- Linux-kselftest-mirror - lists.linaro.org

[PATCH net-next v6] ipv6: add `force_forwarding` sysctl to enable per-interface forwarding

by Gabriel Goller

It is currently impossible to enable ipv6 forwarding on a per-interface basis like in ipv4. To enable forwarding on an ipv6 interface we need to enable it on all interfaces and disable it on the other interfaces using a netfilter rule. This is especially cumbersome if you have lots of interface and only want to enable forwarding on a few. According to the sysctl docs [0] the `net.ipv6.conf.all.forwarding` enables forwarding for all interfaces, while the interface-specific `net.ipv6.conf.<interface>.forwarding` configures the interface Host/Router configuration. Introduce a new sysctl flag `force_forwarding`, which can be set on every interface. The ip6_forwarding function will then check if the global forwarding flag OR the force_forwarding flag is active and forward the packet. To preserver backwards-compatibility reset the flag (on all interfaces) to 0 if the net.ipv6.conf.all.forwarding flag is set to 0. Add a short selftest that checks if a packet gets forwarded with and without `force_forwarding`. [0]: https://www.kernel.org/doc/Documentation/networking/ip-sysctl.txt Signed-off-by: Gabriel Goller <g.goller(a)proxmox.com> Acked-by: Nicolas Dichtel <nicolas.dichtel(a)6wind.com> --- v6: * rebase * remove brackts around single line * add 'nodad' to addresses in selftest to avoid sporadic failures v5: https://lore.kernel.org/netdev/20250707094307.223975-1-g.goller@proxmox.com/ * update conf/all/forwarding docs * simplified backwards-compat comment * remove ASSERT_RTNL as it's guaranteed by __in6_dev_get_rtnl_net() already * cange ip6_forward logic so that it doesn't depend on the idev existing * move WRITE_ONCE inside device lock v4: https://lore.kernel.org/netdev/20250703160154.560239-1-g.goller@proxmox.com/ * actually write the sysctl value to the table * use ASSERT_RTNL() when forwarding the sysctl change * remove useless comments in function body * simplify forwarding and force_forwarding check in ip6_output.c * fix code backticks in Documentation (double instead of single) * add selftests v3: https://lore.kernel.org/netdev/20250702074619.139031-1-g.goller@proxmox.com/ * remove forwarding=0 setting force_forwarding=0 globally. * add min and max (0 and 1) value to sysctl. v2: https://lore.kernel.org/netdev/20250701140423.487411-1-g.goller@proxmox.com/ * rename from `do_forwarding` to `force_forwarding`. * add global `force_forwarding` flag which will enable `force_forwarding` on every interface like the `ipv4.all.forwarding` flag. * `forwarding`=0 will disable global and per-interface `force_forwarding`. * export option as NETCONFA_FORCE_FORWARDING. v1: https://lore.kernel.org/netdev/20250702074619.139031-1-g.goller@proxmox.com/ Documentation/networking/ip-sysctl.rst | 9 +- include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + include/uapi/linux/netconf.h | 1 + include/uapi/linux/sysctl.h | 1 + net/ipv6/addrconf.c | 82 ++++++++++++++ net/ipv6/ip6_output.c | 3 +- tools/testing/selftests/net/Makefile | 1 + .../selftests/net/ipv6_force_forwarding.sh | 105 ++++++++++++++++++ 9 files changed, 201 insertions(+), 3 deletions(-) create mode 100755 tools/testing/selftests/net/ipv6_force_forwarding.sh diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 0f1251cce314..6d92bae0257a 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2281,8 +2281,8 @@ conf/all/disable_ipv6 - BOOLEAN conf/all/forwarding - BOOLEAN Enable global IPv6 forwarding between all interfaces. - IPv4 and IPv6 work differently here; e.g. netfilter must be used - to control which interfaces may forward packets and which not. + IPv4 and IPv6 work differently here; the ``force_forwarding`` flag must + be used to control which interfaces may forward packets. This also sets all interfaces' Host/Router setting 'forwarding' to the specified value. See below for details. @@ -2292,6 +2292,11 @@ conf/all/forwarding - BOOLEAN proxy_ndp - BOOLEAN Do proxy ndp. +force_forwarding - BOOLEAN + Enable forwarding on this interface only -- regardless of the setting on + ``conf/all/forwarding``. When setting ``conf.all.forwarding`` to 0, + the ``force_forwarding`` flag will be reset on all interfaces. + fwmark_reflect - BOOLEAN Controls the fwmark of kernel-generated IPv6 reply packets that are not associated with a socket for example, TCP RSTs or ICMPv6 echo replies). diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5aeeed22f35b..d975a86f29be 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -17,6 +17,7 @@ struct ipv6_devconf { __s32 hop_limit; __s32 mtu6; __s32 forwarding; + __s32 force_forwarding; __s32 disable_policy; __s32 proxy_ndp; __cacheline_group_end(ipv6_devconf_read_txrx); diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index cf592d7b630f..d4d3ae774b26 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -199,6 +199,7 @@ enum { DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_ACCEPT_UNTRACKED_NA, DEVCONF_ACCEPT_RA_MIN_LFT, + DEVCONF_FORCE_FORWARDING, DEVCONF_MAX }; diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index fac4edd55379..1c8c84d65ae3 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -19,6 +19,7 @@ enum { NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, NETCONFA_INPUT, NETCONFA_BC_FORWARDING, + NETCONFA_FORCE_FORWARDING, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 8981f00204db..63d1464cb71c 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -573,6 +573,7 @@ enum { NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27, NET_IPV6_RA_DEFRTR_METRIC=28, + NET_IPV6_FORCE_FORWARDING=29, __NET_IPV6_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ba2ec7c870cc..580aed034849 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -239,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, .ra_honor_pio_pflag = 0, + .force_forwarding = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -303,6 +304,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, .ra_honor_pio_pflag = 0, + .force_forwarding = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -857,6 +859,9 @@ static void addrconf_forward_change(struct net *net, __s32 newf) idev = __in6_dev_get_rtnl_net(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); + /* Disabling all.forwarding sets 0 to force_forwarding for all interfaces */ + if (newf == 0) + WRITE_ONCE(idev->cnf.force_forwarding, 0); WRITE_ONCE(idev->cnf.forwarding, newf); if (changed) @@ -5719,6 +5724,7 @@ static void ipv6_store_devconf(const struct ipv6_devconf *cnf, array[DEVCONF_ACCEPT_UNTRACKED_NA] = READ_ONCE(cnf->accept_untracked_na); array[DEVCONF_ACCEPT_RA_MIN_LFT] = READ_ONCE(cnf->accept_ra_min_lft); + array[DEVCONF_FORCE_FORWARDING] = READ_ONCE(cnf->force_forwarding); } static inline size_t inet6_ifla6_size(void) @@ -6747,6 +6753,75 @@ static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write return ret; } +static void addrconf_force_forward_change(struct net *net, __s32 newf) +{ + struct net_device *dev; + struct inet6_dev *idev; + + for_each_netdev(net, dev) { + idev = __in6_dev_get_rtnl_net(dev); + if (idev) { + int changed = (!idev->cnf.force_forwarding) ^ (!newf); + + WRITE_ONCE(idev->cnf.force_forwarding, newf); + if (changed) + inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF, + NETCONFA_FORCE_FORWARDING, + dev->ifindex, &idev->cnf); + } + } +} + +static int addrconf_sysctl_force_forwarding(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct inet6_dev *idev = ctl->extra1; + struct ctl_table tmp_ctl = *ctl; + struct net *net = ctl->extra2; + int *valp = ctl->data; + int new_val = *valp; + int old_val = *valp; + loff_t pos = *ppos; + int ret; + + tmp_ctl.extra1 = SYSCTL_ZERO; + tmp_ctl.extra2 = SYSCTL_ONE; + tmp_ctl.data = &new_val; + + ret = proc_douintvec_minmax(&tmp_ctl, write, buffer, lenp, ppos); + + if (write && old_val != new_val) { + if (!rtnl_net_trylock(net)) + return restart_syscall(); + + WRITE_ONCE(*valp, new_val); + + if (valp == &net->ipv6.devconf_dflt->force_forwarding) { + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORCE_FORWARDING, + NETCONFA_IFINDEX_DEFAULT, + net->ipv6.devconf_dflt); + } else if (valp == &net->ipv6.devconf_all->force_forwarding) { + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORCE_FORWARDING, + NETCONFA_IFINDEX_ALL, + net->ipv6.devconf_all); + + addrconf_force_forward_change(net, new_val); + } else { + inet6_netconf_notify_devconf(net, RTM_NEWNETCONF, + NETCONFA_FORCE_FORWARDING, + idev->dev->ifindex, + &idev->cnf); + } + rtnl_net_unlock(net); + } + + if (ret) + *ppos = pos; + return ret; +} + static int minus_one = -1; static const int two_five_five = 255; static u32 ioam6_if_id_max = U16_MAX; @@ -7217,6 +7292,13 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, + { + .procname = "force_forwarding", + .data = &ipv6_devconf.force_forwarding, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = addrconf_sysctl_force_forwarding, + }, }; static int __addrconf_sysctl_register(struct net *net, char *dev_name, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 7bd29a9ff0db..3853090d7282 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -509,7 +509,8 @@ int ip6_forward(struct sk_buff *skb) u32 mtu; idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); - if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) + if (!READ_ONCE(net->ipv6.devconf_all->forwarding) && + (!idev || !READ_ONCE(idev->cnf.force_forwarding))) goto error; if (skb->pkt_type != PACKET_HOST) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 332f387615d7..f64ec8a15a77 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -112,6 +112,7 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += ipv6_force_forwarding.sh # YNL files, must be before "include ..lib.mk" YNL_GEN_FILES := busy_poller netlink-dumps diff --git a/tools/testing/selftests/net/ipv6_force_forwarding.sh b/tools/testing/selftests/net/ipv6_force_forwarding.sh new file mode 100755 index 000000000000..bf0243366caa --- /dev/null +++ b/tools/testing/selftests/net/ipv6_force_forwarding.sh @@ -0,0 +1,105 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test IPv6 force_forwarding interface property +# +# This test verifies that the force_forwarding property works correctly: +# - When global forwarding is disabled, packets are not forwarded normally +# - When force_forwarding is enabled on an interface, packets are forwarded +# regardless of the global forwarding setting + +source lib.sh + +cleanup() { + cleanup_ns $ns1 $ns2 $ns3 +} + +trap cleanup EXIT + +setup_test() { + # Create three namespaces: sender, router, receiver + setup_ns ns1 ns2 ns3 + + # Create veth pairs: ns1 <-> ns2 <-> ns3 + ip link add name veth12 type veth peer name veth21 + ip link add name veth23 type veth peer name veth32 + + # Move interfaces to namespaces + ip link set veth12 netns $ns1 + ip link set veth21 netns $ns2 + ip link set veth23 netns $ns2 + ip link set veth32 netns $ns3 + + # Configure interfaces + ip -n $ns1 addr add 2001:db8:1::1/64 dev veth12 nodad + ip -n $ns2 addr add 2001:db8:1::2/64 dev veth21 nodad + ip -n $ns2 addr add 2001:db8:2::1/64 dev veth23 nodad + ip -n $ns3 addr add 2001:db8:2::2/64 dev veth32 nodad + + # Bring up interfaces + ip -n $ns1 link set veth12 up + ip -n $ns2 link set veth21 up + ip -n $ns2 link set veth23 up + ip -n $ns3 link set veth32 up + + # Add routes + ip -n $ns1 route add 2001:db8:2::/64 via 2001:db8:1::2 + ip -n $ns3 route add 2001:db8:1::/64 via 2001:db8:2::1 + + # Disable global forwarding + ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=0 +} + +test_force_forwarding() { + local ret=0 + + echo "TEST: force_forwarding functionality" + + # Check if force_forwarding sysctl exists + if ! ip netns exec $ns2 test -f /proc/sys/net/ipv6/conf/veth21/force_forwarding; then + echo "SKIP: force_forwarding not available" + return $ksft_skip + fi + + # Test 1: Without force_forwarding, ping should fail + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=0 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=0 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "FAIL: ping succeeded when forwarding disabled" + ret=1 + else + echo "PASS: forwarding disabled correctly" + fi + + # Test 2: With force_forwarding enabled, ping should succeed + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=1 + ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=1 + + if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then + echo "PASS: force_forwarding enabled forwarding" + else + echo "FAIL: ping failed with force_forwarding enabled" + ret=1 + fi + + return $ret +} + +echo "IPv6 force_forwarding test" +echo "==========================" + +setup_test +test_force_forwarding +ret=$? + +if [ $ret -eq 0 ]; then + echo "OK" + exit 0 +elif [ $ret -eq $ksft_skip ]; then + echo "SKIP" + exit $ksft_skip +else + echo "FAIL" + exit 1 +fi -- 2.39.5

1 month

3
4
0 0

[PATCH mm-stable] selftests/damon/sysfs.py: stop DAMON for dumping failures

by SeongJae Park

Commit 4ece01897627 ("selftests/damon: add python and drgn-based DAMON sysfs test") in mm-stable tree introduced sysfs.py that runs drgn for dumping DAMON status. When the DAMON status dumping fails for reasons including drgn uninstalled environment, the test fails without stopping DAMON. Following DAMON selftests that assumes DAMON is not running when they executed therefore fail. Catch dumping failures and stop DAMON for that case. Fixes: 4ece01897627 ("selftests/damon: add python and drgn-based DAMON sysfs test") # mm-stable Reported-by: kernel test robot <oliver.sang(a)intel.com> Closes: https://lore.kernel.org/oe-lkp/202507220707.9c5d6247-lkp@intel.com Signed-off-by: SeongJae Park <sj(a)kernel.org> --- tools/testing/selftests/damon/sysfs.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/damon/sysfs.py b/tools/testing/selftests/damon/sysfs.py index 4ff99db0d247..dbf6613529bd 100755 --- a/tools/testing/selftests/damon/sysfs.py +++ b/tools/testing/selftests/damon/sysfs.py @@ -8,6 +8,10 @@ import subprocess import _damon_sysfs def dump_damon_status_dict(pid): + try: + subprocess.check_output(['which', 'drgn'], stderr=subprocess.DEVNULL) + except: + return None, 'drgn not found' file_dir = os.path.dirname(os.path.abspath(__file__)) dump_script = os.path.join(file_dir, 'drgn_dump_damon_status.py') rc = subprocess.call(['drgn', dump_script, pid, 'damon_dump_output'], @@ -31,6 +35,7 @@ def main(): status, err = dump_damon_status_dict(kdamonds.kdamonds[0].pid) if err is not None: print(err) + kdamonds.stop() exit(1) if len(status['contexts']) != 1: base-commit: 49c3f600a9088332b3c1a6db2dc6f3516f273609 -- 2.39.5

1 month

1
0
0 0

[PATCH 00/22] selftests/damon/sysfs.py: test all parameters

by SeongJae Park

sysfs.py tests if DAMON sysfs interface is passing the user-requested parameters to DAMON as expected. But only the default (minimum) parameters are being tested. This is partially because _damon_sysfs.py, which is the library for making the parameter requests, is not supporting the entire parameters. The internal DAMON status dump script (drgn_dump_damon_status.py) is also not dumping entire parameters. Extend the test coverage by updating parameters input and status dumping scripts to support all parameters, and writing additional tests using those. This increased test coverage actually found one real bug (https://lore.kernel.org/20250719181932.72944-1-sj@kernel.org). First seven patches (1-7) extend _damon_sysfs.py for all parameters setup. The eight patch (8) fixes _damon_sysfs.py to use correct max nr_acceses and age values for their type. Following three patches (9-11) extend drgn_dump_damon_status.py to dump full DAMON parameters. Following nine patches (12-20) refactor sysfs.py for general testing code reuse, and extend it for full parameters check. Finally, two patches (21 and 22) add test cases in sysfs.py for full parameters testing. SeongJae Park (22): selftests/damon/_damon_sysfs: support DAMOS watermarks setup selftests/damon/_damon_sysfs: support DAMOS filters setup selftests/damon/_damon_sysfs: support monitoring intervals goal setup selftests/damon/_damon_sysfs: support DAMOS quota weights setup selftests/damon/_damon_sysfs: support DAMOS quota goal nid setup selftests/damon/_damon_sysfs: support DAMOS action dests setup selftests/damon/_damon_sysfs: support DAMOS target_nid setup selftests/damon/_damon_sysfs: use 2**32 - 1 as max nr_accesses and age selftests/damon/drgn_dump_damon_status: dump damos->migrate_dests selftests/damon/drgn_dump_damon_status: dump ctx->ops.id selftests/damon/drgn_dump_damon_status: dump DAMOS filters selftests/damon/sysfs.py: generalize DAMOS Watermarks commit assertion selftests/damon/sysfs.py: generalize DamosQuota commit assertion selftests/damon/sysfs.py: test quota goal commitment selftests/damon/sysfs.py: test DAMOS destinations commitment selftests/damon/sysfs.py: generalize DAMOS schemes commit assertion selftests/damon/sysfs.py: test DAMOS filters commitment selftests/damon/sysfs.py: generalize DAMOS schemes commit assertion selftests/damon/sysfs.py: generalize monitoring attributes commit assertion selftests/damon/sysfs.py: generalize DAMON context commit assertion selftests/damon/sysfs.py: test non-default parameters runtime commit selftests/damon/sysfs.py: test runtime reduction of DAMON parameters tools/testing/selftests/damon/_damon_sysfs.py | 301 +++++++++++++++++- .../selftests/damon/drgn_dump_damon_status.py | 63 +++- tools/testing/selftests/damon/sysfs.py | 284 +++++++++++++---- 3 files changed, 568 insertions(+), 80 deletions(-) base-commit: fc8066077f44a4fd43f8fdb12bc238f8fbeaa3c5 -- 2.39.5

1 month

2
24
0 0

[RESEND PATCH] selftests/pidfd: align stack to fix SP alignment exception

by Shuai Xue

The pidfd_test fails on the ARM64 platform with the following error: Bail out! pidfd_poll check for premature notification on child thread exec test: Failed When exception-trace is enabled, the kernel logs the details: #echo 1 > /proc/sys/debug/exception-trace #dmesg | tail -n 20 [48628.713023] pidfd_test[1082142]: unhandled exception: SP Alignment, ESR 0x000000009a000000, SP/PC alignment exception in pidfd_test[400000+4000] [48628.713049] CPU: 21 PID: 1082142 Comm: pidfd_test Kdump: loaded Tainted: G W E 6.6.71-3_rc1.al8.aarch64 #1 [48628.713051] Hardware name: AlibabaCloud AliServer-Xuanwu2.0AM-1UC1P-5B/AS1111MG1, BIOS 1.2.M1.AL.P.157.00 07/29/2023 [48628.713053] pstate: 60001800 (nZCv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=-c) [48628.713055] pc : 0000000000402100 [48628.713056] lr : 0000ffff98288f9c [48628.713056] sp : 0000ffffde49daa8 [48628.713057] x29: 0000000000000000 x28: 0000000000000000 x27: 0000000000000000 [48628.713060] x26: 0000000000000000 x25: 0000000000000000 x24: 0000000000000000 [48628.713062] x23: 0000000000000000 x22: 0000000000000000 x21: 0000000000400e80 [48628.713065] x20: 0000000000000000 x19: 0000000000402650 x18: 0000000000000000 [48628.713067] x17: 00000000004200d8 x16: 0000ffff98288f40 x15: 0000ffffde49b92c [48628.713070] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000 [48628.713072] x11: 0000000000001011 x10: 0000000000402100 x9 : 0000000000000010 [48628.713074] x8 : 00000000000000dc x7 : 3861616239346564 x6 : 000000000000000a [48628.713077] x5 : 0000ffffde49daa8 x4 : 000000000000000a x3 : 0000ffffde49daa8 [48628.713079] x2 : 0000ffffde49dadc x1 : 0000ffffde49daa8 x0 : 0000000000000000 According to ARM ARM D1.3.10.2 SP alignment checking: > When the SP is used as the base address of a calculation, regardless of > any offset applied by the instruction, if bits [3:0] of the SP are not > 0b0000, there is a misaligned SP. To fix it, align the stack with 16 bytes. Signed-off-by: Shuai Xue <xueshuai(a)linux.alibaba.com> --- tools/testing/selftests/pidfd/pidfd_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index c081ae91313a..ec161a7c3ff9 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -33,7 +33,7 @@ static bool have_pidfd_send_signal; static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; - char *stack[1024] = { 0 }; + char *stack[1024] __attribute__((aligned(16))) = {0}; #ifdef __ia64__ return __clone2(fn, stack, stack_size, flags | SIGCHLD, NULL, pidfd); -- 2.39.3

1 month

3
6
0 0

[PATCH net-next] selftests: tc: Add generic erspan_opts matching support for tc-flower

by shuali＠redhat.com

From: Li Shuang <shuali(a)redhat.com> Add test cases to tc_flower.sh to validate generic matching on ERSPAN options. Both ERSPAN Type II and Type III are covered. Also add check_tc_erspan_support() to verify whether tc supports erspan_opts. Signed-off-by: Li Shuang <shuali(a)redhat.com> --- tools/testing/selftests/net/forwarding/lib.sh | 14 +++++ .../selftests/net/forwarding/tc_flower.sh | 52 ++++++++++++++++++- 2 files changed, 65 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9308b2f77fed..890b3374dacd 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -142,6 +142,20 @@ check_tc_version() fi } +check_tc_erspan_support() +{ + local dev=$1; shift + + tc filter add dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing erspan support" + return $ksft_skip + fi + tc filter del dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null +} + # Old versions of tc don't understand "mpls_uc" check_tc_mpls_support() { diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index b1daad19b01e..b58909a93112 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ match_ip_tos_test match_indev_test match_ip_ttl_test match_mpls_label_test \ match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \ - match_mpls_lse_test" + match_mpls_lse_test match_erspan_opts_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -676,6 +676,56 @@ match_mpls_lse_test() log_test "mpls lse match ($tcflags)" } +match_erspan_opts_test() +{ + RET=0 + + check_tc_erspan_support $h2 || return 0 + + # h1 erspan setup + tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \ + tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II + tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \ + tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \ + # ERSPAN Type III + ip link set dev erspan1 master v$h1 + ip link set dev erspan2 master v$h1 + # h2 erspan setup + ip link add ep-ex type erspan ttl 64 external # To collect tunnel info + ip link set ep-ex up + ip link set dev ep-ex master v$h2 + tc qdisc add dev ep-ex clsact + + # ERSPAN Type II [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 101 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1001 erspan_opts 1:6789:0:0 \ + action drop + # ERSPAN Type III [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 102 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1002 erspan_opts 2:0:1:63 action drop + + ep1mac=$(mac_get erspan1) + $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 101 1 + check_err $? "ERSPAN Type II" + + ep2mac=$(mac_get erspan2) + $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 102 1 + check_err $? "ERSPAN Type III" + + # h2 erspan cleanup + tc qdisc del dev ep-ex clsact + tunnel_destroy ep-ex + # h1 erspan cleanup + tunnel_destroy erspan2 # ERSPAN Type III + tunnel_destroy erspan1 # ERSPAN Type II + + log_test "erspan_opts match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} -- 2.50.1

1 month

3
2
0 0

[PATCH net v2 0/2] selftests: mptcp: connect: cover alt modes

by Matthieu Baerts (NGI0)

mptcp_connect.sh can be executed manually with "-m <MODE>" and "-C" to make sure everything works as expected when using "mmap" and "sendfile" modes instead of "poll", and with the MPTCP checksum support. These modes should be validated, but they are not when the selftests are executed via the kselftest helpers. It means that most CIs validating these selftests, like NIPA for the net development trees and LKFT for the stable ones, are not covering these modes. To fix that, new test programs have been added, simply calling mptcp_connect.sh with the right parameters. The first patch can be backported up to v5.6, and the second one up to v5.14. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Changes in v2: - force using a different prefix in the subtests to avoid having the same test names in all mptcp_connect*.sh selftests. - Link to v1: https://lore.kernel.org/r/20250714-net-mptcp-sft-connect-alt-v1-0-bf1c5abbe… --- Matthieu Baerts (NGI0) (2): selftests: mptcp: connect: also cover alt modes selftests: mptcp: connect: also cover checksum tools/testing/selftests/net/mptcp/Makefile | 3 ++- tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh | 5 +++++ tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh | 5 +++++ tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh | 5 +++++ 4 files changed, 17 insertions(+), 1 deletion(-) --- base-commit: b640daa2822a39ff76e70200cb2b7b892b896dce change-id: 20250714-net-mptcp-sft-connect-alt-c1aaf073ef4e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 month

4
12
0 0

Re: [PATCH v3 5/7] perf test: Introduce storing logs for shell tests

by Ian Rogers

On Mon, Jul 21, 2025 at 6:27 AM Jakub Brnak <jbrnak(a)redhat.com> wrote: > > From: Veronika Molnarova <vmolnaro(a)redhat.com> > > Create temporary directories for storing log files for shell tests > that could help while debugging. The log files are necessary for > perftool testsuite test cases also. If the variable KEEP_TEST_LOGS > is set keep the logs, else delete them. Is there perhaps a kunit equivalent of log files so we could keep the implementations as similar as possible? Thanks, Ian > Signed-off-by: Michael Petlan <mpetlan(a)redhat.com> > Signed-off-by: Veronika Molnarova <vmolnaro(a)redhat.com> > Signed-off-by: Jakub Brnak <jbrnak(a)redhat.com> > --- > tools/perf/tests/builtin-test.c | 90 ++++++++++++++++++++++++++++++++ > tools/perf/tests/tests-scripts.c | 3 ++ > tools/perf/tests/tests-scripts.h | 1 + > 3 files changed, 94 insertions(+) > > diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c > index 4e3d2f779b01..89b180798224 100644 > --- a/tools/perf/tests/builtin-test.c > +++ b/tools/perf/tests/builtin-test.c > @@ -6,6 +6,7 @@ > */ > #include <ctype.h> > #include <fcntl.h> > +#include <ftw.h> > #include <errno.h> > #ifdef HAVE_BACKTRACE_SUPPORT > #include <execinfo.h> > @@ -282,6 +283,86 @@ static bool test_exclusive(const struct test_suite *t, int test_case) > return t->test_cases[test_case].exclusive; > } > > +static int delete_file(const char *fpath, const struct stat *sb __maybe_unused, > + int typeflag, struct FTW *ftwbuf) > +{ > + int rv = -1; > + > + /* Stop traversal if going too deep */ > + if (ftwbuf->level > 5) { > + pr_err("Tree traversal reached level %d, stopping.", ftwbuf->level); > + return rv; > + } > + > + /* Remove only expected directories */ > + if (typeflag == FTW_D || typeflag == FTW_DP){ > + const char *dirname = fpath + ftwbuf->base; > + > + if (strcmp(dirname, "logs") && strcmp(dirname, "examples") && > + strcmp(dirname, "header_tar") && strncmp(dirname, "perf_", 5)) { > + pr_err("Unknown directory %s", dirname); > + return rv; > + } > + } > + > + /* Attempt to remove the file */ > + rv = remove(fpath); > + if (rv) > + pr_err("Failed to remove file: %s", fpath); > + > + return rv; > +} > + > +static bool create_logs(struct test_suite *t, int pass){ > + bool store_logs = t->priv && ((struct shell_info*)(t->priv))->store_logs; > + if (pass == 1 && (!test_exclusive(t, 0) || sequential || dont_fork)) { > + /* Sequential and non-exclusive tests run on the first pass. */ > + return store_logs; > + } > + else if (pass != 1 && test_exclusive(t, 0) && !sequential && !dont_fork) { > + /* Exclusive tests without sequential run on the second pass. */ > + return store_logs; > + } > + return false; > +} > + > +static char *setup_shell_logs(const char *name) > +{ > + char template[PATH_MAX]; > + char *temp_dir; > + > + if (snprintf(template, PATH_MAX, "/tmp/perf_test_%s.XXXXXX", name) < 0) { > + pr_err("Failed to create log dir template"); > + return NULL; /* Skip the testsuite */ > + } > + > + temp_dir = mkdtemp(template); > + if (temp_dir) { > + setenv("PERFSUITE_RUN_DIR", temp_dir, 1); > + return strdup(temp_dir); > + } > + else { > + pr_err("Failed to create the temporary directory"); > + } > + > + return NULL; /* Skip the testsuite */ > +} > + > +static void cleanup_shell_logs(char *dirname) > +{ > + char *keep_logs = getenv("PERFTEST_KEEP_LOGS"); > + > + /* Check if logs should be kept or do cleanup */ > + if (dirname) { > + if (!keep_logs || strcmp(keep_logs, "y") != 0) { > + nftw(dirname, delete_file, 8, FTW_DEPTH | FTW_PHYS); > + } > + free(dirname); > + } > + > + unsetenv("PERFSUITE_RUN_DIR"); > +} > + > static bool perf_test__matches(const char *desc, int suite_num, int argc, const char *argv[]) > { > int i; > @@ -626,6 +707,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], > for (struct test_suite **t = suites; *t; t++, curr_suite++) { > int curr_test_case; > bool suite_matched = false; > + char *tmpdir = NULL; > > if (!perf_test__matches(test_description(*t, -1), curr_suite, argc, argv)) { > /* > @@ -655,6 +737,13 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], > } > > for (unsigned int run = 0; run < runs_per_test; run++) { > + /* Setup temporary log directories for shell test suites */ > + if (create_logs(*t, pass)) { > + tmpdir = setup_shell_logs((*t)->desc); > + > + if (tmpdir == NULL) /* Couldn't create log dir, skip test suite */ > + ((struct shell_info*)((*t)->priv))->has_setup = FAILED_SETUP; > + } > test_suite__for_each_test_case(*t, curr_test_case) { > if (!suite_matched && > !perf_test__matches(test_description(*t, curr_test_case), > @@ -667,6 +756,7 @@ static int __cmd_test(struct test_suite **suites, int argc, const char *argv[], > goto err_out; > } > } > + cleanup_shell_logs(tmpdir); > } > if (!sequential) { > /* Parallel mode starts tests but doesn't finish them. Do that now. */ > diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c > index d680a878800f..d4e382898a30 100644 > --- a/tools/perf/tests/tests-scripts.c > +++ b/tools/perf/tests/tests-scripts.c > @@ -251,6 +251,7 @@ static struct test_suite* prepare_test_suite(int dir_fd) > > test_info->base_path = strdup_check(dirpath); /* Absolute path to dir */ > test_info->has_setup = NO_SETUP; > + test_info->store_logs = false; > > test_suite->priv = test_info; > test_suite->desc = NULL; > @@ -427,6 +428,8 @@ static void append_suits_in_dir(int dir_fd, > continue; > } > > + /* Store logs for testsuite is sub-directories */ > + ((struct shell_info*)(test_suite->priv))->store_logs = true; > if (is_test_script(fd, SHELL_SETUP)) { /* Check for setup existance */ > char *desc = shell_test__description(fd, SHELL_SETUP); > test_suite->desc = desc; /* Set the suite name by the setup description */ > diff --git a/tools/perf/tests/tests-scripts.h b/tools/perf/tests/tests-scripts.h > index da4dcd26140c..41da0a175e4e 100644 > --- a/tools/perf/tests/tests-scripts.h > +++ b/tools/perf/tests/tests-scripts.h > @@ -16,6 +16,7 @@ enum shell_setup { > struct shell_info { > const char *base_path; > enum shell_setup has_setup; > + bool store_logs; > }; > > struct test_suite **create_script_test_suites(void); > -- > 2.50.1 >

1 month

1
0
0 0

[PATCH v4 0/6] binder: Set up KUnit tests for alloc

by Tiffany Yang

Hello, binder_alloc_selftest provides a robust set of checks for the binder allocator, but it rarely runs because it must hook into a running binder process and block all other binder threads until it completes. The test itself is a good candidate for conversion to KUnit, and it can be further isolated from user processes by using a test-specific lru freelist instead of the global one. This series converts the selftest to KUnit to make it less burdensome to run and to set up a foundation for unit testing future binder_alloc changes. Thanks, Tiffany Tiffany Yang (6): binder: Fix selftest page indexing binder: Store lru freelist in binder_alloc kunit: test: Export kunit_attach_mm() binder: Scaffolding for binder_alloc KUnit tests binder: Convert binder_alloc selftests to KUnit binder: encapsulate individual alloc test cases drivers/android/Kconfig | 15 +- drivers/android/Makefile | 2 +- drivers/android/binder.c | 10 +- drivers/android/binder_alloc.c | 39 +- drivers/android/binder_alloc.h | 14 +- drivers/android/binder_alloc_selftest.c | 306 ----------- drivers/android/binder_internal.h | 4 + drivers/android/tests/.kunitconfig | 7 + drivers/android/tests/Makefile | 6 + drivers/android/tests/binder_alloc_kunit.c | 572 +++++++++++++++++++++ include/kunit/test.h | 12 + lib/kunit/user_alloc.c | 4 +- 12 files changed, 651 insertions(+), 340 deletions(-) delete mode 100644 drivers/android/binder_alloc_selftest.c create mode 100644 drivers/android/tests/.kunitconfig create mode 100644 drivers/android/tests/Makefile create mode 100644 drivers/android/tests/binder_alloc_kunit.c -- 2.50.0.727.gbf7dc18ff4-goog

1 month

4
13
0 0

[PATCH] selftests/bpf: Add LPM trie microbenchmarks

by Matt Fleming

From: Matt Fleming <mfleming(a)cloudflare.com> Add benchmarks for the standard set of operations: lookup, update, delete. Also, include a benchmark for trie_free() which is known to have terrible performance for maps with many entries. Benchmarks operate on tries without gaps in the key range, i.e. each test begins with a trie with valid keys in the range [0, nr_entries). This is intended to cause maximum branching when traversing the trie. All measurements are recorded inside the kernel to remove syscall overhead. Most benchmarks run an XDP program to generate stats but free needs to collect latencies using fentry/fexit on map_free_deferred() because it's not possible to use fentry directly on lpm_trie.c since commit c83508da5620 ("bpf: Avoid deadlock caused by nested kprobe and fentry bpf programs") and there's no way to create/destroy a map from within an XDP program. Here is example output from an AMD EPYC 9684X 96-Core machine for each of the benchmarks using a trie with 10K entries and a 32-bit prefix length, e.g. $ ./bench lpm-trie-$op \ --prefix_len=32 \ --producers=1 \ --nr_entries=10000 lookup: throughput 7.423 ± 0.023 M ops/s ( 7.423M ops/prod), latency 134.710 ns/op update: throughput 2.643 ± 0.015 M ops/s ( 2.643M ops/prod), latency 378.310 ns/op delete: throughput 0.712 ± 0.008 M ops/s ( 0.712M ops/prod), latency 1405.152 ns/op free: throughput 0.574 ± 0.003 K ops/s ( 0.574K ops/prod), latency 1.743 ms/op Signed-off-by: Matt Fleming <mfleming(a)cloudflare.com> --- tools/testing/selftests/bpf/Makefile | 2 + tools/testing/selftests/bpf/bench.c | 10 + tools/testing/selftests/bpf/bench.h | 1 + .../selftests/bpf/benchs/bench_lpm_trie_map.c | 345 ++++++++++++++++++ .../selftests/bpf/progs/lpm_trie_bench.c | 175 +++++++++ .../selftests/bpf/progs/lpm_trie_map.c | 19 + 6 files changed, 552 insertions(+) create mode 100644 tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_bench.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_map.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 910d8d6402ef..10a5f1d0fa41 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -815,6 +815,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h +$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -836,6 +837,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_htab_mem.o \ $(OUTPUT)/bench_bpf_crypto.o \ $(OUTPUT)/bench_sockmap.o \ + $(OUTPUT)/bench_lpm_trie_map.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index ddd73d06a1eb..fd15f60fd5a8 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp; extern struct argp bench_trigger_batch_argp; extern struct argp bench_crypto_argp; extern struct argp bench_sockmap_argp; +extern struct argp bench_lpm_trie_map_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = { { &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 }, { &bench_crypto_argp, 0, "bpf crypto benchmark", 0 }, { &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 }, + { &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 }, {}, }; @@ -558,6 +560,10 @@ extern const struct bench bench_htab_mem; extern const struct bench bench_crypto_encrypt; extern const struct bench bench_crypto_decrypt; extern const struct bench bench_sockmap; +extern const struct bench bench_lpm_trie_lookup; +extern const struct bench bench_lpm_trie_update; +extern const struct bench bench_lpm_trie_delete; +extern const struct bench bench_lpm_trie_free; static const struct bench *benchs[] = { &bench_count_global, @@ -625,6 +631,10 @@ static const struct bench *benchs[] = { &bench_crypto_encrypt, &bench_crypto_decrypt, &bench_sockmap, + &bench_lpm_trie_lookup, + &bench_lpm_trie_update, + &bench_lpm_trie_delete, + &bench_lpm_trie_free, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 005c401b3e22..bea323820ffb 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -46,6 +46,7 @@ struct bench_res { unsigned long gp_ns; unsigned long gp_ct; unsigned int stime; + unsigned long duration_ns; }; struct bench { diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c new file mode 100644 index 000000000000..ddd7d3669e70 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +/* + * All of these benchmarks operate on tries with keys in the range + * [0, args.nr_entries), i.e. there are no gaps or partially filled + * branches of the trie for any key < args.nr_entries. + * + * This gives an idea of worst-case behaviour. + */ + +#include <argp.h> +#include <linux/time64.h> +#include <linux/if_ether.h> +#include "lpm_trie_bench.skel.h" +#include "lpm_trie_map.skel.h" +#include "bench.h" +#include "testing_helpers.h" + +static struct ctx { + struct lpm_trie_bench *bench; +} ctx; + +static struct { + __u32 nr_entries; + __u32 prefixlen; +} args = { + .nr_entries = 10000, + .prefixlen = 32, +}; + +enum { + ARG_NR_ENTRIES = 9000, + ARG_PREFIX_LEN, +}; + +static const struct argp_option opts[] = { + { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0, + "Number of unique entries in the LPM trie" }, + { "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0, + "Number of prefix bits to use in the LPM trie" }, + {}, +}; + +static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state) +{ + long ret; + + switch (key) { + case ARG_NR_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid nr_entries count."); + argp_usage(state); + } + args.nr_entries = ret; + break; + case ARG_PREFIX_LEN: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid prefix_len value."); + argp_usage(state); + } + args.prefixlen = ret; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +const struct argp bench_lpm_trie_map_argp = { + .options = opts, + .parser = lpm_parse_arg, +}; + +static void __lpm_validate(void) +{ + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); + exit(1); + } + + if ((1UL << args.prefixlen) < args.nr_entries) { + fprintf(stderr, "prefix_len value too small for nr_entries!\n"); + exit(1); + }; +} + +enum { OP_LOOKUP = 1, OP_UPDATE, OP_DELETE, OP_FREE }; + +static void lpm_delete_validate(void) +{ + __lpm_validate(); + + if (env.producer_cnt != 1) { + fprintf(stderr, + "lpm-trie-delete requires a single producer!\n"); + exit(1); + } +} + +static void lpm_free_validate(void) +{ + __lpm_validate(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-free requires a single producer!\n"); + exit(1); + } +} + +static void fill_map(int map_fd) +{ + int i, err; + + for (i = 0; i < args.nr_entries; i++) { + struct trie_key { + __u32 prefixlen; + __u32 data; + } key = { args.prefixlen, i }; + __u32 val = 1; + + err = bpf_map_update_elem(map_fd, &key, &val, BPF_NOEXIST); + if (err) { + fprintf(stderr, "failed to add key %d to map: %d\n", + key.data, -err); + exit(1); + } + } +} + +static void __lpm_setup(void) +{ + ctx.bench = lpm_trie_bench__open_and_load(); + if (!ctx.bench) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + ctx.bench->bss->nr_entries = args.nr_entries; + ctx.bench->bss->prefixlen = args.prefixlen; + + if (lpm_trie_bench__attach(ctx.bench)) { + fprintf(stderr, "failed to attach skeleton\n"); + exit(1); + } +} + +static void lpm_setup(void) +{ + int fd; + + __lpm_setup(); + + fd = bpf_map__fd(ctx.bench->maps.trie_map); + fill_map(fd); +} + +static void lpm_lookup_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_LOOKUP; +} + +static void lpm_update_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_UPDATE; +} + +static void lpm_delete_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_DELETE; +} + +static void lpm_free_setup(void) +{ + __lpm_setup(); + ctx.bench->bss->op = OP_FREE; +} + +static void lpm_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.bench->bss->hits, 0); + res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0); +} + +/* For LOOKUP, UPDATE, and DELETE */ +static void *lpm_producer(void *unused __always_unused) +{ + int err; + char in[ETH_HLEN]; /* unused */ + + LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in, + .data_size_in = sizeof(in), .repeat = 1, ); + + while (true) { + int fd = bpf_program__fd(ctx.bench->progs.run_bench); + err = bpf_prog_test_run_opts(fd, &opts); + if (err) { + fprintf(stderr, "failed to run BPF prog: %d\n", err); + exit(1); + } + + if (opts.retval < 0) { + fprintf(stderr, "BPF prog returned error: %d\n", + opts.retval); + exit(1); + } + + if (ctx.bench->bss->op == OP_DELETE && opts.retval == 1) { + /* trie_map needs to be refilled */ + fill_map(bpf_map__fd(ctx.bench->maps.trie_map)); + } + } + + return NULL; +} + +static void *lpm_free_producer(void *unused __always_unused) +{ + while (true) { + struct lpm_trie_map *skel; + + skel = lpm_trie_map__open_and_load(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + fill_map(bpf_map__fd(skel->maps.trie_free_map)); + lpm_trie_map__destroy(skel); + } + + return NULL; +} + +static __always_inline double duration_ms(struct bench_res *res) +{ + if (!res->hits) + return 0.0; + + return res->duration_ns / res->hits / NSEC_PER_MSEC; +} + +static void free_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double hits_per_sec, hits_per_prod; + double rate_divisor = 1000.0; + char rate = 'K'; + + hits_per_sec = res->hits / (res->duration_ns / (double)NSEC_PER_SEC) / + rate_divisor; + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, + (delta_ns - NSEC_PER_SEC) / 1000.0); + printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate, + hits_per_prod, rate); +} + +static void free_ops_report_final(struct bench_res res[], int res_cnt) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + double lat_divisor = 1000000.0; + double rate_divisor = 1000.0; + const char *unit = "ms"; + double latency = 0.0; + char rate = 'K'; + int i; + + for (i = 0; i < res_cnt; i++) { + double val = res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_mean += val / (0.0 + res_cnt); + latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt); + } + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + double val = + res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_stddev += (hits_mean - val) * (hits_mean - val) / + (res_cnt - 1.0); + } + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ", + hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt, + rate); + printf("latency %8.3lf %s/op\n", + latency / lat_divisor / env.producer_cnt, unit); +} + +const struct bench bench_lpm_trie_lookup = { + .name = "lpm-trie-lookup", + .argp = &bench_lpm_trie_map_argp, + .validate = __lpm_validate, + .setup = lpm_lookup_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_update = { + .name = "lpm-trie-update", + .argp = &bench_lpm_trie_map_argp, + .validate = __lpm_validate, + .setup = lpm_update_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_delete = { + .name = "lpm-trie-delete", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_delete_validate, + .setup = lpm_delete_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_free = { + .name = "lpm-trie-free", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_free_validate, + .setup = lpm_free_setup, + .producer_thread = lpm_free_producer, + .measure = lpm_measure, + .report_progress = free_ops_report_progress, + .report_final = free_ops_report_final, +}; diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c new file mode 100644 index 000000000000..c335718cc240 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +#define BPF_OBJ_NAME_LEN 16U +#define MAX_ENTRIES 100000000 +#define NR_LOOPS 10000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 512); + __type(key, struct bpf_map *); + __type(value, __u64); +} latency_free_start SEC(".maps"); + +/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */ +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_map SEC(".maps"); + +long hits; +long duration_ns; + +/* Configured from userspace */ +__u64 nr_entries; +__u32 prefixlen; +__u8 op; + +static __always_inline void atomic_inc(long *cnt) +{ + __atomic_add_fetch(cnt, 1, __ATOMIC_SEQ_CST); +} + +static __always_inline long atomic_swap(long *cnt, long val) +{ + return __atomic_exchange_n(cnt, val, __ATOMIC_SEQ_CST); +} + +SEC("fentry/bpf_map_free_deferred") +int BPF_PROG(trie_free_entry, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + const char *name; + u32 map_type; + __u64 val; + + map_type = BPF_CORE_READ(map, map_type); + if (map_type != BPF_MAP_TYPE_LPM_TRIE) + return 0; + + /* + * Ideally we'd have access to the map ID but that's already + * freed before we enter trie_free(). + */ + name = BPF_CORE_READ(map, name); + if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map")) + return 0; + + val = bpf_ktime_get_ns(); + bpf_map_update_elem(&latency_free_start, &map, &val, BPF_ANY); + + return 0; +} + +SEC("fexit/bpf_map_free_deferred") +int BPF_PROG(trie_free_exit, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + __u64 *val; + + val = bpf_map_lookup_elem(&latency_free_start, &map); + if (val) { + __sync_add_and_fetch(&duration_ns, bpf_ktime_get_ns() - *val); + atomic_inc(&hits); + bpf_map_delete_elem(&latency_free_start, &map); + } + + return 0; +} + +static void gen_random_key(struct trie_key *key) +{ + key->prefixlen = prefixlen; + key->data = bpf_get_prandom_u32() % nr_entries; +} + +static int lookup(__u32 index, __u32 *unused) +{ + struct trie_key key; + + gen_random_key(&key); + bpf_map_lookup_elem(&trie_map, &key); + return 0; +} + +static int update(__u32 index, __u32 *unused) +{ + struct trie_key key; + u32 val = bpf_get_prandom_u32(); + + gen_random_key(&key); + bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST); + return 0; +} + +long deleted_entries; +long refill; + +static int delete (__u32 index, __u32 *unused) +{ + struct trie_key key = { + .data = deleted_entries, + .prefixlen = prefixlen, + }; + + bpf_map_delete_elem(&trie_map, &key); + atomic_inc(&deleted_entries); + + /* Do we need to refill the map? */ + if (deleted_entries >= nr_entries) { + atomic_swap(&refill, 1); + atomic_swap(&deleted_entries, 0); + return 1; + } + + return 0; +} + +SEC("xdp") +int BPF_PROG(run_bench) +{ + u64 start, delta; + bool need_refill = false; + + start = bpf_ktime_get_ns(); + + switch (op) { + case 1: + bpf_loop(NR_LOOPS, lookup, NULL, 0); + break; + case 2: + bpf_loop(NR_LOOPS, update, NULL, 0); + break; + case 3: + bpf_loop(NR_LOOPS, delete, NULL, 0); + need_refill = atomic_swap(&refill, 0); + break; + default: + bpf_printk("invalid benchmark operation\n"); + return -1; + } + + delta = bpf_ktime_get_ns() - start; + + __sync_add_and_fetch(&hits, NR_LOOPS); + __sync_add_and_fetch(&duration_ns, delta); + + return need_refill; +} diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c new file mode 100644 index 000000000000..2ab43e2cd6c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_ENTRIES 100000000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_free_map SEC(".maps"); -- 2.34.1

1 month

3
4
0 0

[PATCH bpf-next v2] selftests/bpf: Add LPM trie microbenchmarks

by Matt Fleming

From: Matt Fleming <mfleming(a)cloudflare.com> Add benchmarks for the standard set of operations: lookup, update, delete. Also, include a benchmark for trie_free() which is known to have terrible performance for maps with many entries. Benchmarks operate on tries without gaps in the key range, i.e. each test begins with a trie with valid keys in the range [0, nr_entries). This is intended to cause maximum branching when traversing the trie. All measurements are recorded inside the kernel to remove syscall overhead. Most benchmarks run an XDP program to generate stats but free needs to collect latencies using fentry/fexit on map_free_deferred() because it's not possible to use fentry directly on lpm_trie.c since commit c83508da5620 ("bpf: Avoid deadlock caused by nested kprobe and fentry bpf programs") and there's no way to create/destroy a map from within an XDP program. Here is example output from an AMD EPYC 9684X 96-Core machine for each of the benchmarks using a trie with 10K entries and a 32-bit prefix length, e.g. $ ./bench lpm-trie-$op \ --prefix_len=32 \ --producers=1 \ --nr_entries=10000 lookup: throughput 7.423 ± 0.023 M ops/s ( 7.423M ops/prod), latency 134.710 ns/op update: throughput 2.643 ± 0.015 M ops/s ( 2.643M ops/prod), latency 378.310 ns/op delete: throughput 0.712 ± 0.008 M ops/s ( 0.712M ops/prod), latency 1405.152 ns/op free: throughput 0.574 ± 0.003 K ops/s ( 0.574K ops/prod), latency 1.743 ms/op Tested-by: Jesper Dangaard Brouer <hawk(a)kernel.org> Reviewed-by: Jesper Dangaard Brouer <hawk(a)kernel.org> Signed-off-by: Matt Fleming <mfleming(a)cloudflare.com> --- Changes in v2: - Add Jesper's Tested-by and Revewied-by tags - Remove use of atomic_*() in favour of __sync_add_and_fetch() - Use a file-local 'deleted_entries' in the DELETE op benchmark and add a comment explaining why non-atomic accesses are safe. - Bump 'hits' with the number of bpf_loop() loops actually executed tools/testing/selftests/bpf/Makefile | 2 + tools/testing/selftests/bpf/bench.c | 10 + tools/testing/selftests/bpf/bench.h | 1 + .../selftests/bpf/benchs/bench_lpm_trie_map.c | 337 ++++++++++++++++++ .../selftests/bpf/progs/lpm_trie_bench.c | 171 +++++++++ .../selftests/bpf/progs/lpm_trie_map.c | 19 + 6 files changed, 540 insertions(+) create mode 100644 tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_bench.c create mode 100644 tools/testing/selftests/bpf/progs/lpm_trie_map.c diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 910d8d6402ef..10a5f1d0fa41 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -815,6 +815,7 @@ $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h $(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h $(OUTPUT)/bench_bpf_crypto.o: $(OUTPUT)/crypto_bench.skel.h $(OUTPUT)/bench_sockmap.o: $(OUTPUT)/bench_sockmap_prog.skel.h +$(OUTPUT)/bench_lpm_trie_map.o: $(OUTPUT)/lpm_trie_bench.skel.h $(OUTPUT)/lpm_trie_map.skel.h $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o \ @@ -836,6 +837,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \ $(OUTPUT)/bench_htab_mem.o \ $(OUTPUT)/bench_bpf_crypto.o \ $(OUTPUT)/bench_sockmap.o \ + $(OUTPUT)/bench_lpm_trie_map.o \ # $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@ diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c index ddd73d06a1eb..fd15f60fd5a8 100644 --- a/tools/testing/selftests/bpf/bench.c +++ b/tools/testing/selftests/bpf/bench.c @@ -284,6 +284,7 @@ extern struct argp bench_htab_mem_argp; extern struct argp bench_trigger_batch_argp; extern struct argp bench_crypto_argp; extern struct argp bench_sockmap_argp; +extern struct argp bench_lpm_trie_map_argp; static const struct argp_child bench_parsers[] = { { &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 }, @@ -299,6 +300,7 @@ static const struct argp_child bench_parsers[] = { { &bench_trigger_batch_argp, 0, "BPF triggering benchmark", 0 }, { &bench_crypto_argp, 0, "bpf crypto benchmark", 0 }, { &bench_sockmap_argp, 0, "bpf sockmap benchmark", 0 }, + { &bench_lpm_trie_map_argp, 0, "LPM trie map benchmark", 0 }, {}, }; @@ -558,6 +560,10 @@ extern const struct bench bench_htab_mem; extern const struct bench bench_crypto_encrypt; extern const struct bench bench_crypto_decrypt; extern const struct bench bench_sockmap; +extern const struct bench bench_lpm_trie_lookup; +extern const struct bench bench_lpm_trie_update; +extern const struct bench bench_lpm_trie_delete; +extern const struct bench bench_lpm_trie_free; static const struct bench *benchs[] = { &bench_count_global, @@ -625,6 +631,10 @@ static const struct bench *benchs[] = { &bench_crypto_encrypt, &bench_crypto_decrypt, &bench_sockmap, + &bench_lpm_trie_lookup, + &bench_lpm_trie_update, + &bench_lpm_trie_delete, + &bench_lpm_trie_free, }; static void find_benchmark(void) diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h index 005c401b3e22..bea323820ffb 100644 --- a/tools/testing/selftests/bpf/bench.h +++ b/tools/testing/selftests/bpf/bench.h @@ -46,6 +46,7 @@ struct bench_res { unsigned long gp_ns; unsigned long gp_ct; unsigned int stime; + unsigned long duration_ns; }; struct bench { diff --git a/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c new file mode 100644 index 000000000000..435b5c7ceee9 --- /dev/null +++ b/tools/testing/selftests/bpf/benchs/bench_lpm_trie_map.c @@ -0,0 +1,337 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +/* + * All of these benchmarks operate on tries with keys in the range + * [0, args.nr_entries), i.e. there are no gaps or partially filled + * branches of the trie for any key < args.nr_entries. + * + * This gives an idea of worst-case behaviour. + */ + +#include <argp.h> +#include <linux/time64.h> +#include <linux/if_ether.h> +#include "lpm_trie_bench.skel.h" +#include "lpm_trie_map.skel.h" +#include "bench.h" +#include "testing_helpers.h" + +static struct ctx { + struct lpm_trie_bench *bench; +} ctx; + +static struct { + __u32 nr_entries; + __u32 prefixlen; +} args = { + .nr_entries = 10000, + .prefixlen = 32, +}; + +enum { + ARG_NR_ENTRIES = 9000, + ARG_PREFIX_LEN, +}; + +static const struct argp_option opts[] = { + { "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0, + "Number of unique entries in the LPM trie" }, + { "prefix_len", ARG_PREFIX_LEN, "PREFIX_LEN", 0, + "Number of prefix bits to use in the LPM trie" }, + {}, +}; + +static error_t lpm_parse_arg(int key, char *arg, struct argp_state *state) +{ + long ret; + + switch (key) { + case ARG_NR_ENTRIES: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid nr_entries count."); + argp_usage(state); + } + args.nr_entries = ret; + break; + case ARG_PREFIX_LEN: + ret = strtol(arg, NULL, 10); + if (ret < 1 || ret > UINT_MAX) { + fprintf(stderr, "Invalid prefix_len value."); + argp_usage(state); + } + args.prefixlen = ret; + break; + default: + return ARGP_ERR_UNKNOWN; + } + return 0; +} + +const struct argp bench_lpm_trie_map_argp = { + .options = opts, + .parser = lpm_parse_arg, +}; + +static void __lpm_validate(void) +{ + if (env.consumer_cnt != 0) { + fprintf(stderr, "benchmark doesn't support consumer!\n"); + exit(1); + } + + if ((1UL << args.prefixlen) < args.nr_entries) { + fprintf(stderr, "prefix_len value too small for nr_entries!\n"); + exit(1); + }; +} + +enum { OP_LOOKUP = 1, OP_UPDATE, OP_DELETE, OP_FREE }; + +static void lpm_delete_validate(void) +{ + __lpm_validate(); + + if (env.producer_cnt != 1) { + fprintf(stderr, + "lpm-trie-delete requires a single producer!\n"); + exit(1); + } +} + +static void lpm_free_validate(void) +{ + __lpm_validate(); + + if (env.producer_cnt != 1) { + fprintf(stderr, "lpm-trie-free requires a single producer!\n"); + exit(1); + } +} + +static void fill_map(int map_fd) +{ + int i, err; + + for (i = 0; i < args.nr_entries; i++) { + struct trie_key { + __u32 prefixlen; + __u32 data; + } key = { args.prefixlen, i }; + __u32 val = 1; + + err = bpf_map_update_elem(map_fd, &key, &val, BPF_NOEXIST); + if (err) { + fprintf(stderr, "failed to add key %d to map: %d\n", + key.data, -err); + exit(1); + } + } +} + +static void __lpm_setup(void) +{ + ctx.bench = lpm_trie_bench__open_and_load(); + if (!ctx.bench) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + ctx.bench->bss->nr_entries = args.nr_entries; + ctx.bench->bss->prefixlen = args.prefixlen; + + if (lpm_trie_bench__attach(ctx.bench)) { + fprintf(stderr, "failed to attach skeleton\n"); + exit(1); + } +} + +static void lpm_setup(void) +{ + int fd; + + __lpm_setup(); + + fd = bpf_map__fd(ctx.bench->maps.trie_map); + fill_map(fd); +} + +static void lpm_lookup_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_LOOKUP; +} + +static void lpm_update_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_UPDATE; +} + +static void lpm_delete_setup(void) +{ + lpm_setup(); + + ctx.bench->bss->op = OP_DELETE; +} + +static void lpm_free_setup(void) +{ + __lpm_setup(); + ctx.bench->bss->op = OP_FREE; +} + +static void lpm_measure(struct bench_res *res) +{ + res->hits = atomic_swap(&ctx.bench->bss->hits, 0); + res->duration_ns = atomic_swap(&ctx.bench->bss->duration_ns, 0); +} + +/* For LOOKUP, UPDATE, and DELETE */ +static void *lpm_producer(void *unused __always_unused) +{ + int err; + char in[ETH_HLEN]; /* unused */ + + LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = in, + .data_size_in = sizeof(in), .repeat = 1, ); + + while (true) { + int fd = bpf_program__fd(ctx.bench->progs.run_bench); + err = bpf_prog_test_run_opts(fd, &opts); + if (err) { + fprintf(stderr, "failed to run BPF prog: %d\n", err); + exit(1); + } + + if (opts.retval < 0) { + fprintf(stderr, "BPF prog returned error: %d\n", + opts.retval); + exit(1); + } + + if (ctx.bench->bss->op == OP_DELETE && opts.retval == 1) { + /* trie_map needs to be refilled */ + fill_map(bpf_map__fd(ctx.bench->maps.trie_map)); + } + } + + return NULL; +} + +static void *lpm_free_producer(void *unused __always_unused) +{ + while (true) { + struct lpm_trie_map *skel; + + skel = lpm_trie_map__open_and_load(); + if (!skel) { + fprintf(stderr, "failed to open skeleton\n"); + exit(1); + } + + fill_map(bpf_map__fd(skel->maps.trie_free_map)); + lpm_trie_map__destroy(skel); + } + + return NULL; +} + +static void free_ops_report_progress(int iter, struct bench_res *res, + long delta_ns) +{ + double hits_per_sec, hits_per_prod; + double rate_divisor = 1000.0; + char rate = 'K'; + + hits_per_sec = res->hits / (res->duration_ns / (double)NSEC_PER_SEC) / + rate_divisor; + hits_per_prod = hits_per_sec / env.producer_cnt; + + printf("Iter %3d (%7.3lfus): ", iter, + (delta_ns - NSEC_PER_SEC) / 1000.0); + printf("hits %8.3lf%c/s (%7.3lf%c/prod)\n", hits_per_sec, rate, + hits_per_prod, rate); +} + +static void free_ops_report_final(struct bench_res res[], int res_cnt) +{ + double hits_mean = 0.0, hits_stddev = 0.0; + double lat_divisor = 1000000.0; + double rate_divisor = 1000.0; + const char *unit = "ms"; + double latency = 0.0; + char rate = 'K'; + int i; + + for (i = 0; i < res_cnt; i++) { + double val = res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_mean += val / (0.0 + res_cnt); + latency += res[i].duration_ns / res[i].hits / (0.0 + res_cnt); + } + + if (res_cnt > 1) { + for (i = 0; i < res_cnt; i++) { + double val = + res[i].hits / rate_divisor / + (res[i].duration_ns / (double)NSEC_PER_SEC); + hits_stddev += (hits_mean - val) * (hits_mean - val) / + (res_cnt - 1.0); + } + + hits_stddev = sqrt(hits_stddev); + } + printf("Summary: throughput %8.3lf \u00B1 %5.3lf %c ops/s (%7.3lf%c ops/prod), ", + hits_mean, hits_stddev, rate, hits_mean / env.producer_cnt, + rate); + printf("latency %8.3lf %s/op\n", + latency / lat_divisor / env.producer_cnt, unit); +} + +const struct bench bench_lpm_trie_lookup = { + .name = "lpm-trie-lookup", + .argp = &bench_lpm_trie_map_argp, + .validate = __lpm_validate, + .setup = lpm_lookup_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_update = { + .name = "lpm-trie-update", + .argp = &bench_lpm_trie_map_argp, + .validate = __lpm_validate, + .setup = lpm_update_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_delete = { + .name = "lpm-trie-delete", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_delete_validate, + .setup = lpm_delete_setup, + .producer_thread = lpm_producer, + .measure = lpm_measure, + .report_progress = ops_report_progress, + .report_final = ops_report_final, +}; + +const struct bench bench_lpm_trie_free = { + .name = "lpm-trie-free", + .argp = &bench_lpm_trie_map_argp, + .validate = lpm_free_validate, + .setup = lpm_free_setup, + .producer_thread = lpm_free_producer, + .measure = lpm_measure, + .report_progress = free_ops_report_progress, + .report_final = free_ops_report_final, +}; diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_bench.c b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c new file mode 100644 index 000000000000..1a138e21e156 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_bench.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Cloudflare */ + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include "bpf_misc.h" + +#define BPF_OBJ_NAME_LEN 16U +#define MAX_ENTRIES 100000000 +#define NR_LOOPS 10000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 512); + __type(key, struct bpf_map *); + __type(value, __u64); +} latency_free_start SEC(".maps"); + +/* Filled by userspace. See fill_map() in bench_lpm_trie_map.c */ +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_map SEC(".maps"); + +long hits; +long duration_ns; + +/* Configured from userspace */ +__u32 nr_entries; +__u32 prefixlen; +__u8 op; + +SEC("fentry/bpf_map_free_deferred") +int BPF_PROG(trie_free_entry, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + const char *name; + u32 map_type; + __u64 val; + + map_type = BPF_CORE_READ(map, map_type); + if (map_type != BPF_MAP_TYPE_LPM_TRIE) + return 0; + + /* + * Ideally we'd have access to the map ID but that's already + * freed before we enter trie_free(). + */ + name = BPF_CORE_READ(map, name); + if (bpf_strncmp(name, BPF_OBJ_NAME_LEN, "trie_free_map")) + return 0; + + val = bpf_ktime_get_ns(); + bpf_map_update_elem(&latency_free_start, &map, &val, BPF_ANY); + + return 0; +} + +SEC("fexit/bpf_map_free_deferred") +int BPF_PROG(trie_free_exit, struct work_struct *work) +{ + struct bpf_map *map = container_of(work, struct bpf_map, work); + __u64 *val; + + val = bpf_map_lookup_elem(&latency_free_start, &map); + if (val) { + __sync_add_and_fetch(&duration_ns, bpf_ktime_get_ns() - *val); + __sync_add_and_fetch(&hits, 1); + bpf_map_delete_elem(&latency_free_start, &map); + } + + return 0; +} + +static void gen_random_key(struct trie_key *key) +{ + key->prefixlen = prefixlen; + key->data = bpf_get_prandom_u32() % nr_entries; +} + +static int lookup(__u32 index, __u32 *unused) +{ + struct trie_key key; + + gen_random_key(&key); + bpf_map_lookup_elem(&trie_map, &key); + return 0; +} + +static int update(__u32 index, __u32 *unused) +{ + struct trie_key key; + u32 val = bpf_get_prandom_u32(); + + gen_random_key(&key); + bpf_map_update_elem(&trie_map, &key, &val, BPF_EXIST); + return 0; +} + +static __u32 deleted_entries; + +static int delete (__u32 index, bool *need_refill) +{ + struct trie_key key = { + .data = deleted_entries, + .prefixlen = prefixlen, + }; + + bpf_map_delete_elem(&trie_map, &key); + + /* Do we need to refill the map? */ + if (++deleted_entries == nr_entries) { + /* + * Atomicity isn't required because DELETE only supports + * one producer running concurrently. What we need is a + * way to track how many entries have been deleted from + * the trie between consecutive invocations of the BPF + * prog because a single bpf_loop() call might not + * delete all entries, e.g. when NR_LOOPS < nr_entries. + */ + deleted_entries = 0; + *need_refill = true; + return 1; + } + + return 0; +} + +SEC("xdp") +int BPF_PROG(run_bench) +{ + bool need_refill = false; + u64 start, delta; + int loops; + + start = bpf_ktime_get_ns(); + + switch (op) { + case 1: + loops = bpf_loop(NR_LOOPS, lookup, NULL, 0); + break; + case 2: + loops = bpf_loop(NR_LOOPS, update, NULL, 0); + break; + case 3: + loops = bpf_loop(NR_LOOPS, delete, &need_refill, 0); + break; + default: + bpf_printk("invalid benchmark operation\n"); + return -1; + } + + delta = bpf_ktime_get_ns() - start; + + __sync_add_and_fetch(&duration_ns, delta); + __sync_add_and_fetch(&hits, loops); + + return need_refill; +} diff --git a/tools/testing/selftests/bpf/progs/lpm_trie_map.c b/tools/testing/selftests/bpf/progs/lpm_trie_map.c new file mode 100644 index 000000000000..2ab43e2cd6c6 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/lpm_trie_map.c @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#define MAX_ENTRIES 100000000 + +struct trie_key { + __u32 prefixlen; + __u32 data; +}; + +struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct trie_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, MAX_ENTRIES); +} trie_free_map SEC(".maps"); -- 2.34.1

1 month

1
0
0 0

[PATCH nf-next v4 0/2] Add IPIP flowtable SW acceleratio

by Lorenzo Bianconi

Introduce SW acceleration for IPIP tunnels in the netfilter flowtable infrastructure. --- Changes in v4: - Use the hash value of the saddr, daddr and protocol of outer IP header as encapsulation id. - Link to v3: https://lore.kernel.org/r/20250703-nf-flowtable-ipip-v3-0-880afd319b9f@kern… Changes in v3: - Add outer IP header sanity checks - target nf-next tree instead of net-next - Link to v2: https://lore.kernel.org/r/20250627-nf-flowtable-ipip-v2-0-c713003ce75b@kern… Changes in v2: - Introduce IPIP flowtable selftest - Link to v1: https://lore.kernel.org/r/20250623-nf-flowtable-ipip-v1-1-2853596e3941@kern… --- Lorenzo Bianconi (2): net: netfilter: Add IPIP flowtable SW acceleration selftests: netfilter: nft_flowtable.sh: Add IPIP flowtable selftest include/linux/netdevice.h | 1 + net/ipv4/ipip.c | 25 +++++++++++ net/netfilter/nf_flow_table_ip.c | 48 +++++++++++++++++++++- net/netfilter/nft_flow_offload.c | 1 + .../selftests/net/netfilter/nft_flowtable.sh | 40 ++++++++++++++++++ 5 files changed, 113 insertions(+), 2 deletions(-) --- base-commit: d61f6cb6f6ef3c70d2ccc0d9c85c508cb8017da9 change-id: 20250623-nf-flowtable-ipip-1b3d7b08d067 Best regards, -- Lorenzo Bianconi <lorenzo(a)kernel.org>

1 month

2
7
0 0

[PATCH v2 0/2] rust: minor idiomatic fixes to doctest generator

by Tamir Duberstein

Please see individual commit messages. Signed-off-by: Tamir Duberstein <tamird(a)gmail.com> --- Changes in v2: - rustfmt. - Alice's RB. - Add second patch to emit information in panic rather than separately to stderr. - Link to v1: https://lore.kernel.org/r/20250527-idiomatic-match-slice-v1-1-34b0b1d1d58c@… --- Tamir Duberstein (2): rust: replace length checks with match rust: emit path candidates in panic message scripts/rustdoc_test_gen.rs | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) --- base-commit: 1ce98bb2bb30713ec4374ef11ead0d7d3e856766 change-id: 20250527-idiomatic-match-slice-26a79d100e4d Best regards, -- Tamir Duberstein <tamird(a)gmail.com>

1 month

2
8
0 0

[PATCH v2 00/15] selftests/futex: Refactor tests to use kselftest_harness.h

by André Almeida

This patch series refactors all futex selftests to use kselftest_harness.h instead of futex's logging.h, as discussed here [1]. This allows to remove a lot of boilerplate code and to simplify some parts of the test logic, mainly when the test needs to exit early. The result of this is more than 500 lines removed from tools/testing/selftests/futex/. Also, this enables new tests to use kselftest.h features like ASSERT_s and such. There are some caveats around this refactor: - logging.h had verbosity levels, while kselftest_harness.h doesn't. I created a new print function called ksft_print_dbg_msg() that prints the message if the user uses the -d flag, so now there's an equivalent of this feature. - futex_requeue_pi test accepted command line arguments to be used as test parameters (e.g. ./futex_requeue_pi -b -l -t 500000). This doesn't work with kselftest_harness.h because there's no straightforward way to send command line arguments to the test. I used FIXTURE_VARIANT() to achieve the same result, but now the parameters live inside of the test file, instead of on functional/run.sh. This increased a little bit the number of test cases for futex_requeue_pi, from 22 to 24. - test_harness_run() calls mmap(MAP_SHARED) before running the test and this has caused a side effect on test futex_numa_mpol.c. This test also calls mmap() and then try to access an address out of boundaries of this mapped memory for a "Memory out of range" subtest, where the kernel should return -EACCESS. After the refactor, the test address might be fall inside the first memory mapped region, thus being a valid address and succeeding the syscall, making the test fail. To fix that, I created a small "buffer zone" with mmap(PROT_NONE) between both mmaps. I have compared the results of run.sh before and after this patchset and didn't find any regression from the test results. Thanks, André [1] https://lore.kernel.org/lkml/87ecv6p364.ffs@tglx/ --- Changes in v2: - Rebased on top of tip/master - Dropped priv_hash global test variant now that this feature was dropped - Added include <stdbool.h> in the first patch - Link to v1: https://lore.kernel.org/r/20250704-tonyk-robust_test_cleanup-v1-0-c0ff4f24c… --- André Almeida (15): selftests: kselftest: Create ksft_print_dbg_msg() selftests/futex: Refactor futex_requeue_pi with kselftest_harness.h selftests/futex: Refactor futex_requeue_pi_mismatched_ops with kselftest_harness.h selftests/futex: Refactor futex_requeue_pi_signal_restart with kselftest_harness.h selftests/futex: Refactor futex_wait_timeout with kselftest_harness.h selftests/futex: Refactor futex_wait_wouldblock with kselftest_harness.h selftests/futex: Refactor futex_wait_unitialized_heap with kselftest_harness.h selftests/futex: Refactor futex_wait_private_mapped_file with kselftest_harness.h selftests/futex: Refactor futex_wait with kselftest_harness.h selftests/futex: Refactor futex_requeue with kselftest_harness.h selftests/futex: Refactor futex_waitv with kselftest_harness.h selftests/futex: Refactor futex_priv_hash with kselftest_harness.h selftests/futex: Refactor futex_numa_mpol with kselftest_harness.h selftests/futex: Drop logging.h include from futex_numa selftests/futex: Remove logging.h file tools/testing/selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/futex_numa.c | 3 +- .../selftests/futex/functional/futex_numa_mpol.c | 57 ++--- .../selftests/futex/functional/futex_priv_hash.c | 49 +--- .../selftests/futex/functional/futex_requeue.c | 76 ++---- .../selftests/futex/functional/futex_requeue_pi.c | 261 ++++++++++----------- .../functional/futex_requeue_pi_mismatched_ops.c | 80 ++----- .../functional/futex_requeue_pi_signal_restart.c | 129 +++------- .../selftests/futex/functional/futex_wait.c | 103 +++----- .../functional/futex_wait_private_mapped_file.c | 83 ++----- .../futex/functional/futex_wait_timeout.c | 139 +++++------ .../functional/futex_wait_uninitialized_heap.c | 76 ++---- .../futex/functional/futex_wait_wouldblock.c | 75 ++---- .../selftests/futex/functional/futex_waitv.c | 98 ++++---- tools/testing/selftests/futex/functional/run.sh | 62 +---- tools/testing/selftests/futex/include/logging.h | 148 ------------ tools/testing/selftests/kselftest.h | 14 ++ tools/testing/selftests/kselftest_harness.h | 13 +- 18 files changed, 465 insertions(+), 1004 deletions(-) --- base-commit: ed0272f0675f31642c3d445a596b544de9db405b change-id: 20250703-tonyk-robust_test_cleanup-d1f3406365d9 Best regards, -- André Almeida <andrealmeid(a)igalia.com>

1 month

1
15
0 0

[PATCH v8 0/6] use per-vma locks for /proc/pid/maps reads

by Suren Baghdasaryan

Reading /proc/pid/maps requires read-locking mmap_lock which prevents any other task from concurrently modifying the address space. This guarantees coherent reporting of virtual address ranges, however it can block important updates from happening. Oftentimes /proc/pid/maps readers are low priority monitoring tasks and them blocking high priority tasks results in priority inversion. Locking the entire address space is required to present fully coherent picture of the address space, however even current implementation does not strictly guarantee that by outputting vmas in page-size chunks and dropping mmap_lock in between each chunk. Address space modifications are possible while mmap_lock is dropped and userspace reading the content is expected to deal with possible concurrent address space modifications. Considering these relaxed rules, holding mmap_lock is not strictly needed as long as we can guarantee that a concurrently modified vma is reported either in its original form or after it was modified. This patchset switches from holding mmap_lock while reading /proc/pid/maps to taking per-vma locks as we walk the vma tree. This reduces the contention with tasks modifying the address space because they would have to contend for the same vma as opposed to the entire address space. Previous version of this patchset [1] tried to perform /proc/pid/maps reading under RCU, however its implementation is quite complex and the results are worse than the new version because it still relied on mmap_lock speculation which retries if any part of the address space gets modified. New implementaion is both simpler and results in less contention. Note that similar approach would not work for /proc/pid/smaps reading as it also walks the page table and that's not RCU-safe. Paul McKenney's designed a test [2] to measure mmap/munmap latencies while concurrently reading /proc/pid/maps. The test has a pair of processes scanning /proc/PID/maps, and another process unmapping and remapping 4K pages from a 128MB range of anonymous memory. At the end of each 10 second run, the latency of each mmap() or munmap() operation is measured, and for each run the maximum and mean latency is printed. The map/unmap process is started first, its PID is passed to the scanners, and then the map/unmap process waits until both scanners are running before starting its timed test. The scanners keep scanning until the specified /proc/PID/maps file disappears. The latest results from Paul: Stock mm-unstable, all of the runs had maximum latencies in excess of 0.5 milliseconds, and with 80% of the runs' latencies exceeding a full millisecond, and ranging up beyond 4 full milliseconds. In contrast, 99% of the runs with this patch series applied had maximum latencies of less than 0.5 milliseconds, with the single outlier at only 0.608 milliseconds. From a median-performance (as opposed to maximum-latency) viewpoint, this patch series also looks good, with stock mm weighing in at 11 microseconds and patch series at 6 microseconds, better than a 2x improvement. Before the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.011 0.008 0.521 0.011 0.008 0.552 0.011 0.008 0.590 0.011 0.008 0.660 ... 0.011 0.015 2.987 0.011 0.015 3.038 0.011 0.016 3.431 0.011 0.016 4.707 After the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.006 0.005 0.026 0.006 0.005 0.029 0.006 0.005 0.034 0.006 0.005 0.035 ... 0.006 0.006 0.421 0.006 0.006 0.423 0.006 0.006 0.439 0.006 0.006 0.608 The patchset also adds a number of tests to check for /proc/pid/maps data coherency. They are designed to detect any unexpected data tearing while performing some common address space modifications (vma split, resize and remap). Even before these changes, reading /proc/pid/maps might have inconsistent data because the file is read page-by-page with mmap_lock being dropped between the pages. An example of user-visible inconsistency can be that the same vma is printed twice: once before it was modified and then after the modifications. For example if vma was extended, it might be found and reported twice. What is not expected is to see a gap where there should have been a vma both before and after modification. This patchset increases the chances of such tearing, therefore it's even more important now to test for unexpected inconsistencies. In [3] Lorenzo identified the following possible vma merging/splitting scenarios: Merges with changes to existing vmas: 1 Merge both - mapping a vma over another one and between two vmas which can be merged after this replacement; 2. Merge left full - mapping a vma at the end of an existing one and completely over its right neighbor; 3. Merge left partial - mapping a vma at the end of an existing one and partially over its right neighbor; 4. Merge right full - mapping a vma before the start of an existing one and completely over its left neighbor; 5. Merge right partial - mapping a vma before the start of an existing one and partially over its left neighbor; Merges without changes to existing vmas: 6. Merge both - mapping a vma into a gap between two vmas which can be merged after the insertion; 7. Merge left - mapping a vma at the end of an existing one; 8. Merge right - mapping a vma before the start end of an existing one; Splits 9. Split with new vma at the lower address; 10. Split with new vma at the higher address; If such merges or splits happen concurrently with the /proc/maps reading we might report a vma twice, once before the modification and once after it is modified: Case 1 might report overwritten and previous vma along with the final merged vma; Case 2 might report previous and the final merged vma; Case 3 might cause us to retry once we detect the temporary gap caused by shrinking of the right neighbor; Case 4 might report overritten and the final merged vma; Case 5 might cause us to retry once we detect the temporary gap caused by shrinking of the left neighbor; Case 6 might report previous vma and the gap along with the final marged vma; Case 7 might report previous and the final merged vma; Case 8 might report the original gap and the final merged vma covering the gap; Case 9 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma start; Case 10 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma end; In all these cases the retry mechanism prevents us from reporting possible temporary gaps. Changes since v7 [4]: - Refactored tests to use kselftest harness, per David Hildenbrand and Lorenzo Stoakes - Removed PROCMAP_QUERY selftest, per David Hildenbrand and Lorenzo Stoakes - Added Acked-by, per David Hildenbrand - Replaced sentinels values with named definitions, per Vlastimil Babka - Added Reviewed-by, per Vlastimil Babka !!! NOTES FOR APPLYING THE PATCHSET !!! Applies cleanly over mm-unstable after reverting v7 version of this patchset (from 94951ab6fe6f to e47914e6c28f in mm-unstable). [1] https://lore.kernel.org/all/20250418174959.1431962-1-surenb@google.com/ [2] https://github.com/paulmckrcu/proc-mmap_sem-test [3] https://lore.kernel.org/all/e1863f40-39ab-4e5b-984a-c48765ffde1c@lucifer.lo… [4] https://lore.kernel.org/all/20250716030557.1547501-1-surenb@google.com/ Suren Baghdasaryan (6): selftests/proc: add /proc/pid/maps tearing from vma split test selftests/proc: extend /proc/pid/maps tearing test to include vma resizing selftests/proc: extend /proc/pid/maps tearing test to include vma remapping selftests/proc: add verbose mode for /proc/pid/maps tearing tests fs/proc/task_mmu: remove conversion of seq_file position to unsigned fs/proc/task_mmu: read proc/pid/maps under per-vma lock fs/proc/internal.h | 5 + fs/proc/task_mmu.c | 158 +++- include/linux/mmap_lock.h | 11 + mm/madvise.c | 3 +- mm/mmap_lock.c | 93 +++ tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/proc-maps-race.c | 741 ++++++++++++++++++ 8 files changed, 997 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/proc/proc-maps-race.c -- 2.50.0.727.gbf7dc18ff4-goog

1 month

2
7
0 0

Start Campaign Outreach with Fresh Data from GSX 2025

by Ben Graham

Hi , Interested in getting the GSX 2025 attendee list? Expo Name: Global Security Exchange (GSX) 2025 Total Number of records: 17,000 records List includes: Company Name, Contact Name, Job Title, Mailing Address, Phone, Emails, etc. Are you considering buying these leads? If yes, I can send you the pricing information. Awaiting your message Regards Ben Graham Demand Generation Manager US Marketing Data Inc., Please reply with REMOVE if you don't wish to receive further emails

1 month

1
0
0 0

[PATCH 0/7] Replace "__auto_type" with "auto"

by H. Peter Anvin

"auto" was defined as a keyword back in the K&R days, but as a storage type specifier. No one ever used it, since it was and is the default storage type for local variables. C++11 recycled the keyword to allow a type to be declared based on the type of an initializer. This was finally adopted into standard C in C23. gcc and clang provide the "__auto_type" alias keyword as an extension for pre-C23, however, there is no reason to pollute the bulk of the source base with this temporary keyword; instead define "auto" as a macro unless the compiler is running in C23+ mode. This macro is added in <linux/compiler_types.h> because that header is included in some of the tools headers, wheres <linux/compiler.h> is not as it has a bunch of very kernel-specific things in it. --- arch/nios2/include/asm/uaccess.h | 4 ++-- arch/x86/include/asm/bug.h | 2 +- arch/x86/include/asm/string_64.h | 6 +++--- arch/x86/include/asm/uaccess_64.h | 2 +- fs/proc/inode.c | 16 ++++++++-------- include/linux/cleanup.h | 4 ++-- include/linux/compiler.h | 2 +- include/linux/compiler_types.h | 13 +++++++++++++ include/linux/minmax.h | 6 +++--- tools/testing/selftests/bpf/prog_tests/socket_helpers.h | 9 +++++++-- tools/virtio/linux/compiler.h | 2 +- 11 files changed, 42 insertions(+), 24 deletions(-)

1 month

4
14
0 0

[PATCH RFC 0/3] selftests/landlock: scoping abstractions

by Abhinav Saxena

Hi all, I was starting to work on the memfd-exec[1] feature and observed that Landlock's scoped-IPC features (abstract UNIX sockets and signals) follow a consistent high-level model, which I'm calling a resource-accessor pattern: Resource Process <-> Accessor Process - Resource process: owns or manages the asset - socket creator (bind/accept) - signal handler - memfd creator - Accessor process: attempts to use the asset - socket client (connect/sendto) - signal sender - memfd executor RESOURCE-ACCESSOR PATTERN FUNDAMENTALS ====================================== This pattern appears fundamental to Landlock scoping because: 1. Consistent enforcement model: Landlock restrictions are enforced only on the accessor side; the resource side remains unconstrained across all scope types. 2. Reflects actual security boundaries: In practice, sandboxed processes typically need to access resources created by other processes, not the reverse. 3. Scalable design: This model works consistently whether processes are in parent-child relationships or independent peer domains. 4. Real-world usage patterns: Container runtimes and sandbox orchestrators routinely start multiple workers that restrict themselves independently. CURRENT TEST COVERAGE GAP ========================= Existing self-tests cover hierarchical resource <-> accessor pairs but do not exercise the case where each task enters an independent domain. While 'sibling_domain' tests exist, they still use parent-child relationship patterns rather than true peer domains. Current Coverage (Linear Hierarchies Only): ------------------------------------------- Type 1: Parent-Child (scoped_domains) P1 ---- P2 Type 2: Three Generations (scoped_vs_unscoped) P1 ---- P2 ---- P3 Variations tested for both types: - No domains - Various scoped domain combinations - Nested domains within inherited domains - Mixed domain types (SCOPE vs OTHER vs NONE) Missing Coverage (True Sibling Scenarios): ------------------------------------------ Root | +-- Child A [various domain types] | +-- Child B [various domain types] Missing test scenarios: - A <-> B cross-sibling communication - Mixed sibling domain combinations - Sibling isolation enforcement - Parent -> A, Parent -> B differential access SOLUTION ======== This series implements the missing sibling pattern using the resource-accessor model. The tests create a fork tree that looks like this: coordinator (no domain) | +-- resource_proc (Domain X) /* owns the resource */ | +-- accessor_proc (Domain Y) /* tries to access */ This directly addresses the missing coverage by creating two independent child processes that establish peer domains, rather than the hierarchical parent-child domains covered by existing tests. Both children call landlock_restrict_self() for the first time, so their struct landlock_domain->parent pointers are NULL, creating true peer domains. The harness exposes four test variants: Variant name | Resource domain | Accessor domain | Result -------------------|-----------------|-----------------|---------- none_to_none | none | none | ALLOW none_to_scoped | none | scoped | DENY scoped_to_none | scoped | none | ALLOW scoped_to_scoped | scoped | scoped (peer) | DENY The scoped_to_scoped case was missing from current coverage. TESTING ======= All patches apply cleanly to v6.14-rc2 and pass on landlock/master. The helpers are small and re-use the existing kselftest_harness.h fixture/variant pattern. All patches have been validated with scripts/checkpatch.pl --strict and show no warnings. This series introduces **no kernel changes**, only selftests additions. Feedback very welcome. Thanks, Abhinav [1] https://github.com/landlock-lsm/linux/issues/37 Links: - Landlock documentation: https://docs.kernel.org/userspace-api/landlock.html - Landlock LSM kernel docs: https://docs.kernel.org/security/landlock.html - Existing tests: tools/testing/selftests/landlock/scoped_* Signed-off-by: Abhinav Saxena <xandfury(a)gmail.com> --- Abhinav Saxena (3): selftests/landlock: move sandbox_type to common selftests/landlock: add cross-domain variants selftests/landlock: add cross-domain signal tests tools/testing/selftests/landlock/scoped_common.h | 7 + .../landlock/scoped_cross_domain_variants.h | 54 +++++ .../landlock/scoped_multiple_domain_variants.h | 7 - .../selftests/landlock/scoped_signal_test.c | 237 +++++++++++++++++++++ 4 files changed, 298 insertions(+), 7 deletions(-) --- base-commit: 5b74b2eff1eeefe43584e5b7b348c8cd3b723d38 change-id: 20250715-landlock_abstractions-dbc0aabf1063 Best regards, -- Abhinav Saxena <xandfury(a)gmail.com>

1 month

1
3
0 0

[PATCH v13 net-next 00/14] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v10 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v13 (18-Jul-2025) - Implement tcp_accecn_extract_syn_ect() and tcp_accecn_reflector_flags() with static array lookup of patch #6 (Paolo Abeni <pabeni(a)redhat.com>) - Fix typos in comments of #6 and remove patch #7 of v12 about simulatenous connect (Paolo Abeni <pabeni(a)redhat.com>) - Move TCP_ACCECN_E1B_INIT_OFFSET, TCP_ACCECN_E0B_INIT_OFFSET, and TCP_ACCECN_CEB_INIT_OFFSET from patch #7 to #11 (Paolo Abeni <pabeni(a)redhat.com>) - Use static array lookup in tcp_accecn_optfield_to_ecnfield() of patch #11 (Paolo Abeni <pabeni(a)redhat.com>) - Return false when WARN_ON_ONCE() is true in tcp_accecn_process_option() of patch #11 (Paolo Abeni <pabeni(a)redhat.com>) - Make synack_ecn_bytes as static const array and use const u32 pointer in tcp_options_write() of #11 (Paolo Abeni <pabeni(a)redhat.com>) - Use ALIGN() and ALIGN_DOWN() in tcp_options_fit_accecn() to pad TCP AccECN option to dword of #11 (Paolo Abeni <pabeni(a)redhat.com>) - Return TCP_ACCECN_OPT_FAIL_SEEN if WARN_ON_ONCE() is true in tcp_accecn_option_init() of #12 (Paolo Abeni <pabeni(a)redhat.com>) v12 (04-Jul-2025) - Fix compilation issues with some intermediate patches in v11 - Add more comments for AccECN helpers of tcp_ecn.h v11 (03-Jul-2025) - Fix compilation issues with some intermediate patches in v10 v10 (02-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (5): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 12 + include/linux/tcp.h | 32 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 649 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 28 +- net/ipv4/tcp_input.c | 353 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 294 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1409 insertions(+), 184 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

1 month

2
15
0 0

[PATCH v24 net-next 0/6] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v24. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v24 (18-Jul-2025) - Replace TCA_DUALPI2 prefix with TC_DUALPI2 for enums in pkt_sched.h (Jakub Kicinski <kuba(a)kernel.org>) - Report error if both packet and time step thresholds are provided (Jakub Kicinski <kuba(a)kernel.org>) v23 (13-Jul-2025) and v22 (11-Jul-2025) - Fix issue when user would like to change DualPI2 but provides an empty TCA_OPTIONS with no nested attributes (Paolo Abeni <pabeni(a)redhat.com>, Jakub Kicinski <kuba(a)kernel.org>) v21 (02-Jul-2025) - Replace STEP_THRESH and STEP_PACKETS with STEP_THRESH_PKTS and STEP_THRESH_US (Jakub Kicinski <kuba(a)kernel.org>) - Move READ_ONCE and WRITE_ONCE to later DualPI2 patches (Jakub Kicinski <kuba(a)kernel.org>) - Replace NLA_POLICY_FULL_RANGE with NLA_POLICY_RANGE (Jakub Kicinski <kuba(a)kernel.org>) - Set extra error message for dualpi2_change (Jakub Kicinski <kuba(a)kernel.org>) - Drop redundant else for better readability (Paolo Abeni <pabeni(a)redhat.com>) - Replace step-thresh and step-packets with step-thresh-pkts and step-thresh-us (Jakub Kicinski <kuba(a)kernel.org>) - Remove redundant name-prefix and simplify entries of dualpi2 enums (Jakub Kicinski <kuba(a)kernel.org>) - Fix some typos and format issues of dualpi2 attributes v20 (21-Jun-2025) - Add one more commit to fix warning and style check on tdc.sh reported by shellcheck - Remove double-prefixed of "tc_tc_dualpi2_attrs" in tc-user.h (Donald Hunter <donald.hunter(a)gmail.com>) v19 (14-Jun-2025) - Fix one typo in the comment of #1 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update commit message of #4 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Wrap long lines of Documentation/netlink/specs/tc.yaml to within 80 characters (Jakub Kicinski <kuba(a)kernel.org>) v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (5): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Fix warning and style check on tdc.sh selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 151 ++- include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 68 + net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1174 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 6 +- 9 files changed, 1668 insertions(+), 5 deletions(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

1 month

2
7
0 0

[PATCH 0/2] Fix undetected overflow when allocating IOVA

by Jason Gunthorpe

Syzkaller found this, the ALIGN() call can overflow and corrupt the allocation process. Fix the bug and add some test coverage. Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Jason Gunthorpe (2): iommufd: Prevent ALIGN() overflow iommufd/selftest: Test reserved regions near ULONG_MAX drivers/iommu/iommufd/io_pagetable.c | 41 +++++++++++++++---------- tools/testing/selftests/iommu/iommufd.c | 18 +++++++++++ 2 files changed, 43 insertions(+), 16 deletions(-) base-commit: 601b1d0d9395c711383452bd0d47037afbbb4bcf -- 2.43.0

1 month

4
13
0 0

[PATCH v2] selftests/damon: introduce _common.sh to host shared function

by Enze Li

The current test scripts contain duplicated root permission checks in multiple locations. This patch consolidates these checks into _common.sh to eliminate code redundancy. Signed-off-by: Enze Li <lienze(a)kylinos.cn> --- tools/testing/selftests/damon/_common.sh | 11 +++++++++++ tools/testing/selftests/damon/lru_sort.sh | 8 +++----- tools/testing/selftests/damon/reclaim.sh | 8 +++----- tools/testing/selftests/damon/sysfs.sh | 11 ++--------- .../damon/sysfs_update_removed_scheme_dir.sh | 8 +++----- 5 files changed, 22 insertions(+), 24 deletions(-) create mode 100644 tools/testing/selftests/damon/_common.sh diff --git a/tools/testing/selftests/damon/_common.sh b/tools/testing/selftests/damon/_common.sh new file mode 100644 index 000000000000..0279698f733e --- /dev/null +++ b/tools/testing/selftests/damon/_common.sh @@ -0,0 +1,11 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +check_dependencies() +{ + if [ $EUID -ne 0 ] + then + echo "Run as root" + exit $ksft_skip + fi +} diff --git a/tools/testing/selftests/damon/lru_sort.sh b/tools/testing/selftests/damon/lru_sort.sh index 61b80197c896..1e4849db78a9 100755 --- a/tools/testing/selftests/damon/lru_sort.sh +++ b/tools/testing/selftests/damon/lru_sort.sh @@ -1,14 +1,12 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +source _common.sh + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_lru_sort_enabled="/sys/module/damon_lru_sort/parameters/enabled" if [ ! -f "$damon_lru_sort_enabled" ] diff --git a/tools/testing/selftests/damon/reclaim.sh b/tools/testing/selftests/damon/reclaim.sh index 78dbc2334cbe..e56ceb035129 100755 --- a/tools/testing/selftests/damon/reclaim.sh +++ b/tools/testing/selftests/damon/reclaim.sh @@ -1,14 +1,12 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +source _common.sh + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_reclaim_enabled="/sys/module/damon_reclaim/parameters/enabled" if [ ! -f "$damon_reclaim_enabled" ] diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index e9a976d296e2..83e3b7f63d81 100755 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +source _common.sh + # Kselftest frmework requirement - SKIP code is 4. ksft_skip=4 @@ -364,14 +366,5 @@ test_damon_sysfs() test_kdamonds "$damon_sysfs/kdamonds" } -check_dependencies() -{ - if [ $EUID -ne 0 ] - then - echo "Run as root" - exit $ksft_skip - fi -} - check_dependencies test_damon_sysfs "/sys/kernel/mm/damon/admin" diff --git a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh index ade35576e748..35fc32beeaf7 100755 --- a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh +++ b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh @@ -1,14 +1,12 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +source _common.sh + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_sysfs="/sys/kernel/mm/damon/admin" if [ ! -d "$damon_sysfs" ] base-commit: e2291551827fe5d2d3758c435c191d32b6d1350e -- 2.43.0

1 month

2
1
0 0

[PATCH 0/2] eventpoll: Fix epoll_wait() report false negative

by Nam Cao

Hi, While staring at epoll, I noticed ep_events_available() looks wrong. I wrote a small program to confirm, and yes it is definitely wrong. This series adds a reproducer to kselftest, and fix the bug. Nam Cao (2): selftests/eventpoll: Add test for multiple waiters eventpoll: Fix epoll_wait() report false negative fs/eventpoll.c | 16 +------ .../filesystems/epoll/epoll_wakeup_test.c | 45 +++++++++++++++++++ 2 files changed, 47 insertions(+), 14 deletions(-) -- 2.39.5

1 month

2
4
0 0

[PATCH] selftests/damon: introduce _common.sh to host shared function

by Enze Li

The current test scripts contain duplicated root permission checks in multiple locations. This patch consolidates these checks into _common.sh to eliminate code redundancy. Signed-off-by: Enze Li <lienze(a)kylinos.cn> --- tools/testing/selftests/damon/_common.sh | 14 ++++++++++++++ tools/testing/selftests/damon/lru_sort.sh | 9 ++------- tools/testing/selftests/damon/reclaim.sh | 9 ++------- tools/testing/selftests/damon/sysfs.sh | 12 +----------- .../damon/sysfs_update_removed_scheme_dir.sh | 9 ++------- 5 files changed, 21 insertions(+), 32 deletions(-) create mode 100644 tools/testing/selftests/damon/_common.sh diff --git a/tools/testing/selftests/damon/_common.sh b/tools/testing/selftests/damon/_common.sh new file mode 100644 index 000000000000..3920b619c30f --- /dev/null +++ b/tools/testing/selftests/damon/_common.sh @@ -0,0 +1,14 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest frmework requirement - SKIP code is 4. +ksft_skip=4 + +check_dependencies() +{ + if [ $EUID -ne 0 ] + then + echo "Run as root" + exit $ksft_skip + fi +} diff --git a/tools/testing/selftests/damon/lru_sort.sh b/tools/testing/selftests/damon/lru_sort.sh index 61b80197c896..0d128d809fd3 100755 --- a/tools/testing/selftests/damon/lru_sort.sh +++ b/tools/testing/selftests/damon/lru_sort.sh @@ -1,14 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source _common.sh -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_lru_sort_enabled="/sys/module/damon_lru_sort/parameters/enabled" if [ ! -f "$damon_lru_sort_enabled" ] diff --git a/tools/testing/selftests/damon/reclaim.sh b/tools/testing/selftests/damon/reclaim.sh index 78dbc2334cbe..41e450a696ae 100755 --- a/tools/testing/selftests/damon/reclaim.sh +++ b/tools/testing/selftests/damon/reclaim.sh @@ -1,14 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source _common.sh -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_reclaim_enabled="/sys/module/damon_reclaim/parameters/enabled" if [ ! -f "$damon_reclaim_enabled" ] diff --git a/tools/testing/selftests/damon/sysfs.sh b/tools/testing/selftests/damon/sysfs.sh index e9a976d296e2..0326b9ad55ca 100755 --- a/tools/testing/selftests/damon/sysfs.sh +++ b/tools/testing/selftests/damon/sysfs.sh @@ -1,8 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Kselftest frmework requirement - SKIP code is 4. -ksft_skip=4 +source _common.sh ensure_write_succ() { @@ -364,14 +363,5 @@ test_damon_sysfs() test_kdamonds "$damon_sysfs/kdamonds" } -check_dependencies() -{ - if [ $EUID -ne 0 ] - then - echo "Run as root" - exit $ksft_skip - fi -} - check_dependencies test_damon_sysfs "/sys/kernel/mm/damon/admin" diff --git a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh index ade35576e748..730165bd7f03 100755 --- a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh +++ b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh @@ -1,14 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 +source _common.sh -if [ $EUID -ne 0 ] -then - echo "Run as root" - exit $ksft_skip -fi +check_dependencies damon_sysfs="/sys/kernel/mm/damon/admin" if [ ! -d "$damon_sysfs" ] base-commit: e2291551827fe5d2d3758c435c191d32b6d1350e -- 2.43.0

1 month

3
4
0 0

[PATCH 0/2] selftests/cgroup: better bound for cpu.max tests

by Shashank Balaji

cpu.max selftests (both the normal one and the nested one) test the working of throttling by setting up cpu.max, running a cpu hog process for a specified duration, and comparing usage_usec as reported by cpu.stat with the duration of the cpu hog: they should be far enough. Currently, this is done by using values_close, which has two problems: 1. Semantic: values_close is used with an error percentage of 95%, which one will not expect on seeing "values close". The intent it's actually going for is "values far". 2. Accuracy: the tests can pass even if usage_usec is upto around double the expected amount. That's too high of a margin for usage_usec. Overall, this patchset improves the readability and accuracy of the cpu.max tests. Signed-off-by: Shashank Balaji <shashank.mahadasyam(a)sony.com> --- Shashank Balaji (2): selftests/cgroup: rename `expected` to `duration` in cpu.max tests selftests/cgroup: better bound in cpu.max tests tools/testing/selftests/cgroup/test_cpu.c | 42 ++++++++++++++++++------------- 1 file changed, 24 insertions(+), 18 deletions(-) --- base-commit: 66701750d5565c574af42bef0b789ce0203e3071 change-id: 20250227-kselftest-cgroup-fix-cpu-max-56619928e99b Best regards, -- Shashank Balaji <shashank.mahadasyam(a)sony.com>

1 month, 1 week

3
16
0 0

[PATCH bpf-next v5 0/3] Allow mmap of /sys/kernel/btf/vmlinux

by Lorenz Bauer

I'd like to cut down the memory usage of parsing vmlinux BTF in ebpf-go. With some upcoming changes the library is sitting at 5MiB for a parse. Most of that memory is simply copying the BTF blob into user space. By allowing vmlinux BTF to be mmapped read-only into user space I can cut memory usage by about 75%. Signed-off-by: Lorenz Bauer <lmb(a)isovalent.com> --- Changes in v5: - Fix error return of btf_parse_raw_mmap (Andrii) - Link to v4: https://lore.kernel.org/r/20250510-vmlinux-mmap-v4-0-69e424b2a672@isovalent… Changes in v4: - Go back to remap_pfn_range for aarch64 compat - Dropped btf_new_no_copy (Andrii) - Fixed nits in selftests (Andrii) - Clearer error handling in the mmap handler (Andrii) - Fixed build on s390 - Link to v3: https://lore.kernel.org/r/20250505-vmlinux-mmap-v3-0-5d53afa060e8@isovalent… Changes in v3: - Remove slightly confusing calculation of trailing (Alexei) - Use vm_insert_page (Alexei) - Simplified libbpf code - Link to v2: https://lore.kernel.org/r/20250502-vmlinux-mmap-v2-0-95c271434519@isovalent… Changes in v2: - Use btf__new in selftest - Avoid vm_iomap_memory in btf_vmlinux_mmap - Add VM_DONTDUMP - Add support to libbpf - Link to v1: https://lore.kernel.org/r/20250501-vmlinux-mmap-v1-0-aa2724572598@isovalent… --- Lorenz Bauer (3): btf: allow mmap of vmlinux btf selftests: bpf: add a test for mmapable vmlinux BTF libbpf: Use mmap to parse vmlinux BTF from sysfs include/asm-generic/vmlinux.lds.h | 3 +- kernel/bpf/sysfs_btf.c | 32 ++++++++ tools/lib/bpf/btf.c | 89 +++++++++++++++++----- tools/testing/selftests/bpf/prog_tests/btf_sysfs.c | 81 ++++++++++++++++++++ 4 files changed, 186 insertions(+), 19 deletions(-) --- base-commit: 7220eabff8cb4af3b93cd021aa853b9f5df2923f change-id: 20250501-vmlinux-mmap-2ec5563c3ef1 Best regards, -- Lorenz Bauer <lmb(a)isovalent.com>

1 month, 1 week

6
11
0 0

[PATCH bpf-next v2 0/3] bpf: Show precise rejected function when attaching to __noreturn and deny list functions

by KaFai Wan

Show precise rejected function when attaching fexit/fmod_ret to __noreturn functions. Add log for attaching tracing programs to functions in deny list. Add selftest for attaching tracing programs to functions in deny list. changes: v2: - change verifier log message (Alexei) - add missing Suggested-by v1: https://lore.kernel.org/all/20250710162717.3808020-1-mannkafai@gmail.com/ --- KaFai Wan (3): bpf: Show precise rejected function when attaching fexit/fmod_ret to __noreturn functions bpf: Add log for attaching tracing programs to functions in deny list selftests/bpf: Add selftest for attaching tracing programs to functions in deny list kernel/bpf/verifier.c | 5 ++++- .../selftests/bpf/prog_tests/tracing_deny.c | 11 +++++++++++ .../testing/selftests/bpf/progs/fexit_noreturns.c | 2 +- tools/testing/selftests/bpf/progs/tracing_deny.c | 15 +++++++++++++++ 4 files changed, 31 insertions(+), 2 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_deny.c create mode 100644 tools/testing/selftests/bpf/progs/tracing_deny.c -- 2.43.0

1 month, 1 week

2
5
0 0

[PATCH v23 net-next 0/6] DUALPI2 patch

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the DualPI2 patch v23. This patch serise adds DualPI Improved with a Square (DualPI2) with following features: * Supports congestion controls that comply with the Prague requirements in RFC9331 (e.g. TCP-Prague) * Coupled dual-queue that separates the L4S traffic in a low latency queue (L-queue), without harming remaining traffic that is scheduled in classic queue (C-queue) due to congestion-coupling using PI2 as defined in RFC9332 * Configurable overload strategies * Use of sojourn time to reliably estimate queue delay * Supports ECN L4S-identifier (IP.ECN==0b*1) to classify traffic into respective queues For more details of DualPI2, please refer IETF RFC9332 (https://datatracker.ietf.org/doc/html/rfc9332). Best regards, Chia-Yu --- v23 (13-Jul-2025) and v22 (11-Jul-2025) - Fix issue when user would like to change DualPI2 but provides an empty TCA_OPTIONS with no nested attributes (Paolo Abeni <pabeni(a)redhat.com>, Jakub Kicinski <kuba(a)kernel.org>) v21 (02-Jul-2025) - Replace STEP_THRESH and STEP_PACKETS with STEP_THRESH_PKTS and STEP_THRESH_US (Jakub Kicinski <kuba(a)kernel.org>) - Move READ_ONCE and WRITE_ONCE to later DualPI2 patches (Jakub Kicinski <kuba(a)kernel.org>) - Replace NLA_POLICY_FULL_RANGE with NLA_POLICY_RANGE (Jakub Kicinski <kuba(a)kernel.org>) - Set extra error message for dualpi2_change (Jakub Kicinski <kuba(a)kernel.org>) - Drop redundant else for better readability (Paolo Abeni <pabeni(a)redhat.com>) - Replace step-thresh and step-packets with step-thresh-pkts and step-thresh-us (Jakub Kicinski <kuba(a)kernel.org>) - Remove redundant name-prefix and simplify entries of dualpi2 enums (Jakub Kicinski <kuba(a)kernel.org>) - Fix some typos and format issues of dualpi2 attributes v20 (21-Jun-2025) - Add one more commit to fix warning and style check on tdc.sh reported by shellcheck - Remove double-prefixed of "tc_tc_dualpi2_attrs" in tc-user.h (Donald Hunter <donald.hunter(a)gmail.com>) v19 (14-Jun-2025) - Fix one typo in the comment of #1 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Update commit message of #4 (ALOK TIWARI <alok.a.tiwari(a)oracle.com>) - Wrap long lines of Documentation/netlink/specs/tc.yaml to within 80 characters (Jakub Kicinski <kuba(a)kernel.org>) v18 (13-Jun-2025) - Add the num of enum used by DualPI2 and fix name and name-prefix of DualPI2 enum and attribute - Replace from_timer() with timer_container_of() (Pedro Tammela <pctammela(a)mojatatu.com>) v17 (25-May-2025, Resent at 11-Jun-2025) - Replace 0xffffffff with U32_MAX (Paolo Abeni <pabeni(a)redhat.com>) - Use helper function qdisc_dequeue_internal() and add new helper function skb_apply_step() (Paolo Abeni <pabeni(a)redhat.com>) - Add s64 casting when calculating the delta of the PI controller (Paolo Abeni <pabeni(a)redhat.com>) - Change the drop reason into SKB_DROP_REASON_QDISC_CONGESTED for drop_early (Paolo Abeni <pabeni(a)redhat.com>) - Modify the condition to remove the original skb when enqueuing multiple GSO segments (Paolo Abeni <pabeni(a)redhat.com>) - Add READ_ONCE() in dualpi2_dump_stat() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments, brackets, and brackets for readability (Paolo Abeni <pabeni(a)redhat.com>) v16 (16-MAy-2025) - Add qdisc_lock() to dualpi2_timer() in dualpi2_timer (Paolo Abeni <pabeni(a)redhat.com>) - Introduce convert_ns_to_usec() to convert usec to nsec without overflow in #1 (Paolo Abeni <pabeni(a)redhat.com>) - Update convert_us_tonsec() to convert nsec to usec without overflow in #2 (Paolo Abeni <pabeni(a)redhat.com>) - Add more descriptions with respect to DualPI2 in the cover ltter and add changelog in each patch (Paolo Abeni <pabeni(a)redhat.com>) v15 (09-May-2025) - Add enum of TCA_DUALPI2_ECN_MASK_CLA_ECT to remove potential leakeage in #1 (Simon Horman <horms(a)kernel.org>) - Fix one typo in comment of #2 - Update tc.yaml in #5 to aligh with the updated enum of pkt_sched.h v14 (05-May-2025) - Modify tc.yaml: (1) Replace flags with enum and remove enum-as-flags, (2) Remove credit-queue in xstats, and (3) Change attribute types (Donald Hunter <donald.hun - Add enum and fix the ordering of variables in pkt_sched.h to align with the modified tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add validators for DROP_OVERLOAD, DROP_EARLY, ECN_MASK, and SPLIT_GSO in sch_dualpi2.c (Donald Hunter <donald.hunter(a)gmail.com>) - Update dualpi2.json to align with the updated variable order in pkt_sched.h - Reorder patches (Donald Hunter <donald.hunter(a)gmail.com>) v13 (26-Apr-2025) - Use dashes in member names to follow YNL conventions in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Define enumerations separately for flags of drop-early, drop-overload, ecn-mask, credit-queue in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Change the types of split-gso and step-packets into flag in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Revert to u32/u8 types for tc-dualpi2-xstats members in tc.yaml (Donald Hunter <donald.hunter(a)gmail.com>) - Add new test cases in tc-tests/qdiscs/dualpi2.json to cover all dualpi2 parameters (Donald Hunter <donald.hunter(a)gmail.com>) - Change the type of TCA_DUALPI2_STEP_PACKETS into NLA_FLAG (Donald Hunter <donald.hunter(a)gmail.com>) v12 (22-Apr-2025) - Remove anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Replace u32/u8 with uint and s32 with int in tc spec document (Paolo Abeni <pabeni(a)redhat.com>) - Introduce get_memory_limit function to handle potential overflow when multipling limit with MTU (Paolo Abeni <pabeni(a)redhat.com>) - Double the packet length to further include packet overhead in memory_limit (Paolo Abeni <pabeni(a)redhat.com>) - Remove the check of qdisc_qlen(sch) when calling qdisc_tree_reduce_backlog (Paolo Abeni <pabeni(a)redhat.com>) v11 (15-Apr-2025) - Replace hstimer_init with hstimer_setup in sch_dualpi2.c v10 (25-Mar-2025) - Remove leftover include in include/linux/netdevice.h and anonymous struct in sch_dualpi2.c (Paolo Abeni <pabeni(a)redhat.com>) - Use kfree_skb_reason() and add SKB_DROP_REASON_DUALPI2_STEP_DROP drop reason (Paolo Abeni <pabeni(a)redhat.com>) - Split sch_dualpi2.c into 3 patches (and overall 5 patches): Struct definition & parsing, Dump stats & configuration, Enqueue/Dequeue (Paolo Abeni <pabeni(a)redhat.com>) v9 (16-Mar-2025) - Fix mem_usage error in previous version - Add min_qlen_step to the dualpi2 attribute as the minimum queue length in number of packets in the L-queue to start step threshold marking. In previous versions, this value was fixed to 2, so the step threshold was applied to mark packets in the L queue only when the queue length of the L queue was greater than or equal to 2 packets. This will cause larger queuing delays for L4S traffic at low rates (<20Mbps). So we parameterize it and change the default value to 0. Comparison of tcp_1down run 'HTB 20Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 11.55 11.70 ms 350 TCP upload avg : 18.96 N/A Mbits/s 350 TCP upload sum : 18.96 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 10.81 10.70 ms 350 TCP upload avg : 18.91 N/A Mbits/s 350 TCP upload sum : 18.91 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 12.61 12.80 ms 350 TCP upload avg : 9.48 N/A Mbits/s 350 TCP upload sum : 9.48 N/A Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.06 10.80 ms 350 TCP upload avg : 9.43 N/A Mbits/s 350 TCP upload sum : 9.43 N/A Mbits/s 350 Comparison of tcp_1down run 'HTB 10Mbit + DUALPI2 + 10ms base delay' Old versions: avg median # data pts Ping (ms) ICMP : 40.86 37.45 ms 350 TCP upload avg : 0.88 N/A Mbits/s 350 TCP upload sum : 0.88 N/A Mbits/s 350 TCP upload::1 : 0.88 0.97 Mbits/s 350 New version (v9): avg median # data pts Ping (ms) ICMP : 11.07 10.40 ms 350 TCP upload avg : 0.55 N/A Mbits/s 350 TCP upload sum : 0.55 N/A Mbits/s 350 TCP upload::1 : 0.55 0.59 Mbits/s 350 v8 (11-Mar-2025) - Fix warning messages in v7 v7 (07-Mar-2025) - Separate into 3 patches to avoid mixing changes of documentation, selftest, and code. (Cong Wang <xiyou.wangcong(a)gmail.com>) v6 (04-Mar-2025) - Add modprobe for dulapi2 in tc-testing script tc-testing/tdc.sh (Jakub Kicinski <kuba(a)kernel.org>) - Update test cases in dualpi2.json - Update commit message v5 (22-Feb-2025) - A comparison was done between MQ + DUALPI2, MQ + FQ_PIE, MQ + FQ_CODEL: Unshaped 1gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 - Summary of tcp_4down run 'MQ + FQ_PIE' avg median # data pts Ping (ms) ICMP : 1.21 1.37 ms 350 TCP download avg : 235.42 N/A Mbits/s 350 TCP download sum : 941.61 N/A Mbits/s 350 TCP download::1 : 232.54 233.13 Mbits/s 350 TCP download::2 : 232.52 232.80 Mbits/s 350 TCP download::3 : 233.14 233.78 Mbits/s 350 TCP download::4 : 243.41 241.48 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2' avg median # data pts Ping (ms) ICMP : 1.19 1.34 ms 349 TCP download avg : 235.42 N/A Mbits/s 349 TCP download sum : 941.68 N/A Mbits/s 349 TCP download::1 : 235.19 235.39 Mbits/s 349 TCP download::2 : 235.03 235.35 Mbits/s 349 TCP download::3 : 236.89 235.44 Mbits/s 349 TCP download::4 : 234.57 235.19 Mbits/s 349 Unshaped 1gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 1.88 1.86 ms 350 TCP download avg : 7.39 N/A Mbits/s 350 TCP download sum : 946.47 N/A Mbits/s 350 Unshaped 10gigE with 4 download streams test: - Summary of tcp_4down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 0.22 0.23 ms 350 TCP download avg : 2354.08 N/A Mbits/s 350 TCP download sum : 9416.31 N/A Mbits/s 350 TCP download::1 : 2353.65 2352.81 Mbits/s 350 TCP download::2 : 2354.54 2354.21 Mbits/s 350 TCP download::3 : 2353.56 2353.78 Mbits/s 350 TCP download::4 : 2354.56 2354.45 Mbits/s 350 - Summary of tcp_4down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 0.20 0.19 ms 350 TCP download avg : 2354.76 N/A Mbits/s 350 TCP download sum : 9419.04 N/A Mbits/s 350 TCP download::1 : 2354.77 2353.89 Mbits/s 350 TCP download::2 : 2353.41 2354.29 Mbits/s 350 TCP download::3 : 2356.18 2354.19 Mbits/s 350 TCP download::4 : 2354.68 2353.15 Mbits/s 350 - Summary of tcp_4down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 0.24 0.24 ms 350 TCP download avg : 2354.11 N/A Mbits/s 350 TCP download sum : 9416.43 N/A Mbits/s 350 TCP download::1 : 2354.75 2353.93 Mbits/s 350 TCP download::2 : 2353.15 2353.75 Mbits/s 350 TCP download::3 : 2353.49 2353.72 Mbits/s 350 TCP download::4 : 2355.04 2353.73 Mbits/s 350 Unshaped 10gigE with 128 download streams test: - Summary of tcp_128down run 'MQ + FQ_CODEL': avg median # data pts Ping (ms) ICMP : 7.57 8.69 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9467.82 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + FQ_PIE': avg median # data pts Ping (ms) ICMP : 7.82 8.91 ms 350 TCP download avg : 73.97 N/A Mbits/s 350 TCP download sum : 9468.42 N/A Mbits/s 350 - Summary of tcp_128down run 'MQ + DUALPI2': avg median # data pts Ping (ms) ICMP : 6.87 7.93 ms 350 TCP download avg : 73.95 N/A Mbits/s 350 TCP download sum : 9465.87 N/A Mbits/s 350 From the results shown above, we see small differences between combinations. - Update commit message to include results of no_split_gso and split_gso (Dave Taht <dave.taht(a)gmail.com> and Paolo Abeni <pabeni(a)redhat.com>) - Add memlimit in the dualpi2 attribute, and add memory_used, max_memory_used, memory_limit in dualpi2 stats (Dave Taht <dave.taht(a)gmail.com>) - Update note in sch_dualpi2.c related to BBRv3 status (Dave Taht <dave.taht(a)gmail.com>) - Update license identifier (Dave Taht <dave.taht(a)gmail.com>) - Add selftest in tools/testing/selftests/tc-testing (Cong Wang <xiyou.wangcong(a)gmail.com>) - Use netlink policies for parameter checks (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Modify texts & fix typos in Documentation/netlink/specs/tc.yaml (Dave Taht <dave.taht(a)gmail.com>) - Add descriptions of packet counter statistics and the reset function of sch_dualpi2.c - Fix step_thresh in packets - Update code comments in sch_dualpi2.c v4 (22-Oct-2024) - Update statement in Kconfig for DualPI2 (Stephen Hemminger <stephen(a)networkplumber.org>) - Put a blank line after #define in sch_dualpi2.c (Stephen Hemminger <stephen(a)networkplumber.org>) - Fix line length warning. v3 (19-Oct-2024) - Fix compilaiton error - Update Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Oct-2024) - Add Documentation/netlink/specs/tc.yaml (Jakub Kicinski <kuba(a)kernel.org>) - Use dualpi2 instead of skb prefix (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Replace nla_parse_nested_deprecated with nla_parse_nested (Jamal Hadi Salim <jhs(a)mojatatu.com>) - Fix line length warning --- Chia-Yu Chang (5): sched: Struct definition and parsing of dualpi2 qdisc sched: Dump configuration and statistics of dualpi2 qdisc selftests/tc-testing: Fix warning and style check on tdc.sh selftests/tc-testing: Add selftests for qdisc DualPI2 Documentation: netlink: specs: tc: Add DualPI2 specification Koen De Schepper (1): sched: Add enqueue/dequeue of dualpi2 qdisc Documentation/netlink/specs/tc.yaml | 151 ++- include/net/dropreason-core.h | 6 + include/uapi/linux/pkt_sched.h | 68 + net/sched/Kconfig | 12 + net/sched/Makefile | 1 + net/sched/sch_dualpi2.c | 1171 +++++++++++++++++ tools/testing/selftests/tc-testing/config | 1 + .../tc-testing/tc-tests/qdiscs/dualpi2.json | 254 ++++ tools/testing/selftests/tc-testing/tdc.sh | 6 +- 9 files changed, 1665 insertions(+), 5 deletions(-) create mode 100644 net/sched/sch_dualpi2.c create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json -- 2.34.1

1 month, 1 week

3
11
0 0

[PATCH] selftest/futex: fix format-security warnings in futex_priv_hash

by Nai-Chen Cheng

Fix format-security warnings by using proper format strings when passing message variables to ksft_exit_fail_msg(), ksft_test_result_pass(), and ksft_test_result_skip() function. This prevents potential security issues and eliminates compiler warnings when building with -Wformat-security. Signed-off-by: Nai-Chen Cheng <bleach1827(a)gmail.com> --- .../selftests/futex/functional/futex_priv_hash.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c index 24a92dc94eb8..19651087c4de 100644 --- a/tools/testing/selftests/futex/functional/futex_priv_hash.c +++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c @@ -184,10 +184,10 @@ int main(int argc, char *argv[]) futex_slots1 = futex_hash_slots_get(); if (futex_slots1 <= 0) { ksft_print_msg("Current hash buckets: %d\n", futex_slots1); - ksft_exit_fail_msg(test_msg_auto_create); + ksft_exit_fail_msg("%s", test_msg_auto_create); } - ksft_test_result_pass(test_msg_auto_create); + ksft_test_result_pass("%s", test_msg_auto_create); online_cpus = sysconf(_SC_NPROCESSORS_ONLN); ret = pthread_barrier_init(&barrier_main, NULL, MAX_THREADS + 1); @@ -212,11 +212,11 @@ int main(int argc, char *argv[]) if (futex_slotsn < 0 || futex_slots1 == futex_slotsn) { ksft_print_msg("Expected increase of hash buckets but got: %d -> %d\n", futex_slots1, futex_slotsn); - ksft_exit_fail_msg(test_msg_auto_inc); + ksft_exit_fail_msg("%s", test_msg_auto_inc); } - ksft_test_result_pass(test_msg_auto_inc); + ksft_test_result_pass("%s", test_msg_auto_inc); } else { - ksft_test_result_skip(test_msg_auto_inc); + ksft_test_result_skip("%s", test_msg_auto_inc); } ret = pthread_mutex_unlock(&global_lock); -- 2.43.0

1 month, 1 week

1
0
0 0

[PATCH] kselftest/arm4: Provide local defines for AT_HWCAP3

by Mark Brown

Some build environments for the selftests are not picking up the newly added AT_HWCAP3 when using the libc headers, even with headers_install (which we require already for the arm64 selftests). As a quick fix add local definitions of the constant to tools use it, while auxvec.h is installed with some toolchains it needs some persuasion to get picked up. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/arm64/abi/hwcap.c | 4 ++++ tools/testing/selftests/arm64/mte/check_prctl.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 35f521e5f41c..aa902408facd 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -21,6 +21,10 @@ #define TESTS_PER_HWCAP 3 +#ifndef AT_HWCAP3 +#define AT_HWCAP3 29 +#endif + /* * Function expected to generate exception when the feature is not * supported and return when it is supported. If the specific exception diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c index 4c89e9538ca0..c36c4c49ff95 100644 --- a/tools/testing/selftests/arm64/mte/check_prctl.c +++ b/tools/testing/selftests/arm64/mte/check_prctl.c @@ -12,6 +12,10 @@ #include "kselftest.h" +#ifndef AT_HWCAP3 +#define AT_HWCAP3 29 +#endif + static int set_tagged_addr_ctrl(int val) { int ret; --- base-commit: 86731a2a651e58953fc949573895f2fa6d456841 change-id: 20250710-arm64-selftest-bodge-hwcap3-b6ab30ab69cd Best regards, -- Mark Brown <broonie(a)kernel.org>

1 month, 1 week

3
3
0 0

[PATCH v9 00/29] iommufd: Add vIOMMU infrastructure (Part-4 HW QUEUE)

by Nicolin Chen

The vIOMMU object is designed to represent a slice of an IOMMU HW for its virtualization features shared with or passed to user space (a VM mostly) in a way of HW acceleration. This extended the HWPT-based design for more advanced virtualization feature. HW QUEUE introduced by this series as a part of the vIOMMU infrastructure represents a HW accelerated queue/buffer for VM to use exclusively, e.g. - NVIDIA's Virtual Command Queue - AMD vIOMMU's Command Buffer, Event Log Buffer, and PPR Log Buffer each of which allows its IOMMU HW to directly access a queue memory owned by a guest VM and allows a guest OS to control the HW queue direclty, to avoid VM Exit overheads to improve the performance. Introduce IOMMUFD_OBJ_HW_QUEUE and its pairing IOMMUFD_CMD_HW_QUEUE_ALLOC allowing VMM to forward the IOMMU-specific queue info, such as queue base address, size, and etc. Meanwhile, a guest-owned queue needs the guest kernel to control the queue by reading/writing its consumer and producer indexes, via MMIO acceses to the hardware MMIO registers. Introduce an mmap infrastructure for iommufd to support passing through a piece of MMIO region from the host physical address space to the guest physical address space. The mmap info (offset/ length) used by an mmap syscall must be pre-allocated and returned to the user space via an output driver-data during an IOMMUFD_CMD_HW_QUEUE_ALLOC call. Thus, it requires a driver-specific user data support in the vIOMMU allocation flow. As a real-world use case, this series implements a HW QUEUE support in the tegra241-cmdqv driver for VCMDQs on NVIDIA Grace CPU. In another word, it is also the Tegra CMDQV series Part-2 (user-space support), reworked from Previous RFCv1: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This enables the HW accelerated feature for NVIDIA Grace CPU. Compared to the standard SMMUv3 operating in the nested translation mode trapping CMDQ for TLBI and ATC_INV commands, this gives a huge performance improvement: 70% to 90% reductions of invalidation time were measured by various DMA unmap tests running in a guest OS. // Unmap latencies from "dma_map_benchmark -g @granule -t @threads", // by toggling "/sys/kernel/debug/iommu/tegra241_cmdqv/bypass_vcmdq" @granule | @threads | bypass_vcmdq=1 | bypass_vcmdq=0 4KB 1 35.7 us 5.3 us 16KB 1 41.8 us 6.8 us 64KB 1 68.9 us 9.9 us 128KB 1 109.0 us 12.6 us 256KB 1 187.1 us 18.0 us 4KB 2 96.9 us 6.8 us 16KB 2 97.8 us 7.5 us 64KB 2 151.5 us 10.7 us 128KB 2 257.8 us 12.7 us 256KB 2 443.0 us 17.9 us This is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_hw_queue-v9 Paring QEMU branch for testing (reusing v8): https://github.com/nicolinc/qemu/commits/wip/for_iommufd_hw_queue-v8 Changelog v9 (attached git-diff v8..v9 at the end of this letter) * Add Reviewed-by from Vasant and Jason * [iommufd] Fix offset calculation * [iommufd] Add unaligned iova/length selftest coverage for hw_queue * [iommufd] Pass in aligned iova/length to iommufd_access_pin_pages() * [smmu] Change "u32 *type" at arm_smmu_hw_info() in the header v8 https://lore.kernel.org/all/cover.1751677708.git.nicolinc@nvidia.com/ * Add Reviewed-by from Pranj, Kevin and Jason * Improve kdoc and comments * [iommufd] Skip selftest for no_viommu variants * [iommufd] Add unmap coverage for non internal area * [iommufd] Skip the first page when mtree_alloc_range() * [iommufd] Correct the passed in index to mtree_erase() * [iommufd] Correct variable types in iommufd_hw_queue_alloc_phys() * [iommufd] Reject iopt_unmap_iova_range() if area->num_locks is set * [tegra] Rename "SID replacement" with "SID mapping" * [tegra] Unwrap useless _tegra241_vcmdq_hw_init helper v7 https://lore.kernel.org/all/cover.1750966133.git.nicolinc@nvidia.com/ * Rebased on Jason's for-next tree (iommufd_hw_queue-prep series) * Add Reviewed-by from Baolu, Jason, Pranjal * Update kdocs and notes * [iommu] Replace "u32" with "enum iommu_hw_info_type" * [iommufd] Rename vdev->id to vdev->virt_id * [iommufd] Replace macros with inline helpers * [iommufd] Report unmapped_bytes in error path * [iommufd] Add iommufd_access_is_internal helper * [iommufd] Do not drop ops->unmap check for mdevs * [iommufd] Store physical addresses in immap structure * [iommufd] Reorder access and hw_queue object allocations * [iommufd] Scan for an internal access before any unmap call * [iommufd] Drop unused ictx pointer in struct iommufd_hw_queue * [iommufd] Use kcalloc to avoid failure due to memory fragmentation * [tegra] Use "else" * [tegra] Lock destroy() using lvcmdq_mutex v6 https://lore.kernel.org/all/cover.1749884998.git.nicolinc@nvidia.com/ * Rebase on iommufd_hw_queue-prep-v2 * Add Reviewed-by from Kevin and Jason * [iommufd] Update kdocs and notes * [iommufd] Drop redundant pages[i] check * [iommufd] Allow nesting_parent_iova to be 0 * [iommufd] Add iommufd_hw_queue_alloc_phys() * [iommufd] Revise iommufd_viommu_alloc/destroy_mmap APIs * [iommufd] Move destroy ops to vdevice/hw_queue structures * [iommufd] Add union in hw_info struct to share out_data_type field * [iommufd] Replace iopt_pin/unpin_pages() with internal access APIs * [iommufd] Replace vdevice_alloc with vdevice_size and vdevice_init * [iommufd] Replace hw_queue_alloc with get_hw_queue_size/hw_queue_init * [iommufd] Replace IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA with init_phys * [smmu] Drop arm_smmu_domain_ipa_to_pa * [smmu] Update arm_smmu_impl_ops changes for vsmmu_init * [tegra] Add a vdev_to_vsid macro * [tegra] Add lvcmdq_mutex to protect multi queues * [tegra] Drop duplicated kcalloc for vintf->lvcmdqs (memory leak) v5 https://lore.kernel.org/all/cover.1747537752.git.nicolinc@nvidia.com/ * Rebase on v6.15-rc6 * Add Reviewed-by from Jason and Kevin * Correct typos in kdoc and update commit logs * [iommufd] Add a cosmetic fix * [iommufd] Drop unused num_pfns * [iommufd] Drop unnecessary check * [iommufd] Reorder patch sequence * [iommufd] Use io_remap_pfn_range() * [iommufd] Use success oriented flow * [iommufd] Fix max_npages calculation * [iommufd] Add more selftest coverage * [iommufd] Drop redundant static_assert * [iommufd] Fix mmap pfn range validation * [iommufd] Reject unmap on pinned iovas * [iommufd] Drop redundant vm_flags_set() * [iommufd] Drop iommufd_struct_destroy() * [iommufd] Drop redundant queue iova test * [iommufd] Use "mmio_addr" and "mmio_pfn" * [iommufd] Rename to "nesting_parent_iova" * [iommufd] Make iopt_pin_pages call option * [iommufd] Add ictx comparison in depend() * [iommufd] Add iommufd_object_alloc_ucmd() * [iommufd] Move kcalloc() after validations * [iommufd] Replace ictx setting with WARN_ON * [iommufd] Make hw_info's type bidirectional * [smmu] Add supported_vsmmu_type in impl_ops * [smmu] Drop impl report in smmu vendor struct * [tegra] Add IOMMU_HW_INFO_TYPE_TEGRA241_CMDQV * [tegra] Replace "number of VINTFs" with a note * [tegra] Drop the redundant lvcmdq pointer setting * [tegra] Flag IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA * [tegra] Use "vintf_alloc_vsid" for vdevice_alloc op v4 https://lore.kernel.org/all/cover.1746757630.git.nicolinc@nvidia.com/ * Rebase on v6.15-rc5 * Add Reviewed-by from Vasant * Rename "vQUEUE" to "HW QUEUE" * Use "offset" and "length" for all mmap-related variables * [iommufd] Use u64 for guest PA * [iommufd] Fix typo in uAPI doc * [iommufd] Rename immap_id to offset * [iommufd] Drop the partial-size mmap support * [iommufd] Do not replace WARN_ON with WARN_ON_ONCE * [iommufd] Use "u64 base_addr" for queue base address * [iommufd] Use u64 base_pfn/num_pfns for immap structure * [iommufd] Correct the size passed in to mtree_alloc_range() * [iommufd] Add IOMMUFD_VIOMMU_FLAG_HW_QUEUE_READS_PA to viommu_ops v3 https://lore.kernel.org/all/cover.1746139811.git.nicolinc@nvidia.com/ * Add Reviewed-by from Baolu, Pranjal, and Alok * Revise kdocs, uAPI docs, and commit logs * Rename "vCMDQ" back to "vQUEUE" for AMD cases * [tegra] Add tegra241_vcmdq_hw_flush_timeout() * [tegra] Rename vsmmu_alloc to alloc_vintf_user * [tegra] Use writel for SID replacement registers * [tegra] Move mmap removal call to vsmmu_destroy op * [tegra] Fix revert in tegra241_vintf_alloc_lvcmdq_user() * [iommufd] Replace "& ~PAGE_MASK" with PAGE_ALIGNED() * [iommufd] Add an object-type "owner" to immap structure * [iommufd] Drop the ictx input in the new for-driver APIs * [iommufd] Add iommufd_vma_ops to keep track of mmap lifecycle * [iommufd] Add viommu-based iommufd_viommu_alloc/destroy_mmap helpers * [iommufd] Rename iommufd_ctx_alloc/free_mmap to _iommufd_alloc/destroy_mmap v2 https://lore.kernel.org/all/cover.1745646960.git.nicolinc@nvidia.com/ * Add Reviewed-by from Jason * [smmu] Fix vsmmu initial value * [smmu] Support impl for hw_info * [tegra] Rename "slot" to "vsid" * [tegra] Update kdocs and commit logs * [tegra] Map/unmap LVCMDQ dynamically * [tegra] Refcount the previous LVCMDQ * [tegra] Return -EEXIST if LVCMDQ exists * [tegra] Simplify VINTF cleanup routine * [tegra] Use vmid and s2_domain in vsmmu * [tegra] Rename "mmap_pgoff" to "immap_id" * [tegra] Add more addr and length validation * [iommufd] Add more narrative to mmap's kdoc * [iommufd] Add iommufd_struct_depend/undepend() * [iommufd] Rename vcmdq_free op to vcmdq_destroy * [iommufd] Fix bug in iommu_copy_struct_to_user() * [iommufd] Drop is_io from iommufd_ctx_alloc_mmap() * [iommufd] Test the queue memory for its contiguity * [iommufd] Return -ENXIO if address or length fails * [iommufd] Do not change @min_last in mock_viommu_alloc() * [iommufd] Generalize TEGRA241_VCMDQ data in core structure * [iommufd] Add selftest coverage for IOMMUFD_CMD_VCMDQ_ALLOC * [iommufd] Add iopt_pin_pages() to prevent queue memory from unmapping v1 https://lore.kernel.org/all/cover.1744353300.git.nicolinc@nvidia.com/ Thanks Nicolin Nicolin Chen (29): iommufd: Report unmapped bytes in the error path of iopt_unmap_iova_range iommufd: Correct virt_id kdoc at struct iommu_vdevice_alloc iommufd/viommu: Explicitly define vdev->virt_id iommu: Use enum iommu_hw_info_type for type in hw_info op iommu: Add iommu_copy_struct_to_user helper iommu: Pass in a driver-level user data structure to viommu_init op iommufd/viommu: Allow driver-specific user data for a vIOMMU object iommufd/selftest: Support user_data in mock_viommu_alloc iommufd/selftest: Add coverage for viommu data iommufd/access: Add internal APIs for HW queue to use iommufd/access: Bypass access->ops->unmap for internal use iommufd/viommu: Add driver-defined vDEVICE support iommufd/viommu: Introduce IOMMUFD_OBJ_HW_QUEUE and its related struct iommufd/viommu: Add IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl iommufd/driver: Add iommufd_hw_queue_depend/undepend() helpers iommufd/selftest: Add coverage for IOMMUFD_CMD_HW_QUEUE_ALLOC iommufd: Add mmap interface iommufd/selftest: Add coverage for the new mmap interface Documentation: userspace-api: iommufd: Update HW QUEUE iommu: Allow an input type in hw_info op iommufd: Allow an input data_type via iommu_hw_info iommufd/selftest: Update hw_info coverage for an input data_type iommu/arm-smmu-v3-iommufd: Add vsmmu_size/type and vsmmu_init impl ops iommu/arm-smmu-v3-iommufd: Add hw_info to impl_ops iommu/tegra241-cmdqv: Use request_threaded_irq iommu/tegra241-cmdqv: Simplify deinit flow in tegra241_cmdqv_remove_vintf() iommu/tegra241-cmdqv: Do not statically map LVCMDQs iommu/tegra241-cmdqv: Add user-space use support iommu/tegra241-cmdqv: Add IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV support drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 25 +- drivers/iommu/iommufd/io_pagetable.h | 5 +- drivers/iommu/iommufd/iommufd_private.h | 46 +- drivers/iommu/iommufd/iommufd_test.h | 20 + include/linux/iommu.h | 50 +- include/linux/iommufd.h | 160 ++++++ include/uapi/linux/iommufd.h | 147 +++++- tools/testing/selftests/iommu/iommufd_utils.h | 89 +++- .../arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 28 +- .../iommu/arm/arm-smmu-v3/tegra241-cmdqv.c | 477 +++++++++++++++++- drivers/iommu/intel/iommu.c | 7 +- drivers/iommu/iommufd/device.c | 87 +++- drivers/iommu/iommufd/driver.c | 82 ++- drivers/iommu/iommufd/io_pagetable.c | 13 +- drivers/iommu/iommufd/main.c | 69 +++ drivers/iommu/iommufd/pages.c | 12 +- drivers/iommu/iommufd/selftest.c | 153 +++++- drivers/iommu/iommufd/viommu.c | 218 +++++++- tools/testing/selftests/iommu/iommufd.c | 141 +++++- .../selftests/iommu/iommufd_fail_nth.c | 15 +- Documentation/userspace-api/iommufd.rst | 12 + 21 files changed, 1745 insertions(+), 111 deletions(-) -- 2.43.0 diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index aa25156e04a3..3fa02c51df9f 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -1045,7 +1045,8 @@ struct arm_vsmmu { }; #if IS_ENABLED(CONFIG_ARM_SMMU_V3_IOMMUFD) -void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type); +void *arm_smmu_hw_info(struct device *dev, u32 *length, + enum iommu_hw_info_type *type); size_t arm_smmu_get_viommu_size(struct device *dev, enum iommu_viommu_type viommu_type); int arm_vsmmu_init(struct iommufd_viommu *viommu, diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c index 00641204efb2..91339f799916 100644 --- a/drivers/iommu/iommufd/viommu.c +++ b/drivers/iommu/iommufd/viommu.c @@ -206,7 +206,11 @@ static void iommufd_hw_queue_destroy_access(struct iommufd_ctx *ictx, struct iommufd_access *access, u64 base_iova, size_t length) { - iommufd_access_unpin_pages(access, base_iova, length); + u64 aligned_iova = PAGE_ALIGN_DOWN(base_iova); + u64 offset = base_iova - aligned_iova; + + iommufd_access_unpin_pages(access, aligned_iova, + PAGE_ALIGN(length + offset)); iommufd_access_detach_internal(access); iommufd_access_destroy_internal(ictx, access); } @@ -239,22 +243,23 @@ static struct iommufd_access * iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd, struct iommufd_viommu *viommu, phys_addr_t *base_pa) { + u64 aligned_iova = PAGE_ALIGN_DOWN(cmd->nesting_parent_iova); + u64 offset = cmd->nesting_parent_iova - aligned_iova; struct iommufd_access *access; struct page **pages; size_t max_npages; size_t length; - u64 offset; size_t i; int rc; - offset = - cmd->nesting_parent_iova - PAGE_ALIGN(cmd->nesting_parent_iova); - /* DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE) */ + /* max_npages = DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE) */ if (check_add_overflow(offset, cmd->length, &length)) return ERR_PTR(-ERANGE); if (check_add_overflow(length, PAGE_SIZE - 1, &length)) return ERR_PTR(-ERANGE); max_npages = length / PAGE_SIZE; + /* length needs to be page aligned too */ + length = max_npages * PAGE_SIZE; /* * Use kvcalloc() to avoid memory fragmentation for a large page array. @@ -274,8 +279,7 @@ iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd, if (rc) goto out_destroy; - rc = iommufd_access_pin_pages(access, cmd->nesting_parent_iova, - cmd->length, pages, 0); + rc = iommufd_access_pin_pages(access, aligned_iova, length, pages, 0); if (rc) goto out_detach; @@ -287,13 +291,12 @@ iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd, goto out_unpin; } - *base_pa = page_to_pfn(pages[0]) << PAGE_SHIFT; + *base_pa = (page_to_pfn(pages[0]) << PAGE_SHIFT) + offset; kfree(pages); return access; out_unpin: - iommufd_access_unpin_pages(access, cmd->nesting_parent_iova, - cmd->length); + iommufd_access_unpin_pages(access, aligned_iova, length); out_detach: iommufd_access_detach_internal(access); out_destroy: diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 9d5b852d5e19..d59d48022a24 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -3104,17 +3104,18 @@ TEST_F(iommufd_viommu, hw_queue) /* Allocate index=0, declare ownership of the iova */ test_cmd_hw_queue_alloc(viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 0, iova, PAGE_SIZE, &hw_queue_id[0]); - /* Fail duplicate */ + /* Fail duplicated index */ test_err_hw_queue_alloc(EEXIST, viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 0, iova, PAGE_SIZE, &hw_queue_id[0]); /* Fail unmap, due to iova ownership */ test_err_ioctl_ioas_unmap(EBUSY, iova, PAGE_SIZE); /* The 2nd page is not pinned, so it can be unmmap */ - test_ioctl_ioas_unmap(iova + PAGE_SIZE, PAGE_SIZE); + test_ioctl_ioas_unmap(iova2, PAGE_SIZE); - /* Allocate index=1 */ + /* Allocate index=1, with an unaligned case */ test_cmd_hw_queue_alloc(viommu_id, IOMMU_HW_QUEUE_TYPE_SELFTEST, 1, - iova, PAGE_SIZE, &hw_queue_id[1]); + iova + PAGE_SIZE / 2, PAGE_SIZE / 2, + &hw_queue_id[1]); /* Fail to destroy, due to dependency */ EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, hw_queue_id[0]));

1 month, 1 week

5
41
0 0

[PATCH v3 0/6] binder: Set up KUnit tests for alloc

by Tiffany Yang

Hello, binder_alloc_selftest provides a robust set of checks for the binder allocator, but it rarely runs because it must hook into a running binder process and block all other binder threads until it completes. The test itself is a good candidate for conversion to KUnit, and it can be further isolated from user processes by using a test-specific lru freelist instead of the global one. This series converts the selftest to KUnit to make it less burdensome to run and to set up a foundation for unit testing future binder_alloc changes. Thanks, Tiffany Tiffany Yang (6): binder: Fix selftest page indexing binder: Store lru freelist in binder_alloc kunit: test: Export kunit_attach_mm() binder: Scaffolding for binder_alloc KUnit tests binder: Convert binder_alloc selftests to KUnit binder: encapsulate individual alloc test cases drivers/android/Kconfig | 15 +- drivers/android/Makefile | 2 +- drivers/android/binder.c | 10 +- drivers/android/binder_alloc.c | 39 +- drivers/android/binder_alloc.h | 14 +- drivers/android/binder_alloc_selftest.c | 306 ----------- drivers/android/binder_internal.h | 4 + drivers/android/tests/.kunitconfig | 3 + drivers/android/tests/Makefile | 3 + drivers/android/tests/binder_alloc_kunit.c | 573 +++++++++++++++++++++ include/kunit/test.h | 12 + lib/kunit/user_alloc.c | 4 +- 12 files changed, 645 insertions(+), 340 deletions(-) delete mode 100644 drivers/android/binder_alloc_selftest.c create mode 100644 drivers/android/tests/.kunitconfig create mode 100644 drivers/android/tests/Makefile create mode 100644 drivers/android/tests/binder_alloc_kunit.c -- 2.50.0.727.gbf7dc18ff4-goog

1 month, 1 week

3
24
0 0

[PATCH v7 0/7] use per-vma locks for /proc/pid/maps reads

by Suren Baghdasaryan

Reading /proc/pid/maps requires read-locking mmap_lock which prevents any other task from concurrently modifying the address space. This guarantees coherent reporting of virtual address ranges, however it can block important updates from happening. Oftentimes /proc/pid/maps readers are low priority monitoring tasks and them blocking high priority tasks results in priority inversion. Locking the entire address space is required to present fully coherent picture of the address space, however even current implementation does not strictly guarantee that by outputting vmas in page-size chunks and dropping mmap_lock in between each chunk. Address space modifications are possible while mmap_lock is dropped and userspace reading the content is expected to deal with possible concurrent address space modifications. Considering these relaxed rules, holding mmap_lock is not strictly needed as long as we can guarantee that a concurrently modified vma is reported either in its original form or after it was modified. This patchset switches from holding mmap_lock while reading /proc/pid/maps to taking per-vma locks as we walk the vma tree. This reduces the contention with tasks modifying the address space because they would have to contend for the same vma as opposed to the entire address space. Previous version of this patchset [1] tried to perform /proc/pid/maps reading under RCU, however its implementation is quite complex and the results are worse than the new version because it still relied on mmap_lock speculation which retries if any part of the address space gets modified. New implementaion is both simpler and results in less contention. Note that similar approach would not work for /proc/pid/smaps reading as it also walks the page table and that's not RCU-safe. Paul McKenney's designed a test [2] to measure mmap/munmap latencies while concurrently reading /proc/pid/maps. The test has a pair of processes scanning /proc/PID/maps, and another process unmapping and remapping 4K pages from a 128MB range of anonymous memory. At the end of each 10 second run, the latency of each mmap() or munmap() operation is measured, and for each run the maximum and mean latency is printed. The map/unmap process is started first, its PID is passed to the scanners, and then the map/unmap process waits until both scanners are running before starting its timed test. The scanners keep scanning until the specified /proc/PID/maps file disappears. The latest results from Paul: Stock mm-unstable, all of the runs had maximum latencies in excess of 0.5 milliseconds, and with 80% of the runs' latencies exceeding a full millisecond, and ranging up beyond 4 full milliseconds. In contrast, 99% of the runs with this patch series applied had maximum latencies of less than 0.5 milliseconds, with the single outlier at only 0.608 milliseconds. From a median-performance (as opposed to maximum-latency) viewpoint, this patch series also looks good, with stock mm weighing in at 11 microseconds and patch series at 6 microseconds, better than a 2x improvement. Before the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.011 0.008 0.521 0.011 0.008 0.552 0.011 0.008 0.590 0.011 0.008 0.660 ... 0.011 0.015 2.987 0.011 0.015 3.038 0.011 0.016 3.431 0.011 0.016 4.707 After the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.006 0.005 0.026 0.006 0.005 0.029 0.006 0.005 0.034 0.006 0.005 0.035 ... 0.006 0.006 0.421 0.006 0.006 0.423 0.006 0.006 0.439 0.006 0.006 0.608 The patchset also adds a number of tests to check for /proc/pid/maps data coherency. They are designed to detect any unexpected data tearing while performing some common address space modifications (vma split, resize and remap). Even before these changes, reading /proc/pid/maps might have inconsistent data because the file is read page-by-page with mmap_lock being dropped between the pages. An example of user-visible inconsistency can be that the same vma is printed twice: once before it was modified and then after the modifications. For example if vma was extended, it might be found and reported twice. What is not expected is to see a gap where there should have been a vma both before and after modification. This patchset increases the chances of such tearing, therefore it's even more important now to test for unexpected inconsistencies. In [3] Lorenzo identified the following possible vma merging/splitting scenarios: Merges with changes to existing vmas: 1 Merge both - mapping a vma over another one and between two vmas which can be merged after this replacement; 2. Merge left full - mapping a vma at the end of an existing one and completely over its right neighbor; 3. Merge left partial - mapping a vma at the end of an existing one and partially over its right neighbor; 4. Merge right full - mapping a vma before the start of an existing one and completely over its left neighbor; 5. Merge right partial - mapping a vma before the start of an existing one and partially over its left neighbor; Merges without changes to existing vmas: 6. Merge both - mapping a vma into a gap between two vmas which can be merged after the insertion; 7. Merge left - mapping a vma at the end of an existing one; 8. Merge right - mapping a vma before the start end of an existing one; Splits 9. Split with new vma at the lower address; 10. Split with new vma at the higher address; If such merges or splits happen concurrently with the /proc/maps reading we might report a vma twice, once before the modification and once after it is modified: Case 1 might report overwritten and previous vma along with the final merged vma; Case 2 might report previous and the final merged vma; Case 3 might cause us to retry once we detect the temporary gap caused by shrinking of the right neighbor; Case 4 might report overritten and the final merged vma; Case 5 might cause us to retry once we detect the temporary gap caused by shrinking of the left neighbor; Case 6 might report previous vma and the gap along with the final marged vma; Case 7 might report previous and the final merged vma; Case 8 might report the original gap and the final merged vma covering the gap; Case 9 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma start; Case 10 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma end; In all these cases the retry mechanism prevents us from reporting possible temporary gaps. Changes since v6 [4]: - Updated patch 7/8 changelog, per Lorenzo Stoakes - Added comments, per Lorenzo Stoakes - Added Reviewed-by, per Lorenzo Stoakes and Liam Howlett - Replaced iter with vmi, per Lorenzo Stoakes - Renamed from lock_vma_under_mmap_lock() to lock_next_vma_under_mmap_lock(), per Lorenzo Stoakes - Renamed lock_next_vma() parameter from addr to from_addr - Renamed labels in lock_next_vma() to reflect fallback cases, per Lorenzo Stoakes - Handle vma_start_read_locked() failure inside lock_next_vma_under_mmap_lock() and added fallback_to_mmap_lock() for that, per Vlastimil Babka - Added missing vma_iter_init() after re-entering rcu read section inside lock_next_vma(), per Vlastimil Babka - Replaced vma_iter_init() with vma_iter_set(), per Liam Howlett - Removed the last patch converting PROCMAP_QUERY to use per-vma locks. That patch will be posted separately, per David Hildenbrand, Vlastimil Babka and Liam Howlett - Updated performance numbers, per Paul E. McKenney !!! NOTES FOR APPLYING THE PATCHSET !!! Applies cleanly over mm-unstable after reverting v6 version of this patchset (from 2771a4b86aa1 to a20b00f7cf33 in mm-unstable). [1] https://lore.kernel.org/all/20250418174959.1431962-1-surenb@google.com/ [2] https://github.com/paulmckrcu/proc-mmap_sem-test [3] https://lore.kernel.org/all/e1863f40-39ab-4e5b-984a-c48765ffde1c@lucifer.lo… [4] https://lore.kernel.org/all/20250704060727.724817-1-surenb@google.com/ Suren Baghdasaryan (7): selftests/proc: add /proc/pid/maps tearing from vma split test selftests/proc: extend /proc/pid/maps tearing test to include vma resizing selftests/proc: extend /proc/pid/maps tearing test to include vma remapping selftests/proc: test PROCMAP_QUERY ioctl while vma is concurrently modified selftests/proc: add verbose more for tests to facilitate debugging fs/proc/task_mmu: remove conversion of seq_file position to unsigned fs/proc/task_mmu: read proc/pid/maps under per-vma lock fs/proc/internal.h | 5 + fs/proc/task_mmu.c | 155 +++- include/linux/mmap_lock.h | 11 + mm/madvise.c | 3 +- mm/mmap_lock.c | 93 ++ tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/proc-maps-race.c | 829 ++++++++++++++++++ 8 files changed, 1082 insertions(+), 16 deletions(-) create mode 100644 tools/testing/selftests/proc/proc-maps-race.c -- 2.50.0.727.gbf7dc18ff4-goog

1 month, 1 week

5
19
0 0

[PATCH 0/2] bpf, arm64: relax constraint in BPF JIT compiler

by Alexis Lothoré (eBPF Foundation)

Hello, this series follows up on the one introducing 9+ args for tracing programs [1]. It has been observed with this series that there are cases for which we can not identify accurately the location of the target function arguments to prepare correctly the corresponding BPF trampoline. This is the case for example if: - the function consumes a struct variable _by value_ - it is passed on the stack (no more register available for it) - it has some __packed__ or __aligned(X)__ attribute As a consequence, a small restrictive check has been added to the ARM64 side, highlighting that other arch supporting 9+ args in BPF trampolines are already suffering from the same issue. After a bit of discussions and attempts, the chosen solution is, rather than applying the same constraint to all JIT compilers, to prevent such function from being encoded at all in BTF info([2]). As the pahole side is closed to be integrated, we can now remove the restrictive check from kernel side. [1] https://lore.kernel.org/bpf/20250527-many_args_arm64-v3-0-3faf7bb8e4a2@boot… [2] https://lore.kernel.org/bpf/20250707-btf_skip_structs_on_stack-v3-0-29569e0… Signed-off-by: Alexis Lothoré (eBPF Foundation) <alexis.lothore(a)bootlin.com> --- Alexis Lothoré (eBPF Foundation) (2): bpf, arm64: remove structs on stack constraint selftests/bpf: enable tracing_struct tests for arm64 arch/arm64/net/bpf_jit_comp.c | 5 ----- tools/testing/selftests/bpf/DENYLIST.aarch64 | 1 - 2 files changed, 6 deletions(-) --- base-commit: 8da1e37fc84868b50ba6a7cdf082aa3b0d11e006 change-id: 20250708-arm64_relax_jit_comp-e8889647d8d2 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

1 month, 1 week

5
8
0 0

[PATCH net-next v7 0/3] selftest: net: Add selftest for netpoll

by Breno Leitao

I am submitting a new selftest for the netpoll subsystem specifically targeting the case where the RX is polling in the TX path, which is a case that we don't have any test in the tree today. This is done when netpoll_poll_dev() called, and this test creates a scenario when that is probably. The test does the following: 1) Configuring a single RX/TX queue to increase contention on the interface. 2) Generating background traffic to saturate the network, mimicking real-world congestion. 3) Sending netconsole messages to trigger netpoll polling and monitor its behavior. 4) Using dynamic netconsole targets via configfs, with the ability to delete and recreate targets during the test. 5) Running bpftrace in parallel to verify that netpoll_poll_dev() is called when expected. If it is called, then the test passes, otherwise the test is marked as skipped. In order to achieve it, I stole Jakub's bpftrace helper from [1], and did some small changes that I found useful to use the helper. So, this patchset basically contains: 1) The code stolen from Jakub 2) Improvements on bpftrace() helper 3) The selftest itself Link: https://lore.kernel.org/all/20250421222827.283737-22-kuba@kernel.org/ [1] --- Changes in v7: - Rebased on top of net-next - Using `ethtool -l` json option instead of parsing it manually. - Link to v6: https://lore.kernel.org/r/20250711-netpoll_test-v6-0-130465f286a8@debian.org Changes in v6: - Remove the network toggled (Jakub) - Set ringsize and queue size (Jakub) - Some other general improvements (Jakub) - Link to v5: https://lore.kernel.org/r/20250709-netpoll_test-v5-0-b3737895affe@debian.org Changes in v5: - Rebased on top of net-next. - Calling bpftrace_stop using the defer helper. (Willem) - Link to v4: https://lore.kernel.org/r/20250702-netpoll_test-v4-0-cec227e85639@debian.org Changes in v4: - Make the test XFail if it doesn't hit the function we are looking for - Toggle the interface while the traffic is flowing. - Bumped the number of messages from 10 to 40 per iterations. * This is hitting ~15 times per run on my vng test. - Decreased the time from 15 seconds to 10 seconds, given that if it didn't hit the function in 10 seconds, 5 seconds extra will not help. - Link to v3: https://lore.kernel.org/r/20250627-netpoll_test-v3-0-575bd200c8a9@debian.org Changes in v3: - Make pylint happy (Simon) - Remove the unnecessary patch in bpftrace to raise an exception when it fails. (Jakub) - Improved the bpftrace code (Willem) - Stop sending messages if bpftrace is not alive anymore. - Link to v2: https://lore.kernel.org/r/20250625-netpoll_test-v2-0-47d27775222c@debian.org Changes in v2: - Stole Jakub's helper to run bpftrace - Removed the DEBUG option and moved logs to logging - Change the code to have a higher chance of calling netpoll_poll_dev(). In my current configuration, it is hitting multiple times during the test. - Save and restore TX/RX queue size (Jakub) - Link to v1: https://lore.kernel.org/r/20250620-netpoll_test-v1-1-5068832f72fc@debian.org --- Breno Leitao (2): selftests: drv-net: Strip '@' prefix from bpftrace map keys selftests: net: add netpoll basic functionality test Jakub Kicinski (1): selftests: drv-net: add helper/wrapper for bpftrace tools/testing/selftests/drivers/net/Makefile | 1 + .../selftests/drivers/net/lib/py/__init__.py | 4 +- .../testing/selftests/drivers/net/netpoll_basic.py | 396 +++++++++++++++++++++ tools/testing/selftests/net/lib/py/utils.py | 35 ++ 4 files changed, 434 insertions(+), 2 deletions(-) --- base-commit: b06c4311711c57c5e558bd29824b08f0a6e2a155 change-id: 20250612-netpoll_test-a1324d2057c8 Best regards, -- Breno Leitao <leitao(a)debian.org>

1 month, 1 week

2
4
0 0

[PATCH v2 4/4] selftests/rseq: Add test for mm_cid compaction

by Gabriele Monaco

A task in the kernel (task_mm_cid_work) runs somewhat periodically to compact the mm_cid for each process. Add a test to validate that it runs correctly and timely. The test spawns 1 thread pinned to each CPU, then each thread, including the main one, runs in short bursts for some time. During this period, the mm_cids should be spanning all numbers between 0 and nproc. At the end of this phase, a thread with high enough mm_cid (>= nproc/2) is selected to be the new leader, all other threads terminate. After some time, the only running thread should see 0 as mm_cid, if that doesn't happen, the compaction mechanism didn't work and the test fails. The test never fails if only 1 core is available, in which case, we cannot test anything as the only available mm_cid is 0. Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Gabriele Monaco <gmonaco(a)redhat.com> --- tools/testing/selftests/rseq/.gitignore | 1 + tools/testing/selftests/rseq/Makefile | 2 +- .../selftests/rseq/mm_cid_compaction_test.c | 204 ++++++++++++++++++ 3 files changed, 206 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/rseq/mm_cid_compaction_test.c diff --git a/tools/testing/selftests/rseq/.gitignore b/tools/testing/selftests/rseq/.gitignore index 0fda241fa62b0..b3920c59bf401 100644 --- a/tools/testing/selftests/rseq/.gitignore +++ b/tools/testing/selftests/rseq/.gitignore @@ -3,6 +3,7 @@ basic_percpu_ops_test basic_percpu_ops_mm_cid_test basic_test basic_rseq_op_test +mm_cid_compaction_test param_test param_test_benchmark param_test_compare_twice diff --git a/tools/testing/selftests/rseq/Makefile b/tools/testing/selftests/rseq/Makefile index 0d0a5fae59547..bc4d940f66d40 100644 --- a/tools/testing/selftests/rseq/Makefile +++ b/tools/testing/selftests/rseq/Makefile @@ -17,7 +17,7 @@ OVERRIDE_TARGETS = 1 TEST_GEN_PROGS = basic_test basic_percpu_ops_test basic_percpu_ops_mm_cid_test param_test \ param_test_benchmark param_test_compare_twice param_test_mm_cid \ param_test_mm_cid_benchmark param_test_mm_cid_compare_twice \ - syscall_errors_test + syscall_errors_test mm_cid_compaction_test TEST_GEN_PROGS_EXTENDED = librseq.so diff --git a/tools/testing/selftests/rseq/mm_cid_compaction_test.c b/tools/testing/selftests/rseq/mm_cid_compaction_test.c new file mode 100644 index 0000000000000..d13623625f5a9 --- /dev/null +++ b/tools/testing/selftests/rseq/mm_cid_compaction_test.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: LGPL-2.1 +#define _GNU_SOURCE +#include <assert.h> +#include <pthread.h> +#include <sched.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stddef.h> + +#include "../kselftest.h" +#include "rseq.h" + +#define VERBOSE 0 +#define printf_verbose(fmt, ...) \ + do { \ + if (VERBOSE) \ + printf(fmt, ##__VA_ARGS__); \ + } while (0) + +/* 50 ms */ +#define RUNNER_PERIOD 50000 +/* + * Number of runs before we terminate or get the token. + * The number is slowly increasing with the number of CPUs as the compaction + * process can take longer on larger systems. This is an arbitrary value. + */ +#define THREAD_RUNS (3 + args->num_cpus/8) + +/* + * Number of times we check that the mm_cid were compacted. + * Checks are repeated every RUNNER_PERIOD. + */ +#define MM_CID_COMPACT_TIMEOUT 10 + +struct thread_args { + int cpu; + int num_cpus; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + pthread_t *tinfo; + struct thread_args *args_head; +}; + +static void __noreturn *thread_runner(void *arg) +{ + struct thread_args *args = arg; + int i, ret, curr_mm_cid; + cpu_set_t cpumask; + + CPU_ZERO(&cpumask); + CPU_SET(args->cpu, &cpumask); + ret = pthread_setaffinity_np(pthread_self(), sizeof(cpumask), &cpumask); + if (ret) { + errno = ret; + perror("Error: failed to set affinity"); + abort(); + } + pthread_barrier_wait(args->barrier); + + for (i = 0; i < THREAD_RUNS; i++) + usleep(RUNNER_PERIOD); + curr_mm_cid = rseq_current_mm_cid(); + /* + * We select one thread with high enough mm_cid to be the new leader. + * All other threads (including the main thread) will terminate. + * After some time, the mm_cid of the only remaining thread should + * converge to 0, if not, the test fails. + */ + if (curr_mm_cid >= args->num_cpus / 2 && + !pthread_mutex_trylock(args->token)) { + printf_verbose( + "cpu%d has mm_cid=%d and will be the new leader.\n", + sched_getcpu(), curr_mm_cid); + for (i = 0; i < args->num_cpus; i++) { + if (args->tinfo[i] == pthread_self()) + continue; + ret = pthread_join(args->tinfo[i], NULL); + if (ret) { + errno = ret; + perror("Error: failed to join thread"); + abort(); + } + } + pthread_barrier_destroy(args->barrier); + free(args->tinfo); + free(args->token); + free(args->barrier); + free(args->args_head); + + for (i = 0; i < MM_CID_COMPACT_TIMEOUT; i++) { + curr_mm_cid = rseq_current_mm_cid(); + printf_verbose("run %d: mm_cid=%d on cpu%d.\n", i, + curr_mm_cid, sched_getcpu()); + if (curr_mm_cid == 0) + exit(EXIT_SUCCESS); + usleep(RUNNER_PERIOD); + } + exit(EXIT_FAILURE); + } + printf_verbose("cpu%d has mm_cid=%d and is going to terminate.\n", + sched_getcpu(), curr_mm_cid); + pthread_exit(NULL); +} + +int test_mm_cid_compaction(void) +{ + cpu_set_t affinity; + int i, j, ret = 0, num_threads; + pthread_t *tinfo; + pthread_mutex_t *token; + pthread_barrier_t *barrier; + struct thread_args *args; + + sched_getaffinity(0, sizeof(affinity), &affinity); + num_threads = CPU_COUNT(&affinity); + tinfo = calloc(num_threads, sizeof(*tinfo)); + if (!tinfo) { + perror("Error: failed to allocate tinfo"); + return -1; + } + args = calloc(num_threads, sizeof(*args)); + if (!args) { + perror("Error: failed to allocate args"); + ret = -1; + goto out_free_tinfo; + } + token = malloc(sizeof(*token)); + if (!token) { + perror("Error: failed to allocate token"); + ret = -1; + goto out_free_args; + } + barrier = malloc(sizeof(*barrier)); + if (!barrier) { + perror("Error: failed to allocate barrier"); + ret = -1; + goto out_free_token; + } + if (num_threads == 1) { + fprintf(stderr, "Cannot test on a single cpu. " + "Skipping mm_cid_compaction test.\n"); + /* only skipping the test, this is not a failure */ + goto out_free_barrier; + } + pthread_mutex_init(token, NULL); + ret = pthread_barrier_init(barrier, NULL, num_threads); + if (ret) { + errno = ret; + perror("Error: failed to initialise barrier"); + goto out_free_barrier; + } + for (i = 0, j = 0; i < CPU_SETSIZE && j < num_threads; i++) { + if (!CPU_ISSET(i, &affinity)) + continue; + args[j].num_cpus = num_threads; + args[j].tinfo = tinfo; + args[j].token = token; + args[j].barrier = barrier; + args[j].cpu = i; + args[j].args_head = args; + if (!j) { + /* The first thread is the main one */ + tinfo[0] = pthread_self(); + ++j; + continue; + } + ret = pthread_create(&tinfo[j], NULL, thread_runner, &args[j]); + if (ret) { + errno = ret; + perror("Error: failed to create thread"); + abort(); + } + ++j; + } + printf_verbose("Started %d threads.\n", num_threads); + + /* Also main thread will terminate if it is not selected as leader */ + thread_runner(&args[0]); + + /* only reached in case of errors */ +out_free_barrier: + free(barrier); +out_free_token: + free(token); +out_free_args: + free(args); +out_free_tinfo: + free(tinfo); + + return ret; +} + +int main(int argc, char **argv) +{ + if (!rseq_mm_cid_available()) { + fprintf(stderr, "Error: rseq_mm_cid unavailable\n"); + return -1; + } + if (test_mm_cid_compaction()) + return -1; + return 0; +} -- 2.50.1

1 month, 1 week

1
0
0 0

[PATCH net-next V5 0/5] net: netdevsim: hook in XDP handling

by Mohsin Bashir

This patch series add tests to validate XDP native support for PASS, DROP, ABORT, and TX actions, as well as headroom and tailroom adjustment. For adjustment tests, validate support for both the extension and shrinking cases across various packet sizes and offset values. The pass criteria for head/tail adjustment tests require that at-least one adjustment value works for at-least one packet size. This ensure that the variability in maximum supported head/tail adjustment offset across different drivers is being incorporated. The results reported in this series are based on fbnic. However, the series is tested against multiple other drivers including netdevism. Note: The XDP support for fbnic will be added later. --- Change-log: V5: - Fix warning caused by rcu_dereference() in p1 - Fix checkpatch warnings with P3, P4, and P5 V4: https://lore.kernel.org/netdev/20250714210352.1115230-1-mohsin.bashr@gmail.… V3: https://lore.kernel.org/netdev/20250712002648.2385849-1-mohsin.bashr@gmail.… V2: https://lore.kernel.org/netdev/20250710184351.63797-1-mohsin.bashr@gmail.com V1: https://lore.kernel.org/netdev/20250709173707.3177206-1-mohsin.bashr@gmail.… Jakub Kicinski (1): net: netdevsim: hook in XDP handling Mohsin Bashir (4): selftests: drv-net: Test XDP_PASS/DROP support selftests: drv-net: Test XDP_TX support selftests: drv-net: Test tail-adjustment support selftests: drv-net: Test head-adjustment support drivers/net/netdevsim/netdev.c | 19 +- tools/testing/selftests/drivers/net/Makefile | 1 + tools/testing/selftests/drivers/net/xdp.py | 656 ++++++++++++++++++ .../selftests/net/lib/xdp_native.bpf.c | 540 ++++++++++++++ 4 files changed, 1215 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/xdp.py create mode 100644 tools/testing/selftests/net/lib/xdp_native.bpf.c -- 2.47.1

1 month, 1 week

2
6
0 0

[PATCH v6 0/8] use per-vma locks for /proc/pid/maps reads and PROCMAP_QUERY

by Suren Baghdasaryan

Reading /proc/pid/maps requires read-locking mmap_lock which prevents any other task from concurrently modifying the address space. This guarantees coherent reporting of virtual address ranges, however it can block important updates from happening. Oftentimes /proc/pid/maps readers are low priority monitoring tasks and them blocking high priority tasks results in priority inversion. Locking the entire address space is required to present fully coherent picture of the address space, however even current implementation does not strictly guarantee that by outputting vmas in page-size chunks and dropping mmap_lock in between each chunk. Address space modifications are possible while mmap_lock is dropped and userspace reading the content is expected to deal with possible concurrent address space modifications. Considering these relaxed rules, holding mmap_lock is not strictly needed as long as we can guarantee that a concurrently modified vma is reported either in its original form or after it was modified. This patchset switches from holding mmap_lock while reading /proc/pid/maps to taking per-vma locks as we walk the vma tree. This reduces the contention with tasks modifying the address space because they would have to contend for the same vma as opposed to the entire address space. Same is done for PROCMAP_QUERY ioctl which locks only the vma that fell into the requested range instead of the entire address space. Previous version of this patchset [1] tried to perform /proc/pid/maps reading under RCU, however its implementation is quite complex and the results are worse than the new version because it still relied on mmap_lock speculation which retries if any part of the address space gets modified. New implementaion is both simpler and results in less contention. Note that similar approach would not work for /proc/pid/smaps reading as it also walks the page table and that's not RCU-safe. Paul McKenney's designed a test [2] to measure mmap/munmap latencies while concurrently reading /proc/pid/maps. The test has a pair of processes scanning /proc/PID/maps, and another process unmapping and remapping 4K pages from a 128MB range of anonymous memory. At the end of each 10 second run, the latency of each mmap() or munmap() operation is measured, and for each run the maximum and mean latency is printed. The map/unmap process is started first, its PID is passed to the scanners, and then the map/unmap process waits until both scanners are running before starting its timed test. The scanners keep scanning until the specified /proc/PID/maps file disappears. This test registered close to 10x improvement in update latencies: Before the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.011 0.008 0.455 0.011 0.008 0.472 0.011 0.008 0.535 0.011 0.009 0.545 ... 0.011 0.014 2.875 0.011 0.014 2.913 0.011 0.014 3.007 0.011 0.015 3.018 After the change: ./run-proc-vs-map.sh --nsamples 100 --rawdata -- --busyduration 2 0.006 0.005 0.036 0.006 0.005 0.039 0.006 0.005 0.039 0.006 0.005 0.039 ... 0.006 0.006 0.403 0.006 0.006 0.474 0.006 0.006 0.479 0.006 0.006 0.498 The patchset also adds a number of tests to check for /proc/pid/maps data coherency. They are designed to detect any unexpected data tearing while performing some common address space modifications (vma split, resize and remap). Even before these changes, reading /proc/pid/maps might have inconsistent data because the file is read page-by-page with mmap_lock being dropped between the pages. An example of user-visible inconsistency can be that the same vma is printed twice: once before it was modified and then after the modifications. For example if vma was extended, it might be found and reported twice. What is not expected is to see a gap where there should have been a vma both before and after modification. This patchset increases the chances of such tearing, therefore it's even more important now to test for unexpected inconsistencies. In [3] Lorenzo identified the following possible vma merging/splitting scenarios: Merges with changes to existing vmas: 1 Merge both - mapping a vma over another one and between two vmas which can be merged after this replacement; 2. Merge left full - mapping a vma at the end of an existing one and completely over its right neighbor; 3. Merge left partial - mapping a vma at the end of an existing one and partially over its right neighbor; 4. Merge right full - mapping a vma before the start of an existing one and completely over its left neighbor; 5. Merge right partial - mapping a vma before the start of an existing one and partially over its left neighbor; Merges without changes to existing vmas: 6. Merge both - mapping a vma into a gap between two vmas which can be merged after the insertion; 7. Merge left - mapping a vma at the end of an existing one; 8. Merge right - mapping a vma before the start end of an existing one; Splits 9. Split with new vma at the lower address; 10. Split with new vma at the higher address; If such merges or splits happen concurrently with the /proc/maps reading we might report a vma twice, once before the modification and once after it is modified: Case 1 might report overwritten and previous vma along with the final merged vma; Case 2 might report previous and the final merged vma; Case 3 might cause us to retry once we detect the temporary gap caused by shrinking of the right neighbor; Case 4 might report overritten and the final merged vma; Case 5 might cause us to retry once we detect the temporary gap caused by shrinking of the left neighbor; Case 6 might report previous vma and the gap along with the final marged vma; Case 7 might report previous and the final merged vma; Case 8 might report the original gap and the final merged vma covering the gap; Case 9 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma start; Case 10 might cause us to retry once we detect the temporary gap caused by shrinking of the original vma at the vma end; In all these cases the retry mechanism prevents us from reporting possible temporary gaps. Changes since v5 [4]: - Made /proc/pid/maps tearing test a separate selftest, per Alexey Dobriyan - Changed asserts with or'ed conditions into separate ones, per Alexey Dobriyan - Added a small cleanup patch [6/8] to avoid unnecessary seq_file position type casting - Removed unnecessary is_sentinel_pos() helper - Changed titles to use fs/proc/task_mmu instead of mm/maps prefix, per David Hildenbrand - Included Lorenzo's fix for mmap lock assertion in anon_vma_name() - Reworked the last patch to avoid allocation in the rcu read section, which replaces Jeongjun Park's fix !!! NOTES FOR APPLYING THE PATCHSET !!! Applies cleanly over mm-unstable after reverting old version with fixes. The following patches should be reverted before applyng this patchset: b33ce1be8a40 ("selftests/proc: add /proc/pid/maps tearing from vma split test") b538e0580fd6 ("selftests/proc: extend /proc/pid/maps tearing test to include vma resizing") 4996b4409cc6 ("selftests/proc: extend /proc/pid/maps tearing test to include vma remapping") c39471f78d5e ("selftests/proc: test PROCMAP_QUERY ioctl while vma is concurrently modified") 487570f548f3 ("selftests/proc: add verbose more for tests to facilitate debugging") e1ba4969cba1 ("mm/maps: read proc/pid/maps under per-vma lock") ecb110179e77 ("mm/madvise: fixup stray mmap lock assert in anon_vma_name()") 6772c457a865 ("fs/proc/task_mmu:: execute PROCMAP_QUERY ioctl under per-vma locks") d5c67bb2c5fb ("mm/maps: move kmalloc() call location in do_procmap_query() out of RCU critical section") [1] https://lore.kernel.org/all/20250418174959.1431962-1-surenb@google.com/ [2] https://github.com/paulmckrcu/proc-mmap_sem-test [3] https://lore.kernel.org/all/e1863f40-39ab-4e5b-984a-c48765ffde1c@lucifer.lo… [4] https://lore.kernel.org/all/20250624193359.3865351-1-surenb@google.com/ Suren Baghdasaryan (8): selftests/proc: add /proc/pid/maps tearing from vma split test selftests/proc: extend /proc/pid/maps tearing test to include vma resizing selftests/proc: extend /proc/pid/maps tearing test to include vma remapping selftests/proc: test PROCMAP_QUERY ioctl while vma is concurrently modified selftests/proc: add verbose more for tests to facilitate debugging fs/proc/task_mmu: remove conversion of seq_file position to unsigned fs/proc/task_mmu: read proc/pid/maps under per-vma lock fs/proc/task_mmu: execute PROCMAP_QUERY ioctl under per-vma locks fs/proc/internal.h | 5 + fs/proc/task_mmu.c | 188 +++- include/linux/mmap_lock.h | 11 + mm/madvise.c | 3 +- mm/mmap_lock.c | 88 ++ tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/proc-maps-race.c | 829 ++++++++++++++++++ 8 files changed, 1098 insertions(+), 28 deletions(-) create mode 100644 tools/testing/selftests/proc/proc-maps-race.c -- 2.50.0.727.gbf7dc18ff4-goog

1 month, 1 week

6
46
0 0

[PATCH v5] selftests/mm: add process_madvise() tests

by wang lian

Add tests for process_madvise(), focusing on verifying behavior under various conditions including valid usage and error cases. Signed-off-by: wang lian <lianux.mm(a)gmail.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Suggested-by: Zi Yan <ziy(a)nvidia.com> Suggested-by: Mark Brown <broonie(a)kernel.org> Acked-by: SeongJae Park <sj(a)kernel.org> --- Changelog v5: - Refactor the remote_collapse test to concentrate on its primary goal confirming the successful remote invocation of process_madvise() on a child process. - Split the validation logic for invalid pidfds out of the remote test and into two new (`exited_process_pidfd` and `bad_pidfd`). - Based mm-new branch, can ensure clean application Changelog v4: https://lore.kernel.org/lkml/20250710112249.58722-1-lianux.mm@gmail.com/ - Refine resource cleanup logic in test teardown to be more robust. - Improve remote_collapse test to correctly handle different THP (Transparent Huge Page) policies ('always', 'madvise', 'never'), including handling race conditions with khugepaged. - Resolve build errors Changelog v3: https://lore.kernel.org/lkml/20250703044326.65061-1-lianux.mm@gmail.com/ - Rebased onto the latest mm-stable branch to ensure clean application. - Refactor common signal handling logic into vm_util to reduce code duplication. - Improve test robustness and diagnostics based on community feedback. - Address minor code style and script corrections. Changelog v2: https://lore.kernel.org/lkml/20250630140957.4000-1-lianux.mm@gmail.com/ - Drop MADV_DONTNEED tests based on feedback. - Focus solely on process_madvise() syscall. - Improve error handling and structure. - Add future-proof flag test. - Style and comment cleanups. -V1: https://lore.kernel.org/lkml/20250621133003.4733-1-lianux.mm@gmail.com/ tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/process_madv.c | 304 ++++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + 4 files changed, 311 insertions(+) create mode 100644 tools/testing/selftests/mm/process_madv.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index f2dafa0b700b..e7b23a8a05fe 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -21,6 +21,7 @@ on-fault-limit transhuge-stress pagemap_ioctl pfnmap +process_madv *.tmp* protection_keys protection_keys_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ae6f994d3add..d13b3cef2a2b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -85,6 +85,7 @@ TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..249e2ed8dfe9 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +FIXTURE(process_madvise) +{ + unsigned long page_size; + pid_t child_pid; + int pidfd; +}; + +FIXTURE_SETUP(process_madvise) +{ + self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); + self->pidfd = PIDFD_SELF; + self->child_pid = -1; +}; + +FIXTURE_TEARDOWN_PARENT(process_madvise) +{ + if (self->child_pid > 0) { + kill(self->child_pid, SIGKILL); + waitpid(self->child_pid, NULL, 0); + } +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * This test uses PIDFD_SELF to target the current process. The main + * goal is to verify the basic behavior of process_madvise() with + * a vector of non-contiguous memory ranges, not its cross-process + * capabilities. + */ +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = self->page_size; + const int madvise_pages = 4; + struct iovec vec[madvise_pages]; + int pidfd = self->pidfd; + ssize_t ret; + char *map; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(pidfd, vec, madvise_pages, MADV_DONTNEED, 0); + if (ret == -1 && errno == EPERM) + SKIP(return, + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + SKIP(return, + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, '\0'); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + for (int i = 0; i < pagesize; i++) + ASSERT_EQ(unadvised_page[i], 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +/* + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, + * focus on process_madv remote result, only check addresses and lengths. + * The correctness of the MADV_COLLAPSE can be found in the relevant test examples in khugepaged. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = self->page_size; + int pidfd; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = default_huge_page_size(); + if (huge_page_size <= 0) + SKIP(return, "Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + self->child_pid = fork(); + ASSERT_NE(self->child_pid, -1); + + if (self->child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(self->child_pid, NULL, 0); + SKIP(return, "Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + self->child_pid = info.pid; + + pidfd = syscall(__NR_pidfd_open, self->child_pid, 0); + ASSERT_GE(pidfd, 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + if (ret == -1) { + if (errno == EINVAL) + SKIP(return, "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + SKIP(return, + "No process_madvise() permissions, try running as root.\n"); + goto cleanup; + } + + ASSERT_EQ(ret, huge_page_size); + +cleanup: + /* Cleanup */ + kill(self->child_pid, SIGKILL); + waitpid(self->child_pid, NULL, 0); + if (pidfd >= 0) + close(pidfd); +} + +/* + * Test process_madvise() with a pidfd for a process that has already + * exited to ensure correct error handling. + */ +TEST_F(process_madvise, exited_process_pidfd) +{ + struct iovec vec; + ssize_t ret; + int pidfd; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + self->child_pid = fork(); + ASSERT_NE(self->child_pid, -1); + + if (self->child_pid == 0) + exit(0); + + pidfd = syscall(__NR_pidfd_open, self->child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(self->child_pid, NULL, 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); + close(pidfd); +} + +/* + * Test process_madvise() with bad pidfds to ensure correct error + * handling. + */ +TEST_F(process_madvise, bad_pidfd) +{ + struct iovec vec; + ssize_t ret; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); +} + +/* + * Test process_madvise() with an invalid flag value. Currently, only a flag + * value of 0 is supported. This test is reserved for the future, e.g., if + * synchronous flags are added. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = self->page_size; + unsigned int invalid_flag; + int pidfd = self->pidfd; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + SKIP(return, "mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index a38c984103ce..471e539d82b8 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -65,6 +65,8 @@ separated by spaces: test pagemap_scan IOCTL - pfnmap tests for VM_PFNMAP handling +- process_madv + test for process_madv - cow test copy-on-write semantics - thp @@ -425,6 +427,9 @@ CATEGORY="madv_guard" run_test ./guard-regions # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate +# PROCESS_MADV test +CATEGORY="process_madv" run_test ./process_madv + CATEGORY="vma_merge" run_test ./merge if [ -x ./memfd_secret ] -- 2.43.0

1 month, 1 week

2
4
0 0

[PATCH net-next v12 00/10] tun: Introduce virtio-net hashing feature

by Akihiko Odaki

NOTE: I'm leaving Daynix Computing Ltd., for which I worked on this patch series, by the end of this month. While net-next is closed, this is the last chance for me to send another version so let me send the local changes now. Please contact Yuri Benditovich, who is CCed on this email, for anything about this series. virtio-net have two usage of hashes: one is RSS and another is hash reporting. Conventionally the hash calculation was done by the VMM. However, computing the hash after the queue was chosen defeats the purpose of RSS. Another approach is to use eBPF steering program. This approach has another downside: it cannot report the calculated hash due to the restrictive nature of eBPF. Introduce the code to compute hashes to the kernel in order to overcome thse challenges. An alternative solution is to extend the eBPF steering program so that it will be able to report to the userspace, but it is based on context rewrites, which is in feature freeze. We can adopt kfuncs, but they will not be UAPIs. We opt to ioctl to align with other relevant UAPIs (KVM and vhost_net). The patches for QEMU to use this new feature was submitted as RFC and is available at: https://patchew.org/QEMU/20250530-hash-v5-0-343d7d7a8200@daynix.com/ This work was presented at LPC 2024: https://lpc.events/event/18/contributions/1963/ V1 -> V2: Changed to introduce a new BPF program type. Signed-off-by: Akihiko Odaki <akihiko.odaki(a)daynix.com> --- Changes in v12: - Updated tools/testing/selftests/net/config. - Split TUNSETVNETHASH. - Link to v11: https://lore.kernel.org/r/20250317-rss-v11-0-4cacca92f31f@daynix.com Changes in v11: - Added the missing code to free vnet_hash in patch "tap: Introduce virtio-net hash feature". - Link to v10: https://lore.kernel.org/r/20250313-rss-v10-0-3185d73a9af0@daynix.com Changes in v10: - Split common code and TUN/TAP-specific code into separate patches. - Reverted a spurious style change in patch "tun: Introduce virtio-net hash feature". - Added a comment explaining disable_ipv6 in tests. - Used AF_PACKET for patch "selftest: tun: Add tests for virtio-net hashing". I also added the usage of FIXTURE_VARIANT() as the testing function now needs access to more variant-specific variables. - Corrected the message of patch "selftest: tun: Add tests for virtio-net hashing"; it mentioned validation of configuration but it is not scope of this patch. - Expanded the description of patch "selftest: tun: Add tests for virtio-net hashing". - Added patch "tun: Allow steering eBPF program to fall back". - Changed to handle TUNGETVNETHASHCAP before taking the rtnl lock. - Removed redundant tests for tun_vnet_ioctl(). - Added patch "selftest: tap: Add tests for virtio-net ioctls". - Added a design explanation of ioctls for extensibility and migration. - Removed a few branches in patch "vhost/net: Support VIRTIO_NET_F_HASH_REPORT". - Link to v9: https://lore.kernel.org/r/20250307-rss-v9-0-df76624025eb@daynix.com Changes in v9: - Added a missing return statement in patch "tun: Introduce virtio-net hash feature". - Link to v8: https://lore.kernel.org/r/20250306-rss-v8-0-7ab4f56ff423@daynix.com Changes in v8: - Disabled IPv6 to eliminate noises in tests. - Added a branch in tap to avoid unnecessary dissection when hash reporting is disabled. - Removed unnecessary rtnl_lock(). - Extracted code to handle new ioctls into separate functions to avoid adding extra NULL checks to the code handling other ioctls. - Introduced variable named "fd" to __tun_chr_ioctl(). - s/-/=/g in a patch message to avoid confusing Git. - Link to v7: https://lore.kernel.org/r/20250228-rss-v7-0-844205cbbdd6@daynix.com Changes in v7: - Ensured to set hash_report to VIRTIO_NET_HASH_REPORT_NONE for VHOST_NET_F_VIRTIO_NET_HDR. - s/4/sizeof(u32)/ in patch "virtio_net: Add functions for hashing". - Added tap_skb_cb type. - Rebased. - Link to v6: https://lore.kernel.org/r/20250109-rss-v6-0-b1c90ad708f6@daynix.com Changes in v6: - Extracted changes to fill vnet header holes into another series. - Squashed patches "skbuff: Introduce SKB_EXT_TUN_VNET_HASH", "tun: Introduce virtio-net hash reporting feature", and "tun: Introduce virtio-net RSS" into patch "tun: Introduce virtio-net hash feature". - Dropped the RFC tag. - Link to v5: https://lore.kernel.org/r/20241008-rss-v5-0-f3cf68df005d@daynix.com Changes in v5: - Fixed a compilation error with CONFIG_TUN_VNET_CROSS_LE. - Optimized the calculation of the hash value according to: https://git.dpdk.org/dpdk/commit/?id=3fb1ea032bd6ff8317af5dac9af901f1f324ca… - Added patch "tun: Unify vnet implementation". - Dropped patch "tap: Pad virtio header with zero". - Added patch "selftest: tun: Test vnet ioctls without device". - Reworked selftests to skip for older kernels. - Documented the case when the underlying device is deleted and packets have queue_mapping set by TC. - Reordered test harness arguments. - Added code to handle fragmented packets. - Link to v4: https://lore.kernel.org/r/20240924-rss-v4-0-84e932ec0e6c@daynix.com Changes in v4: - Moved tun_vnet_hash_ext to if_tun.h. - Renamed virtio_net_toeplitz() to virtio_net_toeplitz_calc(). - Replaced htons() with cpu_to_be16(). - Changed virtio_net_hash_rss() to return void. - Reordered variable declarations in virtio_net_hash_rss(). - Removed virtio_net_hdr_v1_hash_from_skb(). - Updated messages of "tap: Pad virtio header with zero" and "tun: Pad virtio header with zero". - Fixed vnet_hash allocation size. - Ensured to free vnet_hash when destructing tun_struct. - Link to v3: https://lore.kernel.org/r/20240915-rss-v3-0-c630015db082@daynix.com Changes in v3: - Reverted back to add ioctl. - Split patch "tun: Introduce virtio-net hashing feature" into "tun: Introduce virtio-net hash reporting feature" and "tun: Introduce virtio-net RSS". - Changed to reuse hash values computed for automq instead of performing RSS hashing when hash reporting is requested but RSS is not. - Extracted relevant data from struct tun_struct to keep it minimal. - Added kernel-doc. - Changed to allow calling TUNGETVNETHASHCAP before TUNSETIFF. - Initialized num_buffers with 1. - Added a test case for unclassified packets. - Fixed error handling in tests. - Changed tests to verify that the queue index will not overflow. - Rebased. - Link to v2: https://lore.kernel.org/r/20231015141644.260646-1-akihiko.odaki@daynix.com --- Akihiko Odaki (10): virtio_net: Add functions for hashing net: flow_dissector: Export flow_keys_dissector_symmetric tun: Allow steering eBPF program to fall back tun: Add common virtio-net hash feature code tun: Introduce virtio-net hash feature tap: Introduce virtio-net hash feature selftest: tun: Test vnet ioctls without device selftest: tun: Add tests for virtio-net hashing selftest: tap: Add tests for virtio-net ioctls vhost/net: Support VIRTIO_NET_F_HASH_REPORT Documentation/networking/tuntap.rst | 7 + drivers/net/Kconfig | 1 + drivers/net/ipvlan/ipvtap.c | 2 +- drivers/net/macvtap.c | 2 +- drivers/net/tap.c | 80 +++++- drivers/net/tun.c | 92 +++++-- drivers/net/tun_vnet.h | 165 +++++++++++- drivers/vhost/net.c | 68 ++--- include/linux/if_tap.h | 4 +- include/linux/skbuff.h | 3 + include/linux/virtio_net.h | 188 ++++++++++++++ include/net/flow_dissector.h | 1 + include/uapi/linux/if_tun.h | 80 ++++++ net/core/flow_dissector.c | 3 +- net/core/skbuff.c | 4 + tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/config | 1 + tools/testing/selftests/net/tap.c | 131 +++++++++- tools/testing/selftests/net/tun.c | 485 ++++++++++++++++++++++++++++++++++- 19 files changed, 1234 insertions(+), 85 deletions(-) --- base-commit: 5cb8274d66c611b7889565c418a8158517810f9b change-id: 20240403-rss-e737d89efa77 Best regards, -- Akihiko Odaki <akihiko.odaki(a)daynix.com>

1 month, 1 week

5
38
0 0

[PATCH v12 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v12 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v12 (04-Jul-2025) - Fix compilation issues with some intermediate patches in v11 - Add more comments for AccECN helpers of tcp_ecn.h v11 (03-Jul-2025) - Fix compilation issues with some intermediate patches in v10 v10 (02-Jul-2025) - Add new patch of separated header file include/net/tcp_ecn.h to include ECN and AccECN functions (Eric Dumazet <edumazet(a)google.com>) - Add comments on the AccECN helper functions in tcp_ecn.h (Eric Dumazet <edumazet(a)google.com>) - Add documentation of tcp_ecn, tcp_ecn_option, tcp_ecn_beacon in ip-sysctl.rst to the corresponding patch (Eric Dumazet <edumazet(a)google.com>) - Split wait third ACK functionality into a separated patch from AccECN negotiation patch (Eric Dumazet <edumazet(a)google.com>) - Add READ_ONCE() over every reads of sysctl for all patches in the series (Eric Dumazet <edumazet(a)google.com>) - Merge heuristics of AccECN option ceb/cep and ACE field multi-wrap into a single patch - Add a table of SACK block reduction and required AccECN field in patch #15 commit message (Eric Dumazet <edumazet(a)google.com>) v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (6): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: ecn functions in separated include file tcp: Add wait_third_ack for ECN negotiation in simultaneous connect tcp: accecn: AccECN option send control tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (9): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option ceb/cep and ACE field multi-wrap heuristics Documentation/networking/ip-sysctl.rst | 55 +- .../networking/net_cachelines/tcp_sock.rst | 13 + include/linux/tcp.h | 33 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 87 ++- include/net/tcp_ecn.h | 663 ++++++++++++++++++ include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 4 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 29 +- net/ipv4/tcp_input.c | 371 ++++++++-- net/ipv4/tcp_ipv4.c | 8 +- net/ipv4/tcp_minisocks.c | 40 +- net/ipv4/tcp_output.c | 297 ++++++-- net/ipv6/syncookies.c | 2 + net/ipv6/tcp_ipv6.c | 1 + 16 files changed, 1444 insertions(+), 187 deletions(-) create mode 100644 include/net/tcp_ecn.h -- 2.34.1

1 month, 1 week

3
30
0 0

[PATCH v17 00/27] riscv control-flow integrity for usermode

by Deepak Gupta

Basics and overview =================== Software with larger attack surfaces (e.g. network facing apps like databases, browsers or apps relying on browser runtimes) suffer from memory corruption issues which can be utilized by attackers to bend control flow of the program to eventually gain control (by making their payload executable). Attackers are able to perform such attacks by leveraging call-sites which rely on indirect calls or return sites which rely on obtaining return address from stack memory. To mitigate such attacks, risc-v extension zicfilp enforces that all indirect calls must land on a landing pad instruction `lpad` else cpu will raise software check exception (a new cpu exception cause code on riscv). Similarly for return flow, risc-v extension zicfiss extends architecture with - `sspush` instruction to push return address on a shadow stack - `sspopchk` instruction to pop return address from shadow stack and compare with input operand (i.e. return address on stack) - `sspopchk` to raise software check exception if comparision above was a mismatch - Protection mechanism using which shadow stack is not writeable via regular store instructions More information an details can be found at extensions github repo [1]. Equivalent to landing pad (zicfilp) on x86 is `ENDBRANCH` instruction in Intel CET [3] and branch target identification (BTI) [4] on arm. Similarly x86's Intel CET has shadow stack [5] and arm64 has guarded control stack (GCS) [6] which are very similar to risc-v's zicfiss shadow stack. x86 and arm64 support for user mode shadow stack is already in mainline. Kernel awareness for user control flow integrity ================================================ This series picks up Samuel Holland's envcfg changes [2] as well. So if those are being applied independently, they should be removed from this series. Enabling: In order to maintain compatibility and not break anything in user mode, kernel doesn't enable control flow integrity cpu extensions on binary by default. Instead exposes a prctl interface to enable, disable and lock the shadow stack or landing pad feature for a task. This allows userspace (loader) to enumerate if all objects in its address space are compiled with shadow stack and landing pad support and accordingly enable the feature. Additionally if a subsequent `dlopen` happens on a library, user mode can take a decision again to disable the feature (if incoming library is not compiled with support) OR terminate the task (if user mode policy is strict to have all objects in address space to be compiled with control flow integirty cpu feature). prctl to enable shadow stack results in allocating shadow stack from virtual memory and activating for user address space. x86 and arm64 are also following same direction due to similar reason(s). clone/fork: On clone and fork, cfi state for task is inherited by child. Shadow stack is part of virtual memory and is a writeable memory from kernel perspective (writeable via a restricted set of instructions aka shadow stack instructions) Thus kernel changes ensure that this memory is converted into read-only when fork/clone happens and COWed when fault is taken due to sspush, sspopchk or ssamoswap. In case `CLONE_VM` is specified and shadow stack is to be enabled, kernel will automatically allocate a shadow stack for that clone call. map_shadow_stack: x86 introduced `map_shadow_stack` system call to allow user space to explicitly map shadow stack memory in its address space. It is useful to allocate shadow for different contexts managed by a single thread (green threads or contexts) risc-v implements this system call as well. signal management: If shadow stack is enabled for a task, kernel performs an asynchronous control flow diversion to deliver the signal and eventually expects userspace to issue sigreturn so that original execution can be resumed. Even though resume context is prepared by kernel, it is in user space memory and is subject to memory corruption and corruption bugs can be utilized by attacker in this race window to perform arbitrary sigreturn and eventually bypass cfi mechanism. Another issue is how to ensure that cfi related state on sigcontext area is not trampled by legacy apps or apps compiled with old kernel headers. In order to mitigate control-flow hijacting, kernel prepares a token and place it on shadow stack before signal delivery and places address of token in sigcontext structure. During sigreturn, kernel obtains address of token from sigcontext struture, reads token from shadow stack and validates it and only then allow sigreturn to succeed. Compatiblity issue is solved by adopting dynamic sigcontext management introduced for vector extension. This series re-factor the code little bit to allow future sigcontext management easy (as proposed by Andy Chiu from SiFive) config and compilation: Introduce a new risc-v config option `CONFIG_RISCV_USER_CFI`. Selecting this config option picks the kernel support for user control flow integrity. This optin is presented only if toolchain has shadow stack and landing pad support. And is on purpose guarded by toolchain support. Reason being that eventually vDSO also needs to be compiled in with shadow stack and landing pad support. vDSO compile patches are not included as of now because landing pad labeling scheme is yet to settle for usermode runtime. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` in following: Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- Get the lastest qemu $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) In case you're building your own rootfs using toolchain, please make sure you pick following patch to ensure that vDSO compiled with lpad and shadow stack. "arch/riscv: compile vdso with landing pad" Branch where above patch can be picked https://github.com/deepak0414/linux-riscv-cfi/tree/vdso_user_cfi_v6.12-rc1 Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. References ========== [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/all/20240814081126.956287-1-samuel.holland@sifive.c… [3] - https://lwn.net/Articles/889475/ [4] - https://developer.arm.com/documentation/109576/0100/Branch-Target-Identific… [5] - https://www.intel.com/content/dam/develop/external/us/en/documents/catc17-i… [6] - https://lwn.net/Articles/940403/ To: Thomas Gleixner <tglx(a)linutronix.de> To: Ingo Molnar <mingo(a)redhat.com> To: Borislav Petkov <bp(a)alien8.de> To: Dave Hansen <dave.hansen(a)linux.intel.com> To: x86(a)kernel.org To: H. Peter Anvin <hpa(a)zytor.com> To: Andrew Morton <akpm(a)linux-foundation.org> To: Liam R. Howlett <Liam.Howlett(a)oracle.com> To: Vlastimil Babka <vbabka(a)suse.cz> To: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> To: Paul Walmsley <paul.walmsley(a)sifive.com> To: Palmer Dabbelt <palmer(a)dabbelt.com> To: Albert Ou <aou(a)eecs.berkeley.edu> To: Conor Dooley <conor(a)kernel.org> To: Rob Herring <robh(a)kernel.org> To: Krzysztof Kozlowski <krzk+dt(a)kernel.org> To: Arnd Bergmann <arnd(a)arndb.de> To: Christian Brauner <brauner(a)kernel.org> To: Peter Zijlstra <peterz(a)infradead.org> To: Oleg Nesterov <oleg(a)redhat.com> To: Eric Biederman <ebiederm(a)xmission.com> To: Kees Cook <kees(a)kernel.org> To: Jonathan Corbet <corbet(a)lwn.net> To: Shuah Khan <shuah(a)kernel.org> To: Jann Horn <jannh(a)google.com> To: Conor Dooley <conor+dt(a)kernel.org> To: Miguel Ojeda <ojeda(a)kernel.org> To: Alex Gaynor <alex.gaynor(a)gmail.com> To: Boqun Feng <boqun.feng(a)gmail.com> To: Gary Guo <gary(a)garyguo.net> To: Björn Roy Baron <bjorn3_gh(a)protonmail.com> To: Benno Lossin <benno.lossin(a)proton.me> To: Andreas Hindborg <a.hindborg(a)kernel.org> To: Alice Ryhl <aliceryhl(a)google.com> To: Trevor Gross <tmgross(a)umich.edu> Cc: linux-kernel(a)vger.kernel.org Cc: linux-fsdevel(a)vger.kernel.org Cc: linux-mm(a)kvack.org Cc: linux-riscv(a)lists.infradead.org Cc: devicetree(a)vger.kernel.org Cc: linux-arch(a)vger.kernel.org Cc: linux-doc(a)vger.kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: alistair.francis(a)wdc.com Cc: richard.henderson(a)linaro.org Cc: jim.shu(a)sifive.com Cc: andybnac(a)gmail.com Cc: kito.cheng(a)sifive.com Cc: charlie(a)rivosinc.com Cc: atishp(a)rivosinc.com Cc: evan(a)rivosinc.com Cc: cleger(a)rivosinc.com Cc: alexghiti(a)rivosinc.com Cc: samitolvanen(a)google.com Cc: broonie(a)kernel.org Cc: rick.p.edgecombe(a)intel.com Cc: rust-for-linux(a)vger.kernel.org changelog --------- v17: - fixed warnings due to empty macros in usercfi.h (reported by alexg) - fixed prefixes in commit titles reported by alexg - took below uprobe with fcfi v2 patch from Zong Li and squashed it with "riscv/traps: Introduce software check exception and uprobe handling" https://lore.kernel.org/all/20250604093403.10916-1-zong.li@sifive.com/ v16: - If FWFT is not implemented or returns error for shadow stack activation, then no_usercfi is set to disable shadow stack. Although this should be picked up by extension validation and activation. Fixed this bug for zicfilp and zicfiss both. Thanks to Charlie Jenkins for reporting this. - If toolchain doesn't support cfi, cfi kselftest shouldn't build. Suggested by Charlie Jenkins. - Default for CONFIG_RISCV_USER_CFI is set to no. Charlie/Atish suggested to keep it off till we have more hardware availibility with RVA23 profile and zimop/zcmop implemented. Else this will start breaking people's workflow - Includes the fix if "!RV64 and !SBI" then definitions for FWFT in asm-offsets.c error. v15: - Toolchain has been updated to include `-fcf-protection` flag. This exists for x86 as well. Updated kernel patches to compile vDSO and selftest to compile with `fcf-protection=full` flag. - selecting CONFIG_RISCV_USERCFI selects CONFIG_RISCV_SBI. - Patch to enable shadow stack for kernel wasn't hidden behind CONFIG_RISCV_USERCFI and CONFIG_RISCV_SBI. fixed that. v14: - rebased on top of palmer/sbi-v3. Thus dropped clement's FWFT patches Updated RISCV_ISA_EXT_XXXX in hwcap and hwprobe constants. - Took Radim's suggestions on bitfields. - Placed cfi_state at the end of thread_info block so that current situation is not disturbed with respect to member fields of thread_info in single cacheline. v13: - cpu_supports_shadow_stack/cpu_supports_indirect_br_lp_instr uses riscv_has_extension_unlikely() - uses nops(count) to create nop slide - RISCV_ACQUIRE_BARRIER is not needed in `amo_user_shstk`. Removed it - changed ternaries to simply use implicit casting to convert to bool. - kernel command line allows to disable zicfilp and zicfiss independently. updated kernel-parameters.txt. - ptrace user abi for cfi uses bitmasks instead of bitfields. Added ptrace kselftest. - cosmetic and grammatical changes to documentation. v12: - It seems like I had accidently squashed arch agnostic indirect branch tracking prctl and riscv implementation of those prctls. Split them again. - set_shstk_status/set_indir_lp_status perform CSR writes only when CPU support is available. As suggested by Zong Li. - Some minor clean up in kselftests as suggested by Zong Li. v11: - patch "arch/riscv: compile vdso with landing pad" was unconditionally selecting `_zicfilp` for vDSO compile. fixed that. Changed `lpad 1` to to `lpad 0`. v10: - dropped "mm: helper `is_shadow_stack_vma` to check shadow stack vma". This patch is not that interesting to this patch series for risc-v. There are instances in arch directories where VM_SHADOW_STACK flag is anyways used. Dropping this patch to expedite merging in riscv tree. - Took suggestions from `Clement` on "riscv: zicfiss / zicfilp enumeration" to validate presence of cfi based on config. - Added a patch for vDSO to have `lpad 0`. I had omitted this earlier to make sure we add single vdso object with cfi enabled. But a vdso object with scheme of zero labeled landing pad is least common denominator and should work with all objects of zero labeled as well as function-signature labeled objects. v9: - rebased on master (39a803b754d5 fix braino in "9p: fix ->rename_sem exclusion") - dropped "mm: Introduce ARCH_HAS_USER_SHADOW_STACK" (master has it from arm64/gcs) - dropped "prctl: arch-agnostic prctl for shadow stack" (master has it from arm64/gcs) v8: - rebased on palmer/for-next - dropped samuel holland's `envcfg` context switch patches. they are in parlmer/for-next v7: - Removed "riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv" Instead using `deactivate_mm` flow to clean up. see here for more context https://lore.kernel.org/all/20230908203655.543765-1-rick.p.edgecombe@intel.… - Changed the header include in `kselftest`. Hopefully this fixes compile issue faced by Zong Li at SiFive. - Cleaned up an orphaned change to `mm/mmap.c` in below patch "riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE" - Lock interfaces for shadow stack and indirect branch tracking expect arg == 0 Any future evolution of this interface should accordingly define how arg should be setup. - `mm/map.c` has an instance of using `VM_SHADOW_STACK`. Fixed it to use helper `is_shadow_stack_vma`. - Link to v6: https://lore.kernel.org/r/20241008-v5_user_cfi_series-v6-0-60d9fe073f37@riv… v6: - Picked up Samuel Holland's changes as is with `envcfg` placed in `thread` instead of `thread_info` - fixed unaligned newline escapes in kselftest - cleaned up messages in kselftest and included test output in commit message - fixed a bug in clone path reported by Zong Li - fixed a build issue if CONFIG_RISCV_ISA_V is not selected (this was introduced due to re-factoring signal context management code) v5: - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT (https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware…) - Link to v5: https://lore.kernel.org/r/20241001-v5_user_cfi_series-v1-0-3ba65b6e550f@riv… (Note: I had an issue in my workflow due to which version number wasn't picked up correctly while sending out patches) v4: - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. - Link to v4: https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ v3: - envcfg logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. - dt-bindings As suggested, split into separate commit. fixed the messaging that spec is in public review - arch_is_shadow_stack change arch_is_shadow_stack changed to vma_is_shadow_stack - hwprobe zicfiss / zicfilp if present will get enumerated in hwprobe - selftests As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. - Link to v3: https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ v2: - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. --- Changes in v17: - Link to v16: https://lore.kernel.org/r/20250522-v5_user_cfi_series-v16-0-64f61a35eee7@ri… Changes in v16: - Link to v15: https://lore.kernel.org/r/20250502-v5_user_cfi_series-v15-0-914966471885@ri… Changes in v15: - changelog posted just below cover letter - Link to v14: https://lore.kernel.org/r/20250429-v5_user_cfi_series-v14-0-5239410d012a@ri… Changes in v14: - changelog posted just below cover letter - Link to v13: https://lore.kernel.org/r/20250424-v5_user_cfi_series-v13-0-971437de586a@ri… Changes in v13: - changelog posted just below cover letter - Link to v12: https://lore.kernel.org/r/20250314-v5_user_cfi_series-v12-0-e51202b53138@ri… Changes in v12: - changelog posted just below cover letter - Link to v11: https://lore.kernel.org/r/20250310-v5_user_cfi_series-v11-0-86b36cbfb910@ri… Changes in v11: - changelog posted just below cover letter - Link to v10: https://lore.kernel.org/r/20250210-v5_user_cfi_series-v10-0-163dcfa31c60@ri… --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Deepak Gupta (25): mm: VM_SHADOW_STACK definition for riscv dt-bindings: riscv: zicfilp and zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv/mm: manufacture shadow stack pte riscv/mm: teach pte_mkwrite to manufacture shadow stack PTEs riscv/mm: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone riscv: Implements arch agnostic shadow stack prctls prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception and uprobe handling riscv/signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: kernel command line option to opt out of user cfi riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Jim Shu (1): arch/riscv: compile vdso with landing pad Documentation/admin-guide/kernel-parameters.txt | 8 + Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 179 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 21 + arch/riscv/Makefile | 5 +- arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/assembler.h | 44 ++ arch/riscv/include/asm/cpufeature.h | 12 + arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 26 + arch/riscv/include/asm/mmu_context.h | 7 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 2 + arch/riscv/include/asm/thread_info.h | 3 + arch/riscv/include/asm/usercfi.h | 95 ++++ arch/riscv/include/asm/vector.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 34 ++ arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 1 + arch/riscv/kernel/asm-offsets.c | 10 + arch/riscv/kernel/cpufeature.c | 27 + arch/riscv/kernel/entry.S | 33 +- arch/riscv/kernel/head.S | 27 + arch/riscv/kernel/process.c | 27 +- arch/riscv/kernel/ptrace.c | 95 ++++ arch/riscv/kernel/signal.c | 148 +++++- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 51 ++ arch/riscv/kernel/usercfi.c | 545 +++++++++++++++++++++ arch/riscv/kernel/vdso/Makefile | 6 + arch/riscv/kernel/vdso/flush_icache.S | 4 + arch/riscv/kernel/vdso/getcpu.S | 4 + arch/riscv/kernel/vdso/rt_sigreturn.S | 4 + arch/riscv/kernel/vdso/sys_hwprobe.S | 4 + arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 16 + include/linux/cpu.h | 4 + include/linux/mm.h | 7 + include/uapi/linux/elf.h | 2 + include/uapi/linux/prctl.h | 27 + kernel/sys.c | 30 ++ tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 16 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 82 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 173 +++++++ tools/testing/selftests/riscv/cfi/shadowstack.c | 385 +++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 27 + 54 files changed, 2369 insertions(+), 29 deletions(-) --- base-commit: 4181f8ad7a1061efed0219951d608d4988302af7 change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

1 month, 1 week

2
34
0 0

[PATCH] tools/nolibc: add support for Alpha

by Thomas Weißschuh

A straightforward new architecture. Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- Only tested on QEMU so far. Testing on real hardware would be very welcome. Test instructions: $ cd tools/testings/selftests/nolibc/ $ make -f Makefile.nolibc ARCH=alpha CROSS_COMPILE=alpha-linux- nolibc-test $ file nolibc-test nolibc-test: ELF 64-bit LSB executable, Alpha (unofficial), version 1 (SYSV), statically linked, not stripped $ ./nolibc-test Running test 'startup' 0 argc = 1 [OK] ... Total number of errors: 0 Exiting with status 0 --- tools/include/nolibc/arch-alpha.h | 164 +++++++++++++++++++++++++ tools/include/nolibc/arch.h | 2 + tools/testing/selftests/nolibc/Makefile.nolibc | 5 + tools/testing/selftests/nolibc/nolibc-test.c | 4 + tools/testing/selftests/nolibc/run-tests.sh | 3 +- 5 files changed, 177 insertions(+), 1 deletion(-) diff --git a/tools/include/nolibc/arch-alpha.h b/tools/include/nolibc/arch-alpha.h new file mode 100644 index 0000000000000000000000000000000000000000..6b9bb6c749b931f30ce7bd6cd125622828405604 --- /dev/null +++ b/tools/include/nolibc/arch-alpha.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ +/* + * Alpha specific definitions for NOLIBC + * Copyright (C) 2025 Thomas Weißschuh <linux(a)weissschuh.net> + */ + +#ifndef _NOLIBC_ARCH_ALPHA_H +#define _NOLIBC_ARCH_ALPHA_H + +#include "compiler.h" +#include "crt.h" + +/* + * Syscalls for Alpha: + * - registers are 64-bit + * - syscall number is passed in $0/v0 + * - the system call is performed by calling callsys + * - syscall return comes in $0/v0, error flag in $19/a4 + * - arguments are passed in $16/a0 to $21/a5 + * - GCC does not support symbol register names + */ + +#define my_syscall0(num) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall1(num, arg1) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall2(num, arg1, arg2) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + register long _arg2 __asm__ ("$17") = (long)(arg2); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1), "r"(_arg2) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall3(num, arg1, arg2, arg3) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + register long _arg2 __asm__ ("$17") = (long)(arg2); \ + register long _arg3 __asm__ ("$18") = (long)(arg3); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1), "r"(_arg2), "r"(_arg3) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall4(num, arg1, arg2, arg3, arg4) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + register long _arg2 __asm__ ("$17") = (long)(arg2); \ + register long _arg3 __asm__ ("$18") = (long)(arg3); \ + register long _arg4 __asm__ ("$19") = (long)(arg4); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + register long _arg2 __asm__ ("$17") = (long)(arg2); \ + register long _arg3 __asm__ ("$18") = (long)(arg3); \ + register long _arg4 __asm__ ("$19") = (long)(arg4); \ + register long _arg5 __asm__ ("$20") = (long)(arg5); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_arg5) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \ +({ \ + register long _num __asm__ ("$0") = (num); \ + register long _ret __asm__ ("$0"); \ + register long _err __asm__ ("$19"); \ + register long _arg1 __asm__ ("$16") = (long)(arg1); \ + register long _arg2 __asm__ ("$17") = (long)(arg2); \ + register long _arg3 __asm__ ("$18") = (long)(arg3); \ + register long _arg4 __asm__ ("$19") = (long)(arg4); \ + register long _arg5 __asm__ ("$20") = (long)(arg5); \ + register long _arg6 __asm__ ("$21") = (long)(arg6); \ + \ + __asm__ volatile ( \ + "callsys" \ + : "=r"(_ret), "=r"(_err) \ + : "r"(_num), "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \ + "r"(_arg5), "r"(_arg6) \ + : "memory", "cc" \ + ); \ + _err ? -_ret : _ret; \ +}) + +/* startup code */ +void __attribute__((weak, noreturn)) __nolibc_entrypoint __no_stack_protector _start(void) +{ + __asm__ volatile ( + "br $gp, 0f\n" /* setup $gp, so that 'lda' works */ + "0: ldgp $gp, 0($gp)\n" + "lda $27, _start_c\n" /* setup current function address for _start_c */ + "mov $sp, $16\n" /* save argc pointer to $16, as arg1 of _start_c */ + "br _start_c\n" /* transfer to c runtime */ + ); + __nolibc_entrypoint_epilogue(); +} + +#endif /* _NOLIBC_ARCH_ALPHA_H */ diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h index 426c89198135564acca44c485e5c2d8ba36a6fe9..72585d4c04e2896a275faadf881e98286f914fb3 100644 --- a/tools/include/nolibc/arch.h +++ b/tools/include/nolibc/arch.h @@ -37,6 +37,8 @@ #include "arch-m68k.h" #elif defined(__sh__) #include "arch-sh.h" +#elif defined(__alpha__) +#include "arch-alpha.h" #else #error Unsupported Architecture #endif diff --git a/tools/testing/selftests/nolibc/Makefile.nolibc b/tools/testing/selftests/nolibc/Makefile.nolibc index 0fb759ba992ee6b1693b88f1b2e77463afa9f38b..0da33fe99bd630ec5100b5beed939d524af2b3d4 100644 --- a/tools/testing/selftests/nolibc/Makefile.nolibc +++ b/tools/testing/selftests/nolibc/Makefile.nolibc @@ -93,6 +93,7 @@ IMAGE_sparc32 = arch/sparc/boot/image IMAGE_sparc64 = arch/sparc/boot/image IMAGE_m68k = vmlinux IMAGE_sh4 = arch/sh/boot/zImage +IMAGE_alpha = vmlinux IMAGE = $(objtree)/$(IMAGE_$(XARCH)) IMAGE_NAME = $(notdir $(IMAGE)) @@ -123,6 +124,7 @@ DEFCONFIG_sparc32 = sparc32_defconfig DEFCONFIG_sparc64 = sparc64_defconfig DEFCONFIG_m68k = virt_defconfig DEFCONFIG_sh4 = rts7751r2dplus_defconfig +DEFCONFIG_alpha = defconfig DEFCONFIG = $(DEFCONFIG_$(XARCH)) EXTRACONFIG_x32 = -e CONFIG_X86_X32_ABI @@ -130,6 +132,7 @@ EXTRACONFIG_arm = -e CONFIG_NAMESPACES EXTRACONFIG_armthumb = -e CONFIG_NAMESPACES EXTRACONFIG_m68k = -e CONFIG_BLK_DEV_INITRD EXTRACONFIG_sh4 = -e CONFIG_BLK_DEV_INITRD -e CONFIG_CMDLINE_FROM_BOOTLOADER +EXTRACONFIG_alpha = -e CONFIG_BLK_DEV_INITRD EXTRACONFIG = $(EXTRACONFIG_$(XARCH)) # optional tests to run (default = all) @@ -162,6 +165,7 @@ QEMU_ARCH_sparc32 = sparc QEMU_ARCH_sparc64 = sparc64 QEMU_ARCH_m68k = m68k QEMU_ARCH_sh4 = sh4 +QEMU_ARCH_alpha = alpha QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) QEMU_ARCH_USER_ppc64le = ppc64le @@ -203,6 +207,7 @@ QEMU_ARGS_sparc32 = -M SS-5 -m 256M -append "console=ttyS0,115200 panic=-1 $( QEMU_ARGS_sparc64 = -M sun4u -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_m68k = -M virt -append "console=ttyGF0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_sh4 = -M r2d -serial file:/dev/stdout -append "console=ttySC1,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_alpha = -M clipper -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) # OUTPUT is only set when run from the main makefile, otherwise diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index a297ee0d6d0754dfcd9f9e5609d42c7442dabc4e..bbbb2a485f220fed69556baaf2603d9cf24a1c36 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -709,6 +709,10 @@ int run_startup(int min, int max) /* checking NULL for argv/argv0, environ and _auxv is not enough, let's compare with sbrk(0) or &end */ extern char end; char *brk = sbrk(0) != (void *)-1 ? sbrk(0) : &end; +#if defined(__alpha__) + /* the ordering above does not work on an alpha kernel */ + brk = NULL; +#endif /* differ from nolibc, both glibc and musl have no global _auxv */ const unsigned long *test_auxv = (void *)-1; #ifdef NOLIBC diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index e8af1fb505cf3573b4a6b37228dee764fe2e5277..8ce57d7006594c531f471d777d579c4f08d87efe 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -28,6 +28,7 @@ all_archs=( sparc32 sparc64 m68k sh4 + alpha ) archs="${all_archs[@]}" @@ -189,7 +190,7 @@ test_arch() { echo "Unsupported configuration" return fi - if [ "$arch" = "m68k" -o "$arch" = "sh4" ] && [ "$llvm" = "1" ]; then + if [ "$arch" = "m68k" -o "$arch" = "sh4" -o "$arch" = "alpha" ] && [ "$llvm" = "1" ]; then echo "Unsupported configuration" return fi --- base-commit: b9e50363178a40c76bebaf2f00faa2b0b6baf8d1 change-id: 20250609-nolibc-alpha-33e79644544c Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 month, 1 week

4
6
0 0

[PATCH net-next V4 0/5] selftests: drv-net: Test XDP native support

by Mohsin Bashir

This patch series add tests to validate XDP native support for PASS, DROP, ABORT, and TX actions, as well as headroom and tailroom adjustment. For adjustment tests, validate support for both the extension and shrinking cases across various packet sizes and offset values. The pass criteria for head/tail adjustment tests require that at-least one adjustment value works for at-least one packet size. This ensure that the variability in maximum supported head/tail adjustment offset across different drivers is being incorporated. The results reported in this series are based on fbnic. However, the series is tested against multiple other drivers including netdevism. Note: The XDP support for fbnic will be added later. --- Change-log: V4: - Support XDP handling for netdevsim - Fix pylint warning with P4 - Update commit message for P2,P3 to show pass/fail summary V3: https://lore.kernel.org/netdev/20250712002648.2385849-1-mohsin.bashr@gmail.… V2: https://lore.kernel.org/netdev/20250710184351.63797-1-mohsin.bashr@gmail.com V1: https://lore.kernel.org/netdev/20250709173707.3177206-1-mohsin.bashr@gmail.… Jakub Kicinski (1): net: netdevsim: hook in XDP handling Mohsin Bashir (4): selftests: drv-net: Test XDP_PASS/DROP support selftests: drv-net: Test XDP_TX support selftests: drv-net: Test tail-adjustment support selftests: drv-net: Test head-adjustment support drivers/net/netdevsim/netdev.c | 19 +- tools/testing/selftests/drivers/net/Makefile | 1 + tools/testing/selftests/drivers/net/xdp.py | 656 ++++++++++++++++++ .../selftests/net/lib/xdp_native.bpf.c | 538 ++++++++++++++ 4 files changed, 1213 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/drivers/net/xdp.py create mode 100644 tools/testing/selftests/net/lib/xdp_native.bpf.c -- 2.47.1

1 month, 1 week

3
8
0 0

[PATCH net-next v3 0/3] netdevsim: add support for PHY devices

by Maxime Chevallier

Hi everyone, Here's a V3 for the netdevsim PHY support. This V3 includes : - A fix for a compiling issue with PHYLIB=n - An updated KConfig to only allow PHYLIB=y|n - Converted the link setting file to a bool debugfs file, relying on link state polling The idea of this series is to allow attaching virtual PHY devices to netdevsim, so that we can test PHY-related ethtool commands. This can be extended in the future for phylib testing as well. V2: https://lore.kernel.org/netdev/20250708115531.111326-1-maxime.chevallier@bo… - Fix building with PHYLIB=m - Use shellcheck on the shell scripts V1: https://lore.kernel.org/netdev/20250702082806.706973-1-maxime.chevallier@bo… Maxime Chevallier (3): net: netdevsim: Add PHY support in netdevsim selftests: ethtool: Drop the unused old_netdevs variable selftests: ethtool: Introduce ethernet PHY selftests on netdevsim drivers/net/Kconfig | 1 + drivers/net/netdevsim/Makefile | 4 + drivers/net/netdevsim/dev.c | 2 + drivers/net/netdevsim/netdev.c | 8 + drivers/net/netdevsim/netdevsim.h | 25 ++ drivers/net/netdevsim/phy.c | 375 ++++++++++++++++++ .../selftests/drivers/net/netdevsim/config | 1 + .../drivers/net/netdevsim/ethtool-common.sh | 19 +- .../drivers/net/netdevsim/ethtool-phy.sh | 64 +++ 9 files changed, 496 insertions(+), 3 deletions(-) create mode 100644 drivers/net/netdevsim/phy.c create mode 100755 tools/testing/selftests/drivers/net/netdevsim/ethtool-phy.sh -- 2.49.0

1 month, 1 week

3
12
0 0

[PATCH net] selftests: net: increase inter-packet timeout in udpgro.sh

by Paolo Abeni

The mentioned test is not very stable when running on top of debug kernel build. Increase the inter-packet timeout to allow more slack in such environments. Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO") Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> --- tools/testing/selftests/net/udpgro.sh | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index 1dc337c709f8..b17e032a6d75 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -48,7 +48,7 @@ run_one() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} & local PID1=$! wait_local_port_listen ${PEER_NS} 8000 udp @@ -95,7 +95,7 @@ run_one_nat() { # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${family} -b ${addr2%/*} ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 8000 udp @@ -117,9 +117,9 @@ run_one_2sock() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 100 ${rx_args} -p 12345 & local PID1=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 100 ${rx_args} & local PID2=$! wait_local_port_listen "${PEER_NS}" 12345 udp -- 2.50.0

1 month, 1 week

3
2
0 0

[PATCH][next] selftests/futex: Fix spelling mistake "Succeffuly" -> "Successfully"

by Colin Ian King

There is a spelling mistake in a ksft_exit_fail_msg message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/futex/functional/futex_priv_hash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c index a9cedc365102..aea001ac4946 100644 --- a/tools/testing/selftests/futex/functional/futex_priv_hash.c +++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c @@ -122,7 +122,7 @@ static void futex_dummy_op(void) } ret = pthread_mutex_timedlock(&lock, &timeout); if (ret == 0) - ksft_exit_fail_msg("Succeffuly locked an already locked mutex.\n"); + ksft_exit_fail_msg("Successfully locked an already locked mutex.\n"); if (ret != ETIMEDOUT) ksft_exit_fail_msg("pthread_mutex_timedlock() did not timeout: %d.\n", ret); -- 2.50.0

1 month, 1 week

1
0
0 0

[PATCH] selftests/mm: refactor common code and improve test skipping in guard_region

by wang lian

Move the generic `FORCE_READ` macro from `guard-regions.c` to the shared `vm_util.h` header to promote code reuse. In `guard-regions.c`, replace `ksft_exit_skip()` with the `SKIP()` macro to ensure only the current test is skipped on permission failure, instead of terminating the entire test binary. Signed-off-by: wang lian <lianux.mm(a)gmail.com> --- tools/testing/selftests/mm/guard-regions.c | 9 +-------- tools/testing/selftests/mm/vm_util.h | 7 +++++++ 2 files changed, 8 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index 93af3d3760f9..b0d42eb04e3a 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -35,13 +35,6 @@ static volatile sig_atomic_t signal_jump_set; static sigjmp_buf signal_jmp_buf; -/* - * Ignore the checkpatch warning, we must read from x but don't want to do - * anything with it in order to trigger a read page fault. We therefore must use - * volatile to stop the compiler from optimising this away. - */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) - /* * How is the test backing the mapping being tested? */ @@ -582,7 +575,7 @@ TEST_F(guard_regions, process_madvise) /* OK we don't have permission to do this, skip. */ if (count == -1 && errno == EPERM) - ksft_exit_skip("No process_madvise() permissions, try running as root.\n"); + SKIP(return, "No process_madvise() permissions, try running as root.\n"); /* Returns the number of bytes advised. */ ASSERT_EQ(count, 6 * page_size); diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 2b154c287591..c20298ae98ea 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -18,6 +18,13 @@ #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + extern unsigned int __page_size; extern unsigned int __page_shift; -- 2.43.0

1 month, 1 week

4
5
0 0

[PATCH net 0/2] selftests: mptcp: connect: cover alt modes

by Matthieu Baerts (NGI0)

mptcp_connect.sh can be executed manually with "-m <MODE>" and "-C" to make sure everything works as expected when using "mmap" and "sendfile" modes instead of "poll", and with the MPTCP checksum support. These modes should be validated, but they are not when the selftests are executed via the kselftest helpers. It means that most CIs validating these selftests, like NIPA for the net development trees and LKFT for the stable ones, are not covering these modes. To fix that, new test programs have been added, simply calling mptcp_connect.sh with the right parameters. The first patch can be backported up to v5.6, and the second one up to v5.14. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Matthieu Baerts (NGI0) (2): selftests: mptcp: connect: also cover alt modes selftests: mptcp: connect: also cover checksum tools/testing/selftests/net/mptcp/Makefile | 3 ++- tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh | 4 ++++ tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh | 4 ++++ tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh | 4 ++++ 4 files changed, 14 insertions(+), 1 deletion(-) --- base-commit: b640daa2822a39ff76e70200cb2b7b892b896dce change-id: 20250714-net-mptcp-sft-connect-alt-c1aaf073ef4e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

1 month, 1 week

2
3
0 0

[PATCH v4 0/7] Add support for FEAT_{LS64, LS64_V} and related tests

by Yicong Yang

From: Yicong Yang <yangyicong(a)hisilicon.com> Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. Add support for Armv8.7 FEAT_{LS64, LS64_V}: - Add identifying and enabling in the cpufeature list - Expose the support of these features to userspace through HWCAP3 and cpuinfo - Add related hwcap test - Handle the trap of unsupported memory (normal/uncacheable) access in a VM A real scenario for this feature is that the userspace driver can make use of this to implement direct WQE (workqueue entry) - a mechanism to fill WQE directly into the hardware. Picked Marc's 2 patches form [1] for handling the LS64 trap in a VM on emulated MMIO and the introduce of KVM_EXIT_ARM_LDST64B. [1] https://lore.kernel.org/linux-arm-kernel/20240815125959.2097734-1-maz@kerne… Tested with updated hwcap test: [root@localhost tmp]# dmesg | grep "All CPU(s) started" [ 14.789859] CPU: All CPU(s) started at EL2 [root@localhost tmp]# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64_V # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 root@localhost:/mnt# dmesg | grep "All CPU(s) started" [ 0.281152] CPU: All CPU(s) started at EL1 root@localhost:/mnt# ./hwcap # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 Change since v3: - Inject DABT fault for LS64 fault on unsupported memory but with valid memslot Link: https://lore.kernel.org/linux-arm-kernel/20250626080906.64230-1-yangyicong@… Change since v2: - Handle the LS64 fault to userspace and allow userspace to inject LS64 fault - Reorder the patches to make KVM handling prior to feature support Link: https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-1-yangyicong@… Change since v1: - Drop the support for LS64_ACCDATA - handle the DABT of unsupported memory type after checking the memory attributes Link: https://lore.kernel.org/linux-arm-kernel/20241202135504.14252-1-yangyicong@… Marc Zyngier (2): KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B Yicong Yang (5): KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1 arm64: Add support for FEAT_{LS64, LS64_V} KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest kselftest/arm64: Add HWCAP test for FEAT_{LS64, LS64_V} Documentation/arch/arm64/booting.rst | 12 +++ Documentation/arch/arm64/elf_hwcaps.rst | 6 ++ Documentation/virt/kvm/api.rst | 43 +++++++++-- arch/arm64/include/asm/el2_setup.h | 12 ++- arch/arm64/include/asm/esr.h | 8 ++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/asm/kvm_emulate.h | 7 ++ arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/kernel/cpufeature.c | 51 +++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/kvm/inject_fault.c | 29 ++++++++ arch/arm64/kvm/mmio.c | 27 ++++++- arch/arm64/kvm/mmu.c | 14 +++- arch/arm64/tools/cpucaps | 2 + include/uapi/linux/kvm.h | 3 +- tools/testing/selftests/arm64/abi/hwcap.c | 90 +++++++++++++++++++++++ 16 files changed, 299 insertions(+), 11 deletions(-) -- 2.24.0

1 month, 1 week

1
7
0 0

[PATCH 00/15] selftests/futex: Refactor tests to use kselftest_harness.h

by André Almeida

This patch series refactors all futex selftests to use kselftest_harness.h instead of futex's logging.h, as discussed here [1]. This allows to remove a lot of boilerplate code and to simplify some parts of the test logic, mainly when the test needs to exit early. The result of this is more than 500 lines removed from tools/testing/selftests/futex/. Also, this enables new tests to use kselftest.h features like ASSERT_s and such. There are some caveats around this refactor: - logging.h had verbosity levels, while kselftest_harness.h doesn't. I created a new print function called ksft_print_dbg_msg() that prints the message if the user uses the -d flag, so now there's an equivalent of this feature. - futex_requeue_pi test accepted command line arguments to be used as test parameters (e.g. ./futex_requeue_pi -b -l -t 500000). This doesn't work with kselftest_harness.h because there's no straightforward way to send command line arguments to the test. I used FIXTURE_VARIANT() to achieve the same result, but now the parameters live inside of the test file, instead of on functional/run.sh. This increased a little bit the number of test cases for futex_requeue_pi, from 22 to 24. - test_harness_run() calls mmap(MAP_SHARED) before running the test and this has caused a side effect on test futex_numa_mpol.c. This test also calls mmap() and then try to access an address out of boundaries of this mapped memory for a "Memory out of range" subtest, where the kernel should return -EACCESS. After the refactor, the test address might be fall inside the first memory mapped region, thus being a valid address and succeeding the syscall, making the test fail. To fix that, I created a small "buffer zone" with mmap(PROT_NONE) between both mmaps. I have compared the results of run.sh before and after this patchset and didn't find any regression from the test results. Thanks, André [1] https://lore.kernel.org/lkml/87ecv6p364.ffs@tglx/ --- André Almeida (15): selftests: kselftest: Create ksft_print_dbg_msg() selftests/futex: Refactor futex_requeue_pi with kselftest_harness.h selftests/futex: Refactor futex_requeue_pi_mismatched_ops with kselftest_harness.h selftests/futex: Refactor futex_requeue_pi_signal_restart with kselftest_harness.h selftests/futex: Refactor futex_wait_timeout with kselftest_harness.h selftests/futex: Refactor futex_wait_wouldblock with kselftest_harness.h selftests/futex: Refactor futex_wait_unitialized_heap with kselftest_harness.h selftests/futex: Refactor futex_wait_private_mapped_file with kselftest_harness.h selftests/futex: Refactor futex_wait with kselftest_harness.h selftests/futex: Refactor futex_requeue with kselftest_harness.h selftests/futex: Refactor futex_waitv with kselftest_harness.h selftests/futex: Refactor futex_priv_hash with kselftest_harness.h selftests/futex: Refactor futex_numa_mpol with kselftest_harness.h selftests/futex: Drop logging.h include from futex_numa selftests/futex: Remove logging.h file tools/testing/selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/futex_numa.c | 3 +- .../selftests/futex/functional/futex_numa_mpol.c | 57 ++--- .../selftests/futex/functional/futex_priv_hash.c | 79 +++---- .../selftests/futex/functional/futex_requeue.c | 76 ++---- .../selftests/futex/functional/futex_requeue_pi.c | 261 ++++++++++----------- .../functional/futex_requeue_pi_mismatched_ops.c | 80 ++----- .../functional/futex_requeue_pi_signal_restart.c | 129 +++------- .../selftests/futex/functional/futex_wait.c | 103 +++----- .../functional/futex_wait_private_mapped_file.c | 83 ++----- .../futex/functional/futex_wait_timeout.c | 139 +++++------ .../functional/futex_wait_uninitialized_heap.c | 76 ++---- .../futex/functional/futex_wait_wouldblock.c | 75 ++---- .../selftests/futex/functional/futex_waitv.c | 98 ++++---- tools/testing/selftests/futex/functional/run.sh | 62 +---- tools/testing/selftests/futex/include/logging.h | 148 ------------ tools/testing/selftests/kselftest.h | 13 + tools/testing/selftests/kselftest_harness.h | 13 +- 18 files changed, 491 insertions(+), 1007 deletions(-) --- base-commit: a24cc6ce1933eade12aa2b9859de0fcd2dac2c06 change-id: 20250703-tonyk-robust_test_cleanup-d1f3406365d9 Best regards, -- André Almeida <andrealmeid(a)igalia.com>

1 month, 1 week

3
17
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror