Linux Networking and Network Devices APIs¶
Linux Networking¶
Networking Base Types¶
-
enum
sock_type
¶ Socket types
Constants
SOCK_STREAM
stream (connection) socket
SOCK_DGRAM
datagram (conn.less) socket
SOCK_RAW
raw socket
SOCK_RDM
reliably-delivered message
SOCK_SEQPACKET
sequential packet socket
SOCK_DCCP
Datagram Congestion Control Protocol socket
SOCK_PACKET
linux specific way of getting packets at the dev level. For writing rarp and other similar things on the user level.
Description
When adding some new socket type please grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS overrides this enum for binary compat reasons.
-
enum
sock_shutdown_cmd
¶ Shutdown types
Constants
SHUT_RD
shutdown receptions
SHUT_WR
shutdown transmissions
SHUT_RDWR
shutdown receptions/transmissions
-
struct
socket
¶ general BSD socket
Definition
struct socket {
socket_state state;
short type;
unsigned long flags;
struct file *file;
struct sock *sk;
const struct proto_ops *ops;
struct socket_wq wq;
};
Members
state
socket state (
SS_CONNECTED
, etc)type
socket type (
SOCK_STREAM
, etc)flags
socket flags (
SOCK_NOSPACE
, etc)file
File back pointer for gc
sk
internal networking protocol agnostic socket representation
ops
protocol specific socket operations
wq
wait queue for several uses
Socket Buffer Functions¶
-
unsigned int
skb_frag_size
(const skb_frag_t *frag)¶ Returns the size of a skb fragment
Parameters
const skb_frag_t *frag
skb fragment
-
void
skb_frag_size_set
(skb_frag_t *frag, unsigned int size)¶ Sets the size of a skb fragment
Parameters
skb_frag_t *frag
skb fragment
unsigned int size
size of fragment
-
void
skb_frag_size_add
(skb_frag_t *frag, int delta)¶ Increments the size of a skb fragment by delta
Parameters
skb_frag_t *frag
skb fragment
int delta
value to add
-
void
skb_frag_size_sub
(skb_frag_t *frag, int delta)¶ Decrements the size of a skb fragment by delta
Parameters
skb_frag_t *frag
skb fragment
int delta
value to subtract
-
bool
skb_frag_must_loop
(struct page *p)¶ Test if
p
is a high memory page
Parameters
struct page *p
fragment’s page
-
skb_frag_foreach_page
(f, f_off, f_len, p, p_off, p_len, copied)¶ loop over pages in a fragment
Parameters
f
skb frag to operate on
f_off
offset from start of f->bv_page
f_len
length from f_off to loop over
p
(temp var) current page
p_off
(temp var) offset from start of current page, non-zero only on first page.
p_len
(temp var) length in current page, < PAGE_SIZE only on first and last page.
copied
(temp var) length so far, excluding current p_len.
A fragment can hold a compound page, in which case per-page operations, notably kmap_atomic, must be called for each regular page.
hardware time stamps
Definition
struct skb_shared_hwtstamps {
ktime_t hwtstamp;
};
Members
hwtstamp
hardware time stamp transformed into duration since arbitrary point in time
Description
Software time stamps generated by ktime_get_real()
are stored in
skb->tstamp.
hwtstamps can only be compared against other hwtstamps from the same device.
This structure is attached to packets as part of the
skb_shared_info
. Use skb_hwtstamps() to get a pointer.
-
struct
sk_buff
¶ socket buffer
Definition
struct sk_buff {
union {
struct {
struct sk_buff *next;
struct sk_buff *prev;
union {
struct net_device *dev;
unsigned long dev_scratch;
};
};
struct rb_node rbnode;
struct list_head list;
struct llist_node ll_node;
};
union {
struct sock *sk;
int ip_defrag_offset;
};
union {
ktime_t tstamp;
u64 skb_mstamp_ns;
};
char cb[48] ;
union {
struct {
unsigned long _skb_refdst;
void (*destructor)(struct sk_buff *skb);
};
struct list_head tcp_tsorted_anchor;
#ifdef CONFIG_NET_SOCK_MSG;
unsigned long _sk_redir;
#endif;
};
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE);
unsigned long _nfct;
#endif;
unsigned int len, data_len;
__u16 mac_len, hdr_len;
__u16 queue_mapping;
#ifdef __BIG_ENDIAN_BITFIELD;
#define CLONED_MASK (1 << 7);
#else;
#define CLONED_MASK 1;
#endif;
#define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset);
__u8 cloned:1,nohdr:1,fclone:2,peeked:1,head_frag:1,pfmemalloc:1, pp_recycle:1;
#ifdef CONFIG_SKB_EXTENSIONS;
__u8 active_extensions;
#endif;
__u8 pkt_type:3;
__u8 ignore_df:1;
__u8 nf_trace:1;
__u8 ip_summed:2;
__u8 ooo_okay:1;
__u8 l4_hash:1;
__u8 sw_hash:1;
__u8 wifi_acked_valid:1;
__u8 wifi_acked:1;
__u8 no_fcs:1;
__u8 encapsulation:1;
__u8 encap_hdr_csum:1;
__u8 csum_valid:1;
__u8 vlan_present:1;
__u8 csum_complete_sw:1;
__u8 csum_level:2;
__u8 csum_not_inet:1;
__u8 dst_pending_confirm:1;
#ifdef CONFIG_IPV6_NDISC_NODETYPE;
__u8 ndisc_nodetype:2;
#endif;
__u8 ipvs_property:1;
__u8 inner_protocol_type:1;
__u8 remcsum_offload:1;
#ifdef CONFIG_NET_SWITCHDEV;
__u8 offload_fwd_mark:1;
__u8 offload_l3_fwd_mark:1;
#endif;
#ifdef CONFIG_NET_CLS_ACT;
__u8 tc_skip_classify:1;
__u8 tc_at_ingress:1;
#endif;
__u8 redirected:1;
#ifdef CONFIG_NET_REDIRECT;
__u8 from_ingress:1;
#endif;
#ifdef CONFIG_NETFILTER_SKIP_EGRESS;
__u8 nf_skip_egress:1;
#endif;
#ifdef CONFIG_TLS_DEVICE;
__u8 decrypted:1;
#endif;
__u8 slow_gro:1;
#ifdef CONFIG_NET_SCHED;
__u16 tc_index;
#endif;
union {
__wsum csum;
struct {
__u16 csum_start;
__u16 csum_offset;
};
};
__u32 priority;
int skb_iif;
__u32 hash;
__be16 vlan_proto;
__u16 vlan_tci;
#if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS);
union {
unsigned int napi_id;
unsigned int sender_cpu;
};
#endif;
#ifdef CONFIG_NETWORK_SECMARK;
__u32 secmark;
#endif;
union {
__u32 mark;
__u32 reserved_tailroom;
};
union {
__be16 inner_protocol;
__u8 inner_ipproto;
};
__u16 inner_transport_header;
__u16 inner_network_header;
__u16 inner_mac_header;
__be16 protocol;
__u16 transport_header;
__u16 network_header;
__u16 mac_header;
#ifdef CONFIG_KCOV;
u64 kcov_handle;
#endif;
sk_buff_data_t tail;
sk_buff_data_t end;
unsigned char *head, *data;
unsigned int truesize;
refcount_t users;
#ifdef CONFIG_SKB_EXTENSIONS;
struct skb_ext *extensions;
#endif;
};
Members
{unnamed_union}
anonymous
{unnamed_struct}
anonymous
next
Next buffer in list
prev
Previous buffer in list
{unnamed_union}
anonymous
dev
Device we arrived on/are leaving by
dev_scratch
(aka dev) alternate use of dev when dev would be
NULL
rbnode
RB tree node, alternative to next/prev for netem/tcp
list
queue head
ll_node
anchor in an llist (eg socket defer_list)
{unnamed_union}
anonymous
sk
Socket we are owned by
ip_defrag_offset
(aka sk) alternate use of sk, used in fragmentation management
{unnamed_union}
anonymous
tstamp
Time we arrived/left
skb_mstamp_ns
(aka tstamp) earliest departure time; start point for retransmit timer
cb
Control buffer. Free for use by every layer. Put private vars here
{unnamed_union}
anonymous
{unnamed_struct}
anonymous
_skb_refdst
destination entry (with norefcount bit)
destructor
Destruct function
tcp_tsorted_anchor
list structure for TCP (tp->tsorted_sent_queue)
_sk_redir
socket redirection information for skmsg
_nfct
Associated connection, if any (with nfctinfo bits)
len
Length of actual data
data_len
Data length
mac_len
Length of link layer header
hdr_len
writable header length of cloned skb
queue_mapping
Queue mapping for multiqueue devices
cloned
Head may be cloned (check refcnt to be sure)
nohdr
Payload reference only, must not modify header
fclone
skbuff clone status
peeked
this packet has been seen already, so stats have been done for it, don’t do them again
head_frag
skb was allocated from page fragments, not allocated by
kmalloc()
orvmalloc()
.pfmemalloc
skbuff was allocated from PFMEMALLOC reserves
pp_recycle
mark the packet for recycling instead of freeing (implies page_pool support on driver)
active_extensions
active extensions (skb_ext_id types)
pkt_type
Packet class
ignore_df
allow local fragmentation
nf_trace
netfilter packet trace flag
ip_summed
Driver fed us an IP checksum
ooo_okay
allow the mapping of a socket to a queue to be changed
l4_hash
indicate hash is a canonical 4-tuple hash over transport ports.
sw_hash
indicates hash was computed in software stack
wifi_acked_valid
wifi_acked was set
wifi_acked
whether frame was acked on wifi or not
no_fcs
Request NIC to treat last 4 bytes as Ethernet FCS
encapsulation
indicates the inner headers in the skbuff are valid
encap_hdr_csum
software checksum is needed
csum_valid
checksum is already valid
vlan_present
VLAN tag is present
csum_complete_sw
checksum was completed by software
csum_level
indicates the number of consecutive checksums found in the packet minus one that have been verified as CHECKSUM_UNNECESSARY (max 3)
csum_not_inet
use CRC32c to resolve CHECKSUM_PARTIAL
dst_pending_confirm
need to confirm neighbour
ndisc_nodetype
router type (from link layer)
ipvs_property
skbuff is owned by ipvs
inner_protocol_type
whether the inner protocol is ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO
remcsum_offload
remote checksum offload is enabled
offload_fwd_mark
Packet was L2-forwarded in hardware
offload_l3_fwd_mark
Packet was L3-forwarded in hardware
tc_skip_classify
do not classify packet. set by IFB device
tc_at_ingress
used within tc_classify to distinguish in/egress
redirected
packet was redirected by packet classifier
from_ingress
packet was redirected from the ingress path
nf_skip_egress
packet shall skip nf egress - see netfilter_netdev.h
decrypted
Decrypted SKB
slow_gro
state present at GRO time, slower prepare step required
tc_index
Traffic control index
{unnamed_union}
anonymous
csum
Checksum (must include start/offset pair)
{unnamed_struct}
anonymous
csum_start
Offset from skb->head where checksumming should start
csum_offset
Offset from csum_start where checksum should be stored
priority
Packet queueing priority
skb_iif
ifindex of device we arrived on
hash
the packet hash
vlan_proto
vlan encapsulation protocol
vlan_tci
vlan tag control information
{unnamed_union}
anonymous
napi_id
id of the NAPI struct this skb came from
sender_cpu
(aka napi_id) source CPU in XPS
secmark
security marking
{unnamed_union}
anonymous
mark
Generic packet mark
reserved_tailroom
(aka mark) number of bytes of free space available at the tail of an sk_buff
{unnamed_union}
anonymous
inner_protocol
Protocol (encapsulation)
inner_ipproto
(aka inner_protocol) stores ipproto when skb->inner_protocol_type == ENCAP_TYPE_IPPROTO;
inner_transport_header
Inner transport layer header (encapsulation)
inner_network_header
Network layer header (encapsulation)
inner_mac_header
Link layer header (encapsulation)
protocol
Packet protocol from driver
transport_header
Transport layer header
network_header
Network layer header
mac_header
Link layer header
kcov_handle
KCOV remote handle for remote coverage collection
tail
Tail pointer
end
End pointer
head
Head of buffer
data
Data head pointer
truesize
Buffer size
users
User count - see {datagram,tcp}.c
extensions
allocated extensions, valid if active_extensions is nonzero
-
bool
skb_pfmemalloc
(const struct sk_buff *skb)¶ Test if the skb was allocated from PFMEMALLOC reserves
Parameters
const struct sk_buff *skb
buffer
Parameters
const struct sk_buff *skb
buffer
Description
Returns skb dst_entry, regardless of reference taken or not.
Parameters
struct sk_buff *skb
buffer
struct dst_entry *dst
dst entry
Description
Sets skb dst, assuming a reference was taken on dst and should be released by skb_dst_drop()
-
void
skb_dst_set_noref
(struct sk_buff *skb, struct dst_entry *dst)¶ sets skb dst, hopefully, without taking reference
Parameters
struct sk_buff *skb
buffer
struct dst_entry *dst
dst entry
Description
Sets skb dst, assuming a reference was not taken on dst. If dst entry is cached, we do not take reference and dst_release will be avoided by refdst_drop. If dst entry is not cached, we take reference, so that last dst_release can destroy the dst immediately.
Parameters
const struct sk_buff *skb
buffer
Parameters
const struct sk_buff *skb
buffer
Parameters
const struct sk_buff *skb
buffer
Parameters
struct sk_buff *skb
buffer
Description
Returns true if we can free the skb.
Parameters
struct sk_buff *skb
buffer to free
Parameters
unsigned int size
size to allocate
gfp_t priority
allocation mask
Description
This function is a convenient wrapper around __alloc_skb()
.
Parameters
const struct sock *sk
socket
const struct sk_buff *skb
buffer
Description
Returns true if skb is a fast clone, and its clone is not freed.
Some drivers call skb_orphan()
in their ndo_start_xmit(),
so we also check that this didnt happen.
-
struct sk_buff *
alloc_skb_fclone
(unsigned int size, gfp_t priority)¶ allocate a network buffer from fclone cache
Parameters
unsigned int size
size to allocate
gfp_t priority
allocation mask
Description
This function is a convenient wrapper around __alloc_skb()
.
Parameters
struct sk_buff *skb
buffer to pad
int pad
space to pad
Ensure that a buffer is followed by a padding area that is zero filled. Used by network drivers which may DMA or transfer data beyond the buffer end onto the wire.
May return error in out of memory cases. The skb is freed on error.
-
int
skb_queue_empty
(const struct sk_buff_head *list)¶ check if a queue is empty
Parameters
const struct sk_buff_head *list
queue head
Returns true if the queue is empty, false otherwise.
-
bool
skb_queue_empty_lockless
(const struct sk_buff_head *list)¶ check if a queue is empty
Parameters
const struct sk_buff_head *list
queue head
Returns true if the queue is empty, false otherwise. This variant can be used in lockless contexts.
-
bool
skb_queue_is_last
(const struct sk_buff_head *list, const struct sk_buff *skb)¶ check if skb is the last entry in the queue
Parameters
const struct sk_buff_head *list
queue head
const struct sk_buff *skb
buffer
Returns true if skb is the last buffer on the list.
-
bool
skb_queue_is_first
(const struct sk_buff_head *list, const struct sk_buff *skb)¶ check if skb is the first entry in the queue
Parameters
const struct sk_buff_head *list
queue head
const struct sk_buff *skb
buffer
Returns true if skb is the first buffer on the list.
-
struct sk_buff *
skb_queue_next
(const struct sk_buff_head *list, const struct sk_buff *skb)¶ return the next packet in the queue
Parameters
const struct sk_buff_head *list
queue head
const struct sk_buff *skb
current buffer
Return the next packet in list after skb. It is only valid to call this if
skb_queue_is_last()
evaluates to false.
-
struct sk_buff *
skb_queue_prev
(const struct sk_buff_head *list, const struct sk_buff *skb)¶ return the prev packet in the queue
Parameters
const struct sk_buff_head *list
queue head
const struct sk_buff *skb
current buffer
Return the prev packet in list before skb. It is only valid to call this if
skb_queue_is_first()
evaluates to false.
Parameters
struct sk_buff *skb
buffer to reference
Makes another reference to a socket buffer and returns a pointer to the buffer.
Parameters
const struct sk_buff *skb
buffer to check
Returns true if the buffer was generated with
skb_clone()
and is one of multiple shared copies of the buffer. Cloned buffers are shared data so must not be written to under normal circumstances.
Parameters
const struct sk_buff *skb
buffer to check
Returns true if modifying the header part of the buffer requires the data to be copied.
Parameters
struct sk_buff *skb
buffer to operate on
is the buffer shared
Parameters
const struct sk_buff *skb
buffer to check
Returns true if more than one person has a reference to this buffer.
check if buffer is shared and if so clone it
Parameters
struct sk_buff *skb
buffer to check
gfp_t pri
priority for memory allocation
If the buffer is shared the buffer is cloned and the old copy drops a reference. A new clone with a single reference is returned. If the buffer is not shared the original buffer is returned. When being called from interrupt status or with spinlocks held pri must be GFP_ATOMIC.
NULL is returned on a memory allocation failure.
make a copy of a shared buffer
Parameters
struct sk_buff *skb
buffer to check
gfp_t pri
priority for memory allocation
If the socket buffer is a clone then this function creates a new copy of the data, drops a reference count on the old copy and returns the new copy with the reference count at 1. If the buffer is not a clone the original buffer is returned. When called with a spinlock held or from interrupt state pri must be
GFP_ATOMIC
NULL
is returned on a memory allocation failure.
Parameters
const struct sk_buff_head *list_
list to peek at
Peek an
sk_buff
. Unlike most other operations you _MUST_ be careful with this one. A peek leaves the buffer on the list and someone else may run off with it. You must hold the appropriate locks or have a private queue to do this.Returns
NULL
for an empty list or a pointer to the head element. The reference count is not incremented and the reference is therefore volatile. Use with caution.
-
struct sk_buff *
__skb_peek
(const struct sk_buff_head *list_)¶ peek at the head of a non-empty
sk_buff_head
Parameters
const struct sk_buff_head *list_
list to peek at
Like
skb_peek()
, but the caller knows that the list is not empty.
-
struct sk_buff *
skb_peek_next
(struct sk_buff *skb, const struct sk_buff_head *list_)¶ peek skb following the given one from a queue
Parameters
struct sk_buff *skb
skb to start from
const struct sk_buff_head *list_
list to peek at
Returns
NULL
when the end of the list is met or a pointer to the next element. The reference count is not incremented and the reference is therefore volatile. Use with caution.
-
struct sk_buff *
skb_peek_tail
(const struct sk_buff_head *list_)¶ peek at the tail of an
sk_buff_head
Parameters
const struct sk_buff_head *list_
list to peek at
Peek an
sk_buff
. Unlike most other operations you _MUST_ be careful with this one. A peek leaves the buffer on the list and someone else may run off with it. You must hold the appropriate locks or have a private queue to do this.Returns
NULL
for an empty list or a pointer to the tail element. The reference count is not incremented and the reference is therefore volatile. Use with caution.
-
__u32
skb_queue_len
(const struct sk_buff_head *list_)¶ get queue length
Parameters
const struct sk_buff_head *list_
list to measure
Return the length of an
sk_buff
queue.
-
__u32
skb_queue_len_lockless
(const struct sk_buff_head *list_)¶ get queue length
Parameters
const struct sk_buff_head *list_
list to measure
Return the length of an
sk_buff
queue. This variant can be used in lockless contexts.
-
void
__skb_queue_head_init
(struct sk_buff_head *list)¶ initialize non-spinlock portions of sk_buff_head
Parameters
struct sk_buff_head *list
queue to initialize
This initializes only the list and queue length aspects of an sk_buff_head object. This allows to initialize the list aspects of an sk_buff_head without reinitializing things like the spinlock. It can also be used for on-stack sk_buff_head objects where the spinlock is known to not be used.
-
void
skb_queue_splice
(const struct sk_buff_head *list, struct sk_buff_head *head)¶ join two skb lists, this is designed for stacks
Parameters
const struct sk_buff_head *list
the new list to add
struct sk_buff_head *head
the place to add it in the first list
-
void
skb_queue_splice_init
(struct sk_buff_head *list, struct sk_buff_head *head)¶ join two skb lists and reinitialise the emptied list
Parameters
struct sk_buff_head *list
the new list to add
struct sk_buff_head *head
the place to add it in the first list
The list at list is reinitialised
-
void
skb_queue_splice_tail
(const struct sk_buff_head *list, struct sk_buff_head *head)¶ join two skb lists, each list being a queue
Parameters
const struct sk_buff_head *list
the new list to add
struct sk_buff_head *head
the place to add it in the first list
-
void
skb_queue_splice_tail_init
(struct sk_buff_head *list, struct sk_buff_head *head)¶ join two skb lists and reinitialise the emptied list
Parameters
struct sk_buff_head *list
the new list to add
struct sk_buff_head *head
the place to add it in the first list
Each of the lists is a queue. The list at list is reinitialised
-
void
__skb_queue_after
(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk)¶ queue a buffer at the list head
Parameters
struct sk_buff_head *list
list to use
struct sk_buff *prev
place after this buffer
struct sk_buff *newsk
buffer to queue
Queue a buffer int the middle of a list. This function takes no locks and you must therefore hold required locks before calling it.
A buffer cannot be placed on two lists at the same time.
-
void
__skb_queue_head
(struct sk_buff_head *list, struct sk_buff *newsk)¶ queue a buffer at the list head
Parameters
struct sk_buff_head *list
list to use
struct sk_buff *newsk
buffer to queue
Queue a buffer at the start of a list. This function takes no locks and you must therefore hold required locks before calling it.
A buffer cannot be placed on two lists at the same time.
-
void
__skb_queue_tail
(struct sk_buff_head *list, struct sk_buff *newsk)¶ queue a buffer at the list tail
Parameters
struct sk_buff_head *list
list to use
struct sk_buff *newsk
buffer to queue
Queue a buffer at the end of a list. This function takes no locks and you must therefore hold required locks before calling it.
A buffer cannot be placed on two lists at the same time.
Parameters
struct sk_buff_head *list
list to dequeue from
Remove the head of the list. This function does not take any locks so must be used with appropriate locks held only. The head item is returned or
NULL
if the list is empty.
Parameters
struct sk_buff_head *list
list to dequeue from
Remove the tail of the list. This function does not take any locks so must be used with appropriate locks held only. The tail item is returned or
NULL
if the list is empty.
-
void
__skb_fill_page_desc
(struct sk_buff *skb, int i, struct page *page, int off, int size)¶ initialise a paged fragment in an skb
Parameters
struct sk_buff *skb
buffer containing fragment to be initialised
int i
paged fragment index to initialise
struct page *page
the page to use for this fragment
int off
the offset to the data with page
int size
the length of the data
Description
Initialises the i’th fragment of skb to point to size
bytes at
offset off within page.
Does not take any additional reference on the fragment.
-
void
skb_fill_page_desc
(struct sk_buff *skb, int i, struct page *page, int off, int size)¶ initialise a paged fragment in an skb
Parameters
struct sk_buff *skb
buffer containing fragment to be initialised
int i
paged fragment index to initialise
struct page *page
the page to use for this fragment
int off
the offset to the data with page
int size
the length of the data
Description
As per __skb_fill_page_desc()
– initialises the i’th fragment of
skb to point to size bytes at offset off within page. In
addition updates skb such that i is the last fragment.
Does not take any additional reference on the fragment.
Parameters
const struct sk_buff *skb
buffer to check
Return the number of bytes of free space at the head of an
sk_buff
.
Parameters
const struct sk_buff *skb
buffer to check
Return the number of bytes of free space at the tail of an sk_buff
Parameters
const struct sk_buff *skb
buffer to check
Return the number of bytes of free space at the tail of an sk_buff allocated by sk_stream_alloc()
Parameters
struct sk_buff *skb
buffer to alter
int len
bytes to move
Increase the headroom of an empty
sk_buff
by reducing the tail room. This is only allowed for an empty buffer.
-
void
skb_tailroom_reserve
(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom)¶ adjust reserved_tailroom
Parameters
struct sk_buff *skb
buffer to alter
unsigned int mtu
maximum amount of headlen permitted
unsigned int needed_tailroom
minimum amount of reserved_tailroom
Set reserved_tailroom so that headlen can be as large as possible but not larger than mtu and tailroom cannot be smaller than needed_tailroom. The required headroom should already have been reserved before using this function.
-
void
pskb_trim_unique
(struct sk_buff *skb, unsigned int len)¶ remove end from a paged unique (not cloned) buffer
Parameters
struct sk_buff *skb
buffer to alter
unsigned int len
new length
This is identical to pskb_trim except that the caller knows that the skb is not cloned so we should never get an error due to out- of-memory.
Parameters
struct sk_buff *skb
buffer to orphan
If a buffer currently has an owner then we call the owner’s destructor function and make the skb unowned. The buffer continues to exist but is no longer charged to its former owner.
Parameters
struct sk_buff *skb
buffer to orphan frags from
gfp_t gfp_mask
allocation mask for replacement pages
For each frag in the SKB which needs a destructor (i.e. has an owner) create a copy of that frag and release the original page by calling the destructor.
-
void
__skb_queue_purge
(struct sk_buff_head *list)¶ empty a list
Parameters
struct sk_buff_head *list
list to empty
Delete all buffers on an
sk_buff
list. Each buffer is removed from the list and one reference dropped. This function does not take the list lock and the caller must hold the relevant locks to use it.
-
void *
netdev_alloc_frag
(unsigned int fragsz)¶ allocate a page fragment
Parameters
unsigned int fragsz
fragment size
Description
Allocates a frag from a page for receive buffer. Uses GFP_ATOMIC allocations.
-
struct sk_buff *
netdev_alloc_skb
(struct net_device *dev, unsigned int length)¶ allocate an skbuff for rx on a specific device
Parameters
struct net_device *dev
network device to receive on
unsigned int length
length to allocate
Allocate a new
sk_buff
and assign it a usage count of one. The buffer has unspecified headroom built in. Users should allocate the headroom they think they need without accounting for the built in space. The built in space is used for optimisations.NULL
is returned if there is no free memory. Although this function allocates memory it can be called from an interrupt.
Parameters
gfp_t gfp_mask
allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
unsigned int order
size of the allocation
Description
Allocate a new page.
NULL
is returned if there is no free memory.
Parameters
gfp_t gfp_mask
allocation priority. Set __GFP_NOMEMALLOC if not for network Rx
Description
Allocate a new page.
NULL
is returned if there is no free memory.
-
bool
dev_page_is_reusable
(const struct page *page)¶ check whether a page can be reused for network Rx
Parameters
const struct page *page
the page to test
Description
A page shouldn’t be considered for reusing/recycling if it was allocated under memory pressure or at a distant memory node.
Returns false if this page should be returned to page allocator, true otherwise.
-
void
skb_propagate_pfmemalloc
(const struct page *page, struct sk_buff *skb)¶ Propagate pfmemalloc if skb is allocated after RX page
Parameters
const struct page *page
The page that was allocated from skb_alloc_page
struct sk_buff *skb
The skb that may need pfmemalloc set
-
unsigned int
skb_frag_off
(const skb_frag_t *frag)¶ Returns the offset of a skb fragment
Parameters
const skb_frag_t *frag
the paged fragment
-
void
skb_frag_off_add
(skb_frag_t *frag, int delta)¶ Increments the offset of a skb fragment by delta
Parameters
skb_frag_t *frag
skb fragment
int delta
value to add
-
void
skb_frag_off_set
(skb_frag_t *frag, unsigned int offset)¶ Sets the offset of a skb fragment
Parameters
skb_frag_t *frag
skb fragment
unsigned int offset
offset of fragment
-
void
skb_frag_off_copy
(skb_frag_t *fragto, const skb_frag_t *fragfrom)¶ Sets the offset of a skb fragment from another fragment
Parameters
skb_frag_t *fragto
skb fragment where offset is set
const skb_frag_t *fragfrom
skb fragment offset is copied from
-
struct page *
skb_frag_page
(const skb_frag_t *frag)¶ retrieve the page referred to by a paged fragment
Parameters
const skb_frag_t *frag
the paged fragment
Description
Returns the struct page
associated with frag.
-
void
__skb_frag_ref
(skb_frag_t *frag)¶ take an addition reference on a paged fragment.
Parameters
skb_frag_t *frag
the paged fragment
Description
Takes an additional reference on the paged fragment frag.
-
void
skb_frag_ref
(struct sk_buff *skb, int f)¶ take an addition reference on a paged fragment of an skb.
Parameters
struct sk_buff *skb
the buffer
int f
the fragment offset.
Description
Takes an additional reference on the f’th paged fragment of skb.
-
void
__skb_frag_unref
(skb_frag_t *frag, bool recycle)¶ release a reference on a paged fragment.
Parameters
skb_frag_t *frag
the paged fragment
bool recycle
recycle the page if allocated via page_pool
Description
Releases a reference on the paged fragment frag or recycles the page via the page_pool API.
Parameters
struct sk_buff *skb
the buffer
int f
the fragment offset
Description
Releases a reference on the f’th paged fragment of skb.
-
void *
skb_frag_address
(const skb_frag_t *frag)¶ gets the address of the data contained in a paged fragment
Parameters
const skb_frag_t *frag
the paged fragment buffer
Description
Returns the address of the data within frag. The page must already be mapped.
-
void *
skb_frag_address_safe
(const skb_frag_t *frag)¶ gets the address of the data contained in a paged fragment
Parameters
const skb_frag_t *frag
the paged fragment buffer
Description
Returns the address of the data within frag. Checks that the page
is mapped and returns NULL
otherwise.
-
void
skb_frag_page_copy
(skb_frag_t *fragto, const skb_frag_t *fragfrom)¶ sets the page in a fragment from another fragment
Parameters
skb_frag_t *fragto
skb fragment where page is set
const skb_frag_t *fragfrom
skb fragment page is copied from
-
void
__skb_frag_set_page
(skb_frag_t *frag, struct page *page)¶ sets the page contained in a paged fragment
Parameters
skb_frag_t *frag
the paged fragment
struct page *page
the page to set
Description
Sets the fragment frag to contain page.
-
void
skb_frag_set_page
(struct sk_buff *skb, int f, struct page *page)¶ sets the page contained in a paged fragment of an skb
Parameters
struct sk_buff *skb
the buffer
int f
the fragment offset
struct page *page
the page to set
Description
Sets the f’th fragment of skb to contain page.
-
dma_addr_t
skb_frag_dma_map
(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir)¶ maps a paged fragment via the DMA API
Parameters
struct device *dev
the device to map the fragment to
const skb_frag_t *frag
the paged fragment to map
size_t offset
the offset within the fragment (starting at the fragment’s own offset)
size_t size
the number of bytes to map
enum dma_data_direction dir
the direction of the mapping (
PCI_DMA_*
)
Description
Maps the page associated with frag to device.
-
int
skb_clone_writable
(const struct sk_buff *skb, unsigned int len)¶ is the header of a clone writable
Parameters
const struct sk_buff *skb
buffer to check
unsigned int len
length up to which to write
Returns true if modifying the header part of the cloned buffer does not requires the data to be copied.
Parameters
struct sk_buff *skb
buffer to cow
unsigned int headroom
needed headroom
If the skb passed lacks sufficient headroom or its data part is shared, data is reallocated. If reallocation fails, an error is returned and original skb is not changed.
The result is skb with writable area skb->head…skb->tail and at least headroom of space at head.
-
int
skb_cow_head
(struct sk_buff *skb, unsigned int headroom)¶ skb_cow but only making the head writable
Parameters
struct sk_buff *skb
buffer to cow
unsigned int headroom
needed headroom
This function is identical to skb_cow except that we replace the skb_cloned check by skb_header_cloned. It should be used when you only need to push on some header and do not need to modify the data.
Parameters
struct sk_buff *skb
buffer to pad
unsigned int len
minimal length
Pads up a buffer to ensure the trailing bytes exist and are blanked. If the buffer already contains sufficient data it is untouched. Otherwise it is extended. Returns zero on success. The skb is freed on error.
-
int
__skb_put_padto
(struct sk_buff *skb, unsigned int len, bool free_on_error)¶ increase size and pad an skbuff up to a minimal size
Parameters
struct sk_buff *skb
buffer to pad
unsigned int len
minimal length
bool free_on_error
free buffer on error
Pads up a buffer to ensure the trailing bytes exist and are blanked. If the buffer already contains sufficient data it is untouched. Otherwise it is extended. Returns zero on success. The skb is freed on error if free_on_error is true.
-
int
skb_put_padto
(struct sk_buff *skb, unsigned int len)¶ increase size and pad an skbuff up to a minimal size
Parameters
struct sk_buff *skb
buffer to pad
unsigned int len
minimal length
Pads up a buffer to ensure the trailing bytes exist and are blanked. If the buffer already contains sufficient data it is untouched. Otherwise it is extended. Returns zero on success. The skb is freed on error.
Parameters
struct sk_buff *skb
buffer to linarize
If there is no free memory -ENOMEM is returned, otherwise zero is returned and the old skb data released.
can any frag be overwritten
Parameters
const struct sk_buff *skb
buffer to test
Description
Return true if the skb has at least one frag that might be modified by an external entity (as in vmsplice()/sendfile())
Parameters
struct sk_buff *skb
buffer to process
If there is no free memory -ENOMEM is returned, otherwise zero is returned and the old skb data released.
-
void
skb_postpull_rcsum
(struct sk_buff *skb, const void *start, unsigned int len)¶ update checksum for received skb after pull
Parameters
struct sk_buff *skb
buffer to update
const void *start
start of data before pull
unsigned int len
length of data pulled
After doing a pull on a received packet, you need to call this to update the CHECKSUM_COMPLETE checksum, or set ip_summed to CHECKSUM_NONE so that it can be recomputed from scratch.
-
void
skb_postpush_rcsum
(struct sk_buff *skb, const void *start, unsigned int len)¶ update checksum for received skb after push
Parameters
struct sk_buff *skb
buffer to update
const void *start
start of data after push
unsigned int len
length of data pushed
After doing a push on a received packet, you need to call this to update the CHECKSUM_COMPLETE checksum.
Parameters
struct sk_buff *skb
buffer to update
unsigned int len
length of data pulled
This function performs an skb_push on the packet and updates the CHECKSUM_COMPLETE checksum. It should be used on receive path processing instead of skb_push unless you know that the checksum difference is zero (e.g., a valid IP header) or you are setting ip_summed to CHECKSUM_NONE.
Parameters
struct sk_buff *skb
buffer to trim
unsigned int len
new length
This is exactly the same as pskb_trim except that it ensures the checksum of received packets are still valid after the operation. It can change skb pointers.
-
bool
skb_needs_linearize
(struct sk_buff *skb, netdev_features_t features)¶ check if we need to linearize a given skb depending on the given device features.
Parameters
struct sk_buff *skb
socket buffer to check
netdev_features_t features
net device features
Returns true if either: 1. skb has frag_list and the device doesn’t support FRAGLIST, or 2. skb is fragmented and the device does not support SG.
-
void
skb_get_timestamp
(const struct sk_buff *skb, struct __kernel_old_timeval *stamp)¶ get timestamp from a skb
Parameters
const struct sk_buff *skb
skb to get stamp from
struct __kernel_old_timeval *stamp
pointer to struct __kernel_old_timeval to store stamp in
Timestamps are stored in the skb as offsets to a base timestamp. This function converts the offset back to a struct timeval and stores it in stamp.
-
void
skb_complete_tx_timestamp
(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps)¶ deliver cloned skb with tx timestamps
Parameters
struct sk_buff *skb
clone of the original outgoing packet
struct skb_shared_hwtstamps *hwtstamps
hardware time stamps
Description
PHY drivers may accept clones of transmitted packets for timestamping via their phy_driver.txtstamp method. These drivers must call this function to return the skb back to the stack with a timestamp.
-
void
skb_tstamp_tx
(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps)¶ queue clone of skb with send time stamps
Parameters
struct sk_buff *orig_skb
the original outgoing packet
struct skb_shared_hwtstamps *hwtstamps
hardware time stamps, may be NULL if not available
Description
If the skb has a socket associated, then this function clones the skb (thus sharing the actual data and optional structures), stores the optional hardware time stamping information (if non NULL) or generates a software time stamp (otherwise), then queues the clone to the error queue of the socket. Errors are silently ignored.
Parameters
struct sk_buff *skb
A socket buffer.
Description
Ethernet MAC Drivers should call this function in their hard_xmit() function immediately before giving the sk_buff to the MAC hardware.
Specifically, one should make absolutely sure that this function is called before TX completion of this packet can trigger. Otherwise the packet could potentially already be freed.
Parameters
struct sk_buff *skb
the original outgoing packet
bool acked
ack status
Parameters
struct sk_buff *skb
packet to process
This function calculates the checksum over the entire packet plus the value of skb->csum. The latter can be used to supply the checksum of a pseudo header as used by TCP/UDP. It returns the checksum.
For protocols that contain complete checksums such as ICMP/TCP/UDP, this function can be used to verify that checksum on received packets. In that case the function should return zero if the checksum is correct. In particular, this function will return zero if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the hardware has already verified the correctness of the checksum.
-
struct
skb_ext
¶ sk_buff extensions
Definition
struct skb_ext {
refcount_t refcnt;
u8 offset[SKB_EXT_NUM];
u8 chunks;
char data[] ;
};
Members
refcnt
1 on allocation, deallocated on 0
offset
offset to add to data to obtain extension address
chunks
size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units
data
start of extension data, variable sized
Note
- offsets/lengths are stored in chunks of 8 bytes, this allows
to use ‘u8’ types while allowing up to 2kb worth of extension data.
Parameters
const struct sk_buff *skb
skb to check
Description
fresh skbs have their ip_summed set to CHECKSUM_NONE. Instead of forcing ip_summed to CHECKSUM_NONE, we can use this helper, to document places where we make this assertion.
Parameters
const struct sk_buff *skb
skb to check
Description
The head on skbs build around a head frag can be removed if they are not cloned. This function returns true if the skb head is locked down due to either being allocated via kmalloc, or by being a clone with multiple references to the head.
-
struct
sock_common
¶ minimal network layer representation of sockets
Definition
struct sock_common {
union {
__addrpair skc_addrpair;
struct {
__be32 skc_daddr;
__be32 skc_rcv_saddr;
};
};
union {
unsigned int skc_hash;
__u16 skc_u16hashes[2];
};
union {
__portpair skc_portpair;
struct {
__be16 skc_dport;
__u16 skc_num;
};
};
unsigned short skc_family;
volatile unsigned char skc_state;
unsigned char skc_reuse:4;
unsigned char skc_reuseport:1;
unsigned char skc_ipv6only:1;
unsigned char skc_net_refcnt:1;
int skc_bound_dev_if;
union {
struct hlist_node skc_bind_node;
struct hlist_node skc_portaddr_node;
};
struct proto *skc_prot;
possible_net_t skc_net;
#if IS_ENABLED(CONFIG_IPV6);
struct in6_addr skc_v6_daddr;
struct in6_addr skc_v6_rcv_saddr;
#endif;
atomic64_t skc_cookie;
union {
unsigned long skc_flags;
struct sock *skc_listener;
struct inet_timewait_death_row *skc_tw_dr;
};
union {
struct hlist_node skc_node;
struct hlist_nulls_node skc_nulls_node;
};
unsigned short skc_tx_queue_mapping;
#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING;
unsigned short skc_rx_queue_mapping;
#endif;
union {
int skc_incoming_cpu;
u32 skc_rcv_wnd;
u32 skc_tw_rcv_nxt;
};
refcount_t skc_refcnt;
};
Members
{unnamed_union}
anonymous
skc_addrpair
8-byte-aligned __u64 union of skc_daddr & skc_rcv_saddr
{unnamed_struct}
anonymous
skc_daddr
Foreign IPv4 addr
skc_rcv_saddr
Bound local IPv4 addr
{unnamed_union}
anonymous
skc_hash
hash value used with various protocol lookup tables
skc_u16hashes
two u16 hash values used by UDP lookup tables
{unnamed_union}
anonymous
skc_portpair
__u32 union of skc_dport & skc_num
{unnamed_struct}
anonymous
skc_dport
placeholder for inet_dport/tw_dport
skc_num
placeholder for inet_num/tw_num
skc_family
network address family
skc_state
Connection state
skc_reuse
SO_REUSEADDR
settingskc_reuseport
SO_REUSEPORT
settingskc_ipv6only
socket is IPV6 only
skc_net_refcnt
socket is using net ref counting
skc_bound_dev_if
bound device index if != 0
{unnamed_union}
anonymous
skc_bind_node
bind hash linkage for various protocol lookup tables
skc_portaddr_node
second hash linkage for UDP/UDP-Lite protocol
skc_prot
protocol handlers inside a network family
skc_net
reference to the network namespace of this socket
skc_v6_daddr
IPV6 destination address
skc_v6_rcv_saddr
IPV6 source address
skc_cookie
socket’s cookie value
{unnamed_union}
anonymous
skc_flags
place holder for sk_flags
SO_LINGER
(l_onoff),SO_BROADCAST
,SO_KEEPALIVE
,SO_OOBINLINE
settings,SO_TIMESTAMPING
settingsskc_listener
connection request listener socket (aka rsk_listener) [union with skc_flags]
skc_tw_dr
(aka tw_dr) ptr to
struct inet_timewait_death_row
[union with skc_flags]{unnamed_union}
anonymous
skc_node
main hash linkage for various protocol lookup tables
skc_nulls_node
main hash linkage for TCP/UDP/UDP-Lite protocol
skc_tx_queue_mapping
tx queue number for this connection
skc_rx_queue_mapping
rx queue number for this connection
{unnamed_union}
anonymous
skc_incoming_cpu
record/match cpu processing incoming packets
skc_rcv_wnd
(aka rsk_rcv_wnd) TCP receive window size (possibly scaled) [union with skc_incoming_cpu]
skc_tw_rcv_nxt
(aka tw_rcv_nxt) TCP window next expected seq number [union with skc_incoming_cpu]
skc_refcnt
reference count
This is the minimal network layer representation of sockets, the header for
struct sock
and struct inet_timewait_sock.
-
struct
sock
¶ network layer representation of sockets
Definition
struct sock {
struct sock_common __sk_common;
#define sk_node __sk_common.skc_node;
#define sk_nulls_node __sk_common.skc_nulls_node;
#define sk_refcnt __sk_common.skc_refcnt;
#define sk_tx_queue_mapping __sk_common.skc_tx_queue_mapping;
#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING;
#define sk_rx_queue_mapping __sk_common.skc_rx_queue_mapping;
#endif;
#define sk_dontcopy_begin __sk_common.skc_dontcopy_begin;
#define sk_dontcopy_end __sk_common.skc_dontcopy_end;
#define sk_hash __sk_common.skc_hash;
#define sk_portpair __sk_common.skc_portpair;
#define sk_num __sk_common.skc_num;
#define sk_dport __sk_common.skc_dport;
#define sk_addrpair __sk_common.skc_addrpair;
#define sk_daddr __sk_common.skc_daddr;
#define sk_rcv_saddr __sk_common.skc_rcv_saddr;
#define sk_family __sk_common.skc_family;
#define sk_state __sk_common.skc_state;
#define sk_reuse __sk_common.skc_reuse;
#define sk_reuseport __sk_common.skc_reuseport;
#define sk_ipv6only __sk_common.skc_ipv6only;
#define sk_net_refcnt __sk_common.skc_net_refcnt;
#define sk_bound_dev_if __sk_common.skc_bound_dev_if;
#define sk_bind_node __sk_common.skc_bind_node;
#define sk_prot __sk_common.skc_prot;
#define sk_net __sk_common.skc_net;
#define sk_v6_daddr __sk_common.skc_v6_daddr;
#define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr;
#define sk_cookie __sk_common.skc_cookie;
#define sk_incoming_cpu __sk_common.skc_incoming_cpu;
#define sk_flags __sk_common.skc_flags;
#define sk_rxhash __sk_common.skc_rxhash;
struct dst_entry __rcu *sk_rx_dst;
int sk_rx_dst_ifindex;
u32 sk_rx_dst_cookie;
socket_lock_t sk_lock;
atomic_t sk_drops;
int sk_rcvlowat;
struct sk_buff_head sk_error_queue;
struct sk_buff_head sk_receive_queue;
struct {
atomic_t rmem_alloc;
int len;
struct sk_buff *head;
struct sk_buff *tail;
} sk_backlog;
struct llist_head defer_list;
#define sk_rmem_alloc sk_backlog.rmem_alloc;
int sk_forward_alloc;
u32 sk_reserved_mem;
#ifdef CONFIG_NET_RX_BUSY_POLL;
unsigned int sk_ll_usec;
unsigned int sk_napi_id;
#endif;
int sk_rcvbuf;
struct sk_filter __rcu *sk_filter;
union {
struct socket_wq __rcu *sk_wq;
};
#ifdef CONFIG_XFRM;
struct xfrm_policy __rcu *sk_policy[2];
#endif;
struct dst_entry __rcu *sk_dst_cache;
atomic_t sk_omem_alloc;
int sk_sndbuf;
int sk_wmem_queued;
refcount_t sk_wmem_alloc;
unsigned long sk_tsq_flags;
union {
struct sk_buff *sk_send_head;
struct rb_root tcp_rtx_queue;
};
struct sk_buff_head sk_write_queue;
__s32 sk_peek_off;
int sk_write_pending;
__u32 sk_dst_pending_confirm;
u32 sk_pacing_status;
long sk_sndtimeo;
struct timer_list sk_timer;
__u32 sk_priority;
__u32 sk_mark;
unsigned long sk_pacing_rate;
unsigned long sk_max_pacing_rate;
struct page_frag sk_frag;
netdev_features_t sk_route_caps;
int sk_gso_type;
unsigned int sk_gso_max_size;
gfp_t sk_allocation;
__u32 sk_txhash;
u8 sk_gso_disabled : 1,sk_kern_sock : 1,sk_no_check_tx : 1,sk_no_check_rx : 1, sk_userlocks : 4;
u8 sk_pacing_shift;
u16 sk_type;
u16 sk_protocol;
u16 sk_gso_max_segs;
unsigned long sk_lingertime;
struct proto *sk_prot_creator;
rwlock_t sk_callback_lock;
int sk_err, sk_err_soft;
u32 sk_ack_backlog;
u32 sk_max_ack_backlog;
kuid_t sk_uid;
#ifdef CONFIG_NET_RX_BUSY_POLL;
u8 sk_prefer_busy_poll;
u16 sk_busy_poll_budget;
#endif;
spinlock_t sk_peer_lock;
int sk_bind_phc;
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;
ktime_t sk_stamp;
#if BITS_PER_LONG==32;
seqlock_t sk_stamp_seq;
#endif;
u16 sk_tsflags;
u8 sk_shutdown;
atomic_t sk_tskey;
atomic_t sk_zckey;
u8 sk_clockid;
u8 sk_txtime_deadline_mode : 1,sk_txtime_report_errors : 1, sk_txtime_unused : 6;
struct socket *sk_socket;
void *sk_user_data;
#ifdef CONFIG_SECURITY;
void *sk_security;
#endif;
struct sock_cgroup_data sk_cgrp_data;
struct mem_cgroup *sk_memcg;
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk);
void (*sk_write_space)(struct sock *sk);
void (*sk_error_report)(struct sock *sk);
int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb);
#ifdef CONFIG_SOCK_VALIDATE_XMIT;
struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk,struct net_device *dev, struct sk_buff *skb);
#endif;
void (*sk_destruct)(struct sock *sk);
struct sock_reuseport __rcu *sk_reuseport_cb;
#ifdef CONFIG_BPF_SYSCALL;
struct bpf_local_storage __rcu *sk_bpf_storage;
#endif;
struct rcu_head sk_rcu;
netns_tracker ns_tracker;
};
Members
__sk_common
shared layout with inet_timewait_sock
sk_rx_dst
receive input route used by early demux
sk_rx_dst_ifindex
ifindex for sk_rx_dst
sk_rx_dst_cookie
cookie for sk_rx_dst
sk_lock
synchronizer
sk_drops
raw/udp drops counter
sk_rcvlowat
SO_RCVLOWAT
settingsk_error_queue
rarely used
sk_receive_queue
incoming packets
sk_backlog
always used with the per-socket spinlock held
defer_list
head of llist storing skbs to be freed
sk_forward_alloc
space allocated forward
sk_reserved_mem
space reserved and non-reclaimable for the socket
sk_ll_usec
usecs to busypoll when there is no data
sk_napi_id
id of the last napi context to receive data for sk
sk_rcvbuf
size of receive buffer in bytes
sk_filter
socket filtering instructions
{unnamed_union}
anonymous
sk_wq
sock wait queue and async head
sk_policy
flow policy
sk_dst_cache
destination cache
sk_omem_alloc
“o” is “option” or “other”
sk_sndbuf
size of send buffer in bytes
sk_wmem_queued
persistent queue size
sk_wmem_alloc
transmit queue bytes committed
sk_tsq_flags
TCP Small Queues flags
{unnamed_union}
anonymous
sk_send_head
front of stuff to transmit
tcp_rtx_queue
TCP re-transmit queue [union with sk_send_head]
sk_write_queue
Packet sending queue
sk_peek_off
current peek_offset value
sk_write_pending
a write to stream socket waits to start
sk_dst_pending_confirm
need to confirm neighbour
sk_pacing_status
Pacing status (requested, handled by sch_fq)
sk_sndtimeo
SO_SNDTIMEO
settingsk_timer
sock cleanup timer
sk_priority
SO_PRIORITY
settingsk_mark
generic packet mark
sk_pacing_rate
Pacing rate (if supported by transport/packet scheduler)
sk_max_pacing_rate
Maximum pacing rate (
SO_MAX_PACING_RATE
)sk_frag
cached page frag
sk_route_caps
route capabilities (e.g.
NETIF_F_TSO
)sk_gso_type
GSO type (e.g.
SKB_GSO_TCPV4
)sk_gso_max_size
Maximum GSO segment size to build
sk_allocation
allocation mode
sk_txhash
computed flow hash for use on transmit
sk_gso_disabled
if set, NETIF_F_GSO_MASK is forbidden.
sk_kern_sock
True if sock is using kernel lock classes
sk_no_check_tx
SO_NO_CHECK
setting, set checksum in TX packetssk_no_check_rx
allow zero checksum in RX packets
sk_userlocks
SO_SNDBUF
andSO_RCVBUF
settingssk_pacing_shift
scaling factor for TCP Small Queues
sk_type
socket type (
SOCK_STREAM
, etc)sk_protocol
which protocol this socket belongs in this network family
sk_gso_max_segs
Maximum number of GSO segments
sk_lingertime
SO_LINGER
l_linger settingsk_prot_creator
sk_prot of original sock creator (see ipv6_setsockopt, IPV6_ADDRFORM for instance)
sk_callback_lock
used with the callbacks in the end of this struct
sk_err
last error
sk_err_soft
errors that don’t cause failure but are the cause of a persistent failure not just ‘timed out’
sk_ack_backlog
current listen backlog
sk_max_ack_backlog
listen backlog set in listen()
sk_uid
user id of owner
sk_prefer_busy_poll
prefer busypolling over softirq processing
sk_busy_poll_budget
napi processing budget when busypolling
sk_peer_lock
lock protecting sk_peer_pid and sk_peer_cred
sk_bind_phc
SO_TIMESTAMPING bind PHC index of PTP virtual clock for timestamping
sk_peer_pid
struct pid
for this socket’s peersk_peer_cred
SO_PEERCRED
settingsk_rcvtimeo
SO_RCVTIMEO
settingsk_stamp
time stamp of last packet received
sk_stamp_seq
lock for accessing sk_stamp on 32 bit architectures only
sk_tsflags
SO_TIMESTAMPING flags
sk_shutdown
mask of
SEND_SHUTDOWN
and/orRCV_SHUTDOWN
sk_tskey
counter to disambiguate concurrent tstamp requests
sk_zckey
counter to order MSG_ZEROCOPY notifications
sk_clockid
clockid used by time-based scheduling (SO_TXTIME)
sk_txtime_deadline_mode
set deadline mode for SO_TXTIME
sk_txtime_report_errors
set report errors mode for SO_TXTIME
sk_txtime_unused
unused txtime flags
sk_socket
Identd and reporting IO signals
sk_user_data
RPC layer private data
sk_security
used by security modules
sk_cgrp_data
cgroup data for this cgroup
sk_memcg
this socket’s memory cgroup association
sk_state_change
callback to indicate change in the state of the sock
sk_data_ready
callback to indicate there is data to be processed
sk_write_space
callback to indicate there is bf sending space available
sk_error_report
callback to indicate errors (e.g.
MSG_ERRQUEUE
)sk_backlog_rcv
callback to process the backlog
sk_validate_xmit_skb
ptr to an optional validate function
sk_destruct
called at sock freeing time, i.e. when all refcnt == 0
sk_reuseport_cb
reuseport group container
sk_bpf_storage
ptr to cache and control for bpf_sk_storage
sk_rcu
used during RCU grace period
ns_tracker
tracker for netns reference
Parameters
const struct sock *sk
socket
-
sk_for_each_entry_offset_rcu
(tpos, pos, head, offset)¶ iterate over a list at a given struct offset
Parameters
tpos
the type * to use as a loop cursor.
pos
the
struct hlist_node
to use as a loop cursor.head
the head for your list.
offset
offset of hlist_node within the struct.
Parameters
struct sock *sk
socket
Description
This version should be used for very small section, where process wont block return false if fast path is taken:
sk_lock.slock locked, owned = 0, BH disabled
return true if slow path is taken:
sk_lock.slock unlocked, owned = 1, BH enabled
Parameters
struct sock *sk
socket
bool slow
slow mode
Description
fast unlock socket for user context. If slow mode is on, we call regular release_sock()
Parameters
const struct sock *sk
socket
Return
sk_wmem_alloc minus initial offset of one
Parameters
const struct sock *sk
socket
Return
sk_rmem_alloc
Parameters
const struct sock *sk
socket
Return
true if socket has write or read allocations
-
bool
skwq_has_sleeper
(struct socket_wq *wq)¶ check if there are any waiting processes
Parameters
struct socket_wq *wq
struct socket_wq
Return
true if socket_wq has waiting processes
Description
The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory barrier call. They were added due to the race found within the tcp code.
Consider following tcp code paths:
CPU1 CPU2
sys_select receive packet
... ...
__add_wait_queue update tp->rcv_nxt
... ...
tp->rcv_nxt check sock_def_readable
... {
schedule rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (wq && waitqueue_active(&wq->wait))
wake_up_interruptible(&wq->wait)
...
}
The race for tcp fires when the __add_wait_queue changes done by CPU1 stay in its cache, and so does the tp->rcv_nxt update on CPU2 side. The CPU1 could then endup calling schedule and sleep forever if there are no more data on the socket.
-
void
sock_poll_wait
(struct file *filp, struct socket *sock, poll_table *p)¶ place memory barrier behind the poll_wait call.
Parameters
struct file *filp
file
struct socket *sock
socket to wait on
poll_table *p
poll_table
Description
See the comments in the wq_has_sleeper function.
Parameters
struct sock *sk
socket
Description
Use the per task page_frag instead of the per socket one for
optimization when we know that we’re in process context and own
everything that’s associated with current
.
Both direct reclaim and page faults can nest inside other
socket operations and end up recursing into sk_page_frag()
while it’s already in use: explicitly avoid task page_frag
usage if the caller is potentially doing any of them.
This assumes that page fault handlers use the GFP_NOFS flags.
Return
a per task page_frag if context allows that, otherwise a per socket one.
-
void
_sock_tx_timestamp
(struct sock *sk, __u16 tsflags, __u8 *tx_flags, __u32 *tskey)¶ checks whether the outgoing packet is to be time stamped
Parameters
struct sock *sk
socket sending this packet
__u16 tsflags
timestamping flags to use
__u8 *tx_flags
completed with instructions for time stamping
__u32 *tskey
filled in with next sk_tskey (not for TCP, which uses seqno)
Note
callers should take care of initial *tx_flags
value (usually 0)
Parameters
struct sock *sk
socket to eat this skb from
struct sk_buff *skb
socket buffer to eat
Description
This routine must be called with interrupts disabled or with the socket locked so that the sk_buff queue operation is ok.
Parameters
struct sk_buff *skb
sk_buff to steal the socket from
bool *refcounted
is set to true if the socket is reference-counted
-
struct file *
sock_alloc_file
(struct socket *sock, int flags, const char *dname)¶ Bind a
socket
to afile
Parameters
struct socket *sock
socket
int flags
file status flags
const char *dname
protocol name
Returns the
file
bound with sock, implicitly storing it in sock->file. If dname isNULL
, sets to “”. On failure the return is a ERR pointer (see linux/err.h). This function uses GFP_KERNEL internally.
Parameters
struct file *file
file
On failure returns
NULL
.
Parameters
int fd
file handle
int *err
pointer to an error code return
The file handle passed in is locked and the socket it is bound to is returned. If an error occurs the err pointer is overwritten with a negative errno code and NULL is returned. The function checks for both invalid handles and passing a handle which is not a socket.
On a success the socket object pointer is returned.
Parameters
void
no arguments
Description
Allocate a new inode and socket object. The two are bound together and initialised. The socket is then returned. If we are out of inodes NULL is returned. This functions uses GFP_KERNEL internally.
Parameters
struct socket *sock
socket to close
The socket is released from the protocol stack if it has a release callback, and the inode is then released if the socket is bound to an inode not a file.
Parameters
struct socket *sock
socket
struct msghdr *msg
message to send
Sends msg through sock, passing through LSM. Returns the number of bytes sent, or an error code.
-
int
kernel_sendmsg
(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size)¶ send a message through sock (kernel-space)
Parameters
struct socket *sock
socket
struct msghdr *msg
message header
struct kvec *vec
kernel vec
size_t num
vec array length
size_t size
total message data size
Builds the message data with vec and sends it through sock. Returns the number of bytes sent, or an error code.
-
int
kernel_sendmsg_locked
(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size)¶ send a message through sock (kernel-space)
Parameters
struct sock *sk
sock
struct msghdr *msg
message header
struct kvec *vec
output s/g array
size_t num
output s/g array length
size_t size
total message data size
Builds the message data with vec and sends it through sock. Returns the number of bytes sent, or an error code. Caller must hold sk.
Parameters
struct socket *sock
socket
struct msghdr *msg
message to receive
int flags
message flags
Receives msg from sock, passing through LSM. Returns the total number of bytes received, or an error.
-
int
kernel_recvmsg
(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags)¶ Receive a message from a socket (kernel space)
Parameters
struct socket *sock
The socket to receive the message from
struct msghdr *msg
Received message
struct kvec *vec
Input s/g array for message data
size_t num
Size of input s/g array
size_t size
Number of bytes to read
int flags
Message flags (MSG_DONTWAIT, etc…)
On return the msg structure contains the scatter/gather array passed in the vec argument. The array is modified so that it consists of the unfilled portion of the original array.
The returned value is the total number of bytes received, or an error.
Parameters
int family
protocol family (AF_INET, …)
int type
communication type (SOCK_STREAM, …)
int protocol
protocol (0, …)
struct socket **res
new socket
Creates a new socket and assigns it to res, passing through LSM. The new socket initialization is not complete, see
kernel_accept()
. Returns 0 or an error. On failure res is set toNULL
. This function internally uses GFP_KERNEL.
-
int
__sock_create
(struct net *net, int family, int type, int protocol, struct socket **res, int kern)¶ creates a socket
Parameters
struct net *net
net namespace
int family
protocol family (AF_INET, …)
int type
communication type (SOCK_STREAM, …)
int protocol
protocol (0, …)
struct socket **res
new socket
int kern
boolean for kernel space sockets
Creates a new socket and assigns it to res, passing through LSM. Returns 0 or an error. On failure res is set to
NULL
. kern must be set to true if the socket resides in kernel space. This function internally uses GFP_KERNEL.
Parameters
int family
protocol family (AF_INET, …)
int type
communication type (SOCK_STREAM, …)
int protocol
protocol (0, …)
struct socket **res
new socket
A wrapper around
__sock_create()
. Returns 0 or an error. This function internally uses GFP_KERNEL.
-
int
sock_create_kern
(struct net *net, int family, int type, int protocol, struct socket **res)¶ creates a socket (kernel space)
Parameters
struct net *net
net namespace
int family
protocol family (AF_INET, …)
int type
communication type (SOCK_STREAM, …)
int protocol
protocol (0, …)
struct socket **res
new socket
A wrapper around
__sock_create()
. Returns 0 or an error. This function internally uses GFP_KERNEL.
-
int
sock_register
(const struct net_proto_family *ops)¶ add a socket protocol handler
Parameters
const struct net_proto_family *ops
description of protocol
This function is called by a protocol handler that wants to advertise its address family, and have it linked into the socket interface. The value ops->family corresponds to the socket system call protocol family.
-
void
sock_unregister
(int family)¶ remove a protocol handler
Parameters
int family
protocol family to remove
This function is called by a protocol handler that wants to remove its address family, and have it unlinked from the new socket creation.
If protocol handler is a module, then it can use module reference counts to protect against new references. If protocol handler is not a module then it needs to provide its own protection in the ops->create routine.
-
int
kernel_bind
(struct socket *sock, struct sockaddr *addr, int addrlen)¶ bind an address to a socket (kernel space)
Parameters
struct socket *sock
socket
struct sockaddr *addr
address
int addrlen
length of address
Returns 0 or an error.
Parameters
struct socket *sock
socket
int backlog
pending connections queue size
Returns 0 or an error.
-
int
kernel_accept
(struct socket *sock, struct socket **newsock, int flags)¶ accept a connection (kernel space)
Parameters
struct socket *sock
listening socket
struct socket **newsock
new connected socket
int flags
flags
flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. If it fails, newsock is guaranteed to be
NULL
. Returns 0 or an error.
-
int
kernel_connect
(struct socket *sock, struct sockaddr *addr, int addrlen, int flags)¶ connect a socket (kernel space)
Parameters
struct socket *sock
socket
struct sockaddr *addr
address
int addrlen
address length
int flags
flags (O_NONBLOCK, …)
For datagram sockets, addr is the address to which datagrams are sent by default, and the only address from which datagrams are received. For stream sockets, attempts to connect to addr. Returns 0 or an error code.
-
int
kernel_getsockname
(struct socket *sock, struct sockaddr *addr)¶ get the address which the socket is bound (kernel space)
Parameters
struct socket *sock
socket
struct sockaddr *addr
address holder
Fills the addr pointer with the address which the socket is bound. Returns the length of the address in bytes or an error code.
-
int
kernel_getpeername
(struct socket *sock, struct sockaddr *addr)¶ get the address which the socket is connected (kernel space)
Parameters
struct socket *sock
socket
struct sockaddr *addr
address holder
Fills the addr pointer with the address which the socket is connected. Returns the length of the address in bytes or an error code.
-
int
kernel_sendpage
(struct socket *sock, struct page *page, int offset, size_t size, int flags)¶ send a
page
through a socket (kernel space)
Parameters
struct socket *sock
socket
struct page *page
page
int offset
page offset
size_t size
total size in bytes
int flags
flags (MSG_DONTWAIT, …)
Returns the total amount sent in bytes or an error.
-
int
kernel_sendpage_locked
(struct sock *sk, struct page *page, int offset, size_t size, int flags)¶ send a
page
through the locked sock (kernel space)
Parameters
struct sock *sk
sock
struct page *page
page
int offset
page offset
size_t size
total size in bytes
int flags
flags (MSG_DONTWAIT, …)
Returns the total amount sent in bytes or an error. Caller must hold sk.
-
int
kernel_sock_shutdown
(struct socket *sock, enum sock_shutdown_cmd how)¶ shut down part of a full-duplex connection (kernel space)
Parameters
struct socket *sock
socket
enum sock_shutdown_cmd how
connection part
Returns 0 or an error.
Parameters
struct sock *sk
socket
This routine returns the IP overhead imposed by a socket i.e. the length of the underlying IP header, depending on whether this is an IPv4 or IPv6 socket and the length from IP options turned on at the socket. Assumes that the caller has a lock on the socket.
-
struct sk_buff *
build_skb_around
(struct sk_buff *skb, void *data, unsigned int frag_size)¶ build a network buffer around provided skb
Parameters
struct sk_buff *skb
sk_buff provide by caller, must be memset cleared
void *data
data buffer provided by caller
unsigned int frag_size
size of data, or 0 if head was kmalloced
Parameters
void *data
data buffer provided by caller
unsigned int frag_size
size of data, or 0 if head was kmalloced
Description
Version of __napi_build_skb() that takes care of skb->head_frag and skb->pfmemalloc when the data is a page or page fragment.
Returns a new sk_buff
on success, NULL
on allocation failure.
-
struct sk_buff *
__alloc_skb
(unsigned int size, gfp_t gfp_mask, int flags, int node)¶ allocate a network buffer
Parameters
unsigned int size
size to allocate
gfp_t gfp_mask
allocation mask
int flags
If SKB_ALLOC_FCLONE is set, allocate from fclone cache instead of head cache and allocate a cloned (child) skb. If SKB_ALLOC_RX is set, __GFP_MEMALLOC will be used for allocations in case the data is required for writeback
int node
numa node to allocate memory on
Allocate a new
sk_buff
. The returned buffer has no headroom and a tail room of at least size bytes. The object has a reference count of one. The return is the buffer. On a failure the return isNULL
.Buffers may only be allocated from interrupts using a gfp_mask of
GFP_ATOMIC
.
-
struct sk_buff *
__netdev_alloc_skb
(struct net_device *dev, unsigned int len, gfp_t gfp_mask)¶ allocate an skbuff for rx on a specific device
Parameters
struct net_device *dev
network device to receive on
unsigned int len
length to allocate
gfp_t gfp_mask
get_free_pages mask, passed to alloc_skb
Allocate a new
sk_buff
and assign it a usage count of one. The buffer has NET_SKB_PAD headroom built in. Users should allocate the headroom they think they need without accounting for the built in space. The built in space is used for optimisations.NULL
is returned if there is no free memory.
-
struct sk_buff *
__napi_alloc_skb
(struct napi_struct *napi, unsigned int len, gfp_t gfp_mask)¶ allocate skbuff for rx in a specific NAPI instance
Parameters
struct napi_struct *napi
napi instance this buffer was allocated for
unsigned int len
length to allocate
gfp_t gfp_mask
get_free_pages mask, passed to alloc_skb and alloc_pages
Allocate a new sk_buff for use in NAPI receive. This buffer will attempt to allocate the head from a special reserved region used only for NAPI Rx allocation. By doing this we can save several CPU cycles by avoiding having to disable and re-enable IRQs.
NULL
is returned if there is no free memory.
Parameters
struct sk_buff *skb
buffer
Free an sk_buff. Release anything attached to the buffer. Clean the state. This is an internal helper function. Users should always call kfree_skb
-
void
kfree_skb_reason
(struct sk_buff *skb, enum skb_drop_reason reason)¶ free an sk_buff with special reason
Parameters
struct sk_buff *skb
buffer to free
enum skb_drop_reason reason
reason why this skb is dropped
Drop a reference to the buffer and free it if the usage count has hit zero. Meanwhile, pass the drop reason to ‘kfree_skb’ tracepoint.
Parameters
struct sk_buff *skb
buffer that triggered an error
Report xmit error if a device callback is tracking this skb. skb must be freed afterwards.
Parameters
struct sk_buff *skb
buffer to free
Drop a ref to the buffer and free it if the usage count has hit zero Functions identically to kfree_skb, but kfree_skb assumes that the frame is being dropped after a failure and notes that
-
struct sk_buff *
alloc_skb_for_msg
(struct sk_buff *first)¶ allocate sk_buff to wrap frag list forming a msg
Parameters
struct sk_buff *first
first sk_buff of the msg
Parameters
struct sk_buff *dst
the skb to receive the contents
struct sk_buff *src
the skb to supply the contents
This is identical to skb_clone except that the target skb is supplied by the user.
The target skb is returned upon exit.
Parameters
struct sk_buff *skb
the skb to modify
gfp_t gfp_mask
allocation priority
This must be called on skb with SKBFL_ZEROCOPY_ENABLE. It will copy all frags into kernel and drop the reference to userspace pages.
If this function is called from an interrupt gfp_mask() must be
GFP_ATOMIC
.Returns 0 on success or a negative error code on failure to allocate kernel memory to copy to.
Parameters
struct sk_buff *skb
buffer to clone
gfp_t gfp_mask
allocation priority
Duplicate an
sk_buff
. The new one is not owned by a socket. Both copies share the same packet data but not structure. The new buffer has a reference count of 1. If the allocation fails the function returnsNULL
otherwise the new buffer is returned.If this function is called from an interrupt gfp_mask() must be
GFP_ATOMIC
.
-
struct sk_buff *
skb_copy
(const struct sk_buff *skb, gfp_t gfp_mask)¶ create private copy of an sk_buff
Parameters
const struct sk_buff *skb
buffer to copy
gfp_t gfp_mask
allocation priority
Make a copy of both an
sk_buff
and its data. This is used when the caller wishes to modify the data and needs a private copy of the data to alter. ReturnsNULL
on failure or the pointer to the buffer on success. The returned buffer has a reference count of 1.As by-product this function converts non-linear
sk_buff
to linear one, so thatsk_buff
becomes completely private and caller is allowed to modify all the data of returned buffer. This means that this function is not recommended for use in circumstances when only header is going to be modified. Use pskb_copy() instead.
-
struct sk_buff *
__pskb_copy_fclone
(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone)¶ create copy of an sk_buff with private head.
Parameters
struct sk_buff *skb
buffer to copy
int headroom
headroom of new skb
gfp_t gfp_mask
allocation priority
bool fclone
if true allocate the copy of the skb from the fclone cache instead of the head cache; it is recommended to set this to true for the cases where the copy will likely be cloned
Make a copy of both an
sk_buff
and part of its data, located in header. Fragmented data remain shared. This is used when the caller wishes to modify only header ofsk_buff
and needs private copy of the header to alter. ReturnsNULL
on failure or the pointer to the buffer on success. The returned buffer has a reference count of 1.
-
int
pskb_expand_head
(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask)¶ reallocate header of
sk_buff
Parameters
struct sk_buff *skb
buffer to reallocate
int nhead
room to add at head
int ntail
room to add at tail
gfp_t gfp_mask
allocation priority
Expands (or creates identical copy, if nhead and ntail are zero) header of skb.
sk_buff
itself is not changed.sk_buff
MUST have reference count of 1. Returns zero in the case of success or error, if expansion failed. In the last case,sk_buff
is not changed.All the pointers pointing into skb header may change and must be reloaded after call to this function.
-
struct sk_buff *
skb_expand_head
(struct sk_buff *skb, unsigned int headroom)¶ reallocate header of
sk_buff
Parameters
struct sk_buff *skb
buffer to reallocate
unsigned int headroom
needed headroom
Unlike skb_realloc_headroom, this one does not allocate a new skb if possible; copies skb->sk to new skb as needed and frees original skb in case of failures.
It expect increased headroom and generates warning otherwise.
-
struct sk_buff *
skb_copy_expand
(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t gfp_mask)¶ copy and expand sk_buff
Parameters
const struct sk_buff *skb
buffer to copy
int newheadroom
new free bytes at head
int newtailroom
new free bytes at tail
gfp_t gfp_mask
allocation priority
Make a copy of both an
sk_buff
and its data and while doing so allocate additional space.This is used when the caller wishes to modify the data and needs a private copy of the data to alter as well as more space for new fields. Returns
NULL
on failure or the pointer to the buffer on success. The returned buffer has a reference count of 1.You must pass
GFP_ATOMIC
as the allocation priority if this function is called from an interrupt.
Parameters
struct sk_buff *skb
buffer to pad
int pad
space to pad
bool free_on_error
free buffer on error
Ensure that a buffer is followed by a padding area that is zero filled. Used by network drivers which may DMA or transfer data beyond the buffer end onto the wire.
May return error in out of memory cases. The skb is freed on error if free_on_error is true.
-
void *
pskb_put
(struct sk_buff *skb, struct sk_buff *tail, int len)¶ add data to the tail of a potentially fragmented buffer
Parameters
struct sk_buff *skb
start of the buffer to use
struct sk_buff *tail
tail fragment of the buffer to use
int len
amount of data to add
This function extends the used data area of the potentially fragmented buffer. tail must be the last fragment of skb – or skb itself. If this would exceed the total buffer size the kernel will panic. A pointer to the first byte of the extra data is returned.
Parameters
struct sk_buff *skb
buffer to use
unsigned int len
amount of data to add
This function extends the used data area of the buffer. If this would exceed the total buffer size the kernel will panic. A pointer to the first byte of the extra data is returned.
Parameters
struct sk_buff *skb
buffer to use
unsigned int len
amount of data to add
This function extends the used data area of the buffer at the buffer start. If this would exceed the total buffer headroom the kernel will panic. A pointer to the first byte of the extra data is returned.
Parameters
struct sk_buff *skb
buffer to use
unsigned int len
amount of data to remove
This function removes data from the start of a buffer, returning the memory to the headroom. A pointer to the next data in the buffer is returned. Once the data has been pulled future pushes will overwrite the old data.
-
void *
skb_pull_data
(struct sk_buff *skb, size_t len)¶ remove data from the start of a buffer returning its original position.
Parameters
struct sk_buff *skb
buffer to use
size_t len
amount of data to remove
This function removes data from the start of a buffer, returning the memory to the headroom. A pointer to the original data in the buffer is returned after checking if there is enough data to pull. Once the data has been pulled future pushes will overwrite the old data.
Parameters
struct sk_buff *skb
buffer to alter
unsigned int len
new length
Cut the length of a buffer down by removing data from the tail. If the buffer is already under the length specified it is not modified. The skb must be linear.
Parameters
struct sk_buff *skb
buffer to reallocate
int delta
number of bytes to advance tail
The function makes a sense only on a fragmented
sk_buff
, it expands header moving its tail forward and copying necessary data from fragmented part.sk_buff
MUST have reference count of 1.Returns
NULL
(andsk_buff
does not change) if pull failed or value of new tail of skb in the case of success.All the pointers pointing into skb header may change and must be reloaded after call to this function.
-
int
skb_copy_bits
(const struct sk_buff *skb, int offset, void *to, int len)¶ copy bits from skb to kernel buffer
Parameters
const struct sk_buff *skb
source skb
int offset
offset in source
void *to
destination buffer
int len
number of bytes to copy
Copy the specified number of bytes from the source skb to the destination buffer.
- CAUTION ! :
If its prototype is ever changed, check arch/{*}/net/{*}.S files, since it is called from BPF assembly code.
-
int
skb_store_bits
(struct sk_buff *skb, int offset, const void *from, int len)¶ store bits from kernel buffer to skb
Parameters
struct sk_buff *skb
destination buffer
int offset
offset in destination
const void *from
source buffer
int len
number of bytes to copy
Copy the specified number of bytes from the source buffer to the destination skb. This function handles all the messy bits of traversing fragment lists and such.
Parameters
struct sk_buff *to
destination buffer
struct sk_buff *from
source buffer
int len
number of bytes to copy from source buffer
int hlen
size of linear headroom in destination buffer
Copies up to len bytes from from to to by creating references to the frags in the source buffer.
The hlen as calculated by skb_zerocopy_headlen() specifies the headroom in the to buffer.
Return value: 0: everything is OK -ENOMEM: couldn’t orphan frags of from due to lack of memory -EFAULT:
skb_copy_bits()
found some problem with skb geometry
Parameters
struct sk_buff_head *list
list to dequeue from
Remove the head of the list. The list lock is taken so the function may be used safely with other locking list functions. The head item is returned or
NULL
if the list is empty.
Parameters
struct sk_buff_head *list
list to dequeue from
Remove the tail of the list. The list lock is taken so the function may be used safely with other locking list functions. The tail item is returned or
NULL
if the list is empty.
-
void
skb_queue_purge
(struct sk_buff_head *list)¶ empty a list
Parameters
struct sk_buff_head *list
list to empty
Delete all buffers on an
sk_buff
list. Each buffer is removed from the list and one reference dropped. This function takes the list lock and is atomic with respect to other list locking functions.
-
void
skb_queue_head
(struct sk_buff_head *list, struct sk_buff *newsk)¶ queue a buffer at the list head
Parameters
struct sk_buff_head *list
list to use
struct sk_buff *newsk
buffer to queue
Queue a buffer at the start of the list. This function takes the list lock and can be used safely with other locking
sk_buff
functions safely.A buffer cannot be placed on two lists at the same time.
-
void
skb_queue_tail
(struct sk_buff_head *list, struct sk_buff *newsk)¶ queue a buffer at the list tail
Parameters
struct sk_buff_head *list
list to use
struct sk_buff *newsk
buffer to queue
Queue a buffer at the tail of the list. This function takes the list lock and can be used safely with other locking
sk_buff
functions safely.A buffer cannot be placed on two lists at the same time.
Parameters
struct sk_buff *skb
buffer to remove
struct sk_buff_head *list
list to use
Remove a packet from a list. The list locks are taken and this function is atomic with respect to other list locked calls
You must know what list the SKB is on.
-
void
skb_append
(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list)¶ append a buffer
Parameters
struct sk_buff *old
buffer to insert after
struct sk_buff *newsk
buffer to insert
struct sk_buff_head *list
list to use
Place a packet after a given packet in a list. The list locks are taken and this function is atomic with respect to other list locked calls. A buffer cannot be placed on two lists at the same time.
-
void
skb_split
(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)¶ Split fragmented skb to two parts at length len.
Parameters
struct sk_buff *skb
the buffer to split
struct sk_buff *skb1
the buffer to receive the second part
const u32 len
new length for skb
-
void
skb_prepare_seq_read
(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st)¶ Prepare a sequential read of skb data
Parameters
struct sk_buff *skb
the buffer to read
unsigned int from
lower offset of data to be read
unsigned int to
upper offset of data to be read
struct skb_seq_state *st
state variable
Description
Initializes the specified state variable. Must be called before
invoking skb_seq_read()
for the first time.
-
unsigned int
skb_seq_read
(unsigned int consumed, const u8 **data, struct skb_seq_state *st)¶ Sequentially read skb data
Parameters
unsigned int consumed
number of bytes consumed by the caller so far
const u8 **data
destination pointer for data to be returned
struct skb_seq_state *st
state variable
Description
Reads a block of skb data at consumed relative to the
lower offset specified to skb_prepare_seq_read()
. Assigns
the head of the data block to data and returns the length
of the block or 0 if the end of the skb data or the upper
offset has been reached.
The caller is not required to consume all of the data
returned, i.e. consumed is typically set to the number
of bytes already consumed and the next call to
skb_seq_read()
will return the remaining part of the block.
- Note 1: The size of each block of data returned can be arbitrary,
this limitation is the cost for zerocopy sequential reads of potentially non linear data.
- Note 2: Fragment lists within fragments are not implemented
at the moment, state->root_skb could be replaced with a stack for this purpose.
-
void
skb_abort_seq_read
(struct skb_seq_state *st)¶ Abort a sequential read of skb data
Parameters
struct skb_seq_state *st
state variable
Description
Must be called if skb_seq_read()
was not called until it
returned 0.
-
unsigned int
skb_find_text
(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config)¶ Find a text pattern in skb data
Parameters
struct sk_buff *skb
the buffer to look in
unsigned int from
search offset
unsigned int to
search limit
struct ts_config *config
textsearch configuration
Description
Finds a pattern in the skb data according to the specified
textsearch configuration. Use textsearch_next()
to retrieve
subsequent occurrences of the pattern. Returns the offset
to the first occurrence or UINT_MAX if no match was found.
Parameters
struct sk_buff *skb
buffer to update
unsigned int len
length of data pulled
This function performs an skb_pull on the packet and updates the CHECKSUM_COMPLETE checksum. It should be used on receive path processing instead of skb_pull unless you know that the checksum difference is zero (e.g., a valid IP header) or you are setting ip_summed to CHECKSUM_NONE.
-
struct sk_buff *
skb_segment
(struct sk_buff *head_skb, netdev_features_t features)¶ Perform protocol segmentation on skb.
Parameters
struct sk_buff *head_skb
buffer to segment
netdev_features_t features
features for the output path (see dev->features)
This function performs segmentation on the given skb. It returns a pointer to the first in a list of new skbs for the segments. In case of error it returns ERR_PTR(err).
-
int
skb_to_sgvec
(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)¶ Fill a scatter-gather list from a socket buffer
Parameters
struct sk_buff *skb
Socket buffer containing the buffers to be mapped
struct scatterlist *sg
The scatter-gather list to map into
int offset
The offset into the buffer’s contents to start mapping
int len
Length of buffer space to be mapped
Fill the specified scatter-gather list with mappings/pointers into a region of the buffer space attached to a socket buffer. Returns either the number of scatterlist items used, or -EMSGSIZE if the contents could not fit.
-
int
skb_cow_data
(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)¶ Check that a socket buffer’s data buffers are writable
Parameters
struct sk_buff *skb
The socket buffer to check.
int tailbits
Amount of trailing space to be added
struct sk_buff **trailer
Returned pointer to the skb where the tailbits space begins
Make sure that the data buffers attached to a socket buffer are writable. If they are not, private copies are made of the data buffers and the socket buffer is set to use these instead.
If tailbits is given, make sure that there is space to write tailbits bytes of data beyond current end of socket buffer. trailer will be set to point to the skb in which this space begins.
The number of scatterlist elements required to completely map the COW’d and extended socket buffer will be returned.
-
struct sk_buff *
skb_clone_sk
(struct sk_buff *skb)¶ create clone of skb, and take reference to socket
Parameters
struct sk_buff *skb
the skb to clone
Description
This function creates a clone of a buffer that holds a reference on sk_refcnt. Buffers created via this function are meant to be returned using sock_queue_err_skb, or free via kfree_skb.
When passing buffers allocated with this function to sock_queue_err_skb it is necessary to wrap the call with sock_hold/sock_put in order to prevent the socket from being released prior to being enqueued on the sk_error_queue.
-
bool
skb_partial_csum_set
(struct sk_buff *skb, u16 start, u16 off)¶ set up and verify partial csum values for packet
Parameters
struct sk_buff *skb
the skb to set
u16 start
the number of bytes after skb->data to start checksumming.
u16 off
the offset from start to place the checksum.
Description
For untrusted partially-checksummed packets, we need to make sure the values for skb->csum_start and skb->csum_offset are valid so we don’t oops.
This function checks and sets those values and skb->ip_summed: if this returns false you should drop the packet.
Parameters
struct sk_buff *skb
the skb to set up
bool recalculate
if true the pseudo-header checksum will be recalculated
-
struct sk_buff *
skb_checksum_trimmed
(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb))¶ validate checksum of an skb
Parameters
struct sk_buff *skb
the skb to check
unsigned int transport_len
the data length beyond the network header
__sum16(*skb_chkf)(struct sk_buff *skb)
checksum function to use
Description
Applies the given checksum function skb_chkf to the provided skb. Returns a checked and maybe trimmed skb. Returns NULL on error.
If the skb has data beyond the given transport length, then a trimmed & cloned skb is checked and returned.
Caller needs to set the skb transport header and free any returned skb if it differs from the provided skb.
-
bool
skb_try_coalesce
(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize)¶ try to merge skb to prior one
Parameters
struct sk_buff *to
prior buffer
struct sk_buff *from
buffer to add
bool *fragstolen
pointer to boolean
int *delta_truesize
how much more was allocated than was requested
Parameters
struct sk_buff *skb
buffer to clean
bool xnet
packet is crossing netns
Description
skb_scrub_packet can be used after encapsulating or decapsulting a packet into/from a tunnel. Some information have to be cleared during these operations. skb_scrub_packet can also be used to clean a skb before injecting it in another namespace (xnet == true). We have to clear all information in the skb that could impact namespace isolation.
-
bool
skb_gso_validate_network_len
(const struct sk_buff *skb, unsigned int mtu)¶ Will a split GSO skb fit into a given MTU?
Parameters
const struct sk_buff *skb
GSO skb
unsigned int mtu
MTU to validate against
Description
skb_gso_validate_network_len validates if a given skb will fit a wanted MTU once split. It considers L3 headers, L4 headers, and the payload.
-
bool
skb_gso_validate_mac_len
(const struct sk_buff *skb, unsigned int len)¶ Will a split GSO skb fit in a given length?
Parameters
const struct sk_buff *skb
GSO skb
unsigned int len
length to validate against
Description
skb_gso_validate_mac_len validates if a given skb will fit a wanted length once split, including L2, L3 and L4 headers and the payload.
Parameters
struct sk_buff *skb
Socket buffer to modify
Description
Drop the Ethernet header of skb.
Expects that skb->data points to the mac header and that no VLAN tags are present.
Returns 0 on success, -errno otherwise.
-
int
skb_eth_push
(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src)¶ Add a new Ethernet header at the head of a packet
Parameters
struct sk_buff *skb
Socket buffer to modify
const unsigned char *dst
Destination MAC address of the new header
const unsigned char *src
Source MAC address of the new header
Description
Prepend skb with a new Ethernet header.
Expects that skb->data points to the mac header, which must be empty.
Returns 0 on success, -errno otherwise.
-
int
skb_mpls_push
(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet)¶ push a new MPLS header after mac_len bytes from start of the packet
Parameters
struct sk_buff *skb
buffer
__be32 mpls_lse
MPLS label stack entry to push
__be16 mpls_proto
ethertype of the new MPLS header (expects 0x8847 or 0x8848)
int mac_len
length of the MAC header
bool ethernet
flag to indicate if the resulting packet after skb_mpls_push is ethernet
Description
Expects skb->data at mac header.
Returns 0 on success, -errno otherwise.
-
int
skb_mpls_pop
(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet)¶ pop the outermost MPLS header
Parameters
struct sk_buff *skb
buffer
__be16 next_proto
ethertype of header after popped MPLS header
int mac_len
length of the MAC header
bool ethernet
flag to indicate if the packet is ethernet
Description
Expects skb->data at mac header.
Returns 0 on success, -errno otherwise.
-
int
skb_mpls_update_lse
(struct sk_buff *skb, __be32 mpls_lse)¶ modify outermost MPLS header and update csum
Parameters
struct sk_buff *skb
buffer
__be32 mpls_lse
new MPLS label stack entry to update to
Description
Expects skb->data at mac header.
Returns 0 on success, -errno otherwise.
Parameters
struct sk_buff *skb
buffer
Description
Expects skb->data at mac header.
Returns 0 on success, -errno otherwise.
-
struct sk_buff *
alloc_skb_with_frags
(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask)¶ allocate skb with page frags
Parameters
unsigned long header_len
size of linear part
unsigned long data_len
needed length in frags
int max_page_order
max page order desired.
int *errcode
pointer to error code if any
gfp_t gfp_mask
allocation mask
Description
This can be used to allocate a paged skb, given a maximal order for frags.
-
void *
skb_ext_add
(struct sk_buff *skb, enum skb_ext_id id)¶ allocate space for given extension, COW if needed
Parameters
struct sk_buff *skb
buffer
enum skb_ext_id id
extension to allocate space for
Description
Allocates enough space for the given extension. If the extension is already present, a pointer to that extension is returned.
If the skb was cloned, COW applies and the returned memory can be modified without changing the extension space of clones buffers.
Returns pointer to the extension or NULL on allocation failure.
-
bool
sk_ns_capable
(const struct sock *sk, struct user_namespace *user_ns, int cap)¶ General socket capability test
Parameters
const struct sock *sk
Socket to use a capability on or through
struct user_namespace *user_ns
The user namespace of the capability to use
int cap
The capability to use
Description
Test to see if the opener of the socket had when the socket was created and the current process has the capability cap in the user namespace user_ns.
Parameters
const struct sock *sk
Socket to use a capability on or through
int cap
The global capability to use
Description
Test to see if the opener of the socket had when the socket was created and the current process has the capability cap in all user namespaces.
Parameters
const struct sock *sk
Socket to use a capability on or through
int cap
The capability to use
Description
Test to see if the opener of the socket had when the socket was created and the current process has the capability cap over the network namespace the socket is a member of.
Parameters
struct sock *sk
socket to set it on
Description
Set SOCK_MEMALLOC
on a socket for access to emergency reserves.
It’s the responsibility of the admin to adjust min_free_kbytes
to meet the requirements
-
struct sock *
sk_alloc
(struct net *net, int family, gfp_t priority, struct proto *prot, int kern)¶ All socket objects are allocated here
Parameters
struct net *net
the applicable net namespace
int family
protocol family
gfp_t priority
for allocation (
GFP_KERNEL
,GFP_ATOMIC
, etc)struct proto *prot
struct proto associated with this new sock instance
int kern
is this to be a kernel socket?
-
struct sock *
sk_clone_lock
(const struct sock *sk, const gfp_t priority)¶ clone a socket, and lock its clone
Parameters
const struct sock *sk
the socket to clone
const gfp_t priority
for allocation (
GFP_KERNEL
,GFP_ATOMIC
, etc)Caller must unlock socket even in error path (bh_unlock_sock(newsk))
-
bool
skb_page_frag_refill
(unsigned int sz, struct page_frag *pfrag, gfp_t gfp)¶ check that a page_frag contains enough room
Parameters
unsigned int sz
minimum size of the fragment we want to get
struct page_frag *pfrag
pointer to page_frag
gfp_t gfp
priority for memory allocation
Note
While this allocator tries to use high order pages, there is no guarantee that allocations succeed. Therefore, sz MUST be less or equal than PAGE_SIZE.
-
int
sk_wait_data
(struct sock *sk, long *timeo, const struct sk_buff *skb)¶ wait for data to arrive at sk_receive_queue
Parameters
struct sock *sk
sock to wait on
long *timeo
for how long
const struct sk_buff *skb
last skb seen on sk_receive_queue
Description
Now socket state including sk->sk_err is changed only under lock, hence we may omit checks after joining wait queue. We check receive queue before schedule() only as optimization; it is very likely that release_sock() added new data.
-
int
__sk_mem_raise_allocated
(struct sock *sk, int size, int amt, int kind)¶ increase memory_allocated
Parameters
struct sock *sk
socket
int size
memory size to allocate
int amt
pages to allocate
int kind
allocation type
Similar to
__sk_mem_schedule()
, but does not update sk_forward_alloc
-
int
__sk_mem_schedule
(struct sock *sk, int size, int kind)¶ increase sk_forward_alloc and memory_allocated
Parameters
struct sock *sk
socket
int size
memory size to allocate
int kind
allocation type
If kind is SK_MEM_SEND, it means wmem allocation. Otherwise it means rmem allocation. This function assumes that protocols which have memory_pressure use sk_wmem_queued as write buffer accounting.
Parameters
struct sock *sk
socket
int amount
number of quanta
Similar to
__sk_mem_reclaim()
, but does not update sk_forward_alloc
Parameters
struct sock *sk
socket
int amount
number of bytes (rounded down to a SK_MEM_QUANTUM multiple)
-
struct sk_buff *
__skb_try_recv_datagram
(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last)¶ Receive a datagram skbuff
Parameters
struct sock *sk
socket
struct sk_buff_head *queue
socket queue from which to receive
unsigned int flags
MSG_ flags
int *off
an offset in bytes to peek skb from. Returns an offset within an skb where data actually starts
int *err
error code returned
struct sk_buff **last
set to last peeked message to inform the wait function what to look for when peeking
Get a datagram skbuff, understands the peeking, nonblocking wakeups and possible races. This replaces identical code in packet, raw and udp, as well as the IPX AX.25 and Appletalk. It also finally fixes the long standing peek and read race for datagram sockets. If you alter this routine remember it must be re-entrant.
This function will lock the socket if a skb is returned, so the caller needs to unlock the socket in that case (usually by calling skb_free_datagram). Returns NULL with err set to -EAGAIN if no data was available or to some other value if an error was detected.
It does not lock socket since today. This function is
free of race conditions. This measure should/can improve
significantly datagram socket latencies at high loads,
when data copying to user space takes lots of time.
(BTW I’ve just killed the last cli() in IP/IPv6/core/netlink/packet
Great win.)
–ANK (980729)
The order of the tests when we find no data waiting are specified quite explicitly by POSIX 1003.1g, don’t change them without having the standard around please.
-
int
skb_kill_datagram
(struct sock *sk, struct sk_buff *skb, unsigned int flags)¶ Free a datagram skbuff forcibly
Parameters
struct sock *sk
socket
struct sk_buff *skb
datagram skbuff
unsigned int flags
MSG_ flags
This function frees a datagram skbuff that was received by skb_recv_datagram. The flags argument must match the one used for skb_recv_datagram.
If the MSG_PEEK flag is set, and the packet is still on the receive queue of the socket, it will be taken off the queue before it is freed.
This function currently only disables BH when acquiring the sk_receive_queue lock. Therefore it must not be used in a context where that lock is acquired in an IRQ context.
It returns 0 if the packet was removed by us.
-
int
skb_copy_and_hash_datagram_iter
(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, struct ahash_request *hash)¶ Copy datagram to an iovec iterator and update a hash.
Parameters
const struct sk_buff *skb
buffer to copy
int offset
offset in the buffer to start copying from
struct iov_iter *to
iovec iterator to copy to
int len
amount of data to copy from buffer to iovec
struct ahash_request *hash
hash request to update
-
int
skb_copy_datagram_iter
(const struct sk_buff *skb, int offset, struct iov_iter *to, int len)¶ Copy a datagram to an iovec iterator.
Parameters
const struct sk_buff *skb
buffer to copy
int offset
offset in the buffer to start copying from
struct iov_iter *to
iovec iterator to copy to
int len
amount of data to copy from buffer to iovec
-
int
skb_copy_datagram_from_iter
(struct sk_buff *skb, int offset, struct iov_iter *from, int len)¶ Copy a datagram from an iov_iter.
Parameters
struct sk_buff *skb
buffer to copy
int offset
offset in the buffer to start copying to
struct iov_iter *from
the copy source
int len
amount of data to copy to buffer from iovec
Returns 0 or -EFAULT.
-
int
zerocopy_sg_from_iter
(struct sk_buff *skb, struct iov_iter *from)¶ Build a zerocopy datagram from an iov_iter
Parameters
struct sk_buff *skb
buffer to copy
struct iov_iter *from
the source to copy from
The function will first copy up to headlen, and then pin the userspace pages and build frags through them.
Returns 0, -EFAULT or -EMSGSIZE.
-
int
skb_copy_and_csum_datagram_msg
(struct sk_buff *skb, int hlen, struct msghdr *msg)¶ Copy and checksum skb to user iovec.
Parameters
struct sk_buff *skb
skbuff
int hlen
hardware length
struct msghdr *msg
destination
Caller _must_ check that skb will fit to this iovec.
Return
- 0 - success.
-EINVAL - checksum failure. -EFAULT - fault during copy.
-
__poll_t
datagram_poll
(struct file *file, struct socket *sock, poll_table *wait)¶ generic datagram poll
Parameters
struct file *file
file struct
struct socket *sock
socket
poll_table *wait
poll table
Datagram poll: Again totally generic. This also handles sequenced packet sockets providing the socket receive queue is only ever holding data ready to receive.
Note
- when you don’t use this routine for this protocol,
and you use a different write policy from sock_writeable() then please supply your own write_space callback.
-
int
sk_stream_wait_connect
(struct sock *sk, long *timeo_p)¶ Wait for a socket to get into the connected state
Parameters
struct sock *sk
sock to wait on
long *timeo_p
for how long to wait
Description
Must be called with the socket locked.
Parameters
struct sock *sk
socket to wait for memory
long *timeo_p
for how long
Socket Filter¶
-
int
sk_filter_trim_cap
(struct sock *sk, struct sk_buff *skb, unsigned int cap)¶ run a packet through a socket filter
Parameters
struct sock *sk
sock associated with
sk_buff
struct sk_buff *skb
buffer to filter
unsigned int cap
limit on how short the eBPF program may trim the packet
Description
Run the eBPF program and then cut skb->data to correct size returned by the program. If pkt_len is 0 we toss packet. If skb->len is smaller than pkt_len we keep whole skb->data. This is the socket level wrapper to bpf_prog_run. It returns 0 if the packet should be accepted or -EPERM if the packet should be tossed.
-
int
bpf_prog_create
(struct bpf_prog **pfp, struct sock_fprog_kern *fprog)¶ create an unattached filter
Parameters
struct bpf_prog **pfp
the unattached filter that is created
struct sock_fprog_kern *fprog
the filter program
Description
Create a filter independent of any socket. We first run some sanity checks on it to make sure it does not explode on us later. If an error occurs or there is insufficient memory for the filter a negative errno code is returned. On success the return is zero.
-
int
bpf_prog_create_from_user
(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig)¶ create an unattached filter from user buffer
Parameters
struct bpf_prog **pfp
the unattached filter that is created
struct sock_fprog *fprog
the filter program
bpf_aux_classic_check_t trans
post-classic verifier transformation handler
bool save_orig
save classic BPF program
Description
This function effectively does the same as bpf_prog_create()
, only
that it builds up its insns buffer from user space provided buffer.
It also allows for passing a bpf_aux_classic_check_t handler.
Parameters
struct sock_fprog *fprog
the filter program
struct sock *sk
the socket to use
Description
Attach the user’s filter code. We first run some sanity checks on it to make sure it does not explode on us later. If an error occurs or there is insufficient memory for the filter a negative errno code is returned. On success the return is zero.
Generic Network Statistics¶
-
struct
gnet_stats_basic
¶ byte/packet throughput statistics
Definition
struct gnet_stats_basic {
__u64 bytes;
__u32 packets;
};
Members
bytes
number of seen bytes
packets
number of seen packets
-
struct
gnet_stats_rate_est
¶ rate estimator
Definition
struct gnet_stats_rate_est {
__u32 bps;
__u32 pps;
};
Members
bps
current byte rate
pps
current packet rate
-
struct
gnet_stats_rate_est64
¶ rate estimator
Definition
struct gnet_stats_rate_est64 {
__u64 bps;
__u64 pps;
};
Members
bps
current byte rate
pps
current packet rate
-
struct
gnet_stats_queue
¶ queuing statistics
Definition
struct gnet_stats_queue {
__u32 qlen;
__u32 backlog;
__u32 drops;
__u32 requeues;
__u32 overlimits;
};
Members
qlen
queue length
backlog
backlog size of queue
drops
number of dropped packets
requeues
number of requeues
overlimits
number of enqueues over the limit
-
struct
gnet_estimator
¶ rate estimator configuration
Definition
struct gnet_estimator {
signed char interval;
unsigned char ewma_log;
};
Members
interval
sampling period
ewma_log
the log of measurement window weight
-
int
gnet_stats_start_copy_compat
(struct sk_buff *skb, int type, int tc_stats_type, int xstats_type, spinlock_t *lock, struct gnet_dump *d, int padattr)¶ start dumping procedure in compatibility mode
Parameters
struct sk_buff *skb
socket buffer to put statistics TLVs into
int type
TLV type for top level statistic TLV
int tc_stats_type
TLV type for backward compatibility struct tc_stats TLV
int xstats_type
TLV type for backward compatibility xstats TLV
spinlock_t *lock
statistics lock
struct gnet_dump *d
dumping handle
int padattr
padding attribute
Description
Initializes the dumping handle, grabs the statistic lock and appends an empty TLV header to the socket buffer for use a container for all other statistic TLVS.
The dumping handle is marked to be in backward compatibility mode telling all gnet_stats_copy_XXX() functions to fill a local copy of struct tc_stats.
Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
-
int
gnet_stats_start_copy
(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr)¶ start dumping procedure in compatibility mode
Parameters
struct sk_buff *skb
socket buffer to put statistics TLVs into
int type
TLV type for top level statistic TLV
spinlock_t *lock
statistics lock
struct gnet_dump *d
dumping handle
int padattr
padding attribute
Description
Initializes the dumping handle, grabs the statistic lock and appends an empty TLV header to the socket buffer for use a container for all other statistic TLVS.
Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
-
int
gnet_stats_copy_basic
(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running)¶ copy basic statistics into statistic TLV
Parameters
struct gnet_dump *d
dumping handle
struct gnet_stats_basic_sync __percpu *cpu
copy statistic per cpu
struct gnet_stats_basic_sync *b
basic statistics
bool running
true if b represents a running qdisc, thus b’s internal values might change during basic reads. Only used if cpu is NULL
Context
task; must not be run from IRQ or BH contexts
Description
Appends the basic statistics to the top level TLV created by
gnet_stats_start_copy()
.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gnet_stats_copy_basic_hw
(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, bool running)¶ copy basic hw statistics into statistic TLV
Parameters
struct gnet_dump *d
dumping handle
struct gnet_stats_basic_sync __percpu *cpu
copy statistic per cpu
struct gnet_stats_basic_sync *b
basic statistics
bool running
true if b represents a running qdisc, thus b’s internal values might change during basic reads. Only used if cpu is NULL
Context
task; must not be run from IRQ or BH contexts
Description
Appends the basic statistics to the top level TLV created by
gnet_stats_start_copy()
.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gnet_stats_copy_rate_est
(struct gnet_dump *d, struct net_rate_estimator __rcu **rate_est)¶ copy rate estimator statistics into statistics TLV
Parameters
struct gnet_dump *d
dumping handle
struct net_rate_estimator __rcu **rate_est
rate estimator
Description
Appends the rate estimator statistics to the top level TLV created by
gnet_stats_start_copy()
.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gnet_stats_copy_queue
(struct gnet_dump *d, struct gnet_stats_queue __percpu *cpu_q, struct gnet_stats_queue *q, __u32 qlen)¶ copy queue statistics into statistics TLV
Parameters
struct gnet_dump *d
dumping handle
struct gnet_stats_queue __percpu *cpu_q
per cpu queue statistics
struct gnet_stats_queue *q
queue statistics
__u32 qlen
queue length statistics
Description
Appends the queue statistics to the top level TLV created by
gnet_stats_start_copy()
. Using per cpu queue statistics if
they are available.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gnet_stats_copy_app
(struct gnet_dump *d, void *st, int len)¶ copy application specific statistics into statistics TLV
Parameters
struct gnet_dump *d
dumping handle
void *st
application specific statistics data
int len
length of data
Description
Appends the application specific statistics to the top level TLV created by
gnet_stats_start_copy()
and remembers the data for XSTATS if the dumping
handle is in backward compatibility mode.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gnet_stats_finish_copy
(struct gnet_dump *d)¶ finish dumping procedure
Parameters
struct gnet_dump *d
dumping handle
Description
Corrects the length of the top level TLV to include all TLVs added
by gnet_stats_copy_XXX() calls. Adds the backward compatibility TLVs
if gnet_stats_start_copy_compat()
was used and releases the statistics
lock.
Returns 0 on success or -1 with the statistic lock released if the room in the socket buffer was not sufficient.
-
int
gen_new_estimator
(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt)¶ create a new rate estimator
Parameters
struct gnet_stats_basic_sync *bstats
basic statistics
struct gnet_stats_basic_sync __percpu *cpu_bstats
bstats per cpu
struct net_rate_estimator __rcu **rate_est
rate estimator statistics
spinlock_t *lock
lock for statistics and control path
bool running
true if bstats represents a running qdisc, thus bstats’ internal values might change during basic reads. Only used if bstats_cpu is NULL
struct nlattr *opt
rate estimator configuration TLV
Description
Creates a new rate estimator with bstats
as source and rate_est
as destination. A new timer with the interval specified in the
configuration TLV is created. Upon each interval, the latest statistics
will be read from bstats
and the estimated rate will be stored in
rate_est
with the statistics lock grabbed during this period.
Returns 0 on success or a negative error code.
-
void
gen_kill_estimator
(struct net_rate_estimator __rcu **rate_est)¶ remove a rate estimator
Parameters
struct net_rate_estimator __rcu **rate_est
rate estimator
Description
Removes the rate estimator.
-
int
gen_replace_estimator
(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, bool running, struct nlattr *opt)¶ replace rate estimator configuration
Parameters
struct gnet_stats_basic_sync *bstats
basic statistics
struct gnet_stats_basic_sync __percpu *cpu_bstats
bstats per cpu
struct net_rate_estimator __rcu **rate_est
rate estimator statistics
spinlock_t *lock
lock for statistics and control path
bool running
true if bstats represents a running qdisc, thus bstats’ internal values might change during basic reads. Only used if cpu_bstats is NULL
struct nlattr *opt
rate estimator configuration TLV
Description
Replaces the configuration of a rate estimator by calling
gen_kill_estimator()
and gen_new_estimator()
.
Returns 0 on success or a negative error code.
-
bool
gen_estimator_active
(struct net_rate_estimator __rcu **rate_est)¶ test if estimator is currently in use
Parameters
struct net_rate_estimator __rcu **rate_est
rate estimator
Description
Returns true if estimator is active, and false if not.
SUN RPC subsystem¶
-
__be32 *
xdr_encode_opaque_fixed
(__be32 *p, const void *ptr, unsigned int nbytes)¶ Encode fixed length opaque data
Parameters
__be32 *p
pointer to current position in XDR buffer.
const void *ptr
pointer to data to encode (or NULL)
unsigned int nbytes
size of data.
Description
Copy the array of data of length nbytes at ptr to the XDR buffer at position p, then align to the next 32-bit boundary by padding with zero bytes (see RFC1832). Returns the updated current XDR buffer position
Note
if ptr is NULL, only the padding is performed.
-
__be32 *
xdr_encode_opaque
(__be32 *p, const void *ptr, unsigned int nbytes)¶ Encode variable length opaque data
Parameters
__be32 *p
pointer to current position in XDR buffer.
const void *ptr
pointer to data to encode (or NULL)
unsigned int nbytes
size of data.
Description
Returns the updated current XDR buffer position
-
void
xdr_terminate_string
(const struct xdr_buf *buf, const u32 len)¶ ‘0’-terminate a string residing in an xdr_buf
Parameters
const struct xdr_buf *buf
XDR buffer where string resides
const u32 len
length of string, in bytes
-
void
xdr_inline_pages
(struct xdr_buf *xdr, unsigned int offset, struct page **pages, unsigned int base, unsigned int len)¶ Prepare receive buffer for a large reply
Parameters
struct xdr_buf *xdr
xdr_buf into which reply will be placed
unsigned int offset
expected offset where data payload will start, in bytes
struct page **pages
vector of struct page pointers
unsigned int base
offset in first page where receive should start, in bytes
unsigned int len
expected size of the upper layer data payload, in bytes
-
void
_copy_from_pages
(char *p, struct page **pages, size_t pgbase, size_t len)¶
Parameters
char *p
pointer to destination
struct page **pages
array of pages
size_t pgbase
offset of source data
size_t len
length
Description
Copies data into an arbitrary memory location from an array of pages The copy is assumed to be non-overlapping.
-
unsigned int
xdr_stream_pos
(const struct xdr_stream *xdr)¶ Return the current offset from the start of the xdr_stream
Parameters
const struct xdr_stream *xdr
pointer to struct xdr_stream
-
unsigned int
xdr_page_pos
(const struct xdr_stream *xdr)¶ Return the current offset from the start of the xdr pages
Parameters
const struct xdr_stream *xdr
pointer to struct xdr_stream
-
void
xdr_init_encode
(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst)¶ Initialize a struct xdr_stream for sending data.
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
struct xdr_buf *buf
pointer to XDR buffer in which to encode data
__be32 *p
current pointer inside XDR buffer
struct rpc_rqst *rqst
pointer to controlling rpc_rqst, for debugging
Note
- at the moment the RPC client only passes the length of our
scratch buffer in the xdr_buf’s header kvec. Previously this meant we needed to call xdr_adjust_iovec() after encoding the data. With the new scheme, the xdr_stream manages the details of the buffer length, and takes care of adjusting the kvec length for us.
-
void
xdr_commit_encode
(struct xdr_stream *xdr)¶ Ensure all data is written to buffer
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
Description
We handle encoding across page boundaries by giving the caller a temporary location to write to, then later copying the data into place; xdr_commit_encode does that copying.
Normally the caller doesn’t need to call this directly, as the following xdr_reserve_space will do it. But an explicit call may be required at the end of encoding, or any other time when the xdr_buf data might be read.
-
__be32 *
xdr_reserve_space
(struct xdr_stream *xdr, size_t nbytes)¶ Reserve buffer space for sending
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
size_t nbytes
number of bytes to reserve
Description
Checks that we have enough buffer space to encode ‘nbytes’ more bytes of data. If so, update the total xdr_buf length, and adjust the length of the current kvec.
-
int
xdr_reserve_space_vec
(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes)¶ Reserves a large amount of buffer space for sending
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
struct kvec *vec
pointer to a kvec array
size_t nbytes
number of bytes to reserve
Description
Reserves enough buffer space to encode ‘nbytes’ of data and stores the
pointers in ‘vec’. The size argument passed to xdr_reserve_space()
is
determined based on the number of bytes remaining in the current page to
avoid invalidating iov_base pointers when xdr_commit_encode()
is called.
-
void
xdr_truncate_encode
(struct xdr_stream *xdr, size_t len)¶ truncate an encode buffer
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
size_t len
new length of buffer
Description
Truncates the xdr stream, so that xdr->buf->len == len, and xdr->p points at offset len from the start of the buffer, and head, tail, and page lengths are adjusted to correspond.
If this means moving xdr->p to a different buffer, we assume that the end pointer should be set to the end of the current page, except in the case of the head buffer when we assume the head buffer’s current length represents the end of the available buffer.
This is not safe to use on a buffer that already has inlined page cache pages (as in a zero-copy server read reply), except for the simple case of truncating from one position in the tail to another.
-
int
xdr_restrict_buflen
(struct xdr_stream *xdr, int newbuflen)¶ decrease available buffer space
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
int newbuflen
new maximum number of bytes available
Description
Adjust our idea of how much space is available in the buffer. If we’ve already used too much space in the buffer, returns -1. If the available space is already smaller than newbuflen, returns 0 and does nothing. Otherwise, adjusts xdr->buf->buflen to newbuflen and ensures xdr->end is set at most offset newbuflen from the start of the buffer.
-
void
xdr_write_pages
(struct xdr_stream *xdr, struct page **pages, unsigned int base, unsigned int len)¶ Insert a list of pages into an XDR buffer for sending
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
struct page **pages
list of pages
unsigned int base
offset of first byte
unsigned int len
length of data in bytes
-
void
xdr_init_decode
(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p, struct rpc_rqst *rqst)¶ Initialize an xdr_stream for decoding data.
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
struct xdr_buf *buf
pointer to XDR buffer from which to decode data
__be32 *p
current pointer inside XDR buffer
struct rpc_rqst *rqst
pointer to controlling rpc_rqst, for debugging
-
void
xdr_init_decode_pages
(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, unsigned int len)¶ Initialize an xdr_stream for decoding into pages
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
struct xdr_buf *buf
pointer to XDR buffer from which to decode data
struct page **pages
list of pages to decode into
unsigned int len
length in bytes of buffer in pages
-
__be32 *
xdr_inline_decode
(struct xdr_stream *xdr, size_t nbytes)¶ Retrieve XDR data to decode
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
size_t nbytes
number of bytes of data to decode
Description
Check if the input buffer is long enough to enable us to decode ‘nbytes’ more bytes of data starting at the current position. If so return the current pointer, then update the current pointer position.
-
unsigned int
xdr_read_pages
(struct xdr_stream *xdr, unsigned int len)¶ align page-based XDR data to current pointer position
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
unsigned int len
number of bytes of page data
Description
Moves data beyond the current pointer position from the XDR head[] buffer into the page list. Any data that lies beyond current position + len bytes is moved into the XDR tail[]. The xdr_stream current position is then advanced past that data to align to the next XDR object in the tail.
Returns the number of XDR encoded bytes now contained in the pages
-
void
xdr_enter_page
(struct xdr_stream *xdr, unsigned int len)¶ decode data from the XDR page
Parameters
struct xdr_stream *xdr
pointer to xdr_stream struct
unsigned int len
number of bytes of page data
Description
Moves data beyond the current pointer position from the XDR head[] buffer into the page list. Any data that lies beyond current position + “len” bytes is moved into the XDR tail[]. The current pointer is then repositioned at the beginning of the first XDR page.
-
int
xdr_buf_subsegment
(const struct xdr_buf *buf, struct xdr_buf *subbuf, unsigned int base, unsigned int len)¶ set subbuf to a portion of buf
Parameters
const struct xdr_buf *buf
an xdr buffer
struct xdr_buf *subbuf
the result buffer
unsigned int base
beginning of range in bytes
unsigned int len
length of range in bytes
Description
sets subbuf to an xdr buffer representing the portion of buf of length len starting at offset base.
buf and subbuf may be pointers to the same struct xdr_buf.
Returns -1 if base of length are out of bounds.
-
bool
xdr_stream_subsegment
(struct xdr_stream *xdr, struct xdr_buf *subbuf, unsigned int nbytes)¶ set subbuf to a portion of xdr
Parameters
struct xdr_stream *xdr
an xdr_stream set up for decoding
struct xdr_buf *subbuf
the result buffer
unsigned int nbytes
length of xdr to extract, in bytes
Description
Sets up subbuf to represent a portion of xdr. The portion starts at the current offset in xdr, and extends for a length of nbytes. If this is successful, xdr is advanced to the next XDR data item following that portion.
- Return values:
true
: subbuf has been initialized, and xdr has been advanced.false
: a bounds error has occurred
-
void
xdr_buf_trim
(struct xdr_buf *buf, unsigned int len)¶ lop at most “len” bytes off the end of “buf”
Parameters
struct xdr_buf *buf
buf to be trimmed
unsigned int len
number of bytes to reduce “buf” by
Description
Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note that it’s possible that we’ll trim less than that amount if the xdr_buf is too small, or if (for instance) it’s all in the head and the parser has already read too far into it.
-
ssize_t
xdr_stream_decode_opaque
(struct xdr_stream *xdr, void *ptr, size_t size)¶ Decode variable length opaque
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
void *ptr
location to store opaque data
size_t size
size of storage buffer ptr
Description
- Return values:
On success, returns size of object stored in *ptr
-EBADMSG
on XDR buffer overflow-EMSGSIZE
on overflow of storage buffer ptr
-
ssize_t
xdr_stream_decode_opaque_dup
(struct xdr_stream *xdr, void **ptr, size_t maxlen, gfp_t gfp_flags)¶ Decode and duplicate variable length opaque
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
void **ptr
location to store pointer to opaque data
size_t maxlen
maximum acceptable object size
gfp_t gfp_flags
GFP mask to use
Description
- Return values:
On success, returns size of object stored in *ptr
-EBADMSG
on XDR buffer overflow-EMSGSIZE
if the size of the object would exceed maxlen-ENOMEM
on memory allocation failure
-
ssize_t
xdr_stream_decode_string
(struct xdr_stream *xdr, char *str, size_t size)¶ Decode variable length string
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
char *str
location to store string
size_t size
size of storage buffer str
Description
- Return values:
On success, returns length of NUL-terminated string stored in *str
-EBADMSG
on XDR buffer overflow-EMSGSIZE
on overflow of storage buffer str
-
ssize_t
xdr_stream_decode_string_dup
(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags)¶ Decode and duplicate variable length string
Parameters
struct xdr_stream *xdr
pointer to xdr_stream
char **str
location to store pointer to string
size_t maxlen
maximum acceptable string length
gfp_t gfp_flags
GFP mask to use
Description
- Return values:
On success, returns length of NUL-terminated string stored in *ptr
-EBADMSG
on XDR buffer overflow-EMSGSIZE
if the size of the string would exceed maxlen-ENOMEM
on memory allocation failure
-
void
svc_xprt_deferred_close
(struct svc_xprt *xprt)¶ Close a transport
Parameters
struct svc_xprt *xprt
transport instance
Description
Used in contexts that need to defer the work of shutting down the transport to an nfsd thread.
-
void
svc_xprt_received
(struct svc_xprt *xprt)¶ start next receiver thread
Parameters
struct svc_xprt *xprt
controlling transport
Description
The caller must hold the XPT_BUSY bit and must not thereafter touch transport data.
Note
XPT_DATA only gets cleared when a read-attempt finds no (or insufficient) data.
-
char *
svc_print_addr
(struct svc_rqst *rqstp, char *buf, size_t len)¶ Format rq_addr field for printing
Parameters
struct svc_rqst *rqstp
svc_rqst struct containing address to print
char *buf
target buffer for formatted address
size_t len
length of target buffer
-
void
svc_reserve
(struct svc_rqst *rqstp, int space)¶ change the space reserved for the reply to a request.
Parameters
struct svc_rqst *rqstp
The request in question
int space
new max space to reserve
Description
Each request reserves some space on the output queue of the transport to make sure the reply fits. This function reduces that reserved space to be the amount of space used already, plus space.
-
struct svc_xprt *
svc_find_xprt
(struct svc_serv *serv, const char *xcl_name, struct net *net, const sa_family_t af, const unsigned short port)¶ find an RPC transport instance
Parameters
struct svc_serv *serv
pointer to svc_serv to search
const char *xcl_name
C string containing transport’s class name
struct net *net
owner net pointer
const sa_family_t af
Address family of transport’s local address
const unsigned short port
transport’s IP port number
Description
Return the transport instance pointer for the endpoint accepting connections/peer traffic from the specified transport class, address family and port.
Specifying 0 for the address family or port is effectively a wild-card, and will result in matching the first transport in the service’s list that has a matching class name.
-
int
svc_xprt_names
(struct svc_serv *serv, char *buf, const int buflen)¶ format a buffer with a list of transport names
Parameters
struct svc_serv *serv
pointer to an RPC service
char *buf
pointer to a buffer to be filled in
const int buflen
length of buffer to be filled in
Description
Fills in buf with a string containing a list of transport names, each name terminated with ‘n’.
Returns positive length of the filled-in string on success; otherwise a negative errno value is returned if an error occurs.
-
int
xprt_register_transport
(struct xprt_class *transport)¶ register a transport implementation
Parameters
struct xprt_class *transport
transport to register
Description
If a transport implementation is loaded as a kernel module, it can call this interface to make itself known to the RPC client.
Return
0: transport successfully registered -EEXIST: transport already registered -EINVAL: transport module being unloaded
-
int
xprt_unregister_transport
(struct xprt_class *transport)¶ unregister a transport implementation
Parameters
struct xprt_class *transport
transport to unregister
Return
0: transport successfully unregistered -ENOENT: transport never registered
-
int
xprt_find_transport_ident
(const char *netid)¶ convert a netid into a transport identifier
Parameters
const char *netid
transport to load
Return
> 0: transport identifier -ENOENT: transport module not available
-
int
xprt_reserve_xprt
(struct rpc_xprt *xprt, struct rpc_task *task)¶ serialize write access to transports
Parameters
struct rpc_xprt *xprt
pointer to the target transport
struct rpc_task *task
task that is requesting access to the transport
Description
This prevents mixing the payload of separate requests, and prevents transport connects from colliding with writes. No congestion control is provided.
-
void
xprt_release_xprt
(struct rpc_xprt *xprt, struct rpc_task *task)¶ allow other requests to use a transport
Parameters
struct rpc_xprt *xprt
transport with other tasks potentially waiting
struct rpc_task *task
task that is releasing access to the transport
Description
Note that “task” can be NULL. No congestion control is provided.
-
void
xprt_release_xprt_cong
(struct rpc_xprt *xprt, struct rpc_task *task)¶ allow other requests to use a transport
Parameters
struct rpc_xprt *xprt
transport with other tasks potentially waiting
struct rpc_task *task
task that is releasing access to the transport
Description
Note that “task” can be NULL. Another task is awoken to use the transport if the transport’s congestion window allows it.
-
bool
xprt_request_get_cong
(struct rpc_xprt *xprt, struct rpc_rqst *req)¶ Request congestion control credits
Parameters
struct rpc_xprt *xprt
pointer to transport
struct rpc_rqst *req
pointer to RPC request
Description
Useful for transports that require congestion control.
-
void
xprt_release_rqst_cong
(struct rpc_task *task)¶ housekeeping when request is complete
Parameters
struct rpc_task *task
RPC request that recently completed
Description
Useful for transports that require congestion control.
-
void
xprt_adjust_cwnd
(struct rpc_xprt *xprt, struct rpc_task *task, int result)¶ adjust transport congestion window
Parameters
struct rpc_xprt *xprt
pointer to xprt
struct rpc_task *task
recently completed RPC request used to adjust window
int result
result code of completed RPC request
Description
The transport code maintains an estimate on the maximum number of out- standing RPC requests, using a smoothed version of the congestion avoidance implemented in 44BSD. This is basically the Van Jacobson congestion algorithm: If a retransmit occurs, the congestion window is halved; otherwise, it is incremented by 1/cwnd when
a reply is received and
a full number of requests are outstanding and
the congestion window hasn’t been updated recently.
-
void
xprt_wake_pending_tasks
(struct rpc_xprt *xprt, int status)¶ wake all tasks on a transport’s pending queue
Parameters
struct rpc_xprt *xprt
transport with waiting tasks
int status
result code to plant in each task before waking it
-
void
xprt_wait_for_buffer_space
(struct rpc_xprt *xprt)¶ wait for transport output buffer to clear
Parameters
struct rpc_xprt *xprt
transport
Description
Note that we only set the timer for the case of RPC_IS_SOFT(), since we don’t in general want to force a socket disconnection due to an incomplete RPC call transmission.
-
bool
xprt_write_space
(struct rpc_xprt *xprt)¶ wake the task waiting for transport output buffer space
Parameters
struct rpc_xprt *xprt
transport with waiting tasks
Description
Can be called in a soft IRQ context, so xprt_write_space never sleeps.
-
void
xprt_disconnect_done
(struct rpc_xprt *xprt)¶ mark a transport as disconnected
Parameters
struct rpc_xprt *xprt
transport to flag for disconnect
-
void
xprt_force_disconnect
(struct rpc_xprt *xprt)¶ force a transport to disconnect
Parameters
struct rpc_xprt *xprt
transport to disconnect
-
unsigned long
xprt_reconnect_delay
(const struct rpc_xprt *xprt)¶ compute the wait before scheduling a connect
Parameters
const struct rpc_xprt *xprt
transport instance
-
void
xprt_reconnect_backoff
(struct rpc_xprt *xprt, unsigned long init_to)¶ compute the new re-establish timeout
Parameters
struct rpc_xprt *xprt
transport instance
unsigned long init_to
initial reestablish timeout
-
struct rpc_rqst *
xprt_lookup_rqst
(struct rpc_xprt *xprt, __be32 xid)¶ find an RPC request corresponding to an XID
Parameters
struct rpc_xprt *xprt
transport on which the original request was transmitted
__be32 xid
RPC XID of incoming reply
Description
Caller holds xprt->queue_lock.
-
void
xprt_pin_rqst
(struct rpc_rqst *req)¶ Pin a request on the transport receive list
Parameters
struct rpc_rqst *req
Request to pin
Description
Caller must ensure this is atomic with the call to xprt_lookup_rqst()
so should be holding xprt->queue_lock.
-
void
xprt_unpin_rqst
(struct rpc_rqst *req)¶ Unpin a request on the transport receive list
Parameters
struct rpc_rqst *req
Request to pin
Description
Caller should be holding xprt->queue_lock.
-
void
xprt_update_rtt
(struct rpc_task *task)¶ Update RPC RTT statistics
Parameters
struct rpc_task *task
RPC request that recently completed
Description
Caller holds xprt->queue_lock.
-
void
xprt_complete_rqst
(struct rpc_task *task, int copied)¶ called when reply processing is complete
Parameters
struct rpc_task *task
RPC request that recently completed
int copied
actual number of bytes received from the transport
Description
Caller holds xprt->queue_lock.
-
void
xprt_wait_for_reply_request_def
(struct rpc_task *task)¶ wait for reply
Parameters
struct rpc_task *task
pointer to rpc_task
Description
Set a request’s retransmit timeout based on the transport’s default timeout parameters. Used by transports that don’t adjust the retransmit timeout based on round-trip time estimation, and put the task to sleep on the pending queue.
-
void
xprt_wait_for_reply_request_rtt
(struct rpc_task *task)¶ wait for reply using RTT estimator
Parameters
struct rpc_task *task
pointer to rpc_task
Description
Set a request’s retransmit timeout using the RTT estimator, and put the task to sleep on the pending queue.
-
struct rpc_xprt *
xprt_get
(struct rpc_xprt *xprt)¶ return a reference to an RPC transport.
Parameters
struct rpc_xprt *xprt
pointer to the transport
-
void
xprt_put
(struct rpc_xprt *xprt)¶ release a reference to an RPC transport.
Parameters
struct rpc_xprt *xprt
pointer to the transport
-
void
rpc_wake_up
(struct rpc_wait_queue *queue)¶ wake up all rpc_tasks
Parameters
struct rpc_wait_queue *queue
rpc_wait_queue on which the tasks are sleeping
Description
Grabs queue->lock
-
void
rpc_wake_up_status
(struct rpc_wait_queue *queue, int status)¶ wake up all rpc_tasks and set their status value.
Parameters
struct rpc_wait_queue *queue
rpc_wait_queue on which the tasks are sleeping
int status
status value to set
Description
Grabs queue->lock
-
int
rpc_malloc
(struct rpc_task *task)¶ allocate RPC buffer resources
Parameters
struct rpc_task *task
RPC task
Description
A single memory region is allocated, which is split between the RPC call and RPC reply that this task is being used for. When this RPC is retired, the memory is released by calling rpc_free.
To prevent rpciod from hanging, this allocator never sleeps, returning -ENOMEM and suppressing warning if the request cannot be serviced immediately. The caller can arrange to sleep in a way that is safe for rpciod.
Most requests are ‘small’ (under 2KiB) and can be serviced from a mempool, ensuring that NFS reads and writes can always proceed, and that there is good locality of reference for these buffers.
-
void
rpc_free
(struct rpc_task *task)¶ free RPC buffer resources allocated via rpc_malloc
Parameters
struct rpc_task *task
RPC task
Parameters
struct xdr_buf *xdr
target XDR buffer
struct sk_buff *skb
source skb
Description
We have set things up such that we perform the checksum of the UDP packet in parallel with the copies into the RPC client iovec. -DaveM
-
struct rpc_iostats *
rpc_alloc_iostats
(struct rpc_clnt *clnt)¶ allocate an rpc_iostats structure
Parameters
struct rpc_clnt *clnt
RPC program, version, and xprt
-
void
rpc_free_iostats
(struct rpc_iostats *stats)¶ release an rpc_iostats structure
Parameters
struct rpc_iostats *stats
doomed rpc_iostats structure
-
void
rpc_count_iostats_metrics
(const struct rpc_task *task, struct rpc_iostats *op_metrics)¶ tally up per-task stats
Parameters
const struct rpc_task *task
completed rpc_task
struct rpc_iostats *op_metrics
stat structure for OP that will accumulate stats from task
-
void
rpc_count_iostats
(const struct rpc_task *task, struct rpc_iostats *stats)¶ tally up per-task stats
Parameters
const struct rpc_task *task
completed rpc_task
struct rpc_iostats *stats
array of stat structures
Description
Uses the statidx from task
-
int
rpc_queue_upcall
(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg)¶ queue an upcall message to userspace
Parameters
struct rpc_pipe *pipe
upcall pipe on which to queue given message
struct rpc_pipe_msg *msg
message to queue
Description
Call with an inode created by rpc_mkpipe() to queue an upcall. A userspace process may then later read the upcall by performing a read on an open file for this inode. It is up to the caller to initialize the fields of msg (other than msg->list) appropriately.
-
struct dentry *
rpc_mkpipe_dentry
(struct dentry *parent, const char *name, void *private, struct rpc_pipe *pipe)¶ make an rpc_pipefs file for kernel<->userspace communication
Parameters
struct dentry *parent
dentry of directory to create new “pipe” in
const char *name
name of pipe
void *private
private data to associate with the pipe, for the caller’s use
struct rpc_pipe *pipe
rpc_pipe
containing input parameters
Description
Data is made available for userspace to read by calls to
rpc_queue_upcall()
. The actual reads will result in calls to
ops->upcall, which will be called with the file pointer,
message, and userspace buffer to copy to.
Writes can come at any time, and do not necessarily have to be responses to upcalls. They will result in calls to msg->downcall.
The private argument passed here will be available to all these methods from the file pointer, via RPC_I(file_inode(file))->private.
-
int
rpc_unlink
(struct dentry *dentry)¶ remove a pipe
Parameters
struct dentry *dentry
dentry for the pipe, as returned from rpc_mkpipe
Description
After this call, lookups will no longer find the pipe, and any attempts to read or write using preexisting opens of the pipe will return -EPIPE.
-
void
rpc_init_pipe_dir_head
(struct rpc_pipe_dir_head *pdh)¶ initialise a struct rpc_pipe_dir_head
Parameters
struct rpc_pipe_dir_head *pdh
pointer to struct rpc_pipe_dir_head
-
void
rpc_init_pipe_dir_object
(struct rpc_pipe_dir_object *pdo, const struct rpc_pipe_dir_object_ops *pdo_ops, void *pdo_data)¶ initialise a struct rpc_pipe_dir_object
Parameters
struct rpc_pipe_dir_object *pdo
pointer to struct rpc_pipe_dir_object
const struct rpc_pipe_dir_object_ops *pdo_ops
pointer to const struct rpc_pipe_dir_object_ops
void *pdo_data
pointer to caller-defined data
-
int
rpc_add_pipe_dir_object
(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo)¶ associate a rpc_pipe_dir_object to a directory
Parameters
struct net *net
pointer to struct net
struct rpc_pipe_dir_head *pdh
pointer to struct rpc_pipe_dir_head
struct rpc_pipe_dir_object *pdo
pointer to struct rpc_pipe_dir_object
-
void
rpc_remove_pipe_dir_object
(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo)¶ remove a rpc_pipe_dir_object from a directory
Parameters
struct net *net
pointer to struct net
struct rpc_pipe_dir_head *pdh
pointer to struct rpc_pipe_dir_head
struct rpc_pipe_dir_object *pdo
pointer to struct rpc_pipe_dir_object
-
struct rpc_pipe_dir_object *
rpc_find_or_alloc_pipe_dir_object
(struct net *net, struct rpc_pipe_dir_head *pdh, int (*match)(struct rpc_pipe_dir_object *, void *), struct rpc_pipe_dir_object *(*alloc)(void *), void *data)¶
Parameters
struct net *net
pointer to struct net
struct rpc_pipe_dir_head *pdh
pointer to struct rpc_pipe_dir_head
int (*match)(struct rpc_pipe_dir_object *, void *)
match struct rpc_pipe_dir_object to data
struct rpc_pipe_dir_object *(*alloc)(void *)
allocate a new struct rpc_pipe_dir_object
void *data
user defined data for match() and alloc()
-
void
rpcb_getport_async
(struct rpc_task *task)¶ obtain the port for a given RPC service on a given host
Parameters
struct rpc_task *task
task that is waiting for portmapper request
Description
This one can be called for an ongoing RPC request, and can be used in an async (rpciod) context.
-
struct rpc_clnt *
rpc_create
(struct rpc_create_args *args)¶ create an RPC client and transport with one call
Parameters
struct rpc_create_args *args
rpc_clnt create argument structure
Description
Creates and initializes an RPC transport and an RPC client.
It can ping the server in order to determine if it is up, and to see if it supports this program and version. RPC_CLNT_CREATE_NOPING disables this behavior so asynchronous tasks can also use rpc_create.
-
struct rpc_clnt *
rpc_clone_client
(struct rpc_clnt *clnt)¶ Clone an RPC client structure
Parameters
struct rpc_clnt *clnt
RPC client whose parameters are copied
Description
Returns a fresh RPC client or an ERR_PTR.
-
struct rpc_clnt *
rpc_clone_client_set_auth
(struct rpc_clnt *clnt, rpc_authflavor_t flavor)¶ Clone an RPC client structure and set its auth
Parameters
struct rpc_clnt *clnt
RPC client whose parameters are copied
rpc_authflavor_t flavor
security flavor for new client
Description
Returns a fresh RPC client or an ERR_PTR.
-
int
rpc_switch_client_transport
(struct rpc_clnt *clnt, struct xprt_create *args, const struct rpc_timeout *timeout)¶ switch the RPC transport on the fly
Parameters
struct rpc_clnt *clnt
pointer to a struct rpc_clnt
struct xprt_create *args
pointer to the new transport arguments
const struct rpc_timeout *timeout
pointer to the new timeout parameters
Description
This function allows the caller to switch the RPC transport for the rpc_clnt structure ‘clnt’ to allow it to connect to a mirrored NFS server, for instance. It assumes that the caller has ensured that there are no active RPC tasks by using some form of locking.
Returns zero if “clnt” is now using the new xprt. Otherwise a negative errno is returned, and “clnt” continues to use the old xprt.
-
int
rpc_clnt_iterate_for_each_xprt
(struct rpc_clnt *clnt, int (*fn)(struct rpc_clnt *, struct rpc_xprt *, void *), void *data)¶ Apply a function to all transports
Parameters
struct rpc_clnt *clnt
pointer to client
int (*fn)(struct rpc_clnt *, struct rpc_xprt *, void *)
function to apply
void *data
void pointer to function data
Description
Iterates through the list of RPC transports currently attached to the client and applies the function fn(clnt, xprt, data).
On error, the iteration stops, and the function returns the error value.
-
struct rpc_clnt *
rpc_bind_new_program
(struct rpc_clnt *old, const struct rpc_program *program, u32 vers)¶ bind a new RPC program to an existing client
Parameters
struct rpc_clnt *old
old rpc_client
const struct rpc_program *program
rpc program to set
u32 vers
rpc program version
Description
Clones the rpc client and sets up a new RPC program. This is mainly of use for enabling different RPC programs to share the same transport. The Sun NFSv2/v3 ACL protocol can do this.
-
struct rpc_task *
rpc_run_task
(const struct rpc_task_setup *task_setup_data)¶ Allocate a new RPC task, then run rpc_execute against it
Parameters
const struct rpc_task_setup *task_setup_data
pointer to task initialisation data
-
int
rpc_call_sync
(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags)¶ Perform a synchronous RPC call
Parameters
struct rpc_clnt *clnt
pointer to RPC client
const struct rpc_message *msg
RPC call parameters
int flags
RPC call flags
-
int
rpc_call_async
(struct rpc_clnt *clnt, const struct rpc_message *msg, int flags, const struct rpc_call_ops *tk_ops, void *data)¶ Perform an asynchronous RPC call
Parameters
struct rpc_clnt *clnt
pointer to RPC client
const struct rpc_message *msg
RPC call parameters
int flags
RPC call flags
const struct rpc_call_ops *tk_ops
RPC call ops
void *data
user call data
-
void
rpc_prepare_reply_pages
(struct rpc_rqst *req, struct page **pages, unsigned int base, unsigned int len, unsigned int hdrsize)¶ Prepare to receive a reply data payload into pages
Parameters
struct rpc_rqst *req
RPC request to prepare
struct page **pages
vector of struct page pointers
unsigned int base
offset in first page where receive should start, in bytes
unsigned int len
expected size of the upper layer data payload, in bytes
unsigned int hdrsize
expected size of upper layer reply header, in XDR words
-
size_t
rpc_peeraddr
(struct rpc_clnt *clnt, struct sockaddr *buf, size_t bufsize)¶ extract remote peer address from clnt’s xprt
Parameters
struct rpc_clnt *clnt
RPC client structure
struct sockaddr *buf
target buffer
size_t bufsize
length of target buffer
Description
Returns the number of bytes that are actually in the stored address.
-
const char *
rpc_peeraddr2str
(struct rpc_clnt *clnt, enum rpc_display_format_t format)¶ return remote peer address in printable format
Parameters
struct rpc_clnt *clnt
RPC client structure
enum rpc_display_format_t format
address format
Description
NB: the lifetime of the memory referenced by the returned pointer is the same as the rpc_xprt itself. As long as the caller uses this pointer, it must hold the RCU read lock.
-
int
rpc_localaddr
(struct rpc_clnt *clnt, struct sockaddr *buf, size_t buflen)¶ discover local endpoint address for an RPC client
Parameters
struct rpc_clnt *clnt
RPC client structure
struct sockaddr *buf
target buffer
size_t buflen
size of target buffer, in bytes
Description
Returns zero and fills in “buf” and “buflen” if successful; otherwise, a negative errno is returned.
This works even if the underlying transport is not currently connected, or if the upper layer never previously provided a source address.
The result of this function call is transient: multiple calls in succession may give different results, depending on how local networking configuration changes over time.
-
struct net *
rpc_net_ns
(struct rpc_clnt *clnt)¶ Get the network namespace for this RPC client
Parameters
struct rpc_clnt *clnt
RPC client to query
-
size_t
rpc_max_payload
(struct rpc_clnt *clnt)¶ Get maximum payload size for a transport, in bytes
Parameters
struct rpc_clnt *clnt
RPC client to query
Description
For stream transports, this is one RPC record fragment (see RFC 1831), as we don’t support multi-record requests yet. For datagram transports, this is the size of an IP packet minus the IP, UDP, and RPC header sizes.
-
size_t
rpc_max_bc_payload
(struct rpc_clnt *clnt)¶ Get maximum backchannel payload size, in bytes
Parameters
struct rpc_clnt *clnt
RPC client to query
-
void
rpc_force_rebind
(struct rpc_clnt *clnt)¶ force transport to check that remote port is unchanged
Parameters
struct rpc_clnt *clnt
client to rebind
-
int
rpc_clnt_test_and_add_xprt
(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, void *dummy)¶ Test and add a new transport to a rpc_clnt
Parameters
struct rpc_clnt *clnt
pointer to struct rpc_clnt
struct rpc_xprt_switch *xps
pointer to struct rpc_xprt_switch,
struct rpc_xprt *xprt
pointer struct rpc_xprt
void *dummy
unused
-
int
rpc_clnt_setup_test_and_add_xprt
(struct rpc_clnt *clnt, struct rpc_xprt_switch *xps, struct rpc_xprt *xprt, void *data)¶
Parameters
struct rpc_clnt *clnt
struct rpc_clnt to get the new transport
struct rpc_xprt_switch *xps
the rpc_xprt_switch to hold the new transport
struct rpc_xprt *xprt
the rpc_xprt to test
void *data
a struct rpc_add_xprt_test pointer that holds the test function and test function call data
Description
- This is an rpc_clnt_add_xprt setup() function which returns 1 so:
1) caller of the test function must dereference the rpc_xprt_switch and the rpc_xprt. 2) test function must call rpc_xprt_switch_add_xprt, usually in the rpc_call_done routine.
Upon success (return of 1), the test function adds the new transport to the rpc_clnt xprt switch
-
int
rpc_clnt_add_xprt
(struct rpc_clnt *clnt, struct xprt_create *xprtargs, int (*setup)(struct rpc_clnt *, struct rpc_xprt_switch *, struct rpc_xprt *, void *), void *data)¶ Add a new transport to a rpc_clnt
Parameters
struct rpc_clnt *clnt
pointer to struct rpc_clnt
struct xprt_create *xprtargs
pointer to struct xprt_create
int (*setup)(struct rpc_clnt *, struct rpc_xprt_switch *, struct rpc_xprt *, void *)
callback to test and/or set up the connection
void *data
pointer to setup function data
Description
Creates a new transport using the parameters set in args and adds it to clnt. If ping is set, then test that connectivity succeeds before adding the new transport.
Network device support¶
Driver Support¶
-
void
dev_add_pack
(struct packet_type *pt)¶ add packet handler
Parameters
struct packet_type *pt
packet type declaration
Add a protocol handler to the networking stack. The passed
packet_type
is linked into kernel lists and may not be freed until it has been removed from the kernel lists.This call does not sleep therefore it can not guarantee all CPU’s that are in middle of receiving packets will see the new packet type (until the next received packet).
-
void
__dev_remove_pack
(struct packet_type *pt)¶ remove packet handler
Parameters
struct packet_type *pt
packet type declaration
Remove a protocol handler that was previously added to the kernel protocol handlers by
dev_add_pack()
. The passedpacket_type
is removed from the kernel lists and can be freed or reused once this function returns.The packet type might still be in use by receivers and must not be freed until after all the CPU’s have gone through a quiescent state.
-
void
dev_remove_pack
(struct packet_type *pt)¶ remove packet handler
Parameters
struct packet_type *pt
packet type declaration
Remove a protocol handler that was previously added to the kernel protocol handlers by
dev_add_pack()
. The passedpacket_type
is removed from the kernel lists and can be freed or reused once this function returns.This call sleeps to guarantee that no CPU is looking at the packet type after return.
-
int
dev_get_iflink
(const struct net_device *dev)¶ get ‘iflink’ value of a interface
Parameters
const struct net_device *dev
targeted interface
Indicates the ifindex the interface is linked to. Physical interfaces have the same ‘ifindex’ and ‘iflink’ values.
-
int
dev_fill_metadata_dst
(struct net_device *dev, struct sk_buff *skb)¶ Retrieve tunnel egress information.
Parameters
struct net_device *dev
targeted interface
struct sk_buff *skb
The packet.
For better visibility of tunnel traffic OVS needs to retrieve egress tunnel information for a packet. Following API allows user to get this info.
-
struct net_device *
__dev_get_by_name
(struct net *net, const char *name)¶ find a device by its name
Parameters
struct net *net
the applicable net namespace
const char *name
name to find
Find an interface by name. Must be called under RTNL semaphore or dev_base_lock. If the name is found a pointer to the device is returned. If the name is not found then
NULL
is returned. The reference counters are not incremented so the caller must be careful with locks.
-
struct net_device *
dev_get_by_name_rcu
(struct net *net, const char *name)¶ find a device by its name
Parameters
struct net *net
the applicable net namespace
const char *name
name to find
Description
Find an interface by name.
If the name is found a pointer to the device is returned.
If the name is not found then NULL
is returned.
The reference counters are not incremented so the caller must be
careful with locks. The caller must hold RCU lock.
-
struct net_device *
dev_get_by_name
(struct net *net, const char *name)¶ find a device by its name
Parameters
struct net *net
the applicable net namespace
const char *name
name to find
Find an interface by name. This can be called from any context and does its own locking. The returned handle has the usage count incremented and the caller must use
dev_put()
to release it when it is no longer needed.NULL
is returned if no matching device is found.
-
struct net_device *
__dev_get_by_index
(struct net *net, int ifindex)¶ find a device by its ifindex
Parameters
struct net *net
the applicable net namespace
int ifindex
index of device
Search for an interface by index. Returns
NULL
if the device is not found or a pointer to the device. The device has not had its reference counter increased so the caller must be careful about locking. The caller must hold either the RTNL semaphore or dev_base_lock.
-
struct net_device *
dev_get_by_index_rcu
(struct net *net, int ifindex)¶ find a device by its ifindex
Parameters
struct net *net
the applicable net namespace
int ifindex
index of device
Search for an interface by index. Returns
NULL
if the device is not found or a pointer to the device. The device has not had its reference counter increased so the caller must be careful about locking. The caller must hold RCU lock.
-
struct net_device *
dev_get_by_index
(struct net *net, int ifindex)¶ find a device by its ifindex
Parameters
struct net *net
the applicable net namespace
int ifindex
index of device
Search for an interface by index. Returns NULL if the device is not found or a pointer to the device. The device returned has had a reference added and the pointer is safe until the user calls dev_put to indicate they have finished with it.
-
struct net_device *
dev_get_by_napi_id
(unsigned int napi_id)¶ find a device by napi_id
Parameters
unsigned int napi_id
ID of the NAPI struct
Search for an interface by NAPI ID. Returns
NULL
if the device is not found or a pointer to the device. The device has not had its reference counter increased so the caller must be careful about locking. The caller must hold RCU lock.
-
struct net_device *
dev_getbyhwaddr_rcu
(struct net *net, unsigned short type, const char *ha)¶ find a device by its hardware address
Parameters
struct net *net
the applicable net namespace
unsigned short type
media type of device
const char *ha
hardware address
Search for an interface by MAC address. Returns NULL if the device is not found or a pointer to the device. The caller must hold RCU or RTNL. The returned device has not had its ref count increased and the caller must therefore be careful about locking
-
struct net_device *
__dev_get_by_flags
(struct net *net, unsigned short if_flags, unsigned short mask)¶ find any device with given flags
Parameters
struct net *net
the applicable net namespace
unsigned short if_flags
IFF_* values
unsigned short mask
bitmask of bits in if_flags to check
Search for any interface with the given flags. Returns NULL if a device is not found or a pointer to the device. Must be called inside rtnl_lock(), and result refcount is unchanged.
-
bool
dev_valid_name
(const char *name)¶ check if name is okay for network device
Parameters
const char *name
name string
Network device names need to be valid file names to allow sysfs to work. We also disallow any kind of whitespace.
-
int
dev_alloc_name
(struct net_device *dev, const char *name)¶ allocate a name for a device
Parameters
struct net_device *dev
device
const char *name
name format string
Passed a format string - eg “lt``d``” it will try and find a suitable id. It scans list of devices to build up a free map, then chooses the first empty slot. The caller must hold the dev_base or rtnl lock while allocating the name and adding the device in order to avoid duplicates. Limited to bits_per_byte * page size devices (ie 32K on most platforms). Returns the number of the unit assigned or a negative errno code.
-
int
dev_set_alias
(struct net_device *dev, const char *alias, size_t len)¶ change ifalias of a device
Parameters
struct net_device *dev
device
const char *alias
name up to IFALIASZ
size_t len
limit of bytes to copy from info
Set ifalias for a device,
-
void
netdev_features_change
(struct net_device *dev)¶ device changes features
Parameters
struct net_device *dev
device to cause notification
Called to indicate a device has changed features.
-
void
netdev_state_change
(struct net_device *dev)¶ device changes state
Parameters
struct net_device *dev
device to cause notification
Called to indicate a device has changed state. This function calls the notifier chains for netdev_chain and sends a NEWLINK message to the routing socket.
-
void
__netdev_notify_peers
(struct net_device *dev)¶ notify network peers about existence of dev, to be called when rtnl lock is already held.
Parameters
struct net_device *dev
network device
Description
Generate traffic such that interested network peers are aware of dev, such as by generating a gratuitous ARP. This may be used when a device wants to inform the rest of the network about some sort of reconfiguration such as a failover event or virtual machine migration.
-
void
netdev_notify_peers
(struct net_device *dev)¶ notify network peers about existence of dev
Parameters
struct net_device *dev
network device
Description
Generate traffic such that interested network peers are aware of dev, such as by generating a gratuitous ARP. This may be used when a device wants to inform the rest of the network about some sort of reconfiguration such as a failover event or virtual machine migration.
-
int
dev_open
(struct net_device *dev, struct netlink_ext_ack *extack)¶ prepare an interface for use.
Parameters
struct net_device *dev
device to open
struct netlink_ext_ack *extack
netlink extended ack
Takes a device from down to up state. The device’s private open function is invoked and then the multicast lists are loaded. Finally the device is moved into the up state and a
NETDEV_UP
message is sent to the netdev notifier chain.Calling this function on an active interface is a nop. On a failure a negative errno code is returned.
-
void
dev_close
(struct net_device *dev)¶ shutdown an interface.
Parameters
struct net_device *dev
device to shutdown
This function moves an active device into down state. A
NETDEV_GOING_DOWN
is sent to the netdev notifier chain. The device is then deactivated and finally aNETDEV_DOWN
is sent to the notifier chain.
-
void
dev_disable_lro
(struct net_device *dev)¶ disable Large Receive Offload on a device
Parameters
struct net_device *dev
device
Disable Large Receive Offload (LRO) on a net device. Must be called under RTNL. This is needed if received packets may be forwarded to another interface.
-
int
register_netdevice_notifier
(struct notifier_block *nb)¶ register a network notifier block
Parameters
struct notifier_block *nb
notifier
Description
Register a notifier to be called when network device events occur. The notifier passed is linked into the kernel structures and must not be reused until it has been unregistered. A negative errno code is returned on a failure.
When registered all registration and up events are replayed to the new notifier to allow device to have a race free view of the network device list.
-
int
unregister_netdevice_notifier
(struct notifier_block *nb)¶ unregister a network notifier block
Parameters
struct notifier_block *nb
notifier
Description
Unregister a notifier previously registered by
register_netdevice_notifier()
. The notifier is unlinked into the
kernel structures and may then be reused. A negative errno code
is returned on a failure.
After unregistering unregister and down device events are synthesized for all devices on the device list to the removed notifier to remove the need for special case cleanup code.
-
int
register_netdevice_notifier_net
(struct net *net, struct notifier_block *nb)¶ register a per-netns network notifier block
Parameters
struct net *net
network namespace
struct notifier_block *nb
notifier
Description
Register a notifier to be called when network device events occur. The notifier passed is linked into the kernel structures and must not be reused until it has been unregistered. A negative errno code is returned on a failure.
When registered all registration and up events are replayed to the new notifier to allow device to have a race free view of the network device list.
-
int
unregister_netdevice_notifier_net
(struct net *net, struct notifier_block *nb)¶ unregister a per-netns network notifier block
Parameters
struct net *net
network namespace
struct notifier_block *nb
notifier
Description
Unregister a notifier previously registered by
register_netdevice_notifier()
. The notifier is unlinked into the
kernel structures and may then be reused. A negative errno code
is returned on a failure.
After unregistering unregister and down device events are synthesized for all devices on the device list to the removed notifier to remove the need for special case cleanup code.
-
int
call_netdevice_notifiers
(unsigned long val, struct net_device *dev)¶ call all network notifier blocks
Parameters
unsigned long val
value passed unmodified to notifier function
struct net_device *dev
net_device pointer passed unmodified to notifier function
Call all network notifier blocks. Parameters and return value are as for raw_notifier_call_chain().
-
int
dev_forward_skb
(struct net_device *dev, struct sk_buff *skb)¶ loopback an skb to another netif
Parameters
struct net_device *dev
destination network device
struct sk_buff *skb
buffer to forward
Description
- return values:
NET_RX_SUCCESS (no congestion) NET_RX_DROP (packet was dropped, but freed)
dev_forward_skb can be used for injecting an skb from the start_xmit function of one device into the receive queue of another device.
The receiving device may be in another namespace, so we have to clear all information in the skb that could impact namespace isolation.
-
bool
dev_nit_active
(struct net_device *dev)¶ return true if any network interface taps are in use
Parameters
struct net_device *dev
network device to check for the presence of taps
-
int
netif_set_real_num_rx_queues
(struct net_device *dev, unsigned int rxq)¶ set actual number of RX queues used
Parameters
struct net_device *dev
Network device
unsigned int rxq
Actual number of RX queues
This must be called either with the rtnl_lock held or before registration of the net device. Returns 0 on success, or a negative error code. If called before registration, it always succeeds.
-
int
netif_set_real_num_queues
(struct net_device *dev, unsigned int txq, unsigned int rxq)¶ set actual number of RX and TX queues used
Parameters
struct net_device *dev
Network device
unsigned int txq
Actual number of TX queues
unsigned int rxq
Actual number of RX queues
Set the real number of both TX and RX queues. Does nothing if the number of queues is already correct.
-
int
netif_get_num_default_rss_queues
(void)¶ default number of RSS queues
Parameters
void
no arguments
Description
This routine should set an upper limit on the number of RSS queues used by default by multiqueue devices.
-
void
netif_device_detach
(struct net_device *dev)¶ mark device as removed
Parameters
struct net_device *dev
network device
Description
Mark device as removed from system and therefore no longer available.
-
void
netif_device_attach
(struct net_device *dev)¶ mark device as attached
Parameters
struct net_device *dev
network device
Description
Mark device as attached from system and restart if needed.
-
struct sk_buff *
__skb_gso_segment
(struct sk_buff *skb, netdev_features_t features, bool tx_path)¶ Perform segmentation on skb.
Parameters
struct sk_buff *skb
buffer to segment
netdev_features_t features
features for the output path (see dev->features)
bool tx_path
whether it is called in TX path
This function segments the given skb and returns a list of segments.
It may return NULL if the skb requires no segmentation. This is only possible when GSO is used for verifying header integrity.
Segmentation preserves SKB_GSO_CB_OFFSET bytes of previous skb cb.
Parameters
struct net *net
network namespace this loopback is happening in
struct sock *sk
sk needed to be a netfilter okfn
struct sk_buff *skb
buffer to transmit
-
bool
rps_may_expire_flow
(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id)¶ check whether an RFS hardware filter may be removed
Parameters
struct net_device *dev
Device on which the filter was set
u16 rxq_index
RX queue index
u32 flow_id
Flow ID passed to ndo_rx_flow_steer()
u16 filter_id
Filter ID returned by ndo_rx_flow_steer()
Description
Drivers that implement ndo_rx_flow_steer() should periodically call
this function for each installed filter and remove the filters for
which it returns true
.
Parameters
struct sk_buff *skb
buffer to post
This function receives a packet from a device driver and queues it for the upper (protocol) levels to process. It always succeeds. The buffer may be dropped during processing for congestion control or by the protocol layers.
return values: NET_RX_SUCCESS (no congestion) NET_RX_DROP (packet was dropped)
-
bool
netdev_is_rx_handler_busy
(struct net_device *dev)¶ check if receive handler is registered
Parameters
struct net_device *dev
device to check
Check if a receive handler is already registered for a given device. Return true if there one.
The caller must hold the rtnl_mutex.
-
int
netdev_rx_handler_register
(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data)¶ register receive handler
Parameters
struct net_device *dev
device to register a handler for
rx_handler_func_t *rx_handler
receive handler to register
void *rx_handler_data
data pointer that is used by rx handler
Register a receive handler for a device. This handler will then be called from __netif_receive_skb. A negative errno code is returned on a failure.
The caller must hold the rtnl_mutex.
For a general description of rx_handler, see enum rx_handler_result.
-
void
netdev_rx_handler_unregister
(struct net_device *dev)¶ unregister receive handler
Parameters
struct net_device *dev
device to unregister a handler from
Unregister a receive handler from a device.
The caller must hold the rtnl_mutex.
Parameters
struct sk_buff *skb
buffer to process
More direct receive version of
netif_receive_skb()
. It should only be used by callers that have a need to skip RPS and Generic XDP. Caller must also take care of handling if(page_is_)pfmemalloc
.This function may only be called from softirq context and interrupts should be enabled.
Return values (usually ignored): NET_RX_SUCCESS: no congestion NET_RX_DROP: packet was dropped
Parameters
struct sk_buff *skb
buffer to process
netif_receive_skb()
is the main receive data processing function. It always succeeds. The buffer may be dropped during processing for congestion control or by the protocol layers.This function may only be called from softirq context and interrupts should be enabled.
Return values (usually ignored): NET_RX_SUCCESS: no congestion NET_RX_DROP: packet was dropped
-
void
netif_receive_skb_list
(struct list_head *head)¶ process many receive buffers from network
Parameters
struct list_head *head
list of skbs to process.
Since return value of
netif_receive_skb()
is normally ignored, and wouldn’t be meaningful for a list, this function returns void.This function may only be called from softirq context and interrupts should be enabled.
-
void
__napi_schedule
(struct napi_struct *n)¶ schedule for receive
Parameters
struct napi_struct *n
entry to schedule
Description
The entry’s receive function will be scheduled to run.
Consider using __napi_schedule_irqoff()
if hard irqs are masked.
-
bool
napi_schedule_prep
(struct napi_struct *n)¶ check if napi can be scheduled
Parameters
struct napi_struct *n
napi context
Description
Test if NAPI routine is already running, and if not mark it as running. This is used as a condition variable to insure only one NAPI poll instance runs. We also make sure there is no pending NAPI disable.
-
void
__napi_schedule_irqoff
(struct napi_struct *n)¶ schedule for receive
Parameters
struct napi_struct *n
entry to schedule
Description
Variant of __napi_schedule()
assuming hard irqs are masked.
On PREEMPT_RT enabled kernels this maps to __napi_schedule()
because the interrupt disabled assumption might not be true
due to force-threaded interrupts and spinlock substitution.
-
void
napi_enable
(struct napi_struct *n)¶ enable NAPI scheduling
Parameters
struct napi_struct *n
NAPI context
Description
Resume NAPI from being scheduled on this context. Must be paired with napi_disable.
-
bool
netdev_has_upper_dev
(struct net_device *dev, struct net_device *upper_dev)¶ Check if device is linked to an upper device
Parameters
struct net_device *dev
device
struct net_device *upper_dev
upper device to check
Description
Find out if a device is linked to specified upper device and return true in case it is. Note that this checks only immediate upper device, not through a complete stack of devices. The caller must hold the RTNL lock.
-
bool
netdev_has_upper_dev_all_rcu
(struct net_device *dev, struct net_device *upper_dev)¶ Check if device is linked to an upper device
Parameters
struct net_device *dev
device
struct net_device *upper_dev
upper device to check
Description
Find out if a device is linked to specified upper device and return true in case it is. Note that this checks the entire upper device chain. The caller must hold rcu lock.
-
bool
netdev_has_any_upper_dev
(struct net_device *dev)¶ Check if device is linked to some device
Parameters
struct net_device *dev
device
Description
Find out if a device is linked to an upper device and return true in case it is. The caller must hold the RTNL lock.
-
struct net_device *
netdev_master_upper_dev_get
(struct net_device *dev)¶ Get master upper device
Parameters
struct net_device *dev
device
Description
Find a master upper device and return pointer to it or NULL in case it’s not there. The caller must hold the RTNL lock.
-
struct net_device *
netdev_upper_get_next_dev_rcu
(struct net_device *dev, struct list_head **iter)¶ Get the next dev from upper list
Parameters
struct net_device *dev
device
struct list_head **iter
list_head ** of the current position
Description
Gets the next device from the dev’s upper list, starting from iter position. The caller must hold RCU read lock.
-
void *
netdev_lower_get_next_private
(struct net_device *dev, struct list_head **iter)¶ Get the next ->private from the lower neighbour list
Parameters
struct net_device *dev
device
struct list_head **iter
list_head ** of the current position
Description
Gets the next netdev_adjacent->private from the dev’s lower neighbour list, starting from iter position. The caller must hold either hold the RTNL lock or its own locking that guarantees that the neighbour lower list will remain unchanged.
-
void *
netdev_lower_get_next_private_rcu
(struct net_device *dev, struct list_head **iter)¶ Get the next ->private from the lower neighbour list, RCU variant
Parameters
struct net_device *dev
device
struct list_head **iter
list_head ** of the current position
Description
Gets the next netdev_adjacent->private from the dev’s lower neighbour list, starting from iter position. The caller must hold RCU read lock.
-
void *
netdev_lower_get_next
(struct net_device *dev, struct list_head **iter)¶ Get the next device from the lower neighbour list
Parameters
struct net_device *dev
device
struct list_head **iter
list_head ** of the current position
Description
Gets the next netdev_adjacent from the dev’s lower neighbour list, starting from iter position. The caller must hold RTNL lock or its own locking that guarantees that the neighbour lower list will remain unchanged.
-
void *
netdev_lower_get_first_private_rcu
(struct net_device *dev)¶ Get the first ->private from the lower neighbour list, RCU variant
Parameters
struct net_device *dev
device
Description
Gets the first netdev_adjacent->private from the dev’s lower neighbour list. The caller must hold RCU read lock.
-
struct net_device *
netdev_master_upper_dev_get_rcu
(struct net_device *dev)¶ Get master upper device
Parameters
struct net_device *dev
device
Description
Find a master upper device and return pointer to it or NULL in case it’s not there. The caller must hold the RCU read lock.
-
int
netdev_upper_dev_link
(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack)¶ Add a link to the upper device
Parameters
struct net_device *dev
device
struct net_device *upper_dev
new upper device
struct netlink_ext_ack *extack
netlink extended ack
Description
Adds a link to device which is upper to this one. The caller must hold the RTNL lock. On a failure a negative errno code is returned. On success the reference counts are adjusted and the function returns zero.
-
int
netdev_master_upper_dev_link
(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack)¶ Add a master link to the upper device
Parameters
struct net_device *dev
device
struct net_device *upper_dev
new upper device
void *upper_priv
upper device private
void *upper_info
upper info to be passed down via notifier
struct netlink_ext_ack *extack
netlink extended ack
Description
Adds a link to device which is upper to this one. In this case, only one master upper device can be linked, although other non-master devices might be linked as well. The caller must hold the RTNL lock. On a failure a negative errno code is returned. On success the reference counts are adjusted and the function returns zero.
-
void
netdev_upper_dev_unlink
(struct net_device *dev, struct net_device *upper_dev)¶ Removes a link to upper device
Parameters
struct net_device *dev
device
struct net_device *upper_dev
new upper device
Description
Removes a link to device which is upper to this one. The caller must hold the RTNL lock.
-
void
netdev_bonding_info_change
(struct net_device *dev, struct netdev_bonding_info *bonding_info)¶ Dispatch event about slave change
Parameters
struct net_device *dev
device
struct netdev_bonding_info *bonding_info
info to dispatch
Description
Send NETDEV_BONDING_INFO to netdev notifiers with info. The caller must hold the RTNL lock.
-
struct net_device *
netdev_get_xmit_slave
(struct net_device *dev, struct sk_buff *skb, bool all_slaves)¶ Get the xmit slave of master device
Parameters
struct net_device *dev
device
struct sk_buff *skb
The packet
bool all_slaves
assume all the slaves are active
Description
The reference counters are not incremented so the caller must be
careful with locks. The caller must hold RCU lock.
NULL
is returned if no slave is found.
-
struct net_device *
netdev_sk_get_lowest_dev
(struct net_device *dev, struct sock *sk)¶ Get the lowest device in chain given device and socket
Parameters
struct net_device *dev
device
struct sock *sk
the socket
Description
NULL
is returned if no lower device is found.
-
void
netdev_lower_state_changed
(struct net_device *lower_dev, void *lower_state_info)¶ Dispatch event about lower device state change
Parameters
struct net_device *lower_dev
device
void *lower_state_info
state to dispatch
Description
Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. The caller must hold the RTNL lock.
-
int
dev_set_promiscuity
(struct net_device *dev, int inc)¶ update promiscuity count on a device
Parameters
struct net_device *dev
device
int inc
modifier
Add or remove promiscuity from a device. While the count in the device remains above zero the interface remains promiscuous. Once it hits zero the device reverts back to normal filtering operation. A negative inc value is used to drop promiscuity on the device. Return 0 if successful or a negative errno code on error.
-
int
dev_set_allmulti
(struct net_device *dev, int inc)¶ update allmulti count on a device
Parameters
struct net_device *dev
device
int inc
modifier
Add or remove reception of all multicast frames to a device. While the count in the device remains above zero the interface remains listening to all interfaces. Once it hits zero the device reverts back to normal filtering operation. A negative inc value is used to drop the counter when releasing a resource needing all multicasts. Return 0 if successful or a negative errno code on error.
-
unsigned int
dev_get_flags
(const struct net_device *dev)¶ get flags reported to userspace
Parameters
const struct net_device *dev
device
Get the combination of flag bits exported through APIs to userspace.
-
int
dev_change_flags
(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack)¶ change device settings
Parameters
struct net_device *dev
device
unsigned int flags
device state flags
struct netlink_ext_ack *extack
netlink extended ack
Change settings on device based state flags. The flags are in the userspace exported format.
-
void
dev_set_group
(struct net_device *dev, int new_group)¶ Change group this device belongs to
Parameters
struct net_device *dev
device
int new_group
group this device should belong to
-
int
dev_pre_changeaddr_notify
(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack)¶ Call NETDEV_PRE_CHANGEADDR.
Parameters
struct net_device *dev
device
const char *addr
new address
struct netlink_ext_ack *extack
netlink extended ack
-
int
dev_set_mac_address
(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack)¶ Change Media Access Control Address
Parameters
struct net_device *dev
device
struct sockaddr *sa
new address
struct netlink_ext_ack *extack
netlink extended ack
Change the hardware (MAC) address of the device
-
int
dev_change_carrier
(struct net_device *dev, bool new_carrier)¶ Change device carrier
Parameters
struct net_device *dev
device
bool new_carrier
new value
Change device carrier
-
int
dev_get_phys_port_id
(struct net_device *dev, struct netdev_phys_item_id *ppid)¶ Get device physical port ID
Parameters
struct net_device *dev
device
struct netdev_phys_item_id *ppid
port ID
Get device physical port ID
-
int
dev_get_phys_port_name
(struct net_device *dev, char *name, size_t len)¶ Get device physical port name
Parameters
struct net_device *dev
device
char *name
port name
size_t len
limit of bytes to copy to name
Get device physical port name
-
int
dev_get_port_parent_id
(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse)¶ Get the device’s port parent identifier
Parameters
struct net_device *dev
network device
struct netdev_phys_item_id *ppid
pointer to a storage for the port’s parent identifier
bool recurse
allow/disallow recursion to lower devices
Get the devices’s port parent identifier
-
bool
netdev_port_same_parent_id
(struct net_device *a, struct net_device *b)¶ Indicate if two network devices have the same port parent identifier
Parameters
struct net_device *a
first network device
struct net_device *b
second network device
-
int
dev_change_proto_down
(struct net_device *dev, bool proto_down)¶ set carrier according to proto_down.
Parameters
struct net_device *dev
device
bool proto_down
new value
-
void
dev_change_proto_down_reason
(struct net_device *dev, unsigned long mask, u32 value)¶ proto down reason
Parameters
struct net_device *dev
device
unsigned long mask
proto down mask
u32 value
proto down value
-
void
netdev_update_features
(struct net_device *dev)¶ recalculate device features
Parameters
struct net_device *dev
the device to check
Recalculate dev->features set and send notifications if it has changed. Should be called after driver or hardware dependent conditions might have changed that influence the features.
-
void
netdev_change_features
(struct net_device *dev)¶ recalculate device features
Parameters
struct net_device *dev
the device to check
Recalculate dev->features set and send notifications even if they have not changed. Should be called instead of
netdev_update_features()
if also dev->vlan_features might have changed to allow the changes to be propagated to stacked VLAN devices.
-
void
netif_stacked_transfer_operstate
(const struct net_device *rootdev, struct net_device *dev)¶ transfer operstate
Parameters
const struct net_device *rootdev
the root or lower level device to transfer state from
struct net_device *dev
the device to transfer operstate to
Transfer operational state from root to device. This is normally called when a stacking relationship exists between the root device and the device(a leaf device).
-
int
register_netdevice
(struct net_device *dev)¶ register a network device
Parameters
struct net_device *dev
device to register
Take a completed network device structure and add it to the kernel interfaces. A
NETDEV_REGISTER
message is sent to the netdev notifier chain. 0 is returned on success. A negative errno code is returned on a failure to set up the device, or if the name is a duplicate.Callers must hold the rtnl semaphore. You may want
register_netdev()
instead of this.BUGS: The locking appears insufficient to guarantee two parallel registers will not get the same name.
-
int
init_dummy_netdev
(struct net_device *dev)¶ init a dummy network device for NAPI
Parameters
struct net_device *dev
device to init
This takes a network device structure and initialize the minimum amount of fields so it can be used to schedule NAPI polls without registering a full blown interface. This is to be used by drivers that need to tie several hardware interfaces to a single NAPI poll scheduler due to HW limitations.
-
int
register_netdev
(struct net_device *dev)¶ register a network device
Parameters
struct net_device *dev
device to register
Take a completed network device structure and add it to the kernel interfaces. A
NETDEV_REGISTER
message is sent to the netdev notifier chain. 0 is returned on success. A negative errno code is returned on a failure to set up the device, or if the name is a duplicate.This is a wrapper around register_netdevice that takes the rtnl semaphore and expands the device name if you passed a format string to alloc_netdev.
-
struct rtnl_link_stats64 *
dev_get_stats
(struct net_device *dev, struct rtnl_link_stats64 *storage)¶ get network device statistics
Parameters
struct net_device *dev
device to get statistics from
struct rtnl_link_stats64 *storage
place to store stats
Get network statistics from device. Return storage. The device driver may provide its own method by setting dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; otherwise the internal statistics structure is used.
-
void
dev_fetch_sw_netstats
(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats)¶ get per-cpu network device statistics
Parameters
struct rtnl_link_stats64 *s
place to store stats
const struct pcpu_sw_netstats __percpu *netstats
per-cpu network stats to read from
Read per-cpu network statistics and populate the related fields in s.
-
void
dev_get_tstats64
(struct net_device *dev, struct rtnl_link_stats64 *s)¶ ndo_get_stats64 implementation
Parameters
struct net_device *dev
device to get statistics from
struct rtnl_link_stats64 *s
place to store stats
Populate s from dev->stats and dev->tstats. Can be used as ndo_get_stats64() callback.
-
struct net_device *
alloc_netdev_mqs
(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs)¶ allocate network device
Parameters
int sizeof_priv
size of private data to allocate space for
const char *name
device name format string
unsigned char name_assign_type
origin of device name
void (*setup)(struct net_device *)
callback to initialize device
unsigned int txqs
the number of TX subqueues to allocate
unsigned int rxqs
the number of RX subqueues to allocate
Description
Allocates a struct net_device
with private data area for driver use
and performs basic initialization. Also allocates subqueue structs
for each queue on the device.
-
void
free_netdev
(struct net_device *dev)¶ free network device
Parameters
struct net_device *dev
device
Description
This function does the last stage of destroying an allocated device interface. The reference to the device object is released. If this is the last reference then it will be freed.Must be called in process context.
-
void
synchronize_net
(void)¶ Synchronize with packet receive processing
Parameters
void
no arguments
Description
Wait for packets currently being received to be done. Does not block later packets from starting.
-
void
unregister_netdevice_queue
(struct net_device *dev, struct list_head *head)¶ remove device from the kernel
Parameters
struct net_device *dev
device
struct list_head *head
list
This function shuts down a device interface and removes it from the kernel tables. If head not NULL, device is queued to be unregistered later.
Callers must hold the rtnl semaphore. You may want
unregister_netdev()
instead of this.
-
void
unregister_netdevice_many
(struct list_head *head)¶ unregister many devices
Parameters
struct list_head *head
list of devices
Note
- As most callers use a stack allocated list_head,
we force a
list_del()
to make sure stack wont be corrupted later.
-
void
unregister_netdev
(struct net_device *dev)¶ remove device from the kernel
Parameters
struct net_device *dev
device
This function shuts down a device interface and removes it from the kernel tables.
This is just a wrapper for unregister_netdevice that takes the rtnl semaphore. In general you want to use this and not unregister_netdevice.
-
int
__dev_change_net_namespace
(struct net_device *dev, struct net *net, const char *pat, int new_ifindex)¶ move device to different nethost namespace
Parameters
struct net_device *dev
device
struct net *net
network namespace
const char *pat
If not NULL name pattern to try if the current device name is already taken in the destination network namespace.
int new_ifindex
If not zero, specifies device index in the target namespace.
This function shuts down a device interface and moves it to a new network namespace. On success 0 is returned, on a failure a netagive errno code is returned.
Callers must hold the rtnl semaphore.
-
netdev_features_t
netdev_increment_features
(netdev_features_t all, netdev_features_t one, netdev_features_t mask)¶ increment feature set by one
Parameters
netdev_features_t all
current feature set
netdev_features_t one
new feature set
netdev_features_t mask
mask feature set
Computes a new feature set after adding a device with feature set one to the master device with current feature set all. Will not enable anything that is off in mask. Returns the new feature set.
-
int
eth_header
(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len)¶ create the Ethernet header
Parameters
struct sk_buff *skb
buffer to alter
struct net_device *dev
source device
unsigned short type
Ethernet type field
const void *daddr
destination address (NULL leave destination address)
const void *saddr
source address (NULL use device source address)
unsigned int len
packet length (<= skb->len)
Description
Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length in here instead.
-
u32
eth_get_headlen
(const struct net_device *dev, const void *data, u32 len)¶ determine the length of header for an ethernet frame
Parameters
const struct net_device *dev
pointer to network device
const void *data
pointer to start of frame
u32 len
total length of frame
Description
Make a best effort attempt to pull the length for all of the headers for a given frame in a linear buffer.
-
__be16
eth_type_trans
(struct sk_buff *skb, struct net_device *dev)¶ determine the packet’s protocol ID.
Parameters
struct sk_buff *skb
received socket data
struct net_device *dev
receiving network device
Description
The rule here is that we assume 802.3 if the type field is short enough to be a length. This is normal practice and works for any ‘now in use’ protocol.
-
int
eth_header_parse
(const struct sk_buff *skb, unsigned char *haddr)¶ extract hardware address from packet
Parameters
const struct sk_buff *skb
packet to extract header from
unsigned char *haddr
destination buffer
-
int
eth_header_cache
(const struct neighbour *neigh, struct hh_cache *hh, __be16 type)¶ fill cache entry from neighbour
Parameters
const struct neighbour *neigh
source neighbour
struct hh_cache *hh
destination cache entry
__be16 type
Ethernet type field
Description
Create an Ethernet header template from the neighbour.
-
void
eth_header_cache_update
(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr)¶ update cache entry
Parameters
struct hh_cache *hh
destination cache entry
const struct net_device *dev
network device
const unsigned char *haddr
new hardware address
Description
Called by Address Resolution module to notify changes in address.
Parameters
const struct sk_buff *skb
packet to extract protocol from
-
int
eth_prepare_mac_addr_change
(struct net_device *dev, void *p)¶ prepare for mac change
Parameters
struct net_device *dev
network device
void *p
socket address
-
void
eth_commit_mac_addr_change
(struct net_device *dev, void *p)¶ commit mac change
Parameters
struct net_device *dev
network device
void *p
socket address
-
int
eth_mac_addr
(struct net_device *dev, void *p)¶ set new Ethernet hardware address
Parameters
struct net_device *dev
network device
void *p
socket address
Description
Change hardware address of device.
This doesn’t change hardware matching, so needs to be overridden for most real devices.
-
void
ether_setup
(struct net_device *dev)¶ setup Ethernet network device
Parameters
struct net_device *dev
network device
Description
Fill in the fields of the device structure with Ethernet-generic values.
-
struct net_device *
alloc_etherdev_mqs
(int sizeof_priv, unsigned int txqs, unsigned int rxqs)¶ Allocates and sets up an Ethernet device
Parameters
int sizeof_priv
Size of additional driver-private structure to be allocated for this Ethernet device
unsigned int txqs
The number of TX queues this device has.
unsigned int rxqs
The number of RX queues this device has.
Description
Fill in the fields of the device structure with Ethernet-generic values. Basically does everything except registering the device.
Constructs a new net device, complete with a private data area of size (sizeof_priv). A 32-byte (not bit) alignment is enforced for this private data area.
-
int
platform_get_ethdev_address
(struct device *dev, struct net_device *netdev)¶ Set netdev’s MAC address from a given device
Parameters
struct device *dev
Pointer to the device
struct net_device *netdev
Pointer to netdev to write the address to
Description
Wrapper around eth_platform_get_mac_address() which writes the address directly to netdev->dev_addr.
-
int
fwnode_get_mac_address
(struct fwnode_handle *fwnode, char *addr)¶ Get the MAC from the firmware node
Parameters
struct fwnode_handle *fwnode
Pointer to the firmware node
char *addr
Address of buffer to store the MAC in
Description
Search the firmware node for the best MAC address to use. ‘mac-address’ is checked first, because that is supposed to contain to “most recent” MAC address. If that isn’t set, then ‘local-mac-address’ is checked next, because that is the default address. If that isn’t set, then the obsolete ‘address’ is checked, just in case we’re using an old device tree.
Note that the ‘address’ property is supposed to contain a virtual address of the register set, but some DTS files have redefined that property to be the MAC address.
All-zero MAC addresses are rejected, because those could be properties that exist in the firmware tables, but were not updated by the firmware. For example, the DTS could define ‘mac-address’ and ‘local-mac-address’, with zero MAC addresses. Some older U-Boots only initialized ‘local-mac-address’. In this case, the real MAC is in ‘local-mac-address’, and ‘mac-address’ exists but is all zeros.
Parameters
struct device *dev
Pointer to the device
char *addr
Address of buffer to store the MAC in
-
int
device_get_ethdev_address
(struct device *dev, struct net_device *netdev)¶ Set netdev’s MAC address from a given device
Parameters
struct device *dev
Pointer to the device
struct net_device *netdev
Pointer to netdev to write the address to
Description
Wrapper around device_get_mac_address()
which writes the address
directly to netdev->dev_addr.
-
void
netif_carrier_on
(struct net_device *dev)¶ set carrier
Parameters
struct net_device *dev
network device
Description
Device has detected acquisition of carrier.
-
void
netif_carrier_off
(struct net_device *dev)¶ clear carrier
Parameters
struct net_device *dev
network device
Description
Device has detected loss of carrier.
-
void
netif_carrier_event
(struct net_device *dev)¶ report carrier state event
Parameters
struct net_device *dev
network device
Description
Device has detected a carrier event but the carrier state wasn’t changed. Use in drivers when querying carrier state asynchronously, to avoid missing events (link flaps) if link recovers before it’s queried.
-
bool
is_link_local_ether_addr
(const u8 *addr)¶ Determine if given Ethernet address is link-local
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if address is link local reserved addr (01:80:c2:00:00:0X) per IEEE 802.1Q 8.6.3 Frame filtering.
Please note: addr must be aligned to u16.
-
bool
is_zero_ether_addr
(const u8 *addr)¶ Determine if give Ethernet address is all zeros.
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if the address is all zeroes.
Please note: addr must be aligned to u16.
-
bool
is_multicast_ether_addr
(const u8 *addr)¶ Determine if the Ethernet address is a multicast.
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if the address is a multicast address. By definition the broadcast address is also a multicast address.
-
bool
is_local_ether_addr
(const u8 *addr)¶ Determine if the Ethernet address is locally-assigned one (IEEE 802).
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if the address is a local address.
-
bool
is_broadcast_ether_addr
(const u8 *addr)¶ Determine if the Ethernet address is broadcast
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if the address is the broadcast address.
Please note: addr must be aligned to u16.
-
bool
is_unicast_ether_addr
(const u8 *addr)¶ Determine if the Ethernet address is unicast
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return true if the address is a unicast address.
-
bool
is_valid_ether_addr
(const u8 *addr)¶ Determine if the given Ethernet address is valid
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not a multicast address, and is not FF:FF:FF:FF:FF:FF.
Return true if the address is valid.
Please note: addr must be aligned to u16.
-
bool
eth_proto_is_802_3
(__be16 proto)¶ Determine if a given Ethertype/length is a protocol
Parameters
__be16 proto
Ethertype/length value to be tested
Description
Check that the value from the Ethertype/length field is a valid Ethertype.
Return true if the valid is an 802.3 supported Ethertype.
-
void
eth_random_addr
(u8 *addr)¶ Generate software assigned random Ethernet address
Parameters
u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Generate a random Ethernet address (MAC) that is not multicast and has the local assigned bit set.
-
void
eth_broadcast_addr
(u8 *addr)¶ Assign broadcast address
Parameters
u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Assign the broadcast address to the given address array.
-
void
eth_zero_addr
(u8 *addr)¶ Assign zero address
Parameters
u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Assign the zero address to the given address array.
-
void
eth_hw_addr_random
(struct net_device *dev)¶ Generate software assigned random Ethernet and set device flag
Parameters
struct net_device *dev
pointer to net_device structure
Description
Generate a random Ethernet address (MAC) to be used by a net device and set addr_assign_type so the state can be read by sysfs and be used by userspace.
-
u32
eth_hw_addr_crc
(struct netdev_hw_addr *ha)¶ Calculate CRC from netdev_hw_addr
Parameters
struct netdev_hw_addr *ha
pointer to hardware address
Description
Calculate CRC from a hardware address as basis for filter hashes.
-
void
ether_addr_copy
(u8 *dst, const u8 *src)¶ Copy an Ethernet address
Parameters
u8 *dst
Pointer to a six-byte array Ethernet address destination
const u8 *src
Pointer to a six-byte array Ethernet address source
Description
Please note: dst & src must both be aligned to u16.
-
void
eth_hw_addr_set
(struct net_device *dev, const u8 *addr)¶ Assign Ethernet address to a net_device
Parameters
struct net_device *dev
pointer to net_device structure
const u8 *addr
address to assign
Description
Assign given address to the net_device, addr_assign_type is not changed.
-
void
eth_hw_addr_inherit
(struct net_device *dst, struct net_device *src)¶ Copy dev_addr from another net_device
Parameters
struct net_device *dst
pointer to net_device to copy dev_addr to
struct net_device *src
pointer to net_device to copy dev_addr from
Description
Copy the Ethernet address from one net_device to another along with the address attributes (addr_assign_type).
-
bool
ether_addr_equal
(const u8 *addr1, const u8 *addr2)¶ Compare two Ethernet addresses
Parameters
const u8 *addr1
Pointer to a six-byte array containing the Ethernet address
const u8 *addr2
Pointer other six-byte array containing the Ethernet address
Description
Compare two Ethernet addresses, returns true if equal
Please note: addr1 & addr2 must both be aligned to u16.
-
bool
ether_addr_equal_64bits
(const u8 addr1[6+2], const u8 addr2[6+2])¶ Compare two Ethernet addresses
Parameters
const u8 addr1[6+2]
Pointer to an array of 8 bytes
const u8 addr2[6+2]
Pointer to an other array of 8 bytes
Description
Compare two Ethernet addresses, returns true if equal, false otherwise.
The function doesn’t need any conditional branches and possibly uses word memory accesses on CPU allowing cheap unaligned memory reads. arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 }
Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits.
-
bool
ether_addr_equal_unaligned
(const u8 *addr1, const u8 *addr2)¶ Compare two not u16 aligned Ethernet addresses
Parameters
const u8 *addr1
Pointer to a six-byte array containing the Ethernet address
const u8 *addr2
Pointer other six-byte array containing the Ethernet address
Description
Compare two Ethernet addresses, returns true if equal
Please note: Use only when any Ethernet address may not be u16 aligned.
-
bool
ether_addr_equal_masked
(const u8 *addr1, const u8 *addr2, const u8 *mask)¶ Compare two Ethernet addresses with a mask
Parameters
const u8 *addr1
Pointer to a six-byte array containing the 1st Ethernet address
const u8 *addr2
Pointer to a six-byte array containing the 2nd Ethernet address
const u8 *mask
Pointer to a six-byte array containing the Ethernet address bitmask
Description
Compare two Ethernet addresses with a mask, returns true if for every bit set in the bitmask the equivalent bits in the ethernet addresses are equal. Using a mask with all bits set is a slower ether_addr_equal.
-
u64
ether_addr_to_u64
(const u8 *addr)¶ Convert an Ethernet address into a u64 value.
Parameters
const u8 *addr
Pointer to a six-byte array containing the Ethernet address
Description
Return a u64 value of the address
-
void
u64_to_ether_addr
(u64 u, u8 *addr)¶ Convert a u64 to an Ethernet address.
Parameters
u64 u
u64 to convert to an Ethernet MAC address
u8 *addr
Pointer to a six-byte array to contain the Ethernet address
-
void
eth_addr_dec
(u8 *addr)¶ Decrement the given MAC address
Parameters
u8 *addr
Pointer to a six-byte array containing Ethernet address to decrement
-
void
eth_addr_inc
(u8 *addr)¶ Increment the given MAC address.
Parameters
u8 *addr
Pointer to a six-byte array containing Ethernet address to increment.
-
bool
is_etherdev_addr
(const struct net_device *dev, const u8 addr[6 + 2])¶ Tell if given Ethernet address belongs to the device.
Parameters
const struct net_device *dev
Pointer to a device structure
const u8 addr[6 + 2]
Pointer to a six-byte array containing the Ethernet address
Description
Compare passed address with all addresses of the device. Return true if the address if one of the device addresses.
Note that this function calls ether_addr_equal_64bits()
so take care of
the right padding.
-
unsigned long
compare_ether_header
(const void *a, const void *b)¶ Compare two Ethernet headers
Parameters
const void *a
Pointer to Ethernet header
const void *b
Pointer to Ethernet header
Description
Compare two Ethernet headers, returns 0 if equal. This assumes that the network header (i.e., IP header) is 4-byte aligned OR the platform can handle unaligned access. This is the case for all packets coming into netif_receive_skb or similar entry points.
-
void
eth_hw_addr_gen
(struct net_device *dev, const u8 *base_addr, unsigned int id)¶ Generate and assign Ethernet address to a port
Parameters
struct net_device *dev
pointer to port’s net_device structure
const u8 *base_addr
base Ethernet address
unsigned int id
offset to add to the base address
Description
Generate a MAC address using a base address and an offset and assign it to a net_device. Commonly used by switch drivers which need to compute addresses for all their ports. addr_assign_type is not changed.
Parameters
struct sk_buff *skb
Buffer to pad
Description
An Ethernet frame should have a minimum size of 60 bytes. This function takes short frames and pads them with zeros up to the 60 byte limit.
-
void
napi_schedule
(struct napi_struct *n)¶ schedule NAPI poll
Parameters
struct napi_struct *n
NAPI context
Description
Schedule NAPI poll routine to be called if it is not already running.
-
void
napi_schedule_irqoff
(struct napi_struct *n)¶ schedule NAPI poll
Parameters
struct napi_struct *n
NAPI context
Description
Variant of napi_schedule()
, assuming hard irqs are masked.
-
bool
napi_complete
(struct napi_struct *n)¶ NAPI processing complete
Parameters
struct napi_struct *n
NAPI context
Description
Mark NAPI processing as complete. Consider using napi_complete_done() instead. Return false if device should avoid rearming interrupts.
-
void
napi_disable
(struct napi_struct *n)¶ prevent NAPI from scheduling
Parameters
struct napi_struct *n
NAPI context
Description
Stop NAPI from being scheduled on this context. Waits till any outstanding processing completes.
-
void
napi_synchronize
(const struct napi_struct *n)¶ wait until NAPI is not running
Parameters
const struct napi_struct *n
NAPI context
Description
Wait until NAPI is done being scheduled on this context. Waits till any outstanding processing completes but does not disable future activations.
-
bool
napi_if_scheduled_mark_missed
(struct napi_struct *n)¶ if napi is running, set the NAPIF_STATE_MISSED
Parameters
struct napi_struct *n
NAPI context
Description
If napi is running, set the NAPIF_STATE_MISSED, and return true if NAPI is scheduled.
-
enum
netdev_priv_flags
¶ struct net_device
priv_flags
Constants
IFF_802_1Q_VLAN
802.1Q VLAN device
IFF_EBRIDGE
Ethernet bridging device
IFF_BONDING
bonding master or slave
IFF_ISATAP
ISATAP interface (RFC4214)
IFF_WAN_HDLC
WAN HDLC device
IFF_XMIT_DST_RELEASE
dev_hard_start_xmit() is allowed to release skb->dst
IFF_DONT_BRIDGE
disallow bridging this ether dev
IFF_DISABLE_NETPOLL
disable netpoll at run-time
IFF_MACVLAN_PORT
device used as macvlan port
IFF_BRIDGE_PORT
device used as bridge port
IFF_OVS_DATAPATH
device used as Open vSwitch datapath port
IFF_TX_SKB_SHARING
The interface supports sharing skbs on transmit
IFF_UNICAST_FLT
Supports unicast filtering
IFF_TEAM_PORT
device used as team port
IFF_SUPP_NOFCS
device supports sending custom FCS
IFF_LIVE_ADDR_CHANGE
device supports hardware address change when it’s running
IFF_MACVLAN
Macvlan device
IFF_XMIT_DST_RELEASE_PERM
IFF_XMIT_DST_RELEASE not taking into account underlying stacked devices
IFF_L3MDEV_MASTER
device is an L3 master device
IFF_NO_QUEUE
device can run without qdisc attached
IFF_OPENVSWITCH
device is a Open vSwitch master
IFF_L3MDEV_SLAVE
device is enslaved to an L3 master device
IFF_TEAM
device is a team device
IFF_RXFH_CONFIGURED
device has had Rx Flow indirection table configured
IFF_PHONY_HEADROOM
the headroom value is controlled by an external entity (i.e. the master device for bridged veth)
IFF_MACSEC
device is a MACsec device
IFF_NO_RX_HANDLER
device doesn’t support the rx_handler hook
IFF_FAILOVER
device is a failover master device
IFF_FAILOVER_SLAVE
device is lower dev of a failover master device
IFF_L3MDEV_RX_HANDLER
only invoke the rx handler of L3 master device
IFF_LIVE_RENAME_OK
rename is allowed while device is up and running
IFF_TX_SKB_NO_LINEAR
device/driver is capable of xmitting frames with skb_headlen(skb) == 0 (data starts from frag0)
IFF_CHANGE_PROTO_DOWN
device supports setting carrier via IFLA_PROTO_DOWN
Description
These are the struct net_device
, they are only set internally
by drivers and used in the kernel. These flags are invisible to
userspace; this means that the order of these flags can change
during any kernel release.
You should have a pretty good reason to be extending these flags.
-
struct
net_device
¶ The DEVICE structure.
Definition
struct net_device {
char name[IFNAMSIZ];
struct netdev_name_node *name_node;
struct dev_ifalias __rcu *ifalias;
unsigned long mem_end;
unsigned long mem_start;
unsigned long base_addr;
unsigned long state;
struct list_head dev_list;
struct list_head napi_list;
struct list_head unreg_list;
struct list_head close_list;
struct list_head ptype_all;
struct list_head ptype_specific;
struct {
struct list_head upper;
struct list_head lower;
} adj_list;
unsigned int flags;
unsigned long long priv_flags;
const struct net_device_ops *netdev_ops;
int ifindex;
unsigned short gflags;
unsigned short hard_header_len;
unsigned int mtu;
unsigned short needed_headroom;
unsigned short needed_tailroom;
netdev_features_t features;
netdev_features_t hw_features;
netdev_features_t wanted_features;
netdev_features_t vlan_features;
netdev_features_t hw_enc_features;
netdev_features_t mpls_features;
netdev_features_t gso_partial_features;
unsigned int min_mtu;
unsigned int max_mtu;
unsigned short type;
unsigned char min_header_len;
unsigned char name_assign_type;
int group;
struct net_device_stats stats;
atomic_long_t rx_dropped;
atomic_long_t tx_dropped;
atomic_long_t rx_nohandler;
atomic_t carrier_up_count;
atomic_t carrier_down_count;
#ifdef CONFIG_WIRELESS_EXT;
const struct iw_handler_def *wireless_handlers;
struct iw_public_data *wireless_data;
#endif;
const struct ethtool_ops *ethtool_ops;
#ifdef CONFIG_NET_L3_MASTER_DEV;
const struct l3mdev_ops *l3mdev_ops;
#endif;
#if IS_ENABLED(CONFIG_IPV6);
const struct ndisc_ops *ndisc_ops;
#endif;
#ifdef CONFIG_XFRM_OFFLOAD;
const struct xfrmdev_ops *xfrmdev_ops;
#endif;
#if IS_ENABLED(CONFIG_TLS_DEVICE);
const struct tlsdev_ops *tlsdev_ops;
#endif;
const struct header_ops *header_ops;
unsigned char operstate;
unsigned char link_mode;
unsigned char if_port;
unsigned char dma;
unsigned char perm_addr[MAX_ADDR_LEN];
unsigned char addr_assign_type;
unsigned char addr_len;
unsigned char upper_level;
unsigned char lower_level;
unsigned short neigh_priv_len;
unsigned short dev_id;
unsigned short dev_port;
unsigned short padded;
spinlock_t addr_list_lock;
int irq;
struct netdev_hw_addr_list uc;
struct netdev_hw_addr_list mc;
struct netdev_hw_addr_list dev_addrs;
#ifdef CONFIG_SYSFS;
struct kset *queues_kset;
#endif;
#ifdef CONFIG_LOCKDEP;
struct list_head unlink_list;
#endif;
unsigned int promiscuity;
unsigned int allmulti;
bool uc_promisc;
#ifdef CONFIG_LOCKDEP;
unsigned char nested_level;
#endif;
#if IS_ENABLED(CONFIG_VLAN_8021Q);
struct vlan_info __rcu *vlan_info;
#endif;
#if IS_ENABLED(CONFIG_NET_DSA);
struct dsa_port *dsa_ptr;
#endif;
#if IS_ENABLED(CONFIG_TIPC);
struct tipc_bearer __rcu *tipc_ptr;
#endif;
#if IS_ENABLED(CONFIG_ATALK);
void *atalk_ptr;
#endif;
struct in_device __rcu *ip_ptr;
#if IS_ENABLED(CONFIG_DECNET);
struct dn_dev __rcu *dn_ptr;
#endif;
struct inet6_dev __rcu *ip6_ptr;
#if IS_ENABLED(CONFIG_AX25);
void *ax25_ptr;
#endif;
struct wireless_dev *ieee80211_ptr;
struct wpan_dev *ieee802154_ptr;
#if IS_ENABLED(CONFIG_MPLS_ROUTING);
struct mpls_dev __rcu *mpls_ptr;
#endif;
#if IS_ENABLED(CONFIG_MCTP);
struct mctp_dev __rcu *mctp_ptr;
#endif;
const unsigned char *dev_addr;
struct netdev_rx_queue *_rx;
unsigned int num_rx_queues;
unsigned int real_num_rx_queues;
struct bpf_prog __rcu *xdp_prog;
unsigned long gro_flush_timeout;
int napi_defer_hard_irqs;
#define GRO_MAX_SIZE 65536;
unsigned int gro_max_size;
rx_handler_func_t __rcu *rx_handler;
void __rcu *rx_handler_data;
#ifdef CONFIG_NET_CLS_ACT;
struct mini_Qdisc __rcu *miniq_ingress;
#endif;
struct netdev_queue __rcu *ingress_queue;
#ifdef CONFIG_NETFILTER_INGRESS;
struct nf_hook_entries __rcu *nf_hooks_ingress;
#endif;
unsigned char broadcast[MAX_ADDR_LEN];
#ifdef CONFIG_RFS_ACCEL;
struct cpu_rmap *rx_cpu_rmap;
#endif;
struct hlist_node index_hlist;
struct netdev_queue *_tx ;
unsigned int num_tx_queues;
unsigned int real_num_tx_queues;
struct Qdisc __rcu *qdisc;
unsigned int tx_queue_len;
spinlock_t tx_global_lock;
struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
#ifdef CONFIG_XPS;
struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
#endif;
#ifdef CONFIG_NET_CLS_ACT;
struct mini_Qdisc __rcu *miniq_egress;
#endif;
#ifdef CONFIG_NETFILTER_EGRESS;
struct nf_hook_entries __rcu *nf_hooks_egress;
#endif;
#ifdef CONFIG_NET_SCHED;
unsigned long qdisc_hash[1 << ((4) - 1)];
#endif;
struct timer_list watchdog_timer;
int watchdog_timeo;
u32 proto_down_reason;
struct list_head todo_list;
#ifdef CONFIG_PCPU_DEV_REFCNT;
int __percpu *pcpu_refcnt;
#else;
refcount_t dev_refcnt;
#endif;
struct ref_tracker_dir refcnt_tracker;
struct list_head link_watch_list;
enum {
NETREG_UNINITIALIZED=0,
NETREG_REGISTERED,
NETREG_UNREGISTERING,
NETREG_UNREGISTERED,
NETREG_RELEASED,
NETREG_DUMMY,
} reg_state:8;
bool dismantle;
enum {
RTNL_LINK_INITIALIZED,
RTNL_LINK_INITIALIZING,
} rtnl_link_state:16;
bool needs_free_netdev;
void (*priv_destructor)(struct net_device *dev);
#ifdef CONFIG_NETPOLL;
struct netpoll_info __rcu *npinfo;
#endif;
possible_net_t nd_net;
void *ml_priv;
enum netdev_ml_priv_type ml_priv_type;
union {
struct pcpu_lstats __percpu *lstats;
struct pcpu_sw_netstats __percpu *tstats;
struct pcpu_dstats __percpu *dstats;
};
#if IS_ENABLED(CONFIG_GARP);
struct garp_port __rcu *garp_port;
#endif;
#if IS_ENABLED(CONFIG_MRP);
struct mrp_port __rcu *mrp_port;
#endif;
struct device dev;
const struct attribute_group *sysfs_groups[4];
const struct attribute_group *sysfs_rx_queue_group;
const struct rtnl_link_ops *rtnl_link_ops;
#define GSO_MAX_SIZE 65536;
unsigned int gso_max_size;
#define GSO_MAX_SEGS 65535;
u16 gso_max_segs;
#ifdef CONFIG_DCB;
const struct dcbnl_rtnl_ops *dcbnl_ops;
#endif;
s16 num_tc;
struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
u8 prio_tc_map[TC_BITMASK + 1];
#if IS_ENABLED(CONFIG_FCOE);
unsigned int fcoe_ddp_xid;
#endif;
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO);
struct netprio_map __rcu *priomap;
#endif;
struct phy_device *phydev;
struct sfp_bus *sfp_bus;
struct lock_class_key *qdisc_tx_busylock;
bool proto_down;
unsigned wol_enabled:1;
unsigned threaded:1;
struct list_head net_notifier_list;
#if IS_ENABLED(CONFIG_MACSEC);
const struct macsec_ops *macsec_ops;
#endif;
const struct udp_tunnel_nic_info *udp_tunnel_nic_info;
struct udp_tunnel_nic *udp_tunnel_nic;
struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE];
u8 dev_addr_shadow[MAX_ADDR_LEN];
netdevice_tracker linkwatch_dev_tracker;
netdevice_tracker watchdog_dev_tracker;
};
Members
name
This is the first field of the “visible” part of this structure (i.e. as seen by users in the “Space.c” file). It is the name of the interface.
name_node
Name hashlist node
ifalias
SNMP alias
mem_end
Shared memory end
mem_start
Shared memory start
base_addr
Device I/O address
state
Generic network queuing layer state, see netdev_state_t
dev_list
The global list of network devices
napi_list
List entry used for polling NAPI devices
unreg_list
List entry when we are unregistering the device; see the function unregister_netdev
close_list
List entry used when we are closing the device
ptype_all
Device-specific packet handlers for all protocols
ptype_specific
Device-specific, protocol-specific packet handlers
adj_list
Directly linked devices, like slaves for bonding
flags
Interface flags (a la BSD)
priv_flags
Like ‘flags’ but invisible to userspace, see if.h for the definitions
netdev_ops
Includes several pointers to callbacks, if one wants to override the ndo_*() functions
ifindex
interface index
gflags
Global flags ( kept as legacy )
hard_header_len
Maximum hardware header length.
mtu
Interface MTU value
needed_headroom
Extra headroom the hardware may need, but not in all cases can this be guaranteed
needed_tailroom
Extra tailroom the hardware may need, but not in all cases can this be guaranteed. Some cases also use LL_MAX_HEADER instead to allocate the skb
interface address info:
features
Currently active device features
hw_features
User-changeable features
wanted_features
User-requested features
vlan_features
Mask of features inheritable by VLAN devices
hw_enc_features
Mask of features inherited by encapsulating devices This field indicates what encapsulation offloads the hardware is capable of doing, and drivers will need to set them appropriately.
mpls_features
Mask of features inheritable by MPLS
gso_partial_features
value(s) from NETIF_F_GSO*
min_mtu
Interface Minimum MTU value
max_mtu
Interface Maximum MTU value
type
Interface hardware type
min_header_len
Minimum hardware header length
name_assign_type
network interface name assignment type
group
The group the device belongs to
stats
Statistics struct, which was left as a legacy, use rtnl_link_stats64 instead
rx_dropped
Dropped packets by core network, do not use this in drivers
tx_dropped
Dropped packets by core network, do not use this in drivers
rx_nohandler
nohandler dropped packets by core network on inactive devices, do not use this in drivers
carrier_up_count
Number of times the carrier has been up
carrier_down_count
Number of times the carrier has been down
wireless_handlers
List of functions to handle Wireless Extensions, instead of ioctl, see <net/iw_handler.h> for details.
wireless_data
Instance data managed by the core of wireless extensions
ethtool_ops
Management operations
l3mdev_ops
Layer 3 master device operations
ndisc_ops
Includes callbacks for different IPv6 neighbour discovery handling. Necessary for e.g. 6LoWPAN.
xfrmdev_ops
Transformation offload operations
tlsdev_ops
Transport Layer Security offload operations
header_ops
Includes callbacks for creating,parsing,caching,etc of Layer 2 headers.
operstate
RFC2863 operstate
link_mode
Mapping policy to operstate
if_port
Selectable AUI, TP, …
dma
DMA channel
perm_addr
Permanent hw address
addr_assign_type
Hw address assignment type
addr_len
Hardware address length
upper_level
Maximum depth level of upper devices.
lower_level
Maximum depth level of lower devices.
neigh_priv_len
Used in neigh_alloc()
dev_id
Used to differentiate devices that share the same link layer address
dev_port
Used to differentiate devices that share the same function
padded
How much padding added by alloc_netdev()
addr_list_lock
XXX: need comments on this one
irq
Device IRQ number
uc
unicast mac addresses
mc
multicast mac addresses
dev_addrs
list of device hw addresses
queues_kset
Group of all Kobjects in the Tx and RX queues
unlink_list
As netif_addr_lock() can be called recursively, keep a list of interfaces to be deleted.
promiscuity
Number of times the NIC is told to work in promiscuous mode; if it becomes 0 the NIC will exit promiscuous mode
allmulti
Counter, enables or disables allmulticast mode
uc_promisc
Counter that indicates promiscuous mode has been enabled due to the need to listen to additional unicast addresses in a device that does not implement ndo_set_rx_mode()
nested_level
Used as a parameter of spin_lock_nested() of dev->addr_list_lock.
vlan_info
VLAN info
dsa_ptr
dsa specific data
tipc_ptr
TIPC specific data
atalk_ptr
AppleTalk link
ip_ptr
IPv4 specific data
dn_ptr
DECnet specific data
ip6_ptr
IPv6 specific data
ax25_ptr
AX.25 specific data
ieee80211_ptr
IEEE 802.11 specific data, assign before registering
ieee802154_ptr
IEEE 802.15.4 low-rate Wireless Personal Area Network device struct
mpls_ptr
mpls_dev struct pointer
mctp_ptr
MCTP specific data
dev_addr
Hw address (before bcast, because most packets are unicast)
_rx
Array of RX queues
num_rx_queues
Number of RX queues allocated at
register_netdev()
timereal_num_rx_queues
Number of RX queues currently active in device
xdp_prog
XDP sockets filter program pointer
gro_flush_timeout
timeout for GRO layer in NAPI
napi_defer_hard_irqs
If not zero, provides a counter that would allow to avoid NIC hard IRQ, on busy queues.
gro_max_size
Maximum size of aggregated packet in generic receive offload (GRO)
rx_handler
handler for received packets
rx_handler_data
XXX: need comments on this one
miniq_ingress
ingress/clsact qdisc specific data for ingress processing
ingress_queue
XXX: need comments on this one
nf_hooks_ingress
netfilter hooks executed for ingress packets
broadcast
hw bcast address
rx_cpu_rmap
CPU reverse-mapping for RX completion interrupts, indexed by RX queue number. Assigned by driver. This must only be set if the ndo_rx_flow_steer operation is defined
index_hlist
Device index hash chain
_tx
Array of TX queues
num_tx_queues
Number of TX queues allocated at alloc_netdev_mq() time
real_num_tx_queues
Number of TX queues currently active in device
qdisc
Root qdisc from userspace point of view
tx_queue_len
Max frames per queue allowed
tx_global_lock
XXX: need comments on this one
xdp_bulkq
XDP device bulk queue
xps_maps
XXX: need comments on this one
miniq_egress
clsact qdisc specific data for egress processing
nf_hooks_egress
netfilter hooks executed for egress packets
qdisc_hash
qdisc hash table
watchdog_timer
List of timers
watchdog_timeo
Represents the timeout that is used by the watchdog (see dev_watchdog())
proto_down_reason
reason a netdev interface is held down
todo_list
Delayed register/unregister
pcpu_refcnt
Number of references to this device
dev_refcnt
Number of references to this device
refcnt_tracker
Tracker directory for tracked references to this device
link_watch_list
XXX: need comments on this one
reg_state
Register/unregister state machine
dismantle
Device is going to be freed
rtnl_link_state
This enum represents the phases of creating a new link
needs_free_netdev
Should unregister perform free_netdev?
priv_destructor
Called from unregister
npinfo
XXX: need comments on this one
nd_net
Network namespace this network device is inside
ml_priv
Mid-layer private
ml_priv_type
Mid-layer private type
{unnamed_union}
anonymous
lstats
Loopback statistics
tstats
Tunnel statistics
dstats
Dummy statistics
garp_port
GARP
mrp_port
MRP
dev
Class/net/name entry
sysfs_groups
Space for optional device, statistics and wireless sysfs groups
sysfs_rx_queue_group
Space for optional per-rx queue attributes
rtnl_link_ops
Rtnl_link_ops
gso_max_size
Maximum size of generic segmentation offload
gso_max_segs
Maximum number of segments that can be passed to the NIC for GSO
dcbnl_ops
Data Center Bridging netlink ops
num_tc
Number of traffic classes in the net device
tc_to_txq
XXX: need comments on this one
prio_tc_map
XXX: need comments on this one
fcoe_ddp_xid
Max exchange id for FCoE LRO by ddp
priomap
XXX: need comments on this one
phydev
Physical device may attach itself for hardware timestamping
sfp_bus
attached
struct sfp_bus
structure.qdisc_tx_busylock
lockdep class annotating Qdisc->busylock spinlock
proto_down
protocol port state information can be sent to the switch driver and used to set the phys state of the switch port.
wol_enabled
Wake-on-LAN is enabled
threaded
napi threaded mode is enabled
net_notifier_list
List of per-net netdev notifier block that follow this device when it is moved to another network namespace.
macsec_ops
MACsec offloading ops
udp_tunnel_nic_info
static structure describing the UDP tunnel offload capabilities of the device
udp_tunnel_nic
UDP tunnel offload state
xdp_state
stores info on attached XDP BPF programs
dev_addr_shadow
Copy of dev_addr to catch direct writes.
linkwatch_dev_tracker
refcount tracker used by linkwatch.
watchdog_dev_tracker
refcount tracker used by watchdog.
FIXME: cleanup
struct net_device
such that network protocol info moves out.
Description
Actually, this whole structure is a big mistake. It mixes I/O data with strictly “high-level” data, and it has to know about almost every data structure used in the INET module.
-
void *
netdev_priv
(const struct net_device *dev)¶ access network device private data
Parameters
const struct net_device *dev
network device
Description
Get network device private data
-
void
netif_napi_add
(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight)¶ initialize a NAPI context
Parameters
struct net_device *dev
network device
struct napi_struct *napi
NAPI context
int (*poll)(struct napi_struct *, int)
polling function
int weight
default weight
Description
netif_napi_add()
must be used to initialize a NAPI context prior to calling
any of the other NAPI-related functions.
-
void
netif_tx_napi_add
(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight)¶ initialize a NAPI context
Parameters
struct net_device *dev
network device
struct napi_struct *napi
NAPI context
int (*poll)(struct napi_struct *, int)
polling function
int weight
default weight
Description
This variant of netif_napi_add()
should be used from drivers using NAPI
to exclusively poll a TX queue.
This will avoid we add it into napi_hash[], thus polluting this hash table.
-
void
__netif_napi_del
(struct napi_struct *napi)¶ remove a NAPI context
Parameters
struct napi_struct *napi
NAPI context
Description
Warning: caller must observe RCU grace period before freeing memory containing napi. Drivers might want to call this helper to combine all the needed RCU grace periods into a single one.
-
void
netif_napi_del
(struct napi_struct *napi)¶ remove a NAPI context
Parameters
struct napi_struct *napi
NAPI context
netif_napi_del()
removes a NAPI context from the network device NAPI list
-
void
netif_start_queue
(struct net_device *dev)¶ allow transmit
Parameters
struct net_device *dev
network device
Allow upper layers to call the device hard_start_xmit routine.
-
void
netif_wake_queue
(struct net_device *dev)¶ restart transmit
Parameters
struct net_device *dev
network device
Allow upper layers to call the device hard_start_xmit routine. Used for flow control when transmit resources are available.
-
void
netif_stop_queue
(struct net_device *dev)¶ stop transmitted packets
Parameters
struct net_device *dev
network device
Stop upper layers calling the device hard_start_xmit routine. Used for flow control when transmit resources are unavailable.
-
bool
netif_queue_stopped
(const struct net_device *dev)¶ test if transmit queue is flowblocked
Parameters
const struct net_device *dev
network device
Test if transmit queue on device is currently unable to send.
-
void
netdev_queue_set_dql_min_limit
(struct netdev_queue *dev_queue, unsigned int min_limit)¶ set dql minimum limit
Parameters
struct netdev_queue *dev_queue
pointer to transmit queue
unsigned int min_limit
dql minimum limit
Description
Forces xmit_more() to return true until the minimum threshold defined by min_limit is reached (or until the tx queue is empty). Warning: to be use with care, misuse will impact the latency.
-
void
netdev_txq_bql_enqueue_prefetchw
(struct netdev_queue *dev_queue)¶ prefetch bql data for write
Parameters
struct netdev_queue *dev_queue
pointer to transmit queue
Description
BQL enabled drivers might use this helper in their ndo_start_xmit(), to give appropriate hint to the CPU.
-
void
netdev_txq_bql_complete_prefetchw
(struct netdev_queue *dev_queue)¶ prefetch bql data for write
Parameters
struct netdev_queue *dev_queue
pointer to transmit queue
Description
BQL enabled drivers might use this helper in their TX completion path, to give appropriate hint to the CPU.
-
void
netdev_sent_queue
(struct net_device *dev, unsigned int bytes)¶ report the number of bytes queued to hardware
Parameters
struct net_device *dev
network device
unsigned int bytes
number of bytes queued to the hardware device queue
Report the number of bytes queued for sending/completion to the network device hardware queue. bytes should be a good approximation and should exactly match
netdev_completed_queue()
bytes
-
void
netdev_completed_queue
(struct net_device *dev, unsigned int pkts, unsigned int bytes)¶ report bytes and packets completed by device
Parameters
struct net_device *dev
network device
unsigned int pkts
actual number of packets sent over the medium
unsigned int bytes
actual number of bytes sent over the medium
Report the number of bytes and packets transmitted by the network device hardware queue over the physical medium, bytes must exactly match the bytes amount passed to
netdev_sent_queue()
-
void
netdev_reset_queue
(struct net_device *dev_queue)¶ reset the packets and bytes count of a network device
Parameters
struct net_device *dev_queue
network device
Reset the bytes and packet count of a network device and clear the software flow control OFF bit for this network device
-
u16
netdev_cap_txqueue
(struct net_device *dev, u16 queue_index)¶ check if selected tx queue exceeds device queues
Parameters
struct net_device *dev
network device
u16 queue_index
given tx queue index
Returns 0 if given tx queue index >= number of device tx queues, otherwise returns the originally passed tx queue index.
-
bool
netif_running
(const struct net_device *dev)¶ test if up
Parameters
const struct net_device *dev
network device
Test if the device has been brought up.
-
void
netif_start_subqueue
(struct net_device *dev, u16 queue_index)¶ allow sending packets on subqueue
Parameters
struct net_device *dev
network device
u16 queue_index
sub queue index
Description
Start individual transmit queue of a device with multiple transmit queues.
-
void
netif_stop_subqueue
(struct net_device *dev, u16 queue_index)¶ stop sending packets on subqueue
Parameters
struct net_device *dev
network device
u16 queue_index
sub queue index
Description
Stop individual transmit queue of a device with multiple transmit queues.
-
bool
__netif_subqueue_stopped
(const struct net_device *dev, u16 queue_index)¶ test status of subqueue
Parameters
const struct net_device *dev
network device
u16 queue_index
sub queue index
Description
Check individual transmit queue of a device with multiple transmit queues.
-
bool
netif_subqueue_stopped
(const struct net_device *dev, struct sk_buff *skb)¶ test status of subqueue
Parameters
const struct net_device *dev
network device
struct sk_buff *skb
sub queue buffer pointer
Description
Check individual transmit queue of a device with multiple transmit queues.
-
void
netif_wake_subqueue
(struct net_device *dev, u16 queue_index)¶ allow sending packets on subqueue
Parameters
struct net_device *dev
network device
u16 queue_index
sub queue index
Description
Resume individual transmit queue of a device with multiple transmit queues.
-
bool
netif_attr_test_mask
(unsigned long j, const unsigned long *mask, unsigned int nr_bits)¶ Test a CPU or Rx queue set in a mask
Parameters
unsigned long j
CPU/Rx queue index
const unsigned long *mask
bitmask of all cpus/rx queues
unsigned int nr_bits
number of bits in the bitmask
Description
Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues.
-
bool
netif_attr_test_online
(unsigned long j, const unsigned long *online_mask, unsigned int nr_bits)¶ Test for online CPU/Rx queue
Parameters
unsigned long j
CPU/Rx queue index
const unsigned long *online_mask
bitmask for CPUs/Rx queues that are online
unsigned int nr_bits
number of bits in the bitmask
Description
Returns true if a CPU/Rx queue is online.
-
unsigned int
netif_attrmask_next
(int n, const unsigned long *srcp, unsigned int nr_bits)¶ get the next CPU/Rx queue in a cpu/Rx queues mask
Parameters
int n
CPU/Rx queue index
const unsigned long *srcp
the cpumask/Rx queue mask pointer
unsigned int nr_bits
number of bits in the bitmask
Description
Returns >= nr_bits if no further CPUs/Rx queues set.
-
int
netif_attrmask_next_and
(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits)¶ get the next CPU/Rx queue in *src1p & *src2p
Parameters
int n
CPU/Rx queue index
const unsigned long *src1p
the first CPUs/Rx queues mask pointer
const unsigned long *src2p
the second CPUs/Rx queues mask pointer
unsigned int nr_bits
number of bits in the bitmask
Description
Returns >= nr_bits if no further CPUs/Rx queues set in both.
-
bool
netif_is_multiqueue
(const struct net_device *dev)¶ test if device has multiple transmit queues
Parameters
const struct net_device *dev
network device
Description
Check if device has multiple transmit queues
-
void
dev_put
(struct net_device *dev)¶ release reference to device
Parameters
struct net_device *dev
network device
Description
Release reference to device to allow it to be freed. Try using dev_put_track() instead.
-
void
dev_hold
(struct net_device *dev)¶ get reference to device
Parameters
struct net_device *dev
network device
Description
Hold reference to device to keep it from being freed. Try using dev_hold_track() instead.
-
bool
netif_carrier_ok
(const struct net_device *dev)¶ test if carrier present
Parameters
const struct net_device *dev
network device
Description
Check if carrier is present on device
-
void
netif_dormant_on
(struct net_device *dev)¶ mark device as dormant.
Parameters
struct net_device *dev
network device
Description
Mark device as dormant (as per RFC2863).
The dormant state indicates that the relevant interface is not actually in a condition to pass packets (i.e., it is not ‘up’) but is in a “pending” state, waiting for some external event. For “on- demand” interfaces, this new state identifies the situation where the interface is waiting for events to place it in the up state.
-
void
netif_dormant_off
(struct net_device *dev)¶ set device as not dormant.
Parameters
struct net_device *dev
network device
Description
Device is not in dormant state.
-
bool
netif_dormant
(const struct net_device *dev)¶ test if device is dormant
Parameters
const struct net_device *dev
network device
Description
Check if device is dormant.
-
void
netif_testing_on
(struct net_device *dev)¶ mark device as under test.
Parameters
struct net_device *dev
network device
Description
Mark device as under test (as per RFC2863).
The testing state indicates that some test(s) must be performed on the interface. After completion, of the test, the interface state will change to up, dormant, or down, as appropriate.
-
void
netif_testing_off
(struct net_device *dev)¶ set device as not under test.
Parameters
struct net_device *dev
network device
Description
Device is not in testing state.
-
bool
netif_testing
(const struct net_device *dev)¶ test if device is under test
Parameters
const struct net_device *dev
network device
Description
Check if device is under test
-
bool
netif_oper_up
(const struct net_device *dev)¶ test if device is operational
Parameters
const struct net_device *dev
network device
Description
Check if carrier is operational
-
bool
netif_device_present
(const struct net_device *dev)¶ is device available or removed
Parameters
const struct net_device *dev
network device
Description
Check if device has not been removed from system.
-
void
netif_tx_lock
(struct net_device *dev)¶ grab network device transmit lock
Parameters
struct net_device *dev
network device
Description
Get network device transmit lock
-
int
__dev_uc_sync
(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *))¶ Synchonize device’s unicast list
Parameters
struct net_device *dev
device to sync
int (*sync)(struct net_device *, const unsigned char *)
function to call if address should be added
int (*unsync)(struct net_device *, const unsigned char *)
function to call if address should be removed
Add newly added addresses to the interface, and release addresses that have been deleted.
-
void
__dev_uc_unsync
(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *))¶ Remove synchronized addresses from device
Parameters
struct net_device *dev
device to sync
int (*unsync)(struct net_device *, const unsigned char *)
function to call if address should be removed
Remove all addresses that were added to the device by dev_uc_sync().
-
int
__dev_mc_sync
(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *))¶ Synchonize device’s multicast list
Parameters
struct net_device *dev
device to sync
int (*sync)(struct net_device *, const unsigned char *)
function to call if address should be added
int (*unsync)(struct net_device *, const unsigned char *)
function to call if address should be removed
Add newly added addresses to the interface, and release addresses that have been deleted.
-
void
__dev_mc_unsync
(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *))¶ Remove synchronized addresses from device
Parameters
struct net_device *dev
device to sync
int (*unsync)(struct net_device *, const unsigned char *)
function to call if address should be removed
Remove all addresses that were added to the device by dev_mc_sync().
PHY Support¶
-
void
phy_print_status
(struct phy_device *phydev)¶ Convenience function to print out the current phy status
Parameters
struct phy_device *phydev
the phy_device struct
-
int
phy_restart_aneg
(struct phy_device *phydev)¶ restart auto-negotiation
Parameters
struct phy_device *phydev
target phy_device struct
Description
Restart the autonegotiation on phydev. Returns >= 0 on success or negative errno on error.
-
int
phy_aneg_done
(struct phy_device *phydev)¶ return auto-negotiation status
Parameters
struct phy_device *phydev
target phy_device struct
Description
Return the auto-negotiation status from this phydev Returns > 0 on success or < 0 on error. 0 means that auto-negotiation is still pending.
-
int
phy_mii_ioctl
(struct phy_device *phydev, struct ifreq *ifr, int cmd)¶ generic PHY MII ioctl interface
Parameters
struct phy_device *phydev
the phy_device struct
struct ifreq *ifr
struct ifreq
for socket ioctl’sint cmd
ioctl cmd to execute
Description
Note that this function is currently incompatible with the PHYCONTROL layer. It changes registers without regard to current state. Use at own risk.
-
int
phy_do_ioctl
(struct net_device *dev, struct ifreq *ifr, int cmd)¶ generic ndo_eth_ioctl implementation
Parameters
struct net_device *dev
the net_device struct
struct ifreq *ifr
struct ifreq
for socket ioctl’sint cmd
ioctl cmd to execute
-
int
phy_do_ioctl_running
(struct net_device *dev, struct ifreq *ifr, int cmd)¶ generic ndo_eth_ioctl implementation but test first
Parameters
struct net_device *dev
the net_device struct
struct ifreq *ifr
struct ifreq
for socket ioctl’sint cmd
ioctl cmd to execute
Description
Same as phy_do_ioctl, but ensures that net_device is running before handling the ioctl.
-
void
phy_queue_state_machine
(struct phy_device *phydev, unsigned long jiffies)¶ Trigger the state machine to run soon
Parameters
struct phy_device *phydev
the phy_device struct
unsigned long jiffies
Run the state machine after these jiffies
-
void
phy_trigger_machine
(struct phy_device *phydev)¶ Trigger the state machine to run now
Parameters
struct phy_device *phydev
the phy_device struct
-
int
phy_ethtool_get_strings
(struct phy_device *phydev, u8 *data)¶ Get the statistic counter names
Parameters
struct phy_device *phydev
the phy_device struct
u8 *data
Where to put the strings
-
int
phy_ethtool_get_sset_count
(struct phy_device *phydev)¶ Get the number of statistic counters
Parameters
struct phy_device *phydev
the phy_device struct
-
int
phy_ethtool_get_stats
(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data)¶ Get the statistic counters
Parameters
struct phy_device *phydev
the phy_device struct
struct ethtool_stats *stats
What counters to get
u64 *data
Where to store the counters
-
int
phy_start_cable_test
(struct phy_device *phydev, struct netlink_ext_ack *extack)¶ Start a cable test
Parameters
struct phy_device *phydev
the phy_device struct
struct netlink_ext_ack *extack
extack for reporting useful error messages
-
int
phy_start_cable_test_tdr
(struct phy_device *phydev, struct netlink_ext_ack *extack, const struct phy_tdr_config *config)¶ Start a raw TDR cable test
Parameters
struct phy_device *phydev
the phy_device struct
struct netlink_ext_ack *extack
extack for reporting useful error messages
const struct phy_tdr_config *config
Configuration of the test to run
-
int
phy_start_aneg
(struct phy_device *phydev)¶ start auto-negotiation for this PHY device
Parameters
struct phy_device *phydev
the phy_device struct
Description
- Sanitizes the settings (if we’re not autonegotiating
them), and then calls the driver’s config_aneg function. If the PHYCONTROL Layer is operating, we change the state to reflect the beginning of Auto-negotiation or forcing.
-
int
phy_speed_down
(struct phy_device *phydev, bool sync)¶ set speed to lowest speed supported by both link partners
Parameters
struct phy_device *phydev
the phy_device struct
bool sync
perform action synchronously
Description
Typically used to save energy when waiting for a WoL packet
WARNING: Setting sync to false may cause the system being unable to suspend in case the PHY generates an interrupt when finishing the autonegotiation. This interrupt may wake up the system immediately after suspend. Therefore use sync = false only if you’re sure it’s safe with the respective network chip.
-
int
phy_speed_up
(struct phy_device *phydev)¶ (re)set advertised speeds to all supported speeds
Parameters
struct phy_device *phydev
the phy_device struct
Description
Used to revert the effect of phy_speed_down
-
void
phy_start_machine
(struct phy_device *phydev)¶ start PHY state machine tracking
Parameters
struct phy_device *phydev
the phy_device struct
Description
- The PHY infrastructure can run a state machine
which tracks whether the PHY is starting up, negotiating, etc. This function starts the delayed workqueue which tracks the state of the PHY. If you want to maintain your own state machine, do not call this function.
-
void
phy_error
(struct phy_device *phydev)¶ enter HALTED state for this PHY device
Parameters
struct phy_device *phydev
target phy_device struct
Description
Moves the PHY to the HALTED state in response to a read or write error, and tells the controller the link is down. Must not be called from interrupt context, or while the phydev->lock is held.
-
void
phy_request_interrupt
(struct phy_device *phydev)¶ request and enable interrupt for a PHY device
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Request and enable the interrupt for the given PHY.
If this fails, then we set irq to PHY_POLL. This should only be called with a valid IRQ number.
-
void
phy_free_interrupt
(struct phy_device *phydev)¶ disable and free interrupt for a PHY device
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Disable and free the interrupt for the given PHY.
This should only be called with a valid IRQ number.
-
void
phy_stop
(struct phy_device *phydev)¶ Bring down the PHY link, and stop checking the status
Parameters
struct phy_device *phydev
target phy_device struct
-
void
phy_start
(struct phy_device *phydev)¶ start or restart a PHY device
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Indicates the attached device’s readiness to
handle PHY-related work. Used during startup to start the PHY, and after a call to
phy_stop()
to resume operation. Also used to indicate the MDIO bus has cleared an error condition.
-
void
phy_mac_interrupt
(struct phy_device *phydev)¶ MAC says the link has changed
Parameters
struct phy_device *phydev
phy_device struct with changed link
Description
The MAC layer is able to indicate there has been a change in the PHY link status. Trigger the state machine and work a work queue.
-
int
phy_init_eee
(struct phy_device *phydev, bool clk_stop_enable)¶ init and check the EEE feature
Parameters
struct phy_device *phydev
target phy_device struct
bool clk_stop_enable
PHY may stop the clock during LPI
Description
it checks if the Energy-Efficient Ethernet (EEE) is supported by looking at the MMD registers 3.20 and 7.60/61 and it programs the MMD register 3.0 setting the “Clock stop enable” bit if required.
-
int
phy_get_eee_err
(struct phy_device *phydev)¶ report the EEE wake error count
Parameters
struct phy_device *phydev
target phy_device struct
Description
it is to report the number of time where the PHY failed to complete its normal wake sequence.
-
int
phy_ethtool_get_eee
(struct phy_device *phydev, struct ethtool_eee *data)¶ get EEE supported and status
Parameters
struct phy_device *phydev
target phy_device struct
struct ethtool_eee *data
ethtool_eee data
Description
it reportes the Supported/Advertisement/LP Advertisement capabilities.
-
int
phy_ethtool_set_eee
(struct phy_device *phydev, struct ethtool_eee *data)¶ set EEE supported and status
Parameters
struct phy_device *phydev
target phy_device struct
struct ethtool_eee *data
ethtool_eee data
Description
it is to program the Advertisement EEE register.
-
int
phy_ethtool_set_wol
(struct phy_device *phydev, struct ethtool_wolinfo *wol)¶ Configure Wake On LAN
Parameters
struct phy_device *phydev
target phy_device struct
struct ethtool_wolinfo *wol
Configuration requested
-
void
phy_ethtool_get_wol
(struct phy_device *phydev, struct ethtool_wolinfo *wol)¶ Get the current Wake On LAN configuration
Parameters
struct phy_device *phydev
target phy_device struct
struct ethtool_wolinfo *wol
Store the current configuration here
-
int
phy_ethtool_nway_reset
(struct net_device *ndev)¶ Restart auto negotiation
Parameters
struct net_device *ndev
Network device to restart autoneg for
-
int
phy_config_interrupt
(struct phy_device *phydev, bool interrupts)¶ configure the PHY device for the requested interrupts
Parameters
struct phy_device *phydev
the phy_device struct
bool interrupts
interrupt flags to configure for this phydev
Description
Returns 0 on success or < 0 on error.
-
const struct phy_setting *
phy_find_valid
(int speed, int duplex, unsigned long *supported)¶ find a PHY setting that matches the requested parameters
Parameters
int speed
desired speed
int duplex
desired duplex
unsigned long *supported
mask of supported link modes
Description
Locate a supported phy setting that is, in priority order:
- an exact match for the specified speed and duplex mode
- a match for the specified speed, or slower speed
- the slowest supported speed
Returns the matched phy_setting entry, or NULL
if no supported phy
settings were found.
-
unsigned int
phy_supported_speeds
(struct phy_device *phy, unsigned int *speeds, unsigned int size)¶ return all speeds currently supported by a phy device
Parameters
struct phy_device *phy
The phy device to return supported speeds of.
unsigned int *speeds
buffer to store supported speeds in.
unsigned int size
size of speeds buffer.
Description
Returns the number of supported speeds, and fills the speeds buffer with the supported speeds. If speeds buffer is too small to contain all currently supported speeds, will return as many speeds as can fit.
-
bool
phy_check_valid
(int speed, int duplex, unsigned long *features)¶ check if there is a valid PHY setting which matches speed, duplex, and feature mask
Parameters
int speed
speed to match
int duplex
duplex to match
unsigned long *features
A mask of the valid settings
Description
Returns true if there is a valid setting, false otherwise.
-
void
phy_sanitize_settings
(struct phy_device *phydev)¶ make sure the PHY is set to supported speed and duplex
Parameters
struct phy_device *phydev
the target phy_device struct
Description
- Make sure the PHY is set to supported speeds and
duplexes. Drop down by one in this order: 1000/FULL, 1000/HALF, 100/FULL, 100/HALF, 10/FULL, 10/HALF.
-
int
phy_check_link_status
(struct phy_device *phydev)¶ check link status and set state accordingly
Parameters
struct phy_device *phydev
the phy_device struct
Description
Check for link and whether autoneg was triggered / is running and set state accordingly
-
int
_phy_start_aneg
(struct phy_device *phydev)¶ start auto-negotiation for this PHY device
Parameters
struct phy_device *phydev
the phy_device struct
Description
- Sanitizes the settings (if we’re not autonegotiating
them), and then calls the driver’s config_aneg function. If the PHYCONTROL Layer is operating, we change the state to reflect the beginning of Auto-negotiation or forcing.
-
void
phy_stop_machine
(struct phy_device *phydev)¶ stop the PHY state machine tracking
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Stops the state machine delayed workqueue, sets the
state to UP (unless it wasn’t up yet). This function must be called BEFORE phy_detach.
-
int
phy_disable_interrupts
(struct phy_device *phydev)¶ Disable the PHY interrupts from the PHY side
Parameters
struct phy_device *phydev
target phy_device struct
-
irqreturn_t
phy_interrupt
(int irq, void *phy_dat)¶ PHY interrupt handler
Parameters
int irq
interrupt line
void *phy_dat
phy_device pointer
Description
Handle PHY interrupt
-
int
phy_enable_interrupts
(struct phy_device *phydev)¶ Enable the interrupts from the PHY side
Parameters
struct phy_device *phydev
target phy_device struct
-
void
phy_state_machine
(struct work_struct *work)¶ Handle the state machine
Parameters
struct work_struct *work
work_struct that describes the work to be done
-
const char *
phy_speed_to_str
(int speed)¶ Return a string representing the PHY link speed
Parameters
int speed
Speed of the link
-
const char *
phy_duplex_to_str
(unsigned int duplex)¶ Return string describing the duplex
Parameters
unsigned int duplex
Duplex setting to describe
-
const struct phy_setting *
phy_lookup_setting
(int speed, int duplex, const unsigned long *mask, bool exact)¶ lookup a PHY setting
Parameters
int speed
speed to match
int duplex
duplex to match
const unsigned long *mask
allowed link modes
bool exact
an exact match is required
Description
Search the settings array for a setting that matches the speed and duplex, and which is supported.
If exact is unset, either an exact match or NULL
for no match will
be returned.
If exact is set, an exact match, the fastest supported setting at
or below the specified speed, the slowest supported setting, or if
they all fail, NULL
will be returned.
-
int
phy_set_max_speed
(struct phy_device *phydev, u32 max_speed)¶ Set the maximum speed the PHY should support
Parameters
struct phy_device *phydev
The phy_device struct
u32 max_speed
Maximum speed
Description
The PHY might be more capable than the MAC. For example a Fast Ethernet is connected to a 1G PHY. This function allows the MAC to indicate its maximum speed, and so limit what the PHY will advertise.
-
void
phy_resolve_aneg_pause
(struct phy_device *phydev)¶ Determine pause autoneg results
Parameters
struct phy_device *phydev
The phy_device struct
Description
Once autoneg has completed the local pause settings can be resolved. Determine if pause and asymmetric pause should be used by the MAC.
-
void
phy_resolve_aneg_linkmode
(struct phy_device *phydev)¶ resolve the advertisements into PHY settings
Parameters
struct phy_device *phydev
The phy_device struct
Description
Resolve our and the link partner advertisements into their corresponding speed and duplex. If full duplex was negotiated, extract the pause mode from the link partner mask.
-
void
phy_check_downshift
(struct phy_device *phydev)¶ check whether downshift occurred
Parameters
struct phy_device *phydev
The phy_device struct
Description
Check whether a downshift to a lower speed occurred. If this should be the case warn the user. Prerequisite for detecting downshift is that PHY driver implements the read_status callback and sets phydev->speed to the actual link speed.
-
int
__phy_read_mmd
(struct phy_device *phydev, int devad, u32 regnum)¶ Convenience function for reading a register from an MMD on a given PHY.
Parameters
struct phy_device *phydev
The phy_device struct
int devad
The MMD to read from (0..31)
u32 regnum
The register on the MMD to read (0..65535)
Description
Same rules as for __phy_read()
;
-
int
phy_read_mmd
(struct phy_device *phydev, int devad, u32 regnum)¶ Convenience function for reading a register from an MMD on a given PHY.
Parameters
struct phy_device *phydev
The phy_device struct
int devad
The MMD to read from
u32 regnum
The register on the MMD to read
Description
Same rules as for phy_read()
;
-
int
__phy_write_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for writing a register on an MMD on a given PHY.
Parameters
struct phy_device *phydev
The phy_device struct
int devad
The MMD to read from
u32 regnum
The register on the MMD to read
u16 val
value to write to regnum
Description
Same rules as for __phy_write()
;
-
int
phy_write_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for writing a register on an MMD on a given PHY.
Parameters
struct phy_device *phydev
The phy_device struct
int devad
The MMD to read from
u32 regnum
The register on the MMD to read
u16 val
value to write to regnum
Description
Same rules as for phy_write()
;
-
int
phy_modify_changed
(struct phy_device *phydev, u32 regnum, u16 mask, u16 set)¶ Function for modifying a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
Description
Returns negative errno, 0 if there was no change, and 1 in case of change
-
int
__phy_modify
(struct phy_device *phydev, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
phy_modify
(struct phy_device *phydev, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a given PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
__phy_modify_mmd_changed
(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set)¶ Function for modifying a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
Description
Unlocked helper function which allows a MMD register to be modified as new register value = (old register value & ~mask) | set
Returns negative errno, 0 if there was no change, and 1 in case of change
-
int
phy_modify_mmd_changed
(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set)¶ Function for modifying a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
Description
Returns negative errno, 0 if there was no change, and 1 in case of change
-
int
__phy_modify_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
phy_modify_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
new value of bits set in mask to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
phy_save_page
(struct phy_device *phydev)¶ take the bus lock and save the current page
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
Description
Take the MDIO bus lock, and return the current page number. On error,
returns a negative errno. phy_restore_page()
must always be called
after this, irrespective of success or failure of this call.
-
int
phy_select_page
(struct phy_device *phydev, int page)¶ take the bus lock, save the current page, and set a page
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int page
desired page
Description
Take the MDIO bus lock to protect against concurrent access, save the
current PHY page, and set the current page. On error, returns a
negative errno, otherwise returns the previous page number.
phy_restore_page()
must always be called after this, irrespective
of success or failure of this call.
-
int
phy_restore_page
(struct phy_device *phydev, int oldpage, int ret)¶ restore the page register and release the bus lock
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int oldpage
the old page, return value from
phy_save_page()
orphy_select_page()
int ret
operation’s return code
Description
Release the MDIO bus lock, restoring oldpage if it is a valid page. This function propagates the earliest error code from the group of operations.
Return
oldpage if it was a negative value, otherwise ret if it was a negative errno value, otherwise phy_write_page()’s negative value if it were in error, otherwise ret.
-
int
phy_read_paged
(struct phy_device *phydev, int page, u32 regnum)¶ Convenience function for reading a paged register
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int page
the page for the phy
u32 regnum
register number
Description
Same rules as for phy_read()
.
-
int
phy_write_paged
(struct phy_device *phydev, int page, u32 regnum, u16 val)¶ Convenience function for writing a paged register
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int page
the page for the phy
u32 regnum
register number
u16 val
value to write
Description
Same rules as for phy_write()
.
-
int
phy_modify_paged_changed
(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set)¶ Function for modifying a paged register
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int page
the page for the phy
u32 regnum
register number
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
Description
Returns negative errno, 0 if there was no change, and 1 in case of change
-
int
phy_modify_paged
(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a paged register
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
int page
the page for the phy
u32 regnum
register number
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
Description
Same rules as for phy_read()
and phy_write()
.
-
int
genphy_c45_pma_resume
(struct phy_device *phydev)¶ wakes up the PMA module
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_c45_pma_suspend
(struct phy_device *phydev)¶ suspends the PMA module
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_c45_pma_setup_forced
(struct phy_device *phydev)¶ configures a forced speed
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_c45_an_config_aneg
(struct phy_device *phydev)¶ configure advertisement registers
Parameters
struct phy_device *phydev
target phy_device struct
Description
Configure advertisement registers based on modes set in phydev->advertising
Returns negative errno code on failure, 0 if advertisement didn’t change, or 1 if advertised modes changed.
-
int
genphy_c45_an_disable_aneg
(struct phy_device *phydev)¶ disable auto-negotiation
Parameters
struct phy_device *phydev
target phy_device struct
Description
Disable auto-negotiation in the Clause 45 PHY. The link parameters are controlled through the PMA/PMD MMD registers.
Returns zero on success, negative errno code on failure.
-
int
genphy_c45_restart_aneg
(struct phy_device *phydev)¶ Enable and restart auto-negotiation
Parameters
struct phy_device *phydev
target phy_device struct
Description
This assumes that the auto-negotiation MMD is present.
Enable and restart auto-negotiation.
-
int
genphy_c45_check_and_restart_aneg
(struct phy_device *phydev, bool restart)¶ Enable and restart auto-negotiation
Parameters
struct phy_device *phydev
target phy_device struct
bool restart
whether aneg restart is requested
Description
This assumes that the auto-negotiation MMD is present.
Check, and restart auto-negotiation if needed.
-
int
genphy_c45_aneg_done
(struct phy_device *phydev)¶ return auto-negotiation complete status
Parameters
struct phy_device *phydev
target phy_device struct
Description
This assumes that the auto-negotiation MMD is present.
Reads the status register from the auto-negotiation MMD, returning: - positive if auto-negotiation is complete - negative errno code on error - zero otherwise
-
int
genphy_c45_read_link
(struct phy_device *phydev)¶ read the overall link status from the MMDs
Parameters
struct phy_device *phydev
target phy_device struct
Description
Read the link status from the specified MMDs, and if they all indicate that the link is up, set phydev->link to 1. If an error is encountered, a negative errno will be returned, otherwise zero.
-
int
genphy_c45_read_lpa
(struct phy_device *phydev)¶ read the link partner advertisement and pause
Parameters
struct phy_device *phydev
target phy_device struct
Description
Read the Clause 45 defined base (7.19) and 10G (7.33) status registers, filling in the link partner advertisement, pause and asym_pause members in phydev. This assumes that the auto-negotiation MMD is present, and the backplane bit (7.48.0) is clear. Clause 45 PHY drivers are expected to fill in the remainder of the link partner advert from vendor registers.
-
int
genphy_c45_read_pma
(struct phy_device *phydev)¶ read link speed etc from PMA
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_c45_read_mdix
(struct phy_device *phydev)¶ read mdix status from PMA
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_c45_pma_read_abilities
(struct phy_device *phydev)¶ read supported link modes from PMA
Parameters
struct phy_device *phydev
target phy_device struct
Description
Read the supported link modes from the PMA Status 2 (1.8) register. If bit 1.8.9 is set, the list of supported modes is build using the values in the PMA Extended Abilities (1.11) register, indicating 1000BASET an 10G related modes. If bit 1.11.14 is set, then the list is also extended with the modes in the 2.5G/5G PMA Extended register (1.21), indicating if 2.5GBASET and 5GBASET are supported.
-
int
genphy_c45_read_status
(struct phy_device *phydev)¶ read PHY status
Parameters
struct phy_device *phydev
target phy_device struct
Description
Reads status from PHY and sets phy_device members accordingly.
-
int
genphy_c45_config_aneg
(struct phy_device *phydev)¶ restart auto-negotiation or forced setup
Parameters
struct phy_device *phydev
target phy_device struct
Description
- If auto-negotiation is enabled, we configure the
advertising, and then restart auto-negotiation. If it is not enabled, then we force a configuration.
-
int
genphy_c45_fast_retrain
(struct phy_device *phydev, bool enable)¶ configure fast retrain registers
Parameters
struct phy_device *phydev
target phy_device struct
bool enable
enable fast retrain or not
Description
- If fast-retrain is enabled, we configure PHY as
advertising fast retrain capable and THP Bypass Request, then enable fast retrain. If it is not enabled, we configure fast retrain disabled.
-
enum
phy_interface_t
¶ Interface Mode definitions
Constants
PHY_INTERFACE_MODE_NA
Not Applicable - don’t touch
PHY_INTERFACE_MODE_INTERNAL
No interface, MAC and PHY combined
PHY_INTERFACE_MODE_MII
Media-independent interface
PHY_INTERFACE_MODE_GMII
Gigabit media-independent interface
PHY_INTERFACE_MODE_SGMII
Serial gigabit media-independent interface
PHY_INTERFACE_MODE_TBI
Ten Bit Interface
PHY_INTERFACE_MODE_REVMII
Reverse Media Independent Interface
PHY_INTERFACE_MODE_RMII
Reduced Media Independent Interface
PHY_INTERFACE_MODE_REVRMII
Reduced Media Independent Interface in PHY role
PHY_INTERFACE_MODE_RGMII
Reduced gigabit media-independent interface
PHY_INTERFACE_MODE_RGMII_ID
RGMII with Internal RX+TX delay
PHY_INTERFACE_MODE_RGMII_RXID
RGMII with Internal RX delay
PHY_INTERFACE_MODE_RGMII_TXID
RGMII with Internal RX delay
PHY_INTERFACE_MODE_RTBI
Reduced TBI
PHY_INTERFACE_MODE_SMII
Serial MII
PHY_INTERFACE_MODE_XGMII
10 gigabit media-independent interface
PHY_INTERFACE_MODE_XLGMII
40 gigabit media-independent interface
PHY_INTERFACE_MODE_MOCA
Multimedia over Coax
PHY_INTERFACE_MODE_QSGMII
Quad SGMII
PHY_INTERFACE_MODE_TRGMII
Turbo RGMII
PHY_INTERFACE_MODE_100BASEX
100 BaseX
PHY_INTERFACE_MODE_1000BASEX
1000 BaseX
PHY_INTERFACE_MODE_2500BASEX
2500 BaseX
PHY_INTERFACE_MODE_5GBASER
5G BaseR
PHY_INTERFACE_MODE_RXAUI
Reduced XAUI
PHY_INTERFACE_MODE_XAUI
10 Gigabit Attachment Unit Interface
PHY_INTERFACE_MODE_10GBASER
10G BaseR
PHY_INTERFACE_MODE_25GBASER
25G BaseR
PHY_INTERFACE_MODE_USXGMII
Universal Serial 10GE MII
PHY_INTERFACE_MODE_10GKR
10GBASE-KR - with Clause 73 AN
PHY_INTERFACE_MODE_MAX
Book keeping
Description
Describes the interface between the MAC and PHY.
-
const char *
phy_modes
(phy_interface_t interface)¶ map phy_interface_t enum to device tree binding of phy-mode
Parameters
phy_interface_t interface
enum phy_interface_t
value
Description
maps enum phy_interface_t
defined in this file
into the device tree binding of ‘phy-mode’, so that Ethernet
device driver can get PHY interface from device tree.
-
struct
mdio_bus_stats
¶ Statistics counters for MDIO busses
Definition
struct mdio_bus_stats {
u64_stats_t transfers;
u64_stats_t errors;
u64_stats_t writes;
u64_stats_t reads;
struct u64_stats_sync syncp;
};
Members
transfers
Total number of transfers, i.e. writes + reads
errors
Number of MDIO transfers that returned an error
writes
Number of write transfers
reads
Number of read transfers
syncp
Synchronisation for incrementing statistics
Shared information in PHY packages
Definition
struct phy_package_shared {
int addr;
refcount_t refcnt;
unsigned long flags;
size_t priv_size;
void *priv;
};
Members
addr
Common PHY address used to combine PHYs in one package
refcnt
Number of PHYs connected to this shared data
flags
Initialization of PHY package
priv_size
Size of the shared private data priv
priv
Driver private data shared across a PHY package
Description
Represents a shared structure between different phydev’s in the same
package, for example a quad PHY. See phy_package_join()
and
phy_package_leave()
.
-
struct
mii_bus
¶ Represents an MDIO bus
Definition
struct mii_bus {
struct module *owner;
const char *name;
char id[MII_BUS_ID_SIZE];
void *priv;
int (*read)(struct mii_bus *bus, int addr, int regnum);
int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val);
int (*reset)(struct mii_bus *bus);
struct mdio_bus_stats stats[PHY_MAX_ADDR];
struct mutex mdio_lock;
struct device *parent;
enum {
MDIOBUS_ALLOCATED = 1,
MDIOBUS_REGISTERED,
MDIOBUS_UNREGISTERED,
MDIOBUS_RELEASED,
} state;
struct device dev;
struct mdio_device *mdio_map[PHY_MAX_ADDR];
u32 phy_mask;
u32 phy_ignore_ta_mask;
int irq[PHY_MAX_ADDR];
int reset_delay_us;
int reset_post_delay_us;
struct gpio_desc *reset_gpiod;
enum {
MDIOBUS_NO_CAP = 0,
MDIOBUS_C22,
MDIOBUS_C45,
MDIOBUS_C22_C45,
} probe_capabilities;
struct mutex shared_lock;
struct phy_package_shared *shared[PHY_MAX_ADDR];
};
Members
owner
Who owns this device
name
User friendly name for this MDIO device, or driver name
id
Unique identifier for this bus, typical from bus hierarchy
priv
Driver private data
read
Perform a read transfer on the bus
write
Perform a write transfer on the bus
reset
Perform a reset of the bus
stats
Statistic counters per device on the bus
mdio_lock
A lock to ensure that only one thing can read/write the MDIO bus at a time
parent
Parent device of this bus
state
State of bus structure
dev
Kernel device representation
mdio_map
list of all MDIO devices on bus
phy_mask
PHY addresses to be ignored when probing
phy_ignore_ta_mask
PHY addresses to ignore the TA/read failure
irq
An array of interrupts, each PHY’s interrupt at the index matching its address
reset_delay_us
GPIO reset pulse width in microseconds
reset_post_delay_us
GPIO reset deassert delay in microseconds
reset_gpiod
Reset GPIO descriptor pointer
probe_capabilities
bus capabilities, used for probing
shared_lock
protect access to the shared element
shared
shared state across different PHYs
Description
The Bus class for PHYs. Devices which provide access to PHYs should register using this structure
Parameters
void
no arguments
Description
The internal state of the MDIO bus will be set of MDIOBUS_ALLOCATED ready for the driver to register the bus.
-
enum
phy_state
¶ PHY state machine states:
Constants
PHY_DOWN
PHY device and driver are not ready for anything. probe should be called if and only if the PHY is in this state, given that the PHY device exists. - PHY driver probe function will set the state to PHY_READY
PHY_READY
PHY is ready to send and receive packets, but the controller is not. By default, PHYs which do not implement probe will be set to this state by
phy_probe()
. - start will set the state to UPPHY_HALTED
PHY is up, but no polling or interrupts are done. Or PHY is in an error state. - phy_start moves to PHY_UP
PHY_UP
The PHY and attached device are ready to do work. Interrupts should be started here. - timer moves to PHY_NOLINK or PHY_RUNNING
PHY_RUNNING
PHY is currently up, running, and possibly sending and/or receiving packets - irq or timer will set PHY_NOLINK if link goes down - phy_stop moves to PHY_HALTED
PHY_NOLINK
PHY is up, but not currently plugged in. - irq or timer will set PHY_RUNNING if link comes back - phy_stop moves to PHY_HALTED
PHY_CABLETEST
PHY is performing a cable test. Packet reception/sending is not expected to work, carrier will be indicated as down. PHY will be poll once per second, or on interrupt for it current state. Once complete, move to UP to restart the PHY. - phy_stop aborts the running test and moves to PHY_HALTED
-
struct
phy_c45_device_ids
¶ 802.3-c45 Device Identifiers
Definition
struct phy_c45_device_ids {
u32 devices_in_package;
u32 mmds_present;
u32 device_ids[MDIO_MMD_NUM];
};
Members
devices_in_package
IEEE 802.3 devices in package register value.
mmds_present
bit vector of MMDs present.
device_ids
The device identifer for each present device.
-
struct
phy_device
¶ An instance of a PHY
Definition
struct phy_device {
struct mdio_device mdio;
struct phy_driver *drv;
u32 phy_id;
struct phy_c45_device_ids c45_ids;
unsigned is_c45:1;
unsigned is_internal:1;
unsigned is_pseudo_fixed_link:1;
unsigned is_gigabit_capable:1;
unsigned has_fixups:1;
unsigned suspended:1;
unsigned suspended_by_mdio_bus:1;
unsigned sysfs_links:1;
unsigned loopback_enabled:1;
unsigned downshifted_rate:1;
unsigned is_on_sfp_module:1;
unsigned mac_managed_pm:1;
unsigned autoneg:1;
unsigned link:1;
unsigned autoneg_complete:1;
unsigned interrupts:1;
enum phy_state state;
u32 dev_flags;
phy_interface_t interface;
int speed;
int duplex;
int port;
int pause;
int asym_pause;
u8 master_slave_get;
u8 master_slave_set;
u8 master_slave_state;
unsigned long supported[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
unsigned long advertising[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
unsigned long lp_advertising[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
unsigned long adv_old[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
u32 eee_broken_modes;
#ifdef CONFIG_LED_TRIGGER_PHY;
struct phy_led_trigger *phy_led_triggers;
unsigned int phy_num_led_triggers;
struct phy_led_trigger *last_triggered;
struct phy_led_trigger *led_link_trigger;
#endif;
int irq;
void *priv;
struct phy_package_shared *shared;
struct sk_buff *skb;
void *ehdr;
struct nlattr *nest;
struct delayed_work state_queue;
struct mutex lock;
bool sfp_bus_attached;
struct sfp_bus *sfp_bus;
struct phylink *phylink;
struct net_device *attached_dev;
struct mii_timestamper *mii_ts;
u8 mdix;
u8 mdix_ctrl;
void (*phy_link_change)(struct phy_device *phydev, bool up);
void (*adjust_link)(struct net_device *dev);
#if IS_ENABLED(CONFIG_MACSEC);
const struct macsec_ops *macsec_ops;
#endif;
};
Members
mdio
MDIO bus this PHY is on
drv
Pointer to the driver for this PHY instance
phy_id
UID for this device found during discovery
c45_ids
802.3-c45 Device Identifiers if is_c45.
is_c45
Set to true if this PHY uses clause 45 addressing.
is_internal
Set to true if this PHY is internal to a MAC.
is_pseudo_fixed_link
Set to true if this PHY is an Ethernet switch, etc.
is_gigabit_capable
Set to true if PHY supports 1000Mbps
has_fixups
Set to true if this PHY has fixups/quirks.
suspended
Set to true if this PHY has been suspended successfully.
suspended_by_mdio_bus
Set to true if this PHY was suspended by MDIO bus.
sysfs_links
Internal boolean tracking sysfs symbolic links setup/removal.
loopback_enabled
Set true if this PHY has been loopbacked successfully.
downshifted_rate
Set true if link speed has been downshifted.
is_on_sfp_module
Set true if PHY is located on an SFP module.
mac_managed_pm
Set true if MAC driver takes of suspending/resuming PHY
autoneg
Flag autoneg being used
link
Current link state
autoneg_complete
Flag auto negotiation of the link has completed
interrupts
Flag interrupts have been enabled
state
State of the PHY for management purposes
dev_flags
Device-specific flags used by the PHY driver.
Bits [15:0] are free to use by the PHY driver to communicate driver specific behavior.
Bits [23:16] are currently reserved for future use.
Bits [31:24] are reserved for defining generic PHY driver behavior.
interface
enum phy_interface_t
valuespeed
Current link speed
duplex
Current duplex
port
Current port
pause
Current pause
asym_pause
Current asymmetric pause
master_slave_get
Current master/slave advertisement
master_slave_set
User requested master/slave configuration
master_slave_state
Current master/slave configuration
supported
Combined MAC/PHY supported linkmodes
advertising
Currently advertised linkmodes
lp_advertising
Current link partner advertised linkmodes
adv_old
Saved advertised while power saving for WoL
eee_broken_modes
Energy efficient ethernet modes which should be prohibited
phy_led_triggers
Array of LED triggers
phy_num_led_triggers
Number of triggers in phy_led_triggers
last_triggered
last LED trigger for link speed
led_link_trigger
LED trigger for link up/down
irq
IRQ number of the PHY’s interrupt (-1 if none)
priv
Pointer to driver private data
shared
Pointer to private data shared by phys in one package
skb
Netlink message for cable diagnostics
ehdr
nNtlink header for cable diagnostics
nest
Netlink nest used for cable diagnostics
state_queue
Work queue for state machine
lock
Mutex for serialization access to PHY
sfp_bus_attached
Flag indicating whether the SFP bus has been attached
sfp_bus
SFP bus attached to this PHY’s fiber port
phylink
Pointer to phylink instance for this PHY
attached_dev
The attached enet driver’s device instance ptr
mii_ts
Pointer to time stamper callbacks
mdix
Current crossover
mdix_ctrl
User setting of crossover
phy_link_change
Callback for phylink for notification of link change
adjust_link
Callback for the enet controller to respond to changes: in the link state.
macsec_ops
MACsec offloading ops.
Description
interrupts currently only supports enabled or disabled, but could be changed in the future to support enabling and disabling specific interrupts
Contains some infrastructure for polling and interrupt handling, as well as handling shifts in PHY hardware state
-
struct
phy_tdr_config
¶ Configuration of a TDR raw test
Definition
struct phy_tdr_config {
u32 first;
u32 last;
u32 step;
s8 pair;
};
Members
first
Distance for first data collection point
last
Distance for last data collection point
step
Step between data collection points
pair
Bitmap of cable pairs to collect data for
Description
A structure containing possible configuration parameters for a TDR cable test. The driver does not need to implement all the parameters, but should report what is actually used. All distances are in centimeters.
-
struct
phy_driver
¶ Driver structure for a particular PHY type
Definition
struct phy_driver {
struct mdio_driver_common mdiodrv;
u32 phy_id;
char *name;
u32 phy_id_mask;
const unsigned long * const features;
u32 flags;
const void *driver_data;
int (*soft_reset)(struct phy_device *phydev);
int (*config_init)(struct phy_device *phydev);
int (*probe)(struct phy_device *phydev);
int (*get_features)(struct phy_device *phydev);
int (*suspend)(struct phy_device *phydev);
int (*resume)(struct phy_device *phydev);
int (*config_aneg)(struct phy_device *phydev);
int (*aneg_done)(struct phy_device *phydev);
int (*read_status)(struct phy_device *phydev);
int (*config_intr)(struct phy_device *phydev);
irqreturn_t (*handle_interrupt)(struct phy_device *phydev);
void (*remove)(struct phy_device *phydev);
int (*match_phy_device)(struct phy_device *phydev);
int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol);
void (*link_change_notify)(struct phy_device *dev);
int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum);
int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val);
int (*read_page)(struct phy_device *dev);
int (*write_page)(struct phy_device *dev, int page);
int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo);
int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data);
int (*cable_test_start)(struct phy_device *dev);
int (*cable_test_tdr_start)(struct phy_device *dev, const struct phy_tdr_config *config);
int (*cable_test_get_status)(struct phy_device *dev, bool *finished);
int (*get_sset_count)(struct phy_device *dev);
void (*get_strings)(struct phy_device *dev, u8 *data);
void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data);
int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data);
int (*set_tunable)(struct phy_device *dev,struct ethtool_tunable *tuna, const void *data);
int (*set_loopback)(struct phy_device *dev, bool enable);
int (*get_sqi)(struct phy_device *dev);
int (*get_sqi_max)(struct phy_device *dev);
};
Members
mdiodrv
Data common to all MDIO devices
phy_id
The result of reading the UID registers of this PHY type, and ANDing them with the phy_id_mask. This driver only works for PHYs with IDs which match this field
name
The friendly name of this PHY type
phy_id_mask
Defines the important bits of the phy_id
features
A mandatory list of features (speed, duplex, etc) supported by this PHY
flags
A bitfield defining certain other features this PHY supports (like interrupts)
driver_data
Static driver data
soft_reset
Called to issue a PHY software reset
config_init
Called to initialize the PHY, including after a reset
probe
Called during discovery. Used to set up device-specific structures, if any
get_features
Probe the hardware to determine what abilities it has. Should only set phydev->supported.
suspend
Suspend the hardware, saving state if needed
resume
Resume the hardware, restoring state if needed
config_aneg
Configures the advertisement and resets autonegotiation if phydev->autoneg is on, forces the speed to the current settings in phydev if phydev->autoneg is off
aneg_done
Determines the auto negotiation result
read_status
Determines the negotiated speed and duplex
config_intr
Enables or disables interrupts. It should also clear any pending interrupts prior to enabling the IRQs and after disabling them.
handle_interrupt
Override default interrupt handling
remove
Clears up any memory if needed
match_phy_device
Returns true if this is a suitable driver for the given phydev. If NULL, matching is based on phy_id and phy_id_mask.
set_wol
Some devices (e.g. qnap TS-119P II) require PHY register changes to enable Wake on LAN, so set_wol is provided to be called in the ethernet driver’s set_wol function.
get_wol
See set_wol, but for checking whether Wake on LAN is enabled.
link_change_notify
Called to inform a PHY device driver when the core is about to change the link state. This callback is supposed to be used as fixup hook for drivers that need to take action when the link state changes. Drivers are by no means allowed to mess with the PHY device structure in their implementations.
read_mmd
PHY specific driver override for reading a MMD register. This function is optional for PHY specific drivers. When not provided, the default MMD read function will be used by
phy_read_mmd()
, which will use either a direct read for Clause 45 PHYs or an indirect read for Clause 22 PHYs. devnum is the MMD device number within the PHY device, regnum is the register within the selected MMD device.write_mmd
PHY specific driver override for writing a MMD register. This function is optional for PHY specific drivers. When not provided, the default MMD write function will be used by
phy_write_mmd()
, which will use either a direct write for Clause 45 PHYs, or an indirect write for Clause 22 PHYs. devnum is the MMD device number within the PHY device, regnum is the register within the selected MMD device. val is the value to be written.read_page
Return the current PHY register page number
write_page
Set the current PHY register page number
module_info
Get the size and type of the eeprom contained within a plug-in module
module_eeprom
Get the eeprom information from the plug-in module
cable_test_start
Start a cable test
cable_test_tdr_start
Start a raw TDR cable test
cable_test_get_status
Once per second, or on interrupt, request the status of the test.
get_sset_count
Number of statistic counters
get_strings
Names of the statistic counters
get_stats
Return the statistic counter values
get_tunable
Return the value of a tunable
set_tunable
Set the value of a tunable
set_loopback
Set the loopback mood of the PHY
get_sqi
Get the signal quality indication
get_sqi_max
Get the maximum signal quality indication
Description
All functions are optional. If config_aneg or read_status are not implemented, the phy core uses the genphy versions. Note that none of these functions should be called from interrupt time. The goal is for the bus read/write functions to be able to block when the bus transaction is happening, and be freed up by an interrupt (The MPC85xx has this ability, though it is not currently supported in the driver).
-
bool
phy_is_started
(struct phy_device *phydev)¶ Convenience function to check whether PHY is started
Parameters
struct phy_device *phydev
The phy_device struct
-
int
phy_read
(struct phy_device *phydev, u32 regnum)¶ Convenience function for reading a given PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to read
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
__phy_read
(struct phy_device *phydev, u32 regnum)¶ convenience function for reading a given PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to read
Description
The caller must have taken the MDIO bus lock.
-
int
phy_write
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for writing a given PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
value to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
__phy_write
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for writing a given PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
value to write to regnum
Description
The caller must have taken the MDIO bus lock.
-
int
__phy_modify_changed
(struct phy_device *phydev, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a PHY register
Parameters
struct phy_device *phydev
a pointer to a
struct phy_device
u32 regnum
register number
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
Description
Unlocked helper function which allows a PHY register to be modified as new register value = (old register value & ~mask) | set
Returns negative errno, 0 if there was no change, and 1 in case of change
-
phy_read_mmd_poll_timeout
(phydev, devaddr, regnum, val, cond, sleep_us, timeout_us, sleep_before_read)¶ Periodically poll a PHY register until a condition is met or a timeout occurs
Parameters
phydev
The phy_device struct
devaddr
The MMD to read from
regnum
The register on the MMD to read
val
Variable to read the register into
cond
Break condition (usually involving val)
sleep_us
Maximum time to sleep between reads in us (0 tight-loops). Should be less than ~20ms since usleep_range is used (see delays - Information on the various kernel delay / sleep mechanisms).
timeout_us
Timeout in us, 0 means never timeout
sleep_before_read
if it is true, sleep sleep_us before read. Returns 0 on success and -ETIMEDOUT upon a timeout. In either case, the last read value at args is stored in val. Must not be called from atomic context if sleep_us or timeout_us are used.
-
int
__phy_set_bits
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for setting bits in a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
bits to set
Description
The caller must have taken the MDIO bus lock.
-
int
__phy_clear_bits
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for clearing bits in a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
bits to clear
Description
The caller must have taken the MDIO bus lock.
-
int
phy_set_bits
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for setting bits in a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
bits to set
-
int
phy_clear_bits
(struct phy_device *phydev, u32 regnum, u16 val)¶ Convenience function for clearing bits in a PHY register
Parameters
struct phy_device *phydev
the phy_device struct
u32 regnum
register number to write
u16 val
bits to clear
-
int
__phy_set_bits_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for setting bits in a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 val
bits to set
Description
The caller must have taken the MDIO bus lock.
-
int
__phy_clear_bits_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for clearing bits in a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 val
bits to clear
Description
The caller must have taken the MDIO bus lock.
-
int
phy_set_bits_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for setting bits in a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 val
bits to set
-
int
phy_clear_bits_mmd
(struct phy_device *phydev, int devad, u32 regnum, u16 val)¶ Convenience function for clearing bits in a register on MMD
Parameters
struct phy_device *phydev
the phy_device struct
int devad
the MMD containing register to modify
u32 regnum
register number to modify
u16 val
bits to clear
-
bool
phy_interrupt_is_valid
(struct phy_device *phydev)¶ Convenience function for testing a given PHY irq
Parameters
struct phy_device *phydev
the phy_device struct
NOTE
must be kept in sync with addition/removal of PHY_POLL and PHY_MAC_INTERRUPT
-
bool
phy_polling_mode
(struct phy_device *phydev)¶ Convenience function for testing whether polling is used to detect PHY status changes
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_has_hwtstamp
(struct phy_device *phydev)¶ Tests whether a PHY time stamp configuration.
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_has_rxtstamp
(struct phy_device *phydev)¶ Tests whether a PHY supports receive time stamping.
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_has_tsinfo
(struct phy_device *phydev)¶ Tests whether a PHY reports time stamping and/or PTP hardware clock capabilities.
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_has_txtstamp
(struct phy_device *phydev)¶ Tests whether a PHY supports transmit time stamping.
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_is_internal
(struct phy_device *phydev)¶ Convenience function for testing if a PHY is internal
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_on_sfp
(struct phy_device *phydev)¶ Convenience function for testing if a PHY is on an SFP module
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_interface_mode_is_rgmii
(phy_interface_t mode)¶ Convenience function for testing if a PHY interface mode is RGMII (all variants)
Parameters
phy_interface_t mode
the
phy_interface_t
enum
-
bool
phy_interface_mode_is_8023z
(phy_interface_t mode)¶ does the PHY interface mode use 802.3z negotiation
Parameters
phy_interface_t mode
one of
enum phy_interface_t
Description
Returns true if the PHY interface mode uses the 16-bit negotiation word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding)
-
bool
phy_interface_is_rgmii
(struct phy_device *phydev)¶ Convenience function for testing if a PHY interface is RGMII (all variants)
Parameters
struct phy_device *phydev
the phy_device struct
-
bool
phy_is_pseudo_fixed_link
(struct phy_device *phydev)¶ Convenience function for testing if this PHY is the CPU port facing side of an Ethernet switch, or similar.
Parameters
struct phy_device *phydev
the phy_device struct
-
phy_module_driver
(__phy_drivers, __count)¶ Helper macro for registering PHY drivers
Parameters
__phy_drivers
array of PHY drivers to register
__count
Numbers of members in array
Description
Helper macro for PHY drivers which do not do anything special in module
init/exit. Each module may only use this macro once, and calling it
replaces module_init()
and module_exit()
.
-
int
phy_register_fixup
(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *))¶ creates a new phy_fixup and adds it to the list
Parameters
const char *bus_id
A string which matches phydev->mdio.dev.bus_id (or PHY_ANY_ID)
u32 phy_uid
Used to match against phydev->phy_id (the UID of the PHY) It can also be PHY_ANY_UID
u32 phy_uid_mask
Applied to phydev->phy_id and fixup->phy_uid before comparison
int (*run)(struct phy_device *)
The actual code to be run when a matching PHY is found
-
int
phy_unregister_fixup
(const char *bus_id, u32 phy_uid, u32 phy_uid_mask)¶ remove a phy_fixup from the list
Parameters
const char *bus_id
A string matches fixup->bus_id (or PHY_ANY_ID) in phy_fixup_list
u32 phy_uid
A phy id matches fixup->phy_id (or PHY_ANY_UID) in phy_fixup_list
u32 phy_uid_mask
Applied to phy_uid and fixup->phy_uid before comparison
-
struct phy_device *
get_phy_device
(struct mii_bus *bus, int addr, bool is_c45)¶ reads the specified PHY device and returns its phy_device struct
Parameters
struct mii_bus *bus
the target MII bus
int addr
PHY address on the MII bus
bool is_c45
If true the PHY uses the 802.3 clause 45 protocol
Description
Probe for a PHY at addr on bus.
When probing for a clause 22 PHY, then read the ID registers. If we find
a valid ID, allocate and return a struct phy_device
.
When probing for a clause 45 PHY, read the “devices in package” registers.
If the “devices in package” appears valid, read the ID registers for each
MMD, allocate and return a struct phy_device
.
Returns an allocated struct phy_device
on success, -ENODEV
if there is
no PHY present, or -EIO
on bus access error.
-
int
phy_device_register
(struct phy_device *phydev)¶ Register the phy device on the MDIO bus
Parameters
struct phy_device *phydev
phy_device structure to be added to the MDIO bus
-
void
phy_device_remove
(struct phy_device *phydev)¶ Remove a previously registered phy device from the MDIO bus
Parameters
struct phy_device *phydev
phy_device structure to remove
Description
This doesn’t free the phy_device itself, it merely reverses the effects
of phy_device_register()
. Use phy_device_free() to free the device
after calling this function.
-
int
phy_get_c45_ids
(struct phy_device *phydev)¶ Read 802.3-c45 IDs for phy device.
Parameters
struct phy_device *phydev
phy_device structure to read 802.3-c45 IDs
Description
Returns zero on success, -EIO
on bus access error, or -ENODEV
if
the “devices in package” is invalid.
-
struct phy_device *
phy_find_first
(struct mii_bus *bus)¶ finds the first PHY device on the bus
Parameters
struct mii_bus *bus
the target MII bus
-
int
phy_connect_direct
(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface)¶ connect an ethernet device to a specific phy_device
Parameters
struct net_device *dev
the network device to connect
struct phy_device *phydev
the pointer to the phy device
void (*handler)(struct net_device *)
callback function for state change notifications
phy_interface_t interface
PHY device’s interface
-
struct phy_device *
phy_connect
(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface)¶ connect an ethernet device to a PHY device
Parameters
struct net_device *dev
the network device to connect
const char *bus_id
the id string of the PHY device to connect
void (*handler)(struct net_device *)
callback function for state change notifications
phy_interface_t interface
PHY device’s interface
Description
- Convenience function for connecting ethernet
devices to PHY devices. The default behavior is for the PHY infrastructure to handle everything, and only notify the connected driver when the link status changes. If you don’t want, or can’t use the provided functionality, you may choose to call only the subset of functions which provide the desired functionality.
-
void
phy_disconnect
(struct phy_device *phydev)¶ disable interrupts, stop state machine, and detach a PHY device
Parameters
struct phy_device *phydev
target phy_device struct
-
void
phy_sfp_attach
(void *upstream, struct sfp_bus *bus)¶ attach the SFP bus to the PHY upstream network device
Parameters
void *upstream
pointer to the phy device
struct sfp_bus *bus
sfp bus representing cage being attached
Description
This is used to fill in the sfp_upstream_ops .attach member.
-
void
phy_sfp_detach
(void *upstream, struct sfp_bus *bus)¶ detach the SFP bus from the PHY upstream network device
Parameters
void *upstream
pointer to the phy device
struct sfp_bus *bus
sfp bus representing cage being attached
Description
This is used to fill in the sfp_upstream_ops .detach member.
-
int
phy_sfp_probe
(struct phy_device *phydev, const struct sfp_upstream_ops *ops)¶ probe for a SFP cage attached to this PHY device
Parameters
struct phy_device *phydev
Pointer to phy_device
const struct sfp_upstream_ops *ops
SFP’s upstream operations
-
int
phy_attach_direct
(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface)¶ attach a network device to a given PHY device pointer
Parameters
struct net_device *dev
network device to attach
struct phy_device *phydev
Pointer to phy_device to attach
u32 flags
PHY device’s dev_flags
phy_interface_t interface
PHY device’s interface
Description
- Called by drivers to attach to a particular PHY
device. The phy_device is found, and properly hooked up to the phy_driver. If no driver is attached, then a generic driver is used. The phy_device is given a ptr to the attaching device, and given a callback for link status change. The phy_device is returned to the attaching driver. This function takes a reference on the phy device.
-
struct phy_device *
phy_attach
(struct net_device *dev, const char *bus_id, phy_interface_t interface)¶ attach a network device to a particular PHY device
Parameters
struct net_device *dev
network device to attach
const char *bus_id
Bus ID of PHY device to attach
phy_interface_t interface
PHY device’s interface
Description
- Same as phy_attach_direct() except that a PHY bus_id
string is passed instead of a pointer to a
struct phy_device
.
-
int
phy_package_join
(struct phy_device *phydev, int addr, size_t priv_size)¶ join a common PHY group
Parameters
struct phy_device *phydev
target phy_device struct
int addr
cookie and PHY address for global register access
size_t priv_size
if non-zero allocate this amount of bytes for private data
Description
This joins a PHY group and provides a shared storage for all phydevs in this group. This is intended to be used for packages which contain more than one PHY, for example a quad PHY transceiver.
The addr parameter serves as a cookie which has to have the same value for all members of one group and as a PHY address to access generic registers of a PHY package. Usually, one of the PHY addresses of the different PHYs in the package provides access to these global registers. The address which is given here, will be used in the phy_package_read() and phy_package_write() convenience functions. If your PHY doesn’t have global registers you can just pick any of the PHY addresses.
This will set the shared pointer of the phydev to the shared storage. If this is the first call for a this cookie the shared storage will be allocated. If priv_size is non-zero, the given amount of bytes are allocated for the priv member.
Returns < 1 on error, 0 on success. Esp. calling phy_package_join()
with the same cookie but a different priv_size is an error.
-
void
phy_package_leave
(struct phy_device *phydev)¶ leave a common PHY group
Parameters
struct phy_device *phydev
target phy_device struct
Description
This leaves a PHY group created by phy_package_join()
. If this phydev
was the last user of the shared data between the group, this data is
freed. Resets the phydev->shared pointer to NULL.
-
int
devm_phy_package_join
(struct device *dev, struct phy_device *phydev, int addr, size_t priv_size)¶ resource managed
phy_package_join()
Parameters
struct device *dev
device that is registering this PHY package
struct phy_device *phydev
target phy_device struct
int addr
cookie and PHY address for global register access
size_t priv_size
if non-zero allocate this amount of bytes for private data
Description
Managed phy_package_join()
. Shared storage fetched by this function,
phy_package_leave()
is automatically called on driver detach. See
phy_package_join()
for more information.
-
void
phy_detach
(struct phy_device *phydev)¶ detach a PHY device from its network device
Parameters
struct phy_device *phydev
target phy_device struct
Description
This detaches the phy device from its network device and the phy
driver, and drops the reference count taken in phy_attach_direct()
.
-
int
phy_reset_after_clk_enable
(struct phy_device *phydev)¶ perform a PHY reset if needed
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Some PHYs are known to need a reset after their refclk was
enabled. This function evaluates the flags and perform the reset if it’s needed. Returns < 0 on error, 0 if the phy wasn’t reset and 1 if the phy was reset.
-
int
genphy_config_eee_advert
(struct phy_device *phydev)¶ disable unwanted eee mode advertisement
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Writes MDIO_AN_EEE_ADV after disabling unsupported energy
efficent ethernet modes. Returns 0 if the PHY’s advertisement hasn’t changed, and 1 if it has changed.
-
int
genphy_setup_forced
(struct phy_device *phydev)¶ configures/forces speed/duplex from phydev
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Configures MII_BMCR to force speed/duplex
to the values in phydev. Assumes that the values are valid. Please see
phy_sanitize_settings()
.
-
int
genphy_restart_aneg
(struct phy_device *phydev)¶ Enable and Restart Autonegotiation
Parameters
struct phy_device *phydev
target phy_device struct
-
int
genphy_check_and_restart_aneg
(struct phy_device *phydev, bool restart)¶ Enable and restart auto-negotiation
Parameters
struct phy_device *phydev
target phy_device struct
bool restart
whether aneg restart is requested
Description
Check, and restart auto-negotiation if needed.
-
int
__genphy_config_aneg
(struct phy_device *phydev, bool changed)¶ restart auto-negotiation or write BMCR
Parameters
struct phy_device *phydev
target phy_device struct
bool changed
whether autoneg is requested
Description
- If auto-negotiation is enabled, we configure the
advertising, and then restart auto-negotiation. If it is not enabled, then we write the BMCR.
-
int
genphy_c37_config_aneg
(struct phy_device *phydev)¶ restart auto-negotiation or write BMCR
Parameters
struct phy_device *phydev
target phy_device struct
Description
- If auto-negotiation is enabled, we configure the
advertising, and then restart auto-negotiation. If it is not enabled, then we write the BMCR. This function is intended for use with Clause 37 1000Base-X mode.
-
int
genphy_aneg_done
(struct phy_device *phydev)¶ return auto-negotiation status
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Reads the status register and returns 0 either if
auto-negotiation is incomplete, or if there was an error. Returns BMSR_ANEGCOMPLETE if auto-negotiation is done.
-
int
genphy_update_link
(struct phy_device *phydev)¶ update link status in phydev
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Update the value in phydev->link to reflect the
current link value. In order to do this, we need to read the status register twice, keeping the second value.
-
int
genphy_read_status_fixed
(struct phy_device *phydev)¶ read the link parameters for !aneg mode
Parameters
struct phy_device *phydev
target phy_device struct
Description
Read the current duplex and speed state for a PHY operating with autonegotiation disabled.
-
int
genphy_read_status
(struct phy_device *phydev)¶ check the link status and update current link state
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Check the link, then figure out the current state
by comparing what we advertise with what the link partner advertises. Start by checking the gigabit possibilities, then move on to 10/100.
-
int
genphy_c37_read_status
(struct phy_device *phydev)¶ check the link status and update current link state
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Check the link, then figure out the current state
by comparing what we advertise with what the link partner advertises. This function is for Clause 37 1000Base-X mode.
-
int
genphy_soft_reset
(struct phy_device *phydev)¶ software reset the PHY via BMCR_RESET bit
Parameters
struct phy_device *phydev
target phy_device struct
Description
Perform a software PHY reset using the standard BMCR_RESET bit and poll for the reset bit to be cleared.
Return
0 on success, < 0 on failure
-
int
genphy_read_abilities
(struct phy_device *phydev)¶ read PHY abilities from Clause 22 registers
Parameters
struct phy_device *phydev
target phy_device struct
Description
Reads the PHY’s abilities and populates phydev->supported accordingly.
Return
0 on success, < 0 on failure
-
void
phy_remove_link_mode
(struct phy_device *phydev, u32 link_mode)¶ Remove a supported link mode
Parameters
struct phy_device *phydev
phy_device structure to remove link mode from
u32 link_mode
Link mode to be removed
Description
Some MACs don’t support all link modes which the PHY does. e.g. a 1G MAC often does not support 1000Half. Add a helper to remove a link mode.
-
void
phy_advertise_supported
(struct phy_device *phydev)¶ Advertise all supported modes
Parameters
struct phy_device *phydev
target phy_device struct
Description
Called to advertise all supported modes, doesn’t touch pause mode advertising.
-
void
phy_support_sym_pause
(struct phy_device *phydev)¶ Enable support of symmetrical pause
Parameters
struct phy_device *phydev
target phy_device struct
Description
Called by the MAC to indicate is supports symmetrical Pause, but not asym pause.
-
void
phy_support_asym_pause
(struct phy_device *phydev)¶ Enable support of asym pause
Parameters
struct phy_device *phydev
target phy_device struct
Description
Called by the MAC to indicate is supports Asym Pause.
-
void
phy_set_sym_pause
(struct phy_device *phydev, bool rx, bool tx, bool autoneg)¶ Configure symmetric Pause
Parameters
struct phy_device *phydev
target phy_device struct
bool rx
Receiver Pause is supported
bool tx
Transmit Pause is supported
bool autoneg
Auto neg should be used
Description
Configure advertised Pause support depending on if receiver pause and pause auto neg is supported. Generally called from the set_pauseparam .ndo.
-
void
phy_set_asym_pause
(struct phy_device *phydev, bool rx, bool tx)¶ Configure Pause and Asym Pause
Parameters
struct phy_device *phydev
target phy_device struct
bool rx
Receiver Pause is supported
bool tx
Transmit Pause is supported
Description
Configure advertised Pause support depending on if transmit and receiver pause is supported. If there has been a change in adverting, trigger a new autoneg. Generally called from the set_pauseparam .ndo.
-
bool
phy_validate_pause
(struct phy_device *phydev, struct ethtool_pauseparam *pp)¶ Test if the PHY/MAC support the pause configuration
Parameters
struct phy_device *phydev
phy_device struct
struct ethtool_pauseparam *pp
requested pause configuration
Description
Test if the PHY/MAC combination supports the Pause configuration the user is requesting. Returns True if it is supported, false otherwise.
-
void
phy_get_pause
(struct phy_device *phydev, bool *tx_pause, bool *rx_pause)¶ resolve negotiated pause modes
Parameters
struct phy_device *phydev
phy_device struct
bool *tx_pause
pointer to bool to indicate whether transmit pause should be enabled.
bool *rx_pause
pointer to bool to indicate whether receive pause should be enabled.
Description
Resolve and return the flow control modes according to the negotiation result. This includes checking that we are operating in full duplex mode. See linkmode_resolve_pause() for further details.
-
s32
phy_get_internal_delay
(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx)¶ returns the index of the internal delay
Parameters
struct phy_device *phydev
phy_device struct
struct device *dev
pointer to the devices device struct
const int *delay_values
array of delays the PHY supports
int size
the size of the delay array
bool is_rx
boolean to indicate to get the rx internal delay
Description
Returns the index within the array of internal delay passed in. If the device property is not present then the interface type is checked if the interface defines use of internal delay then a 1 is returned otherwise a 0 is returned. The array must be in ascending order. If PHY does not have an ascending order array then size = 0 and the value of the delay property is returned. Return -EINVAL if the delay is invalid or cannot be found.
-
struct mdio_device *
fwnode_mdio_find_device
(struct fwnode_handle *fwnode)¶ Given a fwnode, find the mdio_device
Parameters
struct fwnode_handle *fwnode
pointer to the mdio_device’s fwnode
Description
If successful, returns a pointer to the mdio_device with the embedded
struct device
refcount incremented by one, or NULL on failure.
The caller should call put_device()
on the mdio_device after its use.
-
struct phy_device *
fwnode_phy_find_device
(struct fwnode_handle *phy_fwnode)¶ For provided phy_fwnode, find phy_device.
Parameters
struct fwnode_handle *phy_fwnode
Pointer to the phy’s fwnode.
Description
If successful, returns a pointer to the phy_device with the embedded
struct device
refcount incremented by one, or NULL on failure.
-
struct phy_device *
device_phy_find_device
(struct device *dev)¶ For the given device, get the phy_device
Parameters
struct device *dev
Pointer to the given device
Description
Refer return conditions of fwnode_phy_find_device()
.
-
struct fwnode_handle *
fwnode_get_phy_node
(struct fwnode_handle *fwnode)¶ Get the phy_node using the named reference.
Parameters
struct fwnode_handle *fwnode
Pointer to fwnode from which phy_node has to be obtained.
Description
Refer return conditions of fwnode_find_reference(). For ACPI, only “phy-handle” is supported. Legacy DT properties “phy” and “phy-device” are not supported in ACPI. DT supports all the three named references to the phy node.
-
int
phy_driver_register
(struct phy_driver *new_driver, struct module *owner)¶ register a phy_driver with the PHY layer
Parameters
struct phy_driver *new_driver
new phy_driver to register
struct module *owner
module owning this PHY
-
int
get_phy_c45_ids
(struct mii_bus *bus, int addr, struct phy_c45_device_ids *c45_ids)¶ reads the specified addr for its 802.3-c45 IDs.
Parameters
struct mii_bus *bus
the target MII bus
int addr
PHY address on the MII bus
struct phy_c45_device_ids *c45_ids
where to store the c45 ID information.
Description
Read the PHY “devices in package”. If this appears to be valid, read the PHY identifiers for each device. Return the “devices in package” and identifiers in c45_ids.
Returns zero on success, -EIO
on bus access error, or -ENODEV
if
the “devices in package” is invalid.
-
int
get_phy_c22_id
(struct mii_bus *bus, int addr, u32 *phy_id)¶ reads the specified addr for its clause 22 ID.
Parameters
struct mii_bus *bus
the target MII bus
int addr
PHY address on the MII bus
u32 *phy_id
where to store the ID retrieved.
Description
Read the 802.3 clause 22 PHY ID from the PHY at addr on the bus,
placing it in phy_id. Return zero on successful read and the ID is
valid, -EIO
on bus access error, or -ENODEV
if no device responds
or invalid ID.
-
void
phy_prepare_link
(struct phy_device *phydev, void (*handler)(struct net_device *))¶ prepares the PHY layer to monitor link status
Parameters
struct phy_device *phydev
target phy_device struct
void (*handler)(struct net_device *)
callback function for link status change notifications
Description
- Tells the PHY infrastructure to handle the
gory details on monitoring link status (whether through polling or an interrupt), and to call back to the connected device driver when the link status changes. If you want to monitor your own link state, don’t call this function.
-
int
phy_poll_reset
(struct phy_device *phydev)¶ Safely wait until a PHY reset has properly completed
Parameters
struct phy_device *phydev
The PHY device to poll
Description
- According to IEEE 802.3, Section 2, Subsection 22.2.4.1.1, as
published in 2008, a PHY reset may take up to 0.5 seconds. The MII BMCR register must be polled until the BMCR_RESET bit clears.
Furthermore, any attempts to write to PHY registers may have no effect or even generate MDIO bus errors until this is complete.
Some PHYs (such as the Marvell 88E1111) don’t entirely conform to the standard and do not fully reset after the BMCR_RESET bit is set, and may even REQUIRE a soft-reset to properly restart autonegotiation. In an effort to support such broken PHYs, this function is separate from the standard phy_init_hw() which will zero all the other bits in the BMCR and reapply all driver-specific and board-specific fixups.
-
int
genphy_config_advert
(struct phy_device *phydev)¶ sanitize and advertise auto-negotiation parameters
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Writes MII_ADVERTISE with the appropriate values,
after sanitizing the values to make sure we only advertise what is supported. Returns < 0 on error, 0 if the PHY’s advertisement hasn’t changed, and > 0 if it has changed.
-
int
genphy_c37_config_advert
(struct phy_device *phydev)¶ sanitize and advertise auto-negotiation parameters
Parameters
struct phy_device *phydev
target phy_device struct
Description
- Writes MII_ADVERTISE with the appropriate values,
after sanitizing the values to make sure we only advertise what is supported. Returns < 0 on error, 0 if the PHY’s advertisement hasn’t changed, and > 0 if it has changed. This function is intended for Clause 37 1000Base-X mode.
Parameters
struct device *dev
device to probe and init
Description
- Take care of setting up the phy_device structure,
set the state to READY (the driver’s init function should set it to STARTING if needed).
Parameters
size_t size
extra amount of memory to allocate for private storage. If non-zero, then bus->priv is points to that memory.
Description
called by a bus driver to allocate an mii_bus structure to fill in.
-
struct mii_bus *
mdio_find_bus
(const char *mdio_name)¶ Given the name of a mdiobus, find the mii_bus.
Parameters
const char *mdio_name
The name of a mdiobus.
Description
Returns a reference to the mii_bus, or NULL if none found. The
embedded struct device
will have its reference count incremented,
and this must be put_deviced’ed once the bus is finished with.
-
struct mii_bus *
of_mdio_find_bus
(struct device_node *mdio_bus_np)¶ Given an mii_bus node, find the mii_bus.
Parameters
struct device_node *mdio_bus_np
Pointer to the mii_bus.
Description
Returns a reference to the mii_bus, or NULL if none found. The
embedded struct device
will have its reference count incremented,
and this must be put once the bus is finished with.
Because the association of a device_node and mii_bus is made via of_mdiobus_register(), the mii_bus cannot be found before it is registered with of_mdiobus_register().
-
int
__mdiobus_register
(struct mii_bus *bus, struct module *owner)¶ bring up all the PHYs on a given bus and attach them to bus
Parameters
struct mii_bus *bus
target mii_bus
struct module *owner
module containing bus accessor functions
Description
- Called by a bus driver to bring up all the PHYs
on a given bus, and attach them to the bus. Drivers should use mdiobus_register() rather than
__mdiobus_register()
unless they need to pass a specific owner module. MDIO devices which are not PHYs will not be brought up by this function. They are expected to be explicitly listed in DT and instantiated by of_mdiobus_register().
Returns 0 on success or < 0 on error.
-
void
mdiobus_free
(struct mii_bus *bus)¶ free a
struct mii_bus
Parameters
struct mii_bus *bus
mii_bus to free
Description
This function releases the reference to the underlying device object in the mii_bus. If this is the last reference, the mii_bus will be freed.
-
struct phy_device *
mdiobus_scan
(struct mii_bus *bus, int addr)¶ scan a bus for MDIO devices.
Parameters
struct mii_bus *bus
mii_bus to scan
int addr
address on bus to scan
Description
This function scans the MDIO bus, looking for devices which can be identified using a vendor/product ID in registers 2 and 3. Not all MDIO devices have such registers, but PHY devices typically do. Hence this function assumes anything found is a PHY, or can be treated as a PHY. Other MDIO devices, such as switches, will probably not be found during the scan.
-
int
__mdiobus_read
(struct mii_bus *bus, int addr, u32 regnum)¶ Unlocked version of the mdiobus_read function
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to read
Description
Read a MDIO bus register. Caller must hold the mdio bus lock.
NOTE
MUST NOT be called from interrupt context.
-
int
__mdiobus_write
(struct mii_bus *bus, int addr, u32 regnum, u16 val)¶ Unlocked version of the mdiobus_write function
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to write
u16 val
value to write to regnum
Description
Write a MDIO bus register. Caller must hold the mdio bus lock.
NOTE
MUST NOT be called from interrupt context.
-
int
__mdiobus_modify_changed
(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set)¶ Unlocked version of the mdiobus_modify function
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to modify
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
Description
Read, modify, and if any change, write the register value back to the device. Any error returns a negative number.
NOTE
MUST NOT be called from interrupt context.
-
int
mdiobus_read_nested
(struct mii_bus *bus, int addr, u32 regnum)¶ Nested version of the mdiobus_read function
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to read
Description
In case of nested MDIO bus access avoid lockdep false positives by using mutex_lock_nested().
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
mdiobus_read
(struct mii_bus *bus, int addr, u32 regnum)¶ Convenience function for reading a given MII mgmt register
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to read
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
mdiobus_write_nested
(struct mii_bus *bus, int addr, u32 regnum, u16 val)¶ Nested version of the mdiobus_write function
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to write
u16 val
value to write to regnum
Description
In case of nested MDIO bus access avoid lockdep false positives by using mutex_lock_nested().
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
mdiobus_write
(struct mii_bus *bus, int addr, u32 regnum, u16 val)¶ Convenience function for writing a given MII mgmt register
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to write
u16 val
value to write to regnum
NOTE
MUST NOT be called from interrupt context, because the bus read/write functions may wait for an interrupt to conclude the operation.
-
int
mdiobus_modify
(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a given mdio device register
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to write
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
-
int
mdiobus_modify_changed
(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set)¶ Convenience function for modifying a given mdio device register and returning if it changed
Parameters
struct mii_bus *bus
the mii_bus struct
int addr
the phy address
u32 regnum
register number to write
u16 mask
bit mask of bits to clear
u16 set
bit mask of bits to set
Parameters
struct device *d
the target
struct device
that contains the mii_bus
Description
called when the last reference to an mii_bus is dropped, to free the underlying memory.
-
int
mdiobus_create_device
(struct mii_bus *bus, struct mdio_board_info *bi)¶ create a full MDIO device given a mdio_board_info structure
Parameters
struct mii_bus *bus
MDIO bus to create the devices on
struct mdio_board_info *bi
mdio_board_info structure describing the devices
Description
Returns 0 on success or < 0 on error.
-
int
mdio_bus_match
(struct device *dev, struct device_driver *drv)¶ determine if given MDIO driver supports the given MDIO device
Parameters
struct device *dev
target MDIO device
struct device_driver *drv
given MDIO driver
Description
- Given a MDIO device, and a MDIO driver, return 1 if
the driver supports the device. Otherwise, return 0. This may require calling the devices own match function, since different classes of MDIO devices have different match criteria.
PHYLINK¶
PHYLINK interfaces traditional network drivers with PHYLIB, fixed-links, and SFF modules (eg, hot-pluggable SFP) that may contain PHYs. PHYLINK provides management of the link state and link modes.
-
struct
phylink_link_state
¶ link state structure
Definition
struct phylink_link_state {
unsigned long advertising[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
unsigned long lp_advertising[BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS)];
phy_interface_t interface;
int speed;
int duplex;
int pause;
unsigned int link:1;
unsigned int an_enabled:1;
unsigned int an_complete:1;
};
Members
advertising
ethtool bitmask containing advertised link modes
lp_advertising
ethtool bitmask containing link partner advertised link modes
interface
link
typedef phy_interface_t
modespeed
link speed, one of the SPEED_* constants.
duplex
link duplex mode, one of DUPLEX_* constants.
pause
link pause state, described by MLO_PAUSE_* constants.
link
true if the link is up.
an_enabled
true if autonegotiation is enabled/desired.
an_complete
true if autonegotiation has completed.
-
struct
phylink_config
¶ PHYLINK configuration structure
Definition
struct phylink_config {
struct device *dev;
enum phylink_op_type type;
bool legacy_pre_march2020;
bool pcs_poll;
bool poll_fixed_state;
bool ovr_an_inband;
void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state);
unsigned long supported_interfaces[BITS_TO_LONGS(PHY_INTERFACE_MODE_MAX)];
unsigned long mac_capabilities;
};
Members
dev
a pointer to a
struct device
associated with the MACtype
operation type of PHYLINK instance
legacy_pre_march2020
driver has not been updated for March 2020 updates (See commit 7cceb599d15d (“net: phylink: avoid mac_config calls”)
pcs_poll
MAC PCS cannot provide link change interrupt
poll_fixed_state
if true, starts link_poll, if MAC link is at
MLO_AN_FIXED
mode.ovr_an_inband
if true, override PCS to MLO_AN_INBAND
get_fixed_state
callback to execute to determine the fixed link state, if MAC link is at
MLO_AN_FIXED
mode.supported_interfaces
bitmap describing which PHY_INTERFACE_MODE_xxx are supported by the MAC/PCS.
mac_capabilities
MAC pause/speed/duplex capabilities.
-
struct
phylink_mac_ops
¶ MAC operations structure.
Definition
struct phylink_mac_ops {
void (*validate)(struct phylink_config *config,unsigned long *supported, struct phylink_link_state *state);
struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, phy_interface_t interface);
void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state);
int (*mac_prepare)(struct phylink_config *config, unsigned int mode, phy_interface_t iface);
void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state);
int (*mac_finish)(struct phylink_config *config, unsigned int mode, phy_interface_t iface);
void (*mac_an_restart)(struct phylink_config *config);
void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface);
void (*mac_link_up)(struct phylink_config *config,struct phy_device *phy, unsigned int mode,phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause);
};
Members
validate
Validate and update the link configuration.
mac_select_pcs
Select a PCS for the interface mode.
mac_pcs_get_state
Read the current link state from the hardware.
mac_prepare
prepare for a major reconfiguration of the interface.
mac_config
configure the MAC for the selected mode and state.
mac_finish
finish a major reconfiguration of the interface.
mac_an_restart
restart 802.3z BaseX autonegotiation.
mac_link_down
take the link down.
mac_link_up
allow the link to come up.
Description
The individual methods are described more fully below.
-
void
validate
(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state)¶ Validate and update the link configuration
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned long *supported
ethtool bitmask for supported link modes.
struct phylink_link_state *state
a pointer to a
struct phylink_link_state
.
Description
Clear bits in the supported and state->advertising masks that are not supportable by the MAC.
Note that the PHY may be able to transform from one connection
technology to another, so, eg, don’t clear 1000BaseX just
because the MAC is unable to BaseX mode. This is more about
clearing unsupported speeds and duplex settings. The port modes
should not be cleared; phylink_set_port_modes()
will help with this.
If the state->interface mode is PHY_INTERFACE_MODE_1000BASEX
or PHY_INTERFACE_MODE_2500BASEX
, select the appropriate mode
based on state->advertising and/or state->speed and update
state->interface accordingly. See phylink_helper_basex_speed()
.
When config->supported_interfaces has been set, phylink will iterate over the supported interfaces to determine the full capability of the MAC. The validation function must not print errors if state->interface is set to an unexpected value.
When config->supported_interfaces is empty, phylink will call this
function with state->interface set to PHY_INTERFACE_MODE_NA
, and
expects the MAC driver to return all supported link modes.
If the state->interface mode is not supported, then the supported mask must be cleared.
-
struct phylink_pcs *
mac_select_pcs
(struct phylink_config *config, phy_interface_t interface)¶ Select a PCS for the interface mode.
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.phy_interface_t interface
PHY interface mode for PCS
Description
Return the struct phylink_pcs
for the specified interface mode, or
NULL if none is required, or an error pointer on error.
This must not modify any state. It is used to query which PCS should be used. Phylink will use this during validation to ensure that the configuration is valid, and when setting a configuration to internally set the PCS that will be used.
-
void
mac_pcs_get_state
(struct phylink_config *config, struct phylink_link_state *state)¶ Read the current inband link state from the hardware
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.struct phylink_link_state *state
a pointer to a
struct phylink_link_state
.
Description
Read the current inband link state from the MAC PCS, reporting the
current speed in state->speed, duplex mode in state->duplex, pause
mode in state->pause using the MLO_PAUSE_RX
and MLO_PAUSE_TX
bits,
negotiation completion state in state->an_complete, and link up state
in state->link. If possible, state->lp_advertising should also be
populated.
Note
This is a legacy method. This function will not be called unless
legacy_pre_march2020 is set in struct phylink_config
and there is no
PCS attached.
-
int
mac_prepare
(struct phylink_config *config, unsigned int mode, phy_interface_t iface)¶ prepare to change the PHY interface mode
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned int mode
one of
MLO_AN_FIXED
,MLO_AN_PHY
,MLO_AN_INBAND
.phy_interface_t iface
interface mode to switch to
Description
phylink will call this method at the beginning of a full initialisation of the link, which includes changing the interface mode or at initial startup time. It may be called for the current mode. The MAC driver should perform whatever actions are required, e.g. disabling the Serdes PHY.
This will be the first call in the sequence:
- mac_prepare()
- mac_config()
- pcs_config()
- possible pcs_an_restart()
- mac_finish()
Returns zero on success, or negative errno on failure which will be reported to the kernel log.
-
void
mac_config
(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state)¶ configure the MAC for the selected mode and state
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned int mode
one of
MLO_AN_FIXED
,MLO_AN_PHY
,MLO_AN_INBAND
.const struct phylink_link_state *state
a pointer to a
struct phylink_link_state
.
Description
Note - not all members of state are valid. In particular,
state->lp_advertising, state->link, state->an_complete are never
guaranteed to be correct, and so any mac_config()
implementation must
never reference these fields.
- (this requires a rewrite - please refer to mac_link_up() for situations
where the PCS and MAC are not tightly integrated.)
In all negotiation modes, as defined by mode, state->pause indicates the
pause settings which should be applied as follows. If MLO_PAUSE_AN
is not
set, MLO_PAUSE_TX
and MLO_PAUSE_RX
indicate whether the MAC should send
pause frames and/or act on received pause frames respectively. Otherwise,
the results of in-band negotiation/status from the MAC PCS should be used
to control the MAC pause mode settings.
The action performed depends on the currently selected mode:
MLO_AN_FIXED
,MLO_AN_PHY
:Configure for non-inband negotiation mode, where the link settings are completely communicated via
mac_link_up()
. The physical link protocol from the MAC is specified by state->interface.state->advertising may be used, but is not required.
Older drivers (prior to the
mac_link_up()
change) may use state->speed, state->duplex and state->pause to configure the MAC, but this is deprecated; such drivers should be converted to usemac_link_up()
.Other members of state must be ignored.
Valid state members: interface, advertising. Deprecated state members: speed, duplex, pause.
MLO_AN_INBAND
:place the link in an inband negotiation mode (such as 802.3z 1000base-X or Cisco SGMII mode depending on the state->interface mode). In both cases, link state management (whether the link is up or not) is performed by the MAC, and reported via the
mac_pcs_get_state()
callback. Changes in link state must be made by callingphylink_mac_change()
.Interface mode specific details are mentioned below.
If in 802.3z mode, the link speed is fixed, dependent on the state->interface. Duplex and pause modes are negotiated via the in-band configuration word. Advertised pause modes are set according to the state->an_enabled and state->advertising flags. Beware of MACs which only support full duplex at gigabit and higher speeds.
If in Cisco SGMII mode, the link speed and duplex mode are passed in the serial bitstream 16-bit configuration word, and the MAC should be configured to read these bits and acknowledge the configuration word. Nothing is advertised by the MAC. The MAC is responsible for reading the configuration word and configuring itself accordingly.
Valid state members: interface, an_enabled, pause, advertising.
Implementations are expected to update the MAC to reflect the requested settings - i.o.w., if nothing has changed between two calls, no action is expected. If only flow control settings have changed, flow control should be updated without taking the link down. This “update” behaviour is critical to avoid bouncing the link up status.
Note
For legacy March 2020 drivers (drivers with legacy_pre_march2020 set
in their phylnk_config
and which don’t have a PCS), this function will be
called on each link up event, and to also change the in-band advert. For
non-legacy drivers, it will only be called to reconfigure the MAC for a
“major” change in e.g. interface mode. It will not be called for changes
in speed, duplex or pause modes or to change the in-band advertisement.
In any case, it is strongly preferred that speed, duplex and pause settings
are handled in the mac_link_up()
method and not in this method.
-
int
mac_finish
(struct phylink_config *config, unsigned int mode, phy_interface_t iface)¶ finish a to change the PHY interface mode
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned int mode
one of
MLO_AN_FIXED
,MLO_AN_PHY
,MLO_AN_INBAND
.phy_interface_t iface
interface mode to switch to
Description
phylink will call this if it called mac_prepare()
to allow the MAC to
complete any necessary steps after the MAC and PCS have been configured
for the mode and iface. E.g. a MAC driver may wish to re-enable the
Serdes PHY here if it was previously disabled by mac_prepare()
.
Returns zero on success, or negative errno on failure which will be reported to the kernel log.
-
void
mac_an_restart
(struct phylink_config *config)¶ restart 802.3z BaseX autonegotiation
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.
Note
This is a legacy method. This function will not be called unless
legacy_pre_march2020 is set in struct phylink_config
and there is no
PCS attached.
-
void
mac_link_down
(struct phylink_config *config, unsigned int mode, phy_interface_t interface)¶ take the link down
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned int mode
link autonegotiation mode
phy_interface_t interface
link
typedef phy_interface_t
mode
Description
If mode is not an in-band negotiation mode (as defined by
phylink_autoneg_inband()), force the link down and disable any
Energy Efficient Ethernet MAC configuration. Interface type
selection must be done in mac_config()
.
-
void
mac_link_up
(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause)¶ allow the link to come up
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.struct phy_device *phy
any attached phy
unsigned int mode
link autonegotiation mode
phy_interface_t interface
link
typedef phy_interface_t
modeint speed
link speed
int duplex
link duplex
bool tx_pause
link transmit pause enablement status
bool rx_pause
link receive pause enablement status
Description
Configure the MAC for an established link.
speed, duplex, tx_pause and rx_pause indicate the finalised link settings, and should be used to configure the MAC block appropriately where these settings are not automatically conveyed from the PCS block, or if in-band negotiation (as defined by phylink_autoneg_inband(mode)) is disabled.
Note that when 802.3z in-band negotiation is in use, it is possible that the user wishes to override the pause settings, and this should be allowed when considering the implementation of this method.
If in-band negotiation mode is disabled, allow the link to come up. If
phy is non-NULL
, configure Energy Efficient Ethernet by calling
phy_init_eee()
and perform appropriate MAC configuration for EEE.
Interface type selection must be done in mac_config()
.
-
struct
phylink_pcs
¶ PHYLINK PCS instance
Definition
struct phylink_pcs {
const struct phylink_pcs_ops *ops;
bool poll;
};
Members
ops
a pointer to the
struct phylink_pcs_ops
structurepoll
poll the PCS for link changes
Description
This structure is designed to be embedded within the PCS private data, and will be passed between phylink and the PCS.
-
struct
phylink_pcs_ops
¶ MAC PCS operations structure.
Definition
struct phylink_pcs_ops {
int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state);
void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state);
int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode,phy_interface_t interface,const unsigned long *advertising, bool permit_pause_to_mac);
void (*pcs_an_restart)(struct phylink_pcs *pcs);
void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex);
};
Members
pcs_validate
validate the link configuration.
pcs_get_state
read the current MAC PCS link state from the hardware.
pcs_config
configure the MAC PCS for the selected mode and state.
pcs_an_restart
restart 802.3z BaseX autonegotiation.
pcs_link_up
program the PCS for the resolved link configuration (where necessary).
-
int
pcs_validate
(struct phylink_pcs *pcs, unsigned long *supported, const struct phylink_link_state *state)¶ validate the link configuration.
Parameters
struct phylink_pcs *pcs
a pointer to a
struct phylink_pcs
.unsigned long *supported
ethtool bitmask for supported link modes.
const struct phylink_link_state *state
a const pointer to a
struct phylink_link_state
.
Description
Validate the interface mode, and advertising’s autoneg bit, removing any
media ethtool link modes that would not be supportable from the supported
mask. Phylink will propagate the changes to the advertising mask. See the
struct phylink_mac_ops
validate()
method.
Returns -EINVAL if the interface mode/autoneg mode is not supported. Returns non-zero positive if the link state can be supported.
-
void
pcs_get_state
(struct phylink_pcs *pcs, struct phylink_link_state *state)¶ Read the current inband link state from the hardware
Parameters
struct phylink_pcs *pcs
a pointer to a
struct phylink_pcs
.struct phylink_link_state *state
a pointer to a
struct phylink_link_state
.
Description
Read the current inband link state from the MAC PCS, reporting the
current speed in state->speed, duplex mode in state->duplex, pause
mode in state->pause using the MLO_PAUSE_RX
and MLO_PAUSE_TX
bits,
negotiation completion state in state->an_complete, and link up state
in state->link. If possible, state->lp_advertising should also be
populated.
When present, this overrides mac_pcs_get_state()
in struct
phylink_mac_ops
.
-
int
pcs_config
(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising, bool permit_pause_to_mac)¶ Configure the PCS mode and advertisement
Parameters
struct phylink_pcs *pcs
a pointer to a
struct phylink_pcs
.unsigned int mode
one of
MLO_AN_FIXED
,MLO_AN_PHY
,MLO_AN_INBAND
.phy_interface_t interface
interface mode to be used
const unsigned long *advertising
adertisement ethtool link mode mask
bool permit_pause_to_mac
permit forwarding pause resolution to MAC
Description
Configure the PCS for the operating mode, the interface mode, and set the advertisement mask. permit_pause_to_mac indicates whether the hardware may forward the pause mode resolution to the MAC.
When operating in MLO_AN_INBAND
, inband should always be enabled,
otherwise inband should be disabled.
For SGMII, there is no advertisement from the MAC side, the PCS should be programmed to acknowledge the inband word from the PHY.
For 1000BASE-X, the advertisement should be programmed into the PCS.
For most 10GBASE-R, there is no advertisement.
-
void
pcs_an_restart
(struct phylink_pcs *pcs)¶ restart 802.3z BaseX autonegotiation
Parameters
struct phylink_pcs *pcs
a pointer to a
struct phylink_pcs
.
Description
When PCS ops are present, this overrides mac_an_restart()
in struct
phylink_mac_ops
.
-
void
pcs_link_up
(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex)¶ program the PCS for the resolved link configuration
Parameters
struct phylink_pcs *pcs
a pointer to a
struct phylink_pcs
.unsigned int mode
link autonegotiation mode
phy_interface_t interface
link
typedef phy_interface_t
modeint speed
link speed
int duplex
link duplex
Description
This call will be made just before mac_link_up()
to inform the PCS of
the resolved link parameters. For example, a PCS operating in SGMII
mode without in-band AN needs to be manually configured for the link
and duplex setting. Otherwise, this should be a no-op.
-
struct
phylink
¶ internal data type for phylink
Definition
struct phylink {
};
Members
-
void
phylink_set_port_modes
(unsigned long *mask)¶ set the port type modes in the ethtool mask
Parameters
unsigned long *mask
ethtool link mode mask
Description
Sets all the port type modes in the ethtool mask. MAC drivers should use this in their ‘validate’ callback.
-
void
phylink_get_linkmodes
(unsigned long *linkmodes, phy_interface_t interface, unsigned long mac_capabilities)¶ get acceptable link modes
Parameters
unsigned long *linkmodes
ethtool linkmode mask (must be already initialised)
phy_interface_t interface
phy interface mode defined by
typedef phy_interface_t
unsigned long mac_capabilities
bitmask of MAC capabilities
Description
Set all possible pause, speed and duplex linkmodes in linkmodes that are supported by the interface mode and mac_capabilities. linkmodes must have been initialised previously.
-
void
phylink_generic_validate
(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state)¶ generic
validate()
callback implementation
Parameters
struct phylink_config *config
a pointer to a
struct phylink_config
.unsigned long *supported
ethtool bitmask for supported link modes.
struct phylink_link_state *state
a pointer to a
struct phylink_link_state
.
Description
Generic implementation of the validate()
callback that MAC drivers can
use when they pass the range of supported interfaces and MAC capabilities.
This makes use of phylink_get_linkmodes()
.
-
struct phylink *
phylink_create
(struct phylink_config *config, struct fwnode_handle *fwnode, phy_interface_t iface, const struct phylink_mac_ops *mac_ops)¶ create a phylink instance
Parameters
struct phylink_config *config
a pointer to the target
struct phylink_config
struct fwnode_handle *fwnode
a pointer to a
struct fwnode_handle
describing the network interfacephy_interface_t iface
the desired