee802154)
+{
+ int fd;
+};
+
+FIXTURE_SETUP(ieee802154)
+{
+ self->fd = socket(AF_IEEE802154, SOCK_DGRAM, 0);
+ if (self->fd < 0)
+ SKIP(return, "AF_IEEE802154 dgram socket: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(ieee802154)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+}
+
+TEST_F(ieee802154, wantack_exact)
+{
+ socklen_t optlen;
+ int val = -1;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_IEEE802154, WPAN_WANTACK,
+ &val, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+ ASSERT_TRUE(val == 0 || val == 1);
+}
+
+TEST_F(ieee802154, wantack_oversize_clamped)
+{
+ char buf[16] = {};
+ socklen_t optlen = sizeof(buf);
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_IEEE802154, WPAN_WANTACK,
+ buf, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+}
+
+TEST_F(ieee802154, wantack_undersize_clamped)
+{
+ socklen_t optlen = 2;
+ int val = 0;
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_IEEE802154, WPAN_WANTACK,
+ &val, &optlen));
+ ASSERT_EQ(2, optlen);
+}
+
+TEST_F(ieee802154, bad_optname)
+{
+ socklen_t optlen;
+ int val;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_IEEE802154, 0x7fff,
+ &val, &optlen));
+ ASSERT_EQ(ENOPROTOOPT, errno);
+ ASSERT_EQ(sizeof(val), optlen);
+}
+
+/* dgram_getsockopt() rejects any level other than SOL_IEEE802154. */
+TEST_F(ieee802154, bad_level)
+{
+ socklen_t optlen;
+ int val;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_RAW, WPAN_WANTACK,
+ &val, &optlen));
+ ASSERT_EQ(EOPNOTSUPP, errno);
+ ASSERT_EQ(sizeof(val), optlen);
+}
+
+/* ---------- phonet (pep) ---------- */
+
+FIXTURE(phonet)
+{
+ int fd;
+};
+
+FIXTURE_SETUP(phonet)
+{
+ self->fd = socket(AF_PHONET, SOCK_SEQPACKET, PN_PROTO_PIPE);
+ if (self->fd < 0)
+ SKIP(return, "AF_PHONET pipe socket: %s", strerror(errno));
+}
+
+FIXTURE_TEARDOWN(phonet)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+}
+
+TEST_F(phonet, encap_exact)
+{
+ socklen_t optlen;
+ int val = -1;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_PNPIPE, PNPIPE_ENCAP,
+ &val, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+ ASSERT_TRUE(val == PNPIPE_ENCAP_NONE || val == PNPIPE_ENCAP_IP);
+}
+
+TEST_F(phonet, encap_oversize_clamped)
+{
+ char buf[16] = {};
+ socklen_t optlen = sizeof(buf);
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_PNPIPE, PNPIPE_ENCAP,
+ buf, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+}
+
+/* pep clamps the reported length down to the user buffer. Use an
+ * int-sized backing buffer with a short optlen so the baseline kernel,
+ * which writes a full int via put_user(), does not scribble past it.
+ */
+TEST_F(phonet, encap_undersize_clamped)
+{
+ socklen_t optlen = 2;
+ int val = 0;
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_PNPIPE, PNPIPE_ENCAP,
+ &val, &optlen));
+ ASSERT_EQ(2, optlen);
+}
+
+TEST_F(phonet, bad_optname)
+{
+ socklen_t optlen;
+ int val;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_PNPIPE, 0x7fff, &val, &optlen));
+ ASSERT_EQ(ENOPROTOOPT, errno);
+ ASSERT_EQ(sizeof(val), optlen);
+}
+
+/* pep_getsockopt() rejects any level other than SOL_PNPIPE. */
+TEST_F(phonet, bad_level)
+{
+ socklen_t optlen;
+ int val;
+
+ optlen = sizeof(val);
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_RAW, PNPIPE_ENCAP, &val, &optlen));
+ ASSERT_EQ(ENOPROTOOPT, errno);
+ ASSERT_EQ(sizeof(val), optlen);
+}
+
+/* ---------- tls ---------- */
+
+FIXTURE(tls)
+{
+ int fd;
+ int sfd;
+};
+
+FIXTURE_SETUP(tls)
+{
+ struct sockaddr_in a = {
+ .sin_family = AF_INET,
+ .sin_addr.s_addr = htonl(INADDR_LOOPBACK),
+ };
+ socklen_t alen = sizeof(a);
+ int lfd;
+
+ self->fd = -1;
+ self->sfd = -1;
+
+ lfd = socket(AF_INET, SOCK_STREAM, 0);
+ if (lfd < 0)
+ SKIP(return, "TCP socket: %s", strerror(errno));
+ if (bind(lfd, (struct sockaddr *)&a, sizeof(a)) || listen(lfd, 1) ||
+ getsockname(lfd, (struct sockaddr *)&a, &alen)) {
+ close(lfd);
+ SKIP(return, "listener setup: %s", strerror(errno));
+ }
+ self->fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (connect(self->fd, (struct sockaddr *)&a, sizeof(a))) {
+ close(lfd);
+ SKIP(return, "connect: %s", strerror(errno));
+ }
+ self->sfd = accept(lfd, NULL, NULL);
+ close(lfd);
+ if (setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")))
+ SKIP(return, "TCP_ULP=tls: %s (built without TLS?)",
+ strerror(errno));
+}
+
+FIXTURE_TEARDOWN(tls)
+{
+ if (self->fd >= 0)
+ close(self->fd);
+ if (self->sfd >= 0)
+ close(self->sfd);
+}
+
+/* do_tls_getsockopt_tx_zc(): fixed-size int, exact length required. */
+TEST_F(tls, tx_zerocopy_exact)
+{
+ socklen_t optlen = sizeof(int);
+ int val = -1;
+
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_TLS, TLS_TX_ZEROCOPY_RO,
+ &val, &optlen));
+ ASSERT_EQ(sizeof(int), optlen);
+ ASSERT_TRUE(val == 0 || val == 1);
+}
+
+TEST_F(tls, tx_zerocopy_wrong_len)
+{
+ socklen_t optlen = 2;
+ int val;
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_TLS, TLS_TX_ZEROCOPY_RO,
+ &val, &optlen));
+ ASSERT_EQ(EINVAL, errno);
+}
+
+/* do_tls_getsockopt_conf(): NULL optval still yields EINVAL -- the
+ * converted code tests opt->iter_out.ubuf in place of optval.
+ */
+TEST_F(tls, conf_null_optval)
+{
+ socklen_t optlen = 64;
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_TLS, TLS_TX, NULL, &optlen));
+ ASSERT_EQ(EINVAL, errno);
+}
+
+TEST_F(tls, conf_short)
+{
+ socklen_t optlen = 2;
+ char buf[2];
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_TLS, TLS_TX, buf, &optlen));
+ ASSERT_EQ(EINVAL, errno);
+}
+
+/* TLS_TX before crypto is set reports not-ready. */
+TEST_F(tls, conf_not_ready)
+{
+ struct tls_crypto_info info;
+ socklen_t optlen = sizeof(info);
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_TLS, TLS_TX, &info, &optlen));
+ ASSERT_EQ(EBUSY, errno);
+}
+
+/* Set TX crypto, then read it back at the base and full sizes, exercising
+ * both copy_to_iter() branches. SKIP if AES-GCM is unavailable.
+ */
+TEST_F(tls, conf_crypto_roundtrip)
+{
+ struct tls12_crypto_info_aes_gcm_128 tx = {
+ .info.version = TLS_1_2_VERSION,
+ .info.cipher_type = TLS_CIPHER_AES_GCM_128,
+ };
+ struct tls12_crypto_info_aes_gcm_128 full;
+ struct tls_crypto_info base;
+ socklen_t optlen;
+
+ if (setsockopt(self->fd, SOL_TLS, TLS_TX, &tx, sizeof(tx)))
+ SKIP(return, "set TLS_TX aes_gcm_128: %s", strerror(errno));
+
+ optlen = sizeof(base);
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_TLS, TLS_TX, &base, &optlen));
+ ASSERT_EQ(sizeof(base), optlen);
+ ASSERT_EQ(TLS_1_2_VERSION, base.version);
+ ASSERT_EQ(TLS_CIPHER_AES_GCM_128, base.cipher_type);
+
+ optlen = sizeof(full);
+ ASSERT_EQ(0, getsockopt(self->fd, SOL_TLS, TLS_TX, &full, &optlen));
+ ASSERT_EQ(sizeof(full), optlen);
+ ASSERT_EQ(TLS_CIPHER_AES_GCM_128, full.info.cipher_type);
+}
+
+TEST_F(tls, bad_optname)
+{
+ socklen_t optlen = sizeof(int);
+ int val;
+
+ ASSERT_EQ(-1, getsockopt(self->fd, SOL_TLS, 0x7fff, &val, &optlen));
+ ASSERT_EQ(ENOPROTOOPT, errno);
+}
+
TEST_HARNESS_MAIN
--
2.53.0-Meta
^ permalink raw reply related
* [PATCH net-next 6/7] tls: convert getsockopt to sockopt_t
From: Breno Leitao @ 2026-07-16 13:00 UTC (permalink / raw)
To: sdf, David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Alexander Aring, Stefan Schmidt, Miquel Raynal,
Remi Denis-Courmont, Rémi Denis-Courmont, John Fastabend,
Sabrina Dubroca, Shuah Khan
Cc: netdev, linux-kernel, linux-wpan, linux-kselftest, Breno Leitao,
kernel-team
In-Reply-To: <20260716-getsockopt_phase4-v1-0-4f45cb12dce7@debian.org>
Continue converting the proto-layer getsockopt callbacks to the sockopt_t
interface, converting do_tls_getsockopt() and its per-option helpers to
take a sockopt_t.
The thin tls_getsockopt() wrapper keeps its __user signature for now: it
builds a user-backed sockopt_t with sockopt_init_user(), calls the helper,
and writes the returned length back to optlen. The helpers use
copy_to_iter() instead of copy_to_user(); the NULL optval check in the
TLS_TX/TLS_RX path is preserved by testing the iterator user buffer.
No functional change.
Signed-off-by: Breno Leitao <leitao@debian.org>
---
net/tls/tls_main.c | 80 ++++++++++++++++++++++++++----------------------------
1 file changed, 38 insertions(+), 42 deletions(-)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 8c588cdab733d..fbb274287aa5f 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -424,20 +424,16 @@ static __poll_t tls_sk_poll(struct file *file, struct socket *sock,
return mask;
}
-static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
- int __user *optlen, int tx)
+static int do_tls_getsockopt_conf(struct sock *sk, sockopt_t *opt, int tx)
{
int rc = 0;
const struct tls_cipher_desc *cipher_desc;
struct tls_context *ctx = tls_get_ctx(sk);
struct tls_crypto_info *crypto_info;
struct cipher_context *cctx;
- int len;
+ int len = opt->optlen;
- if (get_user(len, optlen))
- return -EFAULT;
-
- if (!optval || (len < sizeof(*crypto_info))) {
+ if (!opt->iter_out.ubuf || len < sizeof(*crypto_info)) {
rc = -EINVAL;
goto out;
}
@@ -462,7 +458,8 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
}
if (len == sizeof(*crypto_info)) {
- if (copy_to_user(optval, crypto_info, sizeof(*crypto_info)))
+ if (copy_to_iter(crypto_info, sizeof(*crypto_info),
+ &opt->iter_out) != sizeof(*crypto_info))
rc = -EFAULT;
goto out;
}
@@ -478,44 +475,38 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
memcpy(crypto_info_rec_seq(crypto_info, cipher_desc),
cctx->rec_seq, cipher_desc->rec_seq);
- if (copy_to_user(optval, crypto_info, cipher_desc->crypto_info))
+ if (copy_to_iter(crypto_info, cipher_desc->crypto_info,
+ &opt->iter_out) != cipher_desc->crypto_info)
rc = -EFAULT;
out:
return rc;
}
-static int do_tls_getsockopt_tx_zc(struct sock *sk, char __user *optval,
- int __user *optlen)
+static int do_tls_getsockopt_tx_zc(struct sock *sk, sockopt_t *opt)
{
struct tls_context *ctx = tls_get_ctx(sk);
unsigned int value;
- int len;
-
- if (get_user(len, optlen))
- return -EFAULT;
+ int len = opt->optlen;
if (len != sizeof(value))
return -EINVAL;
value = ctx->zerocopy_sendfile;
- if (copy_to_user(optval, &value, sizeof(value)))
+ if (copy_to_iter(&value, sizeof(value), &opt->iter_out) != sizeof(value))
return -EFAULT;
return 0;
}
-static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval,
- int __user *optlen)
+static int do_tls_getsockopt_no_pad(struct sock *sk, sockopt_t *opt)
{
struct tls_context *ctx = tls_get_ctx(sk);
- int value, len;
+ int value, len = opt->optlen;
if (ctx->prot_info.version != TLS_1_3_VERSION)
return -EINVAL;
- if (get_user(len, optlen))
- return -EFAULT;
if (len < sizeof(value))
return -EINVAL;
@@ -525,38 +516,31 @@ static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval,
if (value < 0)
return value;
- if (put_user(sizeof(value), optlen))
- return -EFAULT;
- if (copy_to_user(optval, &value, sizeof(value)))
+ opt->optlen = sizeof(value);
+ if (copy_to_iter(&value, sizeof(value), &opt->iter_out) != sizeof(value))
return -EFAULT;
return 0;
}
-static int do_tls_getsockopt_tx_payload_len(struct sock *sk, char __user *optval,
- int __user *optlen)
+static int do_tls_getsockopt_tx_payload_len(struct sock *sk, sockopt_t *opt)
{
struct tls_context *ctx = tls_get_ctx(sk);
u16 payload_len = ctx->tx_max_payload_len;
- int len;
-
- if (get_user(len, optlen))
- return -EFAULT;
+ int len = opt->optlen;
if (len < sizeof(payload_len))
return -EINVAL;
- if (put_user(sizeof(payload_len), optlen))
- return -EFAULT;
-
- if (copy_to_user(optval, &payload_len, sizeof(payload_len)))
+ opt->optlen = sizeof(payload_len);
+ if (copy_to_iter(&payload_len, sizeof(payload_len),
+ &opt->iter_out) != sizeof(payload_len))
return -EFAULT;
return 0;
}
-static int do_tls_getsockopt(struct sock *sk, int optname,
- char __user *optval, int __user *optlen)
+static int do_tls_getsockopt(struct sock *sk, int optname, sockopt_t *opt)
{
int rc = 0;
@@ -565,17 +549,16 @@ static int do_tls_getsockopt(struct sock *sk, int optname,
switch (optname) {
case TLS_TX:
case TLS_RX:
- rc = do_tls_getsockopt_conf(sk, optval, optlen,
- optname == TLS_TX);
+ rc = do_tls_getsockopt_conf(sk, opt, optname == TLS_TX);
break;
case TLS_TX_ZEROCOPY_RO:
- rc = do_tls_getsockopt_tx_zc(sk, optval, optlen);
+ rc = do_tls_getsockopt_tx_zc(sk, opt);
break;
case TLS_RX_EXPECT_NO_PAD:
- rc = do_tls_getsockopt_no_pad(sk, optval, optlen);
+ rc = do_tls_getsockopt_no_pad(sk, opt);
break;
case TLS_TX_MAX_PAYLOAD_LEN:
- rc = do_tls_getsockopt_tx_payload_len(sk, optval, optlen);
+ rc = do_tls_getsockopt_tx_payload_len(sk, opt);
break;
default:
rc = -ENOPROTOOPT;
@@ -591,12 +574,25 @@ static int tls_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct tls_context *ctx = tls_get_ctx(sk);
+ sockopt_t opt;
+ int err;
if (level != SOL_TLS)
return ctx->sk_proto->getsockopt(sk, level,
optname, optval, optlen);
- return do_tls_getsockopt(sk, optname, optval, optlen);
+ err = sockopt_init_user(&opt, optval, optlen);
+ if (err)
+ return err;
+
+ err = do_tls_getsockopt(sk, optname, &opt);
+ if (err)
+ return err;
+
+ if (put_user(opt.optlen, optlen))
+ return -EFAULT;
+
+ return 0;
}
static int validate_crypto_info(const struct tls_crypto_info *crypto_info,
--
2.53.0-Meta
^ permalink raw reply related
* Re: [PATCH net-next v2 2/2] net: phy: add DAPU Telecom DAP8210R(I) Gigabit Ethernet PHY driver
From: Maxime Chevallier @ 2026-07-16 13:01 UTC (permalink / raw)
To: Artem Shimko, netdev, Andrew Lunn, Heiner Kallweit, Russell King,
David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Rob Herring, Krzysztof Kozlowski, Conor Dooley
Cc: linux-kernel, devicetree
In-Reply-To: <20260716113805.593215-3-a.shimko.dev@gmail.com>
Hi,
On 7/16/26 13:38, Artem Shimko wrote:
> Add a new PHY driver for the DAPU Telecom DAP8211R(I) Gigabit
> Ethernet PHY, which is commonly used in enterprise and industrial
> networking applications.
>
> The driver implements extended register access via indirect addressing
> through corresponding registers, and provides comprehensive device tree
> support for RGMII delay configuration. The rx-internal-delay-ps and
> tx-internal-delay-ps properties allow precise tuning of clock delays in
> 150 ps steps from 0 to 2250 ps. Additionally, the optional
> dapu,tx-inverted-clk flag enables 180-degree TX clock phase shift for
> boards where signal integrity or MAC requirements necessitate clock
> inversion.
>
> Signed-off-by: Artem Shimko <a.shimko.dev@gmail.com>
> ---
> drivers/net/phy/Kconfig | 10 ++
> drivers/net/phy/Makefile | 1 +
> drivers/net/phy/dap8211r.c | 281 +++++++++++++++++++++++++++++++++++++
> 3 files changed, 292 insertions(+)
> create mode 100644 drivers/net/phy/dap8211r.c
>
> diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
> index 099f25dceabb..4576f707ac94 100644
> --- a/drivers/net/phy/Kconfig
> +++ b/drivers/net/phy/Kconfig
> @@ -237,6 +237,16 @@ config DAVICOM_PHY
> help
> Currently supports dm9161e and dm9131
>
> +config DAP8211R_PHY
> + tristate "DAPU Telecom DAP8211R(I) Gigabit Ethernet PHY"
> + depends on OF
> + help
> + Support for the DAPU Telecom DAP8211R(I) Gigabit Ethernet PHY.
> + This PHY is designed for enterprise and industrial networking
> + applications, supporting 10/100/1000 Mbps operation.
> + RGMII with: configurable TX/RX clock delays, optional flag to enable
> + 180-degree TX clock phase shift and internal packet generator.
> +
> config ICPLUS_PHY
> tristate "ICPlus PHYs"
> help
> diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
> index de660ae94945..ad35733eb4bb 100644
> --- a/drivers/net/phy/Makefile
> +++ b/drivers/net/phy/Makefile
> @@ -53,6 +53,7 @@ obj-$(CONFIG_BROADCOM_PHY) += broadcom.o
> obj-$(CONFIG_CICADA_PHY) += cicada.o
> obj-$(CONFIG_CORTINA_PHY) += cortina.o
> obj-$(CONFIG_DAVICOM_PHY) += davicom.o
> +obj-$(CONFIG_DAP8211R_PHY) += dap8211r.o
> obj-$(CONFIG_DP83640_PHY) += dp83640.o
> obj-$(CONFIG_DP83822_PHY) += dp83822.o
> obj-$(CONFIG_DP83848_PHY) += dp83848.o
> diff --git a/drivers/net/phy/dap8211r.c b/drivers/net/phy/dap8211r.c
> new file mode 100644
> index 000000000000..e1e6a322ef0c
> --- /dev/null
> +++ b/drivers/net/phy/dap8211r.c
> @@ -0,0 +1,281 @@
> +// SPDX-License-Identifier: GPL
> +/*
> + * Driver for the DAPU Telecom DAP8211R(I) Gigabit Ethernet PHY.
> + *
> + * Specifications:
> + * - IEEE 802.3 10BASE-Te, 100BASE-TX, 1000BASE-T
> + * - IEEE 802.3az-2010 Energy Efficient Ethernet
> + * - IEEE 1588 SyncE support
> + * - RGMII
> + *
> + * Author: Artem Shimko <a.shimko.dev@gmail.com>
> + */
> +
> +#include <linux/bitfield.h>
> +#include <linux/errno.h>
> +#include <linux/ethtool.h>
> +#include <linux/kernel.h>
> +#include <linux/mii.h>
> +#include <linux/module.h>
> +#include <linux/netdevice.h>
> +#include <linux/of.h>
> +#include <linux/phy.h>
> +
> +#define DAP8211R_PHY_ID 0x0008011B
> +#define DAP8211R_PHY_ID_MASK 0xFFFFFFFF
> +
> +#define DAP8211R_EXT_ADD 0x1E
> +#define DAP8211R_EXT_DATA 0x1F
> +
> +#define DAP8211R_PHY_CON 0xA001
> +#define DAP8211R_PHY_SW_RST BIT(15)
> +
> +#define DAP8211R_RGMII_CON 0xA003
> +#define DAP8211R_RGMII_TX_DEL_MASK GENMASK(3, 0)
> +#define DAP8211R_RGMII_RX_DEL_MASK GENMASK(13, 10)
> +#define DAP8211R_RGMII_CLK_INVERT BIT(14)
> +
> +/* Default RGMII delay: 13 * 150 == 1.95ns */
> +#define DAP8211R_DEFAULT_DELAY_SEL 0xD
> +
> +struct dap8211r_delay_config {
> + u32 ps;
> + u8 sel;
> +};
> +
> +static const struct dap8211r_delay_config delay_config[] = {
> + { 0, 0},
> + { 150, 1},
> + { 300, 2},
> + { 450, 3},
> + { 600, 4},
> + { 750, 5},
> + { 900, 6},
> + {1050, 7},
> + {1200, 8},
> + {1350, 9},
> + {1500, 10},
> + {1650, 11},
> + {1800, 12},
> + {1950, 13},
> + {2100, 14},
> + {2250, 15},
> +};
> +
> +#define DAP8211R_DELAY_COUNT ARRAY_SIZE(delay_config)
> +
> +/**
> + * dap8211r_delay_ps_to_sel() - Convert ps to register value (exact match only)
> + * @ps: Delay in picoseconds
> + *
> + * Converts a delay value in picoseconds to the corresponding register value
> + * for RGMII delay configuration. The PHY supports specific values from
> + * 0 to 2250 ps in 150 ps steps.
> + *
> + * Return: Register value (0-15) on success, -EINVAL if @ps is not supported.
> + */
> +
> +static int dap8211r_delay_ps_to_sel(u32 ps)
> +{
> + for (int i = 0; i < DAP8211R_DELAY_COUNT; i++)
> + if (ps == delay_config[i].ps)
> + return delay_config[i].sel;
> +
> + return -EINVAL;
> +}
> +
> +/**
> + * dap8211r_read_ext() - Read extended register
> + * @phydev: PHY device structure
> + * @reg: Extended register address
> + *
> + * Reads a PHY extended register using the indirect access method.
> + * The caller must hold the MDIO bus lock.
> + *
> + * Return: Register value on success, or negative error code
> + */
> +static int dap8211r_read_ext(struct phy_device *phydev, u16 reg)
> +{
> + int ret;
> +
> + phy_lock_mdio_bus(phydev);
> + ret = __phy_write(phydev, DAP8211R_EXT_ADD, reg);
> + if (ret < 0)
> + goto out;
> +
> + ret = __phy_read(phydev, DAP8211R_EXT_DATA);
> +out:
> + phy_unlock_mdio_bus(phydev);
> + return ret;
> +}
> +
> +/**
> + * dap8211r_modify_ext() - Modify extended register bits
> + * @phydev: PHY device structure
> + * @reg: Extended register address
> + * @mask: Bit mask of bits to clear
> + * @set: Bit mask of bits to set
> + *
> + * Modifies a PHY extended register using the indirect access method.
> + * New value = (old value & ~mask) | set.
> + * The caller must hold the MDIO bus lock.
> + *
> + * Return: 0 on success, or negative error code
> + */
> +static int dap8211r_modify_ext(struct phy_device *phydev, u16 reg, u16 mask, u16 set)
> +{
> + int ret;
> +
> + phy_lock_mdio_bus(phydev);
> + ret = __phy_write(phydev, DAP8211R_EXT_ADD, reg);
> + if (ret < 0)
> + goto out;
> +
> + ret = __phy_modify(phydev, DAP8211R_EXT_DATA, mask, set);
> +out:
> + phy_unlock_mdio_bus(phydev);
> + return ret;
> +}
> +
> +/**
> + * dap8211r_get_rgmii_delay() - Get RGMII delay from DT
> + * @phydev: PHY device
> + * @prop_name: DT property name
> + * @is_id: If phy mode is PHY_INTERFACE_MODE_RGMII_[TXID,RXID,ID]
> + *
> + * Reads the RGMII delay from the device tree. If the property is not
> + * specified, the default delay (1950ps) is used.
> + *
> + * Return: Register value (0-15) on success, negative error code on failure.
> + * -EINVAL: Property not specified and is_id is false.
> + */
> +static int dap8211r_get_rgmii_delay(struct phy_device *phydev, const char *prop_name, bool is_id)
> +{
> + struct device_node *np = phydev->mdio.dev.of_node;
> + u32 ps = 0;
> + int ret;
> +
> + ret = of_property_read_u32(np, prop_name, &ps);
> + if (ret == -EINVAL)
> + return (is_id) ? DAP8211R_DEFAULT_DELAY_SEL : ret;
> + if (ret < 0)
> + return ret;
> +
> + return dap8211r_delay_ps_to_sel(ps);
> +}
> +
> +/**
> + * dap8211r_config_init() - Initialize PHY
> + * @phydev: PHY device structure
> + *
> + * Configures the PHY during initialization:
> + * - RGMII delays based on interface mode
> + * - TX clock invertion
> + * - Software reset to apply settings (low active, self clear)
> + *
> + * Return: 0 on success, or negative error code
> + */
> +static int dap8211r_config_init(struct phy_device *phydev)
> +{
> + struct device_node *phydev_node = phydev->mdio.dev.of_node;
> + u16 mask = 0, set = 0;
> + int ret, retries = 10;
> +
> + switch (phydev->interface) {
> + case PHY_INTERFACE_MODE_RGMII:
> + ret = dap8211r_get_rgmii_delay(phydev, "rx-internal-delay-ps", false);
> + if (ret >= 0) {
> + set = FIELD_PREP(DAP8211R_RGMII_RX_DEL_MASK, ret);
> + mask = DAP8211R_RGMII_RX_DEL_MASK;
> + } else if ((ret < 0) && (ret != -EINVAL)) {
> + return ret;
> + }
> +
> + ret = dap8211r_get_rgmii_delay(phydev, "tx-internal-delay-ps", false);
> + if (ret >= 0) {
> + set |= FIELD_PREP(DAP8211R_RGMII_TX_DEL_MASK, ret);
> + mask |= DAP8211R_RGMII_TX_DEL_MASK;
> + } else if ((ret < 0) && (ret != -EINVAL)) {
> + return ret;
> + }
> + break;
> + case PHY_INTERFACE_MODE_RGMII_RXID:
> + ret = dap8211r_get_rgmii_delay(phydev, "rx-internal-delay-ps", true);
> + if (ret < 0)
> + return ret;
> +
> + set = FIELD_PREP(DAP8211R_RGMII_RX_DEL_MASK, ret);
> + mask = DAP8211R_RGMII_RX_DEL_MASK;
> + break;
> + case PHY_INTERFACE_MODE_RGMII_ID:
> + ret = dap8211r_get_rgmii_delay(phydev, "rx-internal-delay-ps", true);
> + if (ret < 0)
> + return ret;
> +
> + set = FIELD_PREP(DAP8211R_RGMII_RX_DEL_MASK, ret);
> + mask = DAP8211R_RGMII_RX_DEL_MASK;
> + fallthrough;
> + case PHY_INTERFACE_MODE_RGMII_TXID:
> + ret = dap8211r_get_rgmii_delay(phydev, "tx-internal-delay-ps", true);
> + if (ret < 0)
> + return ret;
> +
> + set |= FIELD_PREP(DAP8211R_RGMII_TX_DEL_MASK, ret);
> + mask |= DAP8211R_RGMII_TX_DEL_MASK;
> + break;
> + default:
> + phydev_err(phydev, "Unsupported interface: %d\n",
> + phydev->interface);
> + return -EINVAL;
> + }
You can simplify the whole delay parsing a log by using phy_get_internal_delay().
It will give you the index of the delay from the delay table you have :)
https://elixir.bootlin.com/linux/v7.1.3/source/drivers/net/phy/phy_device.c#L3085
You can take a look at the few drivers that use it (mscc, dp83869) for reference
Maxime
^ permalink raw reply
* [PATCH net-next 5/7] phonet: pep: convert getsockopt to sockopt_t
From: Breno Leitao @ 2026-07-16 13:00 UTC (permalink / raw)
To: sdf, David S. Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni,
Simon Horman, Alexander Aring, Stefan Schmidt, Miquel Raynal,
Remi Denis-Courmont, Rémi Denis-Courmont, John Fastabend,
Sabrina Dubroca, Shuah Khan
Cc: netdev, linux-kernel, linux-wpan, linux-kselftest, Breno Leitao,
kernel-team
In-Reply-To: <20260716-getsockopt_phase4-v1-0-4f45cb12dce7@debian.org>
Continue converting the proto-layer getsockopt callbacks to the
sockopt_t interface, splitting pep_getsockopt() into a
do_pep_getsockopt() helper that takes a sockopt_t.
The thin pep_getsockopt() wrapper keeps its __user signature for now:
it builds a user-backed sockopt_t with sockopt_init_user(), calls the
helper, and writes the returned length back to optlen. The helper uses
copy_to_iter() instead of copy_to_user(). No functional change.
Signed-off-by: Breno Leitao <leitao@debian.org>
---
net/phonet/pep.c | 36 ++++++++++++++++++++++++++----------
1 file changed, 26 insertions(+), 10 deletions(-)
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 60d1a5375725b..c7f4ce894af56 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -1078,17 +1078,11 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
return err;
}
-static int pep_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
+static int do_pep_getsockopt(struct sock *sk, int optname, sockopt_t *opt)
{
struct pep_sock *pn = pep_sk(sk);
int len, val;
- if (level != SOL_PNPIPE)
- return -ENOPROTOOPT;
- if (get_user(len, optlen))
- return -EFAULT;
-
switch (optname) {
case PNPIPE_ENCAP:
val = pn->ifindex ? PNPIPE_ENCAP_IP : PNPIPE_ENCAP_NONE;
@@ -1112,11 +1106,33 @@ static int pep_getsockopt(struct sock *sk, int level, int optname,
return -ENOPROTOOPT;
}
- len = min_t(unsigned int, sizeof(int), len);
- if (put_user(len, optlen))
+ len = min_t(unsigned int, sizeof(int), opt->optlen);
+ opt->optlen = len;
+ if (copy_to_iter(&val, len, &opt->iter_out) != len)
return -EFAULT;
- if (copy_to_user(optval, &val, len))
+ return 0;
+}
+
+static int pep_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ sockopt_t opt;
+ int err;
+
+ if (level != SOL_PNPIPE)
+ return -ENOPROTOOPT;
+
+ err = sockopt_init_user(&opt, optval, optlen);
+ if (err)
+ return err;
+
+ err = do_pep_getsockopt(sk, optname, &opt);
+ if (err)
+ return err;
+
+ if (put_user(opt.optlen, optlen))
return -EFAULT;
+
return 0;
}
--
2.53.0-Meta
^ 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