From: "Jastrzebski, MichalX K" <michalx.k.jastrzebski@intel.com>
To: Vladimir Medvedkin <medvedkinv@gmail.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH v1 0/3] lpm: increase number of next hops for lpm (ipv4)
Date: Mon, 26 Oct 2015 11:57:56 +0000 [thread overview]
Message-ID: <60ABE07DBB3A454EB7FAD707B4BB1582139CCBF9@IRSMSX109.ger.corp.intel.com> (raw)
In-Reply-To: <20151026115519.GA7576@MKJASTRX-MOBL>
> -----Original Message-----
> From: Michal Jastrzebski [mailto:michalx.k.jastrzebski@intel.com]
> Sent: Monday, October 26, 2015 12:55 PM
> To: Vladimir Medvedkin
> Subject: Re: [dpdk-dev] [PATCH v1 0/3] lpm: increase number of next hops
> for lpm (ipv4)
>
> On Sun, Oct 25, 2015 at 08:52:04PM +0300, Vladimir Medvedkin wrote:
> > Hi all,
> >
> > Here my implementation
> >
> > Signed-off-by: Vladimir Medvedkin <medvedkinv@gmail.com>
> > ---
> > config/common_bsdapp | 1 +
> > config/common_linuxapp | 1 +
> > lib/librte_lpm/rte_lpm.c | 194
> > +++++++++++++++++++++++++++++------------------
> > lib/librte_lpm/rte_lpm.h | 163 +++++++++++++++++++++++----------------
> > 4 files changed, 219 insertions(+), 140 deletions(-)
> >
> > diff --git a/config/common_bsdapp b/config/common_bsdapp
> > index b37dcf4..408cc2c 100644
> > --- a/config/common_bsdapp
> > +++ b/config/common_bsdapp
> > @@ -344,6 +344,7 @@ CONFIG_RTE_LIBRTE_JOBSTATS=y
> > #
> > CONFIG_RTE_LIBRTE_LPM=y
> > CONFIG_RTE_LIBRTE_LPM_DEBUG=n
> > +CONFIG_RTE_LIBRTE_LPM_ASNUM=n
> >
> > #
> > # Compile librte_acl
> > diff --git a/config/common_linuxapp b/config/common_linuxapp
> > index 0de43d5..1c60e63 100644
> > --- a/config/common_linuxapp
> > +++ b/config/common_linuxapp
> > @@ -352,6 +352,7 @@ CONFIG_RTE_LIBRTE_JOBSTATS=y
> > #
> > CONFIG_RTE_LIBRTE_LPM=y
> > CONFIG_RTE_LIBRTE_LPM_DEBUG=n
> > +CONFIG_RTE_LIBRTE_LPM_ASNUM=n
> >
> > #
> > # Compile librte_acl
> > diff --git a/lib/librte_lpm/rte_lpm.c b/lib/librte_lpm/rte_lpm.c
> > index 163ba3c..363b400 100644
> > --- a/lib/librte_lpm/rte_lpm.c
> > +++ b/lib/librte_lpm/rte_lpm.c
> > @@ -159,9 +159,11 @@ rte_lpm_create(const char *name, int socket_id,
> int
> > max_rules,
> >
> > lpm_list = RTE_TAILQ_CAST(rte_lpm_tailq.head, rte_lpm_list);
> >
> > - RTE_BUILD_BUG_ON(sizeof(struct rte_lpm_tbl24_entry) != 2);
> > - RTE_BUILD_BUG_ON(sizeof(struct rte_lpm_tbl8_entry) != 2);
> > -
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + RTE_BUILD_BUG_ON(sizeof(struct rte_lpm_tbl_entry) != 8);
> > +#else
> > + RTE_BUILD_BUG_ON(sizeof(struct rte_lpm_tbl_entry) != 4);
> > +#endif
> > /* Check user arguments. */
> > if ((name == NULL) || (socket_id < -1) || (max_rules == 0)){
> > rte_errno = EINVAL;
> > @@ -261,7 +263,7 @@ rte_lpm_free(struct rte_lpm *lpm)
> > */
> > static inline int32_t
> > rule_add(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
> > - uint8_t next_hop)
> > + struct rte_lpm_res *res)
> > {
> > uint32_t rule_gindex, rule_index, last_rule;
> > int i;
> > @@ -282,8 +284,11 @@ rule_add(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth,
> >
> > /* If rule already exists update its next_hop and
> > return. */
> > if (lpm->rules_tbl[rule_index].ip == ip_masked) {
> > - lpm->rules_tbl[rule_index].next_hop =
> > next_hop;
> > -
> > + lpm->rules_tbl[rule_index].next_hop =
> > res->next_hop;
> > + lpm->rules_tbl[rule_index].fwd_class =
> > res->fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + lpm->rules_tbl[rule_index].as_num =
> > res->as_num;
> > +#endif
> > return rule_index;
> > }
> > }
> > @@ -320,7 +325,11 @@ rule_add(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth,
> >
> > /* Add the new rule. */
> > lpm->rules_tbl[rule_index].ip = ip_masked;
> > - lpm->rules_tbl[rule_index].next_hop = next_hop;
> > + lpm->rules_tbl[rule_index].next_hop = res->next_hop;
> > + lpm->rules_tbl[rule_index].fwd_class = res->fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + lpm->rules_tbl[rule_index].as_num = res->as_num;
> > +#endif
> >
> > /* Increment the used rules counter for this rule group. */
> > lpm->rule_info[depth - 1].used_rules++;
> > @@ -382,10 +391,10 @@ rule_find(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth)
> > * Find, clean and allocate a tbl8.
> > */
> > static inline int32_t
> > -tbl8_alloc(struct rte_lpm_tbl8_entry *tbl8)
> > +tbl8_alloc(struct rte_lpm_tbl_entry *tbl8)
> > {
> > uint32_t tbl8_gindex; /* tbl8 group index. */
> > - struct rte_lpm_tbl8_entry *tbl8_entry;
> > + struct rte_lpm_tbl_entry *tbl8_entry;
> >
> > /* Scan through tbl8 to find a free (i.e. INVALID) tbl8 group. */
> > for (tbl8_gindex = 0; tbl8_gindex < RTE_LPM_TBL8_NUM_GROUPS;
> > @@ -393,12 +402,12 @@ tbl8_alloc(struct rte_lpm_tbl8_entry *tbl8)
> > tbl8_entry = &tbl8[tbl8_gindex *
> > RTE_LPM_TBL8_GROUP_NUM_ENTRIES];
> > /* If a free tbl8 group is found clean it and set as VALID.
> > */
> > - if (!tbl8_entry->valid_group) {
> > + if (!tbl8_entry->ext_valid) {
> > memset(&tbl8_entry[0], 0,
> > RTE_LPM_TBL8_GROUP_NUM_ENTRIES *
> > sizeof(tbl8_entry[0]));
> >
> > - tbl8_entry->valid_group = VALID;
> > + tbl8_entry->ext_valid = VALID;
> >
> > /* Return group index for allocated tbl8 group. */
> > return tbl8_gindex;
> > @@ -410,46 +419,50 @@ tbl8_alloc(struct rte_lpm_tbl8_entry *tbl8)
> > }
> >
> > static inline void
> > -tbl8_free(struct rte_lpm_tbl8_entry *tbl8, uint32_t tbl8_group_start)
> > +tbl8_free(struct rte_lpm_tbl_entry *tbl8, uint32_t tbl8_group_start)
> > {
> > /* Set tbl8 group invalid*/
> > - tbl8[tbl8_group_start].valid_group = INVALID;
> > + tbl8[tbl8_group_start].ext_valid = INVALID;
> > }
> >
> > static inline int32_t
> > add_depth_small(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
> > - uint8_t next_hop)
> > + struct rte_lpm_res *res)
> > {
> > uint32_t tbl24_index, tbl24_range, tbl8_index, tbl8_group_end, i, j;
> >
> > /* Calculate the index into Table24. */
> > tbl24_index = ip >> 8;
> > tbl24_range = depth_to_range(depth);
> > + struct rte_lpm_tbl_entry new_tbl_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = res->as_num,
> > +#endif
> > + .next_hop = res->next_hop,
> > + .fwd_class = res->fwd_class,
> > + .ext_valid = 0,
> > + .depth = depth,
> > + .valid = VALID,
> > + };
> > +
> >
> > for (i = tbl24_index; i < (tbl24_index + tbl24_range); i++) {
> > /*
> > * For invalid OR valid and non-extended tbl 24 entries set
> > * entry.
> > */
> > - if (!lpm->tbl24[i].valid || (lpm->tbl24[i].ext_entry == 0 &&
> > + if (!lpm->tbl24[i].valid || (lpm->tbl24[i].ext_valid == 0 &&
> > lpm->tbl24[i].depth <= depth)) {
> >
> > - struct rte_lpm_tbl24_entry new_tbl24_entry = {
> > - { .next_hop = next_hop, },
> > - .valid = VALID,
> > - .ext_entry = 0,
> > - .depth = depth,
> > - };
> > -
> > /* Setting tbl24 entry in one go to avoid race
> > * conditions
> > */
> > - lpm->tbl24[i] = new_tbl24_entry;
> > + lpm->tbl24[i] = new_tbl_entry;
> >
> > continue;
> > }
> >
> > - if (lpm->tbl24[i].ext_entry == 1) {
> > + if (lpm->tbl24[i].ext_valid == 1) {
> > /* If tbl24 entry is valid and extended calculate
> > the
> > * index into tbl8.
> > */
> > @@ -461,19 +474,14 @@ add_depth_small(struct rte_lpm *lpm, uint32_t
> ip,
> > uint8_t depth,
> > for (j = tbl8_index; j < tbl8_group_end; j++) {
> > if (!lpm->tbl8[j].valid ||
> > lpm->tbl8[j].depth <=
> > depth) {
> > - struct rte_lpm_tbl8_entry
> > - new_tbl8_entry = {
> > - .valid = VALID,
> > - .valid_group = VALID,
> > - .depth = depth,
> > - .next_hop = next_hop,
> > - };
> > +
> > + new_tbl_entry.ext_valid = VALID;
> >
> > /*
> > * Setting tbl8 entry in one go to
> > avoid
> > * race conditions
> > */
> > - lpm->tbl8[j] = new_tbl8_entry;
> > + lpm->tbl8[j] = new_tbl_entry;
> >
> > continue;
> > }
> > @@ -486,7 +494,7 @@ add_depth_small(struct rte_lpm *lpm, uint32_t ip,
> > uint8_t depth,
> >
> > static inline int32_t
> > add_depth_big(struct rte_lpm *lpm, uint32_t ip_masked, uint8_t depth,
> > - uint8_t next_hop)
> > + struct rte_lpm_res *res)
> > {
> > uint32_t tbl24_index;
> > int32_t tbl8_group_index, tbl8_group_start, tbl8_group_end,
> > tbl8_index,
> > @@ -512,7 +520,11 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth,
> > /* Set tbl8 entry. */
> > for (i = tbl8_index; i < (tbl8_index + tbl8_range); i++) {
> > lpm->tbl8[i].depth = depth;
> > - lpm->tbl8[i].next_hop = next_hop;
> > + lpm->tbl8[i].next_hop = res->next_hop;
> > + lpm->tbl8[i].fwd_class = res->fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + lpm->tbl8[i].as_num = res->as_num;
> > +#endif
> > lpm->tbl8[i].valid = VALID;
> > }
> >
> > @@ -522,17 +534,17 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked, uint8_t depth,
> > * so assign whole structure in one go
> > */
> >
> > - struct rte_lpm_tbl24_entry new_tbl24_entry = {
> > - { .tbl8_gindex = (uint8_t)tbl8_group_index, },
> > - .valid = VALID,
> > - .ext_entry = 1,
> > + struct rte_lpm_tbl_entry new_tbl24_entry = {
> > + .tbl8_gindex = (uint16_t)tbl8_group_index,
> > .depth = 0,
> > + .ext_valid = 1,
> > + .valid = VALID,
> > };
> >
> > lpm->tbl24[tbl24_index] = new_tbl24_entry;
> >
> > }/* If valid entry but not extended calculate the index into
> > Table8. */
> > - else if (lpm->tbl24[tbl24_index].ext_entry == 0) {
> > + else if (lpm->tbl24[tbl24_index].ext_valid == 0) {
> > /* Search for free tbl8 group. */
> > tbl8_group_index = tbl8_alloc(lpm->tbl8);
> >
> > @@ -551,6 +563,11 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth,
> > lpm->tbl8[i].depth = lpm->tbl24[tbl24_index].depth;
> > lpm->tbl8[i].next_hop =
> > lpm->tbl24[tbl24_index].next_hop;
> > + lpm->tbl8[i].fwd_class =
> > + lpm->tbl24[tbl24_index].fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + lpm->tbl8[i].as_num =
> > lpm->tbl24[tbl24_index].as_num;
> > +#endif
> > }
> >
> > tbl8_index = tbl8_group_start + (ip_masked & 0xFF);
> > @@ -561,7 +578,11 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> ip_masked,
> > uint8_t depth,
> > lpm->tbl8[i].depth <= depth) {
> > lpm->tbl8[i].valid = VALID;
> > lpm->tbl8[i].depth = depth;
> > - lpm->tbl8[i].next_hop = next_hop;
> > + lpm->tbl8[i].next_hop = res->next_hop;
> > + lpm->tbl8[i].fwd_class = res->fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + lpm->tbl8[i].as_num = res->as_num;
> > +#endif
> >
> > continue;
> > }
> > @@ -573,11 +594,11 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked, uint8_t depth,
> > * so assign whole structure in one go.
> > */
> >
> > - struct rte_lpm_tbl24_entry new_tbl24_entry = {
> > - { .tbl8_gindex = (uint8_t)tbl8_group_index,
> > },
> > - .valid = VALID,
> > - .ext_entry = 1,
> > + struct rte_lpm_tbl_entry new_tbl24_entry = {
> > + .tbl8_gindex = (uint16_t)tbl8_group_index,
> > .depth = 0,
> > + .ext_valid = 1,
> > + .valid = VALID,
> > };
> >
> > lpm->tbl24[tbl24_index] = new_tbl24_entry;
> > @@ -595,11 +616,15 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked, uint8_t depth,
> >
> > if (!lpm->tbl8[i].valid ||
> > lpm->tbl8[i].depth <= depth) {
> > - struct rte_lpm_tbl8_entry new_tbl8_entry = {
> > - .valid = VALID,
> > + struct rte_lpm_tbl_entry new_tbl8_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = res->as_num,
> > +#endif
> > + .next_hop = res->next_hop,
> > + .fwd_class = res->fwd_class,
> > .depth = depth,
> > - .next_hop = next_hop,
> > - .valid_group =
> > lpm->tbl8[i].valid_group,
> > + .ext_valid = lpm->tbl8[i].ext_valid,
> > + .valid = VALID,
> > };
> >
> > /*
> > @@ -621,19 +646,19 @@ add_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked, uint8_t depth,
> > */
> > int
> > rte_lpm_add(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
> > - uint8_t next_hop)
> > + struct rte_lpm_res *res)
> > {
> > int32_t rule_index, status = 0;
> > uint32_t ip_masked;
> >
> > /* Check user arguments. */
> > - if ((lpm == NULL) || (depth < 1) || (depth > RTE_LPM_MAX_DEPTH))
> > + if ((lpm == NULL) || (res == NULL) || (depth < 1) || (depth >
> > RTE_LPM_MAX_DEPTH))
> > return -EINVAL;
> >
> > ip_masked = ip & depth_to_mask(depth);
> >
> > /* Add the rule to the rule table. */
> > - rule_index = rule_add(lpm, ip_masked, depth, next_hop);
> > + rule_index = rule_add(lpm, ip_masked, depth, res);
> >
> > /* If the is no space available for new rule return error. */
> > if (rule_index < 0) {
> > @@ -641,10 +666,10 @@ rte_lpm_add(struct rte_lpm *lpm, uint32_t ip,
> uint8_t
> > depth,
> > }
> >
> > if (depth <= MAX_DEPTH_TBL24) {
> > - status = add_depth_small(lpm, ip_masked, depth, next_hop);
> > + status = add_depth_small(lpm, ip_masked, depth, res);
> > }
> > else { /* If depth > RTE_LPM_MAX_DEPTH_TBL24 */
> > - status = add_depth_big(lpm, ip_masked, depth, next_hop);
> > + status = add_depth_big(lpm, ip_masked, depth, res);
> >
> > /*
> > * If add fails due to exhaustion of tbl8 extensions delete
> > @@ -665,14 +690,14 @@ rte_lpm_add(struct rte_lpm *lpm, uint32_t ip,
> uint8_t
> > depth,
> > */
> > int
> > rte_lpm_is_rule_present(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
> > -uint8_t *next_hop)
> > + struct rte_lpm_res *res)
> > {
> > uint32_t ip_masked;
> > int32_t rule_index;
> >
> > /* Check user arguments. */
> > if ((lpm == NULL) ||
> > - (next_hop == NULL) ||
> > + (res == NULL) ||
> > (depth < 1) || (depth > RTE_LPM_MAX_DEPTH))
> > return -EINVAL;
> >
> > @@ -681,7 +706,11 @@ uint8_t *next_hop)
> > rule_index = rule_find(lpm, ip_masked, depth);
> >
> > if (rule_index >= 0) {
> > - *next_hop = lpm->rules_tbl[rule_index].next_hop;
> > + res->next_hop = lpm->rules_tbl[rule_index].next_hop;
> > + res->fwd_class = lpm->rules_tbl[rule_index].fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + res->as_num = lpm->rules_tbl[rule_index].as_num;
> > +#endif
> > return 1;
> > }
> >
> > @@ -731,7 +760,7 @@ delete_depth_small(struct rte_lpm *lpm, uint32_t
> > ip_masked,
> > */
> > for (i = tbl24_index; i < (tbl24_index + tbl24_range); i++)
> > {
> >
> > - if (lpm->tbl24[i].ext_entry == 0 &&
> > + if (lpm->tbl24[i].ext_valid == 0 &&
> > lpm->tbl24[i].depth <= depth ) {
> > lpm->tbl24[i].valid = INVALID;
> > }
> > @@ -761,23 +790,30 @@ delete_depth_small(struct rte_lpm *lpm,
> uint32_t
> > ip_masked,
> > * associated with this rule.
> > */
> >
> > - struct rte_lpm_tbl24_entry new_tbl24_entry = {
> > - {.next_hop =
> > lpm->rules_tbl[sub_rule_index].next_hop,},
> > - .valid = VALID,
> > - .ext_entry = 0,
> > + struct rte_lpm_tbl_entry new_tbl24_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = lpm->rules_tbl[sub_rule_index].as_num,
> > +#endif
> > + .next_hop = lpm->rules_tbl[sub_rule_index].next_hop,
> > + .fwd_class =
> > lpm->rules_tbl[sub_rule_index].fwd_class,
> > .depth = sub_rule_depth,
> > + .ext_valid = 0,
> > + .valid = VALID,
> > };
> >
> > - struct rte_lpm_tbl8_entry new_tbl8_entry = {
> > - .valid = VALID,
> > + struct rte_lpm_tbl_entry new_tbl8_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = lpm->rules_tbl[sub_rule_index].as_num,
> > +#endif
> > + .next_hop = lpm->rules_tbl[sub_rule_index].next_hop,
> > + .fwd_class =
> > lpm->rules_tbl[sub_rule_index].fwd_class,
> > .depth = sub_rule_depth,
> > - .next_hop = lpm->rules_tbl
> > - [sub_rule_index].next_hop,
> > + .valid = VALID,
> > };
> >
> > for (i = tbl24_index; i < (tbl24_index + tbl24_range); i++)
> > {
> >
> > - if (lpm->tbl24[i].ext_entry == 0 &&
> > + if (lpm->tbl24[i].ext_valid == 0 &&
> > lpm->tbl24[i].depth <= depth ) {
> > lpm->tbl24[i] = new_tbl24_entry;
> > }
> > @@ -814,7 +850,7 @@ delete_depth_small(struct rte_lpm *lpm, uint32_t
> > ip_masked,
> > * thus can be recycled
> > */
> > static inline int32_t
> > -tbl8_recycle_check(struct rte_lpm_tbl8_entry *tbl8, uint32_t
> > tbl8_group_start)
> > +tbl8_recycle_check(struct rte_lpm_tbl_entry *tbl8, uint32_t
> > tbl8_group_start)
> > {
> > uint32_t tbl8_group_end, i;
> > tbl8_group_end = tbl8_group_start +
> RTE_LPM_TBL8_GROUP_NUM_ENTRIES;
> > @@ -891,11 +927,15 @@ delete_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked,
> > }
> > else {
> > /* Set new tbl8 entry. */
> > - struct rte_lpm_tbl8_entry new_tbl8_entry = {
> > - .valid = VALID,
> > - .depth = sub_rule_depth,
> > - .valid_group =
> > lpm->tbl8[tbl8_group_start].valid_group,
> > + struct rte_lpm_tbl_entry new_tbl8_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = lpm->rules_tbl[sub_rule_index].as_num,
> > +#endif
> > + .fwd_class =
> > lpm->rules_tbl[sub_rule_index].fwd_class,
> > .next_hop = lpm->rules_tbl[sub_rule_index].next_hop,
> > + .depth = sub_rule_depth,
> > + .ext_valid = lpm->tbl8[tbl8_group_start].ext_valid,
> > + .valid = VALID,
> > };
> >
> > /*
> > @@ -923,11 +963,15 @@ delete_depth_big(struct rte_lpm *lpm, uint32_t
> > ip_masked,
> > }
> > else if (tbl8_recycle_index > -1) {
> > /* Update tbl24 entry. */
> > - struct rte_lpm_tbl24_entry new_tbl24_entry = {
> > - { .next_hop =
> > lpm->tbl8[tbl8_recycle_index].next_hop, },
> > - .valid = VALID,
> > - .ext_entry = 0,
> > + struct rte_lpm_tbl_entry new_tbl24_entry = {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + .as_num = lpm->tbl8[tbl8_recycle_index].as_num,
> > +#endif
> > + .next_hop = lpm->tbl8[tbl8_recycle_index].next_hop,
> > + .fwd_class =
> > lpm->tbl8[tbl8_recycle_index].fwd_class,
> > .depth = lpm->tbl8[tbl8_recycle_index].depth,
> > + .ext_valid = 0,
> > + .valid = VALID,
> > };
> >
> > /* Set tbl24 before freeing tbl8 to avoid race condition. */
> > diff --git a/lib/librte_lpm/rte_lpm.h b/lib/librte_lpm/rte_lpm.h
> > index c299ce2..7c615bc 100644
> > --- a/lib/librte_lpm/rte_lpm.h
> > +++ b/lib/librte_lpm/rte_lpm.h
> > @@ -31,8 +31,8 @@
> > * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
> DAMAGE.
> > */
> >
> > -#ifndef _RTE_LPM_H_
> > -#define _RTE_LPM_H_
> > +#ifndef _RTE_LPM_EXT_H_
> > +#define _RTE_LPM_EXT_H_
> >
> > /**
> > * @file
> > @@ -81,57 +81,58 @@ extern "C" {
> > #define RTE_LPM_RETURN_IF_TRUE(cond, retval)
> > #endif
> >
> > -/** @internal bitmask with valid and ext_entry/valid_group fields set */
> > -#define RTE_LPM_VALID_EXT_ENTRY_BITMASK 0x0300
> > +/** @internal bitmask with valid and ext_valid/ext_valid fields set */
> > +#define RTE_LPM_VALID_EXT_ENTRY_BITMASK 0x03
> >
> > /** Bitmask used to indicate successful lookup */
> > -#define RTE_LPM_LOOKUP_SUCCESS 0x0100
> > +#define RTE_LPM_LOOKUP_SUCCESS 0x01
> > +
> > +struct rte_lpm_res {
> > + uint16_t next_hop;
> > + uint8_t fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint32_t as_num;
> > +#endif
> > +};
> >
> > #if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
> > -/** @internal Tbl24 entry structure. */
> > -struct rte_lpm_tbl24_entry {
> > - /* Stores Next hop or group index (i.e. gindex)into tbl8. */
> > +struct rte_lpm_tbl_entry {
> > + uint8_t valid :1;
> > + uint8_t ext_valid :1;
> > + uint8_t depth :6;
> > + uint8_t fwd_class;
> > union {
> > - uint8_t next_hop;
> > - uint8_t tbl8_gindex;
> > + uint16_t next_hop;
> > + uint16_t tbl8_gindex;
> > };
> > - /* Using single uint8_t to store 3 values. */
> > - uint8_t valid :1; /**< Validation flag. */
> > - uint8_t ext_entry :1; /**< External entry. */
> > - uint8_t depth :6; /**< Rule depth. */
> > -};
> > -
> > -/** @internal Tbl8 entry structure. */
> > -struct rte_lpm_tbl8_entry {
> > - uint8_t next_hop; /**< next hop. */
> > - /* Using single uint8_t to store 3 values. */
> > - uint8_t valid :1; /**< Validation flag. */
> > - uint8_t valid_group :1; /**< Group validation flag. */
> > - uint8_t depth :6; /**< Rule depth. */
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint32_t as_num;
> > +#endif
> > };
> > #else
> > -struct rte_lpm_tbl24_entry {
> > - uint8_t depth :6;
> > - uint8_t ext_entry :1;
> > - uint8_t valid :1;
> > +struct rte_lpm_tbl_entry {
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint32_t as_num;
> > +#endif
> > union {
> > - uint8_t tbl8_gindex;
> > - uint8_t next_hop;
> > + uint16_t tbl8_gindex;
> > + uint16_t next_hop;
> > };
> > -};
> > -
> > -struct rte_lpm_tbl8_entry {
> > - uint8_t depth :6;
> > - uint8_t valid_group :1;
> > - uint8_t valid :1;
> > - uint8_t next_hop;
> > + uint8_t fwd_class;
> > + uint8_t depth :6;
> > + uint8_t ext_valid :1;
> > + uint8_t valid :1;
> > };
> > #endif
> >
> > /** @internal Rule structure. */
> > struct rte_lpm_rule {
> > uint32_t ip; /**< Rule IP address. */
> > - uint8_t next_hop; /**< Rule next hop. */
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint32_t as_num;
> > +#endif
> > + uint16_t next_hop; /**< Rule next hop. */
> > + uint8_t fwd_class;
> > };
> >
> > /** @internal Contains metadata about the rules table. */
> > @@ -148,9 +149,9 @@ struct rte_lpm {
> > struct rte_lpm_rule_info rule_info[RTE_LPM_MAX_DEPTH]; /**< Rule
> > info table. */
> >
> > /* LPM Tables. */
> > - struct rte_lpm_tbl24_entry tbl24[RTE_LPM_TBL24_NUM_ENTRIES] \
> > + struct rte_lpm_tbl_entry tbl24[RTE_LPM_TBL24_NUM_ENTRIES] \
> > __rte_cache_aligned; /**< LPM tbl24 table. */
> > - struct rte_lpm_tbl8_entry tbl8[RTE_LPM_TBL8_NUM_ENTRIES] \
> > + struct rte_lpm_tbl_entry tbl8[RTE_LPM_TBL8_NUM_ENTRIES] \
> > __rte_cache_aligned; /**< LPM tbl8 table. */
> > struct rte_lpm_rule rules_tbl[0] \
> > __rte_cache_aligned; /**< LPM rules. */
> > @@ -219,7 +220,7 @@ rte_lpm_free(struct rte_lpm *lpm);
> > * 0 on success, negative value otherwise
> > */
> > int
> > -rte_lpm_add(struct rte_lpm *lpm, uint32_t ip, uint8_t depth, uint8_t
> > next_hop);
> > +rte_lpm_add(struct rte_lpm *lpm, uint32_t ip, uint8_t depth, struct
> > rte_lpm_res *res);
> >
> > /**
> > * Check if a rule is present in the LPM table,
> > @@ -238,7 +239,7 @@ rte_lpm_add(struct rte_lpm *lpm, uint32_t ip,
> uint8_t
> > depth, uint8_t next_hop);
> > */
> > int
> > rte_lpm_is_rule_present(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
> > -uint8_t *next_hop);
> > + struct rte_lpm_res *res);
> >
> > /**
> > * Delete a rule from the LPM table.
> > @@ -277,29 +278,43 @@ rte_lpm_delete_all(struct rte_lpm *lpm);
> > * -EINVAL for incorrect arguments, -ENOENT on lookup miss, 0 on lookup
> > hit
> > */
> > static inline int
> > -rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint8_t *next_hop)
> > +rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, struct rte_lpm_res *res)
> > {
> > unsigned tbl24_index = (ip >> 8);
> > - uint16_t tbl_entry;
> > -
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint64_t tbl_entry;
> > +#else
> > + uint32_t tbl_entry;
> > +#endif
> > /* DEBUG: Check user input arguments. */
> > - RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (next_hop == NULL)),
> > -EINVAL);
> > + RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (res == NULL)), -
> EINVAL);
> >
> > /* Copy tbl24 entry */
> > - tbl_entry = *(const uint16_t *)&lpm->tbl24[tbl24_index];
> > -
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + tbl_entry = *(const uint64_t *)&lpm->tbl24[tbl24_index];
> > +#else
> > + tbl_entry = *(const uint32_t *)&lpm->tbl24[tbl24_index];
> > +#endif
> > /* Copy tbl8 entry (only if needed) */
> > if (unlikely((tbl_entry & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
> > RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
> >
> > unsigned tbl8_index = (uint8_t)ip +
> > - ((uint8_t)tbl_entry *
> > RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
> > + ((*(struct rte_lpm_tbl_entry
> > *)&tbl_entry).tbl8_gindex * RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
> >
> > - tbl_entry = *(const uint16_t *)&lpm->tbl8[tbl8_index];
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + tbl_entry = *(const uint64_t *)&lpm->tbl8[tbl8_index];
> > +#else
> > + tbl_entry = *(const uint32_t *)&lpm->tbl8[tbl8_index];
> > +#endif
> > }
> > -
> > - *next_hop = (uint8_t)tbl_entry;
> > + res->next_hop = ((struct rte_lpm_tbl_entry *)&tbl_entry)->next_hop;
> > + res->fwd_class = ((struct rte_lpm_tbl_entry
> > *)&tbl_entry)->fwd_class;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + res->as_num = ((struct rte_lpm_tbl_entry
> > *)&tbl_entry)->as_num;
> > +#endif
> > return (tbl_entry & RTE_LPM_LOOKUP_SUCCESS) ? 0 : -ENOENT;
> > +
> > }
> >
> > /**
> > @@ -322,19 +337,25 @@ rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip,
> > uint8_t *next_hop)
> > * @return
> > * -EINVAL for incorrect arguments, otherwise 0
> > */
> > -#define rte_lpm_lookup_bulk(lpm, ips, next_hops, n) \
> > - rte_lpm_lookup_bulk_func(lpm, ips, next_hops, n)
> > +#define rte_lpm_lookup_bulk(lpm, ips, res_tbl, n) \
> > + rte_lpm_lookup_bulk_func(lpm, ips, res_tbl, n)
> >
> > static inline int
> > -rte_lpm_lookup_bulk_func(const struct rte_lpm *lpm, const uint32_t * ips,
> > - uint16_t * next_hops, const unsigned n)
> > +rte_lpm_lookup_bulk_func(const struct rte_lpm *lpm, const uint32_t *ips,
> > + struct rte_lpm_res *res_tbl, const unsigned n)
> > {
> > unsigned i;
> > + int ret = 0;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + uint64_t tbl_entry;
> > +#else
> > + uint32_t tbl_entry;
> > +#endif
> > unsigned tbl24_indexes[n];
> >
> > /* DEBUG: Check user input arguments. */
> > RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (ips == NULL) ||
> > - (next_hops == NULL)), -EINVAL);
> > + (res_tbl == NULL)), -EINVAL);
> >
> > for (i = 0; i < n; i++) {
> > tbl24_indexes[i] = ips[i] >> 8;
> > @@ -342,20 +363,32 @@ rte_lpm_lookup_bulk_func(const struct rte_lpm
> *lpm,
> > const uint32_t * ips,
> >
> > for (i = 0; i < n; i++) {
> > /* Simply copy tbl24 entry to output */
> > - next_hops[i] = *(const uint16_t
> > *)&lpm->tbl24[tbl24_indexes[i]];
> > -
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + tbl_entry = *(const uint64_t
> > *)&lpm->tbl24[tbl24_indexes[i]];
> > +#else
> > + tbl_entry = *(const uint32_t
> > *)&lpm->tbl24[tbl24_indexes[i]];
> > +#endif
> > /* Overwrite output with tbl8 entry if needed */
> > - if (unlikely((next_hops[i] &
> > RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
> > - RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
> > + if (unlikely((tbl_entry & RTE_LPM_VALID_EXT_ENTRY_BITMASK)
> > ==
> > + RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
> >
> > unsigned tbl8_index = (uint8_t)ips[i] +
> > - ((uint8_t)next_hops[i] *
> > - RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
> > + ((*(struct rte_lpm_tbl_entry
> > *)&tbl_entry).tbl8_gindex * RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
> >
> > - next_hops[i] = *(const uint16_t
> > *)&lpm->tbl8[tbl8_index];
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + tbl_entry = *(const uint64_t
> > *)&lpm->tbl8[tbl8_index];
> > +#else
> > + tbl_entry = *(const uint32_t
> > *)&lpm->tbl8[tbl8_index];
> > +#endif
> > }
> > + res_tbl[i].next_hop = ((struct rte_lpm_tbl_entry
> > *)&tbl_entry)->next_hop;
> > + res_tbl[i].fwd_class = ((struct rte_lpm_tbl_entry
> > *)&tbl_entry)->next_hop;
> > +#ifdef RTE_LIBRTE_LPM_ASNUM
> > + res_tbl[i].as_num = ((struct rte_lpm_tbl_entry
> > *)&tbl_entry)->as_num;
> > +#endif
> > + ret |= 1 << i;
> > }
> > - return 0;
> > + return ret;
> > }
> >
> > /* Mask four results. */
> > @@ -477,4 +510,4 @@ rte_lpm_lookupx4(const struct rte_lpm *lpm,
> __m128i ip,
> > uint16_t hop[4],
> > }
> > #endif
> >
> > -#endif /* _RTE_LPM_H_ */
> > +#endif /* _RTE_LPM_EXT_H_ */
> >
> > 2015-10-24 9:09 GMT+03:00 Matthew Hall <mhall@mhcomputing.net>:
> >
> > > On 10/23/15 9:20 AM, Matthew Hall wrote:
> > >
> > >> On Fri, Oct 23, 2015 at 03:51:48PM +0200, Michal Jastrzebski wrote:
> > >>
> > >>> From: Michal Kobylinski <michalx.kobylinski@intel.com>
> > >>>
> > >>> The current DPDK implementation for LPM for IPv4 and IPv6 limits the
> > >>> number of next hops to 256, as the next hop ID is an 8-bit long field.
> > >>> Proposed extension increase number of next hops for IPv4 to 2^24 and
> > >>> also allows 32-bits read/write operations.
> > >>>
> > >>> This patchset requires additional change to rte_table library to meet
> > >>> ABI compatibility requirements. A v2 will be sent next week.
> > >>>
> > >>
> > >> I also have a patchset for this.
> > >>
> > >> I will send it out as well so we could compare.
> > >>
> > >> Matthew.
> > >>
> > >
> > > Sorry about the delay; I only work on DPDK in personal time and not as
> > > part of a job. My patchset is attached to this email.
> > >
> > > One possible advantage with my patchset, compared to others, is that the
> > > space problem is fixed in both IPV4 and in IPV6, to prevent asymmetry
> > > between these two standards, which is something I try to avoid as much
> as
> > > humanly possible.
> > >
> > > This is because my application code is green-field, so I absolutely don't
> > > want to put any ugly hacks or incompatibilities in this code if I can
> > > possibly avoid it.
> > >
> > > Otherwise, I am not necessarily as expert about rte_lpm as some of the
> > > full-time guys, but I think with four or five of us in the thread hammering
> > > out patches we will be able to create something amazing together and I
> am
> > > very very very very very happy about this.
> > >
> > > Matthew.
> > >
>
Hi Vladimir,
Thanks for sharing Your implementation.
Could You please clarify what as_num and fwd_class fields represent?
The second issue I have is that Your patch doesn’t want to apply on top of
current head. Could You check this please?
Best regards
Michal
next prev parent reply other threads:[~2015-10-26 11:58 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-23 13:51 Michal Jastrzebski
2015-10-23 13:51 ` [dpdk-dev] [PATCH v1 1/3] " Michal Jastrzebski
2015-10-23 14:38 ` Bruce Richardson
2015-10-23 14:59 ` Jastrzebski, MichalX K
2015-10-23 13:51 ` [dpdk-dev] [PATCH v1 2/3] examples: update of apps using librte_lpm (ipv4) Michal Jastrzebski
2015-10-23 13:51 ` [dpdk-dev] [PATCH v1 3/3] doc: update release 2.2 after changes in librte_lpm Michal Jastrzebski
2015-10-23 14:21 ` Bruce Richardson
2015-10-23 14:33 ` Jastrzebski, MichalX K
2015-10-23 16:20 ` [dpdk-dev] [PATCH v1 0/3] lpm: increase number of next hops for lpm (ipv4) Matthew Hall
2015-10-23 16:33 ` Stephen Hemminger
2015-10-23 18:38 ` Matthew Hall
2015-10-23 19:13 ` Vladimir Medvedkin
2015-10-23 19:59 ` Stephen Hemminger
2015-10-24 6:09 ` Matthew Hall
2015-10-25 17:52 ` Vladimir Medvedkin
[not found] ` <20151026115519.GA7576@MKJASTRX-MOBL>
2015-10-26 11:57 ` Jastrzebski, MichalX K [this message]
2015-10-26 14:03 ` Vladimir Medvedkin
2015-10-26 15:39 ` Michal Jastrzebski
2015-10-26 16:59 ` Vladimir Medvedkin
2015-10-26 12:13 ` Jastrzebski, MichalX K
2015-10-26 18:40 ` Matthew Hall
2015-10-27 10:35 ` Vladimir Medvedkin
2015-10-27 10:33 ` Vladimir Medvedkin
2015-10-30 7:17 ` Matthew Hall
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=60ABE07DBB3A454EB7FAD707B4BB1582139CCBF9@IRSMSX109.ger.corp.intel.com \
--to=michalx.k.jastrzebski@intel.com \
--cc=dev@dpdk.org \
--cc=medvedkinv@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).