From: Jack Wang <jinpu.w...@ionos.com>
I hit following error which testing migration in pure RoCE env:
"-incoming rdma:[::]:8089: RDMA ERROR: You only have RoCE / iWARP devices in
your
systems and your management software has specified '[::]', but IPv6 over RoCE /
iWARP is not supported in Linux.#012'."
In our setup, we use rdma bind on ipv6 on target host, while connect from source
with ipv4, remove the qemu_rdma_broken_ipv6_kernel, migration just work
fine.
Checking the git history, the function was added since introducing of
rdma migration, which is more than 10 years ago. linux-rdma has
improved support on RoCE/iWARP for ipv6 over past years. There are a few fixes
back in 2016 seems related to the issue, eg:
aeb76df46d11 ("IB/core: Set routable RoCE gid type for ipv4/ipv6 networks")
other fixes back in 2018, eg:
052eac6eeb56 RDMA/cma: Update RoCE multicast routines to use net namespace
8d20a1f0ecd5 RDMA/cma: Fix rdma_cm raw IB path setting for RoCE
9327c7afdce3 RDMA/cma: Provide a function to set RoCE path record L2 parameters
5c181bda77f4 RDMA/cma: Set default GID type as RoCE when resolving RoCE route
3c7f67d1880d IB/cma: Fix default RoCE type setting
be1d325a3358 IB/core: Set RoCEv2 MGID according to spec
63a5f483af0e IB/cma: Set default gid type to RoCEv2
So remove the outdated function and it's usage.
Cc: Peter Xu <pet...@redhat.com>
Cc: Li Zhijian <lizhij...@fujitsu.com>
Cc: Yu Zhang <yu.zh...@ionos.com>
Cc: Fabiano Rosas <faro...@suse.de>
Cc: qemu-devel@nongnu.org
Cc: linux-r...@vger.kernel.org
Cc: mich...@flatgalaxy.com
Signed-off-by: Jack Wang <jinpu.w...@ionos.com>
Tested-by: Li zhijian <lizhij...@fujitsu.com>
Reviewed-by: Michael Galaxy <mrgal...@nvidia.com>
Link: https://lore.kernel.org/r/20250402051306.6509-1-jinpu.w...@ionos.com
[peterx: some cosmetic changes]
Signed-off-by: Peter Xu <pet...@redhat.com>
---
migration/rdma.c | 180 ++---------------------------------------------
1 file changed, 4 insertions(+), 176 deletions(-)
diff --git a/migration/rdma.c b/migration/rdma.c
index 4875ca1987..2d839fce6c 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -767,149 +767,6 @@ static void qemu_rdma_dump_gid(const char *who, struct
rdma_cm_id *id)
trace_qemu_rdma_dump_gid(who, sgid, dgid);
}
-/*
- * As of now, IPv6 over RoCE / iWARP is not supported by linux.
- * We will try the next addrinfo struct, and fail if there are
- * no other valid addresses to bind against.
- *
- * If user is listening on '[::]', then we will not have a opened a device
- * yet and have no way of verifying if the device is RoCE or not.
- *
- * In this case, the source VM will throw an error for ALL types of
- * connections (both IPv4 and IPv6) if the destination machine does not have
- * a regular infiniband network available for use.
- *
- * The only way to guarantee that an error is thrown for broken kernels is
- * for the management software to choose a *specific* interface at bind time
- * and validate what time of hardware it is.
- *
- * Unfortunately, this puts the user in a fix:
- *
- * If the source VM connects with an IPv4 address without knowing that the
- * destination has bound to '[::]' the migration will unconditionally fail
- * unless the management software is explicitly listening on the IPv4
- * address while using a RoCE-based device.
- *
- * If the source VM connects with an IPv6 address, then we're OK because we
can
- * throw an error on the source (and similarly on the destination).
- *
- * But in mixed environments, this will be broken for a while until it is
fixed
- * inside linux.
- *
- * We do provide a *tiny* bit of help in this function: We can list all of the
- * devices in the system and check to see if all the devices are RoCE or
- * Infiniband.
- *
- * If we detect that we have a *pure* RoCE environment, then we can safely
- * thrown an error even if the management software has specified '[::]' as the
- * bind address.
- *
- * However, if there is are multiple hetergeneous devices, then we cannot make
- * this assumption and the user just has to be sure they know what they are
- * doing.
- *
- * Patches are being reviewed on linux-rdma.
- */
-static int qemu_rdma_broken_ipv6_kernel(struct ibv_context *verbs, Error
**errp)
-{
- /* This bug only exists in linux, to our knowledge. */
-#ifdef CONFIG_LINUX
- struct ibv_port_attr port_attr;
-
- /*
- * Verbs are only NULL if management has bound to '[::]'.
- *
- * Let's iterate through all the devices and see if there any pure IB
- * devices (non-ethernet).
- *
- * If not, then we can safely proceed with the migration.
- * Otherwise, there are no guarantees until the bug is fixed in linux.
- */
- if (!verbs) {
- int num_devices;
- struct ibv_device **dev_list = ibv_get_device_list(&num_devices);
- bool roce_found = false;
- bool ib_found = false;
-
- for (int x = 0; x < num_devices; x++) {
- verbs = ibv_open_device(dev_list[x]);
- /*
- * ibv_open_device() is not documented to set errno. If
- * it does, it's somebody else's doc bug. If it doesn't,
- * the use of errno below is wrong.
- * TODO Find out whether ibv_open_device() sets errno.
- */
- if (!verbs) {
- if (errno == EPERM) {
- continue;
- } else {
- error_setg_errno(errp, errno,
- "could not open RDMA device context");
- return -1;
- }
- }
-
- if (ibv_query_port(verbs, 1, &port_attr)) {
- ibv_close_device(verbs);
- error_setg(errp,
- "RDMA ERROR: Could not query initial IB port");
- return -1;
- }
-
- if (port_attr.link_layer == IBV_LINK_LAYER_INFINIBAND) {
- ib_found = true;
- } else if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) {
- roce_found = true;
- }
-
- ibv_close_device(verbs);
-
- }
-
- if (roce_found) {
- if (ib_found) {
- warn_report("migrations may fail:"
- " IPv6 over RoCE / iWARP in linux"
- " is broken. But since you appear to have a"
- " mixed RoCE / IB environment, be sure to only"
- " migrate over the IB fabric until the kernel "
- " fixes the bug.");
- } else {
- error_setg(errp, "RDMA ERROR: "
- "You only have RoCE / iWARP devices in your systems"
- " and your management software has specified '[::]'"
- ", but IPv6 over RoCE / iWARP is not supported in
Linux.");
- return -1;
- }
- }
-
- return 0;
- }
-
- /*
- * If we have a verbs context, that means that some other than '[::]' was
- * used by the management software for binding. In which case we can
- * actually warn the user about a potentially broken kernel.
- */
-
- /* IB ports start with 1, not 0 */
- if (ibv_query_port(verbs, 1, &port_attr)) {
- error_setg(errp, "RDMA ERROR: Could not query initial IB port");
- return -1;
- }
-
- if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) {
- error_setg(errp, "RDMA ERROR: "
- "Linux kernel's RoCE / iWARP does not support IPv6 "
- "(but patches on linux-rdma in progress)");
- return -1;
- }
-
-#endif
-
- return 0;
-}
-
/*
* Figure out which RDMA device corresponds to the requested IP hostname
* Also create the initial connection manager identifiers for opening
@@ -917,7 +774,6 @@ static int qemu_rdma_broken_ipv6_kernel(struct ibv_context
*verbs, Error **errp)
*/
static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp)
{
- Error *err = NULL;
int ret;
struct rdma_addrinfo *res;
char port_str[16];
@@ -953,9 +809,8 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error
**errp)
goto err_resolve_get_addr;
}
- /* Try all addresses, saving the first error in @err */
+ /* Try all addresses, exit loop on first success of resolving address */
for (struct rdma_addrinfo *e = res; e != NULL; e = e->ai_next) {
- Error **local_errp = err ? NULL : &err;
inet_ntop(e->ai_family,
&((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip);
@@ -964,25 +819,12 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma,
Error **errp)
ret = rdma_resolve_addr(rdma->cm_id, NULL, e->ai_dst_addr,
RDMA_RESOLVE_TIMEOUT_MS);
if (ret >= 0) {
- if (e->ai_family == AF_INET6) {
- ret = qemu_rdma_broken_ipv6_kernel(rdma->cm_id->verbs,
- local_errp);
- if (ret < 0) {
- continue;
- }
- }
- error_free(err);
goto route;
}
}
rdma_freeaddrinfo(res);
- if (err) {
- error_propagate(errp, err);
- } else {
- error_setg(errp, "RDMA ERROR: could not resolve address %s",
- rdma->host);
- }
+ error_setg(errp, "RDMA ERROR: could not resolve address %s", rdma->host);
goto err_resolve_get_addr;
route:
@@ -2611,7 +2453,6 @@ err_rdma_source_connect:
static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp)
{
- Error *err = NULL;
int ret;
struct rdma_cm_id *listen_id;
char ip[40] = "unknown";
@@ -2661,9 +2502,8 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error
**errp)
goto err_dest_init_bind_addr;
}
- /* Try all addresses, saving the first error in @err */
+ /* Try all addresses */
for (e = res; e != NULL; e = e->ai_next) {
- Error **local_errp = err ? NULL : &err;
inet_ntop(e->ai_family,
&((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip);
@@ -2672,24 +2512,12 @@ static int qemu_rdma_dest_init(RDMAContext *rdma, Error
**errp)
if (ret < 0) {
continue;
}
- if (e->ai_family == AF_INET6) {
- ret = qemu_rdma_broken_ipv6_kernel(listen_id->verbs,
- local_errp);
- if (ret < 0) {
- continue;
- }
- }
- error_free(err);
break;
}
rdma_freeaddrinfo(res);
if (!e) {
- if (err) {
- error_propagate(errp, err);
- } else {
- error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!");
- }
+ error_setg(errp, "RDMA ERROR: Error: could not rdma_bind_addr!");
goto err_dest_init_bind_addr;
}
--
2.48.1
