mbuf(9) - OpenBSD manual pages

NAME

m_copym, m_free, m_get, MGET, m_getclr, m_gethdr, m_removehdr, m_resethdr, m_calchdrlen, MGETHDR, m_prepend, M_PREPEND, m_pulldown, m_pullup, m_split, m_makespace, m_getptr, m_adj, m_copyback, m_defrag, m_freem, m_freemp, m_purge, m_reclaim, m_copydata, m_cat, m_devget, m_apply, MCLGET, MCLGETI, MEXTADD, m_align, M_READONLY, m_leadingspace, m_trailingspace, mtod, m_dup_pkt, m_dup_pkthdr — kernel memory management for networking protocols

SYNOPSIS

#include <sys/mbuf.h>

struct mbuf *
m_copym(struct mbuf *m, int off, int len, int wait);

struct mbuf *
m_free(struct mbuf *m);

struct mbuf *
m_get(int how, int type);

MGET(struct mbuf *m, int how, int type);

struct mbuf *
m_getclr(int how, int type);

void
m_removehdr(struct mbuf *m);

void
m_resethdr(struct mbuf *m);

void
m_calchdrlen(struct mbuf *m);

struct mbuf *
m_gethdr(int how, int type);

MGETHDR(struct mbuf *m, int how, int type);

struct mbuf *
m_prepend(struct mbuf *m, int len, int how);

M_PREPEND(struct mbuf *m, int plen, int how);

struct mbuf *
m_pulldown(struct mbuf *m, int off, int len, int *offp);

struct mbuf *
m_pullup(struct mbuf *n, int len);

struct mbuf *
m_split(struct mbuf *m0, int len0, int wait);

struct mbuf *
m_makespace(struct mbuf *m0, int skip, int hlen, int *off);

struct mbuf *
m_getptr(struct mbuf *m, int loc, int *off);

void
m_adj(struct mbuf *mp, int req_len);

int
m_copyback(struct mbuf *m0, int off, int len, const void *cp, int wait);

int
m_defrag(struct mbuf *m, int wait);

struct mbuf *
m_freem(struct mbuf *m);

struct mbuf *
m_freemp(struct mbuf **mp);

void
m_purge(struct mbuf *m);

void
m_reclaim(void);

void
m_copydata(struct mbuf *m, int off, int len, caddr_t cp);

void
m_cat(struct mbuf *m, struct mbuf *n);

struct mbuf *
m_devget(char *buf, int totlen, int off);

int
m_apply(struct mbuf *m, int off, int len, int (*func)(caddr_t, caddr_t, unsigned int), caddr_t fstate);

MCLGET(struct mbuf *m, int how);

struct mbuf *
MCLGETI(struct mbuf *m, int how, struct ifnet *ifp, int len);

MEXTADD(struct mbuf *m, caddr_t buf, u_int size, int flags, void (*free)(caddr_t, u_int, void *), void *arg);

void
m_align(struct mbuf *m, int len);

M_READONLY(struct mbuf *m);

int
m_leadingspace(struct mbuf *m);

int
m_trailingspace(struct mbuf *m);

struct mbuf *
m_dup_pkt(struct mbuf *m, u_int adj, int how);

int
m_dup_pkthdr(struct mbuf *to, struct mbuf *from, int how);

#define MSIZE           256

#define MLEN            (MSIZE - sizeof(struct m_hdr))
#define MHLEN           (MLEN - sizeof(struct pkthdr))

#define MAXMCLBYTES     (64 * 1024)
#define MINCLSIZE       (MHLEN + MLEN + 1)
#define M_MAXCOMPRESS   (MHLEN / 2)

#define MCLSHIFT        11

#define MCLBYTES        (1 << MCLSHIFT)
#define MCLOFSET        (MCLBYTES - 1)

#define mtod(m,t)       ((t)((m)->m_data))

struct m_hdr {
        struct  mbuf *mh_next;
        struct  mbuf *mh_nextpkt;
        caddr_t mh_data;
        u_int   mh_len;
        short   mh_type;
        u_short mh_flags;
#ifndef __LP64__
        u_int   mh_pad;
#endif
};

struct pkthdr {
	void			*ph_cookie;
	SLIST_HEAD(, m_tag)	 ph_tags;
	int64_t			 ph_timestamp;
	int			 len;
	u_int16_t		 ph_tagsset;
	u_int16_t		 ph_flowid;
	u_int16_t		 csum_flags;
	u_int16_t		 ether_vtag;
	u_int			 ph_rtableid;
	u_int			 ph_ifidx;
	u_int8_t		 ph_loopcnt;
	struct pkthdr_pf	 pf;
};

struct pkthdr_pf {
	struct pf_state_key *statekey;
	struct inpcb *inp;
	u_int32_t qid;
	u_int16_t tag;
	u_int8_t  flags;
	u_int8_t  routed;
	u_int8_t  prio;
	u_int8_t  pad[3];
};

struct mbuf_ext {
	caddr_t ext_buf;
	void	*ext_arg;
	u_int	ext_free_fn;
	u_int   ext_size;
	struct mbuf *ext_nextref;
	struct mbuf *ext_prevref;
};

struct mbuf {
        struct  m_hdr m_hdr;
        union {
                struct {
                        struct  pkthdr MH_pkthdr;
                        union {
                                struct  mbuf_ext MH_ext;
                                char    MH_databuf[MHLEN];
                        } MH_dat;
                } MH;
                char    M_databuf[MLEN];
        } M_dat;
};

#define m_next          m_hdr.mh_next
#define m_len           m_hdr.mh_len
#define m_data          m_hdr.mh_data
#define m_type          m_hdr.mh_type
#define m_flags         m_hdr.mh_flags
#define m_nextpkt       m_hdr.mh_nextpkt
#define m_pkthdr        M_dat.MH.MH_pkthdr
#define m_ext           M_dat.MH.MH_dat.MH_ext
#define m_pktdat        M_dat.MH.MH_dat.MH_databuf
#define m_dat           M_dat.M_databuf

DESCRIPTION

The mbuf functions provide a way to manage the memory buffers used by the kernel's networking subsystem. Several functions and macros are used to allocate and deallocate mbufs, but also to get, inject, remove, copy, modify, prepend or append data inside these mbufs. The size of an mbuf is defined by MSIZE.

An mbuf structure is defined as an m_hdr structure followed by a union. The header contains the following elements:

mh_next: A pointer to the next mbuf in the mbuf chain.
mh_nextpkt: A pointer to the next mbuf chain (i.e., packet) in the queue.
mh_data: Indicates the address of the beginning of data in the mbuf.
mh_len: Indicates the amount of data in the mbuf.
mh_type: Indicates the type of data contained in the mbuf (see below).
mh_flags: Flags (see below).

The mh_type variable can take the following values:

MT_FREE: the mbuf should be on the free list.
MT_DATA: the data in the mbuf was dynamically allocated.
MT_HEADER: the data contains a packet header.
MT_SONAME: the data is a socket name.
MT_SOOPTS: the data are socket options.
MT_FTABLE: the data is a fragment reassembly header.
MT_CONTROL: the mbuf contains extra-data protocol message.
MT_OOBDATA: the data consists of out-of-band data.

The mh_flags variable can take the following values:

M_EXT: mbuf has associated external storage.
M_PKTHDR: the mbuf is the first that forms a packet.
M_EOR: end of record.
M_EXTWR: external storage is writable.
M_PROTO1: protocol-specific.
M_VLANTAG: m_pkthdr.ether_vtag variable is valid.
M_LOOP: packet has been sent from local machine.
M_ACAST: received as IPv6 anycast.
M_BCAST: packet sent/received as link-level broadcast.
M_MCAST: packet sent/received as link-level multicast.
M_CONF: packet was encrypted (ESP-transport).
M_AUTH: packet was authenticated (AH or ESP).
M_TUNNEL: header was IP-in-IP encapsulated by tunnel mode IPsec.
M_ZEROIZE: Zero the data part of the mbufs in the mbuf chain pointed to by m_free.
M_COMP: header was decompressed.
M_LINK0: link layer specific flag.

An external cluster is used when the data to hold in the mbuf is large. The size of an external cluster is between MCLBYTES and MAXMCLBYTES. A cluster should be used when the size of the data reach MINCLSIZE (the minimum size to be held by an external cluster).

The combination of the M_EXT and M_PKTHDR flags give four types of mbuf. When none of these constants are in use, the mbuf is a "normal" one, where the data part of the mbuf has the following elements:

m_dat: buffer holding the data (size MLEN).

When only M_PKTHDR is set, the data contained in the mbuf is a packet header. The data itself is contained in the mbuf (just like the previous case), but part of the mbuf is used to store a packet header. The data part has then the following elements:

m_pkthdr: packet header, containing the length of the data, a pointer to the interface on which the data was received, checksum information and list of mbuf_tags(9).
m_pktdat: buffer holding the data (size MHLEN).

The m_pkthdr.csum_flags variable can take the following values:

M_IPV4_CSUM_OUT: IPv4 checksum needed.
M_TCP_CSUM_OUT: TCP checksum needed.
M_UDP_CSUM_OUT: UDP checksum needed.
M_ICMP_CSUM_OUT: ICMP/ICMPv6 checksum needed.
M_IPV4_CSUM_IN_OK: IPv4 checksum verified.
M_IPV4_CSUM_IN_BAD: IPv4 checksum bad.
M_TCP_CSUM_IN_OK: TCP checksum verified.
M_TCP_CSUM_IN_BAD: TCP checksum bad.
M_UDP_CSUM_IN_OK: UDP checksum verified.
M_UDP_CSUM_IN_BAD: UDP checksum bad.
M_ICMP_CSUM_IN_OK: ICMP/ICMPv6 checksum verified.
M_ICMP_CSUM_IN_BAD: ICMP/ICMPv6 checksum bad.
M_IPV6_DF_OUT: Do not fragment IPv6 on output.

The m_pkthdr.flowid variable can contain a low resolution (15-bit) classification of a flow or connection that the current mbuf is part of. If the flowid is valid, it may be used as an alternative to hashing the packets content to pick between different paths for the traffic. The following masks can be ORed with the flowid:

M_FLOWID_VALID: The flow ID has been set.
M_FLOWID_MASK: The flow ID.

When only M_EXT flag is set, an external storage buffer is being used to hold the data, which is no longer stored in the mbuf. The data part of the mbuf has now the following elements:

m_pkthdr: a packet header, just like the previous case, but it is empty. No information is stored here.
m_ext: a structure containing information about the external storage buffer. The information consists of the address of the external buffer, a pointer to the function used to free the buffer, a pointer to the arguments of the function, the size of the buffer, the type of the buffer, and pointers to the previous and next mbufs using this cluster.

When both the M_EXT and M_PKTHDR flags are set, an external storage buffer is being used to store the data and this data contains a packet header. The structure used is the same as the previous one except that the m_pkthdr element is not empty, it contains the same information as when M_PKTHDR is used alone.

m_copym(struct mbuf *m, int off, int len, int wait): Copy an mbuf chain starting at off bytes from the beginning and continuing for len bytes. If off is zero and m has the M_PKTHDR flag set, the header is copied. If len is M_COPYALL the whole mbuf is copied. The wait parameter can be M_WAIT or M_DONTWAIT. It does not copy clusters, it just increases their reference count.
m_free(struct mbuf *m): Free the mbuf pointed to by m. A pointer to the successor of the mbuf, if it exists, is returned by the function. If m is a NULL pointer, no action occurs and NULL is returned.
m_get(int how, int type): Return a pointer to an mbuf of the type specified. If the how argument is M_WAITOK, the function may call tsleep(9) to await resources. If how is M_DONTWAIT and resources are not available, m_get() returns NULL.
MGET(struct mbuf *m, int how, int type): Return a pointer to an mbuf in m of the type specified. See m_get() for a description of how.
m_getclr(int how, int type): Return a pointer to an mbuf of the type specified, and clear the data area of the mbuf. See m_get() for a description of how.
m_removehdr(struct mbuf *m): Convert an mbuf with packet header to one without. Delete all pf(4) data and all tags attached to an mbuf. Keep the data and mbuf chain, clear the packet header.
m_resethdr(struct mbuf *m): Delete all pf(4) data and all tags attached to an mbuf. Keep the data and mbuf chain, initialize the packet header.
m_calchdrlen(struct mbuf *m): Set the packet header length to the sum of all length values in the mbuf chain.
m_gethdr(int how, int type): Return a pointer to an mbuf of the type specified after initializing it to contain a packet header. See m_get() for a description of how.
MGETHDR(struct mbuf *m, int how, int type): Return a pointer to an mbuf of the type specified after initializing it to contain a packet header. See m_get() for a description of how.
m_prepend(struct mbuf *m, int len, int how): Prepend space of size plen to the mbuf pointed to by m. If necessary allocate a new mbuf and prepend it to the mbuf chain pointed to by m. If m points to an mbuf with a packet header, it is moved to the new mbuf that has been prepended. The return value is a pointer on the new mbuf chain. If this function fails to allocate a new mbuf, m is freed. See m_get() for a description of how.
M_PREPEND(struct mbuf *m, int plen, int how): Prepend space of size plen to the mbuf pointed to by m. If a new mbuf must be allocated, how specifies whether to wait or not. If this function fails to allocate a new mbuf, m is freed.
m_pulldown(struct mbuf *m, int off, int len, int *offp): Ensure that the data in the mbuf chain starting at off and ending at off+len will be put in a continuous memory region. If memory must be allocated, then it will fail if the len argument is greater than MAXMCLBYTES. The pointer returned points to an mbuf in the chain and the new offset for data in this mbuf is *offp. If this function fails, m is freed.
m_pullup(struct mbuf *n, int len): Ensure that the data in the mbuf chain starting at the beginning of the chain and ending at len will be put in continuous memory region. If memory must be allocated, then it will fail if the len argument is greater than MAXMCLBYTES. If this function fails, n is freed.
m_split(struct mbuf *m0, int len0, int wait): Split an mbuf chain in two pieces, returning a pointer to the tail (which is made of the previous mbuf chain except the first len0 bytes).
m_makespace(struct mbuf *m0, int skip, int hlen, int *off): Make space for a continuous memory region of length hlen at skip bytes into the mbuf chain. On success, the mbuf of the continuous memory is returned together with an offset off into the mbuf. On failure, NULL is returned and the mbuf chain may have been modified. The caller is assumed to always free the chain.
m_getptr(struct mbuf *m, int loc, int *off): Returns a pointer to the mbuf containing the data located at loc bytes of the beginning. The offset in the new mbuf is pointed to by off.
m_adj(struct mbuf *mp, int req_len): Trims req_len bytes of data from the mbuf chain pointed to by mp. If req_len is positive, the data will be trimmed from the head of the mbuf chain and if it is negative, it will be trimmed from the tail of the mbuf chain.
m_copyback(struct mbuf *m0, int off, int len, caddr_t cp, int wait): Copy data from a buffer pointed to by cp back into the mbuf chain pointed to by m0 starting at off bytes from the beginning, extending the mbuf chain if necessary, sleeping for mbufs if wait is M_WAIT. If M_NOWAIT is set and no mbufs are available, m_copyback() returns ENOBUFS. The mbuf chain must be initialized properly, including setting m_len.
m_defrag(struct mbuf *m, int wait): Defragment the data mbufs referenced by m by replacing the chain with a copy of their contents made into a single mbuf or cluster. wait specifies whether it can wait or not for the replacement storage. m_defrag() returns 0 on success or ENOBUFS on failure. The mbuf pointer m remains in existence and unchanged on failure.
m_freem(struct mbuf *m): Free the mbuf chain pointed to by m. A pointer to the next mbuf in the list linked by m_nextpkt, if it exists, is returned by the function. If m is a NULL pointer, no action occurs and NULL is returned.
m_freemp(struct mbuf **mp): Set the input mbuf pointer to NULL and call m_freem().
m_purge(struct mbuf *m): Free the list of mbufs linked by m_nextpkt that is pointed to by m. Each mbuf is freed by a call to m_freem(). If m is a NULL pointer, no action occurs.
m_reclaim(void): Ask protocols to free unused memory space.
m_copydata(struct mbuf *m, int off, int len, caddr_t cp): Copy data from the mbuf chain pointed to by m starting at off bytes from the beginning and continuing for len bytes into the buffer pointed to by cp.
m_cat(struct mbuf *m, struct mbuf *n): Concatenate the mbuf chain pointed to by n to the mbuf chain pointed to by m. The mbuf chains must be of the same type.
m_devget(char *buf, int totlen, int off): Copy totlen bytes of data from device local memory pointed to by buf. The data is copied into an mbuf chain at offset off and a pointer to the head of the chain is returned. Returns NULL on failure.
m_apply(struct mbuf *m, int off, int len, int (*func)(caddr_t, caddr_t, unsigned int), caddr_t fstate): Apply the function func to the data in the mbuf chain pointed to by m starting at off bytes from the beginning and continuing for len bytes.
mtod(struct mbuf *m, datatype): Return a pointer to the data contained in the specified mbuf m cast to datatype.
MCLGET(struct mbuf *m, int how): Allocate and add an mbuf cluster to the mbuf pointed to by m. On success, the flag M_EXT is set in the mbuf. See m_get() for a description of how.
MCLGETI(struct mbuf *m, int how, struct ifnet *ifp, int len): If m is NULL, allocate it. Then allocate and add an mbuf cluster of length len to the mbuf pointed to by m. Returns either the mbuf m that was passed in, or the newly allocated one which was allocated; in either case the flag M_EXT is set in the mbuf. See m_get() for a description of how.
MEXTADD(struct mbuf *m, caddr_t buf, u_int size, int flags, void (*free)(caddr_t, u_int, void *), void *arg): Add pre-allocated storage to the mbuf pointed to by m. On success, the flag M_EXT is set in the mbuf, and M_EXTWR is specified in flags.
m_align(struct mbuf *m, int len): Set the m_data pointer of the newly allocated mbuf m to an object of the specified size len at the end of this mbuf data area, longword aligned.
M_READONLY(struct mbuf *m): Check if the data of the mbuf pointed to by m is read-only. This is true for non-cluster external storage and for clusters that are being referenced by more than one mbuf.
m_leadingspace(struct mbuf *m): Compute the amount of space available before the current start of data in the mbuf pointed to by m. If the data of the mbuf pointed to by m is read-only then 0 is returned.
m_trailingspace(struct mbuf *m): Compute the amount of space available after the end of data in the mbuf pointed to by m. If the data of the mbuf pointed to by m is read-only then 0 is returned.
m_dup_pkt(struct mbuf *m, u_int adj, int how): Allocate a new mbuf and storage and copy the packet data and header, including mbuf tags, from m. The data in the new mbuf will be offset from the start of the storage by adj bytes. See m_get() for a description of how.
m_dup_pkthdr(struct mbuf *to, struct mbuf *from, int how): Copy mbuf packet header, including mbuf tags, from from to to. See m_get() for a description of how.

CODE REFERENCES

The mbuf management functions are implemented in the files sys/kern/uipc_mbuf.c and sys/kern/uipc_mbuf2.c. The function prototypes and the macros are located in sys/sys/mbuf.h.

OpenBSD manual page server

NAME

SYNOPSIS

DESCRIPTION

CODE REFERENCES

SEE ALSO