* [PATCH net-next v7 24/26] selftests/vsock: add tests for namespace deletion and mode changes
From: Bobby Eshleman @ 2025-10-21 23:47 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251021-vsock-vmtest-v7-0-0661b7b6f081@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests that validate vsock sockets are resilient to deleting
namespaces or changing namespace modes from global to local. The vsock
sockets should still function normally.
The function check_ns_changes_dont_break_connection() is added to re-use
the step-by-step logic of 1) setup connections, 2) do something that
would maybe break the connections, 3) check that the connections are
still ok.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 123 ++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 0a5751c52fa8..f8fa8b16d6e3 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -62,6 +62,12 @@ readonly TEST_NAMES=(
ns_same_local_loopback_ok
ns_same_local_host_connect_to_local_vm_ok
ns_same_local_vm_connect_to_local_host_ok
+ ns_mode_change_connection_continue_vm_ok
+ ns_mode_change_connection_continue_host_ok
+ ns_mode_change_connection_continue_both_ok
+ ns_delete_vm_ok
+ ns_delete_host_ok
+ ns_delete_both_ok
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -129,6 +135,24 @@ readonly TEST_DESCS=(
# ns_same_local_vm_connect_to_local_host_ok
"Run vsock_test client in VM in a local ns with server in same ns."
+
+ # ns_mode_change_connection_continue_vm_ok
+ "Check that changing NS mode of VM namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_host_ok
+ "Check that changing NS mode of host namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_both_ok
+ "Check that changing NS mode of host and VM namespaces from global to local after a connection is established doesn't break the connection"
+
+ # ns_delete_vm_ok
+ "Check that deleting the VM's namespace does not break the socket connection"
+
+ # ns_delete_host_ok
+ "Check that deleting the host's namespace does not break the socket connection"
+
+ # ns_delete_both_ok
+ "Check that deleting the VM and host's namespaces does not break the socket connection"
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -1141,6 +1165,105 @@ test_vm_loopback() {
return "${KSFT_PASS}"
}
+check_ns_changes_dont_break_connection() {
+ local ns0="global0"
+ local ns1="global1"
+ local port=12345
+ local pidfile
+ local outfile
+ local pids=()
+ local rc=0
+
+ init_namespaces
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ return "${KSFT_FAIL}"
+ fi
+ vm_wait_for_ssh "${ns0}"
+
+ outfile=$(mktemp)
+ vm_ssh "${ns0}" -- \
+ socat VSOCK-LISTEN:"${port}",fork STDOUT > "${outfile}" 2>/dev/null &
+ pids+=($!)
+
+ # wait_for_listener() does not work for vsock because vsock does not
+ # export socket state to /proc/net/. Instead, we have no choice but to
+ # sleep for some hardcoded time.
+ sleep ${WAIT_PERIOD}
+
+ # We use a pipe here so that we can echo into the pipe instead of
+ # using socat and a unix socket file.
+ local pipefile=$(mktemp -u /tmp/vmtest_pipe_XXXX)
+ ip netns exec "${ns1}" \
+ socat PIPE:"${pipefile}" VSOCK-CONNECT:"${VSOCK_CID}":"${port}" &
+ pids+=($!)
+
+ timeout ${WAIT_PERIOD} \
+ bash -c 'while [[ ! -e '"${pipefile}"' ]]; do sleep 1; done; exit 0'
+
+ if [[ $2 == "delete" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ip netns del "${ns0}"
+ elif [[ "$1" == "host" ]]; then
+ ip netns del "${ns1}"
+ elif [[ "$1" == "both" ]]; then
+ ip netns del "${ns0}"
+ ip netns del "${ns1}"
+ fi
+ elif [[ $2 == "change_mode" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ns_set_mode "${ns0}" "local"
+ elif [[ "$1" == "host" ]]; then
+ ns_set_mode "${ns1}" "local"
+ elif [[ "$1" == "both" ]]; then
+ ns_set_mode "${ns0}" "local"
+ ns_set_mode "${ns1}" "local"
+ fi
+ fi
+
+ echo "TEST" > "${pipefile}"
+
+ timeout ${WAIT_PERIOD} \
+ bash -c 'while [[ ! -s '"${outfile}"' ]]; do sleep 1; done; exit 0'
+
+ if grep -q "TEST" "${outfile}"; then
+ rc="${KSFT_PASS}"
+ else
+ rc="${KSFT_FAIL}"
+ fi
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pids[@]}"
+ rm -f "${outfile}"
+
+ return "${rc}"
+}
+
+test_ns_mode_change_connection_continue_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_host_ok() {
+ check_ns_changes_dont_break_connection "host" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_both_ok() {
+ check_ns_changes_dont_break_connection "both" "change_mode"
+}
+
+test_ns_delete_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "delete"
+}
+
+test_ns_delete_host_ok() {
+ check_ns_changes_dont_break_connection "host" "delete"
+}
+
+test_ns_delete_both_ok() {
+ check_ns_changes_dont_break_connection "both" "delete"
+}
+
shared_vm_test() {
local tname
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v7 26/26] selftests/vsock: add 1.37 to tested virtme-ng versions
From: Bobby Eshleman @ 2025-10-21 23:47 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251021-vsock-vmtest-v7-0-0661b7b6f081@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Testing with 1.37 shows all tests passing:
warning: vng version 'virtme-ng 1.37' has not been tested and may not function properly.
The following versions have been tested: 1.33 1.36
1..30
ok 1 vm_server_host_client
ok 2 vm_client_host_server
ok 3 vm_loopback
ok 4 ns_host_vsock_ns_mode_ok
ok 5 ns_host_vsock_ns_mode_write_once_ok
ok 6 ns_global_same_cid_fails
ok 7 ns_local_same_cid_ok
ok 8 ns_global_local_same_cid_ok
ok 9 ns_local_global_same_cid_ok
ok 10 ns_diff_global_host_connect_to_global_vm_ok
ok 11 ns_diff_global_host_connect_to_local_vm_fails
ok 12 ns_diff_global_vm_connect_to_global_host_ok
ok 13 ns_diff_global_vm_connect_to_local_host_fails
ok 14 ns_diff_local_host_connect_to_local_vm_fails
ok 15 ns_diff_local_vm_connect_to_local_host_fails
ok 16 ns_diff_global_to_local_loopback_local_fails
ok 17 ns_diff_local_to_global_loopback_fails
ok 18 ns_diff_local_to_local_loopback_fails
ok 19 ns_diff_global_to_global_loopback_ok
ok 20 ns_same_local_loopback_ok
ok 21 ns_same_local_host_connect_to_local_vm_ok
ok 22 ns_same_local_vm_connect_to_local_host_ok
ok 23 ns_mode_change_connection_continue_vm_ok
ok 24 ns_mode_change_connection_continue_host_ok
ok 25 ns_mode_change_connection_continue_both_ok
ok 26 ns_delete_vm_ok
ok 27 ns_delete_host_ok
ok 28 ns_delete_both_ok
ok 29 ns_loopback_global_global_late_module_load_ok
ok 30 ns_loopback_local_local_late_module_load_fails
This patch adds 1.37 to the virtme-ng versions to get rid of the above
warning.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 648ae71bf45a..d73fdea886fb 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -338,7 +338,7 @@ check_vng() {
local version
local ok
- tested_versions=("1.33" "1.36")
+ tested_versions=("1.33" "1.36" "1.37")
version="$(vng --version)"
ok=0
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v7 25/26] selftests/vsock: add tests for module loading order
From: Bobby Eshleman @ 2025-10-21 23:47 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251021-vsock-vmtest-v7-0-0661b7b6f081@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests to check that module loading order does not break
vsock_loopback. Because vsock_loopback has some per-namespace data
structure initialization that affects vsock namespace modes, lets make
sure that namespace modes are respected and loopback sockets are
functional even when the namespaces and modes are set prior to loading
the vsock_loopback module.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 131 ++++++++++++++++++++++++++++++++
1 file changed, 131 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index f8fa8b16d6e3..648ae71bf45a 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -68,6 +68,8 @@ readonly TEST_NAMES=(
ns_delete_vm_ok
ns_delete_host_ok
ns_delete_both_ok
+ ns_loopback_global_global_late_module_load_ok
+ ns_loopback_local_local_late_module_load_fails
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -153,6 +155,12 @@ readonly TEST_DESCS=(
# ns_delete_both_ok
"Check that deleting the VM and host's namespaces does not break the socket connection"
+
+ # ns_loopback_global_global_late_module_load_ok
+ "Test that loopback still works in global namespaces initialized prior to loading the vsock_loopback kmod"
+
+ # ns_loopback_local_local_late_module_load_fails
+ "Test that loopback connections still fail between local namespaces initialized prior to loading the vsock_loopback kmod"
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -912,6 +920,23 @@ test_ns_diff_local_vm_connect_to_local_host_fails() {
return "${KSFT_FAIL}"
}
+unload_module() {
+ local module=$1
+ local i
+
+ for ((i = 0; i < 5; i++)); do
+ modprobe -r "${module}" 2>/dev/null || :
+
+ if [[ "$(lsmod | grep -c ${module})" -eq 0 ]]; then
+ return 0
+ fi
+
+ sleep 1
+ done
+
+ return 1
+}
+
__test_loopback_two_netns() {
local ns0=$1
local ns1=$2
@@ -1264,6 +1289,112 @@ test_ns_delete_both_ok() {
check_ns_changes_dont_break_connection "both" "delete"
}
+test_ns_loopback_global_global_late_module_load_ok() {
+ declare -a pids
+ local unixfile
+ local ns0 ns1
+ local pids
+ local port
+
+ if ! unload_module vsock_loopback; then
+ log_host "Unable to unload vsock_loopback, skipping..."
+ return "${KSFT_SKIP}"
+ fi
+
+ ns0=loopback_ns0
+ ns1=loopback_ns1
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ ip netns add "${ns0}"
+ ip netns add "${ns1}"
+ ns_set_mode "${ns0}" global
+ ns_set_mode "${ns1}" global
+ ip netns exec "${ns0}" ip link set dev lo up
+ ip netns exec "${ns1}" ip link set dev lo up
+
+ modprobe vsock_loopback &> /dev/null || :
+
+ unixfile=$(mktemp -u /tmp/XXXX.sock)
+ port=321
+ ip netns exec "${ns1}" \
+ socat TCP-LISTEN:"${port}",fork \
+ UNIX-CONNECT:"${unixfile}" &
+ pids+=($!)
+
+ host_wait_for_listener "${ns1}" "${port}"
+ ip netns exec "${ns0}" socat UNIX-LISTEN:"${unixfile}",fork \
+ TCP-CONNECT:localhost:"${port}" &
+ pids+=($!)
+
+ if ! host_vsock_test "${ns0}" "server" 1 "${port}"; then
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ return "${KSFT_FAIL}"
+ fi
+
+ if ! host_vsock_test "${ns1}" "127.0.0.1" 1 "${port}"; then
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ return "${KSFT_FAIL}"
+ fi
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_loopback_local_local_late_module_load_fails() {
+ declare -a pids
+ local ns0 ns1
+ local outfile
+ local pids
+ local rc
+
+ if ! unload_module vsock_loopback; then
+ log_host "Unable to unload vsock_loopback, skipping..."
+ return "${KSFT_SKIP}"
+ fi
+
+ ns0=loopback_ns0
+ ns1=loopback_ns1
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ ip netns add "${ns0}"
+ ip netns add "${ns1}"
+ ns_set_mode "${ns0}" local
+ ns_set_mode "${ns1}" local
+
+ modprobe vsock_loopback &> /dev/null || :
+
+ outfile=$(mktemp /tmp/XXXX.vmtest.out)
+ ip netns exec "${ns0}" socat VSOCK-LISTEN:${port} STDOUT \
+ > "${outfile}" 2>/dev/null &
+ pids+=($!)
+
+ echo TEST | \
+ ip netns exec "${ns1}" socat STDIN VSOCK-CONNECT:1:${port} \
+ 2>/dev/null
+
+ if grep -q "TEST" "${outfile}" 2>/dev/null; then
+ rc="${KSFT_FAIL}"
+ else
+ rc="${KSFT_PASS}"
+ fi
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ rm -f "${outfile}"
+
+ return "${rc}"
+}
+
shared_vm_test() {
local tname
--
2.47.3
^ permalink raw reply related
* Re: [PATCH net-next v7 08/26] selftests/vsock: improve logging in vmtest.sh
From: Jakub Kicinski @ 2025-10-22 0:01 UTC (permalink / raw)
To: Bobby Eshleman
Cc: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, Eugenio Pérez, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, virtualization, netdev,
linux-kselftest, linux-kernel, kvm, linux-hyperv, berrange,
Bobby Eshleman
In-Reply-To: <20251021-vsock-vmtest-v7-8-0661b7b6f081@meta.com>
On Tue, 21 Oct 2025 16:46:51 -0700 Bobby Eshleman wrote:
> Improve usability of logging functions. Remove the test name prefix from
> logging functions so that logging calls can be made deeper into the call
> stack without passing down the test name or setting some global. Teach
> log function to accept a LOG_PREFIX variable to avoid unnecessary
> argument shifting.
>
> Remove log_setup() and instead use log_host(). The host/guest prefixes
> are useful to show whether a failure happened on the guest or host side,
> but "setup" doesn't really give additional useful information. Since all
> log_setup() calls happen on the host, lets just use log_host() instead.
And this cannot be posted separately / before the rest? I don't think
this series has to be 26 patches long.
I'm dropping this from PW, please try to obey the local customs :(
^ permalink raw reply
* Re: [PATCH net-next v7 08/26] selftests/vsock: improve logging in vmtest.sh
From: Bobby Eshleman @ 2025-10-22 0:18 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, Eugenio Pérez, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, virtualization, netdev,
linux-kselftest, linux-kernel, kvm, linux-hyperv, berrange,
Bobby Eshleman
In-Reply-To: <20251021170147.7c0d96b2@kernel.org>
On Tue, Oct 21, 2025 at 05:01:47PM -0700, Jakub Kicinski wrote:
> On Tue, 21 Oct 2025 16:46:51 -0700 Bobby Eshleman wrote:
> > Improve usability of logging functions. Remove the test name prefix from
> > logging functions so that logging calls can be made deeper into the call
> > stack without passing down the test name or setting some global. Teach
> > log function to accept a LOG_PREFIX variable to avoid unnecessary
> > argument shifting.
> >
> > Remove log_setup() and instead use log_host(). The host/guest prefixes
> > are useful to show whether a failure happened on the guest or host side,
> > but "setup" doesn't really give additional useful information. Since all
> > log_setup() calls happen on the host, lets just use log_host() instead.
>
> And this cannot be posted separately / before the rest? I don't think
> this series has to be 26 patches long.
>
> I'm dropping this from PW, please try to obey the local customs :(
Sorry about that, since these selftest changes were all part of one
messier patch in the previous rev, I wasn't sure if the custom was to
keep them in the original series or break them out into another series.
I'll break them out and resend.
^ permalink raw reply
* Re: [PATCH net-next] net: mana: Linearize SKB if TX SGEs exceeds hardware limit
From: Aditya Garg @ 2025-10-22 16:44 UTC (permalink / raw)
To: Eric Dumazet
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, kuba, pabeni,
longli, kotaranov, horms, shradhagupta, ernis, dipayanroy,
shirazsaleem, linux-hyperv, netdev, linux-kernel, linux-rdma,
gargaditya, ssengar
In-Reply-To: <CANn89iKFsuUnwMb-upqwswrCYaTL-MXVwsQdxFhduZeZRAJZ2A@mail.gmail.com>
On 17-10-2025 23:36, Eric Dumazet wrote:
> On Fri, Oct 17, 2025 at 10:41 AM Aditya Garg
> <gargaditya@linux.microsoft.com> wrote:
>>
>> On 08-10-2025 20:58, Aditya Garg wrote:
>>> On 08-10-2025 20:51, Eric Dumazet wrote:
>>>> On Wed, Oct 8, 2025 at 8:16 AM Aditya Garg
>>>> <gargaditya@linux.microsoft.com> wrote:
>>>>>
>>>>> On 03-10-2025 21:45, Eric Dumazet wrote:
>>>>>> On Fri, Oct 3, 2025 at 8:47 AM Aditya Garg
>>>>>> <gargaditya@linux.microsoft.com> wrote:
>>>>>>>
>>>>>>> The MANA hardware supports a maximum of 30 scatter-gather entries
>>>>>>> (SGEs)
>>>>>>> per TX WQE. In rare configurations where MAX_SKB_FRAGS + 2 exceeds
>>>>>>> this
>>>>>>> limit, the driver drops the skb. Add a check in mana_start_xmit() to
>>>>>>> detect such cases and linearize the SKB before transmission.
>>>>>>>
>>>>>>> Return NETDEV_TX_BUSY only for -ENOSPC from
>>>>>>> mana_gd_post_work_request(),
>>>>>>> send other errors to free_sgl_ptr to free resources and record the tx
>>>>>>> drop.
>>>>>>>
>>>>>>> Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
>>>>>>> Reviewed-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
>>>>>>> ---
>>>>>>> drivers/net/ethernet/microsoft/mana/mana_en.c | 26 +++++++++++++
>>>>>>> ++----
>>>>>>> include/net/mana/gdma.h | 8 +++++-
>>>>>>> include/net/mana/mana.h | 1 +
>>>>>>> 3 files changed, 29 insertions(+), 6 deletions(-)
>>>>>>>
>>>>>>> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/
>>>>>>> drivers/net/ethernet/microsoft/mana/mana_en.c
>>>>>>> index f4fc86f20213..22605753ca84 100644
>>>>>>> --- a/drivers/net/ethernet/microsoft/mana/mana_en.c
>>>>>>> +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
>>>>>>> @@ -20,6 +20,7 @@
>>>>>>>
>>>>>>> #include <net/mana/mana.h>
>>>>>>> #include <net/mana/mana_auxiliary.h>
>>>>>>> +#include <linux/skbuff.h>
>>>>>>>
>>>>>>> static DEFINE_IDA(mana_adev_ida);
>>>>>>>
>>>>>>> @@ -289,6 +290,19 @@ netdev_tx_t mana_start_xmit(struct sk_buff
>>>>>>> *skb, struct net_device *ndev)
>>>>>>> cq = &apc->tx_qp[txq_idx].tx_cq;
>>>>>>> tx_stats = &txq->stats;
>>>>>>>
>>>>>>> + BUILD_BUG_ON(MAX_TX_WQE_SGL_ENTRIES !=
>>>>>>> MANA_MAX_TX_WQE_SGL_ENTRIES);
>>>>>>> + #if (MAX_SKB_FRAGS + 2 > MANA_MAX_TX_WQE_SGL_ENTRIES)
>>>>>>> + if (skb_shinfo(skb)->nr_frags + 2 >
>>>>>>> MANA_MAX_TX_WQE_SGL_ENTRIES) {
>>>>>>> + netdev_info_once(ndev,
>>>>>>> + "nr_frags %d exceeds max
>>>>>>> supported sge limit. Attempting skb_linearize\n",
>>>>>>> + skb_shinfo(skb)->nr_frags);
>>>>>>> + if (skb_linearize(skb)) {
>>>>>>
>>>>>> This will fail in many cases.
>>>>>>
>>>>>> This sort of check is better done in ndo_features_check()
>>>>>>
>>>>>> Most probably this would occur for GSO packets, so can ask a software
>>>>>> segmentation
>>>>>> to avoid this big and risky kmalloc() by all means.
>>>>>>
>>>>>> Look at idpf_features_check() which has something similar.
>>>>>
>>>>> Hi Eric,
>>>>> Thank you for your review. I understand your concerns regarding the use
>>>>> of skb_linearize() in the xmit path, as it can fail under memory
>>>>> pressure and introduces additional overhead in the transmit path. Based
>>>>> on your input, I will work on a v2 that will move the SGE limit check to
>>>>> the ndo_features_check() path and for GSO skbs exceding the hw limit
>>>>> will disable the NETIF_F_GSO_MASK to enforce software segmentation in
>>>>> kernel before the call to xmit.
>>>>> Also for non GSO skb exceeding the SGE hw limit should we go for using
>>>>> skb_linearize only then or would you suggest some other approach here?
>>>>
>>>> I think that for non GSO, the linearization attempt is fine.
>>>>
>>>> Note that this is extremely unlikely for non malicious users,
>>>> and MTU being usually small (9K or less),
>>>> the allocation will be much smaller than a GSO packet.
>>>
>>> Okay. Will send a v2
>> Hi Eric,
>> I tested the code by disabling GSO in ndo_features_check when the number
>> of SGEs exceeds the hardware limit, using iperf for a single TCP
>> connection with zerocopy enabled. I noticed a significant difference in
>> throughput compared to when we linearize the skbs.
>> For reference, the throughput is 35.6 Gbits/sec when using
>> skb_linearize, but drops to 6.75 Gbits/sec when disabling GSO per skb.
>
> You must be doing something very wrong.
>
> Difference between TSO and non TSO should not be that high.
>
> ethtool -K eth0 tso on
> netperf -H tjbp27
> MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> tjbp27.prod.google.com () port 0 AF_INET6
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 540000 262144 262144 10.00 92766.69
>
>
> ethtool -K eth0 tso off
> netperf -H tjbp27
> MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> tjbp27.prod.google.com () port 0 AF_INET6
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 540000 262144 262144 10.00 52218.97
>
> Now if I force linearization, you can definitely see the very high
> cost of the copies !
>
> ethtool -K eth1 sg off
> tjbp26:/home/edumazet# ./netperf -H tjbp27
> MIGRATED TCP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> tjbp27.prod.google.com () port 0 AF_INET6
> Recv Send Send
> Socket Socket Message Elapsed
> Size Size Size Time Throughput
> bytes bytes bytes secs. 10^6bits/sec
>
> 540000 262144 262144 10.00 16951.32
>
>>
>> Hence, We propose to linearizing skbs until the first failure occurs.
>
> Hmm... basically hiding a bug then ?
>
>> After that, we switch to a fail-safe mode by disabling GSO for SKBs with
>> sge > hw limit using the ndo_feature_check implementation, while
>> continuing to apply skb_linearize() for non-GSO packets that exceed the
>> hardware limit. This ensures we remain on the optimal performance path
>> initially, and only transition to the fail-safe path after encountering
>> a failure.
>
> Please post your patch (adding the check in ndo_features_check()),
> perhaps one of us is able to help.
Okay Eric, I'll Post a v2 with RFC. Please let me know.
Regards,
Aditya
^ permalink raw reply
* [RFC PATCH net-next v2] net: mana: Handle SKB if TX SGEs exceed hardware limit
From: Aditya Garg @ 2025-10-22 20:43 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, pabeni, longli, kotaranov, horms, shradhagupta, ssengar,
ernis, dipayanroy, shirazsaleem, gargaditya, linux-hyperv, netdev,
linux-kernel, linux-rdma, gargaditya
The MANA hardware supports a maximum of 30 scatter-gather entries (SGEs)
per TX WQE. Exceeding this limit can cause TX failures.
Add ndo_features_check() callback to validate SKB layout before
transmission. For GSO SKBs that would exceed the hardware SGE limit, clear
NETIF_F_GSO_MASK to enforce software segmentation in the stack.
Add a fallback in mana_start_xmit() to linearize non-GSO SKBs that still
exceed the SGE limit.
Return NETDEV_TX_BUSY only for -ENOSPC from mana_gd_post_work_request(),
send other errors to free_sgl_ptr to free resources and record the tx
drop.
Co-developed-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Signed-off-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 48 +++++++++++++++++--
include/net/mana/gdma.h | 6 ++-
include/net/mana/mana.h | 1 +
3 files changed, 49 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 0142fd98392c..8e23a87a779d 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -11,6 +11,7 @@
#include <linux/mm.h>
#include <linux/pci.h>
#include <linux/export.h>
+#include <linux/skbuff.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
@@ -289,6 +290,21 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
cq = &apc->tx_qp[txq_idx].tx_cq;
tx_stats = &txq->stats;
+ if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES &&
+ skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+ /* GSO skb with Hardware SGE limit exceeded is not expected here
+ * as they are handled in mana_features_check() callback
+ */
+ if (skb_is_gso(skb))
+ netdev_warn_once(ndev, "GSO enabled skb exceeds max SGE limit\n");
+ if (skb_linearize(skb)) {
+ netdev_warn_once(ndev, "Failed to linearize skb with nr_frags=%d and is_gso=%d\n",
+ skb_shinfo(skb)->nr_frags,
+ skb_is_gso(skb));
+ goto tx_drop_count;
+ }
+ }
+
pkg.tx_oob.s_oob.vcq_num = cq->gdma_id;
pkg.tx_oob.s_oob.vsq_frame = txq->vsq_frame;
@@ -402,8 +418,6 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
}
}
- WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES);
-
if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) {
pkg.wqe_req.sgl = pkg.sgl_array;
} else {
@@ -438,9 +452,13 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
if (err) {
(void)skb_dequeue_tail(&txq->pending_skbs);
+ mana_unmap_skb(skb, apc);
netdev_warn(ndev, "Failed to post TX OOB: %d\n", err);
- err = NETDEV_TX_BUSY;
- goto tx_busy;
+ if (err == -ENOSPC) {
+ err = NETDEV_TX_BUSY;
+ goto tx_busy;
+ }
+ goto free_sgl_ptr;
}
err = NETDEV_TX_OK;
@@ -478,6 +496,25 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
return NETDEV_TX_OK;
}
+static netdev_features_t mana_features_check(struct sk_buff *skb,
+ struct net_device *ndev,
+ netdev_features_t features)
+{
+ if (MAX_SKB_FRAGS + 2 > MAX_TX_WQE_SGL_ENTRIES &&
+ skb_shinfo(skb)->nr_frags + 2 > MAX_TX_WQE_SGL_ENTRIES) {
+ /* Exceeds HW SGE limit.
+ * GSO case:
+ * Disable GSO so the stack will software-segment the skb
+ * into smaller skbs that fit the SGE budget.
+ * Non-GSO case:
+ * The xmit path will attempt skb_linearize() as a fallback.
+ */
+ if (skb_is_gso(skb))
+ features &= ~NETIF_F_GSO_MASK;
+ }
+ return features;
+}
+
static void mana_get_stats64(struct net_device *ndev,
struct rtnl_link_stats64 *st)
{
@@ -838,6 +875,7 @@ static const struct net_device_ops mana_devops = {
.ndo_open = mana_open,
.ndo_stop = mana_close,
.ndo_select_queue = mana_select_queue,
+ .ndo_features_check = mana_features_check,
.ndo_start_xmit = mana_start_xmit,
.ndo_validate_addr = eth_validate_addr,
.ndo_get_stats64 = mana_get_stats64,
@@ -1606,7 +1644,7 @@ static int mana_move_wq_tail(struct gdma_queue *wq, u32 num_units)
return 0;
}
-static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc)
{
struct mana_skb_head *ash = (struct mana_skb_head *)skb->head;
struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 57df78cfbf82..b35ecc58fbab 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -591,6 +591,9 @@ enum {
/* Driver can self reset on FPGA Reconfig EQE notification */
#define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17)
+/* Driver supports linearizing the skb when num_sge exceeds hardware limit */
+#define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20)
+
#define GDMA_DRV_CAP_FLAGS1 \
(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
@@ -599,7 +602,8 @@ enum {
GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \
GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \
GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \
- GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE)
+ GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \
+ GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE)
#define GDMA_DRV_CAP_FLAGS2 0
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 0921485565c0..330e1bb088bb 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -580,6 +580,7 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed,
void mana_query_phy_stats(struct mana_port_context *apc);
int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
+void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc);
extern const struct ethtool_ops mana_ethtool_ops;
extern struct dentry *mana_debugfs_root;
--
2.43.0
^ permalink raw reply related
* Re: [PATCH v2 2/2] hyperv: Enable clean shutdown for root partition with MSHV
From: Praveen Paladugu @ 2025-10-22 21:26 UTC (permalink / raw)
To: Michael Kelley
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, tglx@linutronix.de, mingo@redhat.com,
linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
hpa@zytor.com, arnd@arndb.de, anbelski@linux.microsoft.com,
easwar.hariharan@linux.microsoft.com,
nunodasneves@linux.microsoft.com,
skinsburskii@linux.microsoft.com
In-Reply-To: <BN7PR02MB41485DB7E9B53B4CEDA596EAD4F5A@BN7PR02MB4148.namprd02.prod.outlook.com>
On Mon, Oct 20, 2025 at 05:30:44PM +0000, Michael Kelley wrote:
> From: Praveen Paladugu <prapal@linux.microsoft.com> Sent: Monday, October 20, 2025 9:00 AM
> >
> > On Thu, Oct 16, 2025 at 07:29:06PM +0000, Michael Kelley wrote:
> > > From: Praveen K Paladugu <prapal@linux.microsoft.com> Sent: Tuesday, October 14, 2025 9:41 AM
> > > >
>
> [snip]
>
> > > > +static int hv_call_enter_sleep_state(u32 sleep_state)
> > > > +{
> > > > + u64 status;
> > > > + int ret;
> > > > + unsigned long flags;
> > > > + struct hv_input_enter_sleep_state *in;
> > > > +
> > > > + ret = hv_initialize_sleep_states();
> > > > + if (ret)
> > > > + return ret;
> > > > +
> > > > + local_irq_save(flags);
> > > > + in = *this_cpu_ptr(hyperv_pcpu_input_arg);
> > > > + in->sleep_state = sleep_state;
> > > > +
> > > > + status = hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
> > >
> > > If this hypercall succeeds, does the root partition (which is the caller) go
> > > to sleep in S5, such that the hypercall never returns? If that's not the case,
> > > what is the behavior of this hypercall?
> > >
> > This hypercall returns to the kernel when the CPU wakes up the next
> > time.
>
> I must be missing something about the big picture, because "returns to
> the kernel when the CPU wakes up" doesn't fit my mental model of what's
> going on. I thought this function would be called, and the hypercall made,
> when Linux in the root partition is shutting down. So if a CPU makes this
> hypercall and goes to sleep, what wakes it up? And when it wakes up, is it
> still running the same Linux instance that was shutting down, or has it
> rebooted into new Linux instance? In the latter case, returning from
> the hypercall doesn't make sense.
>
> Can you explain further how this all works?
>
Sorry for the confusion here. I mis-understood what happens while
entering the sleep state here. I will clarify below:
Sleep state S5 refers to shutdown/poweroff. Although other sleep states
are handled, they are not properly applied while running mshv on
servers. Non-S5 sleep states are only applied on non-server hosts.
This patch only handles S5 sleep state.
If a hypercall for non-S5 sleep state is invoked, the control
is returned back to the kernel. Usually non-S5 sleep state do things
like suspend to memory/hibernate etc.
If the hypecall is for S5 sleep state, then Hypervisor does poweroff the
host and the control does not return back to the kernel.
Now that is clarified, your previous comments about the order of the
reboot_notifiers is relevant now. I will investigate how to apply a
priority/order so that hv_reboot_notifier_handler will be called last.
Praveen
> Michael
>
> >
> > > > + local_irq_restore(flags);
> > > > +
> > > > + if (!hv_result_success(status)) {
> > > > + hv_status_err(status, "\n");
> > > > + return hv_result_to_errno(status);
> > > > + }
> > > > +
> > > > + return 0;
> > > > +}
> > > > +
> > > > +static int hv_reboot_notifier_handler(struct notifier_block *this,
> > > > + unsigned long code, void *another)
> > > > +{
> > > > + int ret = 0;
> > > > +
> > > > + if (code == SYS_HALT || code == SYS_POWER_OFF)
> > > > + ret = hv_call_enter_sleep_state(HV_SLEEP_STATE_S5);
> > >
> > > If hv_call_enter_sleep_state() never returns, here's an issue. There may be
> > > multiple entries on the reboot notifier chain. For example,
> > > mshv_root_partition_init() puts an entry on the reboot notifier chain. At
> > > reboot time, the entries are executed in some order, with the expectation
> > > that all entries will be executed prior to the reboot actually happening. But
> > > if this hypercall never returns, some entries may never be executed.
> > >
> > > Notifier chains support a notion of priority to control the order in
> > > which they are executed, but that priority isn't set in hv_reboot_notifier
> > > below, or in mshv_reboot_nb. And most other reboot notifiers throughout
> > > Linux appear to not set it. So the ordering is unspecified, and having
> > > this notifier never return may be problematic.
> > >
> > Thanks for the detailed explanation Michael!
> >
> > As I mentioned above, this hypercall returns to the kernel, so the rest
> > of the entries in the notifier chain should continue to execute.
> >
> > > > +
> > > > + return ret ? NOTIFY_DONE : NOTIFY_OK;
> > > > +}
> > > > +
> > > > +static struct notifier_block hv_reboot_notifier = {
> > > > + .notifier_call = hv_reboot_notifier_handler,
> > > > +};
> > > > +
> > > > +static int hv_acpi_sleep_handler(u8 sleep_state, u32 pm1a_cnt, u32 pm1b_cnt)
> > > > +{
> > > > + int ret = 0;
> > > > +
> > > > + if (sleep_state == ACPI_STATE_S5)
> > > > + ret = hv_call_enter_sleep_state(HV_SLEEP_STATE_S5);
> > > > +
> > > > + return ret == 0 ? 1 : -1;
> > > > +}
> > > > +
> > > > +static int hv_acpi_extended_sleep_handler(u8 sleep_state, u32 val_a, u32 val_b)
> > > > +{
> > > > + return hv_acpi_sleep_handler(sleep_state, val_a, val_b);
> > > > +}
> > >
> > > Is this function needed? The function signature is identical to hv_acpi_sleep_handler().
> > > So it seems like acpi_os_set_prepare_extended_sleep() could just use
> > > hv_acpi_sleep_handler() directly.
> > >
> > Upon further investigation, I discovered that extended sleep is only
> > supported on platforms with ACPI_REDUCED_HARDWARE.
> >
> > As these patches are targetted at X86, above does not really apply. I
> > will drop this handler in next version.
> >
> > > > +
> > > > +int hv_sleep_notifiers_register(void)
> > > > +{
> > > > + int ret;
> > > > +
> > > > + acpi_os_set_prepare_sleep(&hv_acpi_sleep_handler);
> > > > + acpi_os_set_prepare_extended_sleep(&hv_acpi_extended_sleep_handler);
> > >
> > > I'm not clear on why these handlers are set. If the hv_reboot_notifier is
> > > called, are these ACPI handlers ever called? Or are these to catch any cases
> > > where the hv_reboot_notifier is somehow bypassed? Or maybe I'm just
> > > not understanding something .... :-)
> > >
> >
> > I am trying to trace these calls. I will keep you posted with my
> > findings.
> >
> > > > +
> > > > + ret = register_reboot_notifier(&hv_reboot_notifier);
> > > > + if (ret)
> > > > + pr_err("%s: cannot register reboot notifier %d\n",
> > > > + __func__, ret);
> > > > +
> > > > + return ret;
> > > > +}
> > > > +#endif
> > >
> > > I'm wondering if all this code belongs in hv_common.c, since it is only needed
> > > for Linux in the root partition. Couldn't it go in mshv_common.c? It would still
> > > be built-in code (i.e., not in a loadable module), but only if CONFIG_MSHV_ROOT
> > > is set.
> > >
> >
> > This sounds reasonable. I will discuss this internally and get back you.
> >
> > > Michael
> > >
> > > > --
> > > > 2.51.0
> > > >
^ permalink raw reply
* Re: [PATCH v2 2/2] hyperv: Enable clean shutdown for root partition with MSHV
From: Praveen Paladugu @ 2025-10-22 21:30 UTC (permalink / raw)
To: Michael Kelley
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, tglx@linutronix.de, mingo@redhat.com,
linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
hpa@zytor.com, arnd@arndb.de, anbelski@linux.microsoft.com,
easwar.hariharan@linux.microsoft.com,
nunodasneves@linux.microsoft.com,
skinsburskii@linux.microsoft.com
In-Reply-To: <SN6PR02MB4157FBBE5B77C65B024D3589D4E9A@SN6PR02MB4157.namprd02.prod.outlook.com>
On Thu, Oct 16, 2025 at 07:29:06PM +0000, Michael Kelley wrote:
> From: Praveen K Paladugu <prapal@linux.microsoft.com> Sent: Tuesday, October 14, 2025 9:41 AM
> >
> > When a shutdown is initiated in the root partition without configuring
> > sleep states, the call to `hv_call_enter_sleep_state` fails. In such cases
> > the root falls back to using legacy ACPI mechanisms to poweroff. This call
> > is intercepted by MSHV and will result in a Machine Check Exception (MCE).
> >
> > Root panics with a trace similar to:
> >
> > [ 81.306348] reboot: Power down
> > [ 81.314709] mce: [Hardware Error]: CPU 0: Machine Check Exception: 4 Bank 0: b2000000c0060001
> > [ 81.314711] mce: [Hardware Error]: TSC 3b8cb60a66 PPIN 11d98332458e4ea9
> > [ 81.314713] mce: [Hardware Error]: PROCESSOR 0:606a6 TIME 1759339405 SOCKET 0 APIC 0 microcode ffffffff
> > [ 81.314715] mce: [Hardware Error]: Run the above through 'mcelog --ascii'
> > [ 81.314716] mce: [Hardware Error]: Machine check: Processor context corrupt
> > [ 81.314717] Kernel panic - not syncing: Fatal machine check
> >
> > To prevent this, properly configure sleep states within MSHV, allowing
> > the root partition to shut down cleanly without triggering a panic.
> >
> > Signed-off-by: Praveen K Paladugu <prapal@linux.microsoft.com>
> > Co-developed-by: Anatol Belski <anbelski@linux.microsoft.com>
> > Signed-off-by: Anatol Belski <anbelski@linux.microsoft.com>
> > ---
> > arch/x86/hyperv/hv_init.c | 7 ++
> > arch/x86/include/asm/mshyperv.h | 1 +
> > drivers/hv/hv_common.c | 119 ++++++++++++++++++++++++++++++++
> > 3 files changed, 127 insertions(+)
> >
> > diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
> > index afdbda2dd7b7..57bd96671ead 100644
> > --- a/arch/x86/hyperv/hv_init.c
> > +++ b/arch/x86/hyperv/hv_init.c
> > @@ -510,6 +510,13 @@ void __init hyperv_init(void)
> > memunmap(src);
> >
> > hv_remap_tsc_clocksource();
> > + /*
> > + * The notifier registration might fail at various hops.
> > + * Corresponding error messages will land in dmesg. There is
> > + * otherwise nothing that can be specifically done to handle
> > + * failures here.
> > + */
> > + (void)hv_sleep_notifiers_register();
> > } else {
> > hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
> > wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
> > diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> > index abc4659f5809..fb8d691193df 100644
> > --- a/arch/x86/include/asm/mshyperv.h
> > +++ b/arch/x86/include/asm/mshyperv.h
> > @@ -236,6 +236,7 @@ int hyperv_fill_flush_guest_mapping_list(
> > void hv_apic_init(void);
> > void __init hv_init_spinlocks(void);
> > bool hv_vcpu_is_preempted(int vcpu);
> > +int hv_sleep_notifiers_register(void);
> > #else
> > static inline void hv_apic_init(void) {}
> > #endif
> > diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
> > index e109a620c83f..cfba9ded7bcb 100644
> > --- a/drivers/hv/hv_common.c
> > +++ b/drivers/hv/hv_common.c
> > @@ -837,3 +837,122 @@ const char *hv_result_to_string(u64 status)
> > return "Unknown";
> > }
> > EXPORT_SYMBOL_GPL(hv_result_to_string);
> > +
> > +#if IS_ENABLED(CONFIG_ACPI)
> > +/*
> > + * Corresponding sleep states have to be initialized in order for a subsequent
> > + * HVCALL_ENTER_SLEEP_STATE call to succeed. Currently only S5 state as per
> > + * ACPI 6.4 chapter 7.4.2 is relevant, while S1, S2 and S3 can be supported.
> > + *
> > + * ACPI should be initialized and should support S5 sleep state when this method
> > + * is called, so that it can extract correct PM values and pass them to hv.
> > + */
> > +static int hv_initialize_sleep_states(void)
> > +{
> > + u64 status;
> > + unsigned long flags;
> > + struct hv_input_set_system_property *in;
> > + acpi_status acpi_status;
> > + u8 sleep_type_a, sleep_type_b;
> > +
> > + if (!acpi_sleep_state_supported(ACPI_STATE_S5)) {
> > + pr_err("%s: S5 sleep state not supported.\n", __func__);
> > + return -ENODEV;
> > + }
> > +
> > + acpi_status = acpi_get_sleep_type_data(ACPI_STATE_S5,
> > + &sleep_type_a, &sleep_type_b);
> > + if (ACPI_FAILURE(acpi_status))
> > + return -ENODEV;
> > +
> > + local_irq_save(flags);
> > + in = *this_cpu_ptr(hyperv_pcpu_input_arg);
> > + memset(in, 0, sizeof(*in));
> > +
> > + in->property_id = HV_SYSTEM_PROPERTY_SLEEP_STATE;
> > + in->set_sleep_state_info.sleep_state = HV_SLEEP_STATE_S5;
> > + in->set_sleep_state_info.pm1a_slp_typ = sleep_type_a;
> > + in->set_sleep_state_info.pm1b_slp_typ = sleep_type_b;
> > +
> > + status = hv_do_hypercall(HVCALL_SET_SYSTEM_PROPERTY, in, NULL);
> > + local_irq_restore(flags);
> > +
> > + if (!hv_result_success(status)) {
> > + hv_status_err(status, "\n");
> > + return hv_result_to_errno(status);
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static int hv_call_enter_sleep_state(u32 sleep_state)
> > +{
> > + u64 status;
> > + int ret;
> > + unsigned long flags;
> > + struct hv_input_enter_sleep_state *in;
> > +
> > + ret = hv_initialize_sleep_states();
> > + if (ret)
> > + return ret;
> > +
> > + local_irq_save(flags);
> > + in = *this_cpu_ptr(hyperv_pcpu_input_arg);
> > + in->sleep_state = sleep_state;
> > +
> > + status = hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
>
> If this hypercall succeeds, does the root partition (which is the caller) go
> to sleep in S5, such that the hypercall never returns? If that's not the case,
> what is the behavior of this hypercall?
>
> > + local_irq_restore(flags);
> > +
> > + if (!hv_result_success(status)) {
> > + hv_status_err(status, "\n");
> > + return hv_result_to_errno(status);
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static int hv_reboot_notifier_handler(struct notifier_block *this,
> > + unsigned long code, void *another)
> > +{
> > + int ret = 0;
> > +
> > + if (code == SYS_HALT || code == SYS_POWER_OFF)
> > + ret = hv_call_enter_sleep_state(HV_SLEEP_STATE_S5);
>
> If hv_call_enter_sleep_state() never returns, here's an issue. There may be
> multiple entries on the reboot notifier chain. For example,
> mshv_root_partition_init() puts an entry on the reboot notifier chain. At
> reboot time, the entries are executed in some order, with the expectation
> that all entries will be executed prior to the reboot actually happening. But
> if this hypercall never returns, some entries may never be executed.
>
> Notifier chains support a notion of priority to control the order in
> which they are executed, but that priority isn't set in hv_reboot_notifier
> below, or in mshv_reboot_nb. And most other reboot notifiers throughout
> Linux appear to not set it. So the ordering is unspecified, and having
> this notifier never return may be problematic.
>
> > +
> > + return ret ? NOTIFY_DONE : NOTIFY_OK;
> > +}
> > +
> > +static struct notifier_block hv_reboot_notifier = {
> > + .notifier_call = hv_reboot_notifier_handler,
> > +};
> > +
> > +static int hv_acpi_sleep_handler(u8 sleep_state, u32 pm1a_cnt, u32 pm1b_cnt)
> > +{
> > + int ret = 0;
> > +
> > + if (sleep_state == ACPI_STATE_S5)
> > + ret = hv_call_enter_sleep_state(HV_SLEEP_STATE_S5);
> > +
> > + return ret == 0 ? 1 : -1;
> > +}
> > +
> > +static int hv_acpi_extended_sleep_handler(u8 sleep_state, u32 val_a, u32 val_b)
> > +{
> > + return hv_acpi_sleep_handler(sleep_state, val_a, val_b);
> > +}
>
> Is this function needed? The function signature is identical to hv_acpi_sleep_handler().
> So it seems like acpi_os_set_prepare_extended_sleep() could just use
> hv_acpi_sleep_handler() directly.
>
I confirmed that hv_acpi_xxx_handler methods are not really necessary.
They are usually invoked by `pm_suspend`, when the host is be put into a
non-S5 sleep state. As non-S5 sleep states are not supported by mshv, I
will drop these handlers in next revision.
> > +
> > +int hv_sleep_notifiers_register(void)
> > +{
> > + int ret;
> > +
> > + acpi_os_set_prepare_sleep(&hv_acpi_sleep_handler);
> > + acpi_os_set_prepare_extended_sleep(&hv_acpi_extended_sleep_handler);
>
> I'm not clear on why these handlers are set. If the hv_reboot_notifier is
> called, are these ACPI handlers ever called? Or are these to catch any cases
> where the hv_reboot_notifier is somehow bypassed? Or maybe I'm just
> not understanding something .... :-)
>
> > +
> > + ret = register_reboot_notifier(&hv_reboot_notifier);
> > + if (ret)
> > + pr_err("%s: cannot register reboot notifier %d\n",
> > + __func__, ret);
> > +
> > + return ret;
> > +}
> > +#endif
>
> I'm wondering if all this code belongs in hv_common.c, since it is only needed
> for Linux in the root partition. Couldn't it go in mshv_common.c? It would still
> be built-in code (i.e., not in a loadable module), but only if CONFIG_MSHV_ROOT
> is set.
>
> Michael
>
> > --
> > 2.51.0
> >
^ permalink raw reply
* Re: [PATCH 2/2] net: mana: Add standard counter rx_missed_errors
From: Erni Sri Satya Vennela @ 2025-10-23 5:31 UTC (permalink / raw)
To: Paolo Abeni
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
kuba, longli, kotaranov, horms, shradhagupta, dipayanroy,
shirazsaleem, rosenp, linux-hyperv, netdev, linux-kernel,
linux-rdma
In-Reply-To: <0b5b0d1d-438a-4e41-99c8-a6f61d7581b4@redhat.com>
On Tue, Sep 16, 2025 at 03:22:54PM +0200, Paolo Abeni wrote:
> On 9/15/25 5:58 AM, Erni Sri Satya Vennela wrote:
> > Report standard counter stats->rx_missed_errors
> > using hc_rx_discards_no_wqe from the hardware.
> >
> > Add a dedicated workqueue to periodically run
> > mana_query_gf_stats every 2 seconds to get the latest
> > info in eth_stats and define a driver capability flag
> > to notify hardware of the periodic queries.
> >
> > To avoid repeated failures and log flooding, the workqueue
> > is not rescheduled if mana_query_gf_stats fails.
>
> Can the failure root cause be a "transient" one? If so, this looks like
> a dangerous strategy; is such scenario, AFAICS, stats will be broken
> until the device is removed and re-probed.
>
> /P
After internal discussion, We are planning to fix this issue following
the below approach:
Stop rescheduling the work queue only upon detecting HWC timeout.
In this case:
1. Reset all stats to zero to avoid stale reporting.
2. Introduce a driver flag to detect the first occurrence of HWC timeout.
3. Log a warn_once during subsequent calls to mana_get_stats64 to signal
the issue.
Thanks,
Vennela
^ permalink raw reply
* Re: [PATCH v9 0/2] Drivers: hv: Introduce new driver - mshv_vtl
From: Naman Jain @ 2025-10-23 15:21 UTC (permalink / raw)
To: Michael Kelley, Peter Zijlstra, Sean Christopherson,
Paolo Bonzini
Cc: linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
x86@kernel.org, Mukesh Rathor, Stanislav Kinsburskii,
Nuno Das Neves, Christoph Hellwig, Saurabh Sengar, ALOK TIWARI,
K . Y . Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen,
H . Peter Anvin
In-Reply-To: <SN6PR02MB4157AE454F412993BC1D4BFDD4F6A@SN6PR02MB4157.namprd02.prod.outlook.com>
On 10/18/2025 12:02 AM, Michael Kelley wrote:
> From: Naman Jain <namjain@linux.microsoft.com> Sent: Friday, October 17, 2025 12:45 AM
>>
>> Introduce a new mshv_vtl driver to provide an interface for Virtual
>> Machine Monitor like OpenVMM and its use as OpenHCL paravisor to
>> control VTL0 (Virtual trust Level).
>> Expose devices and support IOCTLs for features like VTL creation,
>> VTL0 memory management, context switch, making hypercalls,
>> mapping VTL0 address space to VTL2 userspace, getting new VMBus
>> messages and channel events in VTL2 etc.
>>
>> OpenVMM : https://openvmm.dev/guide/
>>
>> Changes since v8:
>> https://lore.kernel.org/all/20251013060353.67326-1-namjain@linux.microsoft.com/
>> Addressed Sean's comments:
>> * Removed forcing SIGPENDING, and other minor changes, in
>> mshv_vtl_ioctl_return_to_lower_vtl after referring
>> to Sean's earlier changes for xfer_to_guest_mode_handle_work.
>>
>> * Rebased and resolved merge conflicts, compilation errors on latest
>> linux-next kernel tip, after Roman's Confidential VM changes,
>> which merged recently. No functional changes.
>
> Did your testing against the latest linux-next included testing with
> CONFIG_X86_KERNEL_IBT=y? This is Indirect Branch Tracking, which would
> have generated a fault with your v7 series and earlier because of the indirect
> call instruction when doing VTL Return through the hypercall page (which
> doesn't have the needed ENDBR64 instruction). But now that VTL Return is
> doing a static call, that should be direct, which won't trigger an IBT fault.
>
> To confirm that you really are running with IBT enabled, you should see
>
> [ 0.047008] CET detected: Indirect Branch Tracking enabled
>
> in the VTL2 dmesg output. And "ibt" should appear in the
> "flags" output line of 'cat /proc/cpuinfo' (or the 'lscpu' command).
>
> Michael
Hi Michael,
I have now tested with and without IBT, and in case of IBT enabled, I do
see the log you pasted for IBT in VTL2 logs and there are no failures.
However, this additional testing uncovered another issue here where
there is a crash in VTL0, some time after boot, due to rbp clobbering in
mshv_vtl_return_hypercall() wrapper function.
Thanks a lot Michael for helping me offline on this, to understand and
identify the issue.
Hi Peter, Paolo, Sean,
Here is the summary of the problem and the fix:
Assembly code make a call to mshv_vtl_return_hypercall() after handling
rbp properly. However, current wrapper function in C updates rbp to rsp
before making the static call. This creates problems.
<-snippet->
arch/x86/hyperv/mshv_vtl_asm.S:
/* make a hypercall to switch VTL */
call mshv_vtl_return_hypercall
arch/x86/hyperv/hv_vtl.c:
noinstr void mshv_vtl_return_hypercall(void)
{
asm volatile ("call " STATIC_CALL_TRAMP_STR(__mshv_vtl_return_hypercall) :
ASM_CALL_CONSTRAINT);
}
(gdb) disassemble mshv_vtl_return_hypercall
Dump of assembler code for function mshv_vtl_return_hypercall:
0xffffffff886981a0 <+0>: push %rbp
0xffffffff886981a1 <+1>: mov %rsp,%rbp
0xffffffff886981a4 <+4>: call 0xffffffff886a77a8
<__SCT____mshv_vtl_return_hypercall>
0xffffffff886981a9 <+9>: pop %rbp
0xffffffff886981aa <+10>: jmp 0xffffffff886a7670
<__x86_return_thunk>
<-end->
This is fixed after removing ASM_CALL_CONSTRAINT from above function
which makes sure it does not add save/restore rbp logic before the
assembly call instructions.
<-snippet->
(gdb) disassemble mshv_vtl_return_hypercall
Dump of assembler code for function mshv_vtl_return_hypercall:
0xffffffff886981a0 <+0>: call 0xffffffff886a77a8
<__SCT____mshv_vtl_return_hypercall>
0xffffffff886981a5 <+5>: jmp 0xffffffff886a7670
<__x86_return_thunk>
End of assembler dump.
<-end->
But then we see a warning reported by objtool for frame pointer, but
since this is expected, I will need to add STACK_FRAME_NON_STANDARD_FP
to suppress it.
vmlinux.o: warning: objtool: mshv_vtl_return_hypercall+0x4: call without
frame pointer save/setup
During code review, I found CR2 handling was missing after making
mshv_vtl_return_hypercall call in assembly, which I will *additionally*
fix in next version.
Pasting the diff at the end, on top of this patch, which should fix
these issues.
Please let me know if I should be doing it differently or if you foresee
any issues with this approach.
Regards,
Naman
------------------------
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 636e9253b81e..c61d2dce4d68 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -258,9 +258,9 @@ DEFINE_STATIC_CALL_NULL(__mshv_vtl_return_hypercall,
void (*)(void));
noinstr void mshv_vtl_return_hypercall(void)
{
- asm volatile ("call "
STATIC_CALL_TRAMP_STR(__mshv_vtl_return_hypercall) :
- ASM_CALL_CONSTRAINT);
+ asm volatile ("call "
STATIC_CALL_TRAMP_STR(__mshv_vtl_return_hypercall));
}
+STACK_FRAME_NON_STANDARD_FP(mshv_vtl_return_hypercall);
extern void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0);
diff --git a/arch/x86/hyperv/mshv_vtl_asm.S b/arch/x86/hyperv/mshv_vtl_asm.S
index 4085073a5876..5f4b511749f8 100644
--- a/arch/x86/hyperv/mshv_vtl_asm.S
+++ b/arch/x86/hyperv/mshv_vtl_asm.S
@@ -65,6 +65,9 @@ SYM_FUNC_START(__mshv_vtl_return_call)
mov 16(%rsp), %rcx
mov 24(%rsp), %rax
+ mov %rdx, MSHV_VTL_CPU_CONTEXT_rdx(%rax)
+ mov %cr2, %rdx
+ mov %rdx, MSHV_VTL_CPU_CONTEXT_cr2(%rax)
pop MSHV_VTL_CPU_CONTEXT_rcx(%rax)
pop MSHV_VTL_CPU_CONTEXT_rax(%rax)
add $16, %rsp
^ permalink raw reply related
* [PATCH net-next v8 00/14] vsock: add namespace support to vhost-vsock
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
This series adds namespace support to vhost-vsock and loopback. It does
not add namespaces to any of the other guest transports (virtio-vsock,
hyperv, or vmci).
The current revision supports two modes: local and global. Local
mode is complete isolation of namespaces, while global mode is complete
sharing between namespaces of CIDs (the original behavior).
The mode is set using /proc/sys/net/vsock/ns_mode.
Modes are per-netns and write-once. This allows a system to configure
namespaces independently (some may share CIDs, others are completely
isolated). This also supports future possible mixed use cases, where
there may be namespaces in global mode spinning up VMs while there are
mixed mode namespaces that provide services to the VMs, but are not
allowed to allocate from the global CID pool (this mode not implemented
in this series).
If a socket or VM is created when a namespace is global but the
namespace changes to local, the socket or VM will continue working
normally. That is, the socket or VM assumes the mode behavior of the
namespace at the time the socket/VM was created. The original mode is
captured in vsock_create() and so occurs at the time of socket(2) and
accept(2) for sockets and open(2) on /dev/vhost-vsock for VMs. This
prevents a socket/VM connection from suddenly breaking due to a
namespace mode change. Any new sockets/VMs created after the mode change
will adopt the new mode's behavior.
Additionally, added tests for the new namespace features:
tools/testing/selftests/vsock/vmtest.sh
1..30
ok 1 vm_server_host_client
ok 2 vm_client_host_server
ok 3 vm_loopback
ok 4 ns_host_vsock_ns_mode_ok
ok 5 ns_host_vsock_ns_mode_write_once_ok
ok 6 ns_global_same_cid_fails
ok 7 ns_local_same_cid_ok
ok 8 ns_global_local_same_cid_ok
ok 9 ns_local_global_same_cid_ok
ok 10 ns_diff_global_host_connect_to_global_vm_ok
ok 11 ns_diff_global_host_connect_to_local_vm_fails
ok 12 ns_diff_global_vm_connect_to_global_host_ok
ok 13 ns_diff_global_vm_connect_to_local_host_fails
ok 14 ns_diff_local_host_connect_to_local_vm_fails
ok 15 ns_diff_local_vm_connect_to_local_host_fails
ok 16 ns_diff_global_to_local_loopback_local_fails
ok 17 ns_diff_local_to_global_loopback_fails
ok 18 ns_diff_local_to_local_loopback_fails
ok 19 ns_diff_global_to_global_loopback_ok
ok 20 ns_same_local_loopback_ok
ok 21 ns_same_local_host_connect_to_local_vm_ok
ok 22 ns_same_local_vm_connect_to_local_host_ok
ok 23 ns_mode_change_connection_continue_vm_ok
ok 24 ns_mode_change_connection_continue_host_ok
ok 25 ns_mode_change_connection_continue_both_ok
ok 26 ns_delete_vm_ok
ok 27 ns_delete_host_ok
ok 28 ns_delete_both_ok
ok 29 ns_loopback_global_global_late_module_load_ok
ok 30 ns_loopback_local_local_late_module_load_fails
SUMMARY: PASS=30 SKIP=0 FAIL=0
Dependent on series:
https://lore.kernel.org/all/20251022-vsock-selftests-fixes-and-improvements-v1-0-edeb179d6463@meta.com/
Thanks again for everyone's help and reviews!
Signed-off-by: Bobby Eshleman <bobbyeshleman@gmail.com>
To: Stefano Garzarella <sgarzare@redhat.com>
To: Shuah Khan <shuah@kernel.org>
To: David S. Miller <davem@davemloft.net>
To: Eric Dumazet <edumazet@google.com>
To: Jakub Kicinski <kuba@kernel.org>
To: Paolo Abeni <pabeni@redhat.com>
To: Simon Horman <horms@kernel.org>
To: Stefan Hajnoczi <stefanha@redhat.com>
To: Michael S. Tsirkin <mst@redhat.com>
To: Jason Wang <jasowang@redhat.com>
To: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: Eugenio Pérez <eperezma@redhat.com>
To: K. Y. Srinivasan <kys@microsoft.com>
To: Haiyang Zhang <haiyangz@microsoft.com>
To: Wei Liu <wei.liu@kernel.org>
To: Dexuan Cui <decui@microsoft.com>
To: Bryan Tan <bryan-bt.tan@broadcom.com>
To: Vishnu Dasa <vishnu.dasa@broadcom.com>
To: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
Cc: virtualization@lists.linux.dev
Cc: netdev@vger.kernel.org
Cc: linux-kselftest@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: kvm@vger.kernel.org
Cc: linux-hyperv@vger.kernel.org
Cc: berrange@redhat.com
Changes in v8:
- Break generic cleanup/refactoring patches into standalone series,
remove those from this series
- Link to dependency: https://lore.kernel.org/all/20251022-vsock-selftests-fixes-and-improvements-v1-0-edeb179d6463@meta.com/
- Link to v7: https://lore.kernel.org/r/20251021-vsock-vmtest-v7-0-0661b7b6f081@meta.com
Changes in v7:
- fix hv_sock build
- break out vmtest patches into distinct, more well-scoped patches
- change `orig_net_mode` to `net_mode`
- many fixes and style changes in per-patch change sets (see individual
patches for specific changes)
- optimize `virtio_vsock_skb_cb` layout
- update commit messages with more useful descriptions
- vsock_loopback: use orig_net_mode instead of current net mode
- add tests for edge cases (ns deletion, mode changing, loopback module
load ordering)
- Link to v6: https://lore.kernel.org/r/20250916-vsock-vmtest-v6-0-064d2eb0c89d@meta.com
Changes in v6:
- define behavior when mode changes to local while socket/VM is alive
- af_vsock: clarify description of CID behavior
- af_vsock: use stronger langauge around CID rules (dont use "may")
- af_vsock: improve naming of buf/buffer
- af_vsock: improve string length checking on proc writes
- vsock_loopback: add space in struct to clarify lock protection
- vsock_loopback: do proper cleanup/unregister on vsock_loopback_exit()
- vsock_loopback: use virtio_vsock_skb_net() instead of sock_net()
- vsock_loopback: set loopback to NULL after kfree()
- vsock_loopback: use pernet_operations and remove callback mechanism
- vsock_loopback: add macros for "global" and "local"
- vsock_loopback: fix length checking
- vmtest.sh: check for namespace support in vmtest.sh
- Link to v5: https://lore.kernel.org/r/20250827-vsock-vmtest-v5-0-0ba580bede5b@meta.com
Changes in v5:
- /proc/net/vsock_ns_mode -> /proc/sys/net/vsock/ns_mode
- vsock_global_net -> vsock_global_dummy_net
- fix netns lookup in vhost_vsock to respect pid namespaces
- add callbacks for vsock_loopback to avoid circular dependency
- vmtest.sh loads vsock_loopback module
- remove vsock_net_mode_can_set()
- change vsock_net_write_mode() to return true/false based on success
- make vsock_net_mode enum instead of u8
- Link to v4: https://lore.kernel.org/r/20250805-vsock-vmtest-v4-0-059ec51ab111@meta.com
Changes in v4:
- removed RFC tag
- implemented loopback support
- renamed new tests to better reflect behavior
- completed suite of tests with permutations of ns modes and vsock_test
as guest/host
- simplified socat bridging with unix socket instead of tcp + veth
- only use vsock_test for success case, socat for failure case (context
in commit message)
- lots of cleanup
Changes in v3:
- add notion of "modes"
- add procfs /proc/net/vsock_ns_mode
- local and global modes only
- no /dev/vhost-vsock-netns
- vmtest.sh already merged, so new patch just adds new tests for NS
- Link to v2:
https://lore.kernel.org/kvm/20250312-vsock-netns-v2-0-84bffa1aa97a@gmail.com
Changes in v2:
- only support vhost-vsock namespaces
- all g2h namespaces retain old behavior, only common API changes
impacted by vhost-vsock changes
- add /dev/vhost-vsock-netns for "opt-in"
- leave /dev/vhost-vsock to old behavior
- removed netns module param
- Link to v1:
https://lore.kernel.org/r/20200116172428.311437-1-sgarzare@redhat.com
Changes in v1:
- added 'netns' module param to vsock.ko to enable the
network namespace support (disabled by default)
- added 'vsock_net_eq()' to check the "net" assigned to a socket
only when 'netns' support is enabled
- Link to RFC: https://patchwork.ozlabs.org/cover/1202235/
---
Bobby Eshleman (14):
vsock: a per-net vsock NS mode state
vsock/virtio: pack struct virtio_vsock_skb_cb
vsock: add netns to vsock skb cb
vsock: add netns to vsock core
vsock/loopback: add netns support
vsock/virtio: add netns to virtio transport common
vhost/vsock: add netns support
selftests/vsock: add namespace helpers to vmtest.sh
selftests/vsock: prepare vm management helpers for namespaces
selftests/vsock: add tests for proc sys vsock ns_mode
selftests/vsock: add namespace tests for CID collisions
selftests/vsock: add tests for host <-> vm connectivity with namespaces
selftests/vsock: add tests for namespace deletion and mode changes
selftests/vsock: add tests for module loading order
MAINTAINERS | 1 +
drivers/vhost/vsock.c | 48 +-
include/linux/virtio_vsock.h | 47 +-
include/net/af_vsock.h | 70 ++-
include/net/net_namespace.h | 4 +
include/net/netns/vsock.h | 22 +
net/vmw_vsock/af_vsock.c | 264 +++++++-
net/vmw_vsock/virtio_transport.c | 7 +-
net/vmw_vsock/virtio_transport_common.c | 21 +-
net/vmw_vsock/vsock_loopback.c | 89 ++-
tools/testing/selftests/vsock/vmtest.sh | 1044 ++++++++++++++++++++++++++++++-
11 files changed, 1532 insertions(+), 85 deletions(-)
---
base-commit: 962ac5ca99a5c3e7469215bf47572440402dfd59
change-id: 20250325-vsock-vmtest-b3a21d2102c2
prerequisite-message-id: <20251022-vsock-selftests-fixes-and-improvements-v1-0-edeb179d6463@meta.com>
prerequisite-patch-id: a2eecc3851f2509ed40009a7cab6990c6d7cfff5
prerequisite-patch-id: 501db2100636b9c8fcb3b64b8b1df797ccbede85
prerequisite-patch-id: ba1a2f07398a035bc48ef72edda41888614be449
prerequisite-patch-id: fd5cc5445aca9355ce678e6d2bfa89fab8a57e61
prerequisite-patch-id: 795ab4432ffb0843e22b580374782e7e0d99b909
prerequisite-patch-id: 1499d263dc933e75366c09e045d2125ca39f7ddd
prerequisite-patch-id: f92d99bb1d35d99b063f818a19dcda999152d74c
prerequisite-patch-id: e3296f38cdba6d903e061cff2bbb3e7615e8e671
prerequisite-patch-id: bc4662b4710d302d4893f58708820fc2a0624325
prerequisite-patch-id: f8991f2e98c2661a706183fde6b35e2b8d9aedcf
prerequisite-patch-id: 44bf9ed69353586d284e5ee63d6fffa30439a698
prerequisite-patch-id: d50621bc630eeaf608bbaf260370c8dabf6326df
Best regards,
--
Bobby Eshleman <bobbyeshleman@meta.com>
^ permalink raw reply
* [PATCH net-next v8 01/14] vsock: a per-net vsock NS mode state
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add the per-net vsock NS mode state. This only adds the structure for
holding the mode and some of the functions for setting/getting and
checking the mode, but does not integrate the functionality yet.
A "net_mode" field is added to vsock_sock to store the mode of the
namespace when the vsock_sock was created. In order to evaluate
namespace mode rules we need to know both a) which namespace the
endpoints are in, and b) what mode that namespace had when the endpoints
were created. This allows us to handle the changing of modes from global
to local *after* a socket has been created by remembering that the mode
was global when the socket was created. If we were to use the current
net's mode instead, then the lookup would fail and the socket would
break.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- clarify vsock_net_check_mode() comments
- change to `orig_net_mode == VSOCK_NET_MODE_GLOBAL && orig_net_mode == vsk->orig_net_mode`
- remove extraneous explanation of `orig_net_mode`
- rename `written` to `mode_locked`
- rename `vsock_hdr` to `sysctl_hdr`
- change `orig_net_mode` to `net_mode`
- make vsock_net_check_mode() more generic by taking just net pointers
and modes, instead of a vsock_sock ptr, for reuse by transports
(e.g., vhost_vsock)
Changes in v6:
- add orig_net_mode to store mode at creation time which will be used to
avoid breakage when namespace changes mode during socket/VM lifespan
Changes in v5:
- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
- change from net->vsock.ns_mode to net->vsock.mode
- change vsock_net_set_mode() to vsock_net_write_mode()
- vsock_net_write_mode() returns bool for write success to avoid
need to use vsock_net_mode_can_set()
- remove vsock_net_mode_can_set()
---
MAINTAINERS | 1 +
include/net/af_vsock.h | 56 +++++++++++++++++++++++++++++++++++++++++++++
include/net/net_namespace.h | 4 ++++
include/net/netns/vsock.h | 20 ++++++++++++++++
4 files changed, 81 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index ea72b3bd2248..dd765bbf79ab 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27070,6 +27070,7 @@ L: netdev@vger.kernel.org
S: Maintained
F: drivers/vhost/vsock.c
F: include/linux/virtio_vsock.h
+F: include/net/netns/vsock.h
F: include/uapi/linux/virtio_vsock.h
F: net/vmw_vsock/virtio_transport.c
F: net/vmw_vsock/virtio_transport_common.c
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index d40e978126e3..bce5389ef742 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -10,6 +10,7 @@
#include <linux/kernel.h>
#include <linux/workqueue.h>
+#include <net/netns/vsock.h>
#include <net/sock.h>
#include <uapi/linux/vm_sockets.h>
@@ -65,6 +66,7 @@ struct vsock_sock {
u32 peer_shutdown;
bool sent_request;
bool ignore_connecting_rst;
+ enum vsock_net_mode net_mode;
/* Protected by lock_sock(sk) */
u64 buffer_size;
@@ -256,4 +258,58 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
{
return t->msgzerocopy_allow && t->msgzerocopy_allow();
}
+
+static inline enum vsock_net_mode vsock_net_mode(struct net *net)
+{
+ enum vsock_net_mode ret;
+
+ spin_lock_bh(&net->vsock.lock);
+ ret = net->vsock.mode;
+ spin_unlock_bh(&net->vsock.lock);
+ return ret;
+}
+
+static inline bool vsock_net_write_mode(struct net *net, u8 mode)
+{
+ bool ret;
+
+ spin_lock_bh(&net->vsock.lock);
+
+ if (net->vsock.mode_locked) {
+ ret = false;
+ goto skip;
+ }
+
+ net->vsock.mode = mode;
+ net->vsock.mode_locked = true;
+ ret = true;
+
+skip:
+ spin_unlock_bh(&net->vsock.lock);
+ return ret;
+}
+
+/* Return true if two namespaces and modes pass the mode rules. Otherwise,
+ * return false.
+ *
+ * ns0 and ns1 are the namespaces being checked.
+ * mode0 and mode1 are the vsock namespace modes of ns0 and ns1.
+ *
+ * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c.
+ */
+static inline bool vsock_net_check_mode(struct net *ns0, enum vsock_net_mode mode0,
+ struct net *ns1, enum vsock_net_mode mode1)
+{
+ /* Any vsocks within the same network namespace are always reachable,
+ * regardless of the mode.
+ */
+ if (net_eq(ns0, ns1))
+ return true;
+
+ /*
+ * If the network namespaces differ, vsocks are only reachable if both
+ * were created in VSOCK_NET_MODE_GLOBAL mode.
+ */
+ return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1;
+}
#endif /* __AF_VSOCK_H__ */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index cb664f6e3558..66d3de1d935f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -37,6 +37,7 @@
#include <net/netns/smc.h>
#include <net/netns/bpf.h>
#include <net/netns/mctp.h>
+#include <net/netns/vsock.h>
#include <net/net_trackers.h>
#include <linux/ns_common.h>
#include <linux/idr.h>
@@ -196,6 +197,9 @@ struct net {
/* Move to a better place when the config guard is removed. */
struct mutex rtnl_mutex;
#endif
+#if IS_ENABLED(CONFIG_VSOCKETS)
+ struct netns_vsock vsock;
+#endif
} __randomize_layout;
#include <linux/seq_file_net.h>
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
new file mode 100644
index 000000000000..c9a438ad52f2
--- /dev/null
+++ b/include/net/netns/vsock.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_NET_NAMESPACE_VSOCK_H
+#define __NET_NET_NAMESPACE_VSOCK_H
+
+#include <linux/types.h>
+
+enum vsock_net_mode {
+ VSOCK_NET_MODE_GLOBAL,
+ VSOCK_NET_MODE_LOCAL,
+};
+
+struct netns_vsock {
+ struct ctl_table_header *sysctl_hdr;
+ spinlock_t lock;
+
+ /* protected by lock */
+ enum vsock_net_mode mode;
+ bool mode_locked;
+};
+#endif /* __NET_NET_NAMESPACE_VSOCK_H */
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 02/14] vsock/virtio: pack struct virtio_vsock_skb_cb
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Reduce holes in struct virtio_vsock_skb_cb. As this struct continues to
grow, we want to keep it trimmed down so it doesn't exceed the size of
skb->cb (currently 48 bytes). Eliminating the 2 byte hole provides an
additional two bytes for new fields at the end of the structure. It does
not shrink the total size, however.
Future work could include combining fields like reply and tap_delivered
into a single bitfield, but currently doing so will not make the total
struct size smaller (although, would extend the tail-end padding area by
one byte).
Before this patch:
struct virtio_vsock_skb_cb {
bool reply; /* 0 1 */
bool tap_delivered; /* 1 1 */
/* XXX 2 bytes hole, try to pack */
u32 offset; /* 4 4 */
/* size: 8, cachelines: 1, members: 3 */
/* sum members: 6, holes: 1, sum holes: 2 */
/* last cacheline: 8 bytes */
};
;
After this patch:
struct virtio_vsock_skb_cb {
u32 offset; /* 0 4 */
bool reply; /* 4 1 */
bool tap_delivered; /* 5 1 */
/* size: 8, cachelines: 1, members: 3 */
/* padding: 2 */
/* last cacheline: 8 bytes */
};
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
include/linux/virtio_vsock.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 0c67543a45c8..87cf4dcac78a 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -10,9 +10,9 @@
#define VIRTIO_VSOCK_SKB_HEADROOM (sizeof(struct virtio_vsock_hdr))
struct virtio_vsock_skb_cb {
+ u32 offset;
bool reply;
bool tap_delivered;
- u32 offset;
};
#define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb))
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 03/14] vsock: add netns to vsock skb cb
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add a net pointer and net_mode to the vsock skb and helpers for
getting/setting them. When skbs are received the transport needs a way
to tell the vsock layer and/or virtio common layer which namespace and
what namespace mode the packet belongs to. This will be used by those
upper layers for finding the correct socket object. This patch stashes
these fields in the skb control buffer.
This extends virtio_vsock_skb_cb to 24 bytes:
struct virtio_vsock_skb_cb {
struct net * net; /* 0 8 */
enum vsock_net_mode net_mode; /* 8 4 */
u32 offset; /* 12 4 */
bool reply; /* 16 1 */
bool tap_delivered; /* 17 1 */
/* size: 24, cachelines: 1, members: 5 */
/* padding: 6 */
/* last cacheline: 24 bytes */
};
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- rename `orig_net_mode` to `net_mode`
- update commit message with a more complete explanation of changes
Changes in v5:
- some diff context change due to rebase to current net-next
---
include/linux/virtio_vsock.h | 23 +++++++++++++++++++++++
1 file changed, 23 insertions(+)
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 87cf4dcac78a..7f334a32133c 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -10,6 +10,8 @@
#define VIRTIO_VSOCK_SKB_HEADROOM (sizeof(struct virtio_vsock_hdr))
struct virtio_vsock_skb_cb {
+ struct net *net;
+ enum vsock_net_mode net_mode;
u32 offset;
bool reply;
bool tap_delivered;
@@ -130,6 +132,27 @@ static inline size_t virtio_vsock_skb_len(struct sk_buff *skb)
return (size_t)(skb_end_pointer(skb) - skb->head);
}
+static inline struct net *virtio_vsock_skb_net(struct sk_buff *skb)
+{
+ return VIRTIO_VSOCK_SKB_CB(skb)->net;
+}
+
+static inline void virtio_vsock_skb_set_net(struct sk_buff *skb, struct net *net)
+{
+ VIRTIO_VSOCK_SKB_CB(skb)->net = net;
+}
+
+static inline enum vsock_net_mode virtio_vsock_skb_net_mode(struct sk_buff *skb)
+{
+ return VIRTIO_VSOCK_SKB_CB(skb)->net_mode;
+}
+
+static inline void virtio_vsock_skb_set_net_mode(struct sk_buff *skb,
+ enum vsock_net_mode net_mode)
+{
+ VIRTIO_VSOCK_SKB_CB(skb)->net_mode = net_mode;
+}
+
/* Dimension the RX SKB so that the entire thing fits exactly into
* a single 4KiB page. This avoids wasting memory due to alloc_skb()
* rounding up to the next page order and also means that we
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 04/14] vsock: add netns to vsock core
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add netns logic to vsock core. Additionally, modify transport hook
prototypes to be used by later transport-specific patches (e.g.,
*_seqpacket_allow()).
Namespaces are supported primarily by changing socket lookup functions
(e.g., vsock_find_connected_socket()) to take into account the socket
namespace and the namespace mode before considering a candidate socket a
"match".
Introduce a dummy namespace struct, __vsock_global_dummy_net, to be
used by transports that do not support namespacing. This dummy always
has mode "global" to preserve previous CID behavior.
This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode that
accepts the "global" or "local" mode strings.
The transports (besides vhost) are modified to use the global dummy,
which makes them behave as if always in the global namespace. Vhost is
an exception because it inherits its namespace from the process that
opens the vhost device.
Add netns functionality (initialization, passing to transports, procfs,
etc...) to the af_vsock socket layer. Later patches that add netns
support to transports depend on this patch.
seqpacket_allow() callbacks are modified to take a vsk so that transport
implementations can inspect sock_net(sk) and vsk->net_mode when performing
lookups (e.g., vhost does this in its future netns patch). Because the
API change affects all transports, it seemed more appropriate to make
this internal API change in the "vsock core" patch then in the "vhost"
patch.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- hv_sock: fix hyperv build error
- explain why vhost does not use the dummy
- explain usage of __vsock_global_dummy_net
- explain why VSOCK_NET_MODE_STR_MAX is 8 characters
- use switch-case in vsock_net_mode_string()
- avoid changing transports as much as possible
- add vsock_find_{bound,connected}_socket_net()
- rename `vsock_hdr` to `sysctl_hdr`
- add virtio_vsock_alloc_linear_skb() wrapper for setting dummy net and
global mode for virtio-vsock, move skb->cb zero-ing into wrapper
- explain seqpacket_allow() change
- move net setting to __vsock_create() instead of vsock_create() so
that child sockets also have their net assigned upon accept()
Changes in v6:
- unregister sysctl ops in vsock_exit()
- af_vsock: clarify description of CID behavior
- af_vsock: fix buf vs buffer naming, and length checking
- af_vsock: fix length checking w/ correct ctl_table->maxlen
Changes in v5:
- vsock_global_net() -> vsock_global_dummy_net()
- update comments for new uAPI
- use /proc/sys/net/vsock/ns_mode instead of /proc/net/vsock_ns_mode
- add prototype changes so patch remains compilable
---
drivers/vhost/vsock.c | 4 +-
include/linux/virtio_vsock.h | 21 ++++
include/net/af_vsock.h | 14 ++-
net/vmw_vsock/af_vsock.c | 264 ++++++++++++++++++++++++++++++++++++---
net/vmw_vsock/virtio_transport.c | 7 +-
net/vmw_vsock/vsock_loopback.c | 4 +-
6 files changed, 288 insertions(+), 26 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ae01457ea2cd..34adf0cf9124 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -404,7 +404,7 @@ static bool vhost_transport_msgzerocopy_allow(void)
return true;
}
-static bool vhost_transport_seqpacket_allow(u32 remote_cid);
+static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
static struct virtio_transport vhost_transport = {
.transport = {
@@ -460,7 +460,7 @@ static struct virtio_transport vhost_transport = {
.send_pkt = vhost_transport_send_pkt,
};
-static bool vhost_transport_seqpacket_allow(u32 remote_cid)
+static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
struct vhost_vsock *vsock;
bool seqpacket_allow = false;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 7f334a32133c..29290395054c 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -153,6 +153,27 @@ static inline void virtio_vsock_skb_set_net_mode(struct sk_buff *skb,
VIRTIO_VSOCK_SKB_CB(skb)->net_mode = net_mode;
}
+static inline struct sk_buff *
+virtio_vsock_alloc_rx_skb(unsigned int size, gfp_t mask)
+{
+ struct sk_buff *skb;
+
+ skb = virtio_vsock_alloc_linear_skb(size, mask);
+ if (!skb)
+ return NULL;
+
+ memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM);
+
+ /* virtio-vsock does not yet support namespaces, so on receive
+ * we force legacy namespace behavior using the global dummy net
+ * and global net mode.
+ */
+ virtio_vsock_skb_set_net(skb, vsock_global_dummy_net());
+ virtio_vsock_skb_set_net_mode(skb, VSOCK_NET_MODE_GLOBAL);
+
+ return skb;
+}
+
/* Dimension the RX SKB so that the entire thing fits exactly into
* a single 4KiB page. This avoids wasting memory due to alloc_skb()
* rounding up to the next page order and also means that we
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index bce5389ef742..69bb70c3c0fd 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -145,7 +145,7 @@ struct vsock_transport {
int flags);
int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg,
size_t len);
- bool (*seqpacket_allow)(u32 remote_cid);
+ bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid);
u32 (*seqpacket_has_data)(struct vsock_sock *vsk);
/* Notification. */
@@ -218,6 +218,12 @@ void vsock_remove_connected(struct vsock_sock *vsk);
struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr);
struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
struct sockaddr_vm *dst);
+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, struct net *net,
+ enum vsock_net_mode net_mode);
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode);
void vsock_remove_sock(struct vsock_sock *vsk);
void vsock_for_each_connected_socket(struct vsock_transport *transport,
void (*fn)(struct sock *sk));
@@ -259,6 +265,12 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t)
return t->msgzerocopy_allow && t->msgzerocopy_allow();
}
+extern struct net __vsock_global_dummy_net;
+static inline struct net *vsock_global_dummy_net(void)
+{
+ return &__vsock_global_dummy_net;
+}
+
static inline enum vsock_net_mode vsock_net_mode(struct net *net)
{
enum vsock_net_mode ret;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 4c2db6cca557..656a78810c68 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -83,6 +83,35 @@
* TCP_ESTABLISHED - connected
* TCP_CLOSING - disconnecting
* TCP_LISTEN - listening
+ *
+ * - Namespaces in vsock support two different modes configured
+ * through /proc/sys/net/vsock/ns_mode. The modes are "local" and "global".
+ * Each mode defines how the namespace interacts with CIDs.
+ * /proc/sys/net/vsock/ns_mode is write-once, so that it may be configured
+ * and locked down by a namespace manager. The default is "global". The mode
+ * is set per-namespace.
+ *
+ * The modes affect the allocation and accessibility of CIDs as follows:
+ *
+ * - global - access and allocation are all system-wide
+ * - all CID allocation from global namespaces draw from the same
+ * system-wide pool
+ * - if one global namespace has already allocated some CID, another
+ * global namespace will not be able to allocate the same CID
+ * - global mode AF_VSOCK sockets can reach any VM or socket in any global
+ * namespace, they are not contained to only their own namespace
+ * - AF_VSOCK sockets in a global mode namespace cannot reach VMs or
+ * sockets in any local mode namespace
+ * - local - access and allocation are contained within the namespace
+ * - CID allocation draws only from a private pool local only to the
+ * namespace, and does not affect the CIDs available for allocation in any
+ * other namespace (global or local)
+ * - VMs in a local namespace do not collide with CIDs in any other local
+ * namespace or any global namespace. For example, if a VM in a local mode
+ * namespace is given CID 10, then CID 10 is still available for
+ * allocation in any other namespace, but not in the same namespace
+ * - AF_VSOCK sockets in a local mode namespace can connect only to VMs or
+ * other sockets within their own namespace.
*/
#include <linux/compat.h>
@@ -100,6 +129,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/net.h>
+#include <linux/proc_fs.h>
#include <linux/poll.h>
#include <linux/random.h>
#include <linux/skbuff.h>
@@ -111,9 +141,18 @@
#include <linux/workqueue.h>
#include <net/sock.h>
#include <net/af_vsock.h>
+#include <net/netns/vsock.h>
#include <uapi/linux/vm_sockets.h>
#include <uapi/asm-generic/ioctls.h>
+#define VSOCK_NET_MODE_STR_GLOBAL "global"
+#define VSOCK_NET_MODE_STR_LOCAL "local"
+
+/* 6 chars for "global", 1 for null-terminator, and 1 more for '\n'.
+ * The newline is added by proc_dostring() for read operations.
+ */
+#define VSOCK_NET_MODE_STR_MAX 8
+
static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
static void vsock_sk_destruct(struct sock *sk);
static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
@@ -149,6 +188,15 @@ static const struct vsock_transport *transport_dgram;
static const struct vsock_transport *transport_local;
static DEFINE_MUTEX(vsock_register_mutex);
+/* This net is used only for transports that do support namespaces. It is never
+ * registered with the namespace subsystem and always has
+ * VSOCK_NET_MODE_GLOBAL. Pass this net to the net lookup functions (e.g.,
+ * vsock_find_bound_socket_net()) when you want to force global-mode or the
+ * same behavior as before namespaces were supported.
+ */
+struct net __vsock_global_dummy_net;
+EXPORT_SYMBOL_GPL(__vsock_global_dummy_net);
+
/**** UTILS ****/
/* Each bound VSocket is stored in the bind hash table and each connected
@@ -235,33 +283,44 @@ static void __vsock_remove_connected(struct vsock_sock *vsk)
sock_put(&vsk->sk);
}
-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+static struct sock *__vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_sock *vsk;
list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
- if (vsock_addr_equals_addr(addr, &vsk->local_addr))
- return sk_vsock(vsk);
+ struct sock *sk = sk_vsock(vsk);
+
+ if (vsock_addr_equals_addr(addr, &vsk->local_addr) &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net, net_mode))
+ return sk;
if (addr->svm_port == vsk->local_addr.svm_port &&
(vsk->local_addr.svm_cid == VMADDR_CID_ANY ||
- addr->svm_cid == VMADDR_CID_ANY))
- return sk_vsock(vsk);
+ addr->svm_cid == VMADDR_CID_ANY) &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net, net_mode))
+ return sk;
}
return NULL;
}
-static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
- struct sockaddr_vm *dst)
+static struct sock *__vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_sock *vsk;
list_for_each_entry(vsk, vsock_connected_sockets(src, dst),
connected_table) {
+ struct sock *sk = sk_vsock(vsk);
+
if (vsock_addr_equals_addr(src, &vsk->remote_addr) &&
- dst->svm_port == vsk->local_addr.svm_port) {
- return sk_vsock(vsk);
+ dst->svm_port == vsk->local_addr.svm_port &&
+ vsock_net_check_mode(sock_net(sk), vsk->net_mode, net, net_mode)) {
+ return sk;
}
}
@@ -304,12 +363,14 @@ void vsock_remove_connected(struct vsock_sock *vsk)
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);
-struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct sock *sk;
spin_lock_bh(&vsock_table_lock);
- sk = __vsock_find_bound_socket(addr);
+ sk = __vsock_find_bound_socket_net(addr, net, net_mode);
if (sk)
sock_hold(sk);
@@ -317,15 +378,24 @@ struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_bound_socket_net);
+
+struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr)
+{
+ return vsock_find_bound_socket_net(addr, vsock_global_dummy_net(),
+ VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_bound_socket);
-struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
- struct sockaddr_vm *dst)
+struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst,
+ struct net *net,
+ enum vsock_net_mode net_mode)
{
struct sock *sk;
spin_lock_bh(&vsock_table_lock);
- sk = __vsock_find_connected_socket(src, dst);
+ sk = __vsock_find_connected_socket_net(src, dst, net, net_mode);
if (sk)
sock_hold(sk);
@@ -333,6 +403,15 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
return sk;
}
+EXPORT_SYMBOL_GPL(vsock_find_connected_socket_net);
+
+struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
+ struct sockaddr_vm *dst)
+{
+ return vsock_find_connected_socket_net(src, dst,
+ vsock_global_dummy_net(),
+ VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
@@ -528,7 +607,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
if (sk->sk_type == SOCK_SEQPACKET) {
if (!new_transport->seqpacket_allow ||
- !new_transport->seqpacket_allow(remote_cid)) {
+ !new_transport->seqpacket_allow(vsk, remote_cid)) {
module_put(new_transport->module);
return -ESOCKTNOSUPPORT;
}
@@ -676,6 +755,7 @@ static void vsock_pending_work(struct work_struct *work)
static int __vsock_bind_connectible(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
+ struct net *net = sock_net(sk_vsock(vsk));
static u32 port;
struct sockaddr_vm new_addr;
@@ -695,7 +775,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
new_addr.svm_port = port++;
- if (!__vsock_find_bound_socket(&new_addr)) {
+ if (!__vsock_find_bound_socket_net(&new_addr, net,
+ vsk->net_mode)) {
found = true;
break;
}
@@ -712,7 +793,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
return -EACCES;
}
- if (__vsock_find_bound_socket(&new_addr))
+ if (__vsock_find_bound_socket_net(&new_addr, net,
+ vsk->net_mode))
return -EADDRINUSE;
}
@@ -836,6 +918,8 @@ static struct sock *__vsock_create(struct net *net,
vsk->buffer_max_size = VSOCK_DEFAULT_BUFFER_MAX_SIZE;
}
+ vsk->net_mode = vsock_net_mode(net);
+
return sk;
}
@@ -2636,6 +2720,142 @@ static struct miscdevice vsock_device = {
.fops = &vsock_device_ops,
};
+static int vsock_net_mode_string(const struct ctl_table *table, int write,
+ void *buffer, size_t *lenp, loff_t *ppos)
+{
+ char data[VSOCK_NET_MODE_STR_MAX] = {0};
+ enum vsock_net_mode mode;
+ struct ctl_table tmp;
+ struct net *net;
+ int ret;
+
+ if (!table->data || !table->maxlen || !*lenp) {
+ *lenp = 0;
+ return 0;
+ }
+
+ net = current->nsproxy->net_ns;
+ tmp = *table;
+ tmp.data = data;
+
+ if (!write) {
+ const char *p;
+
+ mode = vsock_net_mode(net);
+
+ switch (mode) {
+ case VSOCK_NET_MODE_GLOBAL:
+ p = VSOCK_NET_MODE_STR_GLOBAL;
+ break;
+ case VSOCK_NET_MODE_LOCAL:
+ p = VSOCK_NET_MODE_STR_LOCAL;
+ break;
+ default:
+ WARN_ONCE(true, "netns has invalid vsock mode");
+ *lenp = 0;
+ return 0;
+ }
+
+ strscpy(data, p, sizeof(data));
+ tmp.maxlen = strlen(p);
+ }
+
+ ret = proc_dostring(&tmp, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+
+ if (write) {
+ if (*lenp >= sizeof(data))
+ return -EINVAL;
+
+ if (!strncmp(data, VSOCK_NET_MODE_STR_GLOBAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_GLOBAL;
+ else if (!strncmp(data, VSOCK_NET_MODE_STR_LOCAL, sizeof(data)))
+ mode = VSOCK_NET_MODE_LOCAL;
+ else
+ return -EINVAL;
+
+ if (!vsock_net_write_mode(net, mode))
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+static struct ctl_table vsock_table[] = {
+ {
+ .procname = "ns_mode",
+ .data = &init_net.vsock.mode,
+ .maxlen = VSOCK_NET_MODE_STR_MAX,
+ .mode = 0644,
+ .proc_handler = vsock_net_mode_string
+ },
+};
+
+static int __net_init vsock_sysctl_register(struct net *net)
+{
+ struct ctl_table *table;
+
+ if (net_eq(net, &init_net)) {
+ table = vsock_table;
+ } else {
+ table = kmemdup(vsock_table, sizeof(vsock_table), GFP_KERNEL);
+ if (!table)
+ goto err_alloc;
+
+ table[0].data = &net->vsock.mode;
+ }
+
+ net->vsock.sysctl_hdr = register_net_sysctl_sz(net, "net/vsock", table,
+ ARRAY_SIZE(vsock_table));
+ if (!net->vsock.sysctl_hdr)
+ goto err_reg;
+
+ return 0;
+
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
+}
+
+static void vsock_sysctl_unregister(struct net *net)
+{
+ const struct ctl_table *table;
+
+ table = net->vsock.sysctl_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->vsock.sysctl_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static void vsock_net_init(struct net *net)
+{
+ spin_lock_init(&net->vsock.lock);
+ net->vsock.mode = VSOCK_NET_MODE_GLOBAL;
+}
+
+static __net_init int vsock_sysctl_init_net(struct net *net)
+{
+ vsock_net_init(net);
+
+ if (vsock_sysctl_register(net))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static __net_exit void vsock_sysctl_exit_net(struct net *net)
+{
+ vsock_sysctl_unregister(net);
+}
+
+static struct pernet_operations vsock_sysctl_ops __net_initdata = {
+ .init = vsock_sysctl_init_net,
+ .exit = vsock_sysctl_exit_net,
+};
+
static int __init vsock_init(void)
{
int err = 0;
@@ -2663,10 +2883,19 @@ static int __init vsock_init(void)
goto err_unregister_proto;
}
+ if (register_pernet_subsys(&vsock_sysctl_ops)) {
+ err = -ENOMEM;
+ goto err_unregister_sock;
+ }
+
+ vsock_net_init(&init_net);
+ vsock_net_init(vsock_global_dummy_net());
vsock_bpf_build_proto();
return 0;
+err_unregister_sock:
+ sock_unregister(AF_VSOCK);
err_unregister_proto:
proto_unregister(&vsock_proto);
err_deregister_misc:
@@ -2680,6 +2909,7 @@ static void __exit vsock_exit(void)
misc_deregister(&vsock_device);
sock_unregister(AF_VSOCK);
proto_unregister(&vsock_proto);
+ unregister_pernet_subsys(&vsock_sysctl_ops);
}
const struct vsock_transport *vsock_core_get_transport(struct vsock_sock *vsk)
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8c867023a2e5..6abec6b9b5bc 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -316,11 +316,10 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
vq = vsock->vqs[VSOCK_VQ_RX];
do {
- skb = virtio_vsock_alloc_linear_skb(total_len, GFP_KERNEL);
+ skb = virtio_vsock_alloc_rx_skb(total_len, GFP_KERNEL);
if (!skb)
break;
- memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM);
sg_init_one(&pkt, virtio_vsock_hdr(skb), total_len);
p = &pkt;
ret = virtqueue_add_sgs(vq, &p, 0, 1, skb, GFP_KERNEL);
@@ -536,7 +535,7 @@ static bool virtio_transport_msgzerocopy_allow(void)
return true;
}
-static bool virtio_transport_seqpacket_allow(u32 remote_cid);
+static bool virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
static struct virtio_transport virtio_transport = {
.transport = {
@@ -593,7 +592,7 @@ static struct virtio_transport virtio_transport = {
.can_msgzerocopy = virtio_transport_can_msgzerocopy,
};
-static bool virtio_transport_seqpacket_allow(u32 remote_cid)
+static bool virtio_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
struct virtio_vsock *vsock;
bool seqpacket_allow;
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index bc2ff918b315..a8f218f0c5a3 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -46,7 +46,7 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
return 0;
}
-static bool vsock_loopback_seqpacket_allow(u32 remote_cid);
+static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid);
static bool vsock_loopback_msgzerocopy_allow(void)
{
return true;
@@ -106,7 +106,7 @@ static struct virtio_transport loopback_transport = {
.send_pkt = vsock_loopback_send_pkt,
};
-static bool vsock_loopback_seqpacket_allow(u32 remote_cid)
+static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
return true;
}
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 05/14] vsock/loopback: add netns support
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add NS support to vsock loopback. Sockets in a global mode netns
communicate with each other, regardless of namespace. Sockets in a local
mode netns may only communicate with other sockets within the same
namespace.
Use pernet_ops to install a vsock_loopback for every namespace that is
created (to be used if local mode is enabled).
Retroactively call init/exit on every namespace when the vsock_loopback
module is loaded in order to initialize the per-ns device.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- drop for_each_net() init/exit, drop net_rwsem, the pernet registration
handles this automatically and race-free
- flush workqueue before destruction, purge pkt list
- remember net_mode instead of current net mode
- keep space after INIT_WORK()
- change vsock_loopback in netns_vsock to ->priv void ptr
- rename `orig_net_mode` to `net_mode`
- remove useless comment
- protect `register_pernet_subsys()` with `net_rwsem`
- do cleanup before releasing `net_rwsem` when failure happens
- call `unregister_pernet_subsys()` in `vsock_loopback_exit()`
- call `vsock_loopback_deinit_vsock()` in `vsock_loopback_exit()`
Changes in v6:
- init pernet ops for vsock_loopback module
- vsock_loopback: add space in struct to clarify lock protection
- do proper cleanup/unregister on vsock_loopback_exit()
- vsock_loopback: use virtio_vsock_skb_net()
Changes in v5:
- add callbacks code to avoid reverse dependency
- add logic for handling vsock_loopback setup for already existing
namespaces
---
include/net/netns/vsock.h | 2 +
net/vmw_vsock/vsock_loopback.c | 85 ++++++++++++++++++++++++++++++++++++------
2 files changed, 75 insertions(+), 12 deletions(-)
diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h
index c9a438ad52f2..9d0d8e2fbc37 100644
--- a/include/net/netns/vsock.h
+++ b/include/net/netns/vsock.h
@@ -16,5 +16,7 @@ struct netns_vsock {
/* protected by lock */
enum vsock_net_mode mode;
bool mode_locked;
+
+ void *priv;
};
#endif /* __NET_NET_NAMESPACE_VSOCK_H */
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index a8f218f0c5a3..474083d4cfcb 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -28,8 +28,16 @@ static u32 vsock_loopback_get_local_cid(void)
static int vsock_loopback_send_pkt(struct sk_buff *skb)
{
- struct vsock_loopback *vsock = &the_vsock_loopback;
+ struct vsock_loopback *vsock;
int len = skb->len;
+ struct net *net;
+
+ net = virtio_vsock_skb_net(skb);
+
+ if (virtio_vsock_skb_net_mode(skb) == VSOCK_NET_MODE_LOCAL)
+ vsock = (struct vsock_loopback *)net->vsock.priv;
+ else
+ vsock = &the_vsock_loopback;
virtio_vsock_skb_queue_tail(&vsock->pkt_queue, skb);
queue_work(vsock->workqueue, &vsock->pkt_work);
@@ -134,11 +142,8 @@ static void vsock_loopback_work(struct work_struct *work)
}
}
-static int __init vsock_loopback_init(void)
+static int vsock_loopback_init_vsock(struct vsock_loopback *vsock)
{
- struct vsock_loopback *vsock = &the_vsock_loopback;
- int ret;
-
vsock->workqueue = alloc_workqueue("vsock-loopback", WQ_PERCPU, 0);
if (!vsock->workqueue)
return -ENOMEM;
@@ -146,15 +151,73 @@ static int __init vsock_loopback_init(void)
skb_queue_head_init(&vsock->pkt_queue);
INIT_WORK(&vsock->pkt_work, vsock_loopback_work);
+ return 0;
+}
+
+static void vsock_loopback_deinit_vsock(struct vsock_loopback *vsock)
+{
+ if (vsock->workqueue) {
+ flush_work(&vsock->pkt_work);
+ virtio_vsock_skb_queue_purge(&vsock->pkt_queue);
+ destroy_workqueue(vsock->workqueue);
+ vsock->workqueue = NULL;
+ }
+}
+
+static int vsock_loopback_init_net(struct net *net)
+{
+ int ret;
+
+ net->vsock.priv = kzalloc(sizeof(struct vsock_loopback), GFP_KERNEL);
+ if (!net->vsock.priv)
+ return -ENOMEM;
+
+ ret = vsock_loopback_init_vsock((struct vsock_loopback *)net->vsock.priv);
+ if (ret < 0) {
+ kfree(net->vsock.priv);
+ net->vsock.priv = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static void vsock_loopback_exit_net(struct net *net)
+{
+ vsock_loopback_deinit_vsock(net->vsock.priv);
+ kfree(net->vsock.priv);
+ net->vsock.priv = NULL;
+}
+
+static struct pernet_operations vsock_loopback_net_ops = {
+ .init = vsock_loopback_init_net,
+ .exit = vsock_loopback_exit_net,
+};
+
+static int __init vsock_loopback_init(void)
+{
+ struct vsock_loopback *vsock = &the_vsock_loopback;
+ int ret;
+
+ ret = vsock_loopback_init_vsock(vsock);
+ if (ret < 0)
+ return ret;
+
+ ret = register_pernet_subsys(&vsock_loopback_net_ops);
+ if (ret < 0)
+ goto out_deinit_vsock;
+
ret = vsock_core_register(&loopback_transport.transport,
VSOCK_TRANSPORT_F_LOCAL);
if (ret)
- goto out_wq;
+ goto out_unregister_pernet_subsys;
return 0;
-out_wq:
- destroy_workqueue(vsock->workqueue);
+out_unregister_pernet_subsys:
+ unregister_pernet_subsys(&vsock_loopback_net_ops);
+out_deinit_vsock:
+ vsock_loopback_deinit_vsock(vsock);
return ret;
}
@@ -164,11 +227,9 @@ static void __exit vsock_loopback_exit(void)
vsock_core_unregister(&loopback_transport.transport);
- flush_work(&vsock->pkt_work);
-
- virtio_vsock_skb_queue_purge(&vsock->pkt_queue);
+ unregister_pernet_subsys(&vsock_loopback_net_ops);
- destroy_workqueue(vsock->workqueue);
+ vsock_loopback_deinit_vsock(vsock);
}
module_init(vsock_loopback_init);
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 06/14] vsock/virtio: add netns to virtio transport common
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Enable network namespace support in the virtio-vsock common transport
layer by declaring namespace pointers in the transmit and receive
paths.
The changes include:
1. Add a 'net' field to virtio_vsock_pkt_info to carry the namespace
pointer for outgoing packets.
2. Store the namespace and namespace mode in the skb control buffer when
allocating packets (except for VIRTIO_VSOCK_OP_RST packets which do
not have an associated socket).
3. Retrieve namespace information from skbs on the receive path for
lookups using vsock_find_connected_socket_net() and
vsock_find_bound_socket_net().
This allows users of virtio transport common code
(vhost-vsock/virtio-vsock) to later enable namespace support.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- add comment explaining the !vsk case in virtio_transport_alloc_skb()
---
include/linux/virtio_vsock.h | 1 +
net/vmw_vsock/virtio_transport_common.c | 21 +++++++++++++++++++--
2 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 29290395054c..f90646f82993 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -217,6 +217,7 @@ struct virtio_vsock_pkt_info {
u32 remote_cid, remote_port;
struct vsock_sock *vsk;
struct msghdr *msg;
+ struct net *net;
u32 pkt_len;
u16 type;
u16 op;
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index dcc8a1d5851e..b8e52c71920a 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -316,6 +316,15 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *
info->flags,
zcopy);
+ /*
+ * If there is no corresponding socket, then we don't have a
+ * corresponding namespace. This only happens For VIRTIO_VSOCK_OP_RST.
+ */
+ if (vsk) {
+ virtio_vsock_skb_set_net(skb, info->net);
+ virtio_vsock_skb_set_net_mode(skb, vsk->net_mode);
+ }
+
return skb;
out:
kfree_skb(skb);
@@ -527,6 +536,7 @@ static int virtio_transport_send_credit_update(struct vsock_sock *vsk)
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1067,6 +1077,7 @@ int virtio_transport_connect(struct vsock_sock *vsk)
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_REQUEST,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1082,6 +1093,7 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
(mode & SEND_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1108,6 +1120,7 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1145,6 +1158,7 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
.op = VIRTIO_VSOCK_OP_RST,
.reply = !!skb,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
/* Send RST only if the original pkt is not a RST pkt */
@@ -1465,6 +1479,7 @@ virtio_transport_send_response(struct vsock_sock *vsk,
.remote_port = le32_to_cpu(hdr->src_port),
.reply = true,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1578,7 +1593,9 @@ static bool virtio_transport_valid_type(u16 type)
void virtio_transport_recv_pkt(struct virtio_transport *t,
struct sk_buff *skb)
{
+ enum vsock_net_mode net_mode = virtio_vsock_skb_net_mode(skb);
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
+ struct net *net = virtio_vsock_skb_net(skb);
struct sockaddr_vm src, dst;
struct vsock_sock *vsk;
struct sock *sk;
@@ -1606,9 +1623,9 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
/* The socket must be in connected or bound table
* otherwise send reset back
*/
- sk = vsock_find_connected_socket(&src, &dst);
+ sk = vsock_find_connected_socket_net(&src, &dst, net, net_mode);
if (!sk) {
- sk = vsock_find_bound_socket(&dst);
+ sk = vsock_find_bound_socket_net(&dst, net, net_mode);
if (!sk) {
(void)virtio_transport_reset_no_sock(t, skb);
goto free_pkt;
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 07/14] vhost/vsock: add netns support
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add the ability to isolate vhost-vsock flows using namespaces.
The VM, via the vhost_vsock struct, inherits its namespace from the
process that opens the vhost-vsock device. vhost_vsock lookup functions
are modified to take into account the mode (e.g., if CIDs are matching
but modes don't align, then return NULL).
vhost_vsock now acquires a reference to the namespace.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v7:
- remove the check_global flag of vhost_vsock_get(), that logic was both
wrong and not necessary, reuse vsock_net_check_mode() instead
- remove 'delete me' comment
Changes in v5:
- respect pid namespaces when assigning namespace to vhost_vsock
---
drivers/vhost/vsock.c | 44 ++++++++++++++++++++++++++++++++++----------
1 file changed, 34 insertions(+), 10 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 34adf0cf9124..df6136633cd8 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -46,6 +46,11 @@ static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8);
struct vhost_vsock {
struct vhost_dev dev;
struct vhost_virtqueue vqs[2];
+ struct net *net;
+ netns_tracker ns_tracker;
+
+ /* The ns mode at the time vhost_vsock was created */
+ enum vsock_net_mode net_mode;
/* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */
struct hlist_node hash;
@@ -67,7 +72,8 @@ static u32 vhost_transport_get_local_cid(void)
/* Callers that dereference the return value must hold vhost_vsock_mutex or the
* RCU read lock.
*/
-static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
+static struct vhost_vsock *vhost_vsock_get(u32 guest_cid, struct net *net,
+ enum vsock_net_mode mode)
{
struct vhost_vsock *vsock;
@@ -78,9 +84,9 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
if (other_cid == 0)
continue;
- if (other_cid == guest_cid)
+ if (other_cid == guest_cid &&
+ vsock_net_check_mode(net, mode, vsock->net, vsock->net_mode))
return vsock;
-
}
return NULL;
@@ -271,14 +277,16 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work)
static int
vhost_transport_send_pkt(struct sk_buff *skb)
{
+ enum vsock_net_mode mode = virtio_vsock_skb_net_mode(skb);
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
+ struct net *net = virtio_vsock_skb_net(skb);
struct vhost_vsock *vsock;
int len = skb->len;
rcu_read_lock();
/* Find the vhost_vsock according to guest context id */
- vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid));
+ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid), net, mode);
if (!vsock) {
rcu_read_unlock();
kfree_skb(skb);
@@ -305,7 +313,8 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
rcu_read_lock();
/* Find the vhost_vsock according to guest context id */
- vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
+ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid,
+ sock_net(sk_vsock(vsk)), vsk->net_mode);
if (!vsock)
goto out;
@@ -327,7 +336,7 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
}
static struct sk_buff *
-vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
+vhost_vsock_alloc_skb(struct vhost_vsock *vsock, struct vhost_virtqueue *vq,
unsigned int out, unsigned int in)
{
struct virtio_vsock_hdr *hdr;
@@ -353,6 +362,9 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
if (!skb)
return NULL;
+ virtio_vsock_skb_set_net(skb, vsock->net);
+ virtio_vsock_skb_set_net_mode(skb, vsock->net_mode);
+
iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len);
hdr = virtio_vsock_hdr(skb);
@@ -462,11 +474,12 @@ static struct virtio_transport vhost_transport = {
static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
+ struct net *net = sock_net(sk_vsock(vsk));
struct vhost_vsock *vsock;
bool seqpacket_allow = false;
rcu_read_lock();
- vsock = vhost_vsock_get(remote_cid);
+ vsock = vhost_vsock_get(remote_cid, net, vsk->net_mode);
if (vsock)
seqpacket_allow = vsock->seqpacket_allow;
@@ -520,7 +533,7 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
break;
}
- skb = vhost_vsock_alloc_skb(vq, out, in);
+ skb = vhost_vsock_alloc_skb(vsock, vq, out, in);
if (!skb) {
vq_err(vq, "Faulted on pkt\n");
continue;
@@ -652,8 +665,10 @@ static void vhost_vsock_free(struct vhost_vsock *vsock)
static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
{
+
struct vhost_virtqueue **vqs;
struct vhost_vsock *vsock;
+ struct net *net;
int ret;
/* This struct is large and allocation could fail, fall back to vmalloc
@@ -669,6 +684,14 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
goto out;
}
+ net = current->nsproxy->net_ns;
+ vsock->net = get_net_track(net, &vsock->ns_tracker, GFP_KERNEL);
+
+ /* Cache the mode of the namespace so that if that netns mode changes,
+ * the vhost_vsock will continue to function as expected.
+ */
+ vsock->net_mode = vsock_net_mode(net);
+
vsock->guest_cid = 0; /* no CID assigned yet */
vsock->seqpacket_allow = false;
@@ -708,7 +731,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk)
*/
/* If the peer is still valid, no need to reset connection */
- if (vhost_vsock_get(vsk->remote_addr.svm_cid))
+ if (vhost_vsock_get(vsk->remote_addr.svm_cid, sock_net(sk), vsk->net_mode))
return;
/* If the close timeout is pending, let it expire. This avoids races
@@ -753,6 +776,7 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
vhost_dev_cleanup(&vsock->dev);
+ put_net_track(vsock->net, &vsock->ns_tracker);
kfree(vsock->dev.vqs);
vhost_vsock_free(vsock);
return 0;
@@ -779,7 +803,7 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
/* Refuse if CID is already in use */
mutex_lock(&vhost_vsock_mutex);
- other = vhost_vsock_get(guest_cid);
+ other = vhost_vsock_get(guest_cid, vsock->net, vsock->net_mode);
if (other && other != vsock) {
mutex_unlock(&vhost_vsock_mutex);
return -EADDRINUSE;
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 09/14] selftests/vsock: prepare vm management helpers for namespaces
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add namespace support to vm management, ssh helpers, and vsock_test
wrapper functions. This enables running VMs and test helpers in specific
namespaces, which is required for upcoming namespace isolation tests.
The functions still work correctly within the init ns, though the caller
must now pass "init_ns" explicitly.
No functional changes for existing tests. All have been updated to pass
"init_ns" explicitly.
Affected functions (such as vm_start() and vm_ssh()) now wrap their
commands with 'ip netns exec' when executing commands in non-init
namespaces.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 102 ++++++++++++++++++++++----------
1 file changed, 71 insertions(+), 31 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 5f4bae952e13..d047f6d27df4 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -141,7 +141,18 @@ ns_set_mode() {
}
vm_ssh() {
- ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@"
+ local ns_exec
+
+ if [[ "${1}" == init_ns ]]; then
+ ns_exec=""
+ else
+ ns_exec="ip netns exec ${1}"
+ fi
+
+ shift
+
+ ${ns_exec} ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost $*
+
return $?
}
@@ -254,10 +265,12 @@ terminate_pidfiles() {
vm_start() {
local pidfile=$1
+ local ns=$2
local logfile=/dev/null
local verbose_opt=""
local kernel_opt=""
local qemu_opts=""
+ local ns_exec=""
local qemu
qemu=$(command -v "${QEMU}")
@@ -278,7 +291,11 @@ vm_start() {
kernel_opt="${KERNEL_CHECKOUT}"
fi
- vng \
+ if [[ "${ns}" != "init_ns" ]]; then
+ ns_exec="ip netns exec ${ns}"
+ fi
+
+ ${ns_exec} vng \
--run \
${kernel_opt} \
${verbose_opt} \
@@ -293,6 +310,7 @@ vm_start() {
}
vm_wait_for_ssh() {
+ local ns=$1
local i
i=0
@@ -300,7 +318,8 @@ vm_wait_for_ssh() {
if [[ ${i} -gt ${WAIT_PERIOD_MAX} ]]; then
die "Timed out waiting for guest ssh"
fi
- if vm_ssh -- true; then
+
+ if vm_ssh "${ns}" -- true; then
break
fi
i=$(( i + 1 ))
@@ -344,28 +363,42 @@ wait_for_listener()
}
vm_wait_for_listener() {
- local port=$1
+ local ns=$1
+ local port=$2
+
+ log "Waiting for listener on port ${port} on vm"
- vm_ssh <<EOF
+ vm_ssh "${ns}" <<EOF
$(declare -f wait_for_listener)
wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
EOF
}
host_wait_for_listener() {
- wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ local ns=$1
+ local port=$2
+
+ if [[ "${ns}" == init_ns ]]; then
+ wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ else
+ ip netns exec "${ns}" bash <<-EOF
+ $(declare -f wait_for_listener)
+ wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
+ EOF
+ fi
}
vm_vsock_test() {
- local host=$1
- local cid=$2
- local port=$3
+ local ns=$1
+ local host=$2
+ local cid=$3
+ local port=$4
local rc
set -o pipefail
if [[ "${host}" != server ]]; then
# log output and use pipefail to respect vsock_test errors
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=client \
--control-host="${host}" \
--peer-cid="${cid}" \
@@ -374,7 +407,7 @@ vm_vsock_test() {
rc=$?
else
# log output and use pipefail to respect vsock_test errors
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=server \
--peer-cid="${cid}" \
--control-port="${port}" \
@@ -386,7 +419,7 @@ vm_vsock_test() {
return $rc
fi
- vm_wait_for_listener "${port}"
+ vm_wait_for_listener "${ns}" "${port}"
rc=$?
fi
set +o pipefail
@@ -395,22 +428,28 @@ vm_vsock_test() {
}
host_vsock_test() {
- local host=$1
- local cid=$2
- local port=$3
+ local ns=$1
+ local host=$2
+ local cid=$3
+ local port=$4
local rc
+ local cmd="${VSOCK_TEST}"
+ if [[ "${ns}" != "init_ns" ]]; then
+ cmd="ip netns exec ${ns} ${cmd}"
+ fi
+
# log output and use pipefail to respect vsock_test errors
set -o pipefail
if [[ "${host}" != server ]]; then
- ${VSOCK_TEST} \
+ ${cmd} \
--mode=client \
--peer-cid="${cid}" \
--control-host="${host}" \
--control-port="${port}" 2>&1 | log_host
rc=$?
else
- ${VSOCK_TEST} \
+ ${cmd} \
--mode=server \
--peer-cid="${cid}" \
--control-port="${port}" 2>&1 | log_host &
@@ -420,7 +459,7 @@ host_vsock_test() {
return $rc
fi
- host_wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ host_wait_for_listener "${ns}" "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
rc=$?
fi
set +o pipefail
@@ -464,11 +503,11 @@ log_guest() {
}
test_vm_server_host_client() {
- if ! vm_vsock_test "server" 2 "${TEST_GUEST_PORT}"; then
+ if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then
return "${KSFT_FAIL}"
fi
- if ! host_vsock_test "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then
+ if ! host_vsock_test "init_ns" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then
return "${KSFT_FAIL}"
fi
@@ -476,11 +515,11 @@ test_vm_server_host_client() {
}
test_vm_client_host_server() {
- if ! host_vsock_test "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then
+ if ! host_vsock_test "init_ns" "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then
return "${KSFT_FAIL}"
fi
- if ! vm_vsock_test "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then
+ if ! vm_vsock_test "init_ns" "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then
return "${KSFT_FAIL}"
fi
@@ -490,13 +529,14 @@ test_vm_client_host_server() {
test_vm_loopback() {
local port=60000 # non-forwarded local port
- vm_ssh -- modprobe vsock_loopback &> /dev/null || :
+ vm_ssh "init_ns" -- modprobe vsock_loopback &> /dev/null || :
- if ! vm_vsock_test "server" 1 "${port}"; then
+ if ! vm_vsock_test "init_ns" "server" 1 "${port}"; then
return "${KSFT_FAIL}"
fi
- if ! vm_vsock_test "127.0.0.1" 1 "${port}"; then
+
+ if ! vm_vsock_test "init_ns" "127.0.0.1" 1 "${port}"; then
return "${KSFT_FAIL}"
fi
@@ -554,8 +594,8 @@ run_shared_vm_test() {
host_oops_cnt_before=$(dmesg | grep -c -i 'Oops')
host_warn_cnt_before=$(dmesg --level=warn | grep -c -i 'vsock')
- vm_oops_cnt_before=$(vm_ssh -- dmesg | grep -c -i 'Oops')
- vm_warn_cnt_before=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock')
+ vm_oops_cnt_before=$(vm_ssh "init_ns" -- dmesg | grep -c -i 'Oops')
+ vm_warn_cnt_before=$(vm_ssh "init_ns" -- dmesg --level=warn | grep -c -i 'vsock')
name=$(echo "${1}" | awk '{ print $1 }')
eval test_"${name}"
@@ -573,13 +613,13 @@ run_shared_vm_test() {
rc=$KSFT_FAIL
fi
- vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l)
+ vm_oops_cnt_after=$(vm_ssh "init_ns" -- dmesg | grep -i 'Oops' | wc -l)
if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then
echo "FAIL: kernel oops detected on vm" | log_host
rc=$KSFT_FAIL
fi
- vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | grep -c -i vsock)
+ vm_warn_cnt_after=$(vm_ssh "init_ns" -- dmesg --level=warn | grep -c -i vsock)
if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then
echo "FAIL: kernel warning detected on vm" | log_host
rc=$KSFT_FAIL
@@ -623,8 +663,8 @@ cnt_total=0
if shared_vm_tests_requested "${ARGS[@]}"; then
log_host "Booting up VM"
pidfile=$(mktemp $PIDFILE_TEMPLATE)
- vm_start "${pidfile}"
- vm_wait_for_ssh
+ vm_start "${pidfile}" "init_ns"
+ vm_wait_for_ssh "init_ns"
log_host "VM booted up"
run_shared_vm_tests "${ARGS[@]}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 08/14] selftests/vsock: add namespace helpers to vmtest.sh
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add functions for initializing namespaces with the different vsock NS
modes. Callers can use add_namespaces() and del_namespaces() to create
namespaces global0, global1, local0, and local1.
The init_namespaces() function initializes global0, local0, etc... with
their respective vsock NS mode. This function is separate so that tests
that depend on this initialization can use it, while other tests that
want to test the initialization interface itself can start with a clean
slate by omitting this call.
Remove namespaces upon exiting the program in cleanup(). This is
unlikely to be needed for a healthy run, but it is useful for tests that
are manually killed mid-test. In that case, this patch prevents the
subsequent test run from finding stale namespaces with
already-write-once-locked vsock ns modes.
This patch is in preparation for later namespace tests.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 45 +++++++++++++++++++++++++++++++++
1 file changed, 45 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 62b4f5ede9f6..5f4bae952e13 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -46,6 +46,7 @@ readonly TEST_DESCS=(
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
+readonly NS_MODES=("local" "global")
VERBOSE=0
@@ -100,11 +101,55 @@ check_result() {
cnt_total=$(( cnt_total + 1 ))
}
+add_namespaces() {
+ # add namespaces local0, local1, global0, and global1
+ for mode in "${NS_MODES[@]}"; do
+ ip netns add "${mode}0" 2>/dev/null
+ ip netns add "${mode}1" 2>/dev/null
+ done
+}
+
+init_namespaces() {
+ for mode in "${NS_MODES[@]}"; do
+ ns_set_mode "${mode}0" "${mode}"
+ ns_set_mode "${mode}1" "${mode}"
+
+ log_host "set ns ${mode}0 to mode ${mode}"
+ log_host "set ns ${mode}1 to mode ${mode}"
+
+ # we need lo for qemu port forwarding
+ ip netns exec "${mode}0" ip link set dev lo up
+ ip netns exec "${mode}1" ip link set dev lo up
+ done
+}
+
+del_namespaces() {
+ for mode in "${NS_MODES[@]}"; do
+ ip netns del "${mode}0" &>/dev/null
+ ip netns del "${mode}1" &>/dev/null
+ log_host "removed ns ${mode}0"
+ log_host "removed ns ${mode}1"
+ done
+}
+
+ns_set_mode() {
+ local ns=$1
+ local mode=$2
+
+ echo "${mode}" | ip netns exec "${ns}" \
+ tee /proc/sys/net/vsock/ns_mode &>/dev/null
+}
+
vm_ssh() {
ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@"
return $?
}
+cleanup() {
+ del_namespaces
+}
+
+trap cleanup EXIT
check_args() {
local found
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 10/14] selftests/vsock: add tests for proc sys vsock ns_mode
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests for the /proc/sys/net/vsock/ns_mode interface. Namely,
that it accepts "global" and "local" strings and enforces a write-once
policy.
Start a convention of commenting the test name over the test
description. Add test name comments over test descriptions that existed
before this convention.
Add a check_netns() function that checks if the test requires namespaces
and if the current kernel supports namespaces. Skip tests that require
namespaces if the system does not have namespace support.
This patch is the first to add tests that do *not* re-use the same
shared VM. For that reason, it adds a run_tests() function to run these
tests and filter out the shared VM tests.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 99 ++++++++++++++++++++++++++++++++-
1 file changed, 98 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index d047f6d27df4..b775fb0cd4ed 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -38,11 +38,28 @@ readonly KERNEL_CMDLINE="\
virtme.ssh virtme_ssh_channel=tcp virtme_ssh_user=$USER \
"
readonly LOG=$(mktemp /tmp/vsock_vmtest_XXXX.log)
-readonly TEST_NAMES=(vm_server_host_client vm_client_host_server vm_loopback)
+readonly TEST_NAMES=(
+ vm_server_host_client
+ vm_client_host_server
+ vm_loopback
+ ns_host_vsock_ns_mode_ok
+ ns_host_vsock_ns_mode_write_once_ok
+)
readonly TEST_DESCS=(
+ # vm_server_host_client
"Run vsock_test in server mode on the VM and in client mode on the host."
+
+ # vm_client_host_server
"Run vsock_test in client mode on the VM and in server mode on the host."
+
+ # vm_loopback
"Run vsock_test using the loopback transport in the VM."
+
+ # ns_host_vsock_ns_mode_ok
+ "Check /proc/sys/net/vsock/ns_mode strings on the host."
+
+ # ns_host_vsock_ns_mode_write_once_ok
+ "Check /proc/sys/net/vsock/ns_mode is write-once on the host."
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -203,6 +220,20 @@ check_deps() {
fi
}
+check_netns() {
+ local tname=$1
+
+ # If the test requires NS support, check if NS support exists
+ # using /proc/self/ns
+ if [[ "${tname}" =~ ^ns_ ]] &&
+ [[ ! -e /proc/self/ns ]]; then
+ log_host "No NS support detected for test ${tname}"
+ return 1
+ fi
+
+ return 0
+}
+
check_vng() {
local tested_versions
local version
@@ -502,6 +533,43 @@ log_guest() {
LOG_PREFIX=guest log $@
}
+test_ns_host_vsock_ns_mode_ok() {
+ add_namespaces
+
+ for mode in "${NS_MODES[@]}"; do
+ if ! ns_set_mode "${mode}0" "${mode}"; then
+ del_namespaces
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ del_namespaces
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_host_vsock_ns_mode_write_once_ok() {
+ add_namespaces
+
+ for mode in "${NS_MODES[@]}"; do
+ local ns="${mode}0"
+ if ! ns_set_mode "${ns}" "${mode}"; then
+ del_namespaces
+ return "${KSFT_FAIL}"
+ fi
+
+ # try writing again and expect failure
+ if ns_set_mode "${ns}" "${mode}"; then
+ del_namespaces
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ del_namespaces
+
+ return "${KSFT_PASS}"
+}
+
test_vm_server_host_client() {
if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then
return "${KSFT_FAIL}"
@@ -575,6 +643,11 @@ run_shared_vm_tests() {
continue
fi
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}"
+ continue
+ fi
+
run_shared_vm_test "${arg}"
check_result $?
done
@@ -628,6 +701,28 @@ run_shared_vm_test() {
return "${rc}"
}
+run_tests() {
+ for arg in "${ARGS[@]}"; do
+ if shared_vm_test "${arg}"; then
+ continue
+ fi
+
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}"
+ continue
+ fi
+
+ add_namespaces
+
+ name=$(echo "${arg}" | awk '{ print $1 }')
+ log_host "Executing test_${name}"
+ eval test_"${name}"
+ check_result $?
+
+ del_namespaces
+ done
+}
+
BUILD=0
QEMU="qemu-system-$(uname -m)"
@@ -671,6 +766,8 @@ if shared_vm_tests_requested "${ARGS[@]}"; then
terminate_pidfiles "${pidfile}"
fi
+run_tests "${ARGS[@]}"
+
echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}"
echo "Log: ${LOG}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 13/14] selftests/vsock: add tests for namespace deletion and mode changes
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests that validate vsock sockets are resilient to deleting
namespaces or changing namespace modes from global to local. The vsock
sockets should still function normally.
The function check_ns_changes_dont_break_connection() is added to re-use
the step-by-step logic of 1) setup connections, 2) do something that
would maybe break the connections, 3) check that the connections are
still ok.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 123 ++++++++++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 60d349c80153..014cecd93858 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -62,6 +62,12 @@ readonly TEST_NAMES=(
ns_same_local_loopback_ok
ns_same_local_host_connect_to_local_vm_ok
ns_same_local_vm_connect_to_local_host_ok
+ ns_mode_change_connection_continue_vm_ok
+ ns_mode_change_connection_continue_host_ok
+ ns_mode_change_connection_continue_both_ok
+ ns_delete_vm_ok
+ ns_delete_host_ok
+ ns_delete_both_ok
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -129,6 +135,24 @@ readonly TEST_DESCS=(
# ns_same_local_vm_connect_to_local_host_ok
"Run vsock_test client in VM in a local ns with server in same ns."
+
+ # ns_mode_change_connection_continue_vm_ok
+ "Check that changing NS mode of VM namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_host_ok
+ "Check that changing NS mode of host namespace from global to local after a connection is established doesn't break the connection"
+
+ # ns_mode_change_connection_continue_both_ok
+ "Check that changing NS mode of host and VM namespaces from global to local after a connection is established doesn't break the connection"
+
+ # ns_delete_vm_ok
+ "Check that deleting the VM's namespace does not break the socket connection"
+
+ # ns_delete_host_ok
+ "Check that deleting the host's namespace does not break the socket connection"
+
+ # ns_delete_both_ok
+ "Check that deleting the VM and host's namespaces does not break the socket connection"
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -1143,6 +1167,105 @@ test_vm_loopback() {
return "${KSFT_PASS}"
}
+check_ns_changes_dont_break_connection() {
+ local ns0="global0"
+ local ns1="global1"
+ local port=12345
+ local pidfile
+ local outfile
+ local pids=()
+ local rc=0
+
+ init_namespaces
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ return "${KSFT_FAIL}"
+ fi
+ vm_wait_for_ssh "${ns0}"
+
+ outfile=$(mktemp)
+ vm_ssh "${ns0}" -- \
+ socat VSOCK-LISTEN:"${port}",fork STDOUT > "${outfile}" 2>/dev/null &
+ pids+=($!)
+
+ # wait_for_listener() does not work for vsock because vsock does not
+ # export socket state to /proc/net/. Instead, we have no choice but to
+ # sleep for some hardcoded time.
+ sleep ${WAIT_PERIOD}
+
+ # We use a pipe here so that we can echo into the pipe instead of
+ # using socat and a unix socket file.
+ local pipefile=$(mktemp -u /tmp/vmtest_pipe_XXXX)
+ ip netns exec "${ns1}" \
+ socat PIPE:"${pipefile}" VSOCK-CONNECT:"${VSOCK_CID}":"${port}" &
+ pids+=($!)
+
+ timeout ${WAIT_PERIOD} \
+ bash -c 'while [[ ! -e '"${pipefile}"' ]]; do sleep 1; done; exit 0'
+
+ if [[ $2 == "delete" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ip netns del "${ns0}"
+ elif [[ "$1" == "host" ]]; then
+ ip netns del "${ns1}"
+ elif [[ "$1" == "both" ]]; then
+ ip netns del "${ns0}"
+ ip netns del "${ns1}"
+ fi
+ elif [[ $2 == "change_mode" ]]; then
+ if [[ "$1" == "vm" ]]; then
+ ns_set_mode "${ns0}" "local"
+ elif [[ "$1" == "host" ]]; then
+ ns_set_mode "${ns1}" "local"
+ elif [[ "$1" == "both" ]]; then
+ ns_set_mode "${ns0}" "local"
+ ns_set_mode "${ns1}" "local"
+ fi
+ fi
+
+ echo "TEST" > "${pipefile}"
+
+ timeout ${WAIT_PERIOD} \
+ bash -c 'while [[ ! -s '"${outfile}"' ]]; do sleep 1; done; exit 0'
+
+ if grep -q "TEST" "${outfile}"; then
+ rc="${KSFT_PASS}"
+ else
+ rc="${KSFT_FAIL}"
+ fi
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pids[@]}"
+ rm -f "${outfile}"
+
+ return "${rc}"
+}
+
+test_ns_mode_change_connection_continue_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_host_ok() {
+ check_ns_changes_dont_break_connection "host" "change_mode"
+}
+
+test_ns_mode_change_connection_continue_both_ok() {
+ check_ns_changes_dont_break_connection "both" "change_mode"
+}
+
+test_ns_delete_vm_ok() {
+ check_ns_changes_dont_break_connection "vm" "delete"
+}
+
+test_ns_delete_host_ok() {
+ check_ns_changes_dont_break_connection "host" "delete"
+}
+
+test_ns_delete_both_ok() {
+ check_ns_changes_dont_break_connection "both" "delete"
+}
+
shared_vm_test() {
local tname
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 12/14] selftests/vsock: add tests for host <-> vm connectivity with namespaces
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests to validate namespace correctness using vsock_test and socat.
The vsock_test tool is used to validate expected success tests, but
socat is used for expected failure tests. socat is used to ensure that
connections are rejected outright instead of failing due to some other
socket behavior (as tested in vsock_test). Additionally, socat is
already required for tunneling TCP traffic from vsock_test. Using only
one of the vsock_test tests like 'test_stream_client_close_client' would
have yielded a similar result, but doing so wouldn't remove the socat
dependency.
Additionally, check for the dependency socat. socat needs special
handling beyond just checking if it is on the path because it must be
compiled with support for both vsock and unix. The function
check_socat() checks that this support exists.
Add more padding to test name printf strings because the tests added in
this patch would otherwise overflow.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 463 +++++++++++++++++++++++++++++++-
1 file changed, 461 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index f2a99cde9fb4..60d349c80153 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -7,6 +7,7 @@
# * virtme-ng
# * busybox-static (used by virtme-ng)
# * qemu (used by virtme-ng)
+# * socat
readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../)
@@ -48,6 +49,19 @@ readonly TEST_NAMES=(
ns_local_same_cid_ok
ns_global_local_same_cid_ok
ns_local_global_same_cid_ok
+ ns_diff_global_host_connect_to_global_vm_ok
+ ns_diff_global_host_connect_to_local_vm_fails
+ ns_diff_global_vm_connect_to_global_host_ok
+ ns_diff_global_vm_connect_to_local_host_fails
+ ns_diff_local_host_connect_to_local_vm_fails
+ ns_diff_local_vm_connect_to_local_host_fails
+ ns_diff_global_to_local_loopback_local_fails
+ ns_diff_local_to_global_loopback_fails
+ ns_diff_local_to_local_loopback_fails
+ ns_diff_global_to_global_loopback_ok
+ ns_same_local_loopback_ok
+ ns_same_local_host_connect_to_local_vm_ok
+ ns_same_local_vm_connect_to_local_host_ok
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -76,6 +90,45 @@ readonly TEST_DESCS=(
# ns_local_global_same_cid_ok
"Check QEMU successfully starts one VM in a local ns and then another VM in a global ns with the same CID."
+
+ # ns_diff_global_host_connect_to_global_vm_ok
+ "Run vsock_test client in global ns with server in VM in another global ns."
+
+ # ns_diff_global_host_connect_to_local_vm_fails
+ "Run socat to test a process in a global ns fails to connect to a VM in a local ns."
+
+ # ns_diff_global_vm_connect_to_global_host_ok
+ "Run vsock_test client in VM in a global ns with server in another global ns."
+
+ # ns_diff_global_vm_connect_to_local_host_fails
+ "Run socat to test a VM in a global ns fails to connect to a host process in a local ns."
+
+ # ns_diff_local_host_connect_to_local_vm_fails
+ "Run socat to test a host process in a local ns fails to connect to a VM in another local ns."
+
+ # ns_diff_local_vm_connect_to_local_host_fails
+ "Run socat to test a VM in a local ns fails to connect to a host process in another local ns."
+
+ # ns_diff_global_to_local_loopback_local_fails
+ "Run socat to test a loopback vsock in a global ns fails to connect to a vsock in a local ns."
+
+ # ns_diff_local_to_global_loopback_fails
+ "Run socat to test a loopback vsock in a local ns fails to connect to a vsock in a global ns."
+
+ # ns_diff_local_to_local_loopback_fails
+ "Run socat to test a loopback vsock in a local ns fails to connect to a vsock in another local ns."
+
+ # ns_diff_global_to_global_loopback_ok
+ "Run socat to test a loopback vsock in a global ns successfully connects to a vsock in another global ns."
+
+ # ns_same_local_loopback_ok
+ "Run socat to test a loopback vsock in a local ns successfully connects to a vsock in the same ns."
+
+ # ns_same_local_host_connect_to_local_vm_ok
+ "Run vsock_test client in a local ns with server in VM in same ns."
+
+ # ns_same_local_vm_connect_to_local_host_ok
+ "Run vsock_test client in VM in a local ns with server in same ns."
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -102,7 +155,7 @@ usage() {
for ((i = 0; i < ${#TEST_NAMES[@]}; i++)); do
name=${TEST_NAMES[${i}]}
desc=${TEST_DESCS[${i}]}
- printf "\t%-35s%-35s\n" "${name}" "${desc}"
+ printf "\t%-55s%-35s\n" "${name}" "${desc}"
done
echo
@@ -222,7 +275,7 @@ check_args() {
}
check_deps() {
- for dep in vng ${QEMU} busybox pkill ssh; do
+ for dep in vng ${QEMU} busybox pkill ssh socat; do
if [[ ! -x $(command -v "${dep}") ]]; then
echo -e "skip: dependency ${dep} not found!\n"
exit "${KSFT_SKIP}"
@@ -273,6 +326,20 @@ check_vng() {
fi
}
+check_socat() {
+ local support_string
+
+ support_string="$(socat -V)"
+
+ if [[ "${support_string}" != *"WITH_VSOCK 1"* ]]; then
+ die "err: socat is missing vsock support"
+ fi
+
+ if [[ "${support_string}" != *"WITH_UNIX 1"* ]]; then
+ die "err: socat is missing unix support"
+ fi
+}
+
handle_build() {
if [[ ! "${BUILD}" -eq 1 ]]; then
return
@@ -310,6 +377,14 @@ terminate_pidfiles() {
done
}
+terminate_pids() {
+ local pid
+
+ for pid in "$@"; do
+ kill -SIGTERM "${pid}" &>/dev/null || :
+ done
+}
+
vm_start() {
local pidfile=$1
local ns=$2
@@ -564,6 +639,389 @@ test_ns_host_vsock_ns_mode_ok() {
return "${KSFT_PASS}"
}
+test_ns_diff_global_host_connect_to_global_vm_ok() {
+ local pids pid pidfile
+ local ns0 ns1 port
+ declare -a pids
+ local unixfile
+ ns0="global0"
+ ns1="global1"
+ port=1234
+ local rc
+
+ init_namespaces
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ unixfile=$(mktemp -u /tmp/XXXX.sock)
+ ip netns exec "${ns1}" \
+ socat TCP-LISTEN:"${TEST_HOST_PORT}",fork \
+ UNIX-CONNECT:"${unixfile}" &
+ pids+=($!)
+ host_wait_for_listener "${ns1}" "${TEST_HOST_PORT}"
+
+ ip netns exec "${ns0}" socat UNIX-LISTEN:"${unixfile}",fork \
+ TCP-CONNECT:localhost:"${TEST_HOST_PORT}" &
+ pids+=($!)
+
+ vm_vsock_test "${ns0}" "server" 2 "${TEST_GUEST_PORT}"
+ vm_wait_for_listener "${ns0}" "${TEST_GUEST_PORT}"
+ host_vsock_test "${ns1}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ for pid in "${pids[@]}"; do
+ if [[ "$(jobs -p)" = *"${pid}"* ]]; then
+ kill -SIGTERM "${pid}" &>/dev/null
+ fi
+ done
+
+ terminate_pidfiles "${pidfile}"
+
+ if [[ $rc -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_diff_global_host_connect_to_local_vm_fails() {
+ local ns0="global0"
+ local ns1="local0"
+ local port=12345
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ outfile=$(mktemp)
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns1}"; then
+ log_host "failed to start vm (cid=${VSOCK_CID}, ns=${ns0})"
+ return $KSFT_FAIL
+ fi
+
+ vm_wait_for_ssh "${ns1}"
+ vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" &
+ echo TEST | ip netns exec "${ns0}" \
+ socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null
+
+ terminate_pidfiles "${pidfile}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]]; then
+ return $KSFT_PASS
+ fi
+
+ return $KSFT_FAIL
+}
+
+test_ns_diff_global_vm_connect_to_global_host_ok() {
+ local ns0="global0"
+ local ns1="global1"
+ local port=12345
+ local unixfile
+ local pidfile
+ local pids
+
+ init_namespaces
+
+ declare -a pids
+
+ log_host "Setup socat bridge from ns ${ns0} to ns ${ns1} over port ${port}"
+
+ unixfile=$(mktemp -u /tmp/XXXX.sock)
+
+ ip netns exec "${ns0}" \
+ socat TCP-LISTEN:"${port}" UNIX-CONNECT:"${unixfile}" &
+ pids+=($!)
+
+ ip netns exec "${ns1}" \
+ socat UNIX-LISTEN:"${unixfile}" TCP-CONNECT:127.0.0.1:"${port}" &
+ pids+=($!)
+
+ log_host "Launching ${VSOCK_TEST} in ns ${ns1}"
+ host_vsock_test "${ns1}" "server" "${VSOCK_CID}" "${port}"
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ log_host "failed to start vm (cid=${cid}, ns=${ns0})"
+ terminate_pids "${pids[@]}"
+ rm -f "${unixfile}"
+ return $KSFT_FAIL
+ fi
+
+ vm_wait_for_ssh "${ns0}"
+ vm_vsock_test "${ns0}" "10.0.2.2" 2 "${port}"
+ rc=$?
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pids[@]}"
+ rm -f "${unixfile}"
+
+ if [[ ! $rc -eq 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+
+}
+
+test_ns_diff_global_vm_connect_to_local_host_fails() {
+ local ns0="global0"
+ local ns1="local0"
+ local port=12345
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ log_host "Launching socat in ns ${ns1}"
+ outfile=$(mktemp)
+ ip netns exec "${ns1}" socat VSOCK-LISTEN:${port} STDOUT &> "${outfile}" &
+ pid=$!
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ log_host "failed to start vm (cid=${cid}, ns=${ns0})"
+ terminate_pids "${pid}"
+ rm -f "${outfile}"
+ return $KSFT_FAIL
+ fi
+
+ vm_wait_for_ssh "${ns0}"
+
+ vm_ssh "${ns0}" -- \
+ bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pid}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]]; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_local_host_connect_to_local_vm_fails() {
+ local ns0="local0"
+ local ns1="local1"
+ local port=12345
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ outfile=$(mktemp)
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns1}"; then
+ log_host "failed to start vm (cid=${cid}, ns=${ns0})"
+ return $KSFT_FAIL
+ fi
+
+ vm_wait_for_ssh "${ns1}"
+ vm_ssh "${ns1}" -- socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" &
+ echo TEST | ip netns exec "${ns0}" \
+ socat STDIN VSOCK-CONNECT:"${VSOCK_CID}":"${port}" 2>/dev/null
+
+ terminate_pidfiles "${pidfile}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]]; then
+ return $KSFT_PASS
+ fi
+
+ return $KSFT_FAIL
+}
+
+test_ns_diff_local_vm_connect_to_local_host_fails() {
+ local ns0="local0"
+ local ns1="local1"
+ local port=12345
+ local pidfile
+ local result
+ local pid
+
+ init_namespaces
+
+ log_host "Launching socat in ns ${ns1}"
+ outfile=$(mktemp)
+ ip netns exec "${ns1}" socat VSOCK-LISTEN:"${port}" STDOUT &> "${outfile}" &
+ pid=$!
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+ if ! vm_start "${pidfile}" "${ns0}"; then
+ log_host "failed to start vm (cid=${cid}, ns=${ns0})"
+ rm -f "${outfile}"
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_wait_for_ssh "${ns0}"
+
+ vm_ssh "${ns0}" -- \
+ bash -c "echo TEST | socat STDIN VSOCK-CONNECT:2:${port}" 2>&1 | log_guest
+
+ terminate_pidfiles "${pidfile}"
+ terminate_pids "${pid}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" != TEST ]]; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+__test_loopback_two_netns() {
+ local ns0=$1
+ local ns1=$2
+ local port=12345
+ local result
+ local pid
+
+ modprobe vsock_loopback &> /dev/null || :
+
+ log_host "Launching socat in ns ${ns1}"
+ outfile=$(mktemp)
+ ip netns exec "${ns1}" socat VSOCK-LISTEN:"${port}" STDOUT > "${outfile}" 2>/dev/null &
+ pid=$!
+
+ log_host "Launching socat in ns ${ns0}"
+ echo TEST | ip netns exec "${ns0}" socat STDIN VSOCK-CONNECT:1:"${port}" 2>/dev/null
+ terminate_pids "${pid}"
+
+ result=$(cat "${outfile}")
+ rm -f "${outfile}"
+
+ if [[ "${result}" == TEST ]]; then
+ return 0
+ fi
+
+ return 1
+}
+
+test_ns_diff_global_to_local_loopback_local_fails() {
+ init_namespaces
+
+ if ! __test_loopback_two_netns "global0" "local0"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_local_to_global_loopback_fails() {
+ init_namespaces
+
+ if ! __test_loopback_two_netns "local0" "global0"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_local_to_local_loopback_fails() {
+ init_namespaces
+
+ if ! __test_loopback_two_netns "local0" "local1"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_diff_global_to_global_loopback_ok() {
+ init_namespaces
+
+ if __test_loopback_two_netns "global0" "global1"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_same_local_loopback_ok() {
+ init_namespaces
+
+ if __test_loopback_two_netns "local0" "local0"; then
+ return "${KSFT_PASS}"
+ fi
+
+ return "${KSFT_FAIL}"
+}
+
+test_ns_same_local_host_connect_to_local_vm_ok() {
+ local ns="local0"
+ local port=1234
+ local pidfile
+ local rc
+
+ init_namespaces
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+
+ if ! vm_start "${pidfile}" "${ns}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}"
+ host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ terminate_pidfiles "${pidfile}"
+
+ if [[ $rc -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_same_local_vm_connect_to_local_host_ok() {
+ local ns="local0"
+ local port=1234
+ local pidfile
+ local rc
+
+ init_namespaces
+
+ pidfile=$(mktemp $PIDFILE_TEMPLATE)
+
+ if ! vm_start "${pidfile}" "${ns}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ vm_vsock_test "${ns}" "server" 2 "${TEST_GUEST_PORT}"
+ host_vsock_test "${ns}" "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"
+ rc=$?
+
+ terminate_pidfiles "${pidfile}"
+
+ if [[ $rc -ne 0 ]]; then
+ return "${KSFT_FAIL}"
+ fi
+
+ return "${KSFT_PASS}"
+}
+
namespaces_can_boot_same_cid() {
local ns0=$1
local ns1=$2
@@ -820,6 +1278,7 @@ fi
check_args "${ARGS[@]}"
check_deps
check_vng
+check_socat
handle_build
echo "1..${#ARGS[@]}"
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v8 14/14] selftests/vsock: add tests for module loading order
From: Bobby Eshleman @ 2025-10-23 18:27 UTC (permalink / raw)
To: Stefano Garzarella, Shuah Khan, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, Stefan Hajnoczi,
Michael S. Tsirkin, Jason Wang, Xuan Zhuo, Eugenio Pérez,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan,
Vishnu Dasa, Broadcom internal kernel review list, Bobby Eshleman
Cc: virtualization, netdev, linux-kselftest, linux-kernel, kvm,
linux-hyperv, berrange, Bobby Eshleman
In-Reply-To: <20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add tests to check that module loading order does not break
vsock_loopback. Because vsock_loopback has some per-namespace data
structure initialization that affects vsock namespace modes, lets make
sure that namespace modes are respected and loopback sockets are
functional even when the namespaces and modes are set prior to loading
the vsock_loopback module.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 138 ++++++++++++++++++++++++++++++++
1 file changed, 138 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 014cecd93858..9aa3200b160f 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -68,6 +68,8 @@ readonly TEST_NAMES=(
ns_delete_vm_ok
ns_delete_host_ok
ns_delete_both_ok
+ ns_loopback_global_global_late_module_load_ok
+ ns_loopback_local_local_late_module_load_fails
)
readonly TEST_DESCS=(
# vm_server_host_client
@@ -153,6 +155,12 @@ readonly TEST_DESCS=(
# ns_delete_both_ok
"Check that deleting the VM and host's namespaces does not break the socket connection"
+
+ # ns_loopback_global_global_late_module_load_ok
+ "Test that loopback still works in global namespaces initialized prior to loading the vsock_loopback kmod"
+
+ # ns_loopback_local_local_late_module_load_fails
+ "Test that loopback connections still fail between local namespaces initialized prior to loading the vsock_loopback kmod"
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
@@ -914,6 +922,30 @@ test_ns_diff_local_vm_connect_to_local_host_fails() {
return "${KSFT_FAIL}"
}
+unload_module() {
+ local module=$1
+ local retries=5
+ readonly retries
+ local delay=1
+ local i
+
+ # Sometimes previously executed tests may result in a delayed release
+ # of the reference to the vsock_loopback module and result in the
+ # module being unremovable. For that reason, we use retries to allow
+ # some time for those references to be dropped.
+ for ((i = 0; i < ${retries}; i++)); do
+ modprobe -r "${module}" 2>/dev/null || :
+
+ if [[ "$(lsmod | grep -c ${module})" -eq 0 ]]; then
+ return 0
+ fi
+
+ sleep ${delay}
+ done
+
+ return 1
+}
+
__test_loopback_two_netns() {
local ns0=$1
local ns1=$2
@@ -1266,6 +1298,112 @@ test_ns_delete_both_ok() {
check_ns_changes_dont_break_connection "both" "delete"
}
+test_ns_loopback_global_global_late_module_load_ok() {
+ declare -a pids
+ local unixfile
+ local ns0 ns1
+ local pids
+ local port
+
+ if ! unload_module vsock_loopback; then
+ log_host "Unable to unload vsock_loopback, skipping..."
+ return "${KSFT_SKIP}"
+ fi
+
+ ns0=loopback_ns0
+ ns1=loopback_ns1
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ ip netns add "${ns0}"
+ ip netns add "${ns1}"
+ ns_set_mode "${ns0}" global
+ ns_set_mode "${ns1}" global
+ ip netns exec "${ns0}" ip link set dev lo up
+ ip netns exec "${ns1}" ip link set dev lo up
+
+ modprobe vsock_loopback &> /dev/null || :
+
+ unixfile=$(mktemp -u /tmp/XXXX.sock)
+ port=321
+ ip netns exec "${ns1}" \
+ socat TCP-LISTEN:"${port}",fork \
+ UNIX-CONNECT:"${unixfile}" &
+ pids+=($!)
+
+ host_wait_for_listener "${ns1}" "${port}"
+ ip netns exec "${ns0}" socat UNIX-LISTEN:"${unixfile}",fork \
+ TCP-CONNECT:localhost:"${port}" &
+ pids+=($!)
+
+ if ! host_vsock_test "${ns0}" "server" 1 "${port}"; then
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ return "${KSFT_FAIL}"
+ fi
+
+ if ! host_vsock_test "${ns1}" "127.0.0.1" 1 "${port}"; then
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ return "${KSFT_FAIL}"
+ fi
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_loopback_local_local_late_module_load_fails() {
+ declare -a pids
+ local ns0 ns1
+ local outfile
+ local pids
+ local rc
+
+ if ! unload_module vsock_loopback; then
+ log_host "Unable to unload vsock_loopback, skipping..."
+ return "${KSFT_SKIP}"
+ fi
+
+ ns0=loopback_ns0
+ ns1=loopback_ns1
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ ip netns add "${ns0}"
+ ip netns add "${ns1}"
+ ns_set_mode "${ns0}" local
+ ns_set_mode "${ns1}" local
+
+ modprobe vsock_loopback &> /dev/null || :
+
+ outfile=$(mktemp /tmp/XXXX.vmtest.out)
+ ip netns exec "${ns0}" socat VSOCK-LISTEN:${port} STDOUT \
+ > "${outfile}" 2>/dev/null &
+ pids+=($!)
+
+ echo TEST | \
+ ip netns exec "${ns1}" socat STDIN VSOCK-CONNECT:1:${port} \
+ 2>/dev/null
+
+ if grep -q "TEST" "${outfile}" 2>/dev/null; then
+ rc="${KSFT_FAIL}"
+ else
+ rc="${KSFT_PASS}"
+ fi
+
+ ip netns del "${ns0}" &>/dev/null || :
+ ip netns del "${ns1}" &>/dev/null || :
+ terminate_pids "${pids[@]}"
+ rm -f "${outfile}"
+
+ return "${rc}"
+}
+
shared_vm_test() {
local tname
--
2.47.3
^ 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