* [PATCH net-next v8 1/2] net: pppoe: implement GRO/GSO support
From: Qingfang Deng @ 2026-05-01 3:50 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, David Ahern, Ido Schimmel,
Qingfang Deng, Guillaume Nault, Kees Cook, Felix Fietkau,
Eric Woudstra, Willem de Bruijn, Kuniyuki Iwashima,
Richard Gobert, netdev, linux-kernel
Cc: linux-ppp
From: Felix Fietkau <nbd@nbd.name>
Only handles packets where the pppoe header length field matches the exact
packet length. Significantly improves rx throughput.
When running NAT traffic through a MediaTek MT7621 devices from a host
behind PPPoE to a host directly connected via ethernet, the TCP throughput
that the device is able to handle improves from ~130 Mbit/s to ~630 Mbit/s,
using fraglist GRO.
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Qingfang Deng <qingfang.deng@linux.dev>
---
v8: no changes
v7: https://lore.kernel.org/netdev/20260428064717.74794-1-qingfang.deng@linux.dev
- Use PPPOE_SES_HLEN macro instead of +2 magic number
v6: https://lore.kernel.org/netdev/20260326081127.61229-1-dqfext@gmail.com
- avoid phdr->length field overflow
- restore skb_is_gso() check
- do not register GRO if INET=n
- do not check for PPP_IPV6 if IPV6=n
- tail call gro_complete
drivers/net/ppp/pppoe.c | 165 +++++++++++++++++++++++++++++++++++++++-
net/ipv4/af_inet.c | 2 +
net/ipv6/ip6_offload.c | 2 +
3 files changed, 168 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index bdd61c504a1c..363204e0c49a 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -77,6 +77,7 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>
+#include <net/gro.h>
#include <linux/uaccess.h>
@@ -409,7 +410,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
if (ppp_skb_is_compressed_proto(skb))
goto drop;
- if (pskb_trim_rcsum(skb, len))
+ if (!skb_is_gso(skb) && pskb_trim_rcsum(skb, len))
goto drop;
ph = pppoe_hdr(skb);
@@ -1103,6 +1104,164 @@ static struct pernet_operations pppoe_net_ops = {
.size = sizeof(struct pppoe_net),
};
+static u16
+compare_pppoe_header(const struct pppoe_hdr *phdr,
+ const struct pppoe_hdr *phdr2)
+{
+ __be16 proto = *(const __be16 *)(phdr + 1);
+ __be16 proto2 = *(const __be16 *)(phdr2 + 1);
+
+ return (__force u16)((phdr->sid ^ phdr2->sid) | (proto ^ proto2));
+}
+
+static __be16 pppoe_hdr_proto(const struct pppoe_hdr *phdr)
+{
+ __be16 proto = *(const __be16 *)(phdr + 1);
+
+ switch (proto) {
+ case cpu_to_be16(PPP_IP):
+ return cpu_to_be16(ETH_P_IP);
+#if IS_ENABLED(CONFIG_IPV6)
+ case cpu_to_be16(PPP_IPV6):
+ return cpu_to_be16(ETH_P_IPV6);
+#endif
+ default:
+ return 0;
+ }
+}
+
+static struct sk_buff *pppoe_gro_receive(struct list_head *head,
+ struct sk_buff *skb)
+{
+ const struct packet_offload *ptype;
+ unsigned int hlen, off_pppoe;
+ const struct pppoe_hdr *phdr;
+ struct sk_buff *pp = NULL;
+ struct sk_buff *p;
+ int flush = 1;
+ __be16 type;
+
+ off_pppoe = skb_gro_offset(skb);
+ hlen = off_pppoe + PPPOE_SES_HLEN;
+ phdr = skb_gro_header(skb, hlen, off_pppoe);
+ if (unlikely(!phdr))
+ goto out;
+
+ /* filter for session packets (type:1, ver:1, code:0) */
+ if (*(const __be16 *)phdr != cpu_to_be16(0x1100))
+ goto out;
+
+ /* ignore packets with padding or invalid length */
+ if (skb_gro_len(skb) != be16_to_cpu(phdr->length) + sizeof(*phdr))
+ goto out;
+
+ type = pppoe_hdr_proto(phdr);
+ ptype = gro_find_receive_by_type(type);
+ if (!ptype)
+ goto out;
+
+ flush = 0;
+
+ list_for_each_entry(p, head, list) {
+ const struct pppoe_hdr *phdr2;
+
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ phdr2 = (const struct pppoe_hdr *)(p->data + off_pppoe);
+ if (compare_pppoe_header(phdr, phdr2))
+ NAPI_GRO_CB(p)->same_flow = 0;
+ }
+
+ skb_gro_pull(skb, PPPOE_SES_HLEN);
+ skb_gro_postpull_rcsum(skb, phdr, PPPOE_SES_HLEN);
+
+ pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
+ ipv6_gro_receive, inet_gro_receive,
+ head, skb);
+
+out:
+ skb_gro_flush_final(skb, pp, flush);
+
+ return pp;
+}
+
+static int pppoe_gro_complete(struct sk_buff *skb, int nhoff)
+{
+ struct pppoe_hdr *phdr = (struct pppoe_hdr *)(skb->data + nhoff);
+ __be16 type = pppoe_hdr_proto(phdr);
+ struct packet_offload *ptype;
+ unsigned int len;
+
+ ptype = gro_find_complete_by_type(type);
+ if (!ptype)
+ return -ENOENT;
+
+ len = skb->len - (nhoff + sizeof(*phdr));
+ len = min(len, 0xFFFFU);
+ phdr->length = cpu_to_be16(len);
+
+ return INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+ ipv6_gro_complete, inet_gro_complete,
+ skb, nhoff + PPPOE_SES_HLEN);
+}
+
+static struct sk_buff *pppoe_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ u16 mac_offset = skb->mac_header;
+ struct packet_offload *ptype;
+ u16 mac_len = skb->mac_len;
+ struct pppoe_hdr *phdr;
+ __be16 orig_type, type;
+ int len, nhoff;
+
+ skb_reset_network_header(skb);
+ nhoff = skb_network_header(skb) - skb_mac_header(skb);
+
+ if (unlikely(!pskb_may_pull(skb, PPPOE_SES_HLEN)))
+ goto out;
+
+ phdr = (struct pppoe_hdr *)skb_network_header(skb);
+ type = pppoe_hdr_proto(phdr);
+ ptype = gro_find_complete_by_type(type);
+ if (!ptype)
+ goto out;
+
+ orig_type = skb->protocol;
+ __skb_pull(skb, PPPOE_SES_HLEN);
+ segs = ptype->callbacks.gso_segment(skb, features);
+ if (IS_ERR_OR_NULL(segs)) {
+ skb_gso_error_unwind(skb, orig_type, PPPOE_SES_HLEN, mac_offset,
+ mac_len);
+ goto out;
+ }
+
+ skb = segs;
+ do {
+ phdr = (struct pppoe_hdr *)(skb_mac_header(skb) + nhoff);
+ len = skb->len - (nhoff + sizeof(*phdr));
+ phdr->length = cpu_to_be16(len);
+ skb->network_header = (u8 *)phdr - skb->head;
+ skb->protocol = orig_type;
+ skb_reset_mac_len(skb);
+ } while ((skb = skb->next));
+
+out:
+ return segs;
+}
+
+static struct packet_offload pppoe_packet_offload __read_mostly = {
+ .type = cpu_to_be16(ETH_P_PPP_SES),
+ .priority = 20,
+ .callbacks = {
+ .gro_receive = pppoe_gro_receive,
+ .gro_complete = pppoe_gro_complete,
+ .gso_segment = pppoe_gso_segment,
+ },
+};
+
static int __init pppoe_init(void)
{
int err;
@@ -1119,6 +1278,8 @@ static int __init pppoe_init(void)
if (err)
goto out_unregister_pppoe_proto;
+ if (IS_ENABLED(CONFIG_INET))
+ dev_add_offload(&pppoe_packet_offload);
dev_add_pack(&pppoes_ptype);
dev_add_pack(&pppoed_ptype);
register_netdevice_notifier(&pppoe_notifier);
@@ -1138,6 +1299,8 @@ static void __exit pppoe_exit(void)
unregister_netdevice_notifier(&pppoe_notifier);
dev_remove_pack(&pppoed_ptype);
dev_remove_pack(&pppoes_ptype);
+ if (IS_ENABLED(CONFIG_INET))
+ dev_remove_offload(&pppoe_packet_offload);
unregister_pppox_proto(PX_PROTO_OE);
proto_unregister(&pppoe_sk_proto);
unregister_pernet_device(&pppoe_net_ops);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 0e62032e76b1..cbac072633bb 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1540,6 +1540,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
return pp;
}
+EXPORT_INDIRECT_CALLABLE(inet_gro_receive);
static struct sk_buff *ipip_gro_receive(struct list_head *head,
struct sk_buff *skb)
@@ -1625,6 +1626,7 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
out:
return err;
}
+EXPORT_INDIRECT_CALLABLE(inet_gro_complete);
static int ipip_gro_complete(struct sk_buff *skb, int nhoff)
{
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index d8072ad6b8c4..78f50c93c536 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -297,6 +297,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
return pp;
}
+EXPORT_INDIRECT_CALLABLE(ipv6_gro_receive);
static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
struct sk_buff *skb)
@@ -359,6 +360,7 @@ INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
out:
return err;
}
+EXPORT_INDIRECT_CALLABLE(ipv6_gro_complete);
static int sit_gro_complete(struct sk_buff *skb, int nhoff)
{
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v8 2/2] selftests: net: test PPPoE packets in gro.sh
From: Qingfang Deng @ 2026-05-01 3:50 UTC (permalink / raw)
To: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Shuah Khan, Simon Horman, Willem de Bruijn,
Petr Machata, Anubhav Singh, Richard Gobert, netdev,
linux-kselftest, linux-kernel
Cc: linux-ppp, Qingfang Deng
In-Reply-To: <20260501035102.293031-1-qingfang.deng@linux.dev>
Add PPPoE test-cases to the GRO selftest. Only run a subset of
common_tests to avoid changing the hardcoded L3 offsets everywhere.
Add a new "pppoe_sid" test case to verify that packets with different
PPPoE session IDs are correctly identified as separate flows and not
coalesced.
Signed-off-by: Qingfang Deng <qingfang.deng@linux.dev>
---
v8:
- add a new macro L2_HLEN_MAX for PPPoE
v7: https://lore.kernel.org/netdev/20260428064717.74794-2-qingfang.deng@linux.dev
- Do not run all the tests for PPPoE
- Add a new test for PPPoE
v6: https://lore.kernel.org/netdev/20260326081127.61229-2-dqfext@gmail.com
tools/testing/selftests/drivers/net/config | 2 +
tools/testing/selftests/drivers/net/gro.py | 11 +++
tools/testing/selftests/net/lib/gro.c | 100 +++++++++++++++++----
3 files changed, 97 insertions(+), 16 deletions(-)
diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config
index fd16994366f4..07e386895b94 100644
--- a/tools/testing/selftests/drivers/net/config
+++ b/tools/testing/selftests/drivers/net/config
@@ -8,5 +8,7 @@ CONFIG_NETCONSOLE=m
CONFIG_NETCONSOLE_DYNAMIC=y
CONFIG_NETCONSOLE_EXTENDED_LOG=y
CONFIG_NETDEVSIM=m
+CONFIG_PPP=y
+CONFIG_PPPOE=y
CONFIG_VLAN_8021Q=m
CONFIG_XDP_SOCKETS=y
diff --git a/tools/testing/selftests/drivers/net/gro.py b/tools/testing/selftests/drivers/net/gro.py
index 221f27e57147..ad7c80f7ba96 100755
--- a/tools/testing/selftests/drivers/net/gro.py
+++ b/tools/testing/selftests/drivers/net/gro.py
@@ -313,6 +313,12 @@ def _gro_variants():
"ip_frag6", "ip_v6ext_same", "ip_v6ext_diff",
]
+ # Tests specific to PPPoE
+ pppoe_tests = [
+ "data_same", "data_lrg_sml", "data_sml_lrg", "data_lrg_1byte",
+ "data_burst", "pppoe_sid",
+ ]
+
for mode in ["sw", "hw", "lro"]:
for protocol in ["ipv4", "ipv6", "ipip", "ip6ip6"]:
for test_name in common_tests:
@@ -325,6 +331,11 @@ def _gro_variants():
for test_name in ipv6_tests:
yield mode, protocol, test_name
+ for mode in ["sw"]:
+ for protocol in ["pppoev4", "pppoev6"]:
+ for test_name in pppoe_tests:
+ yield mode, protocol, test_name
+
@ksft_variants(_gro_variants())
def test(cfg, mode, protocol, test_name):
diff --git a/tools/testing/selftests/net/lib/gro.c b/tools/testing/selftests/net/lib/gro.c
index 11b16ae5f0e8..4ffb0491c0da 100644
--- a/tools/testing/selftests/net/lib/gro.c
+++ b/tools/testing/selftests/net/lib/gro.c
@@ -67,12 +67,14 @@
#include <errno.h>
#include <error.h>
#include <getopt.h>
+#include <net/ethernet.h>
+#include <net/if.h>
#include <linux/filter.h>
#include <linux/if_packet.h>
+#include <linux/if_pppox.h>
#include <linux/ipv6.h>
#include <linux/net_tstamp.h>
-#include <net/ethernet.h>
-#include <net/if.h>
+#include <linux/ppp_defs.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/ip6.h>
@@ -102,6 +104,7 @@
#define MAX_LARGE_PKT_CNT ((IP_MAXPACKET - (MAX_HDR_LEN - ETH_HLEN)) / \
(ASSUMED_MTU - (MAX_HDR_LEN - ETH_HLEN)))
#define MIN_EXTHDR_SIZE 8
+#define L2_HLEN_MAX (ETH_HLEN + PPPOE_SES_HLEN)
#define EXT_PAYLOAD_1 "\x00\x00\x00\x00\x00\x00"
#define EXT_PAYLOAD_2 "\x11\x11\x11\x11\x11\x11"
@@ -134,6 +137,7 @@ static int total_hdr_len = -1;
static int ethhdr_proto = -1;
static bool ipip;
static bool ip6ip6;
+static bool pppoe;
static uint64_t txtime_ns;
static int num_flows = 4;
static bool order_check;
@@ -171,6 +175,22 @@ static void vlog(const char *fmt, ...)
}
}
+static void fill_pppoelayer(void *buf, int payload_len, uint16_t sid)
+{
+ struct pppoe_ppp_hdr {
+ struct pppoe_hdr eh;
+ __be16 proto;
+ } *ph = buf;
+
+ payload_len += sizeof(struct tcphdr);
+ ph->eh.type = 1;
+ ph->eh.ver = 1;
+ ph->eh.code = 0;
+ ph->eh.sid = htons(sid);
+ ph->eh.length = htons(payload_len + sizeof(ph->proto));
+ ph->proto = htons(proto == PF_INET ? PPP_IP : PPP_IPV6);
+}
+
static void setup_sock_filter(int fd)
{
const int dport_off = tcp_offset + offsetof(struct tcphdr, dest);
@@ -412,11 +432,15 @@ static void create_packet(void *buf, int seq_offset, int ack_offset,
fill_networklayer(buf + inner_ip_off, payload_len, IPPROTO_TCP);
if (inner_ip_off > ETH_HLEN) {
- int encap_proto = (proto == PF_INET) ?
- IPPROTO_IPIP : IPPROTO_IPV6;
+ if (pppoe) {
+ fill_pppoelayer(buf + ETH_HLEN, payload_len + ip_hdr_len, 0x1234);
+ } else {
+ int encap_proto = (proto == PF_INET) ?
+ IPPROTO_IPIP : IPPROTO_IPV6;
- fill_networklayer(buf + ETH_HLEN,
- payload_len + ip_hdr_len, encap_proto);
+ fill_networklayer(buf + ETH_HLEN,
+ payload_len + ip_hdr_len, encap_proto);
+ }
}
fill_datalinklayer(buf);
@@ -526,7 +550,7 @@ static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn,
static void send_data_pkts(int fd, struct sockaddr_ll *daddr,
int payload_len1, int payload_len2)
{
- static char buf[ETH_HLEN + IP_MAXPACKET];
+ static char buf[L2_HLEN_MAX + IP_MAXPACKET];
create_packet(buf, 0, 0, payload_len1, 0);
write_packet(fd, buf, total_hdr_len + payload_len1, daddr);
@@ -1071,6 +1095,20 @@ static void send_fragment6(int fd, struct sockaddr_ll *daddr)
write_packet(fd, buf, bufpkt_len, daddr);
}
+static void send_changed_pppoe_sid(int fd, struct sockaddr_ll *daddr)
+{
+ static char buf[L2_HLEN_MAX + PAYLOAD_LEN];
+ int pkt_size = total_hdr_len + PAYLOAD_LEN;
+ struct pppoe_hdr *hdr = (struct pppoe_hdr *)(buf + ETH_HLEN);
+
+ create_packet(buf, 0, 0, PAYLOAD_LEN, 0);
+ write_packet(fd, buf, pkt_size, daddr);
+
+ create_packet(buf, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0);
+ hdr->sid = htons(0x4321);
+ write_packet(fd, buf, pkt_size, daddr);
+}
+
static void bind_packetsocket(int fd)
{
struct sockaddr_ll daddr = {};
@@ -1121,9 +1159,10 @@ static void recv_error(int fd, int rcv_errno)
static void check_recv_pkts(int fd, int *correct_payload,
int correct_num_pkts)
{
- static char buffer[IP_MAXPACKET + ETH_HLEN + 1];
- struct iphdr *iph = (struct iphdr *)(buffer + ETH_HLEN);
- struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + ETH_HLEN);
+ static char buffer[IP_MAXPACKET + L2_HLEN_MAX + 1];
+ int nhoff = ETH_HLEN + (pppoe ? PPPOE_SES_HLEN : 0);
+ struct iphdr *iph = (struct iphdr *)(buffer + nhoff);
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + nhoff);
struct tcphdr *tcph;
bool bad_packet = false;
int tcp_ext_len = 0;
@@ -1140,7 +1179,7 @@ static void check_recv_pkts(int fd, int *correct_payload,
while (1) {
ip_ext_len = 0;
- pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0);
+ pkt_size = recv(fd, buffer, sizeof(buffer), 0);
if (pkt_size < 0)
recv_error(fd, errno);
@@ -1183,9 +1222,10 @@ static void check_recv_pkts(int fd, int *correct_payload,
static void check_capacity_pkts(int fd)
{
- static char buffer[IP_MAXPACKET + ETH_HLEN + 1];
- struct iphdr *iph = (struct iphdr *)(buffer + ETH_HLEN);
- struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + ETH_HLEN);
+ static char buffer[IP_MAXPACKET + L2_HLEN_MAX + 1];
+ int nhoff = ETH_HLEN + (pppoe ? PPPOE_SES_HLEN : 0);
+ struct iphdr *iph = (struct iphdr *)(buffer + nhoff);
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)(buffer + nhoff);
int num_pkt = 0, num_coal = 0, pkt_idx;
const char *fail_reason = NULL;
int flow_order[num_flows * 2];
@@ -1203,7 +1243,7 @@ static void check_capacity_pkts(int fd)
while (1) {
ip_ext_len = 0;
- pkt_size = recv(fd, buffer, IP_MAXPACKET + ETH_HLEN + 1, 0);
+ pkt_size = recv(fd, buffer, sizeof(buffer), 0);
if (pkt_size < 0)
recv_error(fd, errno);
@@ -1499,6 +1539,12 @@ static void gro_sender(void)
usleep(fin_delay_us);
write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+ /* PPPoE sub-tests */
+ } else if (strcmp(testname, "pppoe_sid") == 0) {
+ send_changed_pppoe_sid(txfd, &daddr);
+ usleep(fin_delay_us);
+ write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
} else {
error(1, 0, "Unknown testcase: %s", testname);
}
@@ -1716,6 +1762,12 @@ static void gro_receiver(void)
} else if (strcmp(testname, "capacity") == 0) {
check_capacity_pkts(rxfd);
+ } else if (strcmp(testname, "pppoe_sid") == 0) {
+ correct_payload[0] = PAYLOAD_LEN;
+ correct_payload[1] = PAYLOAD_LEN;
+ printf("different PPPoE session ID doesn't coalesce: ");
+ check_recv_pkts(rxfd, correct_payload, 2);
+
} else {
error(1, 0, "Test case error: unknown testname %s", testname);
}
@@ -1734,6 +1786,8 @@ static void parse_args(int argc, char **argv)
{ "ipv6", no_argument, NULL, '6' },
{ "ipip", no_argument, NULL, 'e' },
{ "ip6ip6", no_argument, NULL, 'E' },
+ { "pppoev4", no_argument, NULL, 'p' },
+ { "pppoev6", no_argument, NULL, 'P' },
{ "num-flows", required_argument, NULL, 'n' },
{ "rx", no_argument, NULL, 'r' },
{ "saddr", required_argument, NULL, 's' },
@@ -1745,7 +1799,7 @@ static void parse_args(int argc, char **argv)
};
int c;
- while ((c = getopt_long(argc, argv, "46d:D:eEi:n:rs:S:t:ov", opts, NULL)) != -1) {
+ while ((c = getopt_long(argc, argv, "46d:D:eEi:n:pPrs:S:t:ov", opts, NULL)) != -1) {
switch (c) {
case '4':
proto = PF_INET;
@@ -1765,6 +1819,16 @@ static void parse_args(int argc, char **argv)
proto = PF_INET6;
ethhdr_proto = htons(ETH_P_IPV6);
break;
+ case 'p':
+ pppoe = true;
+ proto = PF_INET;
+ ethhdr_proto = htons(ETH_P_PPP_SES);
+ break;
+ case 'P':
+ pppoe = true;
+ proto = PF_INET6;
+ ethhdr_proto = htons(ETH_P_PPP_SES);
+ break;
case 'd':
addr4_dst = addr6_dst = optarg;
break;
@@ -1812,6 +1876,10 @@ int main(int argc, char **argv)
} else if (ip6ip6) {
tcp_offset = ETH_HLEN + sizeof(struct ipv6hdr) * 2;
total_hdr_len = tcp_offset + sizeof(struct tcphdr);
+ } else if (pppoe) {
+ tcp_offset = ETH_HLEN + PPPOE_SES_HLEN +
+ (proto == PF_INET ? sizeof(struct iphdr) : sizeof(struct ipv6hdr));
+ total_hdr_len = tcp_offset + sizeof(struct tcphdr);
} else if (proto == PF_INET) {
tcp_offset = ETH_HLEN + sizeof(struct iphdr);
total_hdr_len = tcp_offset + sizeof(struct tcphdr);
--
2.43.0
^ permalink raw reply related
* Re: [PATCH net-next] net: usb: r8152: add TRENDnet TUC-ET2G v2.0
From: Birger Koblitz @ 2026-05-01 4:03 UTC (permalink / raw)
To: Aleksander Jan Bajkowski, andrew+netdev, davem, edumazet, kuba,
pabeni, hayeswang, hsu.chih.kai, kees, linux-usb, netdev,
linux-kernel
Cc: Andrew Lunn
In-Reply-To: <20260430213435.21821-1-olek2@wp.pl>
On 30/04/2026 11:34 pm, Aleksander Jan Bajkowski wrote:
> The TRENDnet TUC-ET2G V2.0 is an RTL8156B based 2.5G Ethernet controller.
>
> Add the vendor and product ID values to the driver. This makes Ethernet
> work with the adapter.
>
> Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
> Reviewed-by: Andrew Lunn <andrew@lunn.ch>
> ---
> drivers/net/usb/r8152.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
> index 7337bf1b7d6a..1ace1d2398c9 100644
> --- a/drivers/net/usb/r8152.c
> +++ b/drivers/net/usb/r8152.c
> @@ -10138,6 +10138,7 @@ static const struct usb_device_id rtl8152_table[] = {
> { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) },
> + { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02c) },
>
You may also add my Reviewed-by: Birger Koblitz <mail@birger-koblitz.de>
Birger
^ permalink raw reply
* Re: [PATCH v3 net-next 0/4] net/sched: tc_dump_qdisc() optimizations
From: patchwork-bot+netdevbpf @ 2026-05-01 4:10 UTC (permalink / raw)
To: Eric Dumazet; +Cc: davem, kuba, pabeni, horms, jhs, jiri, netdev, eric.dumazet
In-Reply-To: <20260430023628.3216283-1-edumazet@google.com>
Hello:
This series was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:
On Thu, 30 Apr 2026 02:36:24 +0000 you wrote:
> Before converting tc_dump_qdisc() to RCU, we make the following changes:
>
> - Use for_each_netdev_dump() instead of for_each_netdev()
>
> - Only dump qdiscs of a single device at user space request.
>
> v2 and v3: addressed Jakub feedback (thanks!)
>
> [...]
Here is the summary with links:
- [v3,net-next,1/4] net/sched: propagate tc_fill_tclass() error
https://git.kernel.org/netdev/net-next/c/db6ac77b0433
- [v3,net-next,2/4] net/sched: tc_dump_qdisc_root() refactor
https://git.kernel.org/netdev/net-next/c/304427709ab8
- [v3,net-next,3/4] net/sched: switch tc_dump_qdisc() to for_each_netdev_dump()
https://git.kernel.org/netdev/net-next/c/748bbef5fc6a
- [v3,net-next,4/4] net/sched: speedup tc_dump_qdisc() when tcm_ifindex is provided
https://git.kernel.org/netdev/net-next/c/6f63b829632c
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* Re: [PATCH v2 net-next] selftests/net: packetdrill: add tcp_syncookies_ip[46]_9k
From: patchwork-bot+netdevbpf @ 2026-05-01 4:10 UTC (permalink / raw)
To: Eric Dumazet
Cc: davem, kuba, pabeni, horms, ncardwell, kuniyu, netdev,
eric.dumazet
In-Reply-To: <20260430021444.2929534-1-edumazet@google.com>
Hello:
This patch was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:
On Thu, 30 Apr 2026 02:14:44 +0000 you wrote:
> These tests check syncookie mode is able to reconstruct some
> client options when TCP TS are used:
>
> - wscale option.
> - sackOK.
> - MSS (in a limited way, especially for IPv4).
> - ECN : not enabled.
>
> [...]
Here is the summary with links:
- [v2,net-next] selftests/net: packetdrill: add tcp_syncookies_ip[46]_9k
https://git.kernel.org/netdev/net-next/c/bc6a9b667f9f
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* [PATCH net-next V2 0/7] net/mlx5: Improve representor lifecycle and allow switchdev by default
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
Hi,
Find detailed description by Mark below.
Regards,
Tariq
This series addresses three problems that have been present for years, and
fixes one representor reload error-unwind case exposed while making the
reload path reusable.
First, there is no coordination between E-Switch reconfiguration and
representor registration. The E-Switch can be mid-way through a mode
change or VF count update while mlx5_ib walks in and registers or
unregisters representors. Nothing stops them. The race window is small
and there is no field report, but it is clearly wrong.
Second, loading mlx5_ib while the device is already in switchdev mode
does not bring up the IB representors. mlx5_eswitch_register_vport_reps()
only stores callbacks; nobody triggers the actual load after registration.
Third, deployments that always use switchdev mode still need a manual
devlink mode change after probe. That makes automated provisioning more
fragile than needed.
The series fixes the registration race with a per-E-Switch representor
mutex. The lock is introduced first, then LAG shared-FDB and multiport
E-Switch transitions are adjusted so auxiliary device rescans and IB
representor reloads do not hold ldev->lock while taking the representor
lock. This keeps the intermediate commits bisectable before the stricter
E-Switch serialization and lock assertions are enabled.
After the LAG ordering is fixed, all E-Switch reconfiguration paths that
create, destroy, load, or unload representors take the representor mutex.
esw_mode_change() deliberately drops the mutex around
mlx5_rescan_drivers_locked(), because auxiliary probe and remove paths
re-enter mlx5_eswitch_register_vport_reps() and
mlx5_eswitch_unregister_vport_reps() on the same thread.
The shared-FDB peer IB registration path can hold one E-Switch
representor mutex and then register peer representor ops on another
E-Switch. The series annotates that case as nested locking so lockdep can
distinguish it from recursive locking on the same E-Switch.
For the missing IB representors, mlx5_eswitch_register_vport_reps() queues
a work item that acquires the devlink lock and loads all relevant
representors. This is the change that actually fixes the long-standing
bug.
The reload path also learns to track which representor types were loaded by
the current attempt, so an error does not unload representors that were
already active before the retry.
Patch 1 is cleanup. LAG and MPESW had the same representor reload
sequence duplicated in several places and the copies had started to
drift. This consolidates them into one helper.
Patch 2 adds the per-E-Switch representor lifecycle lock and helper APIs.
Patch 3 adjusts the LAG shared-FDB and multiport E-Switch transitions so
auxiliary device rescans and IB representor reloads run without
ldev->lock held while taking the representor lock.
Patch 4 protects the E-Switch reconfiguration, representor registration
and peer IB representor paths with the representor lock.
Patch 5 fixes representor load error unwind so only representor types
loaded by the current attempt are unloaded on failure.
Patch 6 moves the representor load triggered by
mlx5_eswitch_register_vport_reps() onto the work queue. This is the patch
that fixes IB representors not coming up when mlx5_ib is loaded while the
device is already in switchdev mode.
Patch 7 adds a driver profile that auto-enables switchdev at device init,
for deployments that always operate in switchdev mode and want to avoid a
manual devlink command after every probe.
V2:
Split v1 into two parts: the E-Switch workqueue deadlock fix and the
representor lifecycle changes. This is the second part; the first part
has already been accepted [1].
Patch 1: Add a cont_on_fail flag so callers can decide whether reload
should continue after a failure.
Patches 2, 3, 4: Replace the atomic-variable based scheme with a mutex,
per Jakub's feedback.
Patch 5: New patch that fixes the unwind on representor load failure.
Patch 7: Switch from profile 4 to profile 8. Since the profile mainly
targets E-Switch handling, keep it separate from the NIC profiles.
[1] https://lore.kernel.org/all/20260428051018.219093-1-tariqt@nvidia.com/
Link to V1:
https://lore.kernel.org/all/20260409115550.156419-1-tariqt@nvidia.com/
Mark Bloch (7):
net/mlx5: Lag: refactor representor reload handling
net/mlx5: E-Switch, add representor lifecycle lock
net/mlx5: Lag, avoid LAG and representor lock cycles
net/mlx5: E-Switch, serialize representor lifecycle
net/mlx5: E-Switch, unwind only newly loaded representor types
net/mlx5: E-switch, load reps via work queue after registration
net/mlx5: Add profile to auto-enable switchdev mode at device init
drivers/infiniband/hw/mlx5/ib_rep.c | 6 +-
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 10 +
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 12 ++
.../mellanox/mlx5/core/eswitch_offloads.c | 186 ++++++++++++++++--
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 171 ++++++++++++----
.../net/ethernet/mellanox/mlx5/core/lag/lag.h | 5 +
.../ethernet/mellanox/mlx5/core/lag/mpesw.c | 18 +-
.../ethernet/mellanox/mlx5/core/lib/devcom.c | 8 +
.../ethernet/mellanox/mlx5/core/lib/devcom.h | 1 +
.../net/ethernet/mellanox/mlx5/core/main.c | 43 +++-
.../ethernet/mellanox/mlx5/core/sf/devlink.c | 5 +
include/linux/mlx5/driver.h | 2 +
include/linux/mlx5/eswitch.h | 6 +
13 files changed, 405 insertions(+), 68 deletions(-)
base-commit: 4e37987362bcac8909f2d4b4458f3aa645e41641
--
2.44.0
^ permalink raw reply
* [PATCH net-next V2 2/7] net/mlx5: E-Switch, add representor lifecycle lock
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
Add a per-E-Switch mutex for serializing representor lifecycle work and
provide small helpers for taking and dropping it. Initialize and destroy
the mutex with the E-Switch offloads state.
Add the lock and helper API first. Follow-up patches will take the lock in
the individual representor lifecycle components. This keeps the functional
changes split by component and leaves this patch without intended behavior
change, making the series easier to review and bisectable.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eswitch.h | 6 ++++++
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 12 ++++++++++++
2 files changed, 18 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2fd601bd102f..3858690e09b4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -316,6 +316,7 @@ struct mlx5_esw_offload {
DECLARE_HASHTABLE(termtbl_tbl, 8);
struct mutex termtbl_mutex; /* protects termtbl hash */
struct xarray vhca_map;
+ struct mutex reps_lock; /* protects representor load/unload/register */
const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES];
u8 inline_mode;
atomic64_t num_flows;
@@ -951,6 +952,8 @@ mlx5_esw_lag_demux_fg_create(struct mlx5_eswitch *esw,
struct mlx5_flow_handle *
mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num,
struct mlx5_flow_table *lag_ft);
+void mlx5_esw_reps_block(struct mlx5_eswitch *esw);
+void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw);
#else /* CONFIG_MLX5_ESWITCH */
/* eswitch API stubs */
static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -1028,6 +1031,9 @@ mlx5_esw_host_functions_enabled(const struct mlx5_core_dev *dev)
return true;
}
+static inline void mlx5_esw_reps_block(struct mlx5_eswitch *esw) {}
+static inline void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw) {}
+
static inline bool
mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 69ddf56e2fc9..6a5143b63dfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2413,6 +2413,16 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw)
return err;
}
+void mlx5_esw_reps_block(struct mlx5_eswitch *esw)
+{
+ mutex_lock(&esw->offloads.reps_lock);
+}
+
+void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw)
+{
+ mutex_unlock(&esw->offloads.reps_lock);
+}
+
static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode)
{
mlx5_devcom_comp_lock(esw->dev->priv.hca_devcom_comp);
@@ -2645,6 +2655,7 @@ static void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
mlx5_esw_for_each_rep(esw, i, rep)
mlx5_esw_offloads_rep_cleanup(esw, rep);
xa_destroy(&esw->offloads.vport_reps);
+ mutex_destroy(&esw->offloads.reps_lock);
}
static int esw_offloads_init_reps(struct mlx5_eswitch *esw)
@@ -2654,6 +2665,7 @@ static int esw_offloads_init_reps(struct mlx5_eswitch *esw)
int err;
xa_init(&esw->offloads.vport_reps);
+ mutex_init(&esw->offloads.reps_lock);
mlx5_esw_for_each_vport(esw, i, vport) {
err = mlx5_esw_offloads_rep_add(esw, vport);
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 1/7] net/mlx5: Lag: refactor representor reload handling
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
Representor reload during LAG/MPESW transitions has to be repeated in
several flows, and each open‑coded loop was easy to get out of sync
when adding new flags or tweaking error handling. Move the sequencing
into a single helper so that all call sites share the same ordering
and checks
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 45 +++++++++++--------
.../net/ethernet/mellanox/mlx5/core/lag/lag.h | 2 +
.../ethernet/mellanox/mlx5/core/lag/mpesw.c | 12 ++---
3 files changed, 33 insertions(+), 26 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 449e4bd86c06..a474f970e056 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1093,6 +1093,27 @@ void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
}
}
+int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags, bool cont_on_fail)
+{
+ struct lag_func *pf;
+ int ret;
+ int i;
+
+ mlx5_ldev_for_each(i, 0, ldev) {
+ pf = mlx5_lag_pf(ldev, i);
+ if (!(pf->dev->priv.flags & flags)) {
+ struct mlx5_eswitch *esw;
+
+ esw = pf->dev->priv.eswitch;
+ ret = mlx5_eswitch_reload_ib_reps(esw);
+ if (ret && !cont_on_fail)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
void mlx5_disable_lag(struct mlx5_lag *ldev)
{
bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
@@ -1130,9 +1151,8 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
mlx5_lag_add_devices(ldev);
if (shared_fdb)
- mlx5_ldev_for_each(i, 0, ldev)
- if (!(mlx5_lag_pf(ldev, i)->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV))
- mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
+ mlx5_lag_reload_ib_reps(ldev, MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV,
+ true);
}
bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
@@ -1388,10 +1408,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
if (err) {
if (shared_fdb || roce_lag)
mlx5_lag_add_devices(ldev);
- if (shared_fdb) {
- mlx5_ldev_for_each(i, 0, ldev)
- mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
- }
+ if (shared_fdb)
+ mlx5_lag_reload_ib_reps(ldev, 0, true);
return;
}
@@ -1409,24 +1427,15 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
mlx5_nic_vport_enable_roce(dev);
}
} else if (shared_fdb) {
- int i;
-
dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
mlx5_rescan_drivers_locked(dev0);
-
- mlx5_ldev_for_each(i, 0, ldev) {
- err = mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
- if (err)
- break;
- }
-
+ err = mlx5_lag_reload_ib_reps(ldev, 0, false);
if (err) {
dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
mlx5_rescan_drivers_locked(dev0);
mlx5_deactivate_lag(ldev);
mlx5_lag_add_devices(ldev);
- mlx5_ldev_for_each(i, 0, ldev)
- mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
+ mlx5_lag_reload_ib_reps(ldev, 0, true);
mlx5_core_err(dev0, "Failed to enable lag\n");
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 6c911374f409..daca8ebd5256 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -199,4 +199,6 @@ int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx);
int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq);
int mlx5_lag_num_devs(struct mlx5_lag *ldev);
int mlx5_lag_num_netdevs(struct mlx5_lag *ldev);
+int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags,
+ bool cont_on_fail);
#endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index 5eea12a6887a..edcd06f3be7a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -70,7 +70,6 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
struct mlx5_core_dev *dev0;
int err;
- int i;
if (ldev->mode == MLX5_LAG_MODE_MPESW)
return 0;
@@ -103,11 +102,9 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
mlx5_rescan_drivers_locked(dev0);
- mlx5_ldev_for_each(i, 0, ldev) {
- err = mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
- if (err)
- goto err_rescan_drivers;
- }
+ err = mlx5_lag_reload_ib_reps(ldev, 0, false);
+ if (err)
+ goto err_rescan_drivers;
mlx5_lag_set_vports_agg_speed(ldev);
@@ -119,8 +116,7 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
mlx5_deactivate_lag(ldev);
err_add_devices:
mlx5_lag_add_devices(ldev);
- mlx5_ldev_for_each(i, 0, ldev)
- mlx5_eswitch_reload_ib_reps(mlx5_lag_pf(ldev, i)->dev->priv.eswitch);
+ mlx5_lag_reload_ib_reps(ldev, 0, true);
mlx5_mpesw_metadata_cleanup(ldev);
return err;
}
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 3/7] net/mlx5: Lag, avoid LAG and representor lock cycles
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
The LAG shared-FDB and multiport E-Switch transitions rescan auxiliary
devices and reload IB representors while holding ldev->lock. Driver
bind/unbind paths may register or unregister E-Switch representor ops, and
representor load paths may enter LAG code, so holding ldev->lock across
those calls creates lock-order cycles with the E-Switch representor lock.
Keep the devcom component locked for the transition, but drop ldev->lock
before rescanning auxiliary devices or reloading IB representors. Mark the
LAG transition as in progress while the lock is dropped and assert the
devcom lock where the helper relies on it. This preserves LAG serialization
while avoiding ldev->lock nesting under E-Switch representor registration.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/lag/lag.c | 142 ++++++++++++++----
.../net/ethernet/mellanox/mlx5/core/lag/lag.h | 7 +-
.../ethernet/mellanox/mlx5/core/lag/mpesw.c | 10 +-
.../ethernet/mellanox/mlx5/core/lib/devcom.c | 8 +
.../ethernet/mellanox/mlx5/core/lib/devcom.h | 1 +
5 files changed, 134 insertions(+), 34 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index a474f970e056..e77f9931c39c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1063,37 +1063,99 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
return true;
}
-void mlx5_lag_add_devices(struct mlx5_lag *ldev)
+static void mlx5_lag_assert_locked_transition(struct mlx5_lag *ldev)
{
+ struct mlx5_devcom_comp_dev *devcom = NULL;
struct lag_func *pf;
int i;
- mlx5_ldev_for_each(i, 0, ldev) {
- pf = mlx5_lag_pf(ldev, i);
- if (pf->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
- continue;
+ lockdep_assert_held(&ldev->lock);
- pf->dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(pf->dev);
+ i = mlx5_get_next_ldev_func(ldev, 0);
+ if (i < MLX5_MAX_PORTS) {
+ pf = mlx5_lag_pf(ldev, i);
+ devcom = pf->dev->priv.hca_devcom_comp;
}
+ mlx5_devcom_comp_assert_locked(devcom);
}
-void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
+static void mlx5_lag_drop_lock_for_reps(struct mlx5_lag *ldev)
+{
+ mlx5_lag_assert_locked_transition(ldev);
+
+ /* Keep PF membership stable while ldev->lock is dropped. Device add
+ * and remove paths observe mode_changes_in_progress and retry.
+ */
+ ldev->mode_changes_in_progress++;
+ mutex_unlock(&ldev->lock);
+}
+
+static void mlx5_lag_retake_lock_after_reps(struct mlx5_lag *ldev)
{
+ mutex_lock(&ldev->lock);
+ ldev->mode_changes_in_progress--;
+}
+
+void mlx5_lag_rescan_dev_locked(struct mlx5_lag *ldev,
+ struct mlx5_core_dev *dev,
+ bool enable)
+{
+ if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
+ return;
+
+ if (enable)
+ dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+ else
+ dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+
+ /* Auxiliary bus probe/remove can register or unregister representor
+ * callbacks and take reps_lock. Drop ldev->lock so the only ordering
+ * remains reps_lock -> ldev->lock from representor callbacks.
+ */
+ mlx5_lag_drop_lock_for_reps(ldev);
+ mlx5_rescan_drivers_locked(dev);
+ mlx5_lag_retake_lock_after_reps(ldev);
+}
+
+static void mlx5_lag_rescan_devices_locked(struct mlx5_lag *ldev, bool enable)
+{
+ struct mlx5_core_dev *devs[MLX5_MAX_PORTS];
struct lag_func *pf;
+ int num_devs = 0;
int i;
+ mlx5_lag_assert_locked_transition(ldev);
+
mlx5_ldev_for_each(i, 0, ldev) {
pf = mlx5_lag_pf(ldev, i);
if (pf->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)
continue;
- pf->dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(pf->dev);
+ if (enable)
+ pf->dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+ else
+ pf->dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+ devs[num_devs++] = pf->dev;
}
+
+ mlx5_lag_drop_lock_for_reps(ldev);
+ for (i = 0; i < num_devs; i++)
+ mlx5_rescan_drivers_locked(devs[i]);
+ mlx5_lag_retake_lock_after_reps(ldev);
}
-int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags, bool cont_on_fail)
+void mlx5_lag_add_devices(struct mlx5_lag *ldev)
+{
+ mlx5_lag_rescan_devices_locked(ldev, true);
+}
+
+void mlx5_lag_remove_devices(struct mlx5_lag *ldev)
+{
+ mlx5_lag_rescan_devices_locked(ldev, false);
+}
+
+static int mlx5_lag_reload_ib_reps_unlocked(struct mlx5_lag *ldev, u32 flags,
+ bool cont_on_fail)
{
struct lag_func *pf;
int ret;
@@ -1105,7 +1167,9 @@ int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags, bool cont_on_fail)
struct mlx5_eswitch *esw;
esw = pf->dev->priv.eswitch;
+ mlx5_esw_reps_block(esw);
ret = mlx5_eswitch_reload_ib_reps(esw);
+ mlx5_esw_reps_unblock(esw);
if (ret && !cont_on_fail)
return ret;
}
@@ -1114,6 +1178,34 @@ int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags, bool cont_on_fail)
return 0;
}
+static int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags,
+ bool cont_on_fail)
+{
+ int ret;
+
+ /* The HCA devcom component lock serializes LAG mode transitions while
+ * ldev->lock is dropped here. Dropping ldev->lock is required because
+ * the reload takes the per-E-Switch reps_lock, and representor
+ * load/unload callbacks can re-enter LAG netdev add/remove and take
+ * ldev->lock. Keep the ordering reps_lock -> ldev->lock.
+ */
+ mlx5_lag_drop_lock_for_reps(ldev);
+ ret = mlx5_lag_reload_ib_reps_unlocked(ldev, flags, cont_on_fail);
+ mlx5_lag_retake_lock_after_reps(ldev);
+
+ return ret;
+}
+
+int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags,
+ bool cont_on_fail)
+{
+ int ret;
+
+ ret = mlx5_lag_reload_ib_reps(ldev, flags, cont_on_fail);
+
+ return ret;
+}
+
void mlx5_disable_lag(struct mlx5_lag *ldev)
{
bool shared_fdb = test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
@@ -1132,10 +1224,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
if (shared_fdb) {
mlx5_lag_remove_devices(ldev);
} else if (roce_lag) {
- if (!(dev0->priv.flags & MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV)) {
- dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
- }
+ mlx5_lag_rescan_dev_locked(ldev, dev0, false);
mlx5_ldev_for_each(i, 0, ldev) {
if (i == idx)
continue;
@@ -1151,8 +1240,9 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
mlx5_lag_add_devices(ldev);
if (shared_fdb)
- mlx5_lag_reload_ib_reps(ldev, MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV,
- true);
+ mlx5_lag_reload_ib_reps_from_locked(ldev,
+ MLX5_PRIV_FLAGS_DISABLE_ALL_ADEV,
+ true);
}
bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
@@ -1409,7 +1499,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
if (shared_fdb || roce_lag)
mlx5_lag_add_devices(ldev);
if (shared_fdb)
- mlx5_lag_reload_ib_reps(ldev, 0, true);
+ mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
+ true);
return;
}
@@ -1417,8 +1508,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
if (roce_lag) {
struct mlx5_core_dev *dev;
- dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
+ mlx5_lag_rescan_dev_locked(ldev, dev0, true);
mlx5_ldev_for_each(i, 0, ldev) {
if (i == idx)
continue;
@@ -1427,15 +1517,15 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
mlx5_nic_vport_enable_roce(dev);
}
} else if (shared_fdb) {
- dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
- err = mlx5_lag_reload_ib_reps(ldev, 0, false);
+ mlx5_lag_rescan_dev_locked(ldev, dev0, true);
+ err = mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
+ false);
if (err) {
- dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
+ mlx5_lag_rescan_dev_locked(ldev, dev0, false);
mlx5_deactivate_lag(ldev);
mlx5_lag_add_devices(ldev);
- mlx5_lag_reload_ib_reps(ldev, 0, true);
+ mlx5_lag_reload_ib_reps_from_locked(ldev, 0,
+ true);
mlx5_core_err(dev0, "Failed to enable lag\n");
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index daca8ebd5256..6afe7707d076 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -164,6 +164,9 @@ void mlx5_disable_lag(struct mlx5_lag *ldev);
void mlx5_lag_remove_devices(struct mlx5_lag *ldev);
int mlx5_deactivate_lag(struct mlx5_lag *ldev);
void mlx5_lag_add_devices(struct mlx5_lag *ldev);
+void mlx5_lag_rescan_dev_locked(struct mlx5_lag *ldev,
+ struct mlx5_core_dev *dev,
+ bool enable);
struct mlx5_devcom_comp_dev *mlx5_lag_get_devcom_comp(struct mlx5_lag *ldev);
#ifdef CONFIG_MLX5_ESWITCH
@@ -199,6 +202,6 @@ int mlx5_get_next_ldev_func(struct mlx5_lag *ldev, int start_idx);
int mlx5_lag_get_dev_index_by_seq(struct mlx5_lag *ldev, int seq);
int mlx5_lag_num_devs(struct mlx5_lag *ldev);
int mlx5_lag_num_netdevs(struct mlx5_lag *ldev);
-int mlx5_lag_reload_ib_reps(struct mlx5_lag *ldev, u32 flags,
- bool cont_on_fail);
+int mlx5_lag_reload_ib_reps_from_locked(struct mlx5_lag *ldev, u32 flags,
+ bool cont_on_fail);
#endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index edcd06f3be7a..8a349f8fd823 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -100,9 +100,8 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
goto err_add_devices;
}
- dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
- err = mlx5_lag_reload_ib_reps(ldev, 0, false);
+ mlx5_lag_rescan_dev_locked(ldev, dev0, true);
+ err = mlx5_lag_reload_ib_reps_from_locked(ldev, 0, false);
if (err)
goto err_rescan_drivers;
@@ -111,12 +110,11 @@ static int mlx5_lag_enable_mpesw(struct mlx5_lag *ldev)
return 0;
err_rescan_drivers:
- dev0->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
- mlx5_rescan_drivers_locked(dev0);
+ mlx5_lag_rescan_dev_locked(ldev, dev0, false);
mlx5_deactivate_lag(ldev);
err_add_devices:
mlx5_lag_add_devices(ldev);
- mlx5_lag_reload_ib_reps(ldev, 0, true);
+ mlx5_lag_reload_ib_reps_from_locked(ldev, 0, true);
mlx5_mpesw_metadata_cleanup(ldev);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
index 4b5ac2db55ce..d40c53193ea8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -3,6 +3,7 @@
#include <linux/mlx5/vport.h>
#include <linux/list.h>
+#include <linux/lockdep.h>
#include "lib/devcom.h"
#include "lib/mlx5.h"
#include "mlx5_core.h"
@@ -438,3 +439,10 @@ int mlx5_devcom_comp_trylock(struct mlx5_devcom_comp_dev *devcom)
return 0;
return down_write_trylock(&devcom->comp->sem);
}
+
+void mlx5_devcom_comp_assert_locked(struct mlx5_devcom_comp_dev *devcom)
+{
+ if (!devcom)
+ return;
+ lockdep_assert_held_write(&devcom->comp->sem);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index 91e5ae529d5c..316052a85ca5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -75,5 +75,6 @@ void *mlx5_devcom_get_next_peer_data_rcu(struct mlx5_devcom_comp_dev *devcom,
void mlx5_devcom_comp_lock(struct mlx5_devcom_comp_dev *devcom);
void mlx5_devcom_comp_unlock(struct mlx5_devcom_comp_dev *devcom);
int mlx5_devcom_comp_trylock(struct mlx5_devcom_comp_dev *devcom);
+void mlx5_devcom_comp_assert_locked(struct mlx5_devcom_comp_dev *devcom);
#endif /* __LIB_MLX5_DEVCOM_H__ */
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 5/7] net/mlx5: E-Switch, unwind only newly loaded representor types
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
__esw_offloads_load_rep() may return success without invoking the
representor load callback when the representor type is already loaded.
On a later load failure, mlx5_esw_offloads_rep_load() unconditionally
unloaded all previously iterated representor types. This could unload
representor types that were already loaded before this load attempt.
Track which representor types were actually loaded by the current call and
unwind only those on error. Also restore the representor state back to
REP_REGISTERED when the load callback itself fails.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 38 ++++++++++++++-----
1 file changed, 29 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index d4ac07c995b9..8f656253981b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2786,13 +2786,28 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
}
static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
- struct mlx5_eswitch_rep *rep, u8 rep_type)
+ struct mlx5_eswitch_rep *rep,
+ u8 rep_type, bool *newly_loaded)
{
+ int err;
+
mlx5_esw_assert_reps_locked(esw);
+ if (newly_loaded)
+ *newly_loaded = false;
+
if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
- REP_REGISTERED, REP_LOADED) == REP_REGISTERED)
- return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+ REP_REGISTERED, REP_LOADED) != REP_REGISTERED)
+ return 0;
+
+ err = esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
+ if (err) {
+ atomic_set(&rep->rep_data[rep_type].state, REP_REGISTERED);
+ return err;
+ }
+
+ if (newly_loaded)
+ *newly_loaded = true;
return 0;
}
@@ -2822,22 +2837,27 @@ static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
static int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num)
{
struct mlx5_eswitch_rep *rep;
+ unsigned long loaded = 0;
+ bool newly_loaded;
int rep_type;
int err;
rep = mlx5_eswitch_get_rep(esw, vport_num);
for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
- err = __esw_offloads_load_rep(esw, rep, rep_type);
+ err = __esw_offloads_load_rep(esw, rep, rep_type,
+ &newly_loaded);
if (err)
goto err_reps;
+ if (newly_loaded)
+ loaded |= BIT(rep_type);
}
return 0;
err_reps:
- atomic_set(&rep->rep_data[rep_type].state, REP_REGISTERED);
- for (--rep_type; rep_type >= 0; rep_type--)
- __esw_offloads_unload_rep(esw, rep, rep_type);
+ while (--rep_type >= 0)
+ if (test_bit(rep_type, &loaded))
+ __esw_offloads_unload_rep(esw, rep, rep_type);
return err;
}
@@ -3591,13 +3611,13 @@ int mlx5_eswitch_reload_ib_reps(struct mlx5_eswitch *esw)
if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
return 0;
- ret = __esw_offloads_load_rep(esw, rep, REP_IB);
+ ret = __esw_offloads_load_rep(esw, rep, REP_IB, NULL);
if (ret)
return ret;
mlx5_esw_for_each_rep(esw, i, rep) {
if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
- __esw_offloads_load_rep(esw, rep, REP_IB);
+ __esw_offloads_load_rep(esw, rep, REP_IB, NULL);
}
return 0;
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 4/7] net/mlx5: E-Switch, serialize representor lifecycle
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
Representor callbacks can be registered and unregistered while the
E-Switch is already in switchdev mode, and the same E-Switch may also be
reconfigured by devlink, VF changes and SF changes. Serialize these paths
with the per-E-Switch representor mutex instead of relying on ad-hoc bit
state and wait queues.
Take the representor lock around the mode transition, VF/SF representor
changes and representor ops registration. Keep mode_lock and the
representor lock unnested by using the operation flag while the mode lock
is dropped. During mode changes, drop the representor lock around the
auxiliary bus rescan because driver bind/unbind may register or unregister
representor ops.
Split representor ops registration into locked public wrappers and blocked
internal helpers, clear the ops pointer on unregister, and add nested
wrappers for the shared-FDB master IB path that registers peer
representor ops while another E-Switch representor lock is already held.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
drivers/infiniband/hw/mlx5/ib_rep.c | 6 +-
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 10 ++
.../mellanox/mlx5/core/eswitch_offloads.c | 102 ++++++++++++++++--
.../ethernet/mellanox/mlx5/core/sf/devlink.c | 5 +
include/linux/mlx5/eswitch.h | 6 ++
5 files changed, 119 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 1709b628702e..65d8767d1830 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -262,9 +262,10 @@ mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
struct mlx5_core_dev *peer_mdev;
struct mlx5_eswitch *esw;
+ /* Called while the master E-Switch reps_lock is held. */
mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
esw = peer_mdev->priv.eswitch;
- mlx5_eswitch_unregister_vport_reps(esw, REP_IB);
+ mlx5_eswitch_unregister_vport_reps_nested(esw, REP_IB);
}
mlx5_ib_release_transport(mdev);
}
@@ -284,9 +285,10 @@ static void mlx5_ib_register_peer_vport_reps(struct mlx5_core_dev *mdev)
struct mlx5_eswitch *esw;
int i;
+ /* Called while the master E-Switch reps_lock is held. */
mlx5_lag_for_each_peer_mdev(mdev, peer_mdev, i) {
esw = peer_mdev->priv.eswitch;
- mlx5_eswitch_register_vport_reps(esw, &rep_ops, REP_IB);
+ mlx5_eswitch_register_vport_reps_nested(esw, &rep_ops, REP_IB);
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 66a773a99876..f70737437954 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1712,6 +1712,7 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
mlx5_lag_disable_change(esw->dev);
mlx5_eswitch_invalidate_wq(esw);
+ mlx5_esw_reps_block(esw);
if (!mlx5_esw_is_fdb_created(esw)) {
ret = mlx5_eswitch_enable_locked(esw, num_vfs);
@@ -1735,6 +1736,8 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs)
}
}
+ mlx5_esw_reps_unblock(esw);
+
if (toggle_lag)
mlx5_lag_enable_change(esw->dev);
@@ -1759,6 +1762,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
esw->esw_funcs.num_vfs, esw->esw_funcs.num_ec_vfs, esw->enabled_vports);
mlx5_eswitch_invalidate_wq(esw);
+ mlx5_esw_reps_block(esw);
if (!mlx5_core_is_ecpf(esw->dev)) {
mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
@@ -1770,6 +1774,8 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf)
mlx5_eswitch_clear_ec_vf_vports_info(esw);
}
+ mlx5_esw_reps_unblock(esw);
+
if (esw->mode == MLX5_ESWITCH_OFFLOADS) {
struct devlink *devlink = priv_to_devlink(esw->dev);
@@ -1825,7 +1831,11 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
devl_assert_locked(priv_to_devlink(esw->dev));
mlx5_lag_disable_change(esw->dev);
+
+ mlx5_esw_reps_block(esw);
mlx5_eswitch_disable_locked(esw);
+ mlx5_esw_reps_unblock(esw);
+
esw->mode = MLX5_ESWITCH_LEGACY;
mlx5_lag_enable_change(esw->dev);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6a5143b63dfd..d4ac07c995b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -36,6 +36,7 @@
#include <linux/mlx5/mlx5_ifc.h>
#include <linux/mlx5/vport.h>
#include <linux/mlx5/fs.h>
+#include <linux/lockdep.h>
#include "mlx5_core.h"
#include "eswitch.h"
#include "esw/indir_table.h"
@@ -2413,11 +2414,21 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw)
return err;
}
+static void mlx5_esw_assert_reps_locked(struct mlx5_eswitch *esw)
+{
+ lockdep_assert_held(&esw->offloads.reps_lock);
+}
+
void mlx5_esw_reps_block(struct mlx5_eswitch *esw)
{
mutex_lock(&esw->offloads.reps_lock);
}
+static void mlx5_esw_reps_block_nested(struct mlx5_eswitch *esw)
+{
+ mutex_lock_nested(&esw->offloads.reps_lock, SINGLE_DEPTH_NESTING);
+}
+
void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw)
{
mutex_unlock(&esw->offloads.reps_lock);
@@ -2425,21 +2436,22 @@ void mlx5_esw_reps_unblock(struct mlx5_eswitch *esw)
static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode)
{
+ mlx5_esw_reps_unblock(esw);
mlx5_devcom_comp_lock(esw->dev->priv.hca_devcom_comp);
if (esw->dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV ||
mlx5_core_mp_enabled(esw->dev)) {
esw->mode = mode;
- mlx5_rescan_drivers_locked(esw->dev);
- mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
- return;
+ goto out;
}
esw->dev->priv.flags |= MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
mlx5_rescan_drivers_locked(esw->dev);
esw->mode = mode;
esw->dev->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV;
+out:
mlx5_rescan_drivers_locked(esw->dev);
mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp);
+ mlx5_esw_reps_block(esw);
}
static void mlx5_esw_fdb_drop_destroy(struct mlx5_eswitch *esw)
@@ -2776,6 +2788,8 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw)
static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep, u8 rep_type)
{
+ mlx5_esw_assert_reps_locked(esw);
+
if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
REP_REGISTERED, REP_LOADED) == REP_REGISTERED)
return esw->offloads.rep_ops[rep_type]->load(esw->dev, rep);
@@ -2786,6 +2800,8 @@ static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
struct mlx5_eswitch_rep *rep, u8 rep_type)
{
+ mlx5_esw_assert_reps_locked(esw);
+
if (atomic_cmpxchg(&rep->rep_data[rep_type].state,
REP_LOADED, REP_REGISTERED) == REP_LOADED) {
if (rep_type == REP_ETH)
@@ -3691,6 +3707,7 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled)
goto free;
+ mlx5_esw_reps_block(esw);
/* Number of VFs can only change from "0 to x" or "x to 0". */
if (esw->esw_funcs.num_vfs > 0) {
mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
@@ -3700,9 +3717,11 @@ static void esw_vfs_changed_event_handler(struct mlx5_eswitch *esw)
err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs,
MLX5_VPORT_UC_ADDR_CHANGE);
if (err)
- goto free;
+ goto unblock;
}
esw->esw_funcs.num_vfs = new_num_vfs;
+unblock:
+ mlx5_esw_reps_unblock(esw);
free:
kvfree(out);
}
@@ -4188,9 +4207,14 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
goto unlock;
}
+ /* Keep mode_lock and reps_lock unnested. The operation flag excludes
+ * mode users while mode_lock is dropped before taking reps_lock.
+ */
esw->eswitch_operation_in_progress = true;
up_write(&esw->mode_lock);
+ mlx5_esw_reps_block(esw);
+
if (mlx5_mode == MLX5_ESWITCH_OFFLOADS &&
!mlx5_devlink_netdev_netns_immutable_set(devlink, true)) {
NL_SET_ERR_MSG_MOD(extack,
@@ -4223,6 +4247,10 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
skip:
if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && err)
mlx5_devlink_netdev_netns_immutable_set(devlink, false);
+ /* Reconfiguration is done; drop reps_lock before taking mode_lock again
+ * to clear the operation flag.
+ */
+ mlx5_esw_reps_unblock(esw);
down_write(&esw->mode_lock);
esw->eswitch_operation_in_progress = false;
unlock:
@@ -4496,9 +4524,10 @@ mlx5_eswitch_vport_has_rep(const struct mlx5_eswitch *esw, u16 vport_num)
return true;
}
-void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
- const struct mlx5_eswitch_rep_ops *ops,
- u8 rep_type)
+static void
+mlx5_eswitch_register_vport_reps_blocked(struct mlx5_eswitch *esw,
+ const struct mlx5_eswitch_rep_ops *ops,
+ u8 rep_type)
{
struct mlx5_eswitch_rep_data *rep_data;
struct mlx5_eswitch_rep *rep;
@@ -4513,9 +4542,40 @@ void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
}
}
}
+
+static void
+mlx5_eswitch_register_vport_reps_locked(struct mlx5_eswitch *esw,
+ const struct mlx5_eswitch_rep_ops *ops,
+ u8 rep_type, bool nested)
+{
+ if (nested)
+ mlx5_esw_reps_block_nested(esw);
+ else
+ mlx5_esw_reps_block(esw);
+ mlx5_eswitch_register_vport_reps_blocked(esw, ops, rep_type);
+ mlx5_esw_reps_unblock(esw);
+}
+
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+ const struct mlx5_eswitch_rep_ops *ops,
+ u8 rep_type)
+{
+ mlx5_eswitch_register_vport_reps_locked(esw, ops, rep_type, false);
+}
EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
-void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
+void
+mlx5_eswitch_register_vport_reps_nested(struct mlx5_eswitch *esw,
+ const struct mlx5_eswitch_rep_ops *ops,
+ u8 rep_type)
+{
+ mlx5_eswitch_register_vport_reps_locked(esw, ops, rep_type, true);
+}
+EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps_nested);
+
+static void
+mlx5_eswitch_unregister_vport_reps_blocked(struct mlx5_eswitch *esw,
+ u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
unsigned long i;
@@ -4525,9 +4585,35 @@ void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
mlx5_esw_for_each_rep(esw, i, rep)
atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
+
+ esw->offloads.rep_ops[rep_type] = NULL;
+}
+
+static void
+mlx5_eswitch_unregister_vport_reps_locked(struct mlx5_eswitch *esw,
+ u8 rep_type, bool nested)
+{
+ if (nested)
+ mlx5_esw_reps_block_nested(esw);
+ else
+ mlx5_esw_reps_block(esw);
+ mlx5_eswitch_unregister_vport_reps_blocked(esw, rep_type);
+ mlx5_esw_reps_unblock(esw);
+}
+
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
+{
+ mlx5_eswitch_unregister_vport_reps_locked(esw, rep_type, false);
}
EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
+void mlx5_eswitch_unregister_vport_reps_nested(struct mlx5_eswitch *esw,
+ u8 rep_type)
+{
+ mlx5_eswitch_unregister_vport_reps_locked(esw, rep_type, true);
+}
+EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps_nested);
+
void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
{
struct mlx5_eswitch_rep *rep;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 8503e532f423..2fc69897e35b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -245,8 +245,10 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
if (IS_ERR(sf))
return PTR_ERR(sf);
+ mlx5_esw_reps_block(esw);
err = mlx5_eswitch_load_sf_vport(esw, sf->hw_fn_id, MLX5_VPORT_UC_ADDR_CHANGE,
&sf->dl_port, new_attr->controller, new_attr->sfnum);
+ mlx5_esw_reps_unblock(esw);
if (err)
goto esw_err;
*dl_port = &sf->dl_port.dl_port;
@@ -367,7 +369,10 @@ int mlx5_devlink_sf_port_del(struct devlink *devlink,
struct mlx5_sf_table *table = dev->priv.sf_table;
struct mlx5_sf *sf = mlx5_sf_by_dl_port(dl_port);
+ mlx5_esw_reps_block(dev->priv.eswitch);
mlx5_sf_del(table, sf);
+ mlx5_esw_reps_unblock(dev->priv.eswitch);
+
return 0;
}
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 3b29a3c6794d..a0dd162baa78 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -63,7 +63,13 @@ struct mlx5_eswitch_rep {
void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
const struct mlx5_eswitch_rep_ops *ops,
u8 rep_type);
+void
+mlx5_eswitch_register_vport_reps_nested(struct mlx5_eswitch *esw,
+ const struct mlx5_eswitch_rep_ops *ops,
+ u8 rep_type);
void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type);
+void mlx5_eswitch_unregister_vport_reps_nested(struct mlx5_eswitch *esw,
+ u8 rep_type);
void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
u16 vport_num,
u8 rep_type);
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 6/7] net/mlx5: E-switch, load reps via work queue after registration
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
mlx5_eswitch_register_vport_reps() only installs representor callbacks and
marks the rep type as registered. If the E-Switch is already in switchdev
mode, the newly registered rep type must then be loaded for already enabled
vports.
That load path needs to run under the devlink lock, which is not held by
the auxiliary driver registration context. Queue the reload to the E-Switch
workqueue, whose handler acquires the devlink lock, and load the relevant
representors from there.
The unregister path is unchanged and still unloads representors
synchronously while tearing down the registered callbacks.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../mellanox/mlx5/core/eswitch_offloads.c | 34 +++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8f656253981b..f26d1652dd05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4563,6 +4563,38 @@ mlx5_eswitch_register_vport_reps_blocked(struct mlx5_eswitch *esw,
}
}
+static void mlx5_eswitch_reload_reps_blocked(struct mlx5_eswitch *esw)
+{
+ struct mlx5_vport *vport;
+ unsigned long i;
+
+ if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+ return;
+
+ if (mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK))
+ return;
+
+ mlx5_esw_for_each_vport(esw, i, vport) {
+ if (!vport)
+ continue;
+ if (!vport->enabled)
+ continue;
+ if (vport->vport == MLX5_VPORT_UPLINK)
+ continue;
+ if (!mlx5_eswitch_vport_has_rep(esw, vport->vport))
+ continue;
+
+ mlx5_esw_offloads_rep_load(esw, vport->vport);
+ }
+}
+
+static void mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+{
+ mlx5_esw_reps_block(esw);
+ mlx5_eswitch_reload_reps_blocked(esw);
+ mlx5_esw_reps_unblock(esw);
+}
+
static void
mlx5_eswitch_register_vport_reps_locked(struct mlx5_eswitch *esw,
const struct mlx5_eswitch_rep_ops *ops,
@@ -4574,6 +4606,8 @@ mlx5_eswitch_register_vport_reps_locked(struct mlx5_eswitch *esw,
mlx5_esw_reps_block(esw);
mlx5_eswitch_register_vport_reps_blocked(esw, ops, rep_type);
mlx5_esw_reps_unblock(esw);
+
+ mlx5_esw_add_work(esw, mlx5_eswitch_reload_reps);
}
void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
--
2.44.0
^ permalink raw reply related
* [PATCH net-next V2 7/7] net/mlx5: Add profile to auto-enable switchdev mode at device init
From: Tariq Toukan @ 2026-05-01 4:16 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Leon Romanovsky, Jason Gunthorpe, Saeed Mahameed, Tariq Toukan,
Mark Bloch, Shay Drory, Or Har-Toov, Edward Srouji, Maher Sanalla,
Simon Horman, Gerd Bayer, Moshe Shemesh, Kees Cook,
Patrisious Haddad, Parav Pandit, Carolina Jubran, Cosmin Ratiu,
linux-rdma, linux-kernel, netdev, Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501041633.231662-1-tariqt@nvidia.com>
From: Mark Bloch <mbloch@nvidia.com>
Deployments that always operate in switchdev mode currently require
manual devlink configuration after driver probe, which complicates
automated provisioning.
Introduce MLX5_PROF_MASK_DEF_SWITCHDEV, a new profile mask bit, and
profile index 8. When a device is initialized or reloaded with this
profile, the driver automatically switches the e-switch to switchdev
mode by calling mlx5_devlink_eswitch_mode_set() immediately after
bringing the device online.
A no-op stub of mlx5_devlink_eswitch_mode_set() is added for builds
without CONFIG_MLX5_ESWITCH.
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 6 +++
.../net/ethernet/mellanox/mlx5/core/main.c | 43 ++++++++++++++++++-
include/linux/mlx5/driver.h | 2 +
3 files changed, 50 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 3858690e09b4..cfb9595f9de8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -1049,6 +1049,12 @@ mlx5_esw_lag_demux_rule_create(struct mlx5_eswitch *esw, u16 vport_num,
return ERR_PTR(-EOPNOTSUPP);
}
+static inline int
+mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+ struct netlink_ext_ack *extack)
+{
+ return -EOPNOTSUPP;
+}
#endif /* CONFIG_MLX5_ESWITCH */
#endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 74827e8ca125..4cdda15ed7f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -86,7 +86,7 @@ MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec t
static unsigned int prof_sel = MLX5_DEFAULT_PROF;
module_param_named(prof_sel, prof_sel, uint, 0444);
-MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2");
+MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 3 and 8");
static u32 sw_owner_id[4];
#define MAX_SW_VHCA_ID (BIT(__mlx5_bit_sz(cmd_hca_cap_2, sw_vhca_id)) - 1)
@@ -99,6 +99,8 @@ enum {
#define LOG_MAX_SUPPORTED_QPS 0xff
+#define MLX5_PROF_SEL_LAST_NIC 3
+#define MLX5_PROF_SEL_FIRST_ESW 8
static struct mlx5_profile profile[] = {
[0] = {
.mask = 0,
@@ -120,6 +122,11 @@ static struct mlx5_profile profile[] = {
.log_max_qp = LOG_MAX_SUPPORTED_QPS,
.num_cmd_caches = 0,
},
+ [8] = {
+ .mask = MLX5_PROF_MASK_DEF_SWITCHDEV | MLX5_PROF_MASK_QP_SIZE,
+ .log_max_qp = LOG_MAX_SUPPORTED_QPS,
+ .num_cmd_caches = MLX5_NUM_COMMAND_CACHES,
+ },
};
static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
@@ -1385,6 +1392,22 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
mlx5_free_bfreg(dev, &dev->priv.bfreg);
}
+static void mlx5_set_default_switchdev(struct mlx5_core_dev *dev)
+{
+ int err;
+
+ /* Default switchdev is best-effort; keep the device usable on
+ * failure.
+ */
+ err = mlx5_devlink_eswitch_mode_set(priv_to_devlink(dev),
+ DEVLINK_ESWITCH_MODE_SWITCHDEV,
+ NULL);
+ if (err && err != -EOPNOTSUPP)
+ mlx5_core_warn(dev,
+ "Failed to set switchdev as default, continuing in current mode, err(%d)\n",
+ err);
+}
+
int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
{
bool light_probe = mlx5_dev_is_lightweight(dev);
@@ -1431,6 +1454,10 @@ int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
mutex_unlock(&dev->intf_state_mutex);
+
+ if (dev->profile.mask & MLX5_PROF_MASK_DEF_SWITCHDEV)
+ mlx5_set_default_switchdev(dev);
+
return 0;
err_register:
@@ -1532,6 +1559,10 @@ int mlx5_load_one_devl_locked(struct mlx5_core_dev *dev, bool recovery)
goto err_attach;
mutex_unlock(&dev->intf_state_mutex);
+
+ if (dev->profile.mask & MLX5_PROF_MASK_DEF_SWITCHDEV)
+ mlx5_set_default_switchdev(dev);
+
return 0;
err_attach:
@@ -2314,6 +2345,16 @@ static void mlx5_core_verify_params(void)
MLX5_DEFAULT_PROF);
prof_sel = MLX5_DEFAULT_PROF;
}
+
+ if (prof_sel > MLX5_PROF_SEL_LAST_NIC &&
+ prof_sel < MLX5_PROF_SEL_FIRST_ESW) {
+ pr_warn("mlx5_core: WARNING: Invalid module parameter prof_sel %d invalid range %d - %d, changing back to default (%d)\n",
+ prof_sel,
+ MLX5_PROF_SEL_LAST_NIC + 1,
+ MLX5_PROF_SEL_FIRST_ESW - 1,
+ MLX5_DEFAULT_PROF);
+ prof_sel = MLX5_DEFAULT_PROF;
+ }
}
static int __init mlx5_init(void)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 04b96c5abb57..65298c07df4d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -705,6 +705,8 @@ struct mlx5_st;
enum {
MLX5_PROF_MASK_QP_SIZE = (u64)1 << 0,
+ MLX5_PROF_MASK_MR_CACHE = (u64)1 << 1,
+ MLX5_PROF_MASK_DEF_SWITCHDEV = (u64)1 << 2,
};
struct mlx5_profile {
--
2.44.0
^ permalink raw reply related
* [PATCH net-next 0/3] net/mlx5: ICM page management in VHCA_ID mode
From: Tariq Toukan @ 2026-05-01 4:41 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch,
Moshe Shemesh, Akiva Goldberger, netdev, linux-rdma, linux-kernel,
Gal Pressman, Dragos Tatulea
Hi,
Find detailed description by Moshe below.
Regards,
Tariq
This series adds driver support for the VHCA_ID page management mode.
When firmware and driver support this mode, ICM (Interconnect Context
Memory) page management uses the device vhca_id as the function
identifier in MANAGE_PAGES, QUERY_PAGES, and page request events instead
of the legacy function_id + ec_function pair.
Background
Firmware can operate page management in two modes:
FUNC_ID mode (current): Function identity is (function_id, ec_function).
This remains the default and is used for boot pages and when the new
mode capability is not set.
VHCA_ID mode (new): Function identity is vhca_id only; ec_function is
ignored. This aligns page management with the vhca_id-based model used
by other firmware commands and simplifies identification on SmartNIC and
multi-function setups.
Moshe Shemesh (3):
net/mlx5: Relax capability check for eswitch query paths
net/mlx5: Make debugfs page counters by function type dynamic
net/mlx5: Add VHCA_ID page management mode support
.../net/ethernet/mellanox/mlx5/core/debugfs.c | 39 ++-
.../ethernet/mellanox/mlx5/core/esw/ipsec.c | 2 +-
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 48 +++-
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 7 +
.../mellanox/mlx5/core/eswitch_offloads.c | 14 +-
.../net/ethernet/mellanox/mlx5/core/main.c | 10 +-
.../ethernet/mellanox/mlx5/core/pagealloc.c | 226 ++++++++++++++----
include/linux/mlx5/driver.h | 9 +
8 files changed, 289 insertions(+), 66 deletions(-)
base-commit: 4e37987362bcac8909f2d4b4458f3aa645e41641
--
2.44.0
^ permalink raw reply
* [PATCH net-next 1/3] net/mlx5: Relax capability check for eswitch query paths
From: Tariq Toukan @ 2026-05-01 4:41 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch,
Moshe Shemesh, Akiva Goldberger, netdev, linux-rdma, linux-kernel,
Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501044156.260875-1-tariqt@nvidia.com>
From: Moshe Shemesh <moshe@nvidia.com>
Several eswitch functions that only query other functions' HCA
capabilities or read cached vport state are guarded by the
vhca_resource_manager capability. This capability is required for
set_hca_cap operations but query_hca_cap of other functions only
requires the vport_group_manager capability.
Relax the capability check from vhca_resource_manager to
vport_group_manager in the following query-only paths:
- mlx5_esw_vport_caps_get() - queries other function general caps
- esw_ipsec_vf_query_generic() - queries other function ipsec cap
- mlx5_devlink_port_fn_migratable_get() - reads cached vport state
- mlx5_devlink_port_fn_roce_get() - reads cached vport state
- mlx5_devlink_port_fn_max_io_eqs_get() - queries other function caps
- mlx5_esw_vport_enable/disable() - vhca_id map/unmap
Functions that perform also set_hca_cap (migratable_set, roce_set,
max_io_eqs_set, esw_ipsec_vf_set_generic, esw_ipsec_vf_set_bytype)
retain the vhca_resource_manager requirement.
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/esw/ipsec.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 6 +++---
.../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 14 ++++++++------
3 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
index 8b12c3ae0cf7..4811b60ea430 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec.c
@@ -12,7 +12,7 @@ static int esw_ipsec_vf_query_generic(struct mlx5_core_dev *dev, u16 vport_num,
void *hca_cap, *query_cap;
int err;
- if (!MLX5_CAP_GEN(dev, vhca_resource_manager))
+ if (!MLX5_CAP_GEN(dev, vport_group_manager))
return -EOPNOTSUPP;
if (!mlx5_esw_ipsec_vf_offload_supported(dev)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 66a773a99876..e0eafcf0c52a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -806,7 +806,7 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
void *hca_caps;
int err;
- if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
return 0;
query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
@@ -938,7 +938,7 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
vport->info.trusted = true;
if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
- MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+ MLX5_CAP_GEN(esw->dev, vport_group_manager)) {
ret = mlx5_esw_vport_vhca_id_map(esw, vport);
if (ret)
goto err_vhca_mapping;
@@ -976,7 +976,7 @@ void mlx5_esw_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
arm_vport_context_events_cmd(esw->dev, vport_num, 0);
if (!mlx5_esw_is_manager_vport(esw, vport_num) &&
- MLX5_CAP_GEN(esw->dev, vhca_resource_manager))
+ MLX5_CAP_GEN(esw->dev, vport_group_manager))
mlx5_esw_vport_vhca_id_unmap(esw, vport);
if (vport->vport != MLX5_VPORT_HOST_PF &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 69ddf56e2fc9..392d8f364db6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4677,8 +4677,9 @@ int mlx5_devlink_port_fn_migratable_get(struct devlink_port *port, bool *is_enab
return -EOPNOTSUPP;
}
- if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
- NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Device doesn't support vport group management");
return -EOPNOTSUPP;
}
@@ -4753,8 +4754,9 @@ int mlx5_devlink_port_fn_roce_get(struct devlink_port *port, bool *is_enabled,
struct mlx5_eswitch *esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port);
- if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
- NL_SET_ERR_MSG_MOD(extack, "Device doesn't support VHCA management");
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Device doesn't support vport group management");
return -EOPNOTSUPP;
}
@@ -5076,9 +5078,9 @@ mlx5_devlink_port_fn_max_io_eqs_get(struct devlink_port *port, u32 *max_io_eqs,
int err;
esw = mlx5_devlink_eswitch_nocheck_get(port->devlink);
- if (!MLX5_CAP_GEN(esw->dev, vhca_resource_manager)) {
+ if (!MLX5_CAP_GEN(esw->dev, vport_group_manager)) {
NL_SET_ERR_MSG_MOD(extack,
- "Device doesn't support VHCA management");
+ "Device doesn't support vport group management");
return -EOPNOTSUPP;
}
--
2.44.0
^ permalink raw reply related
* [PATCH net-next 2/3] net/mlx5: Make debugfs page counters by function type dynamic
From: Tariq Toukan @ 2026-05-01 4:41 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch,
Moshe Shemesh, Akiva Goldberger, netdev, linux-rdma, linux-kernel,
Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501044156.260875-1-tariqt@nvidia.com>
From: Moshe Shemesh <moshe@nvidia.com>
Make the per function type debugfs page counters dynamically added after
mlx5_eswitch_init(). When page management operates in vhca_id mode, only
the function acting as either eSwitch or vport manager can initialize
the eSwitch structure and translate the vhca_id to function type for the
functions to which it supplies pages. The next patch will add support
for page management in vhca_id mode.
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/debugfs.c | 39 +++++++++++++++++--
.../net/ethernet/mellanox/mlx5/core/main.c | 7 +++-
include/linux/mlx5/driver.h | 2 +
3 files changed, 42 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 8fe263190d38..6347957fefcb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -285,10 +285,6 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev)
pages = dev->priv.dbg.pages_debugfs;
debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages);
- debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]);
- debugfs_create_u32("fw_pages_ec_vfs", 0400, pages, &dev->priv.page_counters[MLX5_EC_VF]);
- debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]);
- debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]);
debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed);
debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped);
debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages,
@@ -300,6 +296,41 @@ void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev)
debugfs_remove_recursive(dev->priv.dbg.pages_debugfs);
}
+void mlx5_pages_by_func_type_debugfs_init(struct mlx5_core_dev *dev)
+{
+ struct dentry *pages = dev->priv.dbg.pages_debugfs;
+
+ if (!pages)
+ return;
+
+ if (!dev->priv.eswitch &&
+ MLX5_CAP_GEN(dev, icm_mng_function_id_mode) ==
+ MLX5_ID_MODE_FUNCTION_VHCA_ID)
+ return;
+
+ debugfs_create_u32("fw_pages_vfs", 0400, pages,
+ &dev->priv.page_counters[MLX5_VF]);
+ debugfs_create_u32("fw_pages_ec_vfs", 0400, pages,
+ &dev->priv.page_counters[MLX5_EC_VF]);
+ debugfs_create_u32("fw_pages_sfs", 0400, pages,
+ &dev->priv.page_counters[MLX5_SF]);
+ debugfs_create_u32("fw_pages_host_pf", 0400, pages,
+ &dev->priv.page_counters[MLX5_HOST_PF]);
+}
+
+void mlx5_pages_by_func_type_debugfs_cleanup(struct mlx5_core_dev *dev)
+{
+ struct dentry *pages = dev->priv.dbg.pages_debugfs;
+
+ if (!pages)
+ return;
+
+ debugfs_lookup_and_remove("fw_pages_vfs", pages);
+ debugfs_lookup_and_remove("fw_pages_ec_vfs", pages);
+ debugfs_lookup_and_remove("fw_pages_sfs", pages);
+ debugfs_lookup_and_remove("fw_pages_host_pf", pages);
+}
+
static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
int index, int *is_str)
{
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 74827e8ca125..a242053f3a58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -987,11 +987,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
mlx5_core_err(dev, "Failed to init eswitch %d\n", err);
goto err_sriov_cleanup;
}
+ mlx5_pages_by_func_type_debugfs_init(dev);
err = mlx5_fpga_init(dev);
if (err) {
mlx5_core_err(dev, "Failed to init fpga device %d\n", err);
- goto err_eswitch_cleanup;
+ goto err_page_debugfs_cleanup;
}
err = mlx5_vhca_event_init(dev);
@@ -1034,7 +1035,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
mlx5_vhca_event_cleanup(dev);
err_fpga_cleanup:
mlx5_fpga_cleanup(dev);
-err_eswitch_cleanup:
+err_page_debugfs_cleanup:
+ mlx5_pages_by_func_type_debugfs_cleanup(dev);
mlx5_eswitch_cleanup(dev->priv.eswitch);
err_sriov_cleanup:
mlx5_sriov_cleanup(dev);
@@ -1072,6 +1074,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
mlx5_sf_hw_table_cleanup(dev);
mlx5_vhca_event_cleanup(dev);
mlx5_fpga_cleanup(dev);
+ mlx5_pages_by_func_type_debugfs_cleanup(dev);
mlx5_eswitch_cleanup(dev->priv.eswitch);
mlx5_sriov_cleanup(dev);
mlx5_mpfs_cleanup(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 04b96c5abb57..b460b3bae195 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1034,6 +1034,8 @@ void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev);
void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev);
+void mlx5_pages_by_func_type_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_pages_by_func_type_debugfs_cleanup(struct mlx5_core_dev *dev);
int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
void mlx5_register_debugfs(void);
--
2.44.0
^ permalink raw reply related
* [PATCH net-next 3/3] net/mlx5: Add VHCA_ID page management mode support
From: Tariq Toukan @ 2026-05-01 4:41 UTC (permalink / raw)
To: Eric Dumazet, Jakub Kicinski, Paolo Abeni, Andrew Lunn,
David S. Miller
Cc: Saeed Mahameed, Leon Romanovsky, Tariq Toukan, Mark Bloch,
Moshe Shemesh, Akiva Goldberger, netdev, linux-rdma, linux-kernel,
Gal Pressman, Dragos Tatulea
In-Reply-To: <20260501044156.260875-1-tariqt@nvidia.com>
From: Moshe Shemesh <moshe@nvidia.com>
Add support for VHCA_ID-based page management mode. When the device
firmware advertises the icm_mng_function_id_mode capability with
MLX5_ID_MODE_FUNCTION_VHCA_ID, page management operations between the
driver and firmware may use vhca_id instead of function_id as the
effective function identifier, and the ec_function field is ignored.
Update page management commands to conditionally set ec_function field
only in FUNC_ID mode. Boot page allocation always uses FUNC_ID mode
semantics for backward compatibility, as the capability bit is only
available after set_hca_cap(). If after set_hca_cap() VHCA_ID mode was
set, modify the tracking of the boot pages in page_root_xa to use
vhca_id too.
Add mlx5_esw_vhca_id_to_func_type() to resolve the function type via
vport lookup in VHCA_ID mode, enabling per-type debugfs counters.
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
.../net/ethernet/mellanox/mlx5/core/eswitch.c | 42 ++++
.../net/ethernet/mellanox/mlx5/core/eswitch.h | 7 +
.../net/ethernet/mellanox/mlx5/core/main.c | 3 +
.../ethernet/mellanox/mlx5/core/pagealloc.c | 226 ++++++++++++++----
include/linux/mlx5/driver.h | 7 +
5 files changed, 235 insertions(+), 50 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index e0eafcf0c52a..d3eaefc5c0e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -852,6 +852,48 @@ bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
return true;
}
+u16 mlx5_esw_vhca_id_to_func_type(struct mlx5_core_dev *dev, u16 vhca_id)
+{
+ struct mlx5_eswitch *esw = dev->priv.eswitch;
+ struct mlx5_vport *vport;
+ unsigned long i;
+ u16 type;
+
+ if (vhca_id == MLX5_CAP_GEN(dev, vhca_id))
+ return MLX5_SELF;
+
+ if (!esw)
+ return MLX5_FUNC_TYPE_NONE;
+
+ mutex_lock(&esw->state_lock);
+ mlx5_esw_for_each_vport(esw, i, vport) {
+ if (vport->vhca_id != vhca_id)
+ continue;
+
+ if (vport->vport == MLX5_VPORT_HOST_PF) {
+ type = MLX5_HOST_PF;
+ goto unlock;
+ }
+
+ if (xa_get_mark(&esw->vports, i, MLX5_ESW_VPT_SF)) {
+ type = MLX5_SF;
+ goto unlock;
+ }
+
+ if (xa_get_mark(&esw->vports, i, MLX5_ESW_VPT_VF)) {
+ type = MLX5_VF;
+ goto unlock;
+ }
+
+ type = MLX5_EC_VF;
+ goto unlock;
+ }
+ type = MLX5_FUNC_TYPE_NONE;
+unlock:
+ mutex_unlock(&esw->state_lock);
+ return type;
+}
+
static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
{
bool vst_mode_steering = esw_vst_mode_is_steering(esw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 2fd601bd102f..5940b4cbfd77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -863,6 +863,7 @@ void mlx5_esw_vport_vhca_id_unmap(struct mlx5_eswitch *esw,
struct mlx5_vport *vport);
int mlx5_eswitch_vhca_id_to_vport(struct mlx5_eswitch *esw, u16 vhca_id, u16 *vport_num);
bool mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id);
+u16 mlx5_esw_vhca_id_to_func_type(struct mlx5_core_dev *dev, u16 vhca_id);
void mlx5_esw_offloads_rep_remove(struct mlx5_eswitch *esw,
const struct mlx5_vport *vport);
@@ -1034,6 +1035,12 @@ mlx5_esw_vport_vhca_id(struct mlx5_eswitch *esw, u16 vportn, u16 *vhca_id)
return false;
}
+static inline u16
+mlx5_esw_vhca_id_to_func_type(struct mlx5_core_dev *dev, u16 vhca_id)
+{
+ return MLX5_FUNC_TYPE_NONE;
+}
+
static inline void
mlx5_eswitch_safe_aux_devs_remove(struct mlx5_core_dev *dev) {}
static inline struct mlx5_flow_handle *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a242053f3a58..52cf341ad6b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -597,6 +597,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
if (MLX5_CAP_GEN_MAX(dev, release_all_pages))
MLX5_SET(cmd_hca_cap, set_hca_cap, release_all_pages, 1);
+ if (MLX5_CAP_GEN_MAX(dev, icm_mng_function_id_mode))
+ MLX5_SET(cmd_hca_cap, set_hca_cap, icm_mng_function_id_mode, 1);
+
if (MLX5_CAP_GEN_MAX(dev, mkey_by_name))
MLX5_SET(cmd_hca_cap, set_hca_cap, mkey_by_name, 1);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 77ffa31cc505..7ebe88aa3b3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -38,6 +38,7 @@
#include "mlx5_core.h"
#include "lib/eq.h"
#include "lib/tout.h"
+#include "eswitch.h"
enum {
MLX5_PAGES_CANT_GIVE = 0,
@@ -69,9 +70,24 @@ enum {
MLX5_NUM_4K_IN_PAGE = PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
};
-static u32 get_function(u16 func_id, bool ec_function)
+static bool mlx5_page_mgt_mode_is_vhca_id(const struct mlx5_core_dev *dev)
{
- return (u32)func_id | (ec_function << 16);
+ return dev->priv.page_mgt_mode == MLX5_PAGE_MGT_MODE_VHCA_ID;
+}
+
+static void mlx5_page_mgt_mode_set(struct mlx5_core_dev *dev,
+ enum mlx5_page_mgt_mode mode)
+{
+ dev->priv.page_mgt_mode = mode;
+}
+
+static u32 get_function_key(struct mlx5_core_dev *dev, u16 func_vhca_id,
+ bool ec_function)
+{
+ if (mlx5_page_mgt_mode_is_vhca_id(dev))
+ return (u32)func_vhca_id;
+
+ return (u32)func_vhca_id | (ec_function << 16);
}
static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function)
@@ -89,12 +105,21 @@ static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_funct
return MLX5_SF;
}
+static u16 func_vhca_id_to_type(struct mlx5_core_dev *dev, u16 func_vhca_id,
+ bool ec_function)
+{
+ if (mlx5_page_mgt_mode_is_vhca_id(dev))
+ return mlx5_esw_vhca_id_to_func_type(dev, func_vhca_id);
+
+ return func_id_to_type(dev, func_vhca_id, ec_function);
+}
+
static u32 mlx5_get_ec_function(u32 function)
{
return function >> 16;
}
-static u32 mlx5_get_func_id(u32 function)
+static u32 mlx5_get_func_vhca_id(u32 function)
{
return function & 0xffff;
}
@@ -196,7 +221,7 @@ static struct fw_page *find_fw_page(struct mlx5_core_dev *dev, u64 addr,
return result;
}
-static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
+static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_vhca_id,
s32 *npages, int boot)
{
u32 out[MLX5_ST_SZ_DW(query_pages_out)] = {};
@@ -207,14 +232,20 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
MLX5_SET(query_pages_in, in, op_mod, boot ?
MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES :
MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
- MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
+
+ if (mlx5_page_mgt_mode_is_vhca_id(dev))
+ MLX5_SET(query_pages_in, in, function_id,
+ MLX5_CAP_GEN(dev, vhca_id));
+ else
+ MLX5_SET(query_pages_in, in, embedded_cpu_function,
+ mlx5_core_is_ecpf(dev));
err = mlx5_cmd_exec_inout(dev, query_pages, in, out);
if (err)
return err;
*npages = MLX5_GET(query_pages_out, out, num_pages);
- *func_id = MLX5_GET(query_pages_out, out, function_id);
+ *func_vhca_id = MLX5_GET(query_pages_out, out, function_id);
return err;
}
@@ -334,7 +365,7 @@ static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
return err;
}
-static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
+static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_vhca_id,
bool ec_function)
{
u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
@@ -342,19 +373,23 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE);
- MLX5_SET(manage_pages_in, in, function_id, func_id);
- MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
+ MLX5_SET(manage_pages_in, in, function_id, func_vhca_id);
+
+ if (!mlx5_page_mgt_mode_is_vhca_id(dev))
+ MLX5_SET(manage_pages_in, in, embedded_cpu_function,
+ ec_function);
err = mlx5_cmd_exec_in(dev, manage_pages, in);
if (err)
- mlx5_core_warn(dev, "page notify failed func_id(%d) err(%d)\n",
- func_id, err);
+ mlx5_core_warn(dev,
+ "page notify failed func_vhca_id(%d) err(%d)\n",
+ func_vhca_id, err);
}
-static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
+static int give_pages(struct mlx5_core_dev *dev, u16 func_vhca_id, int npages,
int event, bool ec_function)
{
- u32 function = get_function(func_id, ec_function);
+ u32 function = get_function_key(dev, func_vhca_id, ec_function);
u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
int notify_fail = event;
@@ -390,9 +425,12 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE);
- MLX5_SET(manage_pages_in, in, function_id, func_id);
+ MLX5_SET(manage_pages_in, in, function_id, func_vhca_id);
MLX5_SET(manage_pages_in, in, input_num_entries, npages);
- MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
+
+ if (!mlx5_page_mgt_mode_is_vhca_id(dev))
+ MLX5_SET(manage_pages_in, in, embedded_cpu_function,
+ ec_function);
err = mlx5_cmd_do(dev, in, inlen, out, sizeof(out));
if (err == -EREMOTEIO) {
@@ -405,17 +443,20 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
}
err = mlx5_cmd_check(dev, err, in, out);
if (err) {
- mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
- func_id, npages, err);
+ mlx5_core_warn(dev, "func_vhca_id 0x%x, npages %d, err %d\n",
+ func_vhca_id, npages, err);
goto out_dropped;
}
- func_type = func_id_to_type(dev, func_id, ec_function);
- dev->priv.page_counters[func_type] += npages;
+ func_type = func_vhca_id_to_type(dev, func_vhca_id, ec_function);
+ if (func_type != MLX5_FUNC_TYPE_NONE)
+ dev->priv.page_counters[func_type] += npages;
dev->priv.fw_pages += npages;
- mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
- npages, ec_function, func_id, err);
+ mlx5_core_dbg(dev,
+ "npages %d, ec_function %d, func 0x%x, mode %d, err %d\n",
+ npages, ec_function, func_vhca_id,
+ mlx5_page_mgt_mode_is_vhca_id(dev), err);
kvfree(in);
return 0;
@@ -428,14 +469,14 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
out_free:
kvfree(in);
if (notify_fail)
- page_notify_fail(dev, func_id, ec_function);
+ page_notify_fail(dev, func_vhca_id, ec_function);
return err;
}
-static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id,
+static void release_all_pages(struct mlx5_core_dev *dev, u16 func_vhca_id,
bool ec_function)
{
- u32 function = get_function(func_id, ec_function);
+ u32 function = get_function_key(dev, func_vhca_id, ec_function);
struct rb_root *root;
struct rb_node *p;
int npages = 0;
@@ -454,12 +495,14 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id,
free_fwp(dev, fwp, fwp->free_count);
}
- func_type = func_id_to_type(dev, func_id, ec_function);
- dev->priv.page_counters[func_type] -= npages;
+ func_type = func_vhca_id_to_type(dev, func_vhca_id, ec_function);
+ if (func_type != MLX5_FUNC_TYPE_NONE)
+ dev->priv.page_counters[func_type] -= npages;
dev->priv.fw_pages -= npages;
- mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n",
- npages, ec_function, func_id);
+ mlx5_core_dbg(dev, "npages %d, ec_function %d, func 0x%x, mode %d\n",
+ npages, ec_function, func_vhca_id,
+ mlx5_page_mgt_mode_is_vhca_id(dev));
}
static u32 fwp_fill_manage_pages_out(struct fw_page *fwp, u32 *out, u32 index,
@@ -487,7 +530,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
struct fw_page *fwp;
struct rb_node *p;
bool ec_function;
- u32 func_id;
+ u32 func_vhca_id;
u32 npages;
u32 i = 0;
int err;
@@ -499,10 +542,11 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
/* No hard feelings, we want our pages back! */
npages = MLX5_GET(manage_pages_in, in, input_num_entries);
- func_id = MLX5_GET(manage_pages_in, in, function_id);
+ func_vhca_id = MLX5_GET(manage_pages_in, in, function_id);
ec_function = MLX5_GET(manage_pages_in, in, embedded_cpu_function);
- root = xa_load(&dev->priv.page_root_xa, get_function(func_id, ec_function));
+ root = xa_load(&dev->priv.page_root_xa,
+ get_function_key(dev, func_vhca_id, ec_function));
if (WARN_ON_ONCE(!root))
return -EEXIST;
@@ -518,10 +562,11 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
return 0;
}
-static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
- int *nclaimed, bool event, bool ec_function)
+static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_vhca_id,
+ int npages, int *nclaimed, bool event,
+ bool ec_function)
{
- u32 function = get_function(func_id, ec_function);
+ u32 function = get_function_key(dev, func_vhca_id, ec_function);
int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {};
int num_claimed;
@@ -540,12 +585,16 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE);
- MLX5_SET(manage_pages_in, in, function_id, func_id);
+ MLX5_SET(manage_pages_in, in, function_id, func_vhca_id);
MLX5_SET(manage_pages_in, in, input_num_entries, npages);
- MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
- mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d\n",
- func_id, npages, outlen);
+ if (!mlx5_page_mgt_mode_is_vhca_id(dev))
+ MLX5_SET(manage_pages_in, in, embedded_cpu_function,
+ ec_function);
+
+ mlx5_core_dbg(dev, "func 0x%x, npages %d, outlen %d mode %d\n",
+ func_vhca_id, npages, outlen,
+ mlx5_page_mgt_mode_is_vhca_id(dev));
err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
if (err) {
npages = MLX5_GET(manage_pages_in, in, input_num_entries);
@@ -577,8 +626,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
if (nclaimed)
*nclaimed = num_claimed;
- func_type = func_id_to_type(dev, func_id, ec_function);
- dev->priv.page_counters[func_type] -= num_claimed;
+ func_type = func_vhca_id_to_type(dev, func_vhca_id, ec_function);
+ if (func_type != MLX5_FUNC_TYPE_NONE)
+ dev->priv.page_counters[func_type] -= num_claimed;
dev->priv.fw_pages -= num_claimed;
out_free:
@@ -658,30 +708,101 @@ static int req_pages_handler(struct notifier_block *nb,
* req->npages (and not min ()).
*/
req->npages = max_t(s32, npages, MAX_RECLAIM_NPAGES);
- req->ec_function = ec_function;
+ if (!mlx5_page_mgt_mode_is_vhca_id(dev))
+ req->ec_function = ec_function;
req->release_all = release_all;
INIT_WORK(&req->work, pages_work_handler);
queue_work(dev->priv.pg_wq, &req->work);
return NOTIFY_OK;
}
+/*
+ * After set_hca_cap(), the second satisfy_startup_pages(dev, 0) may see
+ * VHCA_ID mode. If page_root_xa already has the PF entry from the first
+ * (boot) call under FUNC_ID keys 0 or (ec_function << 16), migrate that
+ * entry to the device vhca_id key so lookups use VHCA_ID semantics.
+ */
+static int mlx5_pagealloc_migrate_pf_to_vhca_id(struct mlx5_core_dev *dev)
+{
+ u32 vhca_id_key, old_key;
+ struct rb_root *root;
+ struct fw_page *fwp;
+ struct rb_node *p;
+ bool ec_function;
+ int err;
+
+ if (xa_empty(&dev->priv.page_root_xa))
+ return 0;
+
+ vhca_id_key = MLX5_CAP_GEN(dev, vhca_id);
+ ec_function = mlx5_core_is_ecpf(dev);
+
+ old_key = ec_function ? (1U << 16) : 0;
+ root = xa_load(&dev->priv.page_root_xa, old_key);
+ if (!root)
+ return 0;
+
+ if (old_key == vhca_id_key)
+ return 0;
+
+ err = xa_insert(&dev->priv.page_root_xa, vhca_id_key, root, GFP_KERNEL);
+ if (err) {
+ mlx5_core_warn(dev,
+ "failed to migrate page root key 0x%x to vhca_id 0x%x\n",
+ old_key, vhca_id_key);
+ return err;
+ }
+
+ xa_erase(&dev->priv.page_root_xa, old_key);
+
+ for (p = rb_first(root); p; p = rb_next(p)) {
+ fwp = rb_entry(p, struct fw_page, rb_node);
+ fwp->function = vhca_id_key;
+ }
+
+ return 0;
+}
+
int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
{
- u16 func_id;
+ bool ec_function = false;
+ u16 func_vhca_id;
s32 npages;
int err;
- err = mlx5_cmd_query_pages(dev, &func_id, &npages, boot);
+ /* When boot flag is set, the icm_mng_function_id_mode capability is
+ * not yet set (only set after set_hca_cap()), so use FUNC_ID mode
+ * for backward compatibility. When boot is false, set mode from
+ * cap (set_hca_cap has run successfully).
+ */
+ if (boot) {
+ mlx5_page_mgt_mode_set(dev, MLX5_PAGE_MGT_MODE_FUNC_ID);
+ } else {
+ if (MLX5_CAP_GEN_MAX(dev, icm_mng_function_id_mode) ==
+ MLX5_ID_MODE_FUNCTION_VHCA_ID) {
+ err = mlx5_pagealloc_migrate_pf_to_vhca_id(dev);
+ if (err)
+ return err;
+ mlx5_page_mgt_mode_set(dev, MLX5_PAGE_MGT_MODE_VHCA_ID);
+ }
+ }
+
+ err = mlx5_cmd_query_pages(dev, &func_vhca_id, &npages, boot);
if (err)
return err;
- mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
- npages, boot ? "boot" : "init", func_id);
+ mlx5_core_dbg(dev,
+ "requested %d %s pages for func_vhca_id 0x%x\n",
+ npages, boot ? "boot" : "init", func_vhca_id);
if (!npages)
return 0;
- return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
+ /* In VHCA_ID mode, ec_function remains false (not used). */
+ if (!mlx5_page_mgt_mode_is_vhca_id(dev))
+ ec_function = mlx5_core_is_ecpf(dev);
+
+ return give_pages(dev, func_vhca_id, npages, 0, ec_function);
}
enum {
@@ -709,15 +830,17 @@ static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev,
while (!RB_EMPTY_ROOT(root)) {
u32 ec_function = mlx5_get_ec_function(function);
- u32 function_id = mlx5_get_func_id(function);
+ u32 func_vhca_id = mlx5_get_func_vhca_id(function);
int nclaimed;
int err;
- err = reclaim_pages(dev, function_id, optimal_reclaimed_pages(),
+ err = reclaim_pages(dev, func_vhca_id,
+ optimal_reclaimed_pages(),
&nclaimed, false, ec_function);
if (err) {
- mlx5_core_warn(dev, "reclaim_pages err (%d) func_id=0x%x ec_func=0x%x\n",
- err, function_id, ec_function);
+ mlx5_core_warn(dev,
+ "reclaim_pages err (%d) func_vhca_id=0x%x ec_func=0x%x\n",
+ err, func_vhca_id, ec_function);
return err;
}
@@ -751,6 +874,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
WARN(dev->priv.fw_pages,
"FW pages counter is %d after reclaiming all pages\n",
dev->priv.fw_pages);
+ if (mlx5_page_mgt_mode_is_vhca_id(dev) && !dev->priv.eswitch)
+ return 0;
+
WARN(dev->priv.page_counters[MLX5_VF],
"VFs FW pages counter is %d after reclaiming all pages\n",
dev->priv.page_counters[MLX5_VF]);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index b460b3bae195..8e22ea662644 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -556,6 +556,12 @@ enum mlx5_func_type {
MLX5_HOST_PF,
MLX5_EC_VF,
MLX5_FUNC_TYPE_NUM,
+ MLX5_FUNC_TYPE_NONE = MLX5_FUNC_TYPE_NUM,
+};
+
+enum mlx5_page_mgt_mode {
+ MLX5_PAGE_MGT_MODE_FUNC_ID,
+ MLX5_PAGE_MGT_MODE_VHCA_ID,
};
struct mlx5_ft_pool;
@@ -575,6 +581,7 @@ struct mlx5_priv {
u32 fw_pages_alloc_failed;
u32 give_pages_dropped;
u32 reclaim_pages_discard;
+ enum mlx5_page_mgt_mode page_mgt_mode;
struct mlx5_core_health health;
struct list_head traps;
--
2.44.0
^ permalink raw reply related
* Re: [PATCH net-next 3/4] r8152: Add irq mitigation for RTL8157/9
From: Michal Pecio @ 2026-05-01 5:24 UTC (permalink / raw)
To: Andrew Lunn
Cc: Birger Koblitz, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, linux-usb, netdev, linux-kernel,
Chih Kai Hsu
In-Reply-To: <fac7da10-a2d3-4c14-9208-8762f38564cd@lunn.ch>
On Thu, 30 Apr 2026 16:19:30 +0200, Andrew Lunn wrote:
> If you are getting interrupts after the device has been disabled, i
> guess it is because the timer for a delayed interrupt is not cancelled
> by the firmware. If so you might be able to work around this firmware
> bug. Disable the receiver, sleep for 10ms but keep processing
> interrupts, and then continue with the tear down.
If the device responded to this URB, it would complete with a normal
status (success or some USB error). ESHUTDOWN (and the debug log)
indicate that the URB was unlinked by USB core due to rmmod, before
the driver knew that it's being unloaded and disabled anything.
Regards,
Michal
^ permalink raw reply
* [syzbot] [mptcp?] KMSAN: uninit-value in mptcp_established_options
From: syzbot @ 2026-05-01 6:15 UTC (permalink / raw)
To: davem, edumazet, geliang, horms, kuba, linux-kernel, martineau,
matttbe, mptcp, netdev, pabeni, syzkaller-bugs
Hello,
syzbot found the following issue on:
HEAD commit: 08d0d3466664 Merge tag 'net-7.1-rc2' of git://git.kernel.o..
git tree: upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=15f6976c580000
kernel config: https://syzkaller.appspot.com/x/.config?x=1c3f61154f3bb7e5
dashboard link: https://syzkaller.appspot.com/bug?extid=ff020673c5e3d94d9478
compiler: Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
userspace arch: i386
Unfortunately, I don't have any reproducer for this issue yet.
Downloadable assets:
disk image: https://storage.googleapis.com/syzbot-assets/8688db3eb9ae/disk-08d0d346.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/72c570681077/vmlinux-08d0d346.xz
kernel image: https://storage.googleapis.com/syzbot-assets/21669c9bddcd/bzImage-08d0d346.xz
IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+ff020673c5e3d94d9478@syzkaller.appspotmail.com
=====================================================
BUG: KMSAN: uninit-value in mptcp_write_data_fin net/mptcp/options.c:542 [inline]
BUG: KMSAN: uninit-value in mptcp_established_options_dss net/mptcp/options.c:590 [inline]
BUG: KMSAN: uninit-value in mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874
mptcp_write_data_fin net/mptcp/options.c:542 [inline]
mptcp_established_options_dss net/mptcp/options.c:590 [inline]
mptcp_established_options+0x112f/0x3530 net/mptcp/options.c:874
tcp_established_options+0x312/0xcc0 net/ipv4/tcp_output.c:1192
__tcp_transmit_skb+0x5dc/0x5fe0 net/ipv4/tcp_output.c:1575
__tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499
tcp_send_ack+0x3d/0x60 net/ipv4/tcp_output.c:4505
mptcp_subflow_shutdown+0x164/0x690 net/mptcp/protocol.c:3137
mptcp_check_send_data_fin+0x31b/0x3d0 net/mptcp/protocol.c:3218
__mptcp_wr_shutdown net/mptcp/protocol.c:3234 [inline]
__mptcp_close+0x860/0x1360 net/mptcp/protocol.c:3313
mptcp_close+0x42/0x260 net/mptcp/protocol.c:3367
inet_release+0x1ee/0x2a0 net/ipv4/af_inet.c:442
__sock_release net/socket.c:722 [inline]
sock_close+0xd6/0x2f0 net/socket.c:1514
__fput+0x60e/0x1010 fs/file_table.c:510
____fput+0x25/0x30 fs/file_table.c:538
task_work_run+0x208/0x2b0 kernel/task_work.c:233
resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
__exit_to_user_mode_loop kernel/entry/common.c:67 [inline]
exit_to_user_mode_loop+0x306/0x1b60 kernel/entry/common.c:98
__exit_to_user_mode_prepare include/linux/irq-entry-common.h:207 [inline]
syscall_exit_to_user_mode_prepare include/linux/irq-entry-common.h:238 [inline]
syscall_exit_to_user_mode include/linux/entry-common.h:318 [inline]
__do_fast_syscall_32+0x2c7/0x460 arch/x86/entry/syscall_32.c:310
do_fast_syscall_32+0x37/0x80 arch/x86/entry/syscall_32.c:332
do_SYSENTER_32+0x1f/0x30 arch/x86/entry/syscall_32.c:370
entry_SYSENTER_compat_after_hwframe+0x84/0x8e
Local variable opts created at:
__tcp_transmit_skb+0x4d/0x5fe0 net/ipv4/tcp_output.c:1536
__tcp_send_ack+0x967/0xad0 net/ipv4/tcp_output.c:4499
CPU: 0 UID: 0 PID: 24584 Comm: syz.4.6812 Tainted: G W syzkaller #0 PREEMPT(full)
Tainted: [W]=WARN
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 04/18/2026
=====================================================
---
This report is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.
If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title
If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)
If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report
If you want to undo deduplication, reply with:
#syz undup
^ permalink raw reply
* [PATCH net-next v2 0/3] netfilter: conntrack: add shared port parser and use it in IRC and Amanda helpers
From: HACKE-RC @ 2026-05-01 6:31 UTC (permalink / raw)
To: Pablo Neira Ayuso, Florian Westphal
Cc: Phil Sutter, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, netfilter-devel, coreteam, netdev,
linux-kernel, HACKE-RC
Both nf_conntrack_irc and nf_conntrack_amanda parse port numbers
from application-layer protocol data using simple_strtoul(), which
relies on nul-terminated strings and returns unsigned long without
range checking. Port values above 65535 silently truncate when
stored in u16.
This v2 adds a shared nf_ct_helper_parse_port() function to the
conntrack helper core, modeled after the approach in 8cf6809cddcb
("netfilter: nf_conntrack_sip: don't use simple_strtoul"), then
converts both helpers to use it.
Changes since v1:
- Added shared nf_ct_helper_parse_port() in the helper core
instead of open-coding range checks in each helper (Pablo)
- Parser does not rely on nul-terminated strings
- Dropped simple_strtoul usage entirely for port parsing
HACKE-RC (3):
netfilter: conntrack: add shared port parser for helpers
netfilter: nf_conntrack_irc: use nf_ct_helper_parse_port()
netfilter: nf_conntrack_amanda: use nf_ct_helper_parse_port()
include/net/netfilter/nf_conntrack_helper.h | 3 +++
net/netfilter/nf_conntrack_amanda.c | 11 ++++----
net/netfilter/nf_conntrack_helper.c | 28 +++++++++++++++++++++
net/netfilter/nf_conntrack_irc.c | 4 ++-
4 files changed, 40 insertions(+), 6 deletions(-)
--
2.54.0
^ permalink raw reply
* [PATCH net-next v2 1/3] netfilter: conntrack: add shared port parser for helpers
From: HACKE-RC @ 2026-05-01 6:31 UTC (permalink / raw)
To: Pablo Neira Ayuso, Florian Westphal
Cc: Phil Sutter, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, netfilter-devel, coreteam, netdev,
linux-kernel, HACKE-RC
In-Reply-To: <20260501063156.2520780-1-rc@rexion.ai>
Add nf_ct_helper_parse_port() to the conntrack helper core. This
provides a port parser that does not rely on nul-terminated strings,
taking an explicit length parameter and validating the result fits
in the 1-65535 range.
Modeled after the approach in 8cf6809cddcb ("netfilter:
nf_conntrack_sip: don't use simple_strtoul") but as a shared
function so IRC, Amanda, and other helpers can use it instead of
open-coding simple_strtoul calls with ad-hoc range checks.
Signed-off-by: HACKE-RC <rc@rexion.ai>
---
include/net/netfilter/nf_conntrack_helper.h | 3 +++
net/netfilter/nf_conntrack_helper.c | 28 +++++++++++++++++++++
2 files changed, 31 insertions(+)
diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index de2f956ab..db19fe25f 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -160,6 +160,9 @@ nf_ct_helper_expectfn_find_by_name(const char *name);
struct nf_ct_helper_expectfn *
nf_ct_helper_expectfn_find_by_symbol(const void *symbol);
+int nf_ct_helper_parse_port(const char *cp, unsigned int len,
+ u16 *port, char **endp);
+
extern struct hlist_head *nf_ct_helper_hash;
extern unsigned int nf_ct_helper_hsize;
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a715304a5..12f51670d 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -499,6 +499,34 @@ void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat)
}
EXPORT_SYMBOL_GPL(nf_nat_helper_unregister);
+int nf_ct_helper_parse_port(const char *cp, unsigned int len,
+ u16 *port, char **endp)
+{
+ unsigned long result = 0;
+ const char *start = cp;
+
+ while (len > 0 && *cp >= '0' && *cp <= '9') {
+ result = result * 10 + (*cp - '0');
+ if (result > 65535)
+ return -1;
+ cp++;
+ len--;
+ }
+
+ if (cp == start)
+ return -1;
+
+ if (result == 0)
+ return -1;
+
+ *port = result;
+ if (endp)
+ *endp = (char *)cp;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(nf_ct_helper_parse_port);
+
int nf_conntrack_helper_init(void)
{
nf_ct_helper_hsize = 1; /* gets rounded up to use one page */
--
2.54.0
^ permalink raw reply related
* [PATCH net-next v2 2/3] netfilter: nf_conntrack_irc: use nf_ct_helper_parse_port()
From: HACKE-RC @ 2026-05-01 6:31 UTC (permalink / raw)
To: Pablo Neira Ayuso, Florian Westphal
Cc: Phil Sutter, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, netfilter-devel, coreteam, netdev,
linux-kernel, HACKE-RC
In-Reply-To: <20260501063156.2520780-1-rc@rexion.ai>
Replace the bare simple_strtoul() call for port parsing with the
shared nf_ct_helper_parse_port(). This avoids reliance on the
nul-terminated string guarantee (currently provided by the newline
scan earlier in parse_dcc) and validates the port fits in u16.
The simple_strtoul() for the IP address field is left as-is since
it returns unsigned long for a __be32 conversion, which is a
separate concern.
Fixes: 869f37d8e48f ("[NETFILTER]: nf_conntrack/nf_nat: add IRC helper port")
Signed-off-by: HACKE-RC <rc@rexion.ai>
---
net/netfilter/nf_conntrack_irc.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c
index 522183b9a..1b51f5a6a 100644
--- a/net/netfilter/nf_conntrack_irc.c
+++ b/net/netfilter/nf_conntrack_irc.c
@@ -93,7 +93,9 @@ static int parse_dcc(char *data, const char *data_end, __be32 *ip,
data++;
}
- *port = simple_strtoul(data, &data, 10);
+ if (nf_ct_helper_parse_port(data, data_end - data, port, &data))
+ return -1;
+
*ad_end_p = data;
return 0;
--
2.54.0
^ permalink raw reply related
* [PATCH net-next v2 3/3] netfilter: nf_conntrack_amanda: use nf_ct_helper_parse_port()
From: HACKE-RC @ 2026-05-01 6:31 UTC (permalink / raw)
To: Pablo Neira Ayuso, Florian Westphal
Cc: Phil Sutter, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, netfilter-devel, coreteam, netdev,
linux-kernel, HACKE-RC
In-Reply-To: <20260501063156.2520780-1-rc@rexion.ai>
Replace the bare simple_strtoul() call with the shared
nf_ct_helper_parse_port(). This removes reliance on the
nul-terminated pbuf string for parsing and validates the port
range in a single call.
The len > 5 guard and port == 0 check are now handled by the
shared parser, which rejects zero and values above 65535.
Reorder local variable declarations to reverse christmas tree.
Fixes: 16958900578b ("[NETFILTER]: nf_conntrack/nf_nat: add amanda helper port")
Signed-off-by: HACKE-RC <rc@rexion.ai>
---
net/netfilter/nf_conntrack_amanda.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index d2c09e8dd..30b5c4b84 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -88,11 +88,12 @@ static int amanda_help(struct sk_buff *skb,
struct nf_conntrack_expect *exp;
struct nf_conntrack_tuple *tuple;
unsigned int dataoff, start, stop, off, i;
+ nf_nat_amanda_hook_fn *nf_nat_amanda;
char pbuf[sizeof("65535")], *tmp;
+ int ret = NF_ACCEPT;
u_int16_t len;
+ u16 parsed_port;
__be16 port;
- int ret = NF_ACCEPT;
- nf_nat_amanda_hook_fn *nf_nat_amanda;
/* Only look at packets from the Amanda server */
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
@@ -132,10 +133,10 @@ static int amanda_help(struct sk_buff *skb,
break;
pbuf[len] = '\0';
- port = htons(simple_strtoul(pbuf, &tmp, 10));
- len = tmp - pbuf;
- if (port == 0 || len > 5)
+ if (nf_ct_helper_parse_port(pbuf, len, &parsed_port, &tmp))
break;
+ port = htons(parsed_port);
+ len = tmp - pbuf;
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
--
2.54.0
^ permalink raw reply related
* [PATCH net] ipv6: rpl: fix hdrlen overflow in ipv6_rpl_srh_decompress()
From: HACKE-RC @ 2026-05-01 6:32 UTC (permalink / raw)
To: David S . Miller, Eric Dumazet, Jakub Kicinski, Paolo Abeni
Cc: Simon Horman, Alexander Aring, netdev, linux-kernel, HACKE-RC
ipv6_rpl_srh_decompress() computes:
outhdr->hdrlen = (((n + 1) * sizeof(struct in6_addr)) >> 3);
hdrlen is __u8. For n >= 127 the result exceeds 255 and silently
truncates. With n=127 (cmpri=15, cmpre=15, pad=0, hdrlen=16):
(128 * 16) >> 3 = 256, truncated to 0 as __u8
The caller in ipv6_rpl_srh_rcv() then places the compressed header
at buf + ((ohdr->hdrlen + 1) << 3). With hdrlen=0 this is buf + 8,
but the decompressed region occupies buf[0..2055] (8-byte header
plus 128 full addresses). The compressed header overlaps the
decompressed data, and ipv6_rpl_srh_compress() writes into this
overlap, corrupting the routing header of the forwarded packet.
The existing guard at exthdrs.c:546 checks (n + 1) > 255, which
prevents n+1 from overflowing unsigned char (the segments_left
field), but does not prevent the computed hdrlen from overflowing
__u8. n=127 passes because 128 <= 255, yet hdrlen=256 does not
fit.
Tighten the bound to (n + 1) > 127. This caps n at 126, giving
hdrlen = (127 * 16) >> 3 = 254, which fits in __u8. The compressed
header then lands at buf + ((254 + 1) << 3) = buf + 2040, exactly
past the decompressed region (buf[0..2039]). No overlap. 127
segments is well beyond any realistic RPL deployment.
Fixes: 8610c7c6e3bd ("net: ipv6: add support for rpl sr exthdr")
Signed-off-by: HACKE-RC <rc@rexion.ai>
---
net/ipv6/exthdrs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 95558fd6f..35a02584f 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -543,7 +543,7 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb)
* unsigned char which is segments_left field. Should not be
* higher than that.
*/
- if (r || (n + 1) > 255) {
+ if (r || (n + 1) > 127) {
kfree_skb(skb);
return -1;
}
--
2.54.0
^ permalink raw reply related
* [PATCH net-next 01/15] ixgbe: E610: add discovering EEE capability
From: Jacob Keller @ 2026-05-01 6:37 UTC (permalink / raw)
To: Przemek Kitszel, Andrew Lunn, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Alexander Lobakin, Simon Horman,
Michal Swiatkowski, Jedrzej Jagielski, Aleksandr Loktionov,
Grzegorz Nitka, Ivan Vecera, Arkadiusz Kubalewski, Tony Nguyen,
Stefan Wegrzyn
Cc: Piotr Kwapulinski, netdev, linux-kernel, Jacob Keller, Rinitha S
In-Reply-To: <20260430-jk-iwl-net-next-2026-04-30-v1-0-6f27ae1cd073@intel.com>
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Add detecting and parsing EEE device capability.
Recently EEE functionality support has been introduced to E610 FW.
Currently ixgbe driver has no possibility to detect whether NVM
loaded on given adapter supports EEE.
There's dedicated device capability element reflecting FW support
for given EEE link speed.
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h | 1 +
include/linux/net/intel/libie/adminq.h | 1 +
drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c | 3 +++
3 files changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index ff8d640a50b1..34f62a416eaa 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -891,6 +891,7 @@ struct ixgbe_hw_caps {
u8 apm_wol_support;
u8 acpi_prog_mthd;
u8 proxy_support;
+ u8 eee_support;
bool nvm_update_pending_nvm;
bool nvm_update_pending_orom;
bool nvm_update_pending_netlist;
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
index ab13bd777a28..839114d8975a 100644
--- a/include/linux/net/intel/libie/adminq.h
+++ b/include/linux/net/intel/libie/adminq.h
@@ -196,6 +196,7 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
#define LIBIE_AQC_BIT_ROCEV2_LAG BIT(0)
#define LIBIE_AQC_BIT_SRIOV_LAG BIT(1)
#define LIBIE_AQC_BIT_SRIOV_AA_LAG BIT(2)
+#define LIBIE_AQC_CAPS_EEE 0x009B
#define LIBIE_AQC_CAPS_FLEX10 0x00F1
#define LIBIE_AQC_CAPS_CEM 0x00F2
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index 52f73142ff75..5383f0fd55d6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -628,6 +628,9 @@ static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
(phys_id & IXGBE_EXT_TOPO_DEV_IMG_PROG_EN) != 0;
break;
}
+ case LIBIE_AQC_CAPS_EEE:
+ caps->eee_support = (u8)number;
+ break;
default:
/* Not one of the recognized common capabilities */
return false;
--
2.54.0.rc2.531.gaf818d63126a
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox