d/freebsd-nq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge from projects/sendfile:

Browse Source 
o Introduce a notion of "not ready" mbufs in socket buffers.  These
mbufs are now being populated by some I/O in background and are
referenced outside.  This forces following implications:
- An mbuf which is "not ready" can't be taken out of the buffer.
- An mbuf that is behind a "not ready" in the queue neither.
- If sockbet buffer is flushed, then "not ready" mbufs shouln't be
  freed.

o In struct sockbuf the sb_cc field is split into sb_ccc and sb_acc.
  The sb_ccc stands for ""claimed character count", or "committed
  character count".  And the sb_acc is "available character count".
  Consumers of socket buffer API shouldn't already access them directly,
  but use sbused() and sbavail() respectively.
o Not ready mbufs are marked with M_NOTREADY, and ready but blocked ones
  with M_BLOCKED.
o New field sb_fnrdy points to the first not ready mbuf, to avoid linear
  search.
o New function sbready() is provided to activate certain amount of mbufs
  in a socket buffer.

A special note on SCTP:
  SCTP has its own sockbufs.  Unfortunately, FreeBSD stack doesn't yet
allow protocol specific sockbufs.  Thus, SCTP does some hacks to make
itself compatible with FreeBSD: it manages sockbufs on its own, but keeps
sb_cc updated to inform the stack of amount of data in them.  The new
notion of "not ready" data isn't supported by SCTP.  Instead, only a
mechanical substitute is done: s/sb_cc/sb_ccc/.
  A proper solution would be to take away struct sockbuf from struct
socket and allow protocols to implement their own socket buffers, like
SCTP already does.  This was discussed with rrs@.

Sponsored by:	Netflix
Sponsored by:	Nginx, Inc.
This commit is contained in:
Gleb Smirnoff 2014-11-30 12:52:33 +00:00
parent abcd412940
commit 0f9d0a73a4
21 changed files with 229 additions and 112 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
sys/dev/cxgbe/tom/t4_ddp.c
View File

@ -971,8 +971,9 @@ handle_ddp(struct socket *so, struct uio *uio, int flags, int error)
*/
rc = sbwait(sb);
while (toep->ddp_flags & buf_flag) {
/* XXXGL: shouldn't here be sbwait() call? */
sb->sb_flags |= SB_WAIT;
msleep(&sb->sb_cc, &sb->sb_mtx, PSOCK , "sbwait", 0);
msleep(&sb->sb_acc, &sb->sb_mtx, PSOCK , "sbwait", 0);
}
unwire_ddp_buffer(db);
return (rc);

3
sys/kern/uipc_debug.c
View File

@ -401,7 +401,8 @@ db_print_sockbuf(struct sockbuf *sb, const char *sockbufname, int indent)
db_printf("sb_sndptroff: %u\n", sb->sb_sndptroff);
db_print_indent(indent);
db_printf("sb_cc: %u ", sb->sb_cc);
db_printf("sb_acc: %u ", sb->sb_acc);
db_printf("sb_ccc: %u ", sb->sb_ccc);
db_printf("sb_hiwat: %u ", sb->sb_hiwat);
db_printf("sb_mbcnt: %u ", sb->sb_mbcnt);
db_printf("sb_mbmax: %u\n", sb->sb_mbmax);

153
sys/kern/uipc_sockbuf.c
View File

@ -68,6 +68,43 @@ static u_long sb_efficiency = 8; /* parameter for sbreserve() */
static struct mbuf *sbcut_internal(struct sockbuf *sb, int len);
static void sbflush_internal(struct sockbuf *sb);
/*
* Mark ready "count" mbufs starting with "m".
*/
int
sbready(struct sockbuf *sb, struct mbuf *m, int count)
{
u_int blocker;
SOCKBUF_LOCK_ASSERT(sb);
KASSERT(sb->sb_fnrdy != NULL, ("%s: sb %p NULL fnrdy", __func__, sb));
blocker = (sb->sb_fnrdy == m) ? M_BLOCKED : 0;
for (int i = 0; i < count; i++, m = m->m_next) {
KASSERT(m->m_flags & M_NOTREADY,
("%s: m %p !M_NOTREADY", __func__, m));
m->m_flags &= ~(M_NOTREADY | blocker);
if (blocker)
sb->sb_acc += m->m_len;
}
if (!blocker)
return (EINPROGRESS);
/* This one was blocking all the queue. */
for (; m && (m->m_flags & M_NOTREADY) == 0; m = m->m_next) {
KASSERT(m->m_flags & M_BLOCKED,
("%s: m %p !M_BLOCKED", __func__, m));
m->m_flags &= ~M_BLOCKED;
sb->sb_acc += m->m_len;
}
sb->sb_fnrdy = m;
return (0);
}
/*
* Adjust sockbuf state reflecting allocation of m.
*/
@ -77,7 +114,15 @@ sballoc(struct sockbuf *sb, struct mbuf *m)
SOCKBUF_LOCK_ASSERT(sb);
sb->sb_cc += m->m_len;
sb->sb_ccc += m->m_len;
if (sb->sb_fnrdy == NULL) {
if (m->m_flags & M_NOTREADY)
sb->sb_fnrdy = m;
else
sb->sb_acc += m->m_len;
} else
m->m_flags |= M_BLOCKED;
if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
sb->sb_ctl += m->m_len;
@ -102,7 +147,25 @@ sbfree(struct sockbuf *sb, struct mbuf *m)
SOCKBUF_LOCK_ASSERT(sb);
#endif
sb->sb_cc -= m->m_len;
sb->sb_ccc -= m->m_len;
if (!(m->m_flags & M_NOTAVAIL))
sb->sb_acc -= m->m_len;
if (m == sb->sb_fnrdy) {
struct mbuf *n;
KASSERT(m->m_flags & M_NOTREADY,
("%s: m %p !M_NOTREADY", __func__, m));
n = m->m_next;
while (n != NULL && !(n->m_flags & M_NOTREADY)) {
n->m_flags &= ~M_BLOCKED;
sb->sb_acc += n->m_len;
n = n->m_next;
}
sb->sb_fnrdy = n;
}
if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
sb->sb_ctl -= m->m_len;
@ -181,7 +244,7 @@ sbwait(struct sockbuf *sb)
SOCKBUF_LOCK_ASSERT(sb);
sb->sb_flags |= SB_WAIT;
return (msleep_sbt(&sb->sb_cc, &sb->sb_mtx,
return (msleep_sbt(&sb->sb_acc, &sb->sb_mtx,
(sb->sb_flags & SB_NOINTR) ? PSOCK : PSOCK | PCATCH, "sbwait",
sb->sb_timeo, 0, 0));
}
@ -238,7 +301,7 @@ sowakeup(struct socket *so, struct sockbuf *sb)
sb->sb_flags &= ~SB_SEL;
if (sb->sb_flags & SB_WAIT) {
sb->sb_flags &= ~SB_WAIT;
wakeup(&sb->sb_cc);
wakeup(&sb->sb_acc);
}
KNOTE_LOCKED(&sb->sb_sel.si_note, 0);
if (sb->sb_upcall != NULL) {
@ -609,12 +672,13 @@ sbappendstream(struct sockbuf *sb, struct mbuf *m)
void
sbcheck(struct sockbuf *sb, const char *file, int line)
{
struct mbuf *m, *n;
u_long cc, mbcnt;
struct mbuf *m, *n, *fnrdy;
u_long acc, ccc, mbcnt;
SOCKBUF_LOCK_ASSERT(sb);
cc = mbcnt = 0;
acc = ccc = mbcnt = 0;
fnrdy = NULL;
for (m = sb->sb_mb; m; m = n) {
n = m->m_nextpkt;
@ -623,15 +687,31 @@ sbcheck(struct sockbuf *sb, const char *file, int line)
printf("sb %p empty mbuf %p\n", sb, m);
goto fail;
}
cc += m->m_len;
if ((m->m_flags & M_NOTREADY) && fnrdy == NULL) {
if (m != sb->sb_fnrdy) {
printf("sb %p: fnrdy %p != m %p\n",
sb, sb->sb_fnrdy, m);
goto fail;
}
fnrdy = m;
}
if (fnrdy) {
if (!(m->m_flags & M_NOTAVAIL)) {
printf("sb %p: fnrdy %p, m %p is avail\n",
sb, sb->sb_fnrdy, m);
goto fail;
}
} else
acc += m->m_len;
ccc += m->m_len;
mbcnt += MSIZE;
if (m->m_flags & M_EXT) /*XXX*/ /* pretty sure this is bogus */
mbcnt += m->m_ext.ext_size;
}
}
if (cc != sb->sb_cc || mbcnt != sb->sb_mbcnt) {
printf("cc %ld != %u || mbcnt %ld != %u\n", cc, sb->sb_cc,
mbcnt, sb->sb_mbcnt);
if (acc != sb->sb_acc || ccc != sb->sb_ccc || mbcnt != sb->sb_mbcnt) {
printf("acc %ld/%u ccc %ld/%u mbcnt %ld/%u\n",
acc, sb->sb_acc, ccc, sb->sb_ccc, mbcnt, sb->sb_mbcnt);
goto fail;
}
return;
@ -832,8 +912,8 @@ sbappendcontrol(struct sockbuf *sb, struct mbuf *m0, struct mbuf *control)
*
* (2) The mbuf may be coalesced -- i.e., data in the mbuf may be copied into
* an mbuf already in the socket buffer. This can occur if an
* appropriate mbuf exists, there is room, and no merging of data types
* will occur.
* appropriate mbuf exists, there is room, both mbufs are not marked as
* not ready, and no merging of data types will occur.
*
* (3) The mbuf may be appended to the end of the existing mbuf chain.
*
@ -862,13 +942,17 @@ sbcompress(struct sockbuf *sb, struct mbuf *m, struct mbuf *n)
if (n && (n->m_flags & M_EOR) == 0 &&
M_WRITABLE(n) &&
((sb->sb_flags & SB_NOCOALESCE) == 0) &&
!(m->m_flags & M_NOTREADY) &&
!(n->m_flags & M_NOTREADY) &&
m->m_len <= MCLBYTES / 4 && /* XXX: Don't copy too much */
m->m_len <= M_TRAILINGSPACE(n) &&
n->m_type == m->m_type) {
bcopy(mtod(m, caddr_t), mtod(n, caddr_t) + n->m_len,
(unsigned)m->m_len);
n->m_len += m->m_len;
sb->sb_cc += m->m_len;
sb->sb_ccc += m->m_len;
if (sb->sb_fnrdy == NULL)
sb->sb_acc += m->m_len;
if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
/* XXX: Probably don't need.*/
sb->sb_ctl += m->m_len;
@ -905,13 +989,13 @@ sbflush_internal(struct sockbuf *sb)
* Don't call sbcut(sb, 0) if the leading mbuf is non-empty:
* we would loop forever. Panic instead.
*/
if (!sb->sb_cc && (sb->sb_mb == NULL || sb->sb_mb->m_len))
if (sb->sb_ccc == 0 && (sb->sb_mb == NULL || sb->sb_mb->m_len))
break;
m_freem(sbcut_internal(sb, (int)sb->sb_cc));
m_freem(sbcut_internal(sb, (int)sb->sb_ccc));
}
if (sb->sb_cc || sb->sb_mb || sb->sb_mbcnt)
panic("sbflush_internal: cc %u || mb %p || mbcnt %u",
sb->sb_cc, (void *)sb->sb_mb, sb->sb_mbcnt);
KASSERT(sb->sb_ccc == 0 && sb->sb_mb == 0 && sb->sb_mbcnt == 0,
("%s: ccc %u mb %p mbcnt %u", __func__,
sb->sb_ccc, (void *)sb->sb_mb, sb->sb_mbcnt));
}
void
@ -937,7 +1021,7 @@ sbflush(struct sockbuf *sb)
static struct mbuf *
sbcut_internal(struct sockbuf *sb, int len)
{
struct mbuf *m, *n, *next, *mfree;
struct mbuf *m, *next, *mfree;
next = (m = sb->sb_mb) ? m->m_nextpkt : 0;
mfree = NULL;
@ -949,9 +1033,12 @@ sbcut_internal(struct sockbuf *sb, int len)
next = m->m_nextpkt;
}
if (m->m_len > len) {
KASSERT(!(m->m_flags & M_NOTAVAIL),
("%s: m %p M_NOTAVAIL", __func__, m));
m->m_len -= len;
m->m_data += len;
sb->sb_cc -= len;
sb->sb_ccc -= len;
sb->sb_acc -= len;
if (sb->sb_sndptroff != 0)
sb->sb_sndptroff -= len;
if (m->m_type != MT_DATA && m->m_type != MT_OOBDATA)
@ -960,10 +1047,20 @@ sbcut_internal(struct sockbuf *sb, int len)
}
len -= m->m_len;
sbfree(sb, m);
n = m->m_next;
m->m_next = mfree;
mfree = m;
m = n;
/*
* Do not put M_NOTREADY buffers to the free list, they
* are referenced from outside.
*/
if (m->m_flags & M_NOTREADY)
m = m->m_next;
else {
struct mbuf *n;
n = m->m_next;
m->m_next = mfree;
mfree = m;
m = n;
}
}
if (m) {
sb->sb_mb = m;
@ -1030,8 +1127,8 @@ sbsndptr(struct sockbuf *sb, u_int off, u_int len, u_int *moff)
struct mbuf *m, *ret;
KASSERT(sb->sb_mb != NULL, ("%s: sb_mb is NULL", __func__));
KASSERT(off + len <= sb->sb_cc, ("%s: beyond sb", __func__));
KASSERT(sb->sb_sndptroff <= sb->sb_cc, ("%s: sndptroff broken", __func__));
KASSERT(off + len <= sb->sb_acc, ("%s: beyond sb", __func__));
KASSERT(sb->sb_sndptroff <= sb->sb_acc, ("%s: sndptroff broken", __func__));
/*
* Is off below stored offset? Happens on retransmits.
@ -1180,7 +1277,7 @@ void
sbtoxsockbuf(struct sockbuf *sb, struct xsockbuf *xsb)
{
xsb->sb_cc = sb->sb_cc;
xsb->sb_cc = sb->sb_ccc;
xsb->sb_hiwat = sb->sb_hiwat;
xsb->sb_mbcnt = sb->sb_mbcnt;
xsb->sb_mcnt = sb->sb_mcnt;

5
sys/kern/uipc_socket.c
View File

@ -1706,7 +1706,8 @@ soreceive_generic(struct socket *so, struct sockaddr **psa, struct uio *uio,
*/
moff = 0;
offset = 0;
while (m != NULL && uio->uio_resid > 0 && error == 0) {
while (m != NULL && !(m->m_flags & M_NOTAVAIL) && uio->uio_resid > 0
&& error == 0) {
/*
* If the type of mbuf has changed since the last mbuf
* examined ('type'), end the receive operation.
@ -2044,6 +2045,8 @@ soreceive_stream(struct socket *so, struct sockaddr **psa, struct uio *uio,
for (m = sb->sb_mb;
m != NULL && m->m_len <= len;
m = m->m_next) {
KASSERT(!(m->m_flags & M_NOTAVAIL),
("%s: m %p not available", __func__, m));
len -= m->m_len;
uio->uio_resid -= m->m_len;
sbfree(sb, m);

6
sys/netinet/sctp_indata.c
View File

@ -70,14 +70,14 @@ sctp_calc_rwnd(struct sctp_tcb *stcb, struct sctp_association *asoc)
/*
* This is really set wrong with respect to a 1-2-m socket. Since
* the sb_cc is the count that everyone as put up. When we re-write
* the sb_ccc is the count that everyone as put up. When we re-write
* sctp_soreceive then we will fix this so that ONLY this
* associations data is taken into account.
*/
if (stcb->sctp_socket == NULL)
return (calc);
if (stcb->asoc.sb_cc == 0 &&
if (stcb->asoc.sb_ccc == 0 &&
asoc->size_on_reasm_queue == 0 &&
asoc->size_on_all_streams == 0) {
/* Full rwnd granted */
@ -1363,7 +1363,7 @@ sctp_process_a_data_chunk(struct sctp_tcb *stcb, struct sctp_association *asoc,
* When we have NO room in the rwnd we check to make sure
* the reader is doing its job...
*/
if (stcb->sctp_socket->so_rcv.sb_cc) {
if (stcb->sctp_socket->so_rcv.sb_ccc) {
/* some to read, wake-up */
#if defined(__APPLE__) || defined(SCTP_SO_LOCK_TESTING)
struct socket *so;

2
sys/netinet/sctp_input.c
View File

@ -1032,7 +1032,7 @@ sctp_handle_shutdown_ack(struct sctp_shutdown_ack_chunk *cp SCTP_UNUSED,
if (stcb->sctp_socket) {
if ((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) ||
(stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL)) {
stcb->sctp_socket->so_snd.sb_cc = 0;
stcb->sctp_socket->so_snd.sb_ccc = 0;
}
sctp_ulp_notify(SCTP_NOTIFY_ASSOC_DOWN, stcb, 0, NULL, SCTP_SO_NOT_LOCKED);
}

2
sys/netinet/sctp_os_bsd.h
View File

@ -399,7 +399,7 @@ typedef struct callout sctp_os_timer_t;
#define SCTP_SOWAKEUP(so) wakeup(&(so)->so_timeo)
/* clear the socket buffer state */
#define SCTP_SB_CLEAR(sb) \
(sb).sb_cc = 0; \
(sb).sb_ccc = 0; \
(sb).sb_mb = NULL; \
(sb).sb_mbcnt = 0;

4
sys/netinet/sctp_output.c
View File

@ -7250,7 +7250,7 @@ sctp_move_to_outqueue(struct sctp_tcb *stcb,
if ((stcb->sctp_socket != NULL) && \
((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) ||
(stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL))) {
atomic_subtract_int(&stcb->sctp_socket->so_snd.sb_cc, sp->length);
atomic_subtract_int(&stcb->sctp_socket->so_snd.sb_ccc, sp->length);
}
if (sp->data) {
sctp_m_freem(sp->data);
@ -11532,7 +11532,7 @@ sctp_send_packet_dropped(struct sctp_tcb *stcb, struct sctp_nets *net,
drp->current_onq = htonl(asoc->size_on_reasm_queue +
asoc->size_on_all_streams +
asoc->my_rwnd_control_len +
stcb->sctp_socket->so_rcv.sb_cc);
stcb->sctp_socket->so_rcv.sb_ccc);
} else {
/*-
* If my rwnd is 0, possibly from mbuf depletion as well as

6
sys/netinet/sctp_pcb.c
View File

@ -3397,7 +3397,7 @@ sctp_inpcb_free(struct sctp_inpcb *inp, int immediate, int from)
if ((asoc->asoc.size_on_reasm_queue > 0) ||
(asoc->asoc.control_pdapi) ||
(asoc->asoc.size_on_all_streams > 0) ||
(so && (so->so_rcv.sb_cc > 0))) {
(so && (so->so_rcv.sb_ccc > 0))) {
/* Left with Data unread */
struct mbuf *op_err;
@ -3625,7 +3625,7 @@ sctp_inpcb_free(struct sctp_inpcb *inp, int immediate, int from)
TAILQ_REMOVE(&inp->read_queue, sq, next);
sctp_free_remote_addr(sq->whoFrom);
if (so)
so->so_rcv.sb_cc -= sq->length;
so->so_rcv.sb_ccc -= sq->length;
if (sq->data) {
sctp_m_freem(sq->data);
sq->data = NULL;
@ -4853,7 +4853,7 @@ sctp_free_assoc(struct sctp_inpcb *inp, struct sctp_tcb *stcb, int from_inpcbfre
inp->sctp_flags |= SCTP_PCB_FLAGS_WAS_CONNECTED;
if (so) {
SOCK_LOCK(so);
if (so->so_rcv.sb_cc == 0) {
if (so->so_rcv.sb_ccc == 0) {
so->so_state &= ~(SS_ISCONNECTING |
SS_ISDISCONNECTING |
SS_ISCONFIRMING |

2
sys/netinet/sctp_pcb.h
View File

@ -369,7 +369,7 @@ struct sctp_inpcb {
} ip_inp;
/* Socket buffer lock protects read_queue and of course sb_cc */
/* Socket buffer lock protects read_queue and of course sb_ccc */
struct sctp_readhead read_queue;
LIST_ENTRY(sctp_inpcb) sctp_list; /* lists all endpoints */

2
sys/netinet/sctp_structs.h
View File

@ -990,7 +990,7 @@ struct sctp_association {
uint32_t total_output_queue_size;
uint32_t sb_cc; /* shadow of sb_cc */
uint32_t sb_ccc; /* shadow of sb_ccc */
uint32_t sb_send_resv; /* amount reserved on a send */
uint32_t my_rwnd_control_len; /* shadow of sb_mbcnt used for rwnd
* control */

8
sys/netinet/sctp_usrreq.c
View File

@ -586,7 +586,7 @@ sctp_close(struct socket *so)
if (((flags & SCTP_PCB_FLAGS_SOCKET_GONE) == 0) &&
(atomic_cmpset_int(&inp->sctp_flags, flags, (flags | SCTP_PCB_FLAGS_SOCKET_GONE | SCTP_PCB_FLAGS_CLOSE_IP)))) {
if (((so->so_options & SO_LINGER) && (so->so_linger == 0)) ||
(so->so_rcv.sb_cc > 0)) {
(so->so_rcv.sb_ccc > 0)) {
#ifdef SCTP_LOG_CLOSING
sctp_log_closing(inp, NULL, 13);
#endif
@ -751,7 +751,7 @@ sctp_disconnect(struct socket *so)
}
if (((so->so_options & SO_LINGER) &&
(so->so_linger == 0)) ||
(so->so_rcv.sb_cc > 0)) {
(so->so_rcv.sb_ccc > 0)) {
if (SCTP_GET_STATE(asoc) !=
SCTP_STATE_COOKIE_WAIT) {
/* Left with Data unread */
@ -916,7 +916,7 @@ sctp_flush(struct socket *so, int how)
inp->sctp_flags |= SCTP_PCB_FLAGS_SOCKET_CANT_READ;
SCTP_INP_READ_UNLOCK(inp);
SCTP_INP_WUNLOCK(inp);
so->so_rcv.sb_cc = 0;
so->so_rcv.sb_ccc = 0;
so->so_rcv.sb_mbcnt = 0;
so->so_rcv.sb_mb = NULL;
}
@ -925,7 +925,7 @@ sctp_flush(struct socket *so, int how)
* First make sure the sb will be happy, we don't use these
* except maybe the count
*/
so->so_snd.sb_cc = 0;
so->so_snd.sb_ccc = 0;
so->so_snd.sb_mbcnt = 0;
so->so_snd.sb_mb = NULL;

12
sys/netinet/sctp_var.h
View File

@ -82,9 +82,9 @@ extern struct pr_usrreqs sctp_usrreqs;
#define sctp_maxspace(sb) (max((sb)->sb_hiwat,SCTP_MINIMAL_RWND))
#define sctp_sbspace(asoc, sb) ((long) ((sctp_maxspace(sb) > (asoc)->sb_cc) ? (sctp_maxspace(sb) - (asoc)->sb_cc) : 0))
#define sctp_sbspace(asoc, sb) ((long) ((sctp_maxspace(sb) > (asoc)->sb_ccc) ? (sctp_maxspace(sb) - (asoc)->sb_ccc) : 0))
#define sctp_sbspace_failedmsgs(sb) ((long) ((sctp_maxspace(sb) > (sb)->sb_cc) ? (sctp_maxspace(sb) - (sb)->sb_cc) : 0))
#define sctp_sbspace_failedmsgs(sb) ((long) ((sctp_maxspace(sb) > (sb)->sb_ccc) ? (sctp_maxspace(sb) - (sb)->sb_ccc) : 0))
#define sctp_sbspace_sub(a,b) ((a > b) ? (a - b) : 0)
@ -195,10 +195,10 @@ extern struct pr_usrreqs sctp_usrreqs;
}
#define sctp_sbfree(ctl, stcb, sb, m) { \
SCTP_SAVE_ATOMIC_DECREMENT(&(sb)->sb_cc, SCTP_BUF_LEN((m))); \
SCTP_SAVE_ATOMIC_DECREMENT(&(sb)->sb_ccc, SCTP_BUF_LEN((m))); \
SCTP_SAVE_ATOMIC_DECREMENT(&(sb)->sb_mbcnt, MSIZE); \
if (((ctl)->do_not_ref_stcb == 0) && stcb) {\
SCTP_SAVE_ATOMIC_DECREMENT(&(stcb)->asoc.sb_cc, SCTP_BUF_LEN((m))); \
SCTP_SAVE_ATOMIC_DECREMENT(&(stcb)->asoc.sb_ccc, SCTP_BUF_LEN((m))); \
SCTP_SAVE_ATOMIC_DECREMENT(&(stcb)->asoc.my_rwnd_control_len, MSIZE); \
} \
if (SCTP_BUF_TYPE(m) != MT_DATA && SCTP_BUF_TYPE(m) != MT_HEADER && \
@ -207,10 +207,10 @@ extern struct pr_usrreqs sctp_usrreqs;
}
#define sctp_sballoc(stcb, sb, m) { \
atomic_add_int(&(sb)->sb_cc,SCTP_BUF_LEN((m))); \
atomic_add_int(&(sb)->sb_ccc,SCTP_BUF_LEN((m))); \
atomic_add_int(&(sb)->sb_mbcnt, MSIZE); \
if (stcb) { \
atomic_add_int(&(stcb)->asoc.sb_cc,SCTP_BUF_LEN((m))); \
atomic_add_int(&(stcb)->asoc.sb_ccc,SCTP_BUF_LEN((m))); \
atomic_add_int(&(stcb)->asoc.my_rwnd_control_len, MSIZE); \
} \
if (SCTP_BUF_TYPE(m) != MT_DATA && SCTP_BUF_TYPE(m) != MT_HEADER && \

52
sys/netinet/sctputil.c
View File

@ -67,9 +67,9 @@ sctp_sblog(struct sockbuf *sb, struct sctp_tcb *stcb, int from, int incr)
struct sctp_cwnd_log sctp_clog;
sctp_clog.x.sb.stcb = stcb;
sctp_clog.x.sb.so_sbcc = sb->sb_cc;
sctp_clog.x.sb.so_sbcc = sb->sb_ccc;
if (stcb)
sctp_clog.x.sb.stcb_sbcc = stcb->asoc.sb_cc;
sctp_clog.x.sb.stcb_sbcc = stcb->asoc.sb_ccc;
else
sctp_clog.x.sb.stcb_sbcc = 0;
sctp_clog.x.sb.incr = incr;
@ -4363,7 +4363,7 @@ sctp_add_to_readq(struct sctp_inpcb *inp,
{
/*
* Here we must place the control on the end of the socket read
* queue AND increment sb_cc so that select will work properly on
* queue AND increment sb_ccc so that select will work properly on
* read.
*/
struct mbuf *m, *prev = NULL;
@ -4489,7 +4489,7 @@ sctp_append_to_readq(struct sctp_inpcb *inp,
* the reassembly queue.
*
* If PDAPI this means we need to add m to the end of the data.
* Increase the length in the control AND increment the sb_cc.
* Increase the length in the control AND increment the sb_ccc.
* Otherwise sb is NULL and all we need to do is put it at the end
* of the mbuf chain.
*/
@ -4701,10 +4701,10 @@ sctp_free_bufspace(struct sctp_tcb *stcb, struct sctp_association *asoc,
if (stcb->sctp_socket && (((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL)) ||
((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE)))) {
if (stcb->sctp_socket->so_snd.sb_cc >= tp1->book_size) {
stcb->sctp_socket->so_snd.sb_cc -= tp1->book_size;
if (stcb->sctp_socket->so_snd.sb_ccc >= tp1->book_size) {
stcb->sctp_socket->so_snd.sb_ccc -= tp1->book_size;
} else {
stcb->sctp_socket->so_snd.sb_cc = 0;
stcb->sctp_socket->so_snd.sb_ccc = 0;
}
}
@ -5254,11 +5254,11 @@ sctp_sorecvmsg(struct socket *so,
in_eeor_mode = sctp_is_feature_on(inp, SCTP_PCB_FLAGS_EXPLICIT_EOR);
if (SCTP_BASE_SYSCTL(sctp_logging_level) & SCTP_RECV_RWND_LOGGING_ENABLE) {
sctp_misc_ints(SCTP_SORECV_ENTER,
rwnd_req, in_eeor_mode, so->so_rcv.sb_cc, uio->uio_resid);
rwnd_req, in_eeor_mode, so->so_rcv.sb_ccc, uio->uio_resid);
}
if (SCTP_BASE_SYSCTL(sctp_logging_level) & SCTP_RECV_RWND_LOGGING_ENABLE) {
sctp_misc_ints(SCTP_SORECV_ENTERPL,
rwnd_req, block_allowed, so->so_rcv.sb_cc, uio->uio_resid);
rwnd_req, block_allowed, so->so_rcv.sb_ccc, uio->uio_resid);
}
error = sblock(&so->so_rcv, (block_allowed ? SBL_WAIT : 0));
if (error) {
@ -5277,23 +5277,23 @@ sctp_sorecvmsg(struct socket *so,
(inp->sctp_flags & SCTP_PCB_FLAGS_SOCKET_ALLGONE)) {
goto out;
}
if ((so->so_rcv.sb_state & SBS_CANTRCVMORE) && (so->so_rcv.sb_cc == 0)) {
if ((so->so_rcv.sb_state & SBS_CANTRCVMORE) && (so->so_rcv.sb_ccc == 0)) {
if (so->so_error) {
error = so->so_error;
if ((in_flags & MSG_PEEK) == 0)
so->so_error = 0;
goto out;
} else {
if (so->so_rcv.sb_cc == 0) {
if (so->so_rcv.sb_ccc == 0) {
/* indicate EOF */
error = 0;
goto out;
}
}
}
if ((so->so_rcv.sb_cc <= held_length) && block_allowed) {
if ((so->so_rcv.sb_ccc <= held_length) && block_allowed) {
/* we need to wait for data */
if ((so->so_rcv.sb_cc == 0) &&
if ((so->so_rcv.sb_ccc == 0) &&
((inp->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) ||
(inp->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL))) {
if ((inp->sctp_flags & SCTP_PCB_FLAGS_CONNECTED) == 0) {
@ -5329,7 +5329,7 @@ sctp_sorecvmsg(struct socket *so,
}
held_length = 0;
goto restart_nosblocks;
} else if (so->so_rcv.sb_cc == 0) {
} else if (so->so_rcv.sb_ccc == 0) {
if (so->so_error) {
error = so->so_error;
if ((in_flags & MSG_PEEK) == 0)
@ -5386,11 +5386,11 @@ sctp_sorecvmsg(struct socket *so,
SCTP_INP_READ_LOCK(inp);
}
control = TAILQ_FIRST(&inp->read_queue);
if ((control == NULL) && (so->so_rcv.sb_cc != 0)) {
if ((control == NULL) && (so->so_rcv.sb_ccc != 0)) {
#ifdef INVARIANTS
panic("Huh, its non zero and nothing on control?");
#endif
so->so_rcv.sb_cc = 0;
so->so_rcv.sb_ccc = 0;
}
SCTP_INP_READ_UNLOCK(inp);
hold_rlock = 0;
@ -5511,11 +5511,11 @@ sctp_sorecvmsg(struct socket *so,
}
/*
* if we reach here, not suitable replacement is available
* <or> fragment interleave is NOT on. So stuff the sb_cc
* <or> fragment interleave is NOT on. So stuff the sb_ccc
* into the our held count, and its time to sleep again.
*/
held_length = so->so_rcv.sb_cc;
control->held_length = so->so_rcv.sb_cc;
held_length = so->so_rcv.sb_ccc;
control->held_length = so->so_rcv.sb_ccc;
goto restart;
}
/* Clear the held length since there is something to read */
@ -5812,10 +5812,10 @@ sctp_sorecvmsg(struct socket *so,
if (SCTP_BASE_SYSCTL(sctp_logging_level) & SCTP_SB_LOGGING_ENABLE) {
sctp_sblog(&so->so_rcv, control->do_not_ref_stcb ? NULL : stcb, SCTP_LOG_SBFREE, cp_len);
}
atomic_subtract_int(&so->so_rcv.sb_cc, cp_len);
atomic_subtract_int(&so->so_rcv.sb_ccc, cp_len);
if ((control->do_not_ref_stcb == 0) &&
stcb) {
atomic_subtract_int(&stcb->asoc.sb_cc, cp_len);
atomic_subtract_int(&stcb->asoc.sb_ccc, cp_len);
}
copied_so_far += cp_len;
freed_so_far += cp_len;
@ -5960,7 +5960,7 @@ sctp_sorecvmsg(struct socket *so,
(sctp_is_feature_on(inp, SCTP_PCB_FLAGS_FRAG_INTERLEAVE))) {
goto release;
}
if (so->so_rcv.sb_cc <= control->held_length) {
if (so->so_rcv.sb_ccc <= control->held_length) {
error = sbwait(&so->so_rcv);
if (error) {
goto release;
@ -5987,8 +5987,8 @@ sctp_sorecvmsg(struct socket *so,
}
goto done_with_control;
}
if (so->so_rcv.sb_cc > held_length) {
control->held_length = so->so_rcv.sb_cc;
if (so->so_rcv.sb_ccc > held_length) {
control->held_length = so->so_rcv.sb_ccc;
held_length = 0;
}
goto wait_some_more;
@ -6135,13 +6135,13 @@ sctp_sorecvmsg(struct socket *so,
freed_so_far,
((uio) ? (slen - uio->uio_resid) : slen),
stcb->asoc.my_rwnd,
so->so_rcv.sb_cc);
so->so_rcv.sb_ccc);
} else {
sctp_misc_ints(SCTP_SORECV_DONE,
freed_so_far,
((uio) ? (slen - uio->uio_resid) : slen),
0,
so->so_rcv.sb_cc);
so->so_rcv.sb_ccc);
}
}
stage_left:

14
sys/netinet/sctputil.h
View File

@ -286,10 +286,10 @@ do { \
} \
if (stcb->sctp_socket && ((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) || \
(stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL))) { \
if (stcb->sctp_socket->so_snd.sb_cc >= tp1->book_size) { \
atomic_subtract_int(&((stcb)->sctp_socket->so_snd.sb_cc), tp1->book_size); \
if (stcb->sctp_socket->so_snd.sb_ccc >= tp1->book_size) { \
atomic_subtract_int(&((stcb)->sctp_socket->so_snd.sb_ccc), tp1->book_size); \
} else { \
stcb->sctp_socket->so_snd.sb_cc = 0; \
stcb->sctp_socket->so_snd.sb_ccc = 0; \
} \
} \
} \
@ -307,10 +307,10 @@ do { \
} \
if (stcb->sctp_socket && ((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) || \
(stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL))) { \
if (stcb->sctp_socket->so_snd.sb_cc >= sp->length) { \
atomic_subtract_int(&stcb->sctp_socket->so_snd.sb_cc,sp->length); \
if (stcb->sctp_socket->so_snd.sb_ccc >= sp->length) { \
atomic_subtract_int(&stcb->sctp_socket->so_snd.sb_ccc,sp->length); \
} else { \
stcb->sctp_socket->so_snd.sb_cc = 0; \
stcb->sctp_socket->so_snd.sb_ccc = 0; \
} \
} \
} \
@ -322,7 +322,7 @@ do { \
if ((stcb->sctp_socket != NULL) && \
((stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_TCPTYPE) || \
(stcb->sctp_ep->sctp_flags & SCTP_PCB_FLAGS_IN_TCPPOOL))) { \
atomic_add_int(&stcb->sctp_socket->so_snd.sb_cc,sz); \
atomic_add_int(&stcb->sctp_socket->so_snd.sb_ccc,sz); \
} \
} while (0)

37
sys/sys/sockbuf.h
View File

@ -89,8 +89,10 @@ struct sockbuf {
struct mbuf *sb_lastrecord; /* (c/d) first mbuf of last
* record in socket buffer */
struct mbuf *sb_sndptr; /* (c/d) pointer into mbuf chain */
struct mbuf *sb_fnrdy; /* (c/d) pointer to first not ready buffer */
u_int sb_sndptroff; /* (c/d) byte offset of ptr into chain */
u_int sb_cc; /* (c/d) actual chars in buffer */
u_int sb_acc; /* (c/d) available chars in buffer */
u_int sb_ccc; /* (c/d) claimed chars in buffer */
u_int sb_hiwat; /* (c/d) max actual char count */
u_int sb_mbcnt; /* (c/d) chars of mbufs used */
u_int sb_mcnt; /* (c/d) number of mbufs in buffer */
@ -120,6 +122,13 @@ struct sockbuf {
#define SOCKBUF_LOCK_ASSERT(_sb) mtx_assert(SOCKBUF_MTX(_sb), MA_OWNED)
#define SOCKBUF_UNLOCK_ASSERT(_sb) mtx_assert(SOCKBUF_MTX(_sb), MA_NOTOWNED)
/*
* Socket buffer private mbuf(9) flags.
*/
#define M_NOTREADY M_PROTO1 /* m_data not populated yet */
#define M_BLOCKED M_PROTO2 /* M_NOTREADY in front of m */
#define M_NOTAVAIL (M_NOTREADY | M_BLOCKED)
void sbappend(struct sockbuf *sb, struct mbuf *m);
void sbappend_locked(struct sockbuf *sb, struct mbuf *m);
void sbappendstream(struct sockbuf *sb, struct mbuf *m);
@ -165,10 +174,11 @@ int sblock(struct sockbuf *sb, int flags);
void sbunlock(struct sockbuf *sb);
void sballoc(struct sockbuf *, struct mbuf *);
void sbfree(struct sockbuf *, struct mbuf *);
int sbready(struct sockbuf *, struct mbuf *, int);
/*
* Return how much data is available to be taken out of socket
* bufffer right now.
* buffer right now.
*/
static inline u_int
sbavail(struct sockbuf *sb)
@ -177,7 +187,7 @@ sbavail(struct sockbuf *sb)
#if 0
SOCKBUF_LOCK_ASSERT(sb);
#endif
return (sb->sb_cc);
return (sb->sb_acc);
}
/*
@ -191,27 +201,30 @@ sbused(struct sockbuf *sb)
#if 0
SOCKBUF_LOCK_ASSERT(sb);
#endif
return (sb->sb_cc);
return (sb->sb_ccc);
}
/*
* How much space is there in a socket buffer (so->so_snd or so->so_rcv)?
* This is problematical if the fields are unsigned, as the space might
* still be negative (cc > hiwat or mbcnt > mbmax). Should detect
* overflow and return 0. Should use "lmin" but it doesn't exist now.
* still be negative (ccc > hiwat or mbcnt > mbmax).
*/
static __inline
long
static inline long
sbspace(struct sockbuf *sb)
{
long bleft;
long mleft;
long bleft, mleft;
#if 0
SOCKBUF_LOCK_ASSERT(sb);
#endif
if (sb->sb_flags & SB_STOP)
return(0);
bleft = sb->sb_hiwat - sb->sb_cc;
bleft = sb->sb_hiwat - sb->sb_ccc;
mleft = sb->sb_mbmax - sb->sb_mbcnt;
return((bleft < mleft) ? bleft : mleft);
return ((bleft < mleft) ? bleft : mleft);
}
#define SB_EMPTY_FIXUP(sb) do { \

16
usr.bin/bluetooth/btsockstat/btsockstat.c
View File

@ -255,8 +255,8 @@ hcirawpr(kvm_t *kvmd, u_long addr)
(unsigned long) pcb.so,
(unsigned long) this,
pcb.flags,
so.so_rcv.sb_cc,
so.so_snd.sb_cc,
so.so_rcv.sb_ccc,
so.so_snd.sb_ccc,
pcb.addr.hci_node);
}
} /* hcirawpr */
@ -303,8 +303,8 @@ l2caprawpr(kvm_t *kvmd, u_long addr)
"%-8lx %-8lx %6d %6d %-17.17s\n",
(unsigned long) pcb.so,
(unsigned long) this,
so.so_rcv.sb_cc,
so.so_snd.sb_cc,
so.so_rcv.sb_ccc,
so.so_snd.sb_ccc,
bdaddrpr(&pcb.src, NULL, 0));
}
} /* l2caprawpr */
@ -361,8 +361,8 @@ l2cappr(kvm_t *kvmd, u_long addr)
fprintf(stdout,
"%-8lx %6d %6d %-17.17s/%-5d %-17.17s %-5d %s\n",
(unsigned long) this,
so.so_rcv.sb_cc,
so.so_snd.sb_cc,
so.so_rcv.sb_ccc,
so.so_snd.sb_ccc,
bdaddrpr(&pcb.src, local, sizeof(local)),
pcb.psm,
bdaddrpr(&pcb.dst, remote, sizeof(remote)),
@ -467,8 +467,8 @@ rfcommpr(kvm_t *kvmd, u_long addr)
fprintf(stdout,
"%-8lx %6d %6d %-17.17s %-17.17s %-4d %-4d %s\n",
(unsigned long) this,
so.so_rcv.sb_cc,
so.so_snd.sb_cc,
so.so_rcv.sb_ccc,
so.so_snd.sb_ccc,
bdaddrpr(&pcb.src, local, sizeof(local)),
bdaddrpr(&pcb.dst, remote, sizeof(remote)),
pcb.channel,

5
usr.bin/netstat/inet.c
View File

@ -137,7 +137,7 @@ pcblist_sysctl(int proto, const char *name, char **bufp, int istcp __unused)
static void
sbtoxsockbuf(struct sockbuf *sb, struct xsockbuf *xsb)
{
xsb->sb_cc = sb->sb_cc;
xsb->sb_cc = sb->sb_ccc;
xsb->sb_hiwat = sb->sb_hiwat;
xsb->sb_mbcnt = sb->sb_mbcnt;
xsb->sb_mcnt = sb->sb_mcnt;
@ -479,7 +479,8 @@ protopr(u_long off, const char *name, int af1, int proto)
printf("%6u %6u %6u ", tp->t_sndrexmitpack,
tp->t_rcvoopack, tp->t_sndzerowin);
} else {
printf("%6u %6u ", so->so_rcv.sb_cc, so->so_snd.sb_cc);
printf("%6u %6u ",
so->so_rcv.sb_cc, so->so_snd.sb_cc);
}
if (numeric_port) {
if (inp->inp_vflag & INP_IPV4) {

2
usr.bin/netstat/netgraph.c
View File

@ -119,7 +119,7 @@ netgraphprotopr(u_long off, const char *name, int af1 __unused,
if (Aflag)
printf("%8lx ", (u_long) this);
printf("%-5.5s %6u %6u ",
name, sockb.so_rcv.sb_cc, sockb.so_snd.sb_cc);
name, sockb.so_rcv.sb_ccc, sockb.so_snd.sb_ccc);
/* Get info on associated node */
if (ngpcb.node_id == 0 || csock == -1)

3
usr.bin/netstat/unix.c
View File

@ -287,7 +287,8 @@ unixdomainpr(struct xunpcb *xunp, struct xsocket *so)
} else {
printf("%8lx %-6.6s %6u %6u %8lx %8lx %8lx %8lx",
(long)so->so_pcb, socktype[so->so_type], so->so_rcv.sb_cc,
so->so_snd.sb_cc, (long)unp->unp_vnode, (long)unp->unp_conn,
so->so_snd.sb_cc, (long)unp->unp_vnode,
(long)unp->unp_conn,
(long)LIST_FIRST(&unp->unp_refs),
(long)LIST_NEXT(unp, unp_reflink));
}

4
usr.bin/systat/netstat.c
View File

@ -333,8 +333,8 @@ enter_kvm(struct inpcb *inp, struct socket *so, int state, const char *proto)
struct netinfo *p;
if ((p = enter(inp, state, proto)) != NULL) {
p->ni_rcvcc = so->so_rcv.sb_cc;
p->ni_sndcc = so->so_snd.sb_cc;
p->ni_rcvcc = so->so_rcv.sb_ccc;
p->ni_sndcc = so->so_snd.sb_ccc;
}
}