/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
*/
#include <sys/pool_pset.h>
#include <inet/ipsec_impl.h>
#include <inet/ipsecesp.h>
#include <sys/mac_impl.h>
#include <sys/mac_client_impl.h>
#include <sys/mac_client_priv.h>
#include <sys/mac_soft_ring.h>
#include <sys/mac_flow_impl.h>
#include <sys/mac_stat.h>
static void mac_srs_update_fanout_list(mac_soft_ring_set_t *);
static void mac_srs_poll_unbind(mac_soft_ring_set_t *);
static void mac_srs_worker_unbind(mac_soft_ring_set_t *);
static int mac_srs_cpu_setup(cpu_setup_t, int, void *);
static void mac_srs_threads_unbind(mac_soft_ring_set_t *);
static void mac_srs_add_glist(mac_soft_ring_set_t *);
static void mac_srs_remove_glist(mac_soft_ring_set_t *);
static void mac_srs_fanout_list_free(mac_soft_ring_set_t *);
static int mac_compute_soft_ring_count(flow_entry_t *, int, int);
static void mac_walk_srs_and_bind(int);
static void mac_walk_srs_and_unbind(int);
extern boolean_t mac_latency_optimize;
/*
* The duration in msec we wait before signalling the soft ring
* worker thread in case packets get queued.
*/
/*
* polling is always on and is always very beneficial. It should be
* turned off with absolute care and for the rare workload (very
* low latency sensitive traffic).
*/
/*
* Need to set mac_soft_ring_max_q_cnt based on bandwidth and perhaps latency.
* Large values could end up in consuming lot of system memory and cause
* system hang.
*/
/*
* mac_tx_srs_hiwat is the queue depth threshold at which callers of
* mac_tx() will be notified of flow control condition.
*
* TCP does not honour flow control condition sent up by mac_tx().
* Thus provision is made for TCP to allow more packets to be queued
* in SRS upto a maximum of mac_tx_srs_max_q_cnt.
*
* Note that mac_tx_srs_hiwat is always be lesser than
* mac_tx_srs_max_q_cnt.
*/
/*
* mac_rx_soft_ring_count, mac_soft_ring_10gig_count:
*
* Global tunables that determines the number of soft rings to be used for
* fanning out incoming traffic on a link. These count will be used only
* when no explicit set of CPUs was assigned to the data-links.
*
* mac_rx_soft_ring_count tunable will come into effect only if
* mac_soft_ring_enable is set. mac_soft_ring_enable is turned on by
* default only for sun4v platforms.
*
* mac_rx_soft_ring_10gig_count will come into effect if you are running on a
* 10Gbps link and is not dependent upon mac_soft_ring_enable.
*
* The number of soft rings for fanout for a link or a flow is determined
* by mac_compute_soft_ring_count() routine. This routine will take into
* account mac_soft_ring_enable, mac_rx_soft_ring_count and
* mac_rx_soft_ring_10gig_count to determine the soft ring count for a link.
*
* If a bandwidth is specified, the determination of the number of soft
* rings is based on specified bandwidth, CPU speed and number of CPUs in
* the system.
*/
/*
* Every Tx and Rx mac_soft_ring_set_t (mac_srs) created gets added
* to mac_srs_g_list and mac_srs_g_lock protects mac_srs_g_list. The
* list is used to walk the list of all MAC threads when a CPU is
* coming online or going offline.
*/
/*
* Whether the SRS threads should be bound, or not.
*/
/*
* dladm command would override this.
*/
/*
* If cpu bindings are specified by user, then Tx SRS and its soft
* rings should also be bound to the CPUs specified by user. The
* CPUs for Tx bindings are at the end of the cpu list provided by
* the user. If enough CPUs are not available (for Tx and Rx
* SRSes), then the CPUs are shared by both Tx and Rx SRSes.
*/
int i; \
mac_cpus_t *srs_cpu; \
\
if (MAC_TX_SOFT_RINGS(mac_tx_srs)) { \
for (i = 0; i < mac_tx_srs->srs_tx_ring_count; i++) { \
if (cpuid != -1) { \
(void) mac_soft_ring_bind(softring, \
cpuid); \
} \
} \
} \
}
/*
* Re-targeting is allowed only for exclusive group or for primary.
*/
/* INIT and FINI ROUTINES */
void
mac_soft_ring_init(void)
{
sizeof (mac_soft_ring_set_t),
}
void
mac_soft_ring_finish(void)
{
}
static void
{
/*
* Synchronize with mac_walk_srs_bind/unbind which are callbacks from
* DR. The callbacks from DR are called with cpu_lock held, and hence
* can't wait to grab the mac perimeter. The soft ring list is hence
* protected for read access by srs_lock. Changing the soft ring list
* needs the mac perimeter and the srs_lock.
*/
mac_srs->srs_soft_ring_count = 0;
}
}
static void
{
if (mac_srs_g_list == NULL) {
} else {
}
}
static void
{
if (mac_srs == mac_srs_g_list) {
if (mac_srs_g_list != NULL)
} else {
}
}
/* POLLING SETUP AND TEAR DOWN ROUTINES */
/*
* mac_srs_client_poll_quiesce and mac_srs_client_poll_restart
*
* These routines are used to call back into the upper layer
* (primarily TCP squeue) to stop polling the soft rings or
* restart polling.
*/
void
{
return;
}
}
}
}
void
{
return;
}
}
}
}
/*
* Register the given SRS and associated soft rings with the consumer and
* enable the polling interface used by the consumer.(i.e IP) over this
* SRS and associated soft rings.
*/
void
{
return;
/*
* A SRS is capable of acting as a soft ring for cases
* where no fanout is needed. This is the case for userland
* flows.
*/
return;
/*
* TCP and UDP support DLS bypass. Squeue polling
* support implies DLS bypass since the squeue poll
* path does not have DLS processing.
*/
}
/*
* Non-TCP protocols don't support squeues. Hence we don't
* make any ring addition callbacks for non-TCP rings
*/
continue;
}
}
}
/*
* Unregister the given SRS and associated soft rings with the consumer and
* disable the polling interface used by the consumer.(i.e IP) over this
* SRS and associated soft rings.
*/
void
{
/*
* A SRS is capable of acting as a soft ring for cases
* where no protocol fanout is needed. This is the case
* for userland flows. Nothing to do here.
*/
return;
return;
}
/*
* DLS bypass is now disabled in the case of both TCP and UDP.
* Reset the soft ring callbacks to the standard 'mac_rx_deliver'
* callback. In addition, in the case of TCP, invoke IP's callback
* for ring removal.
*/
continue;
}
&softring->s_ring_lock);
}
}
}
/*
* Enable or disable poll capability of the SRS on the underlying Rx ring.
*
* There is a need to enable or disable the poll capability of an SRS over an
* Rx ring depending on the number of mac clients sharing the ring and also
* whether user flows are configured on it. However the poll state is actively
* manipulated by the SRS worker and poll threads and uncoordinated changes by
* yet another thread to the underlying capability can surprise them leading
* to assert failures. Instead we quiesce the SRS, make the changes and then
* restart the SRS.
*/
static void
{
if (!SRS_QUIESCED(mac_srs)) {
}
if (turn_off_poll_capab)
else if (mac_poll_enable)
}
if (need_restart)
}
/* CPU RECONFIGURATION AND FANOUT COMPUTATION ROUTINES */
/*
* Return the next CPU to be used to bind a MAC kernel thread.
* If a cpupart is specified, the cpu chosen must be from that
* cpu partition.
*/
static processorid_t
{
do {
return (NULL);
}
/* ARGSUSED */
static int
{
switch (what) {
case CPU_CONFIG:
case CPU_ON:
case CPU_CPUPART_IN:
break;
case CPU_UNCONFIG:
case CPU_OFF:
case CPU_CPUPART_OUT:
break;
default:
break;
}
return (0);
}
/*
* mac_compute_soft_ring_count():
*
* This routine computes the number of soft rings needed to handle incoming
* load given a flow_entry.
*
* The routine does the following:
* 1) soft rings will be created if mac_soft_ring_enable is set.
* 2) If the underlying link is a 10Gbps link, then soft rings will be
* created even if mac_soft_ring_enable is not set. The number of soft
* rings, so created, will equal mac_rx_soft_ring_10gig_count.
* 3) On a sun4v platform (i.e., mac_soft_ring_enable is set), 2 times the
* mac_rx_soft_ring_10gig_count number of soft rings will be created for a
* 10Gbps link.
*
* If a bandwidth limit is specified, the number that gets computed is
* dependent upon CPU speed, the number of Rx rings configured, and
* the bandwidth limit.
* If more Rx rings are available, less number of soft rings is needed.
*
* mac_use_bw_heuristic is another "hidden" variable that can be used to
* override the default use of soft ring count computation. Depending upon
* the usefulness of it, mac_use_bw_heuristic can later be made into a
* data-link property or removed altogether.
*
* TODO: Cleanup and tighten some of the assumptions.
*/
static int
{
int srings = 0;
/* bandwidth enabled */
bw_enabled = B_TRUE;
}
if (!bw_enabled) {
/* No bandwidth enabled */
if (mac_soft_ring_enable)
/* Is this a 10Gig link? */
/* convert to Mbps */
mac_rx_soft_ring_10gig_count > 0) {
/* This is a 10Gig link */
/*
* Use 2 times mac_rx_soft_ring_10gig_count for
* sun4v systems.
*/
if (mac_soft_ring_enable)
}
} else {
/*
* Soft ring computation using CPU speed and specified
* bandwidth limit.
*/
/* Assumption: all CPUs have the same frequency */
/* cpu_speed is in MHz; make bw in units of Mbps. */
if (bw >= 1000) {
/*
* bw is greater than or equal to 1Gbps.
* The number of soft rings required is a function
* of bandwidth and CPU speed. To keep this simple,
* let's use this rule: 1GHz CPU can handle 1Gbps.
* If bw is less than 1 Gbps, then there is no need
* for soft rings. Assumption is that CPU speeds
* (on modern systems) are at least 1GHz.
*/
/*
* Give at least 2 soft rings
* for sun4v systems
*/
srings = 2;
}
}
}
/*
* If the flent has multiple Rx SRSs, then each SRS need not
* have that many soft rings on top of it. The number of
* soft rings for each Rx SRS is found by dividing srings by
* rx_srs_cnt.
*/
if (rx_srs_cnt > 1) {
int remainder;
if (remainder != 0)
srings++;
/*
* Fanning out to 1 soft ring is not very useful.
* Set it as well to 0 and mac_srs_fanout_init()
* will take care of creating a single soft ring
* for proto fanout.
*/
if (srings == 1)
srings = 0;
}
/* Do some more massaging */
return (srings);
}
/*
* mac_tx_cpu_init:
* set up CPUs for Tx interrupt re-targeting and Tx worker
* thread binding
*/
static void
{
int i, j;
}
if (MAC_TX_SOFT_RINGS(tx_srs)) {
for (i = 0; i < tx_srs->srs_tx_ring_count; i++) {
if (j < 0)
} else {
/*
* Bind interrupt to the next CPU available
* and leave the worker unbound.
*/
worker_cpuid = -1;
}
if (MAC_RING_RETARGETABLE(ring) &&
srs_cpu->mc_tx_intr_cpu[i] =
} else {
}
j--;
}
} else {
/* Tx mac_ring_handle_t is stored in st_arg2 */
srs_cpu->mc_tx_fanout_cpus[0] =
} else {
}
}
}
/*
* Assignment of user specified CPUs to a link.
*
* Minimum CPUs required to get an optimal assignmet:
* For each Rx SRS, atleast two CPUs are needed if mac_latency_optimize
* flag is set -- one for polling, one for fanout soft ring.
* If mac_latency_optimize is not set, then 3 CPUs are needed -- one
* for polling, one for SRS worker thread and one for fanout soft ring.
*
* The CPUs needed for Tx side is equal to the number of Tx rings
* the link is using.
*
* mac_flow_user_cpu_init() categorizes the CPU assignment depending
* upon the number of CPUs in 3 different buckets.
*
* In the first bucket, the most optimal case is handled. The user has
* passed enough number of CPUs and every thread gets its own CPU.
*
* The second and third are the sub-optimal cases. Enough CPUs are not
* available.
*
* The second bucket handles the case where atleast one distinct CPU is
* is available for each of the Rx rings (Rx SRSes) and Tx rings (Tx
* SRS or soft rings).
*
* In the third case (worst case scenario), specified CPU count is less
* than the Rx rings configured for the link. In this case, we round
*/
static void
{
int i, srs_cnt;
/*
* The check for nbc_ncpus to be within limits for
* the user specified case was done earlier and if
* not within limits, an error would have been
* returned to the user.
*/
/*
* interrupt has been re-targetted. Poll
* thread needs to be bound to interrupt
* CPU.
*
* Find where in the list is the intr
* CPU and swap it with the first one.
* We will be using the first CPU in the
* list for poll.
*/
for (i = 0; i < no_of_cpus; i++) {
break;
}
}
/*
* Requirements:
* The number of CPUs that each Rx ring needs is dependent
* upon mac_latency_optimize flag.
* 1) If set, atleast 2 CPUs are needed -- one for
* polling, one for fanout soft ring.
* 2) If not set, then atleast 3 CPUs are needed -- one
* for polling, one for srs worker thread, and one for
* fanout soft ring.
*/
/* How many CPUs are needed for Tx side? */
/* CPUs needed for Rx SRSes poll and worker threads */
/* Has the user provided enough CPUs? */
/*
* Best case scenario. There is enough CPUs. All
* Rx rings will get their own set of CPUs plus
* Tx soft rings will get their own.
*/
/*
* fanout_cpu_cnt is the number of CPUs available
* for Rx side fanout soft rings.
*/
/*
* Divide fanout_cpu_cnt by rx_srs_cnt to find
* out how many fanout soft rings each Rx SRS
* can have.
*/
/* fanout_cnt_per_srs should not be > MAX_SR_FANOUT */
/* Do the assignment for the default Rx ring */
cpu_cnt = 0;
/* Retarget the interrupt to the same CPU as the poll */
for (i = 0; i < fanout_cnt_per_srs; i++)
/* Do the assignment for h/w Rx SRSes */
cpu_cnt = 0;
for (srs_cnt = 1;
if (rx_srs->srs_fanout_state ==
}
/* The first CPU in the list is the intr CPU */
for (i = 0; i < fanout_cnt_per_srs; i++) {
srs_cpu->mc_rx_fanout_cpus[i] =
}
}
}
goto tx_cpu_init;
}
/*
* Sub-optimal case.
* We have the following information:
* no_of_cpus - no. of cpus that user passed.
* rx_srs_cnt - no. of rx rings.
* reqd_rx_cpu_cnt = mac_latency_optimize?rx_srs_cnt*2:rx_srs_cnt*3
* reqd_tx_cpu_cnt - no. of cpus reqd. for Tx side.
* reqd_poll_worker_cnt = mac_latency_optimize?rx_srs_cnt:rx_srs_cnt*2
*/
/*
* If we bind the Rx fanout soft rings to the same CPUs
*/
/*
* If mac_latency_optimize is not set, are there
* enough CPUs to assign a CPU for worker also?
*/
/*
* Zero'th Rx SRS is the default Rx ring. It is not
* associated with h/w Rx ring.
*/
cpu_cnt = 0;
/* Retarget the interrupt to the same CPU as the poll */
((!mac_latency_optimize && worker_assign) ?
/* Do CPU bindings for SRSes having h/w Rx rings */
cpu_cnt = 0;
for (srs_cnt = 1;
if (rx_srs->srs_fanout_state ==
}
((!mac_latency_optimize && worker_assign) ?
srs_cpu->mc_rx_fanout_cpus[0] =
cpu_cnt++;
}
}
goto tx_cpu_init;
}
/*
* Real sub-optimal case. Not enough CPUs for poll and
* Tx soft rings. Do a round robin assignment where
* each Rx SRS will get the same CPU for poll, worker
* and fanout soft ring.
*/
cpu_cnt = 0;
/* Retarget the interrupt to the same CPU as the poll */
if (++cpu_cnt >= no_of_cpus)
cpu_cnt = 0;
}
/*
* Copy the user specified CPUs to the effective CPUs
*/
}
}
/*
* mac_flow_cpu_init():
*
* Each SRS has a mac_cpu_t structure, srs_cpu. This routine fills in
* the CPU binding information in srs_cpu for all Rx SRSes associated
* with a flent.
*/
static void
{
/*
* The maximum number of CPUs available can either be
* the number of CPUs in the pool or the number of CPUs
* in the system.
*/
/*
* Compute the number of soft rings needed on top for each Rx
* SRS. "rx_srs_cnt-1" indicates the number of Rx SRS
* associated with h/w Rx rings. Soft ring count needed for
* each h/w Rx SRS is computed and the same is applied to
* software classified Rx SRS. The first Rx SRS in fe_rx_srs[]
* is the software classified Rx SRS.
*/
if (soft_ring_cnt == 0) {
/*
* Even when soft_ring_cnt is 0, we still need
* to create a soft ring for TCP, UDP and
* OTHER. So set it to 1.
*/
soft_ring_cnt = 1;
}
for (j = 0; j < soft_ring_cnt; j++) {
}
/* increment ncpus to account for polling cpu */
if (!mac_latency_optimize) {
}
}
nscpus = 0;
}
}
/*
* Copy cpu list to fe_effective_props
* without duplicates.
*/
k = 0;
for (i = 0; i < nscpus; i++) {
for (j = 0; j < k; j++) {
break;
}
if (j == k)
}
}
/*
* DATAPATH SETUP ROUTINES
*/
/*
* mac_srs_fanout_list_alloc:
*
* The underlying device can expose upto MAX_RINGS_PER_GROUP worth of
* rings to a client. In such a case, MAX_RINGS_PER_GROUP worth of
* array space is needed to store Tx soft rings. Thus we allocate so
* much array space for srs_tx_soft_rings.
*
* And when it is an aggr, again we allocate MAX_RINGS_PER_GROUP worth
* of space to st_soft_rings. This array is used for quick access to
* soft ring associated with a pseudo Tx ring based on the pseudo
* ring's index (mr_index).
*/
static void
{
kmem_zalloc(sizeof (mac_soft_ring_t *) *
kmem_zalloc(sizeof (mac_soft_ring_t *) *
}
} else {
KM_SLEEP);
KM_SLEEP);
KM_SLEEP);
}
}
static void
{
if (!mac_srs_thread_bind)
return;
return;
if (clear)
}
static void
{
return;
return;
if (clear)
}
/*
* Re-target interrupt to the passed CPU. If re-target is successful,
* set mc_rx_intr_cpu to the re-targeted CPU. Otherwise set it to -1.
*/
void
{
/*
* Don't re-target the interrupt for these cases:
* 1) ring is NULL
* 2) the interrupt is shared (mi_ddi_shared)
* 3) ddi_handle is NULL and !primary
* 4) primary, ddi_handle is NULL but fe_rx_srs_cnt > 2
* Case 3 & 4 are because of mac_client_intr_cpu() routine.
* This routine will re-target fixed interrupt for primary
* mac client if the client has only one ring. In that
* case, mc_rx_intr_cpu will already have the correct value.
*/
return;
}
return;
return;
/* Drop the cpu_lock as set_intr_affinity() holds it */
else
}
/*
* Re-target Tx interrupts
*/
void
{
int i;
if (MAC_TX_SOFT_RINGS(mac_srs)) {
for (i = 0; i < mac_srs->srs_tx_ring_count; i++) {
continue;
}
/*
* Drop the cpu_lock as set_intr_affinity()
* holds it
*/
cpuid) == DDI_SUCCESS) {
} else {
}
}
} else {
return;
}
if (MAC_RING_RETARGETABLE(ring)) {
cpuid) == DDI_SUCCESS)) {
} else {
}
}
}
}
/*
* When a CPU comes back online, bind the MAC kernel threads which
* were previously bound to that CPU, and had to be unbound because
* the CPU was going away.
*
* These functions are called with cpu_lock held and hence we can't
* cv_wait to grab the mac perimeter. Since these functions walk the soft
* ring list of an SRS without being in the perimeter, the list itself
* is protected by the SRS lock.
*/
static void
{
goto done;
}
}
}
/* Next tackle the soft rings associated with the srs */
}
}
}
done:
}
/*
* Change the priority of the SRS's poll and worker thread. Additionally,
* update the priority of the worker threads for the SRS's soft rings.
* Need to modify any associated squeue threads.
*/
void
{
}
return;
}
}
/*
* Change the receive bandwidth limit.
*/
static void
{
/* Reset bandwidth limit */
}
}
} else {
/*
* Give twice the queuing capability before
*/
}
}
}
done:
}
/* Change the transmit bandwidth limit */
static void
{
/*
* srs->srs_tx->st_func do not hold srs->srs_lock while accessing
* st_mode and related fields, which are modified by the code below.
*/
/* Reset bandwidth limit */
if (mac_tx_serialize ||
(ring_info & MAC_RING_TX_SERIALIZE)) {
} else {
}
} else if (tx_mode == SRS_TX_BW_FANOUT) {
} else if (tx_mode == SRS_TX_BW_AGGR) {
}
} else {
/*
* Give twice the queuing capability before
*/
tx_mode != SRS_TX_BW_AGGR) {
if (tx_mode == SRS_TX_SERIALIZE ||
tx_mode == SRS_TX_DEFAULT) {
} else if (tx_mode == SRS_TX_FANOUT) {
} else if (tx_mode == SRS_TX_AGGR) {
} else {
ASSERT(0);
}
}
}
done:
}
/*
* The uber function that deals with any update to bandwidth limits.
*/
void
{
int count;
}
void
{
}
}
/*
* When the first sub-flow is added to a link, we disable polling on the
* link and also modify the entry point to mac_rx_srs_subflow_process.
* (polling is disabled because with the subflow added, accounting
* for polling needs additional logic, it is assumed that when a subflow is
* added, we can take some hit as a result of disabling polling rather than
* adding more complexity - if this becomes a perf. issue we need to
* re-rvaluate this logic). When the last subflow is removed, we turn back
* polling and also reset the entry point to mac_rx_srs_process.
*
* In the future if there are multiple SRS, we can simply
* take one and give it to the flow rather than disabling polling and
* resetting the entry point.
*/
void
{
int i;
/* Tell mac_srs_poll_state_change to disable polling if necessary */
/*
* If receive function has already been configured correctly for
* current subflow configuration, do nothing.
*/
return;
for (i = 0; i < rx_srs_cnt; i++) {
}
/*
* Change the S/W classifier so that we can land in the
* correct processing function with correct argument.
* If all subflows have been removed we can revert to
* mac_rx_srsprocess, else we need mac_rx_srs_subflow_process.
*/
}
static void
{
mac_srs->srs_tcp_ring_count = 0;
mac_srs->srs_udp_ring_count = 0;
mac_srs->srs_oth_ring_count = 0;
mac_srs->srs_tx_ring_count = 0;
return;
}
} else {
}
}
}
void
{
/*
* TCP and UDP support DLS bypass. In addition TCP
* squeue can also poll their corresponding soft rings.
*/
/*
* Make a call in IP to get a TCP squeue assigned to
* this softring to maintain full CPU locality through
* the stack and allow the squeue to be able to poll
* the softring so the flow control can be pushed
* all the way to H/W.
*/
(mac_resource_t *)&mrf);
}
/*
* Non-TCP protocols don't support squeues. Hence we
* don't make any ring addition callbacks for non-TCP
* rings. Now create the UDP softring and allow it to
* bypass the DLS layer.
*/
}
/* Create the Oth softrings which has to go through the DLS */
}
/*
* This routine associates a CPU or a set of CPU to process incoming
* traffic from a mac client. If multiple CPUs are specified, then
* so many soft rings are created with each soft ring worker thread
* bound to a CPU in the set. Each soft ring in turn will be
* associated with an squeue and the squeue will be moved to the
* same CPU as that of the soft ring's.
*/
static void
{
/* fanout state is REINIT. Set it back to INIT */
/* how many are present right now */
/* new request */
if (new_fanout_cnt > srings_present) {
/* soft rings increased */
for (i = mac_rx_srs->srs_tcp_ring_count;
i < new_fanout_cnt; i++) {
/*
* Create the protocol softrings and set the
* DLS bypass where possible.
*/
}
} else if (new_fanout_cnt < srings_present) {
/* soft rings decreased */
if (new_fanout_cnt == 1) {
}
/* Get rid of extra soft rings */
for (i = new_fanout_cnt;
i < mac_rx_srs->srs_tcp_ring_count; i++) {
(void *)mcip->mci_resource_arg,
}
mac_rx_srs->srs_tcp_soft_rings[i]);
mac_rx_srs->srs_udp_soft_rings[i]);
mac_rx_srs->srs_oth_soft_rings[i]);
}
}
for (i = 0; i < mac_rx_srs->srs_tcp_ring_count; i++) {
cpuid);
cpuid);
cpuid);
}
}
/*
* Bind Tx srs and soft ring threads too. Let's bind tx
* srs to the last cpu in mrp list.
*/
if (mac_tx_srs != NULL) {
}
}
/*
*/
void
{
int i;
int soft_ring_cnt;
/*
* Remove the no soft ring flag and we will adjust it
* appropriately further down.
*/
/*
* Ring count can be 0 if no fanout is required and no cpu
* were specified. Leave the SRS worker and poll thread
* unbound
*/
/* Step 1: bind cpu contains cpu list where threads need to bind */
if (soft_ring_cnt > 0) {
for (i = 0; i < soft_ring_cnt; i++) {
/* Create the protocol softrings */
}
/*
* Bind Tx srs and soft ring threads too.
* Let's bind tx srs to the last cpu in
* mrp list.
*/
if (mac_tx_srs == NULL) {
goto alldone;
}
} else {
/*
* For a subflow, mrp_workerid and mrp_pollid
* is not set.
*/
goto no_softrings;
}
if (soft_ring_cnt > 1)
return;
/* Create the protocol softrings */
} else {
/*
* This is the case when there is no fanout which is
* true for subflows.
*/
}
}
/*
* mac_fanout_setup:
*
* Calls mac_srs_fanout_init() or modify() depending upon whether
* the SRS is getting initialized or re-initialized.
*/
void
{
int i, rx_srs_cnt;
/*
* This is an aggregation port. Fanout will be setup
* over the aggregation itself.
*/
return;
/*
* Set up the fanout on the tx side only once, with the
* first rx SRS. The CPU binding, fanout, and bandwidth
* criteria are common to both RX and TX, so
* initializing them along side avoids redundant code.
*/
/* No fanout for subflows */
cpupart);
return;
}
else
/*
* Set up fanout for both SW (0th SRS) and HW classified
* SRS (the rest of Rx SRSs in flent).
*/
for (i = 0; i < rx_srs_cnt; i++) {
if (i != 0)
mac_tx_srs = NULL;
switch (mac_rx_srs->srs_fanout_state) {
case SRS_FANOUT_UNINIT:
cpupart);
break;
case SRS_FANOUT_INIT:
break;
case SRS_FANOUT_REINIT:
break;
default:
break;
}
}
}
/*
* mac_srs_create:
*
* Create a mac_soft_ring_set_t (SRS). If soft_ring_fanout_type is
* SRST_TX, an SRS for Tx side is created. Otherwise an SRS for Rx side
* processing is created.
*
* Details on Rx SRS:
* Create a SRS and also add the necessary soft rings for TCP and
* non-TCP based on fanout type and count specified.
*
* mac_soft_ring_fanout, mac_srs_fanout_modify (?),
* mac_soft_ring_stop_workers, mac_soft_ring_set_destroy, etc need
* to be heavily modified.
*
* mi_soft_ring_list_size, mi_soft_ring_size, etc need to disappear.
*/
{
/*
* Get the bandwidth control structure from the flent. Get
* rid of any residual values in the control structure for
* the tx bw struct and also for the rx, if the rx srs is
* the 1st one being brought up (the rx bw ctl struct may
* be shared by multiple SRSs)
*/
if (is_tx_srs) {
} else {
/*
* The bw counter (stored in the flent) is shared
* by SRS's within an rx group.
*/
/* First rx SRS, clear the bw structure */
if (flent->fe_rx_srs_cnt == 0)
/*
* It is better to panic here rather than just assert because
* on a non-debug kernel we might end up courrupting memory
* and making it difficult to debug.
*/
panic("Array Overrun detected due to MAC client %p "
" having more rings than %d", (void *)mcip,
}
flent->fe_rx_srs_cnt++;
}
/*
* For a flow we use the underlying MAC client's priority range with
* the priority value to find an absolute priority value. For a MAC
* client we use the MAC client's maximum priority as the value.
*/
} else {
}
/*
* We need to insert the SRS in the global list before
* binding the SRS and SR threads. Otherwise there is a
* is a small window where the cpu reconfig callbacks
* may miss the SRS in the list walk and DR could fail
* as there are bound threads.
*/
/* Initialize bw limit */
/*
* Give twice the queuing capability before
*/
} else {
}
/*
* We use the following policy to control Receive
* Side Dynamic Polling:
* 1) We switch to poll mode anytime the processing thread causes
* a backlog to build up in SRS and its associated Soft Rings
* (sr_poll_pkt_cnt > 0).
* 2) As long as the backlog stays under the low water mark
* (sr_lowat), we poll the H/W for more packets.
* 3) If the backlog (sr_poll_pkt_cnt) exceeds low water mark, we
* stay in poll mode but don't poll the H/W for more packets.
* 4) Anytime in polling mode, if we poll the H/W for packets and
* find nothing plus we have an existing backlog
* (sr_poll_pkt_cnt > 0), we stay in polling mode but don't poll
* the H/W for packets anymore (let the polling thread go to sleep).
* 5) Once the backlog is relived (packets are processed) we reenable
* polling (by signalling the poll thread) only when the backlog
* dips below sr_poll_thres.
* 6) sr_hiwat is used exclusively when we are not polling capable
* and is used to decide when to drop packets so the SRS queue
* length doesn't grow infinitely.
*/
if (!is_tx_srs) {
/* Low water mark needs to be less than high water mark */
(mac_soft_ring_max_q_cnt >> 2);
/* Poll threshold need to be half of low water mark or less */
if (mac_latency_optimize)
else
}
if (is_tx_srs) {
/* Handle everything about Tx SRS and return */
goto done;
}
else
/* Is the mac_srs created over the RX default group? */
}
/*
* Some drivers require serialization and don't send
* packet chains in interrupt context. For such
* drivers, we should always queue in soft ring
* so that we get a chance to switch into a polling
* mode under backlog.
*/
if (ring_info & MAC_RING_RX_ENQUEUE)
}
done:
return (mac_srs);
}
/*
* Figure out the number of soft rings required. Its dependant on
* if protocol fanout is required (for LINKs), global settings
* require us to do fanout for performance (based on mac_soft_ring_enable),
* or user has specifically requested fanout.
*/
static uint32_t
{
/* no fanout for subflows */
switch (link_type) {
case SRST_FLOW:
break;
case SRST_LINK:
break;
}
}
/* A VNIC is being created */
}
}
return (fanout_type);
}
/*
* Change a group from h/w to s/w classification.
*/
void
{
/*
* Remove the SRS associated with the HW ring.
* As a result, polling will be disabled.
*/
}
(void) mac_start_ring(ring);
/*
* We need to perform SW classification
* for packets landing in these rings
*/
}
}
/*
* Create the Rx SRS for S/W classifier and for each ring in the
* group (if exclusive group). Also create the Tx SRS.
*/
void
{
pool_lock();
pool_unlock();
}
/*
* Set up the RX SRSs. If the S/W SRS is not set, set it up, if there
* is a group associated with this MAC client, set up SRSs for individual
* h/w rings.
*/
void
{
/* Create the SRS for S/W classification if none exists */
/* Setup the Rx SRS */
}
return;
/*
* fanout for default SRS is done when default SRS are created
* above. As each ring is added to the group, we setup the
* SRS and fanout to it.
*/
case MAC_GROUP_STATE_RESERVED:
case MR_INUSE:
case MR_FREE:
break;
(void) mac_start_ring(ring);
/*
* Since the group is exclusively ours create
* an SRS for this ring to allow the
* individual SRS to dynamically poll the
* ring. Do this only if the client is not
* a VLAN MAC client, since for VLAN we do
* s/w classification for the VID check, and
* if it has a unicast address.
*/
if ((mcip->mci_state_flags &
VLAN_ID_NONE) {
break;
}
break;
default:
"srs_setup: mcip = %p "
"trying to add UNKNOWN ring = %p\n",
break;
}
}
break;
case MAC_GROUP_STATE_SHARED:
/*
* Set all rings of this group to software classified.
*
* If the group is current RESERVED, the existing mac
* client (the only client on this group) is using
* this group exclusively. In that case we need to
* disable polling on the rings of the group (if it
* was enabled), and free the SRS associated with the
* rings.
*/
break;
default:
break;
}
}
/*
* Set up the TX SRS.
*/
void
{
int cnt;
int ringcnt;
/*
* If we are opened exclusively (like aggr does for aggr_ports),
* don't set up Tx SRS and Tx soft rings as they won't be used.
* The same thing has to be done for Rx side also. See bug:
* 6880080
*/
/*
* If we have rings, start them here.
*/
return;
(void) mac_start_ring(ring);
}
}
return;
}
}
}
/*
* Remove all the RX SRSs. If we want to remove only the SRSs associated
* with h/w rings, leave the S/W SRS alone. This is used when we want to
* move the MAC client from one group to another, so we need to teardown
* on the h/w SRSs.
*/
void
{
int i;
for (i = 0; i < count; i++) {
if (i == 0 && hwonly)
continue;
flent->fe_rx_srs_cnt--;
}
}
/*
* Remove the TX SRS.
*/
void
{
return;
switch (link_type) {
case SRST_FLOW:
/*
* For flows, we need to work with passed
*/
break;
case SRST_LINK:
/*
* The ring itself will be stopped when
* we release the group or in the
* mac_datapath_teardown (for the default
* group)
*/
}
break;
default:
break;
}
}
/*
* This is the group state machine.
*
* The state of an Rx group is given by
* the following table. The default group and its rings are started in
* mac_start itself and the default group stays in SHARED state until
* mac_stop at which time the group and rings are stopped and and it
* reverts to the Registered state.
*
* Typically this function is called on a group after adding or removing a
* client from it, to find out what should be the new state of the group.
* If the new state is RESERVED, then the client that owns this group
* exclusively is also returned. Note that adding or removing a client from
* a group could also impact the default group and the caller needs to
* evaluate the effect on the default group.
*
* Group type # of clients mi_nactiveclients Group State
* in the group
*
* Non-default 0 N.A. REGISTERED
* Non-default 1 N.A. RESERVED
*
* Default 0 N.A. SHARED
* Default 1 1 RESERVED
* Default 1 > 1 SHARED
* Default > 1 N.A. SHARED
*
* For a TX group, the following is the state table.
*
* Group type # of clients Group State
* in the group
*
* Non-default 0 REGISTERED
* Non-default 1 RESERVED
*
* Default 0 REGISTERED
* Default 1 RESERVED
* Default > 1 SHARED
*/
{
*group_only_mcip = NULL;
/* Non-default group */
if (MAC_GROUP_NO_CLIENT(grp))
return (MAC_GROUP_STATE_REGISTERED);
if (*group_only_mcip != NULL)
return (MAC_GROUP_STATE_RESERVED);
return (MAC_GROUP_STATE_SHARED);
}
/* Default group */
if (MAC_GROUP_NO_CLIENT(grp)) {
if (rx_group)
return (MAC_GROUP_STATE_SHARED);
else
return (MAC_GROUP_STATE_REGISTERED);
}
if (*group_only_mcip == NULL)
return (MAC_GROUP_STATE_SHARED);
return (MAC_GROUP_STATE_SHARED);
return (MAC_GROUP_STATE_RESERVED);
}
/*
* OVERVIEW NOTES FOR DATAPATH
* ===========================
*
* Create an SRS and setup the corresponding flow function and args.
* Add a classification rule for the flow specified by 'flent' and program
* the hardware classifier when applicable.
*
* Rx ring assignment, SRS, polling and B/W enforcement
* ----------------------------------------------------
*
* We try to use H/W classification on NIC and assign traffic to a
* MAC address to a particular Rx ring. There is a 1-1 mapping
* between a SRS and a Rx ring. The SRS (short for soft ring set)
* dynamically switches the underlying Rx ring between interrupt
* and polling mode and enforces any specified B/W control.
*
* There is always a SRS created and tied to each H/W and S/W rule.
* Whenever we create a H/W rule, we always add the the same rule to
* S/W classifier and tie a SRS to it.
*
* In case a B/W control is specified, its broken into bytes
* per ticks and as soon as the quota for a tick is exhausted,
* the underlying Rx ring is forced into poll mode for remianing
* tick. The SRS poll thread only polls for bytes that are
* allowed to come in the SRS. We typically let 4x the configured
* B/W worth of packets to come in the SRS (to prevent unnecessary
* drops due to bursts) but only process the specified amount.
*
* A Link (primary NIC, VNIC, VLAN or aggr) can have 1 or more
* Rx rings (and corresponding SRSs) assigned to it. The SRS
* in turn can have softrings to do protocol level fanout or
* softrings to do S/W based fanout or both. In case the NIC
* has no Rx rings, we do S/W classification to respective SRS.
* The S/W classification rule is always setup and ready. This
* allows the MAC layer to reassign Rx rings whenever needed
* but packets still continue to flow via the default path and
* getting S/W classified to correct SRS.
*
* In other cases where a NIC or VNIC is plumbed, our goal is use
* H/W classifier and get two Rx ring assigned for the Link. One
* for TCP and one for UDP|SCTP. The respective SRS still do the
* polling on the Rx ring. For Link that is plumbed for IP, there
* is a TCP squeue which also does polling and can control the
* the Rx ring directly (where SRS is just pass through). For
* the following cases, the SRS does the polling underneath.
* 1) non IP based Links (Links which are not plumbed via ifconfig)
* and paths which have no IP squeues (UDP & SCTP)
* 2) If B/W control is specified on the Link
* 3) If S/W fanout is secified
*
* Note1: As of current implementation, we try to assign only 1 Rx
* ring per Link and more than 1 Rx ring for primary Link for
* H/W based fanout. We always create following softrings per SRS:
* 1) TCP softring which is polled by TCP squeue where possible
* (and also bypasses DLS)
* 3) OTH softring which goes via DLS (currently deal with IPv6
*
* It is necessary to create 3 softrings since SRS has to poll
* the single Rx ring underneath and enforce any link level B/W
* control (we can't switch the Rx ring in poll mode just based
* on TCP squeue if the same Rx ring is sharing UDP and other
* traffic as well). Once polling is done and any Link level B/W
* control is specified, the packets are assigned to respective
* softring based on protocol. Since TCP has IP based squeue
* which benefits by polling, we separate TCP packets into
* its own softring which can be polled by IP squeue. We need
* the DLS layer which has heavy performance advanatges and we
* need a softring (OTH) for rest.
*
* ToDo: The 3 softrings for protocol are needed only till we can
* get rid of DLS from datapath, make IPv4 and IPv6 paths
* symmetric (deal with mac_header_info for v6 and polling for
* IPv4 TCP - ip_accept_tcp is IPv4 specific although squeues
* are generic), and bring SAP based classification to MAC layer
*
* H/W and S/W based fanout and multiple Rx rings per Link
* -------------------------------------------------------
*
* In case, fanout is requested (or determined automatically based
* on Link speed and processor speed), we try to assign multiple
* Rx rings per Link with their respective SRS. In this case
* the NIC should be capable of fanning out incoming packets between
* the assigned Rx rings (H/W based fanout). All the SRS
* individually switch their Rx ring between interrupt and polling
* mode but share a common B/W control counter in case of Link
* level B/W is specified.
*
* If S/W based fanout is specified in lieu of H/W based fanout,
* the Link SRS creates the specified number of softrings for
* each protocol (TCP, UDP, OTH). Incoming packets are fanned
* out to the correct softring based on their protocol and
* protocol specific hash function.
*
* Primary and non primary MAC clients
* -----------------------------------
*
* The NICs, VNICs, Vlans, and Aggrs are typically termed as Links
* and are a Layer 2 construct.
*
* Primary NIC:
* The Link that owns the primary MAC address and typically
* is used as the data NIC in non virtualized cases. As such
* H/W resources are preferntially given to primary NIC. As
* far as code is concerned, there is no difference in the
* primary NIC vs VNICs. They are all treated as Links.
* At the very first call to mac_unicast_add() we program the S/W
* classifier for the primary MAC address, get a soft ring set
* (and soft rings based on 'ip_soft_ring_cnt')
* and a Rx ring assigned for polling to get enabled.
* When IP get plumbed and negotiates polling, we can
* let squeue do the polling on TCP softring.
*
* VNICs:
* Same as any other Link. As long as the H/W resource assignments
* are equal, the data path and setup for all Links is same.
*
* Flows:
* Can be configured on Links. They have their own SRS and the
* S/W classifier is programmed appropriately based on the flow.
* The flows typically deal with layer 3 and above and
* creates a soft ring set specific to the flow. The receive
* side function is switched from mac_rx_srs_process to
* mac_rx_srs_subflow_process which first tries to assign the
* packet to appropriate flow SRS and failing which assigns it
* to link SRS. This allows us to avoid the layered approach
* which gets complex.
*
* By the time mac_datapath_setup() completes, we already have the
* soft rings set, Rx rings, soft rings, etc figured out and both H/W
* and S/W classifiers programmed. IP is not plumbed yet (and might
* never be for Virtual Machines guest OS path). When IP is plumbed
* (for both NIC and VNIC), we do a capability negotiation for polling
* and upcall functions etc.
*
* Rx ring Assignement NOTES
* -------------------------
*
* For NICs which have only 1 Rx ring (we treat NICs with no Rx rings
* as NIC with a single default ring), we assign the only ring to
* primary Link. The primary Link SRS can do polling on it as long as
* it is the only link in use and we compare the MAC address for unicast
* packets before accepting an incoming packet (there is no need for S/W
* classification in this case). We disable polling on the only ring the
* moment 2nd link gets created (the polling remains enabled even though
* there are broadcast and * multicast flows created).
*
* If the NIC has more than 1 Rx ring, we assign the default ring (the
* 1st ring) to deal with broadcast, multicast and traffic for other
* NICs which needs S/W classification. We assign the primary mac
* addresses to another ring by specifiying a classification rule for
* primary unicast MAC address to the selected ring. The primary Link
* (and its SRS) can continue to poll the assigned Rx ring at all times
* independantly.
*
* Note: In future, if no fanout is specified, we try to assign 2 Rx
* rings for the primary Link with the primary MAC address + TCP going
* to one ring and primary MAC address + UDP|SCTP going to other ring.
* Any remaining traffic for primary MAC address can go to the default
* Rx ring and get S/W classified. This way the respective SRSs don't
* need to do proto fanout and don't need to have softrings at all and
* can poll their respective Rx rings.
*
* As an optimization, when a new NIC or VNIC is created, we can get
* only one Rx ring and make it a TCP specific Rx ring and use the
* H/W default Rx ring for the rest (this Rx ring is never polled).
*
* For clients that don't have MAC address, but want to receive and
* transmit packets (e.g, bpf, gvrp etc.), we need to setup the datapath.
* For such clients (identified by the MCIS_NO_UNICAST_ADDR flag) we
* always give the default group and use software classification (i.e.
* even if this is the only client in the default group, we will
* leave group as shared).
*/
int
{
int err;
switch (link_type) {
case SRST_FLOW:
return (0);
case SRST_LINK:
/* Default RX group */
/* Default TX group */
if (no_unicast) {
goto grp_found;
}
(mrp->mrp_nrxrings > 0 ||
(mrp->mrp_ntxrings > 0 ||
/*
* By default we have given the primary all the rings
* i.e. the default group. Let's see if the primary
* needs to be relocated so that the addition of this
* client doesn't impact the primary's performance,
* i.e. if the primary is in the default group and
* we add this client, the primary will lose polling.
* We do this only for NICs supporting dynamic ring
* grouping and only when this is the first client
* after the primary (i.e. nactiveclients is 2)
*/
}
/*
* Check to see if we can get an exclusive group for
* this mac address or if there already exists a
* group that has this mac address (case of VLANs).
* If no groups are available, use the default group.
*/
goto setup_failed;
}
/*
* Check to see if we can get an exclusive group for
* this mac client. If no groups are available, use
* the default group.
*/
goto setup_failed;
}
/*
* Some NICs don't support any Rx rings, so there may not
* even be a default group.
*/
if (rgroup != default_rgroup &&
if (mip->mi_rx_group_type ==
}
}
/*
* Add the client to the group. This could cause
* either this group to move to the shared state or
* cause the default group to move to the shared state.
* The actions on this group are done here, while the
* actions on the default group are postponed to
* the end of this function.
*/
}
if (tgroup != default_tgroup &&
if (mip->mi_tx_group_type ==
}
}
}
/*
* Setup the Rx and Tx SRSes. If we got a pristine group
* exclusively above, mac_srs_group_setup would simply create
* the required SRSes. If we ended up sharing a previously
* reserved group, mac_srs_group_setup would also dismantle the
* SRSes of the previously exclusive group
*/
/* We are setting up minimal datapath only */
if (no_unicast)
break;
/* Program the S/W Classifer */
goto setup_failed;
/* Program the H/W Classifier */
goto setup_failed;
/* (Re)init the v6 token & local addr used by link protection */
break;
default:
break;
}
/*
* All broadcast and multicast traffic is received only on the default
* group. If we have setup the datapath for a non-default group above
* then move the default group to shared state to allow distribution of
* incoming broadcast traffic to the other groups and dismantle the
* SRSes over the default group.
*/
if (rgroup != default_rgroup) {
if (default_rgroup->mrg_state ==
pool_lock();
cpupart);
pool_unlock();
}
}
/*
* If we get an exclusive group for a VLAN MAC client we
* need to take the s/w path to make the additional check for
* the vid. Disable polling and set it to s/w classification.
* Similarly for clients that don't have a unicast address.
*/
}
}
return (0);
/* Switch the primary back to default group */
if (reloc_pmcip != NULL) {
(void) mac_rx_switch_group(reloc_pmcip,
}
return (err);
}
void
{
switch (link_type) {
case SRST_FLOW:
return;
case SRST_LINK:
/* Stop sending packets */
/* Stop the packets coming from the H/W */
int err;
if (err != 0) {
" address because of error 0x%x",
}
}
/* Stop the packets coming from the S/W classifier */
/* Now quiesce and destroy all SRS and soft rings */
/*
* Release our hold on the group as well. We need
* to check if the shared group has only one client
* left who can use it exclusively. Also, if we
* were the last client, release the group.
*/
if (next_state == MAC_GROUP_STATE_RESERVED) {
/*
* Only one client left on this RX group.
*/
/*
* The only remaining client has exclusive
* access on the group. Allow it to
* dynamically poll the H/W rings etc.
*/
} else if (next_state == MAC_GROUP_STATE_REGISTERED) {
/*
* This is a non-default group being freed up.
* We need to reevaluate the default group
* to see if the primary client can get
* exclusive access to the default group.
*/
if (mip->mi_rx_group_type ==
}
}
} else {
}
}
/*
* Remove the client from the TX group. Additionally, if
* this a non-default group, then we also need to release
* the group.
*/
if (next_state == MAC_GROUP_STATE_REGISTERED) {
if (group != default_group) {
if (mip->mi_tx_group_type ==
}
}
/*
* If the default group is reserved,
* then we need to set the effective
* rings as we would have given
* back some rings when the group
* was released
*/
if (mip->mi_tx_group_type ==
}
} else {
int cnt;
int ringcnt;
/*
* Stop all the rings except the
* default ring.
*/
(mac_ring_t *)
}
}
}
} else if (next_state == MAC_GROUP_STATE_RESERVED) {
}
}
break;
default:
break;
}
/*
* The mac client using the default group gets exclusive access to the
* default group if and only if it is the sole client on the entire
* mip. If so set the group state to reserved, and set up the SRSes
* over the default group.
*/
if (check_default_group) {
if (next_state == MAC_GROUP_STATE_RESERVED) {
}
}
/*
* If the primary is the only one left and the MAC supports
* dynamic grouping, we need to see if the primary needs to
* be moved to the default group so that it can use all the
* H/W rings.
*/
if (grp_only_mcip == NULL)
return;
/*
* If the primary has an explicit property set, leave it
* alone.
*/
return;
/*
* Switch the primary to the default group.
*/
(void) mac_rx_switch_group(grp_only_mcip,
}
}
/* DATAPATH TEAR DOWN ROUTINES (SRS and FANOUT teardown) */
static void
{
sizeof (mac_soft_ring_t *) * MAX_RINGS_PER_GROUP);
sizeof (mac_soft_ring_t *) * MAX_RINGS_PER_GROUP);
}
} else {
sizeof (mac_soft_ring_t *) * MAX_SR_FANOUT);
sizeof (mac_soft_ring_t *) * MAX_SR_FANOUT);
sizeof (mac_soft_ring_t *) * MAX_SR_FANOUT);
}
}
/*
* An RX SRS is attached to at most one mac_ring.
* A TX SRS has no rings.
*/
static void
{
return;
}
return;
/*
* Broadcast flows don't have a client impl association, but they
* use only soft rings.
*/
}
/*
* Physical unlink and free of the data structures happen below. This is
* driven from mac_flow_destroy(), on the last refrele of a flow.
*
* Assumes Rx srs is 1-1 mapped with an ring.
*/
void
{
}
static void
{
if (s_ring_flag == S_RING_CONDEMNED) {
while (mac_srs->srs_soft_ring_condemned_count !=
} else {
while (mac_srs->srs_soft_ring_quiesced_count !=
}
}
/*
* The block comment above mac_rx_classify_flow_state_change explains the
* background. At this point upcalls from the driver (both hardware classified
* and software classified) have been cut off. We now need to quiesce the
* SRS worker, poll, and softring threads. The SRS worker thread serves as
* the master controller. The steps involved are described below in the function
*/
void
{
} else {
}
/*
* In the case of Rx SRS wait till the poll thread is done.
*/
/*
* Turn off polling as part of the quiesce operation.
*/
}
/*
* Then signal the soft ring worker threads to quiesce or quit
* as needed and then wait till that happens.
*/
else
}
/*
* Signal an SRS to start a temporary quiesce, or permanent removal, or restart
* a quiesced SRS by setting the appropriate flags and signaling the SRS worker
* or poll thread. This function is internal to the quiescing logic and is
* called internally from the SRS quiesce or flow quiesce or client quiesce
* higher level functions.
*/
void
{
if (srs_flag == SRS_CONDEMNED) {
/*
* The SRS is going away. We need to unbind the SRS and SR
* threads before removing from the global SRS list. Otherwise
* there is a small window where the cpu reconfig callbacks
* may miss the SRS in the list walk and DR could fail since
* there are still bound threads.
*/
}
/*
* Wakeup the SRS worker and poll threads.
*/
}
/*
* In the Rx side, the quiescing is done bottom up. After the Rx upcalls
* from the driver are done, then the Rx SRS is quiesced and only then can
* we signal the soft rings. Thus this function can't be called arbitrarily
* without satisfying the prerequisites. On the Tx side, the threads from
* top need to quiesced, then the Tx SRS and only then can we signal the
* Tx soft rings.
*/
static void
{
}
/*
* The block comment above mac_rx_classify_flow_state_change explains the
* background. At this point the SRS is quiesced and we need to restart the
* SRS worker, poll, and softring threads. The SRS worker thread serves as
* the master controller. The steps involved are described below in the function
*/
void
{
(SRS_QUIESCE_DONE | SRS_QUIESCE));
} else {
iam_rx_srs = B_TRUE;
(SRS_QUIESCE_DONE | SRS_QUIESCE)) ==
(SRS_QUIESCE_DONE | SRS_QUIESCE));
}
}
/*
* Signal any quiesced soft ring workers to restart and wait for the
* soft ring down count to come down to zero.
*/
if (mac_srs->srs_soft_ring_quiesced_count != 0) {
continue;
}
while (mac_srs->srs_soft_ring_quiesced_count != 0)
}
/*
* Signal the poll thread and ask it to restart. Wait till it
* actually restarts and the SRS_POLL_THR_QUIESCED flag gets
* cleared.
*/
}
/* Wake up any waiter waiting for the restart to complete */
}
static void
{
return;
}
}
static void
{
return;
}
}
static void
{
}
}
/*
* When a CPU is going away, unbind all MAC threads which are bound
* to that CPU. The affinity of the thread to the CPU is saved to allow
* the thread to be rebound to the CPU if it comes back online.
*/
static void
{
goto done;
}
}
}
/* Next tackle the soft rings associated with the srs */
}
}
}
done:
}
/* TX SETUP and TEARDOWN ROUTINES */
/*
* XXXHIO need to make sure the two mac_tx_srs_{add,del}_ring()
* handle the case where the number of rings is one. I.e. there is
* a ring pointed to by mac_srs->srs_tx_arg2.
*/
void
{
/*
* put this soft ring in quiesce mode too so when we restart
* all soft rings in the srs are in the same state.
*/
}
static void
{
int sringcnt;
} else {
}
} else {
} else {
}
}
}
void
{
int i;
for (i = 0; i < mac_srs->srs_tx_ring_count; i++) {
break;
}
/*
* In the case of aggr, the soft ring associated with a Tx ring
* is also stored in st_soft_rings[] array. That entry should
* be removed.
*/
}
}
/*
* mac_tx_srs_setup():
* Used to setup Tx rings. If no free Tx ring is available, then default
* Tx ring is used.
*/
void
{
int i;
int tx_ring_count = 0;
goto no_group;
}
/*
* An attempt is made to reserve 'tx_ring_count' number
* of Tx rings. If tx_ring_count is 0, default Tx ring
* is used. If it is 1, an attempt is made to reserve one
* Tx ring. In both the cases, the ring information is
* stored in Tx SRS. If multiple Tx rings are specified,
* then each Tx ring will have a Tx-side soft ring. All
* these soft rings will be hang off Tx SRS.
*/
case MAC_GROUP_STATE_SHARED:
case MAC_GROUP_STATE_RESERVED:
(void) mac_start_ring(ring);
}
} else if (mac_tx_serialize ||
(ring_info & MAC_RING_TX_SERIALIZE)) {
} else {
}
break;
}
} else {
}
for (i = 0; i < tx_ring_count; i++) {
case MR_INUSE:
case MR_FREE:
(void) mac_start_ring(ring);
if (mac_tx_serialize || (ring_info &
}
(void) mac_soft_ring_create(i, 0,
break;
default:
"srs_setup: mcip = %p "
"trying to add UNKNOWN ring = %p\n",
break;
}
}
break;
default:
break;
}
if (is_aggr) {
}
}
/*
* Update the fanout of a client if its recorded link speed doesn't match
* its current link speed.
*/
void
{
if ((link_speed != 0) &&
/*
* Before calling mac_fanout_setup(), check to see if
* the SRSes already have the right number of soft
* rings. mac_fanout_setup() is a heavy duty operation
* where new cpu bindings are done for SRS and soft
* ring threads and interrupts re-targeted.
*/
/*
* If soft_ring_count returned by
* mac_compute_soft_ring_count() is 0, bump it
* up by 1 because we always have atleast one
* TCP, UDP, and OTH soft ring associated with
* an SRS.
*/
soft_ring_count = (soft_ring_count == 0) ?
1 : soft_ring_count;
}
}
}
/*
* Walk through the list of mac clients for the MAC.
* For each active mac client, recompute the number of soft rings
* associated with every client, only if current speed is different
* from the speed that was previously used for soft ring computation.
* If the cable is disconnected whlie the NIC is started, we would get
* notification with speed set to 0. We do not recompute in that case.
*/
void
{
return;
}
continue;
pool_lock();
pool_unlock();
}
}
/*
* Given a MAC, change the polling state for all its MAC clients. 'enable' is
* B_TRUE to enable polling or B_FALSE to disable. Polling is enabled by
* default.
*/
void
{
if (enable)
else
}