* [PATCH net-next v12 09/12] selftests/vsock: add tests for proc sys vsock ns_mode
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@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.
Add a test to verify that guest VMs with an active G2H transport
(virtio-vsock) cannot set namespace mode to 'local'. This validates
the mutual exclusion between G2H transports and LOCAL mode.
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.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v12:
- remove ns_vm_local_mode_rejected test, due to dropping that constraint
Changes in v11:
- Document ns_ prefix above TEST_NAMES (Stefano)
Changes in v10:
- Remove extraneous add_namespaces/del_namespaces calls.
- Rename run_tests() to run_ns_tests() since it is designed to only
run ns tests.
Changes in v9:
- add test ns_vm_local_mode_rejected to check that guests cannot use
local mode
---
tools/testing/selftests/vsock/vmtest.sh | 118 +++++++++++++++++++++++++++++++-
1 file changed, 116 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index e32997db322d..28b91b906cdc 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -41,14 +41,38 @@ 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)
+
+# Namespace tests must use the ns_ prefix. This is checked in check_netns() and
+# is used to determine if a test needs namespace setup before test execution.
+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)
+readonly USE_SHARED_VM=(
+ vm_server_host_client
+ vm_client_host_server
+ vm_loopback
+)
readonly NS_MODES=("local" "global")
VERBOSE=0
@@ -205,6 +229,20 @@ 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 ${tname}"
+ return 1
+ fi
+
+ return 0
+}
+
check_vng() {
local tested_versions
local version
@@ -528,6 +566,32 @@ log_guest() {
LOG_PREFIX=guest log "$@"
}
+test_ns_host_vsock_ns_mode_ok() {
+ for mode in "${NS_MODES[@]}"; do
+ if ! ns_set_mode "${mode}0" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ return "${KSFT_PASS}"
+}
+
+test_ns_host_vsock_ns_mode_write_once_ok() {
+ for mode in "${NS_MODES[@]}"; do
+ local ns="${mode}0"
+ if ! ns_set_mode "${ns}" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+
+ # try writing again and expect failure
+ if ns_set_mode "${ns}" "${mode}"; then
+ return "${KSFT_FAIL}"
+ fi
+ done
+
+ return "${KSFT_PASS}"
+}
+
test_vm_server_host_client() {
if ! vm_vsock_test "init_ns" "server" 2 "${TEST_GUEST_PORT}"; then
return "${KSFT_FAIL}"
@@ -601,6 +665,11 @@ run_shared_vm_tests() {
continue
fi
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}" "${arg}"
+ continue
+ fi
+
run_shared_vm_test "${arg}"
check_result "$?" "${arg}"
done
@@ -654,6 +723,49 @@ run_shared_vm_test() {
return "${rc}"
}
+run_ns_tests() {
+ for arg in "${ARGS[@]}"; do
+ if shared_vm_test "${arg}"; then
+ continue
+ fi
+
+ if ! check_netns "${arg}"; then
+ check_result "${KSFT_SKIP}" "${arg}"
+ continue
+ fi
+
+ add_namespaces
+
+ name=$(echo "${arg}" | awk '{ print $1 }')
+ log_host "Executing test_${name}"
+
+ host_oops_before=$(dmesg 2>/dev/null | grep -c -i 'Oops')
+ host_warn_before=$(dmesg --level=warn 2>/dev/null | grep -c -i 'vsock')
+ eval test_"${name}"
+ rc=$?
+
+ host_oops_after=$(dmesg 2>/dev/null | grep -c -i 'Oops')
+ if [[ "${host_oops_after}" -gt "${host_oops_before}" ]]; then
+ echo "FAIL: kernel oops detected on host" | log_host
+ check_result "${KSFT_FAIL}" "${name}"
+ del_namespaces
+ continue
+ fi
+
+ host_warn_after=$(dmesg --level=warn 2>/dev/null | grep -c -i 'vsock')
+ if [[ "${host_warn_after}" -gt "${host_warn_before}" ]]; then
+ echo "FAIL: kernel warning detected on host" | log_host
+ check_result "${KSFT_FAIL}" "${name}"
+ del_namespaces
+ continue
+ fi
+
+ check_result "${rc}" "${name}"
+
+ del_namespaces
+ done
+}
+
BUILD=0
QEMU="qemu-system-$(uname -m)"
@@ -699,6 +811,8 @@ if shared_vm_tests_requested "${ARGS[@]}"; then
terminate_pidfiles "${pidfile}"
fi
+run_ns_tests "${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 v12 08/12] selftests/vsock: use ss to wait for listeners instead of /proc/net
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Replace /proc/net parsing with ss(8) for detecting listening sockets in
wait_for_listener() functions and add support for TCP, VSOCK, and Unix
socket protocols.
The previous implementation parsed /proc/net/tcp using awk to detect
listening sockets, but this approach could not support vsock because
vsock does not export socket information to /proc/net/.
Instead, use ss so that we can detect listeners on tcp, vsock, and unix.
The protocol parameter is now required for all wait_for_listener family
functions (wait_for_listener, vm_wait_for_listener,
host_wait_for_listener) to explicitly specify which socket type to wait
for.
ss is added to the dependency check in check_deps().
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 47 +++++++++++++++++++++------------
1 file changed, 30 insertions(+), 17 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 1623e4da15e2..e32997db322d 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -191,7 +191,7 @@ check_args() {
}
check_deps() {
- for dep in vng ${QEMU} busybox pkill ssh; do
+ for dep in vng ${QEMU} busybox pkill ssh ss; do
if [[ ! -x $(command -v "${dep}") ]]; then
echo -e "skip: dependency ${dep} not found!\n"
exit "${KSFT_SKIP}"
@@ -346,21 +346,32 @@ wait_for_listener()
local port=$1
local interval=$2
local max_intervals=$3
- local protocol=tcp
- local pattern
+ local protocol=$4
local i
- pattern=":$(printf "%04X" "${port}") "
-
- # for tcp protocol additionally check the socket state
- [ "${protocol}" = "tcp" ] && pattern="${pattern}0A"
-
for i in $(seq "${max_intervals}"); do
- if awk -v pattern="${pattern}" \
- 'BEGIN {rc=1} $2" "$4 ~ pattern {rc=0} END {exit rc}' \
- /proc/net/"${protocol}"*; then
+ case "${protocol}" in
+ tcp)
+ if ss --listening --tcp --numeric | grep -q ":${port} "; then
+ break
+ fi
+ ;;
+ vsock)
+ if ss --listening --vsock --numeric | grep -q ":${port} "; then
+ break
+ fi
+ ;;
+ unix)
+ # For unix sockets, port is actually the socket path
+ if ss --listening --unix | grep -q "${port}"; then
+ break
+ fi
+ ;;
+ *)
+ echo "Unknown protocol: ${protocol}" >&2
break
- fi
+ ;;
+ esac
sleep "${interval}"
done
}
@@ -368,23 +379,25 @@ wait_for_listener()
vm_wait_for_listener() {
local ns=$1
local port=$2
+ local protocol=$3
vm_ssh "${ns}" <<EOF
$(declare -f wait_for_listener)
-wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
+wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} ${protocol}
EOF
}
host_wait_for_listener() {
local ns=$1
local port=$2
+ local protocol=$3
if [[ "${ns}" == "init_ns" ]]; then
- wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" "${protocol}"
else
ip netns exec "${ns}" bash <<-EOF
$(declare -f wait_for_listener)
- wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
+ wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX} ${protocol}
EOF
fi
}
@@ -431,7 +444,7 @@ vm_vsock_test() {
return $rc
fi
- vm_wait_for_listener "${ns}" "${port}"
+ vm_wait_for_listener "${ns}" "${port}" "tcp"
rc=$?
fi
set +o pipefail
@@ -472,7 +485,7 @@ host_vsock_test() {
return $rc
fi
- host_wait_for_listener "${ns}" "${port}"
+ host_wait_for_listener "${ns}" "${port}" "tcp"
rc=$?
fi
set +o pipefail
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 07/12] selftests/vsock: add vm_dmesg_{warn,oops}_count() helpers
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
These functions are reused by the VM tests to collect and compare dmesg
warnings and oops counts. The future VM-specific tests use them heavily.
This patches relies on vm_ssh() already supporting namespaces.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v11:
- break these out into an earlier patch so that they can be used
directly in new patches (instead of causing churn by adding this
later)
---
tools/testing/selftests/vsock/vmtest.sh | 19 +++++++++++++++----
1 file changed, 15 insertions(+), 4 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index 4da91828a6a0..1623e4da15e2 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -389,6 +389,17 @@ host_wait_for_listener() {
fi
}
+vm_dmesg_oops_count() {
+ local ns=$1
+
+ vm_ssh "${ns}" -- dmesg 2>/dev/null | grep -c -i 'Oops'
+}
+
+vm_dmesg_warn_count() {
+ local ns=$1
+
+ vm_ssh "${ns}" -- dmesg --level=warn 2>/dev/null | grep -c -i 'vsock'
+}
vm_vsock_test() {
local ns=$1
@@ -596,8 +607,8 @@ run_shared_vm_test() {
host_oops_cnt_before=$(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_dmesg_oops_count "init_ns")
+ vm_warn_cnt_before=$(vm_dmesg_warn_count "init_ns")
name=$(echo "${1}" | awk '{ print $1 }')
eval test_"${name}"
@@ -615,13 +626,13 @@ 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_dmesg_oops_count "init_ns")
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_dmesg_warn_count "init_ns")
if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then
echo "FAIL: kernel warning detected on vm" | log_host
rc=$KSFT_FAIL
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 06/12] selftests/vsock: prepare vm management helpers for namespaces
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@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.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 93 +++++++++++++++++++++++----------
1 file changed, 65 insertions(+), 28 deletions(-)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index f78cc574c274..4da91828a6a0 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -144,7 +144,18 @@ 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 $?
}
@@ -267,10 +278,12 @@ 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 "${QEMU}")
@@ -291,7 +304,11 @@ vm_start() {
kernel_opt="${KERNEL_CHECKOUT}"
fi
- vng \
+ if [[ "${ns}" != "init_ns" ]]; then
+ ns_exec="ip netns exec ${ns}"
+ fi
+
+ ${ns_exec} vng \
--run \
${kernel_opt} \
${verbose_opt} \
@@ -306,6 +323,7 @@ vm_start() {
}
vm_wait_for_ssh() {
+ local ns=$1
local i
i=0
@@ -313,7 +331,8 @@ 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 ))
@@ -347,30 +366,41 @@ wait_for_listener()
}
vm_wait_for_listener() {
- local port=$1
+ local ns=$1
+ local port=$2
- vm_ssh <<EOF
+ vm_ssh "${ns}" <<EOF
$(declare -f wait_for_listener)
wait_for_listener ${port} ${WAIT_PERIOD} ${WAIT_PERIOD_MAX}
EOF
}
host_wait_for_listener() {
- local port=$1
+ local ns=$1
+ local port=$2
- wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}"
+ 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=$4
local rc
# log output and use pipefail to respect vsock_test errors
set -o pipefail
if [[ "${host}" != server ]]; then
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=client \
--control-host="${host}" \
--peer-cid="${cid}" \
@@ -378,7 +408,7 @@ vm_vsock_test() {
2>&1 | log_guest
rc=$?
else
- vm_ssh -- "${VSOCK_TEST}" \
+ vm_ssh "${ns}" -- "${VSOCK_TEST}" \
--mode=server \
--peer-cid="${cid}" \
--control-port="${port}" \
@@ -390,7 +420,7 @@ vm_vsock_test() {
return $rc
fi
- vm_wait_for_listener "${port}"
+ vm_wait_for_listener "${ns}" "${port}"
rc=$?
fi
set +o pipefail
@@ -399,22 +429,28 @@ 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 &
@@ -425,7 +461,7 @@ host_vsock_test() {
return $rc
fi
- host_wait_for_listener "${port}"
+ host_wait_for_listener "${ns}" "${port}"
rc=$?
fi
set +o pipefail
@@ -469,11 +505,11 @@ log_guest() {
}
test_vm_server_host_client() {
- if ! vm_vsock_test "server" 2 "${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 "${KSFT_FAIL}"
fi
@@ -481,11 +517,11 @@ test_vm_server_host_client() {
}
test_vm_client_host_server() {
- if ! host_vsock_test "server" "${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 "${KSFT_FAIL}"
fi
@@ -495,13 +531,14 @@ test_vm_client_host_server() {
test_vm_loopback() {
local port=60000 # non-forwarded local port
- vm_ssh -- modprobe vsock_loopback &> /dev/null || :
+ vm_ssh "init_ns" -- modprobe vsock_loopback &> /dev/null || :
- if ! vm_vsock_test "server" 1 "${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 "${KSFT_FAIL}"
fi
@@ -630,8 +667,8 @@ cnt_total=0
if shared_vm_tests_requested "${ARGS[@]}"; then
log_host "Booting up VM"
pidfile="$(create_pidfile)"
- vm_start "${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 v12 05/12] selftests/vsock: add namespace helpers to vmtest.sh
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@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.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
tools/testing/selftests/vsock/vmtest.sh | 41 +++++++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh
index c7b270dd77a9..f78cc574c274 100755
--- a/tools/testing/selftests/vsock/vmtest.sh
+++ b/tools/testing/selftests/vsock/vmtest.sh
@@ -49,6 +49,7 @@ readonly TEST_DESCS=(
)
readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback)
+readonly NS_MODES=("local" "global")
VERBOSE=0
@@ -103,6 +104,45 @@ check_result() {
fi
}
+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 $?
@@ -110,6 +150,7 @@ vm_ssh() {
cleanup() {
terminate_pidfiles "${!PIDFILES[@]}"
+ del_namespaces
}
check_args() {
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 04/12] vsock: add netns support to virtio transports
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Add netns support to loopback and vhost. Keep netns disabled for
virtio-vsock, but add necessary changes to comply with common API
updates.
This is the patch in the series when vhost-vsock namespaces actually
come online. Hence, vhost_transport_supports_local_mode() is switched
to return true.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v12:
- change seqpacket_allow() and stream_allow() to return true for
loopback and vhost (Stefano)
Changes in v11:
- reorder with the skb ownership patch for loopback (Stefano)
- toggle vhost_transport_supports_local_mode() to true
Changes in v10:
- Splitting patches complicates the series with meaningless placeholder
values that eventually get replaced anyway, so to avoid that this
patch combines into one. Links to previous patches here:
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-3-852787a37bed@meta.com/
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-6-852787a37bed@meta.com/
- Link: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-7-852787a37bed@meta.com/
- remove placeholder values (Stefano)
- update comment describe net/net_mode for
virtio_transport_reset_no_sock()
---
drivers/vhost/vsock.c | 56 +++++++++++++++++++++--------
include/linux/virtio_vsock.h | 8 +++--
net/vmw_vsock/virtio_transport.c | 10 ++++--
net/vmw_vsock/virtio_transport_common.c | 63 ++++++++++++++++++++++++---------
net/vmw_vsock/vsock_loopback.c | 19 +++++++---
5 files changed, 118 insertions(+), 38 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 83937e1d63fa..82cb9ec09e78 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 +84,10 @@ 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;
@@ -269,7 +276,8 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work)
}
static int
-vhost_transport_send_pkt(struct sk_buff *skb)
+vhost_transport_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct vhost_vsock *vsock;
@@ -278,7 +286,7 @@ vhost_transport_send_pkt(struct sk_buff *skb)
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, 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;
@@ -407,6 +416,12 @@ static bool vhost_transport_msgzerocopy_allow(void)
static bool vhost_transport_seqpacket_allow(struct vsock_sock *vsk,
u32 remote_cid);
+static bool
+vhost_transport_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port)
+{
+ return true;
+}
+
static struct virtio_transport vhost_transport = {
.transport = {
.module = THIS_MODULE,
@@ -431,7 +446,7 @@ static struct virtio_transport vhost_transport = {
.stream_has_space = virtio_transport_stream_has_space,
.stream_rcvhiwat = virtio_transport_stream_rcvhiwat,
.stream_is_active = virtio_transport_stream_is_active,
- .stream_allow = virtio_transport_stream_allow,
+ .stream_allow = vhost_transport_stream_allow,
.seqpacket_dequeue = virtio_transport_seqpacket_dequeue,
.seqpacket_enqueue = virtio_transport_seqpacket_enqueue,
@@ -464,14 +479,12 @@ 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;
- if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
- return 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;
@@ -542,7 +555,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid &&
le64_to_cpu(hdr->dst_cid) ==
vhost_transport_get_local_cid())
- virtio_transport_recv_pkt(&vhost_transport, skb);
+ virtio_transport_recv_pkt(&vhost_transport, skb,
+ vsock->net, vsock->net_mode);
else
kfree_skb(skb);
@@ -659,6 +673,7 @@ 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
@@ -674,6 +689,17 @@ 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);
+
+ /* Store the mode of the namespace at the time of creation. If this
+ * namespace later changes from "global" to "local", we want this vsock
+ * to continue operating normally and not suddenly break. For that
+ * reason, we save the mode here and later use it when performing
+ * socket lookups with vsock_net_check_mode() (see vhost_vsock_get()).
+ */
+ vsock->net_mode = vsock_net_mode(net);
+
vsock->guest_cid = 0; /* no CID assigned yet */
vsock->seqpacket_allow = false;
@@ -713,7 +739,8 @@ 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
@@ -758,6 +785,7 @@ 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;
@@ -784,7 +812,7 @@ 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;
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 1845e8d4f78d..7ea264dcfff7 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -173,6 +173,8 @@ struct virtio_vsock_pkt_info {
u32 remote_cid, remote_port;
struct vsock_sock *vsk;
struct msghdr *msg;
+ struct net *net;
+ enum vsock_net_mode net_mode;
u32 pkt_len;
u16 type;
u16 op;
@@ -185,7 +187,8 @@ struct virtio_transport {
struct vsock_transport transport;
/* Takes ownership of the packet */
- int (*send_pkt)(struct sk_buff *skb);
+ int (*send_pkt)(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode);
/* Used in MSG_ZEROCOPY mode. Checks, that provided data
* (number of buffers) could be transmitted with zerocopy
@@ -280,7 +283,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
void virtio_transport_destruct(struct vsock_sock *vsk);
void virtio_transport_recv_pkt(struct virtio_transport *t,
- struct sk_buff *skb);
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode);
void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff *skb);
u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index f5123810192d..3ff695740108 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -231,7 +231,8 @@ static int virtio_transport_send_skb_fast_path(struct virtio_vsock *vsock, struc
}
static int
-virtio_transport_send_pkt(struct sk_buff *skb)
+virtio_transport_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr;
struct virtio_vsock *vsock;
@@ -665,7 +666,12 @@ static void virtio_transport_rx_work(struct work_struct *work)
virtio_vsock_skb_put(skb, payload_len);
virtio_transport_deliver_tap_pkt(skb);
- virtio_transport_recv_pkt(&virtio_transport, skb);
+
+ /* Force virtio-transport into global mode since it
+ * does not yet support local-mode namespacing.
+ */
+ virtio_transport_recv_pkt(&virtio_transport, skb,
+ NULL, VSOCK_NET_MODE_GLOBAL);
}
} while (!virtqueue_enable_cb(vq));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index de71e2b3f77e..a818152d8b79 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -413,7 +413,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
virtio_transport_inc_tx_pkt(vvs, skb);
- ret = t_ops->send_pkt(skb);
+ ret = t_ops->send_pkt(skb, info->net, info->net_mode);
if (ret < 0)
break;
@@ -527,6 +527,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1067,6 +1069,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1082,6 +1086,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1108,6 +1114,8 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1145,6 +1153,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
.op = VIRTIO_VSOCK_OP_RST,
.reply = !!skb,
.vsk = vsk,
+ .net = sock_net(sk_vsock(vsk)),
+ .net_mode = vsk->net_mode,
};
/* Send RST only if the original pkt is not a RST pkt */
@@ -1156,9 +1166,14 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
/* Normally packets are associated with a socket. There may be no socket if an
* attempt was made to connect to a socket that does not exist.
+ *
+ * net and net_mode refer to the namespace of whoever sent the invalid message.
+ * For loopback, this is the namespace of the socket. For vhost, this is the
+ * namespace of the VM (i.e., vhost_vsock).
*/
static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct virtio_vsock_pkt_info info = {
@@ -1171,6 +1186,13 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
* sock_net(sk) until the reply skb is freed.
*/
.vsk = vsock_sk(skb->sk),
+
+ /* net or net_mode are not defined here because we pass
+ * net and net_mode directly to t->send_pkt(), instead of
+ * relying on virtio_transport_send_pkt_info() to pass them to
+ * t->send_pkt(). They are not needed by
+ * virtio_transport_alloc_skb().
+ */
};
struct sk_buff *reply;
@@ -1189,7 +1211,7 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
if (!reply)
return -ENOMEM;
- return t->send_pkt(reply);
+ return t->send_pkt(reply, net, net_mode);
}
/* This function should be called with sk_lock held and SOCK_DONE set */
@@ -1471,6 +1493,8 @@ 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)),
+ .net_mode = vsk->net_mode,
};
return virtio_transport_send_pkt_info(vsk, &info);
@@ -1513,12 +1537,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
int ret;
if (le16_to_cpu(hdr->op) != VIRTIO_VSOCK_OP_REQUEST) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ENOMEM;
}
@@ -1526,13 +1552,15 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
* Subsequent enqueues would lead to a memory leak.
*/
if (sk->sk_shutdown == SHUTDOWN_MASK) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ESHUTDOWN;
}
child = vsock_create_connected(sk);
if (!child) {
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
return -ENOMEM;
}
@@ -1554,7 +1582,8 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
*/
if (ret || vchild->transport != &t->transport) {
release_sock(child);
- virtio_transport_reset_no_sock(t, skb);
+ virtio_transport_reset_no_sock(t, skb, sock_net(sk),
+ vsk->net_mode);
sock_put(child);
return ret;
}
@@ -1582,7 +1611,8 @@ static bool virtio_transport_valid_type(u16 type)
* lock.
*/
void virtio_transport_recv_pkt(struct virtio_transport *t,
- struct sk_buff *skb)
+ struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
struct sockaddr_vm src, dst;
@@ -1605,24 +1635,25 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
le32_to_cpu(hdr->fwd_cnt));
if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
goto free_pkt;
}
/* 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);
+ (void)virtio_transport_reset_no_sock(t, skb, net,
+ net_mode);
goto free_pkt;
}
}
if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
sock_put(sk);
goto free_pkt;
}
@@ -1641,7 +1672,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
*/
if (sock_flag(sk, SOCK_DONE) ||
(sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
release_sock(sk);
sock_put(sk);
goto free_pkt;
@@ -1673,7 +1704,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
kfree_skb(skb);
break;
default:
- (void)virtio_transport_reset_no_sock(t, skb);
+ (void)virtio_transport_reset_no_sock(t, skb, net, net_mode);
kfree_skb(skb);
break;
}
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index afad27cf533a..aef44d1631c3 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -26,7 +26,8 @@ static u32 vsock_loopback_get_local_cid(void)
return VMADDR_CID_LOCAL;
}
-static int vsock_loopback_send_pkt(struct sk_buff *skb)
+static int vsock_loopback_send_pkt(struct sk_buff *skb, struct net *net,
+ enum vsock_net_mode net_mode)
{
struct vsock_loopback *vsock = &the_vsock_loopback;
int len = skb->len;
@@ -48,6 +49,13 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
static bool vsock_loopback_seqpacket_allow(struct vsock_sock *vsk,
u32 remote_cid);
+
+static bool vsock_loopback_stream_allow(struct vsock_sock *vsk, u32 cid,
+ u32 port)
+{
+ return true;
+}
+
static bool vsock_loopback_msgzerocopy_allow(void)
{
return true;
@@ -77,7 +85,7 @@ static struct virtio_transport loopback_transport = {
.stream_has_space = virtio_transport_stream_has_space,
.stream_rcvhiwat = virtio_transport_stream_rcvhiwat,
.stream_is_active = virtio_transport_stream_is_active,
- .stream_allow = virtio_transport_stream_allow,
+ .stream_allow = vsock_loopback_stream_allow,
.seqpacket_dequeue = virtio_transport_seqpacket_dequeue,
.seqpacket_enqueue = virtio_transport_seqpacket_enqueue,
@@ -110,7 +118,7 @@ static struct virtio_transport loopback_transport = {
static bool
vsock_loopback_seqpacket_allow(struct vsock_sock *vsk, u32 remote_cid)
{
- return vsk->net_mode == VSOCK_NET_MODE_GLOBAL;
+ return true;
}
static void vsock_loopback_work(struct work_struct *work)
@@ -132,7 +140,10 @@ static void vsock_loopback_work(struct work_struct *work)
*/
virtio_transport_consume_skb_sent(skb, false);
virtio_transport_deliver_tap_pkt(skb);
- virtio_transport_recv_pkt(&loopback_transport, skb);
+
+ virtio_transport_recv_pkt(&loopback_transport, skb,
+ sock_net(skb->sk),
+ vsock_sk(skb->sk)->net_mode);
}
}
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 03/12] virtio: set skb owner of virtio_transport_reset_no_sock() reply
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@meta.com>
From: Bobby Eshleman <bobbyeshleman@meta.com>
Associate reply packets with the sending socket. When vsock must reply
with an RST packet and there exists a sending socket (e.g., for
loopback), setting the skb owner to the socket correctly handles
reference counting between the skb and sk (i.e., the sk stays alive
until the skb is freed).
This allows the net namespace to be used for socket lookups for the
duration of the reply skb's lifetime, preventing race conditions between
the namespace lifecycle and vsock socket search using the namespace
pointer.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v11:
- move before adding to netns support (Stefano)
Changes in v10:
- break this out into its own patch for easy revert (Stefano)
---
net/vmw_vsock/virtio_transport_common.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index e6391eb7cc1b..de71e2b3f77e 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1165,6 +1165,12 @@ static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(hdr->type),
.reply = true,
+
+ /* Set sk owner to socket we are replying to (may be NULL for
+ * non-loopback). This keeps a reference to the sock and
+ * sock_net(sk) until the reply skb is freed.
+ */
+ .vsk = vsock_sk(skb->sk),
};
struct sk_buff *reply;
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 02/12] vsock: add netns to vsock core
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@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".
This patch also introduces the sysctl /proc/sys/net/vsock/ns_mode that
accepts the "global" or "local" mode strings.
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.
dgram_allow(), stream_allow(), and seqpacket_allow() callbacks are
modified to take a vsk in order to perform logic on namespace modes. In
future patches, the net and net_mode will also be used for socket
lookups in these functions.
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v12:
- return true in dgram_allow(), stream_allow(), and seqpacket_allow()
only if net_mode == VSOCK_NET_MODE_GLOBAL (Stefano)
- document bind(VMADDR_CID_ANY) case in af_vsock.c (Stefano)
- change order of stream_allow() call in vmci so we can pass vsk
to it
Changes in v10:
- add file-level comment about what happens to sockets/devices
when the namespace mode changes (Stefano)
- change the 'if (write)' boolean in vsock_net_mode_string() to
if (!write), this simplifies a later patch which adds "goto"
for mutex unlocking on function exit.
Changes in v9:
- remove virtio_vsock_alloc_rx_skb() (Stefano)
- remove vsock_global_dummy_net, not needed as net=NULL +
net_mode=VSOCK_NET_MODE_GLOBAL achieves identical result
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 | 9 +-
include/linux/virtio_vsock.h | 4 +-
include/net/af_vsock.h | 13 +-
net/vmw_vsock/af_vsock.c | 272 +++++++++++++++++++++++++++++---
net/vmw_vsock/hyperv_transport.c | 7 +-
net/vmw_vsock/virtio_transport.c | 9 +-
net/vmw_vsock/virtio_transport_common.c | 6 +-
net/vmw_vsock/vmci_transport.c | 26 ++-
net/vmw_vsock/vsock_loopback.c | 8 +-
9 files changed, 310 insertions(+), 44 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ae01457ea2cd..83937e1d63fa 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -404,7 +404,8 @@ 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 = {
@@ -460,11 +461,15 @@ 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;
+ if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
+ return false;
+
rcu_read_lock();
vsock = vhost_vsock_get(remote_cid);
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 0c67543a45c8..1845e8d4f78d 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -256,10 +256,10 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val);
u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
-bool virtio_transport_stream_allow(u32 cid, u32 port);
+bool virtio_transport_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port);
int virtio_transport_dgram_bind(struct vsock_sock *vsk,
struct sockaddr_vm *addr);
-bool virtio_transport_dgram_allow(u32 cid, u32 port);
+bool virtio_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port);
int virtio_transport_connect(struct vsock_sock *vsk);
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 9b5bdd083b6f..d10e73cd7413 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -126,7 +126,7 @@ struct vsock_transport {
size_t len, int flags);
int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *,
struct msghdr *, size_t len);
- bool (*dgram_allow)(u32 cid, u32 port);
+ bool (*dgram_allow)(struct vsock_sock *vsk, u32 cid, u32 port);
/* STREAM. */
/* TODO: stream_bind() */
@@ -138,14 +138,14 @@ struct vsock_transport {
s64 (*stream_has_space)(struct vsock_sock *);
u64 (*stream_rcvhiwat)(struct vsock_sock *);
bool (*stream_is_active)(struct vsock_sock *);
- bool (*stream_allow)(u32 cid, u32 port);
+ bool (*stream_allow)(struct vsock_sock *vsk, u32 cid, u32 port);
/* SEQ_PACKET. */
ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
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 +218,13 @@ 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));
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index adcba1b7bf74..6113c22db8dc 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -83,6 +83,46 @@
* 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.
+ * - sockets bound to VMADDR_CID_ANY in local namespaces will never resolve
+ * to any transport that is not compatible with local mode. There is no
+ * error that propagates to the user (as there is for connection attempts)
+ * because it is possible for some packet to reach this socket from
+ * a different transport that *does* support local mode. For
+ * example, virtio-vsock may not support local mode, but the socket
+ * may still accept a connection from vhost-vsock which does.
+ *
+ * - when a socket or device is initialized in a namespace with mode
+ * global, it will stay in global mode even if the namespace later
+ * changes to local.
*/
#include <linux/compat.h>
@@ -100,6 +140,7 @@
#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 +152,18 @@
#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);
@@ -235,33 +285,47 @@ 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 +368,14 @@ 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 +383,23 @@ 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, NULL, 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 +407,14 @@ 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,
+ NULL, VSOCK_NET_MODE_GLOBAL);
+}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
@@ -528,7 +610,7 @@ 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 +758,7 @@ 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 +778,8 @@ 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 +796,8 @@ 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 +921,8 @@ 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;
}
@@ -1314,7 +1401,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
goto out;
}
- if (!transport->dgram_allow(remote_addr->svm_cid,
+ if (!transport->dgram_allow(vsk, remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -EINVAL;
goto out;
@@ -1355,7 +1442,7 @@ static int vsock_dgram_connect(struct socket *sock,
if (err)
goto out;
- if (!vsk->transport->dgram_allow(remote_addr->svm_cid,
+ if (!vsk->transport->dgram_allow(vsk, remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -EINVAL;
goto out;
@@ -1585,7 +1672,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr,
* endpoints.
*/
if (!transport ||
- !transport->stream_allow(remote_addr->svm_cid,
+ !transport->stream_allow(vsk, remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -ENETUNREACH;
goto out;
@@ -2658,6 +2745,142 @@ 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)
+ return 0;
+
+ 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)
+{
+ 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;
@@ -2685,10 +2908,18 @@ 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_bpf_build_proto();
return 0;
+err_unregister_sock:
+ sock_unregister(AF_VSOCK);
err_unregister_proto:
proto_unregister(&vsock_proto);
err_deregister_misc:
@@ -2702,6 +2933,7 @@ 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/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 432fcbbd14d4..b2ade188c8c7 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -570,7 +570,7 @@ static int hvs_dgram_enqueue(struct vsock_sock *vsk,
return -EOPNOTSUPP;
}
-static bool hvs_dgram_allow(u32 cid, u32 port)
+static bool hvs_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port)
{
return false;
}
@@ -745,8 +745,11 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk)
return hvs->chan != NULL;
}
-static bool hvs_stream_allow(u32 cid, u32 port)
+static bool hvs_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port)
{
+ if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
+ return false;
+
if (cid == VMADDR_CID_HOST)
return true;
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 8c867023a2e5..f5123810192d 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -536,7 +536,8 @@ 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 = {
@@ -593,11 +594,15 @@ 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;
+ if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
+ return false;
+
seqpacket_allow = false;
rcu_read_lock();
vsock = rcu_dereference(the_virtio_vsock);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index dcc8a1d5851e..e6391eb7cc1b 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1043,9 +1043,9 @@ bool virtio_transport_stream_is_active(struct vsock_sock *vsk)
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active);
-bool virtio_transport_stream_allow(u32 cid, u32 port)
+bool virtio_transport_stream_allow(struct vsock_sock *vsk, u32 cid, u32 port)
{
- return true;
+ return vsk->net_mode == VSOCK_NET_MODE_GLOBAL;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);
@@ -1056,7 +1056,7 @@ int virtio_transport_dgram_bind(struct vsock_sock *vsk,
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind);
-bool virtio_transport_dgram_allow(u32 cid, u32 port)
+bool virtio_transport_dgram_allow(struct vsock_sock *vsk, u32 cid, u32 port)
{
return false;
}
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 7eccd6708d66..0ce44dc11708 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -646,13 +646,17 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg)
return VMCI_SUCCESS;
}
-static bool vmci_transport_stream_allow(u32 cid, u32 port)
+static bool vmci_transport_stream_allow(struct vsock_sock *vsk, u32 cid,
+ u32 port)
{
static const u32 non_socket_contexts[] = {
VMADDR_CID_LOCAL,
};
int i;
+ if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
+ return false;
+
BUILD_BUG_ON(sizeof(cid) != sizeof(*non_socket_contexts));
for (i = 0; i < ARRAY_SIZE(non_socket_contexts); i++) {
@@ -682,12 +686,10 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
err = VMCI_SUCCESS;
bh_process_pkt = false;
- /* Ignore incoming packets from contexts without sockets, or resources
- * that aren't vsock implementations.
+ /* Ignore incoming packets from resources that aren't vsock
+ * implementations.
*/
-
- if (!vmci_transport_stream_allow(dg->src.context, -1)
- || vmci_transport_peer_rid(dg->src.context) != dg->src.resource)
+ if (vmci_transport_peer_rid(dg->src.context) != dg->src.resource)
return VMCI_ERROR_NO_ACCESS;
if (VMCI_DG_SIZE(dg) < sizeof(*pkt))
@@ -749,6 +751,12 @@ static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg)
goto out;
}
+ /* Ignore incoming packets from contexts without sockets. */
+ if (!vmci_transport_stream_allow(vsk, dg->src.context, -1)) {
+ err = VMCI_ERROR_NO_ACCESS;
+ goto out;
+ }
+
/* We do most everything in a work queue, but let's fast path the
* notification of reads and writes to help data transfer performance.
* We can only do this if there is no process context code executing
@@ -1784,8 +1792,12 @@ static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk,
return err;
}
-static bool vmci_transport_dgram_allow(u32 cid, u32 port)
+static bool vmci_transport_dgram_allow(struct vsock_sock *vsk, u32 cid,
+ u32 port)
{
+ if (vsk->net_mode != VSOCK_NET_MODE_GLOBAL)
+ return false;
+
if (cid == VMADDR_CID_HYPERVISOR) {
/* Registrations of PBRPC Servers do not modify VMX/Hypervisor
* state and are allowed.
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index bc2ff918b315..afad27cf533a 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -46,7 +46,8 @@ 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;
@@ -106,9 +107,10 @@ 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;
+ return vsk->net_mode == VSOCK_NET_MODE_GLOBAL;
}
static void vsock_loopback_work(struct work_struct *work)
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 01/12] vsock: a per-net vsock NS mode state
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
Bobby Eshleman
In-Reply-To: <20251126-vsock-vmtest-v12-0-257ee21cd5de@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.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
Changes in v10:
- change mode_locked to int (Stefano)
Changes in v9:
- use xchg(), WRITE_ONCE(), READ_ONCE() for mode and mode_locked (Stefano)
- clarify mode0/mode1 meaning in vsock_net_check_mode() comment
- remove spin lock in net->vsock (not used anymore)
- change mode from u8 to enum vsock_net_mode in vsock_net_write_mode()
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 | 44 ++++++++++++++++++++++++++++++++++++++++++++
include/net/net_namespace.h | 4 ++++
include/net/netns/vsock.h | 17 +++++++++++++++++
4 files changed, 66 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index e9a8d945632b..b6ac6720d706 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -27105,6 +27105,7 @@ 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..9b5bdd083b6f 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 +258,46 @@ 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)
+{
+ return READ_ONCE(net->vsock.mode);
+}
+
+static inline bool vsock_net_write_mode(struct net *net,
+ enum vsock_net_mode mode)
+{
+ if (xchg(&net->vsock.mode_locked, 1))
+ return false;
+
+ WRITE_ONCE(net->vsock.mode, mode);
+ return true;
+}
+
+/* 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 at the time
+ * the vsock objects were created.
+ *
+ * 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..c1a5e805949d
--- /dev/null
+++ b/include/net/netns/vsock.h
@@ -0,0 +1,17 @@
+/* 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;
+ enum vsock_net_mode mode;
+ int mode_locked;
+};
+#endif /* __NET_NET_NAMESPACE_VSOCK_H */
--
2.47.3
^ permalink raw reply related
* [PATCH net-next v12 00/12] vsock: add namespace support to vhost-vsock and loopback
From: Bobby Eshleman @ 2025-11-27 7:47 UTC (permalink / raw)
To: Stefano Garzarella, David S. Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Stefan Hajnoczi, Michael S. Tsirkin,
Jason Wang, Eugenio Pérez, Xuan Zhuo, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
Broadcom internal kernel review list, Shuah Khan
Cc: linux-kernel, virtualization, netdev, kvm, linux-hyperv,
linux-kselftest, berrange, Sargun Dhillon, Bobby Eshleman,
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 is 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..28
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
SUMMARY: PASS=28 SKIP=0 FAIL=0
Dependent on series:
https://lore.kernel.org/all/20251108-vsock-selftests-fixes-and-improvements-v4-0-d5e8d6c87289@meta.com/
Thanks again for everyone's help and reviews!
Suggested-by: Sargun Dhillon <sargun@sargun.me>
Signed-off-by: Bobby Eshleman <bobbyeshleman@gmail.com>
Changes in v12:
- add ns mode checking to _allow() callbacks to reject local mode for
incompatible transports (Stefano)
- flip vhost/loopback to return true for stream_allow() and
seqpacket_allow() in "vsock: add netns support to virtio transports"
(Stefano)
- add VMADDR_CID_ANY + local mode documentation in af_vsock.c (Stefano)
- change "selftests/vsock: add tests for host <-> vm connectivity with
namespaces" to skip test 29 in vsock_test for namespace local
vsock_test calls in a host local-mode namespace. There is a
false-positive edge case for that test encountered with the
->stream_allow() approach. More details in that patch.
- updated cover letter with new test output
- Link to v11: https://lore.kernel.org/r/20251120-vsock-vmtest-v11-0-55cbc80249a7@meta.com
Changes in v11:
- vmtest: add a patch to use ss in wait_for_listener functions and
support vsock, tcp, and unix. Change all patches to use the new
functions.
- vmtest: add a patch to re-use vm dmesg / warn counting functions
- Link to v10: https://lore.kernel.org/r/20251117-vsock-vmtest-v10-0-df08f165bf3e@meta.com
Changes in v10:
- Combine virtio common patches into one (Stefano)
- Resolve vsock_loopback virtio_transport_reset_no_sock() issue
with info->vsk setting. This eliminates the need for skb->cb,
so remove skb->cb patches.
- many line width 80 fixes
- Link to v9: https://lore.kernel.org/all/20251111-vsock-vmtest-v9-0-852787a37bed@meta.com
Changes in v9:
- reorder loopback patch after patch for virtio transport common code
- remove module ordering tests patch because loopback no longer depends
on pernet ops
- major simplifications in vsock_loopback
- added a new patch for blocking local mode for guests, added test case
to check
- add net ref tracking to vsock_loopback patch
- Link to v8: https://lore.kernel.org/r/20251023-vsock-vmtest-v8-0-dea984d02bb0@meta.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 (12):
vsock: a per-net vsock NS mode state
vsock: add netns to vsock core
virtio: set skb owner of virtio_transport_reset_no_sock() reply
vsock: add netns support to virtio transports
selftests/vsock: add namespace helpers to vmtest.sh
selftests/vsock: prepare vm management helpers for namespaces
selftests/vsock: add vm_dmesg_{warn,oops}_count() helpers
selftests/vsock: use ss to wait for listeners instead of /proc/net
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
MAINTAINERS | 1 +
drivers/vhost/vsock.c | 59 +-
include/linux/virtio_vsock.h | 12 +-
include/net/af_vsock.h | 57 +-
include/net/net_namespace.h | 4 +
include/net/netns/vsock.h | 17 +
net/vmw_vsock/af_vsock.c | 272 +++++++-
net/vmw_vsock/hyperv_transport.c | 7 +-
net/vmw_vsock/virtio_transport.c | 19 +-
net/vmw_vsock/virtio_transport_common.c | 75 ++-
net/vmw_vsock/vmci_transport.c | 26 +-
net/vmw_vsock/vsock_loopback.c | 23 +-
tools/testing/selftests/vsock/vmtest.sh | 1077 +++++++++++++++++++++++++++++--
13 files changed, 1522 insertions(+), 127 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
* Re: [PATCH v3 0/9] arch,sysfb,efi: Support EDID on non-x86 EFI systems
From: Thomas Zimmermann @ 2025-11-27 7:43 UTC (permalink / raw)
To: Richard Lyu, ardb, javierm, arnd, helgaas
Cc: x86, linux-arm-kernel, linux-kernel, linux-efi, loongarch,
linux-riscv, dri-devel, linux-hyperv, linux-pci, linux-fbdev
In-Reply-To: <aSe1ZBXa3JBidhem@r1chard>
Hi
Am 27.11.25 um 03:20 schrieb Richard Lyu:
> Hi Thomas,
>
> I am attempting to test this patch series but encountered merge conflicts when applying it to various trees.
> Could you please clarify the specific base commit (or branch/tag) this series was generated against?
Thanks for testing.
>
> When testing on the next branch on commits 7a2ff00 and e41ef37, I hit a conflict on PATCH v3 4/9:
> patching file drivers/pci/vgaarb.c
> Hunk #2 FAILED at 557.
> 1 out of 2 hunks FAILED -- rejects in file drivers/pci/vgaarb.c
>
> When testing against 3a86608 (Linux 6.18-rc1), the following conflicts occurred:
> patching file drivers/gpu/drm/sysfb/efidrm.c
> Hunk #1 FAILED at 24.
> 1 out of 2 hunks FAILED -- rejects in file drivers/gpu/drm/sysfb/efidrm.c
> patching file drivers/gpu/drm/sysfb/vesadrm.c
> Hunk #1 FAILED at 25.
> 1 out of 2 hunks FAILED -- rejects in file drivers/gpu/drm/sysfb/vesadrm.c
>
> Please let me know the correct base, and I will retest.
It's in the cover letter: d724c6f85e80a23ed46b7ebc6e38b527c09d64f5 The
commit is in linux-next. The idea is that the EFI tree can pick up the
changes easily in the next cycle. linux-next seemed like the best
choice. Best regards Thomas
>
> Thanks,
> Richard Lyu
>
> On 2025/11/26 17:03, Thomas Zimmermann wrote:
>> Replace screen_info and edid_info with sysfb_primary_device of type
>> struct sysfb_display_info. Update all users. Then implement EDID support
>> in the kernel EFI code.
>>
>> Sysfb DRM drivers currently fetch the global edid_info directly, when
>> they should get that information together with the screen_info from their
>> device. Wrapping screen_info and edid_info in sysfb_primary_display and
>> passing this to drivers enables this.
>>
>> Replacing both with sysfb_primary_display has been motivate by the EFI
>> stub. EFI wants to transfer EDID via config table in a single entry.
>> Using struct sysfb_display_info this will become easily possible. Hence
>> accept some churn in architecture code for the long-term improvements.
>>
>> Patches 1 and 2 reduce the exposure of screen_info in EFI-related code.
>>
>> Patch 3 adds struct sysfb_display_info.
>>
>> Patch 4 replaces scren_info with sysfb_primary_display. This results in
>> several changes throught the kernel, but is really just a refactoring.
>>
>> Patch 5 updates sysfb to transfer sysfb_primary_display to the related
>> drivers.
>>
>> Patch 6 moves edid_info into sysfb_primary_display. This resolves some
>> drivers' reference to the global edid_info, but also makes the EDID data
>> available on non-x86 architectures.
>>
>> Patches 7 and 8 add support for EDID transfers on non-x86 EFI systems.
>>
>> Patch 9 cleans up the config-table allocation to be easier to understand.
>>
>> v3:
>> - replace SCREEN_INFO table entry (Ard)
>> - merge libstub patch into kernel patch
>> v2:
>> - combine v1 of the series at [1] plus changes from [2] and [3].
>>
>> [1] https://lore.kernel.org/dri-devel/20251121135624.494768-1-tzimmermann@suse.de/
>> [2] https://lore.kernel.org/dri-devel/20251015160816.525825-1-tzimmermann@suse.de/
>> [3] https://lore.kernel.org/linux-efi/20251119123011.1187249-5-ardb+git@google.com/
>>
>> Thomas Zimmermann (9):
>> efi: earlycon: Reduce number of references to global screen_info
>> efi: sysfb_efi: Reduce number of references to global screen_info
>> sysfb: Add struct sysfb_display_info
>> sysfb: Replace screen_info with sysfb_primary_display
>> sysfb: Pass sysfb_primary_display to devices
>> sysfb: Move edid_info into sysfb_primary_display
>> efi: Refactor init_primary_display() helpers
>> efi: Support EDID information
>> efi: libstub: Simplify interfaces for primary_display
>>
>> arch/arm64/kernel/image-vars.h | 2 +-
>> arch/loongarch/kernel/efi.c | 38 ++++-----
>> arch/loongarch/kernel/image-vars.h | 2 +-
>> arch/riscv/kernel/image-vars.h | 2 +-
>> arch/x86/kernel/kexec-bzimage64.c | 4 +-
>> arch/x86/kernel/setup.c | 16 ++--
>> arch/x86/video/video-common.c | 4 +-
>> drivers/firmware/efi/earlycon.c | 42 +++++-----
>> drivers/firmware/efi/efi-init.c | 46 ++++++-----
>> drivers/firmware/efi/efi.c | 4 +-
>> drivers/firmware/efi/libstub/Makefile | 2 +-
>> drivers/firmware/efi/libstub/efi-stub-entry.c | 36 +++++++--
>> drivers/firmware/efi/libstub/efi-stub.c | 49 +++++++----
>> drivers/firmware/efi/libstub/efistub.h | 7 +-
>> .../firmware/efi/libstub/primary_display.c | 41 ++++++++++
>> drivers/firmware/efi/libstub/screen_info.c | 53 ------------
>> drivers/firmware/efi/libstub/zboot.c | 6 +-
>> drivers/firmware/efi/sysfb_efi.c | 81 ++++++++++---------
>> drivers/firmware/sysfb.c | 13 +--
>> drivers/firmware/sysfb_simplefb.c | 2 +-
>> drivers/gpu/drm/sysfb/efidrm.c | 14 ++--
>> drivers/gpu/drm/sysfb/vesadrm.c | 14 ++--
>> drivers/hv/vmbus_drv.c | 6 +-
>> drivers/pci/vgaarb.c | 4 +-
>> drivers/video/Kconfig | 8 +-
>> drivers/video/fbdev/core/fbmon.c | 8 +-
>> drivers/video/fbdev/efifb.c | 10 ++-
>> drivers/video/fbdev/vesafb.c | 10 ++-
>> drivers/video/fbdev/vga16fb.c | 8 +-
>> drivers/video/screen_info_pci.c | 5 +-
>> include/linux/efi.h | 9 ++-
>> include/linux/screen_info.h | 2 -
>> include/linux/sysfb.h | 23 ++++--
>> include/video/edid.h | 4 -
>> 34 files changed, 321 insertions(+), 254 deletions(-)
>> create mode 100644 drivers/firmware/efi/libstub/primary_display.c
>> delete mode 100644 drivers/firmware/efi/libstub/screen_info.c
>>
>>
>> base-commit: d724c6f85e80a23ed46b7ebc6e38b527c09d64f5
>> --
>> 2.51.1
>>
--
--
Thomas Zimmermann
Graphics Driver Developer
SUSE Software Solutions Germany GmbH
Frankenstr. 146, 90461 Nürnberg, Germany, www.suse.com
GF: Jochen Jaser, Andrew McDonald, Werner Knoblich, (HRB 36809, AG Nürnberg)
^ permalink raw reply
* [PATCH v4 21/21] x86/pvlocks: Move paravirt spinlock functions into own header
From: Juergen Gross @ 2025-11-27 7:08 UTC (permalink / raw)
To: linux-kernel, x86, linux-hyperv, virtualization, kvm
Cc: Juergen Gross, K. Y. Srinivasan, Haiyang Zhang, Wei Liu,
Dexuan Cui, Thomas Gleixner, Ingo Molnar, Borislav Petkov,
Dave Hansen, H. Peter Anvin, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Paolo Bonzini,
Vitaly Kuznetsov, Boris Ostrovsky, Josh Poimboeuf, Peter Zijlstra,
xen-devel
In-Reply-To: <20251127070844.21919-1-jgross@suse.com>
Instead of having the pv spinlock function definitions in paravirt.h,
move them into the new header paravirt-spinlock.h.
Signed-off-by: Juergen Gross <jgross@suse.com>
---
V2:
- use new header instead of qspinlock.h
- use dedicated pv_ops_lock array
- move more paravirt related lock code
V3:
- hide native_pv_lock_init() with CONFIG_SMP (kernel test robot)
V4:
- don't reference pv_ops_lock without CONFIG_PARAVIRT_SPINLOCKS
(kernel test robot)
---
arch/x86/hyperv/hv_spinlock.c | 10 +-
arch/x86/include/asm/paravirt-spinlock.h | 146 +++++++++++++++++++++++
arch/x86/include/asm/paravirt.h | 61 ----------
arch/x86/include/asm/paravirt_types.h | 17 ---
arch/x86/include/asm/qspinlock.h | 89 ++------------
arch/x86/kernel/Makefile | 2 +-
arch/x86/kernel/kvm.c | 12 +-
arch/x86/kernel/paravirt-spinlocks.c | 26 +++-
arch/x86/kernel/paravirt.c | 21 ----
arch/x86/xen/spinlock.c | 10 +-
tools/objtool/check.c | 1 +
11 files changed, 196 insertions(+), 199 deletions(-)
create mode 100644 arch/x86/include/asm/paravirt-spinlock.h
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index 2a3c2afb0154..210b494e4de0 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -78,11 +78,11 @@ void __init hv_init_spinlocks(void)
pr_info("PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_ops.lock.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_ops.lock.wait = hv_qlock_wait;
- pv_ops.lock.kick = hv_qlock_kick;
- pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(hv_vcpu_is_preempted);
+ pv_ops_lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops_lock.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+ pv_ops_lock.wait = hv_qlock_wait;
+ pv_ops_lock.kick = hv_qlock_kick;
+ pv_ops_lock.vcpu_is_preempted = PV_CALLEE_SAVE(hv_vcpu_is_preempted);
}
static __init int hv_parse_nopvspin(char *arg)
diff --git a/arch/x86/include/asm/paravirt-spinlock.h b/arch/x86/include/asm/paravirt-spinlock.h
new file mode 100644
index 000000000000..ed3ed343903d
--- /dev/null
+++ b/arch/x86/include/asm/paravirt-spinlock.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_X86_PARAVIRT_SPINLOCK_H
+#define _ASM_X86_PARAVIRT_SPINLOCK_H
+
+#include <asm/paravirt_types.h>
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock_types.h>
+#endif
+
+struct qspinlock;
+
+struct pv_lock_ops {
+ void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
+ struct paravirt_callee_save queued_spin_unlock;
+
+ void (*wait)(u8 *ptr, u8 val);
+ void (*kick)(int cpu);
+
+ struct paravirt_callee_save vcpu_is_preempted;
+} __no_randomize_layout;
+
+extern struct pv_lock_ops pv_ops_lock;
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __pv_init_lock_hash(void);
+extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
+extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
+extern bool nopvspin;
+
+static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
+ u32 val)
+{
+ PVOP_VCALL2(pv_ops_lock, queued_spin_lock_slowpath, lock, val);
+}
+
+static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
+{
+ PVOP_ALT_VCALLEE1(pv_ops_lock, queued_spin_unlock, lock,
+ "movb $0, (%%" _ASM_ARG1 ");",
+ ALT_NOT(X86_FEATURE_PVUNLOCK));
+}
+
+static __always_inline bool pv_vcpu_is_preempted(long cpu)
+{
+ return PVOP_ALT_CALLEE1(bool, pv_ops_lock, vcpu_is_preempted, cpu,
+ "xor %%" _ASM_AX ", %%" _ASM_AX ";",
+ ALT_NOT(X86_FEATURE_VCPUPREEMPT));
+}
+
+#define queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * A smp_store_release() on the least-significant byte.
+ */
+static inline void native_queued_spin_unlock(struct qspinlock *lock)
+{
+ smp_store_release(&lock->locked, 0);
+}
+
+static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+{
+ pv_queued_spin_lock_slowpath(lock, val);
+}
+
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+ kcsan_release();
+ pv_queued_spin_unlock(lock);
+}
+
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(long cpu)
+{
+ return pv_vcpu_is_preempted(cpu);
+}
+
+static __always_inline void pv_wait(u8 *ptr, u8 val)
+{
+ PVOP_VCALL2(pv_ops_lock, wait, ptr, val);
+}
+
+static __always_inline void pv_kick(int cpu)
+{
+ PVOP_VCALL1(pv_ops_lock, kick, cpu);
+}
+
+void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
+bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+void __init native_pv_lock_init(void);
+__visible void __native_queued_spin_unlock(struct qspinlock *lock);
+bool pv_is_native_spin_unlock(void);
+__visible bool __native_vcpu_is_preempted(long cpu);
+bool pv_is_native_vcpu_is_preempted(void);
+
+/*
+ * virt_spin_lock_key - disables by default the virt_spin_lock() hijack.
+ *
+ * Native (and PV wanting native due to vCPU pinning) should keep this key
+ * disabled. Native does not touch the key.
+ *
+ * When in a guest then native_pv_lock_init() enables the key first and
+ * KVM/XEN might conditionally disable it later in the boot process again.
+ */
+DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
+/*
+ * Shortcut for the queued_spin_lock_slowpath() function that allows
+ * virt to hijack it.
+ *
+ * Returns:
+ * true - lock has been negotiated, all done;
+ * false - queued_spin_lock_slowpath() will do its thing.
+ */
+#define virt_spin_lock virt_spin_lock
+static inline bool virt_spin_lock(struct qspinlock *lock)
+{
+ int val;
+
+ if (!static_branch_likely(&virt_spin_lock_key))
+ return false;
+
+ /*
+ * On hypervisors without PARAVIRT_SPINLOCKS support we fall
+ * back to a Test-and-Set spinlock, because fair locks have
+ * horrible lock 'holder' preemption issues.
+ */
+
+ __retry:
+ val = atomic_read(&lock->val);
+
+ if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) {
+ cpu_relax();
+ goto __retry;
+ }
+
+ return true;
+}
+
+#endif /* _ASM_X86_PARAVIRT_SPINLOCK_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ec274d13bae0..b21072af731d 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -19,15 +19,6 @@
#include <linux/cpumask.h>
#include <asm/frame.h>
-__visible void __native_queued_spin_unlock(struct qspinlock *lock);
-bool pv_is_native_spin_unlock(void);
-__visible bool __native_vcpu_is_preempted(long cpu);
-bool pv_is_native_vcpu_is_preempted(void);
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-void __init paravirt_set_cap(void);
-#endif
-
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
@@ -522,46 +513,7 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
{
pv_ops.mmu.set_fixmap(idx, phys, flags);
}
-#endif
-
-#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
-
-static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock,
- u32 val)
-{
- PVOP_VCALL2(pv_ops, lock.queued_spin_lock_slowpath, lock, val);
-}
-
-static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
-{
- PVOP_ALT_VCALLEE1(pv_ops, lock.queued_spin_unlock, lock,
- "movb $0, (%%" _ASM_ARG1 ");",
- ALT_NOT(X86_FEATURE_PVUNLOCK));
-}
-
-static __always_inline void pv_wait(u8 *ptr, u8 val)
-{
- PVOP_VCALL2(pv_ops, lock.wait, ptr, val);
-}
-
-static __always_inline void pv_kick(int cpu)
-{
- PVOP_VCALL1(pv_ops, lock.kick, cpu);
-}
-
-static __always_inline bool pv_vcpu_is_preempted(long cpu)
-{
- return PVOP_ALT_CALLEE1(bool, pv_ops, lock.vcpu_is_preempted, cpu,
- "xor %%" _ASM_AX ", %%" _ASM_AX ";",
- ALT_NOT(X86_FEATURE_VCPUPREEMPT));
-}
-void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
-bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
-
-#endif /* SMP && PARAVIRT_SPINLOCKS */
-
-#ifdef CONFIG_PARAVIRT_XXL
static __always_inline unsigned long arch_local_save_flags(void)
{
return PVOP_ALT_CALLEE0(unsigned long, pv_ops, irq.save_fl, "pushf; pop %%rax;",
@@ -588,8 +540,6 @@ static __always_inline unsigned long arch_local_irq_save(void)
}
#endif
-void native_pv_lock_init(void) __init;
-
#else /* __ASSEMBLER__ */
#ifdef CONFIG_X86_64
@@ -613,12 +563,6 @@ void native_pv_lock_init(void) __init;
#endif /* __ASSEMBLER__ */
#else /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
-
-#ifndef __ASSEMBLER__
-static inline void native_pv_lock_init(void)
-{
-}
-#endif
#endif /* !CONFIG_PARAVIRT */
#ifndef __ASSEMBLER__
@@ -634,10 +578,5 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
}
#endif
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
-static inline void paravirt_set_cap(void)
-{
-}
-#endif
#endif /* __ASSEMBLER__ */
#endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 01a485f1a7f1..e2b487d35d14 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -184,22 +184,6 @@ struct pv_mmu_ops {
#endif
} __no_randomize_layout;
-#ifdef CONFIG_SMP
-#include <asm/spinlock_types.h>
-#endif
-
-struct qspinlock;
-
-struct pv_lock_ops {
- void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val);
- struct paravirt_callee_save queued_spin_unlock;
-
- void (*wait)(u8 *ptr, u8 val);
- void (*kick)(int cpu);
-
- struct paravirt_callee_save vcpu_is_preempted;
-} __no_randomize_layout;
-
/* This contains all the paravirt structures: we get a convenient
* number for each function using the offset which we use to indicate
* what to patch. */
@@ -207,7 +191,6 @@ struct paravirt_patch_template {
struct pv_cpu_ops cpu;
struct pv_irq_ops irq;
struct pv_mmu_ops mmu;
- struct pv_lock_ops lock;
} __no_randomize_layout;
extern struct paravirt_patch_template pv_ops;
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 68da67df304d..a2668bdf4c84 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -7,6 +7,9 @@
#include <asm-generic/qspinlock_types.h>
#include <asm/paravirt.h>
#include <asm/rmwcc.h>
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt-spinlock.h>
+#endif
#define _Q_PENDING_LOOPS (1 << 9)
@@ -27,89 +30,13 @@ static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lo
return val;
}
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_init_lock_hash(void);
-extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock);
-extern bool nopvspin;
-
-#define queued_spin_unlock queued_spin_unlock
-/**
- * queued_spin_unlock - release a queued spinlock
- * @lock : Pointer to queued spinlock structure
- *
- * A smp_store_release() on the least-significant byte.
- */
-static inline void native_queued_spin_unlock(struct qspinlock *lock)
-{
- smp_store_release(&lock->locked, 0);
-}
-
-static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
-{
- pv_queued_spin_lock_slowpath(lock, val);
-}
-
-static inline void queued_spin_unlock(struct qspinlock *lock)
-{
- kcsan_release();
- pv_queued_spin_unlock(lock);
-}
-
-#define vcpu_is_preempted vcpu_is_preempted
-static inline bool vcpu_is_preempted(long cpu)
-{
- return pv_vcpu_is_preempted(cpu);
-}
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void) { }
#endif
-#ifdef CONFIG_PARAVIRT
-/*
- * virt_spin_lock_key - disables by default the virt_spin_lock() hijack.
- *
- * Native (and PV wanting native due to vCPU pinning) should keep this key
- * disabled. Native does not touch the key.
- *
- * When in a guest then native_pv_lock_init() enables the key first and
- * KVM/XEN might conditionally disable it later in the boot process again.
- */
-DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
-
-/*
- * Shortcut for the queued_spin_lock_slowpath() function that allows
- * virt to hijack it.
- *
- * Returns:
- * true - lock has been negotiated, all done;
- * false - queued_spin_lock_slowpath() will do its thing.
- */
-#define virt_spin_lock virt_spin_lock
-static inline bool virt_spin_lock(struct qspinlock *lock)
-{
- int val;
-
- if (!static_branch_likely(&virt_spin_lock_key))
- return false;
-
- /*
- * On hypervisors without PARAVIRT_SPINLOCKS support we fall
- * back to a Test-and-Set spinlock, because fair locks have
- * horrible lock 'holder' preemption issues.
- */
-
- __retry:
- val = atomic_read(&lock->val);
-
- if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) {
- cpu_relax();
- goto __retry;
- }
-
- return true;
-}
-
-#endif /* CONFIG_PARAVIRT */
+#ifndef CONFIG_PARAVIRT
+static inline void native_pv_lock_init(void) { }
+#endif
#include <asm-generic/qspinlock.h>
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index bc184dd38d99..e9aeeeafad17 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -126,7 +126,7 @@ obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o
obj-$(CONFIG_PARAVIRT) += paravirt.o
-obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
+obj-$(CONFIG_PARAVIRT) += paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d54fd2bc0402..e767f8ed405a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -824,8 +824,10 @@ static void __init kvm_guest_init(void)
has_steal_clock = 1;
static_call_update(pv_steal_clock, kvm_steal_clock);
- pv_ops.lock.vcpu_is_preempted =
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+ pv_ops_lock.vcpu_is_preempted =
PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
+#endif
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1121,11 +1123,11 @@ void __init kvm_spinlock_init(void)
pr_info("PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_ops.lock.queued_spin_unlock =
+ pv_ops_lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops_lock.queued_spin_unlock =
PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_ops.lock.wait = kvm_wait;
- pv_ops.lock.kick = kvm_kick_cpu;
+ pv_ops_lock.wait = kvm_wait;
+ pv_ops_lock.kick = kvm_kick_cpu;
/*
* When PV spinlock is enabled which is preferred over
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 9e1ea99ad9df..95452444868f 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -3,12 +3,22 @@
* Split spinlock implementation out into its own file, so it can be
* compiled in a FTRACE-compatible way.
*/
+#include <linux/static_call.h>
#include <linux/spinlock.h>
#include <linux/export.h>
#include <linux/jump_label.h>
-#include <asm/paravirt.h>
+DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
+#ifdef CONFIG_SMP
+void __init native_pv_lock_init(void)
+{
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ static_branch_enable(&virt_spin_lock_key);
+}
+#endif
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
__visible void __native_queued_spin_unlock(struct qspinlock *lock)
{
native_queued_spin_unlock(lock);
@@ -17,7 +27,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
{
- return pv_ops.lock.queued_spin_unlock.func ==
+ return pv_ops_lock.queued_spin_unlock.func ==
__raw_callee_save___native_queued_spin_unlock;
}
@@ -29,7 +39,7 @@ PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
bool pv_is_native_vcpu_is_preempted(void)
{
- return pv_ops.lock.vcpu_is_preempted.func ==
+ return pv_ops_lock.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
@@ -41,3 +51,13 @@ void __init paravirt_set_cap(void)
if (!pv_is_native_vcpu_is_preempted())
setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
}
+
+struct pv_lock_ops pv_ops_lock = {
+ .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
+ .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
+ .wait = paravirt_nop,
+ .kick = paravirt_nop,
+ .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
+};
+EXPORT_SYMBOL(pv_ops_lock);
+#endif
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5dfbd3f55792..a6ed52cae003 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -57,14 +57,6 @@ DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text);
DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text);
#endif
-DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
-
-void __init native_pv_lock_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
- static_branch_enable(&virt_spin_lock_key);
-}
-
static noinstr void pv_native_safe_halt(void)
{
native_safe_halt();
@@ -221,19 +213,6 @@ struct paravirt_patch_template pv_ops = {
.mmu.set_fixmap = native_set_fixmap,
#endif /* CONFIG_PARAVIRT_XXL */
-
-#if defined(CONFIG_PARAVIRT_SPINLOCKS)
- /* Lock ops. */
-#ifdef CONFIG_SMP
- .lock.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
- .lock.queued_spin_unlock =
- PV_CALLEE_SAVE(__native_queued_spin_unlock),
- .lock.wait = paravirt_nop,
- .lock.kick = paravirt_nop,
- .lock.vcpu_is_preempted =
- PV_CALLEE_SAVE(__native_vcpu_is_preempted),
-#endif /* SMP */
-#endif
};
#ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index fe56646d6919..83ac24ead289 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -134,10 +134,10 @@ void __init xen_init_spinlocks(void)
printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
__pv_init_lock_hash();
- pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
- pv_ops.lock.queued_spin_unlock =
+ pv_ops_lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+ pv_ops_lock.queued_spin_unlock =
PV_CALLEE_SAVE(__pv_queued_spin_unlock);
- pv_ops.lock.wait = xen_qlock_wait;
- pv_ops.lock.kick = xen_qlock_kick;
- pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
+ pv_ops_lock.wait = xen_qlock_wait;
+ pv_ops_lock.kick = xen_qlock_kick;
+ pv_ops_lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index d63d0891924a..36e04988babe 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -550,6 +550,7 @@ static struct {
int idx_off;
} pv_ops_tables[] = {
{ .name = "pv_ops", },
+ { .name = "pv_ops_lock", },
{ .name = NULL, .idx_off = -1 }
};
--
2.51.0
^ permalink raw reply related
* [PATCH v4 12/21] x86/paravirt: Move paravirt_sched_clock() related code into tsc.c
From: Juergen Gross @ 2025-11-27 7:08 UTC (permalink / raw)
To: linux-kernel, x86, virtualization, kvm, linux-hyperv
Cc: Juergen Gross, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, Dave Hansen, H. Peter Anvin,
Paolo Bonzini, Vitaly Kuznetsov, Boris Ostrovsky,
K. Y. Srinivasan, Haiyang Zhang, Wei Liu, Dexuan Cui,
Daniel Lezcano, xen-devel, Peter Zijlstra (Intel)
In-Reply-To: <20251127070844.21919-1-jgross@suse.com>
The only user of paravirt_sched_clock() is in tsc.c, so move the code
from paravirt.c and paravirt.h to tsc.c.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
arch/x86/include/asm/paravirt.h | 12 ------------
arch/x86/include/asm/timer.h | 1 +
arch/x86/kernel/kvmclock.c | 1 +
arch/x86/kernel/paravirt.c | 7 -------
arch/x86/kernel/tsc.c | 10 +++++++++-
arch/x86/xen/time.c | 1 +
drivers/clocksource/hyperv_timer.c | 2 ++
7 files changed, 14 insertions(+), 20 deletions(-)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 766a7cee3d64..b69e75a5c872 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -14,20 +14,8 @@
#ifndef __ASSEMBLER__
#include <linux/types.h>
#include <linux/cpumask.h>
-#include <linux/static_call_types.h>
#include <asm/frame.h>
-u64 dummy_sched_clock(void);
-
-DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
-
-void paravirt_set_sched_clock(u64 (*func)(void));
-
-static __always_inline u64 paravirt_sched_clock(void)
-{
- return static_call(pv_sched_clock)();
-}
-
__visible void __native_queued_spin_unlock(struct qspinlock *lock);
bool pv_is_native_spin_unlock(void);
__visible bool __native_vcpu_is_preempted(long cpu);
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 23baf8c9b34c..fda18bcb19b4 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -12,6 +12,7 @@ extern void recalibrate_cpu_khz(void);
extern int no_timer_check;
extern bool using_native_sched_clock(void);
+void paravirt_set_sched_clock(u64 (*func)(void));
/*
* We use the full linear equation: f(x) = a + b*x, in order to allow
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index ca0a49eeac4a..b5991d53fc0e 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -19,6 +19,7 @@
#include <linux/cc_platform.h>
#include <asm/hypervisor.h>
+#include <asm/timer.h>
#include <asm/x86_init.h>
#include <asm/kvmclock.h>
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 42991d471bf3..4e37db8073f9 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -60,13 +60,6 @@ void __init native_pv_lock_init(void)
static_branch_enable(&virt_spin_lock_key);
}
-DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
-
-void paravirt_set_sched_clock(u64 (*func)(void))
-{
- static_call_update(pv_sched_clock, func);
-}
-
static noinstr void pv_native_safe_halt(void)
{
native_safe_halt();
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 87e749106dda..554b54783a04 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -266,19 +266,27 @@ u64 native_sched_clock_from_tsc(u64 tsc)
/* We need to define a real function for sched_clock, to override the
weak default version */
#ifdef CONFIG_PARAVIRT
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
noinstr u64 sched_clock_noinstr(void)
{
- return paravirt_sched_clock();
+ return static_call(pv_sched_clock)();
}
bool using_native_sched_clock(void)
{
return static_call_query(pv_sched_clock) == native_sched_clock;
}
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+ static_call_update(pv_sched_clock, func);
+}
#else
u64 sched_clock_noinstr(void) __attribute__((alias("native_sched_clock")));
bool using_native_sched_clock(void) { return true; }
+void paravirt_set_sched_clock(u64 (*func)(void)) { }
#endif
notrace u64 sched_clock(void)
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index e4754b2fa900..6f9f665bb7ae 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -19,6 +19,7 @@
#include <linux/sched/cputime.h>
#include <asm/pvclock.h>
+#include <asm/timer.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/cpuid.h>
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 10356d4ec55c..e9f5034a1bc8 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -535,6 +535,8 @@ static __always_inline void hv_setup_sched_clock(void *sched_clock)
sched_clock_register(sched_clock, 64, NSEC_PER_SEC);
}
#elif defined CONFIG_PARAVIRT
+#include <asm/timer.h>
+
static __always_inline void hv_setup_sched_clock(void *sched_clock)
{
/* We're on x86/x64 *and* using PV ops */
--
2.51.0
^ permalink raw reply related
* [PATCH v4 01/21] x86/paravirt: Remove not needed includes of paravirt.h
From: Juergen Gross @ 2025-11-27 7:08 UTC (permalink / raw)
To: linux-kernel, x86, linux-hyperv
Cc: Juergen Gross, Andy Lutomirski, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, H. Peter Anvin, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Peter Zijlstra, Will Deacon,
Boqun Feng, Waiman Long, Jiri Kosina, Josh Poimboeuf, Pawan Gupta,
Boris Ostrovsky, xen-devel
In-Reply-To: <20251127070844.21919-1-jgross@suse.com>
In some places asm/paravirt.h is included without really being needed.
Remove the related #include statements.
Signed-off-by: Juergen Gross <jgross@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
V3:
- reinstate the include in mmu_context.h (kernel test robot)
V4:
- reinstate the include in arch/x86/kernel/x86_init.c (Boris Petkov)
---
arch/x86/entry/entry_64.S | 1 -
arch/x86/entry/vsyscall/vsyscall_64.c | 1 -
arch/x86/hyperv/hv_spinlock.c | 1 -
arch/x86/include/asm/apic.h | 4 ----
arch/x86/include/asm/highmem.h | 1 -
arch/x86/include/asm/mshyperv.h | 1 -
arch/x86/include/asm/pgtable_32.h | 1 -
arch/x86/include/asm/spinlock.h | 1 -
arch/x86/include/asm/tlbflush.h | 4 ----
arch/x86/kernel/apm_32.c | 1 -
arch/x86/kernel/callthunks.c | 1 -
arch/x86/kernel/cpu/bugs.c | 1 -
arch/x86/kernel/vsmp_64.c | 1 -
arch/x86/lib/cache-smp.c | 1 -
arch/x86/mm/init.c | 1 -
arch/x86/xen/spinlock.c | 1 -
16 files changed, 22 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index ed04a968cc7d..7a82305405af 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -30,7 +30,6 @@
#include <asm/hw_irq.h>
#include <asm/page_types.h>
#include <asm/irqflags.h>
-#include <asm/paravirt.h>
#include <asm/percpu.h>
#include <asm/asm.h>
#include <asm/smap.h>
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 6e6c0a740837..4bd1e271bb22 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -37,7 +37,6 @@
#include <asm/unistd.h>
#include <asm/fixmap.h>
#include <asm/traps.h>
-#include <asm/paravirt.h>
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index 81b006601370..2a3c2afb0154 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -13,7 +13,6 @@
#include <linux/spinlock.h>
#include <asm/mshyperv.h>
-#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/msr.h>
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a26e66d66444..9cd493d467d4 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -90,10 +90,6 @@ static inline bool apic_from_smp_config(void)
/*
* Basic functions accessing APICs.
*/
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
-
static inline void native_apic_mem_write(u32 reg, u32 v)
{
volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 585bdadba47d..decfaaf52326 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -24,7 +24,6 @@
#include <linux/interrupt.h>
#include <linux/threads.h>
#include <asm/tlbflush.h>
-#include <asm/paravirt.h>
#include <asm/fixmap.h>
#include <asm/pgtable_areas.h>
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 605abd02158d..15e2693b8070 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -8,7 +8,6 @@
#include <linux/io.h>
#include <linux/static_call.h>
#include <asm/nospec-branch.h>
-#include <asm/paravirt.h>
#include <asm/msr.h>
#include <hyperv/hvhdk.h>
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index b612cc57a4d3..acea0cfa2460 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -16,7 +16,6 @@
#ifndef __ASSEMBLER__
#include <asm/processor.h>
#include <linux/threads.h>
-#include <asm/paravirt.h>
#include <linux/bitops.h>
#include <linux/list.h>
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 5b6bc7016c22..934632b78d09 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -7,7 +7,6 @@
#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
-#include <asm/paravirt.h>
#include <asm/bitops.h>
/*
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 00daedfefc1b..238a6b807da5 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -300,10 +300,6 @@ static inline void mm_clear_asid_transition(struct mm_struct *mm) { }
static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
#endif /* CONFIG_BROADCAST_TLB_FLUSH */
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
-
#define flush_tlb_mm(mm) \
flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL, true)
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index b37ab1095707..3175d7c134e9 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -229,7 +229,6 @@
#include <linux/uaccess.h>
#include <asm/desc.h>
#include <asm/olpc.h>
-#include <asm/paravirt.h>
#include <asm/reboot.h>
#include <asm/nospec-branch.h>
#include <asm/ibt.h>
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index a951333c5995..e37728f70322 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -15,7 +15,6 @@
#include <asm/insn.h>
#include <asm/kexec.h>
#include <asm/nospec-branch.h>
-#include <asm/paravirt.h>
#include <asm/sections.h>
#include <asm/switch_to.h>
#include <asm/sync_core.h>
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d7fa03bf51b4..cb200930510e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -25,7 +25,6 @@
#include <asm/fpu/api.h>
#include <asm/msr.h>
#include <asm/vmx.h>
-#include <asm/paravirt.h>
#include <asm/cpu_device_id.h>
#include <asm/e820/api.h>
#include <asm/hypervisor.h>
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 73511332bb67..25625e3fc183 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -18,7 +18,6 @@
#include <asm/apic.h>
#include <asm/pci-direct.h>
#include <asm/io.h>
-#include <asm/paravirt.h>
#include <asm/setup.h>
#define TOPOLOGY_REGISTER_OFFSET 0x10
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index c5c60d07308c..ae5a5dfd33c7 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -1,5 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
-#include <asm/paravirt.h>
#include <linux/smp.h>
#include <linux/export.h>
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 8bf6ad4b9400..76537d40493c 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -27,7 +27,6 @@
#include <asm/pti.h>
#include <asm/text-patching.h>
#include <asm/memtype.h>
-#include <asm/paravirt.h>
#include <asm/mmu_context.h>
/*
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 8e4efe0fb6f9..fe56646d6919 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -8,7 +8,6 @@
#include <linux/slab.h>
#include <linux/atomic.h>
-#include <asm/paravirt.h>
#include <asm/qspinlock.h>
#include <xen/events.h>
--
2.51.0
^ permalink raw reply related
* [PATCH v4 00/21] paravirt: cleanup and reorg
From: Juergen Gross @ 2025-11-27 7:08 UTC (permalink / raw)
To: linux-kernel, x86, linux-hyperv, virtualization, loongarch,
linuxppc-dev, linux-riscv, kvm
Cc: Juergen Gross, Andy Lutomirski, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, Dave Hansen, H. Peter Anvin, K. Y. Srinivasan,
Haiyang Zhang, Wei Liu, Dexuan Cui, Peter Zijlstra, Will Deacon,
Boqun Feng, Waiman Long, Jiri Kosina, Josh Poimboeuf, Pawan Gupta,
Boris Ostrovsky, xen-devel, Ajay Kaher, Alexey Makhalov,
Broadcom internal kernel review list, Russell King,
Catalin Marinas, Huacai Chen, WANG Xuerui, Madhavan Srinivasan,
Michael Ellerman, Nicholas Piggin, Christophe Leroy,
Paul Walmsley, Palmer Dabbelt, Albert Ou, Alexandre Ghiti,
Juri Lelli, Vincent Guittot, Dietmar Eggemann, Steven Rostedt,
Ben Segall, Mel Gorman, Valentin Schneider, linux-arm-kernel,
Paolo Bonzini, Vitaly Kuznetsov, Stefano Stabellini,
Oleksandr Tyshchenko, Daniel Lezcano, Oleg Nesterov
Some cleanups and reorg of paravirt code and headers:
- The first 2 patches should be not controversial at all, as they
remove just some no longer needed #include and struct forward
declarations.
- The 3rd patch is removing CONFIG_PARAVIRT_DEBUG, which IMO has
no real value, as it just changes a crash to a BUG() (the stack
trace will basically be the same). As the maintainer of the main
paravirt user (Xen) I have never seen this crash/BUG() to happen.
- The 4th patch is just a movement of code.
- I don't know for what reason asm/paravirt_api_clock.h was added,
as all archs supporting it do it exactly in the same way. Patch
5 is removing it.
- Patches 6-14 are streamlining the paravirt clock interfaces by
using a common implementation across architectures where possible
and by moving the related code into common sched code, as this is
where it should live.
- Patches 15-20 are more like RFC material preparing the paravirt
infrastructure to support multiple pv_ops function arrays.
As a prerequisite for that it makes life in objtool much easier
with dropping the Xen static initializers of the pv_ops sub-
structures, which is done in patches 15-17.
Patches 18-20 are doing the real preparations for multiple pv_ops
arrays and using those arrays in multiple headers.
- Patch 21 is an example how the new scheme can look like using the
PV-spinlocks.
Changes in V2:
- new patches 13-18 and 20
- complete rework of patch 21
Changes in V3:
- fixed 2 issues detected by kernel test robot
Changes in V4:
- fixed one build issue
Juergen Gross (21):
x86/paravirt: Remove not needed includes of paravirt.h
x86/paravirt: Remove some unneeded struct declarations
x86/paravirt: Remove PARAVIRT_DEBUG config option
x86/paravirt: Move thunk macros to paravirt_types.h
paravirt: Remove asm/paravirt_api_clock.h
sched: Move clock related paravirt code to kernel/sched
arm/paravirt: Use common code for paravirt_steal_clock()
arm64/paravirt: Use common code for paravirt_steal_clock()
loongarch/paravirt: Use common code for paravirt_steal_clock()
riscv/paravirt: Use common code for paravirt_steal_clock()
x86/paravirt: Use common code for paravirt_steal_clock()
x86/paravirt: Move paravirt_sched_clock() related code into tsc.c
x86/paravirt: Introduce new paravirt-base.h header
x86/paravirt: Move pv_native_*() prototypes to paravirt.c
x86/xen: Drop xen_irq_ops
x86/xen: Drop xen_cpu_ops
x86/xen: Drop xen_mmu_ops
objtool: Allow multiple pv_ops arrays
x86/paravirt: Allow pv-calls outside paravirt.h
x86/paravirt: Specify pv_ops array in paravirt macros
x86/pvlocks: Move paravirt spinlock functions into own header
arch/Kconfig | 3 +
arch/arm/Kconfig | 1 +
arch/arm/include/asm/paravirt.h | 22 --
arch/arm/include/asm/paravirt_api_clock.h | 1 -
arch/arm/kernel/Makefile | 1 -
arch/arm/kernel/paravirt.c | 23 --
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/paravirt.h | 14 -
arch/arm64/include/asm/paravirt_api_clock.h | 1 -
arch/arm64/kernel/paravirt.c | 11 +-
arch/loongarch/Kconfig | 1 +
arch/loongarch/include/asm/paravirt.h | 13 -
.../include/asm/paravirt_api_clock.h | 1 -
arch/loongarch/kernel/paravirt.c | 10 +-
arch/powerpc/include/asm/paravirt.h | 3 -
arch/powerpc/include/asm/paravirt_api_clock.h | 2 -
arch/powerpc/platforms/pseries/setup.c | 4 +-
arch/riscv/Kconfig | 1 +
arch/riscv/include/asm/paravirt.h | 14 -
arch/riscv/include/asm/paravirt_api_clock.h | 1 -
arch/riscv/kernel/paravirt.c | 11 +-
arch/x86/Kconfig | 8 +-
arch/x86/entry/entry_64.S | 1 -
arch/x86/entry/vsyscall/vsyscall_64.c | 1 -
arch/x86/hyperv/hv_spinlock.c | 11 +-
arch/x86/include/asm/apic.h | 4 -
arch/x86/include/asm/highmem.h | 1 -
arch/x86/include/asm/mshyperv.h | 1 -
arch/x86/include/asm/paravirt-base.h | 29 ++
arch/x86/include/asm/paravirt-spinlock.h | 146 ++++++++
arch/x86/include/asm/paravirt.h | 331 +++++-------------
arch/x86/include/asm/paravirt_api_clock.h | 1 -
arch/x86/include/asm/paravirt_types.h | 269 +++++++-------
arch/x86/include/asm/pgtable_32.h | 1 -
arch/x86/include/asm/ptrace.h | 2 +-
arch/x86/include/asm/qspinlock.h | 89 +----
arch/x86/include/asm/spinlock.h | 1 -
arch/x86/include/asm/timer.h | 1 +
arch/x86/include/asm/tlbflush.h | 4 -
arch/x86/kernel/Makefile | 2 +-
arch/x86/kernel/apm_32.c | 1 -
arch/x86/kernel/callthunks.c | 1 -
arch/x86/kernel/cpu/bugs.c | 1 -
arch/x86/kernel/cpu/vmware.c | 1 +
arch/x86/kernel/kvm.c | 13 +-
arch/x86/kernel/kvmclock.c | 1 +
arch/x86/kernel/paravirt-spinlocks.c | 26 +-
arch/x86/kernel/paravirt.c | 42 +--
arch/x86/kernel/tsc.c | 10 +-
arch/x86/kernel/vsmp_64.c | 1 -
arch/x86/lib/cache-smp.c | 1 -
arch/x86/mm/init.c | 1 -
arch/x86/xen/enlighten_pv.c | 82 ++---
arch/x86/xen/irq.c | 20 +-
arch/x86/xen/mmu_pv.c | 100 ++----
arch/x86/xen/spinlock.c | 11 +-
arch/x86/xen/time.c | 2 +
drivers/clocksource/hyperv_timer.c | 2 +
drivers/xen/time.c | 2 +-
include/linux/sched/cputime.h | 18 +
kernel/sched/core.c | 5 +
kernel/sched/cputime.c | 13 +
kernel/sched/sched.h | 3 +-
tools/objtool/arch/x86/decode.c | 8 +-
tools/objtool/check.c | 78 ++++-
tools/objtool/include/objtool/check.h | 2 +
66 files changed, 661 insertions(+), 826 deletions(-)
delete mode 100644 arch/arm/include/asm/paravirt.h
delete mode 100644 arch/arm/include/asm/paravirt_api_clock.h
delete mode 100644 arch/arm/kernel/paravirt.c
delete mode 100644 arch/arm64/include/asm/paravirt_api_clock.h
delete mode 100644 arch/loongarch/include/asm/paravirt_api_clock.h
delete mode 100644 arch/powerpc/include/asm/paravirt_api_clock.h
delete mode 100644 arch/riscv/include/asm/paravirt_api_clock.h
create mode 100644 arch/x86/include/asm/paravirt-base.h
create mode 100644 arch/x86/include/asm/paravirt-spinlock.h
delete mode 100644 arch/x86/include/asm/paravirt_api_clock.h
--
2.51.0
^ permalink raw reply
* Re: [PATCH 2/3] irqchip/gic-v3: allocate one SGI for MSHV
From: Anirudh Rayabharam @ 2025-11-27 6:26 UTC (permalink / raw)
To: Marc Zyngier
Cc: kys, haiyangz, wei.liu, decui, longli, catalin.marinas, will,
tglx, Arnd Bergmann, akpm, agordeev, guoweikang.kernel, osandov,
bsz, linux-hyperv, linux-arm-kernel, linux-kernel, linux-arch
In-Reply-To: <87bjkofpsc.wl-maz@kernel.org>
On Wed, Nov 26, 2025 at 09:27:15PM +0000, Marc Zyngier wrote:
> On Wed, 26 Nov 2025 10:46:31 +0000,
> Anirudh Rayabharam <anirudh@anirudhrb.com> wrote:
> >
> > On Wed, Nov 26, 2025 at 09:02:30AM +0000, Marc Zyngier wrote:
> > > On Wed, 26 Nov 2025 08:51:59 +0000,
> > > Anirudh Rayabharam <anirudh@anirudhrb.com> wrote:
> > > >
> > > > On Tue, Nov 25, 2025 at 06:01:38PM +0000, Marc Zyngier wrote:
> > > > > On Tue, 25 Nov 2025 17:01:23 +0000,
> > > > > Anirudh Raybharam <anirudh@anirudhrb.com> wrote:
> > > > > >
> > > > > > From: Anirudh Rayabharam <anirudh@anirudhrb.com>
> > > > > >
> > > > > > From: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
> > > > > >
> > > > > > Currently SGIs are allocated only for the smp subsystem. The MSHV
> > > > > > (Microsoft Hypervisor aka Hyper-V) code also needs an SGI that can be
> > > > > > programmed into the SYNIC to receive intercepts from the hypervisor. The
> > > > > > hypervisor would then assert this SGI whenever there is a guest
> > > > > > VMEXIT.
> > > > > >
> > > > > > Allocate one SGI for MSHV use in addition to the SGIs allocated for
> > > > > > IPIs. When running under MSHV, the full SGI range can be used i.e. no
> > > > > > need to reserve SGIs 8-15 for the secure firmware.
> > > > > >
> > > > > > Since this SGI is needed only when running as a parent partition (i.e.
> > > > > > we can create guest partitions), check for it before allocating an SGI.
> > > > >
> > > > > Sorry, but that's not an acceptable situation.
> > > > >
> > > > > SGIs are for Linux to use, nobody else, and that allocation must be
> > > >
> > > > Why does this restriction exist? In the code SGIs 8-15 are left for
> > > > secure firmware. So, things other than Linux can use SGIs. Why not MSHV
> > > > then?
> > >
> > > Because SGIs are for *internal* usage. Not usage from another random
> > > piece of SW. The ACPI tables explicitly don't describe SGIs. DT
> > > explicitly don't describe SGIs. Do you get the clue?
> >
> > The name Software Generated Interrupts suggests that it is supposed to be
> > used by pieces of SW.
>
> I'm so glad you spell it out for me, I had no idea. I can't help but
> notice that it is not called SGIFRPOSIDKA (Software Generated
> Interrupt From Random Piece Of Software I Don't Know About).
Haha.
>
> Linux owns the SGIs, full stop. If you want to generate interrupts
> from outside of Linux, use a standard interrupts. Not rocket science.
>
> > Yes, ACPI/DT don't describe SGIs because they're not supposed to be used
> > by devices. SW has full control over SGIs and it is up to the SW to
> > assign meaning to them, isn't it?
>
> No. It means that a single *consistent* software agent *owns* these
> interrupts and doesn't have to let *anyone* else use them from outer
> space.
Okay, got it.
>
> > > > > the same irrespective of whether Linux runs virtualised or not. This
> > > > > also won't work with GICv5 (there are no SGIs at all), so this is
> > > > > doomed from the very start, and would immediately create technical
> > > > > debt.
> > > >
> > > > Hyper-V always presents a GICv3 so we don't need to worry about GICv5.
> > >
> > > Well, that's pretty short sighted of you, and eventually you'll have
> > > to support it, or just die. So do the right thing from the beginning.
> >
> > Well, we don't when or if that will happen. But if it does happen, we
> > can solve it in a way that makes sense for GICv5. If there are no SGIs
> > at all, great, maybe we'll have a nicer solution then.
>
> Great. See you then. In the meantime, I have no interest in this sort
> of sorry hacks polluting the stuff I maintain.
>
> > > > > If you want to signal an interrupt to Linux, expose a device with an
> > > > > interrupt in a firmware table (i.e. not an SGI), and use that in your
> > > > > driver.
> > > >
> > > > You mean in the ACPI tables? That would require us to modify the
> > > > firmware to expose this virtual device right?
> > >
> > > Yes. How is that surprising?
> >
> > It's not ideal that we would need some custom firmware to run Linux on
> > MSHV (as a parent). Do you think there could be some other possible solution
> > for handling this in the kernel? Maybe by thinking of it as a platform specific
> > quirk or something?
>
> You either do it the *correct* way, by exposing a virtual device, with
> an edge-triggered PPI, just like other hypervisors have done, or you
> keep your toy to yourself. It is that simple. We don't have to accept
> ugly crap in Linux just for the sake of you not having to do the right
> thing in your firmware.
>
> Feel free to post a new series once you have something that matches
> the above expectations.
Okay got it, I'll come up with a series that reads PPIs from ACPI.
Thanks for your feedback!
Anirudh.
>
> M.
>
> --
> Jazz isn't dead. It just smells funny.
^ permalink raw reply
* Re: [RFC PATCH] Drivers: hv: Confidential VMBus exernal memory support
From: vdso @ 2025-11-27 5:15 UTC (permalink / raw)
To: ltykernel
Cc: decui, haiyangz, kys, linux-hyperv, linux-kernel, longli, tiala,
vdso, wei.liu
In-Reply-To: <20251124182920.9365-1-tiala@microsoft.com>
From: Roman Kisel <vdso@hexbites.dev>
Tianyu Lan wrote:
> In CVM(Confidential VM), system memory is encrypted
> by default. Device drivers typically use the swiotlb
> bounce buffer for DMA memory, which is decrypted
> and shared between the guest and host. Confidential
> Vmbus, however, supports a confidential channel
> that employs encrypted memory for the Vmbus ring
> buffer and external DMA memory. The support for
> the confidential ring buffer has already been
> integrated.
>
> In CVM, device drivers usually employ the standard
> DMA API to map DMA memory with the bounce buffer,
> which remains transparent to the device driver.
> For external DMA memory support, Hyper-V specific
> DMA operations are introduced, bypassing the bounce
> buffer when the confidential external memory flag
> is set. These DMA operations might also be reused
> for TDISP devices in the future, which also support
> DMA operations with encrypted memory.
>
> The DMA operations used are global architecture
> DMA operations (for details, see get_arch_dma_ops()
> and get_dma_ops()), and there is no need to set up
> for each device individually.
>
> Signed-off-by: Tianyu Lan <tiala@microsoft.com>
Tinayu,
Looks great to me!
Reviewed-by: Roman Kisel <vdso@hexbites.dev>
P.S. For the inclined reader, here is how the old, only for
storage and not satisfactory in other ways my attempt to solve this:
https://lore.kernel.org/linux-hyperv/20250409000835.285105-6-romank@linux.microsoft.com/
https://lore.kernel.org/linux-hyperv/20250409000835.285105-7-romank@linux.microsoft.com/
Maybe it'd be a good idea to CC folks who provided feedback back then.
> ---
> drivers/hv/vmbus_drv.c | 90 +++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 89 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index 0dc4692b411a..ca31231b2c32 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -39,6 +39,9 @@
> #include <clocksource/hyperv_timer.h>
> #include <asm/mshyperv.h>
> #include "hyperv_vmbus.h"
> +#include "../../kernel/dma/direct.h"
> +
> +extern const struct dma_map_ops *dma_ops;
>
> struct vmbus_dynid {
> struct list_head node;
> @@ -1429,6 +1432,88 @@ static int vmbus_alloc_synic_and_connect(void)
> return -ENOMEM;
> }
>
> +
> +static bool hyperv_private_memory_dma(struct device *dev)
> +{
> + struct hv_device *hv_dev = device_to_hv_device(dev);
> +
> + if (hv_dev && hv_dev->channel && hv_dev->channel->co_external_memory)
> + return true;
> + else
> + return false;
> +}
> +
> +static dma_addr_t hyperv_dma_map_page(struct device *dev, struct page *page,
> + unsigned long offset, size_t size,
> + enum dma_data_direction dir,
> + unsigned long attrs)
> +{
> + phys_addr_t phys = page_to_phys(page) + offset;
> +
> + if (hyperv_private_memory_dma(dev))
> + return __phys_to_dma(dev, phys);
> + else
> + return dma_direct_map_phys(dev, phys, size, dir, attrs);
> +}
> +
> +static void hyperv_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
> + size_t size, enum dma_data_direction dir, unsigned long attrs)
> +{
> + if (!hyperv_private_memory_dma(dev))
> + dma_direct_unmap_phys(dev, dma_handle, size, dir, attrs);
> +}
> +
> +static int hyperv_dma_map_sg(struct device *dev, struct scatterlist *sgl,
> + int nelems, enum dma_data_direction dir,
> + unsigned long attrs)
> +{
> + struct scatterlist *sg;
> + dma_addr_t dma_addr;
> + int i;
> +
> + if (hyperv_private_memory_dma(dev)) {
> + for_each_sg(sgl, sg, nelems, i) {
> + dma_addr = __phys_to_dma(dev, sg_phys(sg));
> + sg_dma_address(sg) = dma_addr;
> + sg_dma_len(sg) = sg->length;
> + }
> +
> + return nelems;
> + } else {
> + return dma_direct_map_sg(dev, sgl, nelems, dir, attrs);
> + }
> +}
> +
> +static void hyperv_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
> + int nelems, enum dma_data_direction dir, unsigned long attrs)
> +{
> + if (!hyperv_private_memory_dma(dev))
> + dma_direct_unmap_sg(dev, sgl, nelems, dir, attrs);
> +}
> +
> +static int hyperv_dma_supported(struct device *dev, u64 mask)
> +{
> + dev->coherent_dma_mask = mask;
> + return 1;
> +}
> +
> +static size_t hyperv_dma_max_mapping_size(struct device *dev)
> +{
> + if (hyperv_private_memory_dma(dev))
> + return SIZE_MAX;
> + else
> + return swiotlb_max_mapping_size(dev);
> +}
> +
> +const struct dma_map_ops hyperv_dma_ops = {
> + .map_page = hyperv_dma_map_page,
> + .unmap_page = hyperv_dma_unmap_page,
> + .map_sg = hyperv_dma_map_sg,
> + .unmap_sg = hyperv_dma_unmap_sg,
> + .dma_supported = hyperv_dma_supported,
> + .max_mapping_size = hyperv_dma_max_mapping_size,
> +};
> +
> /*
> * vmbus_bus_init -Main vmbus driver initialization routine.
> *
> @@ -1479,8 +1564,11 @@ static int vmbus_bus_init(void)
> * doing that on each VP while initializing SynIC's wastes time.
> */
> is_confidential = ms_hyperv.confidential_vmbus_available;
> - if (is_confidential)
> + if (is_confidential) {
> + dma_ops = &hyperv_dma_ops;
> pr_info("Establishing connection to the confidential VMBus\n");
> + }
> +
> hv_para_set_sint_proxy(!is_confidential);
> ret = vmbus_alloc_synic_and_connect();
> if (ret)
> --
> 2.50.1
^ permalink raw reply
* Re: [PATCH net-next, v4] net: mana: Implement ndo_tx_timeout and serialize queue resets per port.
From: Jakub Kicinski @ 2025-11-27 4:05 UTC (permalink / raw)
To: Dipayaan Roy
Cc: kys, haiyangz, wei.liu, decui, andrew+netdev, davem, edumazet,
pabeni, longli, kotaranov, horms, shradhagupta, ssengar, ernis,
shirazsaleem, linux-hyperv, netdev, linux-kernel, linux-rdma,
dipayanroy
In-Reply-To: <20251123180818.GA18398@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net>
On Sun, 23 Nov 2025 10:08:18 -0800 Dipayaan Roy wrote:
> Implement .ndo_tx_timeout for MANA so any stalled TX queue can be detected
> and a device-controlled port reset for all queues can be scheduled to a
> ordered workqueue. The reset for all queues on stall detection is
> recomended by hardware team.
>
> The change introduces a single ordered workqueue
> "mana_per_port_queue_reset_wq" queuing one work_struct per port,
> using WQ_UNBOUND | WQ_MEM_RECLAIM so stalled queue reset work can
> run on any CPU and still make forward progress under memory
> pressure.
And we need to be able to reset the NIC queue under memory pressure
because.. ? I could be wrong but I still find this unusual / defensive
programming, if you could point me at some existing drivers that'd help.
> @@ -3287,6 +3341,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
> ndev->min_mtu = ETH_MIN_MTU;
> ndev->needed_headroom = MANA_HEADROOM;
> ndev->dev_port = port_idx;
> + ndev->watchdog_timeo = 15 * HZ;
5 sec is typical, off the top of my head
> @@ -3647,6 +3717,11 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
> free_netdev(ndev);
> }
>
> + if (ac->per_port_queue_reset_wq) {
> + destroy_workqueue(ac->per_port_queue_reset_wq);
> + ac->per_port_queue_reset_wq = NULL;
> + }
I think you're missing this cleanup in the failure path of mana_probe
--
pw-bot: cr
^ permalink raw reply
* Re: [PATCH v3 0/9] arch,sysfb,efi: Support EDID on non-x86 EFI systems
From: Richard Lyu @ 2025-11-27 2:20 UTC (permalink / raw)
To: Thomas Zimmermann, ardb, javierm, arnd, helgaas
Cc: x86, linux-arm-kernel, linux-kernel, linux-efi, loongarch,
linux-riscv, dri-devel, linux-hyperv, linux-pci, linux-fbdev
In-Reply-To: <20251126160854.553077-1-tzimmermann@suse.de>
Hi Thomas,
I am attempting to test this patch series but encountered merge conflicts when applying it to various trees.
Could you please clarify the specific base commit (or branch/tag) this series was generated against?
When testing on the next branch on commits 7a2ff00 and e41ef37, I hit a conflict on PATCH v3 4/9:
patching file drivers/pci/vgaarb.c
Hunk #2 FAILED at 557.
1 out of 2 hunks FAILED -- rejects in file drivers/pci/vgaarb.c
When testing against 3a86608 (Linux 6.18-rc1), the following conflicts occurred:
patching file drivers/gpu/drm/sysfb/efidrm.c
Hunk #1 FAILED at 24.
1 out of 2 hunks FAILED -- rejects in file drivers/gpu/drm/sysfb/efidrm.c
patching file drivers/gpu/drm/sysfb/vesadrm.c
Hunk #1 FAILED at 25.
1 out of 2 hunks FAILED -- rejects in file drivers/gpu/drm/sysfb/vesadrm.c
Please let me know the correct base, and I will retest.
Thanks,
Richard Lyu
On 2025/11/26 17:03, Thomas Zimmermann wrote:
> Replace screen_info and edid_info with sysfb_primary_device of type
> struct sysfb_display_info. Update all users. Then implement EDID support
> in the kernel EFI code.
>
> Sysfb DRM drivers currently fetch the global edid_info directly, when
> they should get that information together with the screen_info from their
> device. Wrapping screen_info and edid_info in sysfb_primary_display and
> passing this to drivers enables this.
>
> Replacing both with sysfb_primary_display has been motivate by the EFI
> stub. EFI wants to transfer EDID via config table in a single entry.
> Using struct sysfb_display_info this will become easily possible. Hence
> accept some churn in architecture code for the long-term improvements.
>
> Patches 1 and 2 reduce the exposure of screen_info in EFI-related code.
>
> Patch 3 adds struct sysfb_display_info.
>
> Patch 4 replaces scren_info with sysfb_primary_display. This results in
> several changes throught the kernel, but is really just a refactoring.
>
> Patch 5 updates sysfb to transfer sysfb_primary_display to the related
> drivers.
>
> Patch 6 moves edid_info into sysfb_primary_display. This resolves some
> drivers' reference to the global edid_info, but also makes the EDID data
> available on non-x86 architectures.
>
> Patches 7 and 8 add support for EDID transfers on non-x86 EFI systems.
>
> Patch 9 cleans up the config-table allocation to be easier to understand.
>
> v3:
> - replace SCREEN_INFO table entry (Ard)
> - merge libstub patch into kernel patch
> v2:
> - combine v1 of the series at [1] plus changes from [2] and [3].
>
> [1] https://lore.kernel.org/dri-devel/20251121135624.494768-1-tzimmermann@suse.de/
> [2] https://lore.kernel.org/dri-devel/20251015160816.525825-1-tzimmermann@suse.de/
> [3] https://lore.kernel.org/linux-efi/20251119123011.1187249-5-ardb+git@google.com/
>
> Thomas Zimmermann (9):
> efi: earlycon: Reduce number of references to global screen_info
> efi: sysfb_efi: Reduce number of references to global screen_info
> sysfb: Add struct sysfb_display_info
> sysfb: Replace screen_info with sysfb_primary_display
> sysfb: Pass sysfb_primary_display to devices
> sysfb: Move edid_info into sysfb_primary_display
> efi: Refactor init_primary_display() helpers
> efi: Support EDID information
> efi: libstub: Simplify interfaces for primary_display
>
> arch/arm64/kernel/image-vars.h | 2 +-
> arch/loongarch/kernel/efi.c | 38 ++++-----
> arch/loongarch/kernel/image-vars.h | 2 +-
> arch/riscv/kernel/image-vars.h | 2 +-
> arch/x86/kernel/kexec-bzimage64.c | 4 +-
> arch/x86/kernel/setup.c | 16 ++--
> arch/x86/video/video-common.c | 4 +-
> drivers/firmware/efi/earlycon.c | 42 +++++-----
> drivers/firmware/efi/efi-init.c | 46 ++++++-----
> drivers/firmware/efi/efi.c | 4 +-
> drivers/firmware/efi/libstub/Makefile | 2 +-
> drivers/firmware/efi/libstub/efi-stub-entry.c | 36 +++++++--
> drivers/firmware/efi/libstub/efi-stub.c | 49 +++++++----
> drivers/firmware/efi/libstub/efistub.h | 7 +-
> .../firmware/efi/libstub/primary_display.c | 41 ++++++++++
> drivers/firmware/efi/libstub/screen_info.c | 53 ------------
> drivers/firmware/efi/libstub/zboot.c | 6 +-
> drivers/firmware/efi/sysfb_efi.c | 81 ++++++++++---------
> drivers/firmware/sysfb.c | 13 +--
> drivers/firmware/sysfb_simplefb.c | 2 +-
> drivers/gpu/drm/sysfb/efidrm.c | 14 ++--
> drivers/gpu/drm/sysfb/vesadrm.c | 14 ++--
> drivers/hv/vmbus_drv.c | 6 +-
> drivers/pci/vgaarb.c | 4 +-
> drivers/video/Kconfig | 8 +-
> drivers/video/fbdev/core/fbmon.c | 8 +-
> drivers/video/fbdev/efifb.c | 10 ++-
> drivers/video/fbdev/vesafb.c | 10 ++-
> drivers/video/fbdev/vga16fb.c | 8 +-
> drivers/video/screen_info_pci.c | 5 +-
> include/linux/efi.h | 9 ++-
> include/linux/screen_info.h | 2 -
> include/linux/sysfb.h | 23 ++++--
> include/video/edid.h | 4 -
> 34 files changed, 321 insertions(+), 254 deletions(-)
> create mode 100644 drivers/firmware/efi/libstub/primary_display.c
> delete mode 100644 drivers/firmware/efi/libstub/screen_info.c
>
>
> base-commit: d724c6f85e80a23ed46b7ebc6e38b527c09d64f5
> --
> 2.51.1
>
^ permalink raw reply
* Re: [PATCH v3 5/9] sysfb: Pass sysfb_primary_display to devices
From: Richard Lyu @ 2025-11-27 1:23 UTC (permalink / raw)
To: Thomas Zimmermann, ardb, javierm, arnd, helgaas
Cc: x86, linux-arm-kernel, linux-kernel, linux-efi, loongarch,
linux-riscv, dri-devel, linux-hyperv, linux-pci, linux-fbdev
In-Reply-To: <20251126160854.553077-6-tzimmermann@suse.de>
Reviewed-by: Richard Lyu <richard.lyu@suse.com>
On 2025/11/26 17:03, Thomas Zimmermann wrote:
> Instead of screen_info, store a copy of sysfb_primary_display as
> device data. Pick it up in drivers. Later changes will add additional
> data to the display info, such as EDID information.
>
> Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
> Acked-by: Arnd Bergmann <arnd@arndb.de>
> Acked-by: Ard Biesheuvel <ardb@kernel.org>
> ---
> drivers/firmware/sysfb.c | 5 +++--
> drivers/gpu/drm/sysfb/efidrm.c | 9 ++++++---
> drivers/gpu/drm/sysfb/vesadrm.c | 9 ++++++---
> drivers/video/fbdev/efifb.c | 10 ++++++----
> drivers/video/fbdev/vesafb.c | 10 ++++++----
> drivers/video/fbdev/vga16fb.c | 8 +++++---
> 6 files changed, 32 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
> index 1f671f9219b0..8833582c1883 100644
> --- a/drivers/firmware/sysfb.c
> +++ b/drivers/firmware/sysfb.c
> @@ -141,7 +141,8 @@ static struct device *sysfb_parent_dev(const struct screen_info *si)
>
> static __init int sysfb_init(void)
> {
> - struct screen_info *si = &sysfb_primary_display.screen;
> + struct sysfb_display_info *dpy = &sysfb_primary_display;
> + struct screen_info *si = &dpy->screen;
> struct device *parent;
> unsigned int type;
> struct simplefb_platform_data mode;
> @@ -202,7 +203,7 @@ static __init int sysfb_init(void)
>
> sysfb_set_efifb_fwnode(si, pd);
>
> - ret = platform_device_add_data(pd, si, sizeof(*si));
> + ret = platform_device_add_data(pd, dpy, sizeof(*dpy));
> if (ret)
> goto err;
>
> diff --git a/drivers/gpu/drm/sysfb/efidrm.c b/drivers/gpu/drm/sysfb/efidrm.c
> index 1b683d55d6ea..29533ae8fbbf 100644
> --- a/drivers/gpu/drm/sysfb/efidrm.c
> +++ b/drivers/gpu/drm/sysfb/efidrm.c
> @@ -4,7 +4,7 @@
> #include <linux/efi.h>
> #include <linux/limits.h>
> #include <linux/platform_device.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
>
> #include <drm/clients/drm_client_setup.h>
> #include <drm/drm_atomic.h>
> @@ -141,6 +141,7 @@ static const struct drm_mode_config_funcs efidrm_mode_config_funcs = {
> static struct efidrm_device *efidrm_device_create(struct drm_driver *drv,
> struct platform_device *pdev)
> {
> + const struct sysfb_display_info *dpy;
> const struct screen_info *si;
> const struct drm_format_info *format;
> int width, height, stride;
> @@ -160,9 +161,11 @@ static struct efidrm_device *efidrm_device_create(struct drm_driver *drv,
> size_t nformats;
> int ret;
>
> - si = dev_get_platdata(&pdev->dev);
> - if (!si)
> + dpy = dev_get_platdata(&pdev->dev);
> + if (!dpy)
> return ERR_PTR(-ENODEV);
> + si = &dpy->screen;
> +
> if (screen_info_video_type(si) != VIDEO_TYPE_EFI)
> return ERR_PTR(-ENODEV);
>
> diff --git a/drivers/gpu/drm/sysfb/vesadrm.c b/drivers/gpu/drm/sysfb/vesadrm.c
> index 7b7b5ba26317..16fc223f8c5b 100644
> --- a/drivers/gpu/drm/sysfb/vesadrm.c
> +++ b/drivers/gpu/drm/sysfb/vesadrm.c
> @@ -4,7 +4,7 @@
> #include <linux/ioport.h>
> #include <linux/limits.h>
> #include <linux/platform_device.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
>
> #include <drm/clients/drm_client_setup.h>
> #include <drm/drm_atomic.h>
> @@ -391,6 +391,7 @@ static const struct drm_mode_config_funcs vesadrm_mode_config_funcs = {
> static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv,
> struct platform_device *pdev)
> {
> + const struct sysfb_display_info *dpy;
> const struct screen_info *si;
> const struct drm_format_info *format;
> int width, height, stride;
> @@ -410,9 +411,11 @@ static struct vesadrm_device *vesadrm_device_create(struct drm_driver *drv,
> size_t nformats;
> int ret;
>
> - si = dev_get_platdata(&pdev->dev);
> - if (!si)
> + dpy = dev_get_platdata(&pdev->dev);
> + if (!dpy)
> return ERR_PTR(-ENODEV);
> + si = &dpy->screen;
> +
> if (screen_info_video_type(si) != VIDEO_TYPE_VLFB)
> return ERR_PTR(-ENODEV);
>
> diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
> index 0e1bd3dba255..47ebc0107209 100644
> --- a/drivers/video/fbdev/efifb.c
> +++ b/drivers/video/fbdev/efifb.c
> @@ -15,7 +15,7 @@
> #include <linux/fb.h>
> #include <linux/platform_device.h>
> #include <linux/printk.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <video/vga.h>
> #include <asm/efi.h>
> #include <drm/drm_utils.h> /* For drm_get_panel_orientation_quirk */
> @@ -345,6 +345,7 @@ ATTRIBUTE_GROUPS(efifb);
>
> static int efifb_probe(struct platform_device *dev)
> {
> + struct sysfb_display_info *dpy;
> struct screen_info *si;
> struct fb_info *info;
> struct efifb_par *par;
> @@ -360,10 +361,11 @@ static int efifb_probe(struct platform_device *dev)
> * driver. We get a copy of the attached screen_info, so that we can
> * modify its values without affecting later drivers.
> */
> - si = dev_get_platdata(&dev->dev);
> - if (!si)
> + dpy = dev_get_platdata(&dev->dev);
> + if (!dpy)
> return -ENODEV;
> - si = devm_kmemdup(&dev->dev, si, sizeof(*si), GFP_KERNEL);
> +
> + si = devm_kmemdup(&dev->dev, &dpy->screen, sizeof(*si), GFP_KERNEL);
> if (!si)
> return -ENOMEM;
>
> diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c
> index f135033c22fb..f84f4db244bf 100644
> --- a/drivers/video/fbdev/vesafb.c
> +++ b/drivers/video/fbdev/vesafb.c
> @@ -20,7 +20,7 @@
> #include <linux/ioport.h>
> #include <linux/init.h>
> #include <linux/platform_device.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/io.h>
>
> #include <video/vga.h>
> @@ -243,6 +243,7 @@ static int vesafb_setup(char *options)
>
> static int vesafb_probe(struct platform_device *dev)
> {
> + struct sysfb_display_info *dpy;
> struct screen_info *si;
> struct fb_info *info;
> struct vesafb_par *par;
> @@ -257,10 +258,11 @@ static int vesafb_probe(struct platform_device *dev)
> * driver. We get a copy of the attached screen_info, so that we can
> * modify its values without affecting later drivers.
> */
> - si = dev_get_platdata(&dev->dev);
> - if (!si)
> + dpy = dev_get_platdata(&dev->dev);
> + if (!dpy)
> return -ENODEV;
> - si = devm_kmemdup(&dev->dev, si, sizeof(*si), GFP_KERNEL);
> +
> + si = devm_kmemdup(&dev->dev, &dpy->screen, sizeof(*si), GFP_KERNEL);
> if (!si)
> return -ENOMEM;
>
> diff --git a/drivers/video/fbdev/vga16fb.c b/drivers/video/fbdev/vga16fb.c
> index 6b81337a4909..22085d3668e8 100644
> --- a/drivers/video/fbdev/vga16fb.c
> +++ b/drivers/video/fbdev/vga16fb.c
> @@ -21,7 +21,7 @@
> #include <linux/ioport.h>
> #include <linux/init.h>
> #include <linux/platform_device.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
>
> #include <asm/io.h>
> #include <video/vga.h>
> @@ -1305,15 +1305,17 @@ static const struct fb_ops vga16fb_ops = {
>
> static int vga16fb_probe(struct platform_device *dev)
> {
> + struct sysfb_display_info *dpy;
> struct screen_info *si;
> struct fb_info *info;
> struct vga16fb_par *par;
> int i;
> int ret = 0;
>
> - si = dev_get_platdata(&dev->dev);
> - if (!si)
> + dpy = dev_get_platdata(&dev->dev);
> + if (!dpy)
> return -ENODEV;
> + si = &dpy->screen;
>
> ret = check_mode_supported(si);
> if (ret)
> --
> 2.51.1
>
^ permalink raw reply
* Re: [PATCH v3 4/9] sysfb: Replace screen_info with sysfb_primary_display
From: Richard Lyu @ 2025-11-27 1:21 UTC (permalink / raw)
To: Thomas Zimmermann, ardb, javierm, arnd
Cc: x86, linux-arm-kernel, linux-kernel, linux-efi, loongarch,
linux-riscv, dri-devel, linux-hyperv, linux-pci, linux-fbdev
In-Reply-To: <20251126160854.553077-5-tzimmermann@suse.de>
Reviewed-by: Richard Lyu <richard.lyu@suse.com>
On 2025/11/26 17:03, Thomas Zimmermann wrote:
> Replace the global screen_info with sysfb_primary_display of type
> struct sysfb_display_info. Adapt all users of screen_info.
>
> Instances of screen_info are defined for x86, loongarch and EFI,
> with only one instance compiled into a specific build. Replace all
> of them with sysfb_primary_display.
>
> All existing users of screen_info are updated by pointing them to
> sysfb_primary_display.screen instead. This introduces some churn to
> the code, but has no impact on functionality.
>
> Boot parameters and EFI config tables are unchanged. They transfer
> screen_info as before. The logic in EFI's alloc_screen_info() changes
> slightly, as it now returns the screen field of sysfb_primary_display.
>
> v2:
> - update comment
> - rename init_screen_info() to init_primary_display()
>
> Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
> Acked-by: Arnd Bergmann <arnd@arndb.de>
> Acked-by: Ard Biesheuvel <ardb@kernel.org>
> Acked-by: Bjorn Helgaas <bhelgaas@google.com> # drivers/pci/
> ---
> arch/arm64/kernel/image-vars.h | 2 +-
> arch/loongarch/kernel/efi.c | 15 +++++++------
> arch/loongarch/kernel/image-vars.h | 2 +-
> arch/riscv/kernel/image-vars.h | 2 +-
> arch/x86/kernel/kexec-bzimage64.c | 4 +++-
> arch/x86/kernel/setup.c | 10 +++++----
> arch/x86/video/video-common.c | 4 ++--
> drivers/firmware/efi/earlycon.c | 8 +++----
> drivers/firmware/efi/efi-init.c | 22 +++++++++----------
> drivers/firmware/efi/libstub/efi-stub-entry.c | 18 ++++++++++-----
> drivers/firmware/efi/sysfb_efi.c | 4 ++--
> drivers/firmware/sysfb.c | 6 ++---
> drivers/hv/vmbus_drv.c | 6 ++---
> drivers/pci/vgaarb.c | 4 ++--
> drivers/video/screen_info_pci.c | 5 +++--
> include/linux/screen_info.h | 2 --
> include/linux/sysfb.h | 5 +++--
> 17 files changed, 66 insertions(+), 53 deletions(-)
>
> diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
> index 85bc629270bd..d7b0d12b1015 100644
> --- a/arch/arm64/kernel/image-vars.h
> +++ b/arch/arm64/kernel/image-vars.h
> @@ -38,7 +38,7 @@ PROVIDE(__efistub__end = _end);
> PROVIDE(__efistub___inittext_end = __inittext_end);
> PROVIDE(__efistub__edata = _edata);
> #if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB)
> -PROVIDE(__efistub_screen_info = screen_info);
> +PROVIDE(__efistub_sysfb_primary_display = sysfb_primary_display);
> #endif
> PROVIDE(__efistub__ctype = _ctype);
>
> diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
> index 860a3bc030e0..638a392d2cd2 100644
> --- a/arch/loongarch/kernel/efi.c
> +++ b/arch/loongarch/kernel/efi.c
> @@ -18,7 +18,7 @@
> #include <linux/kobject.h>
> #include <linux/memblock.h>
> #include <linux/reboot.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/uaccess.h>
>
> #include <asm/early_ioremap.h>
> @@ -75,11 +75,11 @@ bool efi_poweroff_required(void)
> unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
>
> #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON)
> -struct screen_info screen_info __section(".data");
> -EXPORT_SYMBOL_GPL(screen_info);
> +struct sysfb_display_info sysfb_primary_display __section(".data");
> +EXPORT_SYMBOL_GPL(sysfb_primary_display);
> #endif
>
> -static void __init init_screen_info(void)
> +static void __init init_primary_display(void)
> {
> struct screen_info *si;
>
> @@ -91,11 +91,12 @@ static void __init init_screen_info(void)
> pr_err("Could not map screen_info config table\n");
> return;
> }
> - screen_info = *si;
> + sysfb_primary_display.screen = *si;
> memset(si, 0, sizeof(*si));
> early_memunmap(si, sizeof(*si));
>
> - memblock_reserve(__screen_info_lfb_base(&screen_info), screen_info.lfb_size);
> + memblock_reserve(__screen_info_lfb_base(&sysfb_primary_display.screen),
> + sysfb_primary_display.screen.lfb_size);
> }
>
> void __init efi_init(void)
> @@ -127,7 +128,7 @@ void __init efi_init(void)
> set_bit(EFI_CONFIG_TABLES, &efi.flags);
>
> if (IS_ENABLED(CONFIG_EFI_EARLYCON) || IS_ENABLED(CONFIG_SYSFB))
> - init_screen_info();
> + init_primary_display();
>
> if (boot_memmap == EFI_INVALID_TABLE_ADDR)
> return;
> diff --git a/arch/loongarch/kernel/image-vars.h b/arch/loongarch/kernel/image-vars.h
> index 41ddcf56d21c..e557ebd46c2b 100644
> --- a/arch/loongarch/kernel/image-vars.h
> +++ b/arch/loongarch/kernel/image-vars.h
> @@ -12,7 +12,7 @@ __efistub_kernel_entry = kernel_entry;
> __efistub_kernel_asize = kernel_asize;
> __efistub_kernel_fsize = kernel_fsize;
> #if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB)
> -__efistub_screen_info = screen_info;
> +__efistub_sysfb_primary_display = sysfb_primary_display;
> #endif
>
> #endif
> diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h
> index 3df30dd1c458..3bd9d06a8b8f 100644
> --- a/arch/riscv/kernel/image-vars.h
> +++ b/arch/riscv/kernel/image-vars.h
> @@ -29,7 +29,7 @@ __efistub__end = _end;
> __efistub__edata = _edata;
> __efistub___init_text_end = __init_text_end;
> #if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB)
> -__efistub_screen_info = screen_info;
> +__efistub_sysfb_primary_display = sysfb_primary_display;
> #endif
>
> #endif
> diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
> index c3244ac680d1..7508d0ccc740 100644
> --- a/arch/x86/kernel/kexec-bzimage64.c
> +++ b/arch/x86/kernel/kexec-bzimage64.c
> @@ -20,6 +20,7 @@
> #include <linux/of_fdt.h>
> #include <linux/efi.h>
> #include <linux/random.h>
> +#include <linux/sysfb.h>
>
> #include <asm/bootparam.h>
> #include <asm/setup.h>
> @@ -303,7 +304,8 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
> params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch;
>
> /* Copying screen_info will do? */
> - memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info));
> + memcpy(¶ms->screen_info, &sysfb_primary_display.screen,
> + sizeof(sysfb_primary_display.screen));
>
> /* Fill in memsize later */
> params->screen_info.ext_mem_k = 0;
> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
> index 1b2edd07a3e1..675e4b9deb1f 100644
> --- a/arch/x86/kernel/setup.c
> +++ b/arch/x86/kernel/setup.c
> @@ -22,6 +22,7 @@
> #include <linux/random.h>
> #include <linux/root_dev.h>
> #include <linux/static_call.h>
> +#include <linux/sysfb.h>
> #include <linux/swiotlb.h>
> #include <linux/tboot.h>
> #include <linux/usb/xhci-dbgp.h>
> @@ -211,8 +212,9 @@ arch_initcall(init_x86_sysctl);
> /*
> * Setup options
> */
> -struct screen_info screen_info;
> -EXPORT_SYMBOL(screen_info);
> +
> +struct sysfb_display_info sysfb_primary_display;
> +EXPORT_SYMBOL(sysfb_primary_display);
> #if defined(CONFIG_FIRMWARE_EDID)
> struct edid_info edid_info;
> EXPORT_SYMBOL_GPL(edid_info);
> @@ -526,7 +528,7 @@ static void __init parse_setup_data(void)
> static void __init parse_boot_params(void)
> {
> ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
> - screen_info = boot_params.screen_info;
> + sysfb_primary_display.screen = boot_params.screen_info;
> #if defined(CONFIG_FIRMWARE_EDID)
> edid_info = boot_params.edid_info;
> #endif
> @@ -1254,7 +1256,7 @@ void __init setup_arch(char **cmdline_p)
> #ifdef CONFIG_VT
> #if defined(CONFIG_VGA_CONSOLE)
> if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
> - vgacon_register_screen(&screen_info);
> + vgacon_register_screen(&sysfb_primary_display.screen);
> #endif
> #endif
> x86_init.oem.banner();
> diff --git a/arch/x86/video/video-common.c b/arch/x86/video/video-common.c
> index e0aeee99bc99..152789f00fcd 100644
> --- a/arch/x86/video/video-common.c
> +++ b/arch/x86/video/video-common.c
> @@ -9,7 +9,7 @@
>
> #include <linux/module.h>
> #include <linux/pci.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/vgaarb.h>
>
> #include <asm/video.h>
> @@ -29,7 +29,7 @@ EXPORT_SYMBOL(pgprot_framebuffer);
> bool video_is_primary_device(struct device *dev)
> {
> #ifdef CONFIG_SCREEN_INFO
> - struct screen_info *si = &screen_info;
> + struct screen_info *si = &sysfb_primary_display.screen;
> struct resource res[SCREEN_INFO_MAX_RESOURCES];
> ssize_t i, numres;
> #endif
> diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c
> index 42e3a173dac1..3d060d59968c 100644
> --- a/drivers/firmware/efi/earlycon.c
> +++ b/drivers/firmware/efi/earlycon.c
> @@ -9,7 +9,7 @@
> #include <linux/io.h>
> #include <linux/kernel.h>
> #include <linux/serial_core.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/string.h>
>
> #include <asm/early_ioremap.h>
> @@ -32,7 +32,7 @@ static void *efi_fb;
> */
> static int __init efi_earlycon_remap_fb(void)
> {
> - const struct screen_info *si = &screen_info;
> + const struct screen_info *si = &sysfb_primary_display.screen;
>
> /* bail if there is no bootconsole or it was unregistered already */
> if (!earlycon_console || !console_is_registered(earlycon_console))
> @@ -147,7 +147,7 @@ static void efi_earlycon_write_char(u32 *dst, unsigned char c, unsigned int h,
> static void
> efi_earlycon_write(struct console *con, const char *str, unsigned int num)
> {
> - const struct screen_info *si = &screen_info;
> + const struct screen_info *si = &sysfb_primary_display.screen;
> u32 cur_efi_x = efi_x;
> unsigned int len;
> const char *s;
> @@ -227,7 +227,7 @@ void __init efi_earlycon_reprobe(void)
> static int __init efi_earlycon_setup(struct earlycon_device *device,
> const char *opt)
> {
> - const struct screen_info *si = &screen_info;
> + const struct screen_info *si = &sysfb_primary_display.screen;
> u16 xres, yres;
> u32 i;
>
> diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
> index a65c2d5b9e7b..d1d418a34407 100644
> --- a/drivers/firmware/efi/efi-init.c
> +++ b/drivers/firmware/efi/efi-init.c
> @@ -19,7 +19,7 @@
> #include <linux/of_address.h>
> #include <linux/of_fdt.h>
> #include <linux/platform_device.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
>
> #include <asm/efi.h>
>
> @@ -57,15 +57,15 @@ static phys_addr_t __init efi_to_phys(unsigned long addr)
> extern __weak const efi_config_table_type_t efi_arch_tables[];
>
> /*
> - * x86 defines its own screen_info and uses it even without EFI,
> - * everything else can get it from here.
> + * x86 defines its own instance of sysfb_primary_display and uses
> + * it even without EFI, everything else can get them from here.
> */
> #if !defined(CONFIG_X86) && (defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON))
> -struct screen_info screen_info __section(".data");
> -EXPORT_SYMBOL_GPL(screen_info);
> +struct sysfb_display_info sysfb_primary_display __section(".data");
> +EXPORT_SYMBOL_GPL(sysfb_primary_display);
> #endif
>
> -static void __init init_screen_info(void)
> +static void __init init_primary_display(void)
> {
> struct screen_info *si;
>
> @@ -75,13 +75,13 @@ static void __init init_screen_info(void)
> pr_err("Could not map screen_info config table\n");
> return;
> }
> - screen_info = *si;
> + sysfb_primary_display.screen = *si;
> memset(si, 0, sizeof(*si));
> early_memunmap(si, sizeof(*si));
>
> - if (memblock_is_map_memory(screen_info.lfb_base))
> - memblock_mark_nomap(screen_info.lfb_base,
> - screen_info.lfb_size);
> + if (memblock_is_map_memory(sysfb_primary_display.screen.lfb_base))
> + memblock_mark_nomap(sysfb_primary_display.screen.lfb_base,
> + sysfb_primary_display.screen.lfb_size);
>
> if (IS_ENABLED(CONFIG_EFI_EARLYCON))
> efi_earlycon_reprobe();
> @@ -274,5 +274,5 @@ void __init efi_init(void)
> if (IS_ENABLED(CONFIG_X86) ||
> IS_ENABLED(CONFIG_SYSFB) ||
> IS_ENABLED(CONFIG_EFI_EARLYCON))
> - init_screen_info();
> + init_primary_display();
> }
> diff --git a/drivers/firmware/efi/libstub/efi-stub-entry.c b/drivers/firmware/efi/libstub/efi-stub-entry.c
> index a6c049835190..401ecbbdf331 100644
> --- a/drivers/firmware/efi/libstub/efi-stub-entry.c
> +++ b/drivers/firmware/efi/libstub/efi-stub-entry.c
> @@ -1,13 +1,18 @@
> // SPDX-License-Identifier: GPL-2.0-only
>
> #include <linux/efi.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
>
> #include <asm/efi.h>
>
> #include "efistub.h"
>
> -static unsigned long screen_info_offset;
> +static unsigned long kernel_image_offset;
> +
> +static void *kernel_image_addr(void *addr)
> +{
> + return addr + kernel_image_offset;
> +}
>
> struct screen_info *alloc_screen_info(void)
> {
> @@ -16,8 +21,11 @@ struct screen_info *alloc_screen_info(void)
>
> if (IS_ENABLED(CONFIG_X86) ||
> IS_ENABLED(CONFIG_EFI_EARLYCON) ||
> - IS_ENABLED(CONFIG_SYSFB))
> - return (void *)&screen_info + screen_info_offset;
> + IS_ENABLED(CONFIG_SYSFB)) {
> + struct sysfb_display_info *dpy = kernel_image_addr(&sysfb_primary_display);
> +
> + return &dpy->screen;
> + }
>
> return NULL;
> }
> @@ -73,7 +81,7 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
> return status;
> }
>
> - screen_info_offset = image_addr - (unsigned long)image->image_base;
> + kernel_image_offset = image_addr - (unsigned long)image->image_base;
>
> status = efi_stub_common(handle, image, image_addr, cmdline_ptr);
>
> diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c
> index 8e0f9d08397f..46ad95084b50 100644
> --- a/drivers/firmware/efi/sysfb_efi.c
> +++ b/drivers/firmware/efi/sysfb_efi.c
> @@ -176,7 +176,7 @@ static int __init efifb_set_system(struct screen_info *si, const struct dmi_syst
>
> static int __init efifb_set_system_callback(const struct dmi_system_id *id)
> {
> - return efifb_set_system(&screen_info, id);
> + return efifb_set_system(&sysfb_primary_display.screen, id);
> }
>
> #define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid) \
> @@ -316,7 +316,7 @@ static struct device_node *find_pci_overlap_node(void)
> }
>
> for_each_of_pci_range(&parser, &range)
> - if (efifb_overlaps_pci_range(&screen_info, &range))
> + if (efifb_overlaps_pci_range(&sysfb_primary_display.screen, &range))
> return np;
> }
> return NULL;
> diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
> index 916b28538a29..1f671f9219b0 100644
> --- a/drivers/firmware/sysfb.c
> +++ b/drivers/firmware/sysfb.c
> @@ -66,7 +66,7 @@ static bool sysfb_unregister(void)
> */
> void sysfb_disable(struct device *dev)
> {
> - struct screen_info *si = &screen_info;
> + struct screen_info *si = &sysfb_primary_display.screen;
> struct device *parent;
>
> mutex_lock(&disable_lock);
> @@ -92,7 +92,7 @@ EXPORT_SYMBOL_GPL(sysfb_disable);
> */
> bool sysfb_handles_screen_info(void)
> {
> - const struct screen_info *si = &screen_info;
> + const struct screen_info *si = &sysfb_primary_display.screen;
>
> return !!screen_info_video_type(si);
> }
> @@ -141,7 +141,7 @@ static struct device *sysfb_parent_dev(const struct screen_info *si)
>
> static __init int sysfb_init(void)
> {
> - struct screen_info *si = &screen_info;
> + struct screen_info *si = &sysfb_primary_display.screen;
> struct device *parent;
> unsigned int type;
> struct simplefb_platform_data mode;
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index a53af6fe81a6..9c937190be81 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -29,7 +29,7 @@
> #include <linux/delay.h>
> #include <linux/panic_notifier.h>
> #include <linux/ptrace.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/efi.h>
> #include <linux/random.h>
> #include <linux/kernel.h>
> @@ -2340,8 +2340,8 @@ static void __maybe_unused vmbus_reserve_fb(void)
> if (efi_enabled(EFI_BOOT)) {
> /* Gen2 VM: get FB base from EFI framebuffer */
> if (IS_ENABLED(CONFIG_SYSFB)) {
> - start = screen_info.lfb_base;
> - size = max_t(__u32, screen_info.lfb_size, 0x800000);
> + start = sysfb_primary_display.screen.lfb_base;
> + size = max_t(__u32, sysfb_primary_display.screen.lfb_size, 0x800000);
> }
> } else {
> /* Gen1 VM: get FB base from PCI */
> diff --git a/drivers/pci/vgaarb.c b/drivers/pci/vgaarb.c
> index 436fa7f4c387..805be9ea4a34 100644
> --- a/drivers/pci/vgaarb.c
> +++ b/drivers/pci/vgaarb.c
> @@ -26,7 +26,7 @@
> #include <linux/poll.h>
> #include <linux/miscdevice.h>
> #include <linux/slab.h>
> -#include <linux/screen_info.h>
> +#include <linux/sysfb.h>
> #include <linux/vt.h>
> #include <linux/console.h>
> #include <linux/acpi.h>
> @@ -557,7 +557,7 @@ EXPORT_SYMBOL(vga_put);
> static bool vga_is_firmware_default(struct pci_dev *pdev)
> {
> #if defined CONFIG_X86
> - return pdev == screen_info_pci_dev(&screen_info);
> + return pdev == screen_info_pci_dev(&sysfb_primary_display.screen);
> #else
> return false;
> #endif
> diff --git a/drivers/video/screen_info_pci.c b/drivers/video/screen_info_pci.c
> index 66bfc1d0a6dc..8f34d8a74f09 100644
> --- a/drivers/video/screen_info_pci.c
> +++ b/drivers/video/screen_info_pci.c
> @@ -4,6 +4,7 @@
> #include <linux/printk.h>
> #include <linux/screen_info.h>
> #include <linux/string.h>
> +#include <linux/sysfb.h>
>
> static struct pci_dev *screen_info_lfb_pdev;
> static size_t screen_info_lfb_bar;
> @@ -26,7 +27,7 @@ static bool __screen_info_relocation_is_valid(const struct screen_info *si, stru
>
> void screen_info_apply_fixups(void)
> {
> - struct screen_info *si = &screen_info;
> + struct screen_info *si = &sysfb_primary_display.screen;
>
> if (screen_info_lfb_pdev) {
> struct resource *pr = &screen_info_lfb_pdev->resource[screen_info_lfb_bar];
> @@ -75,7 +76,7 @@ static void screen_info_fixup_lfb(struct pci_dev *pdev)
> .flags = IORESOURCE_MEM,
> };
> const struct resource *pr;
> - const struct screen_info *si = &screen_info;
> + const struct screen_info *si = &sysfb_primary_display.screen;
>
> if (screen_info_lfb_pdev)
> return; // already found
> diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h
> index 1690706206e8..c022403c599a 100644
> --- a/include/linux/screen_info.h
> +++ b/include/linux/screen_info.h
> @@ -151,6 +151,4 @@ static inline struct pci_dev *screen_info_pci_dev(const struct screen_info *si)
> }
> #endif
>
> -extern struct screen_info screen_info;
> -
> #endif /* _SCREEN_INFO_H */
> diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
> index 8b37247528bf..e8bde392c690 100644
> --- a/include/linux/sysfb.h
> +++ b/include/linux/sysfb.h
> @@ -8,11 +8,10 @@
> */
>
> #include <linux/err.h>
> +#include <linux/platform_data/simplefb.h>
> #include <linux/screen_info.h>
> #include <linux/types.h>
>
> -#include <linux/platform_data/simplefb.h>
> -
> struct device;
> struct platform_device;
> struct screen_info;
> @@ -65,6 +64,8 @@ struct sysfb_display_info {
> struct screen_info screen;
> };
>
> +extern struct sysfb_display_info sysfb_primary_display;
> +
> #ifdef CONFIG_SYSFB
>
> void sysfb_disable(struct device *dev);
> --
> 2.51.1
>
^ permalink raw reply
* Re: [PATCH v3 3/9] sysfb: Add struct sysfb_display_info
From: Richard Lyu @ 2025-11-27 1:18 UTC (permalink / raw)
To: Thomas Zimmermann, ardb, javierm, arnd, helgaas
Cc: x86, linux-arm-kernel, linux-kernel, linux-efi, loongarch,
linux-riscv, dri-devel, linux-hyperv, linux-pci, linux-fbdev,
Thomas Zimmermann
In-Reply-To: <20251126160854.553077-4-tzimmermann@suse.de>
Reviewed-by: Richard Lyu <richard.lyu@suse.com>
On 2025/11/26 17:03, Thomas Zimmermann wrote:
> Add struct sysfb_display_info to wrap display-related state. For now
> it contains only the screen's video mode. Later EDID will be added as
> well.
>
> This struct will be helpful for passing display state to sysfb drivers
> or from the EFI stub library.
>
> Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
> Acked-by: Arnd Bergmann <arnd@arndb.de>
> Acked-by: Ard Biesheuvel <ardb@kernel.org>
> ---
> include/linux/sysfb.h | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
> index 8527a50a5290..8b37247528bf 100644
> --- a/include/linux/sysfb.h
> +++ b/include/linux/sysfb.h
> @@ -8,6 +8,7 @@
> */
>
> #include <linux/err.h>
> +#include <linux/screen_info.h>
> #include <linux/types.h>
>
> #include <linux/platform_data/simplefb.h>
> @@ -60,6 +61,10 @@ struct efifb_dmi_info {
> int flags;
> };
>
> +struct sysfb_display_info {
> + struct screen_info screen;
> +};
> +
> #ifdef CONFIG_SYSFB
>
> void sysfb_disable(struct device *dev);
> --
> 2.51.1
>
^ permalink raw reply
* Re: [PATCH 2/3] irqchip/gic-v3: allocate one SGI for MSHV
From: Wei Liu @ 2025-11-26 22:25 UTC (permalink / raw)
To: Anirudh Raybharam
Cc: kys, haiyangz, wei.liu, decui, longli, catalin.marinas, will, maz,
tglx, Arnd Bergmann, akpm, agordeev, guoweikang.kernel, osandov,
bsz, linux-hyperv, linux-arm-kernel, linux-kernel, linux-arch
In-Reply-To: <20251125170124.2443340-3-anirudh@anirudhrb.com>
On Tue, Nov 25, 2025 at 05:01:23PM +0000, Anirudh Raybharam wrote:
> From: Anirudh Rayabharam <anirudh@anirudhrb.com>
[...]
> /* SMCCC hypercall parameters */
> #define HV_SMCCC_FUNC_NUMBER 1
> #define HV_FUNC_ID ARM_SMCCC_CALL_VAL( \
> diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
> index 3de351e66ee8..56013dd0564c 100644
> --- a/drivers/irqchip/irq-gic-v3.c
> +++ b/drivers/irqchip/irq-gic-v3.c
> @@ -35,6 +35,7 @@
> #include <asm/exception.h>
> #include <asm/smp_plat.h>
> #include <asm/virt.h>
> +#include <asm/mshyperv.h>
>
> #include "irq-gic-common.h"
>
> @@ -1456,8 +1457,24 @@ static void __init gic_smp_init(void)
> .fwnode = gic_data.fwnode,
> .param_count = 1,
> };
> + /* Register all 8 non-secure SGIs */
> + const int NR_SMP_SGIS = 8;
> + int nr_sgis = NR_SMP_SGIS;
> int base_sgi;
>
> + /*
> + * Allocate one more SGI for use by Hyper-V. This is only needed when
> + * Linux is running in a parent partition. Hyper-V will use this interrupt
> + * to notify the parent partition of intercepts.
> + *
> + * When running on Hyper-V, it is okay to use SGIs 8-15. They're not reserved
> + * for secure firmware.
> + */
> +#if IS_ENABLED(CONFIG_HYPERV)
> + if (hv_parent_partition())
> + nr_sgis += 1;
> +#endif
> +
This is far too intrusive. Let's take Marc's feedback and work with the
hypervisor team to resolve this properly.
Wei
^ permalink raw reply
* [PATCH v6 3/3] hyperv: Cleanly shutdown root partition with MSHV
From: Praveen K Paladugu @ 2025-11-26 21:49 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, tglx, mingo, linux-hyperv,
linux-kernel, bp, dave.hansen, x86, hpa, arnd
Cc: anbelski, prapal, easwar.hariharan, nunodasneves, skinsburskii
In-Reply-To: <20251126215013.11549-1-prapal@linux.microsoft.com>
When a root partition running on MSHV is powered off, the default
behavior is to write ACPI registers to power-off. However, this ACPI
write is intercepted by MSHV and will result in a Machine Check
Exception(MCE).
The root partition eventually 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 correctly shutdown a root partition running on MSHV hypervisor, sleep
state information must be configured within the hypervsior. Later, the
HVCALL_ENTER_SLEEP_STATE hypercall should be invoked as the last step in
the shutdown sequence.
The previous patch configures the sleep state information and this patch
invokes HVCALL_ENTER_SLEEP_STATE hypercall to cleanly shutdown the root
partition.
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>
Reviewed-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
---
arch/x86/include/asm/mshyperv.h | 2 ++
arch/x86/kernel/cpu/mshyperv.c | 2 ++
drivers/hv/mshv_common.c | 18 ++++++++++++++++++
3 files changed, 22 insertions(+)
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 166053df0484..4c22f3257368 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -183,9 +183,11 @@ void hv_apic_init(void);
void __init hv_init_spinlocks(void);
bool hv_vcpu_is_preempted(int vcpu);
void hv_sleep_notifiers_register(void);
+void hv_machine_power_off(void);
#else
static inline void hv_apic_init(void) {}
static inline void hv_sleep_notifiers_register(void) {};
+static inline void hv_machine_power_off(void) {};
#endif
struct irq_domain *hv_create_pci_msi_domain(void);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index fac9953a72ef..579fb2c64cfd 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -621,6 +621,8 @@ static void __init ms_hyperv_init_platform(void)
#endif
#if IS_ENABLED(CONFIG_HYPERV)
+ if (hv_root_partition())
+ machine_ops.power_off = hv_machine_power_off;
#if defined(CONFIG_KEXEC_CORE)
machine_ops.shutdown = hv_machine_shutdown;
#endif
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index f1d4e81107ee..28905e3ed9c0 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -217,4 +217,22 @@ void hv_sleep_notifiers_register(void)
pr_err("%s: cannot register reboot notifier %d\n", __func__,
ret);
}
+
+/*
+ * Power off the machine by entering S5 sleep state via Hyper-V hypercall.
+ * This call does not return if successful.
+ */
+void hv_machine_power_off(void)
+{
+ unsigned long flags;
+ struct hv_input_enter_sleep_state *in;
+
+ local_irq_save(flags);
+ in = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ in->sleep_state = HV_SLEEP_STATE_S5;
+
+ (void)hv_do_hypercall(HVCALL_ENTER_SLEEP_STATE, in, NULL);
+ local_irq_restore(flags);
+
+}
#endif
--
2.51.0
^ permalink raw reply related
* [PATCH v6 2/3] hyperv: Use reboot notifier to configure sleep state
From: Praveen K Paladugu @ 2025-11-26 21:49 UTC (permalink / raw)
To: kys, haiyangz, wei.liu, decui, tglx, mingo, linux-hyperv,
linux-kernel, bp, dave.hansen, x86, hpa, arnd
Cc: anbelski, prapal, easwar.hariharan, nunodasneves, skinsburskii
In-Reply-To: <20251126215013.11549-1-prapal@linux.microsoft.com>
Configure sleep state information in mshv hypervisor. This sleep state
information from ACPI will be used by hypervisor to poweroff the host.
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>
Reviewed-by: Easwar Hariharan <easwar.hariharan@linux.microsoft.com>
---
arch/x86/hyperv/hv_init.c | 1 +
arch/x86/include/asm/mshyperv.h | 2 +
drivers/hv/mshv_common.c | 80 +++++++++++++++++++++++++++++++++
3 files changed, 83 insertions(+)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e28737ec7054..daf97a984b78 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -555,6 +555,7 @@ void __init hyperv_init(void)
hv_remap_tsc_clocksource();
hv_root_crash_init();
+ 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 10037125099a..166053df0484 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -182,8 +182,10 @@ 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);
+void hv_sleep_notifiers_register(void);
#else
static inline void hv_apic_init(void) {}
+static inline void hv_sleep_notifiers_register(void) {};
#endif
struct irq_domain *hv_create_pci_msi_domain(void);
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
index aa2be51979fd..f1d4e81107ee 100644
--- a/drivers/hv/mshv_common.c
+++ b/drivers/hv/mshv_common.c
@@ -14,6 +14,9 @@
#include <asm/mshyperv.h>
#include <linux/resume_user_mode.h>
#include <linux/export.h>
+#include <linux/acpi.h>
+#include <linux/notifier.h>
+#include <linux/reboot.h>
#include "mshv.h"
@@ -138,3 +141,80 @@ int hv_call_get_partition_property(u64 partition_id,
return 0;
}
EXPORT_SYMBOL_GPL(hv_call_get_partition_property);
+
+#ifdef CONFIG_X86_64
+/*
+ * 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.
+ *
+ * In order to pass proper PM values to mshv, ACPI should be initialized and
+ * should support S5 sleep state when this method is invoked.
+ */
+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;
+}
+
+/*
+ * This notifier initializes sleep states in mshv hypervisor which will be
+ * used during power off.
+ */
+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_initialize_sleep_states();
+
+ return ret ? NOTIFY_DONE : NOTIFY_OK;
+}
+
+static struct notifier_block hv_reboot_notifier = {
+ .notifier_call = hv_reboot_notifier_handler,
+};
+
+void hv_sleep_notifiers_register(void)
+{
+ int ret;
+
+ ret = register_reboot_notifier(&hv_reboot_notifier);
+ if (ret)
+ pr_err("%s: cannot register reboot notifier %d\n", __func__,
+ ret);
+}
+#endif
--
2.51.0
^ 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