migration/rdma.c | 157 ----------------------------------------------- 1 file changed, 157 deletions(-)
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So remove the outdated function and it's usage.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 <peterx@redhat.com>
Cc: Li Zhijian <lizhijian@fujitsu.com>
Cc: Yu Zhang <yu.zhang@ionos.com>
Cc: qemu-devel@nongnu.org
Cc: linux-rdma@vger.kernel.org
Cc: michael@flatgalaxy.com
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
---
migration/rdma.c | 157 -----------------------------------------------
1 file changed, 157 deletions(-)
diff --git a/migration/rdma.c b/migration/rdma.c
index 76fb0349238a..5ce628ddeef0 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
@@ -964,13 +821,6 @@ 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;
}
@@ -2672,13 +2522,6 @@ 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;
}
--
2.43.0
Please fix this compiling error.
cc -m64 -mcx16 -Ilibcommon.a.p -Isubprojects/libvduse -I../subprojects/libvduse -I/usr/include/p11-kit-1 -I/usr/include/pixman-1 -I/usr/include/libpng16 -I/usr/include/spice-server -I/usr/include/spice-1 -I/usr/include/libusb-1.0 -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/gio-unix-2.0 -I/usr/include/gtk-3.0 -I/usr/include/pango-1.0 -I/usr/include/harfbuzz -I/usr/include/freetype2 -I/usr/include/fribidi -I/usr/include/uuid -I/usr/include/cairo -I/usr/include/gdk-pixbuf-2.0 -I/usr/include/x86_64-linux-gnu -I/usr/include/atk-1.0 -I/usr/include/at-spi2-atk/2.0 -I/usr/include/dbus-1.0 -I/usr/lib/x86_64-linux-gnu/dbus-1.0/include -I/usr/include/at-spi-2.0 -I/usr/include/cacard -I/usr/include/nss -I/usr/include/nspr -I/usr/include/PCSC -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -fstack-protector-strong -gsplit-dwarf -Wempty-body -Wendif-labels -Wexpansion-to-defined -Wformat-security -Wformat-y2k -Wignored-qualifiers -Wimplicit-fallthrough=2 -Winit-self -Wmissing-format-attribute -Wmissing-prototypes -Wnested-externs -Wold-style-declaration -Wold-style-definition -Wredundant-decls -Wshadow=local -Wstrict-prototypes -Wtype-limits -Wundef -Wvla -Wwrite-strings -Wno-missing-include-dirs -Wno-psabi -Wno-shift-negative-value -isystem /home/lizj/workspace/qemu/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/lizj/workspace/qemu/qemu -iquote /home/lizj/workspace/qemu/qemu/include -iquote /home/lizj/workspace/qemu/qemu/host/include/x86_64 -iquote /home/lizj/workspace/qemu/qemu/host/include/generic -iquote /home/lizj/workspace/qemu/qemu/tcg/i386 -pthread -mcx16 -msse2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -fno-strict-aliasing -fno-common -fwrapv -fzero-call-used-regs=used-gpr -fPIE -D_DEFAULT_SOURCE -D_XOPEN_SOURCE=600 -DNCURSES_WIDECHAR=1 -DSTRUCT_IOVEC_DEFINED -MD -MQ libcommon.a.p/migration_rdma.c.o -MF libcommon.a.p/migration_rdma.c.o.d -o libcommon.a.p/migration_rdma.c.o -c ../migration/rdma.c
../migration/rdma.c: In function ‘qemu_rdma_resolve_host’:
../migration/rdma.c:815:17: error: unused variable ‘local_errp’ [-Werror=unused-variable]
815 | Error **local_errp = err ? NULL : &err;
| ^~~~~~~~~~
../migration/rdma.c: In function ‘qemu_rdma_dest_init’:
../migration/rdma.c:2504:17: error: unused variable ‘local_errp’ [-Werror=unused-variable]
2504 | Error **local_errp = err ? NULL : &err;
| ^~~~~~~~~~
cc1: all warnings being treated as errors
[17/19] Compiling C object qemu-img.p/qemu-img.c.o
After this fixing, feel free to add
Tested-by: Li zhijian <lizhijian@fujitsu.com>
On 26/03/2025 17:52, Jack Wang wrote:
> 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 <peterx@redhat.com>
> Cc: Li Zhijian <lizhijian@fujitsu.com>
> Cc: Yu Zhang <yu.zhang@ionos.com>
> Cc: qemu-devel@nongnu.org
> Cc: linux-rdma@vger.kernel.org
> Cc: michael@flatgalaxy.com
> Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
> ---
> migration/rdma.c | 157 -----------------------------------------------
> 1 file changed, 157 deletions(-)
>
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 76fb0349238a..5ce628ddeef0 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
> @@ -964,13 +821,6 @@ 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;
> }
> @@ -2672,13 +2522,6 @@ 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;
> }
Hi Zhijian,
On Thu, Mar 27, 2025 at 2:18 AM Zhijian Li (Fujitsu)
<lizhijian@fujitsu.com> wrote:
>
>
> Please fix this compiling error.
>
>
> cc -m64 -mcx16 -Ilibcommon.a.p -Isubprojects/libvduse -I../subprojects/libvduse -I/usr/include/p11-kit-1 -I/usr/include/pixman-1 -I/usr/include/libpng16 -I/usr/include/spice-server -I/usr/include/spice-1 -I/usr/include/libusb-1.0 -I/usr/include/glib-2.0 -I/usr/lib/x86_64-linux-gnu/glib-2.0/include -I/usr/include/libmount -I/usr/include/blkid -I/usr/include/gio-unix-2.0 -I/usr/include/gtk-3.0 -I/usr/include/pango-1.0 -I/usr/include/harfbuzz -I/usr/include/freetype2 -I/usr/include/fribidi -I/usr/include/uuid -I/usr/include/cairo -I/usr/include/gdk-pixbuf-2.0 -I/usr/include/x86_64-linux-gnu -I/usr/include/atk-1.0 -I/usr/include/at-spi2-atk/2.0 -I/usr/include/dbus-1.0 -I/usr/lib/x86_64-linux-gnu/dbus-1.0/include -I/usr/include/at-spi-2.0 -I/usr/include/cacard -I/usr/include/nss -I/usr/include/nspr -I/usr/include/PCSC -fdiagnostics-color=auto -Wall -Winvalid-pch -Werror -std=gnu11 -O2 -g -fstack-protector-strong -gsplit-dwarf -Wempty-body -Wendif-labels -Wexpansion-to-defined -Wformat-security -Wformat-y2k -Wignored-qualifiers -Wimplicit-fallthrough=2 -Winit-self -Wmissing-format-attribute -Wmissing-prototypes -Wnested-externs -Wold-style-declaration -Wold-style-definition -Wredundant-decls -Wshadow=local -Wstrict-prototypes -Wtype-limits -Wundef -Wvla -Wwrite-strings -Wno-missing-include-dirs -Wno-psabi -Wno-shift-negative-value -isystem /home/lizj/workspace/qemu/qemu/linux-headers -isystem linux-headers -iquote . -iquote /home/lizj/workspace/qemu/qemu -iquote /home/lizj/workspace/qemu/qemu/include -iquote /home/lizj/workspace/qemu/qemu/host/include/x86_64 -iquote /home/lizj/workspace/qemu/qemu/host/include/generic -iquote /home/lizj/workspace/qemu/qemu/tcg/i386 -pthread -mcx16 -msse2 -D_GNU_SOURCE -D_FILE_OFFSET_BITS=64 -D_LARGEFILE_SOURCE -fno-strict-aliasing -fno-common -fwrapv -fzero-call-used-regs=used-gpr -fPIE -D_DEFAULT_SOURCE -D_XOPEN_SOURCE=600 -DNCURSES_WIDECHAR=1 -DSTRUCT_IOVEC_DEFINED -MD -MQ libcommon.a.p/migration_rdma.c.o -MF libcommon.a.p/migration_rdma.c.o.d -o libcommon.a.p/migration_rdma.c.o -c ../migration/rdma.c
> ../migration/rdma.c: In function ‘qemu_rdma_resolve_host’:
> ../migration/rdma.c:815:17: error: unused variable ‘local_errp’ [-Werror=unused-variable]
> 815 | Error **local_errp = err ? NULL : &err;
> | ^~~~~~~~~~
> ../migration/rdma.c: In function ‘qemu_rdma_dest_init’:
> ../migration/rdma.c:2504:17: error: unused variable ‘local_errp’ [-Werror=unused-variable]
> 2504 | Error **local_errp = err ? NULL : &err;
> | ^~~~~~~~~~
> cc1: all warnings being treated as errors
> [17/19] Compiling C object qemu-img.p/qemu-img.c.o
>
>
> After this fixing, feel free to add
>
> Tested-by: Li zhijian <lizhijian@fujitsu.com>
Thx for checking, will fix them.
>
>
> On 26/03/2025 17:52, Jack Wang wrote:
> > 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 <peterx@redhat.com>
> > Cc: Li Zhijian <lizhijian@fujitsu.com>
> > Cc: Yu Zhang <yu.zhang@ionos.com>
> > Cc: qemu-devel@nongnu.org
> > Cc: linux-rdma@vger.kernel.org
> > Cc: michael@flatgalaxy.com
> > Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
> > ---
> > migration/rdma.c | 157 -----------------------------------------------
> > 1 file changed, 157 deletions(-)
> >
> > diff --git a/migration/rdma.c b/migration/rdma.c
> > index 76fb0349238a..5ce628ddeef0 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
> > @@ -964,13 +821,6 @@ 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;
> > }
> > @@ -2672,13 +2522,6 @@ 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;
> > }
Excellent find. Thank you very much for checking on the history.
Hopefully my comments were not too hard to read. =)
FYI: I've since left Akamai last year and now work at Nvidia.
Reviewed-by: Michael Galaxy <mrgalaxy@nvidia.com>
On 3/26/25 04:52, Jack Wang wrote:
> 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<peterx@redhat.com>
> Cc: Li Zhijian<lizhijian@fujitsu.com>
> Cc: Yu Zhang<yu.zhang@ionos.com>
> Cc:qemu-devel@nongnu.org
> Cc:linux-rdma@vger.kernel.org
> Cc:michael@flatgalaxy.com
> Signed-off-by: Jack Wang<jinpu.wang@ionos.com>
> ---
> migration/rdma.c | 157 -----------------------------------------------
> 1 file changed, 157 deletions(-)
>
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 76fb0349238a..5ce628ddeef0 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
> @@ -964,13 +821,6 @@ 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;
> }
> @@ -2672,13 +2522,6 @@ 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;
> }
Excellent find. Thank you very much for checking on the history.
Hopefully my comments were not too hard to read. =)
FYI: I've since left Akamai last year and now work at Nvidia.
Reviewed-by: Michael Galaxy <mrgalaxy@nvidia.com>
> On 3/26/25 04:52, Jack Wang wrote:
>> 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<peterx@redhat.com>
>> Cc: Li Zhijian<lizhijian@fujitsu.com>
>> Cc: Yu Zhang<yu.zhang@ionos.com>
>> Cc:qemu-devel@nongnu.org
>> Cc:linux-rdma@vger.kernel.org
>> Cc:michael@flatgalaxy.com
>> Signed-off-by: Jack Wang<jinpu.wang@ionos.com>
>> ---
>> migration/rdma.c | 157 -----------------------------------------------
>> 1 file changed, 157 deletions(-)
>>
>> diff --git a/migration/rdma.c b/migration/rdma.c
>> index 76fb0349238a..5ce628ddeef0 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
>> @@ -964,13 +821,6 @@ 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;
>> }
>> @@ -2672,13 +2522,6 @@ 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;
>> }
On Wed, Mar 26, 2025 at 2:47 PM Michael Galaxy <michael@flatgalaxy.com> wrote:
>
> Excellent find. Thank you very much for checking on the history. Hopefully my comments were not too hard to read. =)
Yeah, it's pretty clear.
>
> FYI: I've since left Akamai last year and now work at Nvidia.
>
> Reviewed-by: Michael Galaxy <mrgalaxy@nvidia.com>
cool, thx for the review. All the best at your new job.
>
> On 3/26/25 04:52, Jack Wang wrote:
>
> 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 <peterx@redhat.com>
> Cc: Li Zhijian <lizhijian@fujitsu.com>
> Cc: Yu Zhang <yu.zhang@ionos.com>
> Cc: qemu-devel@nongnu.org
> Cc: linux-rdma@vger.kernel.org
> Cc: michael@flatgalaxy.com
> Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
> ---
> migration/rdma.c | 157 -----------------------------------------------
> 1 file changed, 157 deletions(-)
>
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 76fb0349238a..5ce628ddeef0 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
> @@ -964,13 +821,6 @@ 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;
> }
> @@ -2672,13 +2522,6 @@ 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;
> }
© 2016 - 2025 Red Hat, Inc.