summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2023-12-26 20:24:33 +0000
committerDavid S. Miller <davem@davemloft.net>2023-12-26 20:24:33 +0000
commite3eb47f2347b8cfae9de4a9a6fdddec79554652c (patch)
tree3039dfce81ff61cee3378a044ef4b4602d0b3b34 /net
parente9301af385e7864dea353f5e58cad7339dd6c718 (diff)
parentb3bf76024f645369e1fc45e0b08a2bd24f200d9b (diff)
downloadlinux-e3eb47f2347b8cfae9de4a9a6fdddec79554652c.tar.gz
linux-e3eb47f2347b8cfae9de4a9a6fdddec79554652c.tar.bz2
linux-e3eb47f2347b8cfae9de4a9a6fdddec79554652c.zip
Merge branch 'net-smcv2.1-ISM-device-support'
Wen Gu says: ==================== net/smc: implement SMCv2.1 virtual ISM device support The fourth edition of SMCv2 adds the SMC version 2.1 feature updates for SMC-Dv2 with virtual ISM. Virtual ISM are created and supported mainly by OS or hypervisor software, comparable to IBM ISM which is based on platform firmware or hardware. With the introduction of virtual ISM, SMCv2.1 makes some updates: - Introduce feature bitmask to indicate supplemental features. - Reserve a range of CHIDs for virtual ISM. - Support extended GIDs (128 bits) in CLC handshake. So this patch set aims to implement these updates in Linux kernel. And it acts as the first part of SMC-D virtual ISM extension & loopback-ism [1]. [1] https://lore.kernel.org/netdev/1695568613-125057-1-git-send-email-guwen@linux.alibaba.com/ v8->v7: - Patch #7: v7 mistakenly changed the type of gid_ext in smc_clc_msg_accept_confirm to u64 instead of __be64 as previous versions when fixing the rebase conflicts. So fix this mistake. v7->v6: Link: https://lore.kernel.org/netdev/20231219084536.8158-1-guwen@linux.alibaba.com/ - Collect the Reviewed-by tag in v6; - Patch #3: redefine the struct smc_clc_msg_accept_confirm; - Patch #7: Because that the Patch #3 already adds '__packed' to smc_clc_msg_accept_confirm, so Patch #7 doesn't need to do the same thing. But this is a minor change, so I kept the 'Reviewed-by' tag. Other changes in previous versions but not yet acked: - Patch #1: Some minor changes in subject and fix the format issue (length exceeds 80 columns) compared to v3. - Patch #5: removes useless ini->feature_mask assignment in __smc_connect() and smc_listen_v2_check() compared to v4. - Patch #8: new added, compared to v3. v6->v5: Link: https://lore.kernel.org/netdev/1702371151-125258-1-git-send-email-guwen@linux.alibaba.com/ - Add 'Reviewed-by' label given in the previous versions: * Patch #4, #6, #9, #10 have nothing changed since v3; - Patch #2: * fix the format issue (Alignment should match open parenthesis) compared to v5; * remove useless clc->hdr.length assignment in smcr_clc_prep_confirm_accept() compared to v5; - Patch #3: new added compared to v5. - Patch #7: some minor changes like aclc_v2->aclc or clc_v2->clc compared to v5 due to the introduction of Patch #3. Since there were no major changes, I kept the 'Reviewed-by' label. Other changes in previous versions but not yet acked: - Patch #1: Some minor changes in subject and fix the format issue (length exceeds 80 columns) compared to v3. - Patch #5: removes useless ini->feature_mask assignment in __smc_connect() and smc_listen_v2_check() compared to v4. - Patch #8: new added, compared to v3. v5->v4: Link: https://lore.kernel.org/netdev/1702021259-41504-1-git-send-email-guwen@linux.alibaba.com/ - Patch #6: improve the comment of SMCD_CLC_MAX_V2_GID_ENTRIES; - Patch #4: remove useless ini->feature_mask assignment; v4->v3: https://lore.kernel.org/netdev/1701920994-73705-1-git-send-email-guwen@linux.alibaba.com/ - Patch #6: use SMCD_CLC_MAX_V2_GID_ENTRIES to indicate the max gid entries in CLC proposal and using SMC_MAX_V2_ISM_DEVS to indicate the max devices to propose; - Patch #6: use i and i+1 in smc_find_ism_v2_device_serv(); - Patch #2: replace the large if-else block in smc_clc_send_confirm_accept() with 2 subfunctions; - Fix missing byte order conversion of GID and token in CLC handshake, which is in a separate patch sending to net: https://lore.kernel.org/netdev/1701882157-87956-1-git-send-email-guwen@linux.alibaba.com/ - Patch #7: add extended GID in SMC-D lgr netlink attribute; v3->v2: https://lore.kernel.org/netdev/1701343695-122657-1-git-send-email-guwen@linux.alibaba.com/ - Rename smc_clc_fill_fce as smc_clc_fill_fce_v2x; - Remove ISM_IDENT_MASK from drivers/s390/net/ism.h; - Add explicitly assigning 'false' to ism_v2_capable in ism_dev_init(); - Remove smc_ism_set_v2_capable() helper for now, and introduce it in later loopback-ism implementation; v2->v1: - Fix sparse complaint; - Rebase to the latest net-next; ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/smc/af_smc.c118
-rw-r--r--net/smc/smc.h10
-rw-r--r--net/smc/smc_clc.c318
-rw-r--r--net/smc/smc_clc.h64
-rw-r--r--net/smc/smc_core.c37
-rw-r--r--net/smc/smc_core.h18
-rw-r--r--net/smc/smc_diag.c9
-rw-r--r--net/smc/smc_ism.c50
-rw-r--r--net/smc/smc_ism.h30
-rw-r--r--net/smc/smc_pnet.c4
10 files changed, 417 insertions, 241 deletions
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7fc2f3c6d248..a2cb30af46cb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -677,8 +677,6 @@ static bool smc_isascii(char *hostname)
static void smc_conn_save_peer_info_fce(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *clc)
{
- struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)clc;
struct smc_clc_first_contact_ext *fce;
int clc_v2_len;
@@ -687,17 +685,15 @@ static void smc_conn_save_peer_info_fce(struct smc_sock *smc,
return;
if (smc->conn.lgr->is_smcd) {
- memcpy(smc->conn.lgr->negotiated_eid, clc_v2->d1.eid,
+ memcpy(smc->conn.lgr->negotiated_eid, clc->d1.eid,
SMC_MAX_EID_LEN);
- clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2,
- d1);
+ clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, d1);
} else {
- memcpy(smc->conn.lgr->negotiated_eid, clc_v2->r1.eid,
+ memcpy(smc->conn.lgr->negotiated_eid, clc->r1.eid,
SMC_MAX_EID_LEN);
- clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm_v2,
- r1);
+ clc_v2_len = offsetofend(struct smc_clc_msg_accept_confirm, r1);
}
- fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc_v2) + clc_v2_len);
+ fce = (struct smc_clc_first_contact_ext *)(((u8 *)clc) + clc_v2_len);
smc->conn.lgr->peer_os = fce->os_type;
smc->conn.lgr->peer_smc_release = fce->release;
if (smc_isascii(fce->hostname))
@@ -1048,7 +1044,8 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
{
int rc = SMC_CLC_DECL_NOSMCDDEV;
struct smcd_dev *smcd;
- int i = 1;
+ int i = 1, entry = 1;
+ bool is_virtual;
u16 chid;
if (smcd_indicated(ini->smc_type_v1))
@@ -1060,14 +1057,23 @@ static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
chid = smc_ism_get_chid(smcd);
if (!smc_find_ism_v2_is_unique_chid(chid, ini, i))
continue;
+ is_virtual = __smc_ism_is_virtual(chid);
if (!smc_pnet_is_pnetid_set(smcd->pnetid) ||
smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) {
+ if (is_virtual && entry == SMCD_CLC_MAX_V2_GID_ENTRIES)
+ /* It's the last GID-CHID entry left in CLC
+ * Proposal SMC-Dv2 extension, but a virtual
+ * ISM device will take two entries. So give
+ * up it and try the next potential ISM device.
+ */
+ continue;
ini->ism_dev[i] = smcd;
ini->ism_chid[i] = chid;
ini->is_smcd = true;
rc = 0;
i++;
- if (i > SMC_MAX_ISM_DEVS)
+ entry = is_virtual ? entry + 2 : entry + 1;
+ if (entry > SMCD_CLC_MAX_V2_GID_ENTRIES)
break;
}
}
@@ -1149,13 +1155,13 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
}
#define SMC_CLC_MAX_ACCEPT_LEN \
- (sizeof(struct smc_clc_msg_accept_confirm_v2) + \
+ (sizeof(struct smc_clc_msg_accept_confirm) + \
sizeof(struct smc_clc_first_contact_ext_v2x) + \
sizeof(struct smc_clc_msg_trail))
/* CLC handshake during connect */
static int smc_connect_clc(struct smc_sock *smc,
- struct smc_clc_msg_accept_confirm_v2 *aclc2,
+ struct smc_clc_msg_accept_confirm *aclc,
struct smc_init_info *ini)
{
int rc = 0;
@@ -1165,7 +1171,7 @@ static int smc_connect_clc(struct smc_sock *smc,
if (rc)
return rc;
/* receive SMC Accept CLC message */
- return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN,
+ return smc_clc_wait_msg(smc, aclc, SMC_CLC_MAX_ACCEPT_LEN,
SMC_CLC_ACCEPT, CLC_WAIT_TIME);
}
@@ -1201,10 +1207,8 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
struct smc_clc_msg_accept_confirm *aclc,
struct smc_init_info *ini)
{
- struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)aclc;
struct smc_clc_first_contact_ext *fce =
- smc_get_clc_first_contact_ext(clc_v2, false);
+ smc_get_clc_first_contact_ext(aclc, false);
struct net *net = sock_net(&smc->sk);
int rc;
@@ -1327,10 +1331,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
}
if (aclc->hdr.version > SMC_V1) {
- struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
- eid = clc_v2->r1.eid;
+ eid = aclc->r1.eid;
if (ini->first_contact_local)
smc_fill_gid_list(link->lgr, &ini->smcrv2.gidlist,
link->smcibdev, link->gid);
@@ -1371,7 +1372,7 @@ connect_abort:
* Determine from the CHID of the received CLC ACCEPT the ISM device chosen.
*/
static int
-smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc,
+smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm *aclc,
struct smc_init_info *ini)
{
int i;
@@ -1398,12 +1399,9 @@ static int smc_connect_ism(struct smc_sock *smc,
ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
if (aclc->hdr.version == SMC_V2) {
- struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
if (ini->first_contact_peer) {
struct smc_clc_first_contact_ext *fce =
- smc_get_clc_first_contact_ext(aclc_v2, true);
+ smc_get_clc_first_contact_ext(aclc, true);
ini->release_nr = fce->release;
rc = smc_clc_clnt_v2x_features_validate(fce, ini);
@@ -1411,11 +1409,16 @@ static int smc_connect_ism(struct smc_sock *smc,
return rc;
}
- rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
+ rc = smc_v2_determine_accepted_chid(aclc, ini);
if (rc)
return rc;
+
+ if (__smc_ism_is_virtual(ini->ism_chid[ini->ism_selected]))
+ ini->ism_peer_gid[ini->ism_selected].gid_ext =
+ ntohll(aclc->d1.gid_ext);
+ /* for non-virtual ISM devices, peer gid_ext remains 0. */
}
- ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid);
+ ini->ism_peer_gid[ini->ism_selected].gid = ntohll(aclc->d0.gid);
/* there is only one lgr role for SMC-D; use server lock */
mutex_lock(&smc_server_lgr_pending);
@@ -1437,12 +1440,8 @@ static int smc_connect_ism(struct smc_sock *smc,
smc_rx_init(smc);
smc_tx_init(smc);
- if (aclc->hdr.version > SMC_V1) {
- struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)aclc;
-
- eid = clc_v2->d1.eid;
- }
+ if (aclc->hdr.version > SMC_V1)
+ eid = aclc->d1.eid;
rc = smc_clc_send_confirm(smc, ini->first_contact_local,
aclc->hdr.version, eid, ini);
@@ -1493,7 +1492,6 @@ static int smc_connect_check_aclc(struct smc_init_info *ini,
static int __smc_connect(struct smc_sock *smc)
{
u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
- struct smc_clc_msg_accept_confirm_v2 *aclc2;
struct smc_clc_msg_accept_confirm *aclc;
struct smc_init_info *ini = NULL;
u8 *buf = NULL;
@@ -1541,11 +1539,10 @@ static int __smc_connect(struct smc_sock *smc)
rc = SMC_CLC_DECL_MEM;
goto fallback;
}
- aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf;
- aclc = (struct smc_clc_msg_accept_confirm *)aclc2;
+ aclc = (struct smc_clc_msg_accept_confirm *)buf;
/* perform CLC handshake */
- rc = smc_connect_clc(smc, aclc2, ini);
+ rc = smc_connect_clc(smc, aclc, ini);
if (rc) {
/* -EAGAIN on timeout, see tcp_recvmsg() */
if (rc == -EAGAIN) {
@@ -2106,7 +2103,8 @@ static bool smc_is_already_selected(struct smcd_dev *smcd,
/* check for ISM devices matching proposed ISM devices */
static void smc_check_ism_v2_match(struct smc_init_info *ini,
- u16 proposed_chid, u64 proposed_gid,
+ u16 proposed_chid,
+ struct smcd_gid *proposed_gid,
unsigned int *matches)
{
struct smcd_dev *smcd;
@@ -2118,7 +2116,11 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini,
continue;
if (smc_ism_get_chid(smcd) == proposed_chid &&
!smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) {
- ini->ism_peer_gid[*matches] = proposed_gid;
+ ini->ism_peer_gid[*matches].gid = proposed_gid->gid;
+ if (__smc_ism_is_virtual(proposed_chid))
+ ini->ism_peer_gid[*matches].gid_ext =
+ proposed_gid->gid_ext;
+ /* non-virtual ISM's peer gid_ext remains 0. */
ini->ism_dev[*matches] = smcd;
(*matches)++;
break;
@@ -2140,9 +2142,11 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
struct smc_clc_v2_extension *smc_v2_ext;
struct smc_clc_msg_smcd *pclc_smcd;
unsigned int matches = 0;
+ struct smcd_gid smcd_gid;
u8 smcd_version;
u8 *eid = NULL;
int i, rc;
+ u16 chid;
if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
goto not_found;
@@ -2152,18 +2156,35 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
mutex_lock(&smcd_dev_list.mutex);
- if (pclc_smcd->ism.chid)
+ if (pclc_smcd->ism.chid) {
/* check for ISM device matching proposed native ISM device */
+ smcd_gid.gid = ntohll(pclc_smcd->ism.gid);
+ smcd_gid.gid_ext = 0;
smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid),
- ntohll(pclc_smcd->ism.gid), &matches);
- for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) {
+ &smcd_gid, &matches);
+ }
+ for (i = 0; i < smc_v2_ext->hdr.ism_gid_cnt; i++) {
/* check for ISM devices matching proposed non-native ISM
* devices
*/
- smc_check_ism_v2_match(ini,
- ntohs(smcd_v2_ext->gidchid[i - 1].chid),
- ntohll(smcd_v2_ext->gidchid[i - 1].gid),
- &matches);
+ smcd_gid.gid = ntohll(smcd_v2_ext->gidchid[i].gid);
+ smcd_gid.gid_ext = 0;
+ chid = ntohs(smcd_v2_ext->gidchid[i].chid);
+ if (__smc_ism_is_virtual(chid)) {
+ if ((i + 1) == smc_v2_ext->hdr.ism_gid_cnt ||
+ chid != ntohs(smcd_v2_ext->gidchid[i + 1].chid))
+ /* each virtual ISM device takes two GID-CHID
+ * entries and CHID of the second entry repeats
+ * that of the first entry.
+ *
+ * So check if the next GID-CHID entry exists
+ * and both two entries' CHIDs are the same.
+ */
+ continue;
+ smcd_gid.gid_ext =
+ ntohll(smcd_v2_ext->gidchid[++i].gid);
+ }
+ smc_check_ism_v2_match(ini, chid, &smcd_gid, &matches);
}
mutex_unlock(&smcd_dev_list.mutex);
@@ -2212,7 +2233,8 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
goto not_found;
ini->is_smcd = true; /* prepare ISM check */
- ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
+ ini->ism_peer_gid[0].gid = ntohll(pclc_smcd->ism.gid);
+ ini->ism_peer_gid[0].gid_ext = 0;
rc = smc_find_ism_device(new_smc, ini);
if (rc)
goto not_found;
diff --git a/net/smc/smc.h b/net/smc/smc.h
index cd51261b7d9e..df64efd2dee8 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -29,9 +29,6 @@
#define SMCPROTO_SMC 0 /* SMC protocol, IPv4 */
#define SMCPROTO_SMC6 1 /* SMC protocol, IPv6 */
-#define SMC_MAX_ISM_DEVS 8 /* max # of proposed non-native ISM
- * devices
- */
#define SMC_AUTOCORKING_DEFAULT_SIZE 0x10000 /* 64K by default */
extern struct proto smc_proto;
@@ -58,6 +55,13 @@ enum smc_state { /* possible states of an SMC socket */
SMC_PROCESSABORT = 27,
};
+enum smc_supplemental_features {
+ SMC_SPF_VIRT_ISM_DEV = 0,
+};
+
+#define SMC_FEATURE_MASK \
+ (BIT(SMC_SPF_VIRT_ISM_DEV))
+
struct smc_link_group;
struct smc_wr_rx_hdr { /* common prefix part of LLC and CDC to demultiplex */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 95e19aa3e769..9a13709bea1c 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -155,10 +155,12 @@ static int smc_clc_ueid_remove(char *ueid)
rc = 0;
}
}
+#if IS_ENABLED(CONFIG_S390)
if (!rc && !smc_clc_eid_table.ueid_cnt) {
smc_clc_eid_table.seid_enabled = 1;
rc = -EAGAIN; /* indicate success and enabling of seid */
}
+#endif
write_unlock(&smc_clc_eid_table.lock);
return rc;
}
@@ -273,22 +275,30 @@ err:
int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info)
{
+#if IS_ENABLED(CONFIG_S390)
write_lock(&smc_clc_eid_table.lock);
smc_clc_eid_table.seid_enabled = 1;
write_unlock(&smc_clc_eid_table.lock);
return 0;
+#else
+ return -EOPNOTSUPP;
+#endif
}
int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info)
{
int rc = 0;
+#if IS_ENABLED(CONFIG_S390)
write_lock(&smc_clc_eid_table.lock);
if (!smc_clc_eid_table.ueid_cnt)
rc = -ENOENT;
else
smc_clc_eid_table.seid_enabled = 0;
write_unlock(&smc_clc_eid_table.lock);
+#else
+ rc = -EOPNOTSUPP;
+#endif
return rc;
}
@@ -377,9 +387,9 @@ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
/* check arriving CLC accept or confirm */
static bool
-smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
+smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm *clc)
{
- struct smc_clc_msg_hdr *hdr = &clc_v2->hdr;
+ struct smc_clc_msg_hdr *hdr = &clc->hdr;
if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D)
return false;
@@ -418,15 +428,16 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc)
return true;
}
-static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
- struct smc_init_info *ini)
+static int smc_clc_fill_fce_v2x(struct smc_clc_first_contact_ext_v2x *fce_v2x,
+ struct smc_init_info *ini)
{
- int ret = sizeof(*fce);
+ int ret = sizeof(*fce_v2x);
- memset(fce, 0, sizeof(*fce));
- fce->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
- fce->fce_v2_base.release = ini->release_nr;
- memcpy(fce->fce_v2_base.hostname, smc_hostname, sizeof(smc_hostname));
+ memset(fce_v2x, 0, sizeof(*fce_v2x));
+ fce_v2x->fce_v2_base.os_type = SMC_CLC_OS_LINUX;
+ fce_v2x->fce_v2_base.release = ini->release_nr;
+ memcpy(fce_v2x->fce_v2_base.hostname,
+ smc_hostname, sizeof(smc_hostname));
if (ini->is_smcd && ini->release_nr < SMC_RELEASE_1) {
ret = sizeof(struct smc_clc_first_contact_ext);
goto out;
@@ -434,9 +445,10 @@ static int smc_clc_fill_fce(struct smc_clc_first_contact_ext_v2x *fce,
if (ini->release_nr >= SMC_RELEASE_1) {
if (!ini->is_smcd) {
- fce->max_conns = ini->max_conns;
- fce->max_links = ini->max_links;
+ fce_v2x->max_conns = ini->max_conns;
+ fce_v2x->max_links = ini->max_links;
}
+ fce_v2x->feature_mask = htons(ini->feature_mask);
}
out:
@@ -448,7 +460,7 @@ out:
*/
static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
{
- struct smc_clc_msg_accept_confirm_v2 *clc_v2;
+ struct smc_clc_msg_accept_confirm *clc;
struct smc_clc_msg_proposal *pclc;
struct smc_clc_msg_decline *dclc;
struct smc_clc_msg_trail *trl;
@@ -466,12 +478,11 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
break;
case SMC_CLC_ACCEPT:
case SMC_CLC_CONFIRM:
- clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm;
- if (!smc_clc_msg_acc_conf_valid(clc_v2))
+ clc = (struct smc_clc_msg_accept_confirm *)clcm;
+ if (!smc_clc_msg_acc_conf_valid(clc))
return false;
trl = (struct smc_clc_msg_trail *)
- ((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) -
- sizeof(*trl));
+ ((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
break;
case SMC_CLC_DECLINE:
dclc = (struct smc_clc_msg_decline *)clcm;
@@ -882,11 +893,13 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
ETH_ALEN);
}
if (smcd_indicated(ini->smc_type_v1)) {
+ struct smcd_gid smcd_gid;
+
/* add SMC-D specifics */
if (ini->ism_dev[0]) {
smcd = ini->ism_dev[0];
- pclc_smcd->ism.gid =
- htonll(smcd->ops->get_local_gid(smcd));
+ smcd->ops->get_local_gid(smcd, &smcd_gid);
+ pclc_smcd->ism.gid = htonll(smcd_gid.gid);
pclc_smcd->ism.chid =
htons(smc_ism_get_chid(ini->ism_dev[0]));
}
@@ -907,6 +920,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
pclc_smcd->v2_ext_offset = htons(v2_ext_offset);
plen += sizeof(*v2_ext);
+ v2_ext->feature_mask = htons(SMC_FEATURE_MASK);
read_lock(&smc_clc_eid_table.lock);
v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt;
plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN;
@@ -918,10 +932,11 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
read_unlock(&smc_clc_eid_table.lock);
}
if (smcd_indicated(ini->smc_type_v2)) {
+ struct smcd_gid smcd_gid;
u8 *eid = NULL;
+ int entry = 0;
v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled;
- v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;
v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -
offsetofend(struct smc_clnt_opts_area_hdr,
smcd_v2_ext_offset) +
@@ -933,14 +948,26 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
if (ini->ism_offered_cnt) {
for (i = 1; i <= ini->ism_offered_cnt; i++) {
smcd = ini->ism_dev[i];
- gidchids[i - 1].gid =
- htonll(smcd->ops->get_local_gid(smcd));
- gidchids[i - 1].chid =
+ smcd->ops->get_local_gid(smcd, &smcd_gid);
+ gidchids[entry].chid =
htons(smc_ism_get_chid(ini->ism_dev[i]));
+ gidchids[entry].gid = htonll(smcd_gid.gid);
+ if (smc_ism_is_virtual(smcd)) {
+ /* a virtual ISM device takes two
+ * entries. CHID of the second entry
+ * repeats that of the first entry.
+ */
+ gidchids[entry + 1].chid =
+ gidchids[entry].chid;
+ gidchids[entry + 1].gid =
+ htonll(smcd_gid.gid_ext);
+ entry++;
+ }
+ entry++;
}
- plen += ini->ism_offered_cnt *
- sizeof(struct smc_clc_smcd_gid_chid);
+ plen += entry * sizeof(struct smc_clc_smcd_gid_chid);
}
+ v2_ext->hdr.ism_gid_cnt = entry;
}
if (smcr_indicated(ini->smc_type_v2)) {
memcpy(v2_ext->roce, ini->smcrv2.ib_gid_v2, SMC_GID_SIZE);
@@ -976,7 +1003,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
vec[i++].iov_len = sizeof(*smcd_v2_ext);
if (ini->ism_offered_cnt) {
vec[i].iov_base = gidchids;
- vec[i++].iov_len = ini->ism_offered_cnt *
+ vec[i++].iov_len = v2_ext->hdr.ism_gid_cnt *
sizeof(struct smc_clc_smcd_gid_chid);
}
}
@@ -997,109 +1024,143 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
return reason_code;
}
+static void
+smcd_clc_prep_confirm_accept(struct smc_connection *conn,
+ struct smc_clc_msg_accept_confirm *clc,
+ int first_contact, u8 version,
+ u8 *eid, struct smc_init_info *ini,
+ int *fce_len,
+ struct smc_clc_first_contact_ext_v2x *fce_v2x,
+ struct smc_clc_msg_trail *trl)
+{
+ struct smcd_dev *smcd = conn->lgr->smcd;
+ struct smcd_gid smcd_gid;
+ u16 chid;
+ int len;
+
+ /* SMC-D specific settings */
+ memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+ smcd->ops->get_local_gid(smcd, &smcd_gid);
+ clc->hdr.typev1 = SMC_TYPE_D;
+ clc->d0.gid = htonll(smcd_gid.gid);
+ clc->d0.token = htonll(conn->rmb_desc->token);
+ clc->d0.dmbe_size = conn->rmbe_size_comp;
+ clc->d0.dmbe_idx = 0;
+ memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+ if (version == SMC_V1) {
+ clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+ } else {
+ chid = smc_ism_get_chid(smcd);
+ clc->d1.chid = htons(chid);
+ if (eid && eid[0])
+ memcpy(clc->d1.eid, eid, SMC_MAX_EID_LEN);
+ if (__smc_ism_is_virtual(chid))
+ clc->d1.gid_ext = htonll(smcd_gid.gid_ext);
+ len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
+ if (first_contact) {
+ *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini);
+ len += *fce_len;
+ }
+ clc->hdr.length = htons(len);
+ }
+ memcpy(trl->eyecatcher, SMCD_EYECATCHER,
+ sizeof(SMCD_EYECATCHER));
+}
+
+static void
+smcr_clc_prep_confirm_accept(struct smc_connection *conn,
+ struct smc_clc_msg_accept_confirm *clc,
+ int first_contact, u8 version,
+ u8 *eid, struct smc_init_info *ini,
+ int *fce_len,
+ struct smc_clc_first_contact_ext_v2x *fce_v2x,
+ struct smc_clc_fce_gid_ext *gle,
+ struct smc_clc_msg_trail *trl)
+{
+ struct smc_link *link = conn->lnk;
+ int len;
+
+ /* SMC-R specific settings */
+ memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
+ sizeof(SMC_EYECATCHER));
+ clc->hdr.typev1 = SMC_TYPE_R;
+ memcpy(clc->r0.lcl.id_for_peer, local_systemid,
+ sizeof(local_systemid));
+ memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
+ memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+ ETH_ALEN);
+ hton24(clc->r0.qpn, link->roce_qp->qp_num);
+ clc->r0.rmb_rkey =
+ htonl(conn->rmb_desc->mr[link->link_idx]->rkey);
+ clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+ clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
+ switch (clc->hdr.type) {
+ case SMC_CLC_ACCEPT:
+ clc->r0.qp_mtu = link->path_mtu;
+ break;
+ case SMC_CLC_CONFIRM:
+ clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
+ break;
+ }
+ clc->r0.rmbe_size = conn->rmbe_size_comp;
+ clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ?
+ cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) :
+ cpu_to_be64((u64)sg_dma_address
+ (conn->rmb_desc->sgt[link->link_idx].sgl));
+ hton24(clc->r0.psn, link->psn_initial);
+ if (version == SMC_V1) {
+ clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+ } else {
+ if (eid && eid[0])
+ memcpy(clc->r1.eid, eid, SMC_MAX_EID_LEN);
+ len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
+ if (first_contact) {
+ *fce_len = smc_clc_fill_fce_v2x(fce_v2x, ini);
+ len += *fce_len;
+ fce_v2x->fce_v2_base.v2_direct =
+ !link->lgr->uses_gateway;
+ if (clc->hdr.type == SMC_CLC_CONFIRM) {
+ memset(gle, 0, sizeof(*gle));
+ gle->gid_cnt = ini->smcrv2.gidlist.len;
+ len += sizeof(*gle);
+ len += gle->gid_cnt * sizeof(gle->gid[0]);
+ }
+ }
+ clc->hdr.length = htons(len);
+ }
+ memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+}
+
/* build and send CLC CONFIRM / ACCEPT message */
static int smc_clc_send_confirm_accept(struct smc_sock *smc,
- struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+ struct smc_clc_msg_accept_confirm *clc,
int first_contact, u8 version,
u8 *eid, struct smc_init_info *ini)
{
+ struct smc_clc_first_contact_ext_v2x fce_v2x;
struct smc_connection *conn = &smc->conn;
- struct smc_clc_first_contact_ext_v2x fce;
- struct smcd_dev *smcd = conn->lgr->smcd;
- struct smc_clc_msg_accept_confirm *clc;
struct smc_clc_fce_gid_ext gle;
struct smc_clc_msg_trail trl;
- int i, len, fce_len;
+ int i, fce_len;
struct kvec vec[5];
struct msghdr msg;
/* send SMC Confirm CLC msg */
- clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
clc->hdr.version = version; /* SMC version */
if (first_contact)
clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK;
- if (conn->lgr->is_smcd) {
- /* SMC-D specific settings */
- memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
- sizeof(SMCD_EYECATCHER));
- clc->hdr.typev1 = SMC_TYPE_D;
- clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd));
- clc->d0.token = htonll(conn->rmb_desc->token);
- clc->d0.dmbe_size = conn->rmbe_size_comp;
- clc->d0.dmbe_idx = 0;
- memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
- if (version == SMC_V1) {
- clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
- } else {
- clc_v2->d1.chid = htons(smc_ism_get_chid(smcd));
- if (eid && eid[0])
- memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN);
- len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
- if (first_contact) {
- fce_len = smc_clc_fill_fce(&fce, ini);
- len += fce_len;
- }
- clc_v2->hdr.length = htons(len);
- }
- memcpy(trl.eyecatcher, SMCD_EYECATCHER,
- sizeof(SMCD_EYECATCHER));
- } else {
- struct smc_link *link = conn->lnk;
-
- /* SMC-R specific settings */
- memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
- sizeof(SMC_EYECATCHER));
- clc->hdr.typev1 = SMC_TYPE_R;
- clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
- memcpy(clc->r0.lcl.id_for_peer, local_systemid,
- sizeof(local_systemid));
- memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
- memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
- ETH_ALEN);
- hton24(clc->r0.qpn, link->roce_qp->qp_num);
- clc->r0.rmb_rkey =
- htonl(conn->rmb_desc->mr[link->link_idx]->rkey);
- clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
- clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
- switch (clc->hdr.type) {
- case SMC_CLC_ACCEPT:
- clc->r0.qp_mtu = link->path_mtu;
- break;
- case SMC_CLC_CONFIRM:
- clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
- break;
- }
- clc->r0.rmbe_size = conn->rmbe_size_comp;
- clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ?
- cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) :
- cpu_to_be64((u64)sg_dma_address
- (conn->rmb_desc->sgt[link->link_idx].sgl));
- hton24(clc->r0.psn, link->psn_initial);
- if (version == SMC_V1) {
- clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
- } else {
- if (eid && eid[0])
- memcpy(clc_v2->r1.eid, eid, SMC_MAX_EID_LEN);
- len = SMCR_CLC_ACCEPT_CONFIRM_LEN_V2;
- if (first_contact) {
- fce_len = smc_clc_fill_fce(&fce, ini);
- len += fce_len;
- fce.fce_v2_base.v2_direct = !link->lgr->uses_gateway;
- if (clc->hdr.type == SMC_CLC_CONFIRM) {
- memset(&gle, 0, sizeof(gle));
- gle.gid_cnt = ini->smcrv2.gidlist.len;
- len += sizeof(gle);
- len += gle.gid_cnt * sizeof(gle.gid[0]);
- }
- }
- clc_v2->hdr.length = htons(len);
- }
- memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
- }
-
+ if (conn->lgr->is_smcd)
+ smcd_clc_prep_confirm_accept(conn, clc, first_contact,
+ version, eid, ini, &fce_len,
+ &fce_v2x, &trl);
+ else
+ smcr_clc_prep_confirm_accept(conn, clc, first_contact,
+ version, eid, ini, &fce_len,
+ &fce_v2x, &gle, &trl);
memset(&msg, 0, sizeof(msg));
i = 0;
- vec[i].iov_base = clc_v2;
+ vec[i].iov_base = clc;
if (version > SMC_V1)
vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ?
SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 :
@@ -1111,7 +1172,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
SMCR_CLC_ACCEPT_CONFIRM_LEN) -
sizeof(trl);
if (version > SMC_V1 && first_contact) {
- vec[i].iov_base = &fce;
+ vec[i].iov_base = &fce_v2x;
vec[i++].iov_len = fce_len;
if (!conn->lgr->is_smcd) {
if (clc->hdr.type == SMC_CLC_CONFIRM) {
@@ -1133,16 +1194,16 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc,
int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
u8 version, u8 *eid, struct smc_init_info *ini)
{
- struct smc_clc_msg_accept_confirm_v2 cclc_v2;
+ struct smc_clc_msg_accept_confirm cclc;
int reason_code = 0;
int len;
/* send SMC Confirm CLC msg */
- memset(&cclc_v2, 0, sizeof(cclc_v2));
- cclc_v2.hdr.type = SMC_CLC_CONFIRM;
- len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact,
+ memset(&cclc, 0, sizeof(cclc));
+ cclc.hdr.type = SMC_CLC_CONFIRM;
+ len = smc_clc_send_confirm_accept(smc, &cclc, clnt_first_contact,
version, eid, ini);
- if (len < ntohs(cclc_v2.hdr.length)) {
+ if (len < ntohs(cclc.hdr.length)) {
if (len >= 0) {
reason_code = -ENETUNREACH;
smc->sk.sk_err = -reason_code;
@@ -1158,14 +1219,14 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
u8 version, u8 *negotiated_eid, struct smc_init_info *ini)
{
- struct smc_clc_msg_accept_confirm_v2 aclc_v2;
+ struct smc_clc_msg_accept_confirm aclc;
int len;
- memset(&aclc_v2, 0, sizeof(aclc_v2));
- aclc_v2.hdr.type = SMC_CLC_ACCEPT;
- len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
+ memset(&aclc, 0, sizeof(aclc));
+ aclc.hdr.type = SMC_CLC_ACCEPT;
+ len = smc_clc_send_confirm_accept(new_smc, &aclc, srv_first_contact,
version, negotiated_eid, ini);
- if (len < ntohs(aclc_v2.hdr.length))
+ if (len < ntohs(aclc.hdr.length))
len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
return len > 0 ? 0 : len;
@@ -1180,6 +1241,7 @@ int smc_clc_srv_v2x_features_validate(struct smc_sock *smc,
ini->max_conns = SMC_CONN_PER_LGR_MAX;
ini->max_links = SMC_LINKS_ADD_LNK_MAX;
+ ini->feature_mask = SMC_FEATURE_MASK;
if ((!(ini->smcd_version & SMC_V2) && !(ini->smcr_version & SMC_V2)) ||
ini->release_nr < SMC_RELEASE_1)
@@ -1223,6 +1285,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
return SMC_CLC_DECL_MAXLINKERR;
ini->max_links = fce_v2x->max_links;
}
+ /* common supplemental features of server and client */
+ ini->feature_mask = ntohs(fce_v2x->feature_mask) & SMC_FEATURE_MASK;
return 0;
}
@@ -1230,10 +1294,8 @@ int smc_clc_clnt_v2x_features_validate(struct smc_clc_first_contact_ext *fce,
int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
struct smc_init_info *ini)
{
- struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
- (struct smc_clc_msg_accept_confirm_v2 *)cclc;
struct smc_clc_first_contact_ext *fce =
- smc_get_clc_first_contact_ext(clc_v2, ini->is_smcd);
+ smc_get_clc_first_contact_ext(cclc, ini->is_smcd);
struct smc_clc_first_contact_ext_v2x *fce_v2x =
(struct smc_clc_first_contact_ext_v2x *)fce;
@@ -1253,6 +1315,8 @@ int smc_clc_v2x_features_confirm_check(struct smc_clc_msg_accept_confirm *cclc,
if (fce_v2x->max_links != ini->max_links)
return SMC_CLC_DECL_MAXLINKERR;
}
+ /* common supplemental features returned by client */
+ ini->feature_mask = ntohs(fce_v2x->feature_mask);
return 0;
}
@@ -1274,7 +1338,11 @@ void __init smc_clc_init(void)
INIT_LIST_HEAD(&smc_clc_eid_table.list);
r