--- /dev/null
+From stable+bounces-5312-greg=kroah.com@vger.kernel.org Mon Dec 11 13:44:00 2023
+From: Ido Schimmel <idosch@nvidia.com>
+Date: Mon, 11 Dec 2023 14:43:01 +0200
+Subject: drop_monitor: Require 'CAP_SYS_ADMIN' when joining "events" group
+To: <stable@vger.kernel.org>
+Cc: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>, <edumazet@google.com>, <nhorman@tuxdriver.com>, <yotam.gi@gmail.com>, <sashal@kernel.org>, <fw@strlen.de>, <jacob.e.keller@intel.com>, <jiri@nvidia.com>
+Message-ID: <20231211124301.822961-5-idosch@nvidia.com>
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+commit e03781879a0d524ce3126678d50a80484a513c4b upstream.
+
+The "NET_DM" generic netlink family notifies drop locations over the
+"events" multicast group. This is problematic since by default generic
+netlink allows non-root users to listen to these notifications.
+
+Fix by adding a new field to the generic netlink multicast group
+structure that when set prevents non-root users or root without the
+'CAP_SYS_ADMIN' capability (in the user namespace owning the network
+namespace) from joining the group. Set this field for the "events"
+group. Use 'CAP_SYS_ADMIN' rather than 'CAP_NET_ADMIN' because of the
+nature of the information that is shared over this group.
+
+Note that the capability check in this case will always be performed
+against the initial user namespace since the family is not netns aware
+and only operates in the initial network namespace.
+
+A new field is added to the structure rather than using the "flags"
+field because the existing field uses uAPI flags and it is inappropriate
+to add a new uAPI flag for an internal kernel check. In net-next we can
+rework the "flags" field to use internal flags and fold the new field
+into it. But for now, in order to reduce the amount of changes, add a
+new field.
+
+Since the information can only be consumed by root, mark the control
+plane operations that start and stop the tracing as root-only using the
+'GENL_ADMIN_PERM' flag.
+
+Tested using [1].
+
+Before:
+
+ # capsh -- -c ./dm_repo
+ # capsh --drop=cap_sys_admin -- -c ./dm_repo
+
+After:
+
+ # capsh -- -c ./dm_repo
+ # capsh --drop=cap_sys_admin -- -c ./dm_repo
+ Failed to join "events" multicast group
+
+[1]
+ $ cat dm.c
+ #include <stdio.h>
+ #include <netlink/genl/ctrl.h>
+ #include <netlink/genl/genl.h>
+ #include <netlink/socket.h>
+
+ int main(int argc, char **argv)
+ {
+ struct nl_sock *sk;
+ int grp, err;
+
+ sk = nl_socket_alloc();
+ if (!sk) {
+ fprintf(stderr, "Failed to allocate socket\n");
+ return -1;
+ }
+
+ err = genl_connect(sk);
+ if (err) {
+ fprintf(stderr, "Failed to connect socket\n");
+ return err;
+ }
+
+ grp = genl_ctrl_resolve_grp(sk, "NET_DM", "events");
+ if (grp < 0) {
+ fprintf(stderr,
+ "Failed to resolve \"events\" multicast group\n");
+ return grp;
+ }
+
+ err = nl_socket_add_memberships(sk, grp, NFNLGRP_NONE);
+ if (err) {
+ fprintf(stderr, "Failed to join \"events\" multicast group\n");
+ return err;
+ }
+
+ return 0;
+ }
+ $ gcc -I/usr/include/libnl3 -lnl-3 -lnl-genl-3 -o dm_repo dm.c
+
+Fixes: 9a8afc8d3962 ("Network Drop Monitor: Adding drop monitor implementation & Netlink protocol")
+Reported-by: "The UK's National Cyber Security Centre (NCSC)" <security@ncsc.gov.uk>
+Signed-off-by: Ido Schimmel <idosch@nvidia.com>
+Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
+Reviewed-by: Jiri Pirko <jiri@nvidia.com>
+Link: https://lore.kernel.org/r/20231206213102.1824398-3-idosch@nvidia.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/genetlink.h | 2 ++
+ net/core/drop_monitor.c | 4 +++-
+ net/netlink/genetlink.c | 3 +++
+ 3 files changed, 8 insertions(+), 1 deletion(-)
+
+--- a/include/net/genetlink.h
++++ b/include/net/genetlink.h
+@@ -11,10 +11,12 @@
+ /**
+ * struct genl_multicast_group - generic netlink multicast group
+ * @name: name of the multicast group, names are per-family
++ * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding
+ */
+ struct genl_multicast_group {
+ char name[GENL_NAMSIZ];
+ u8 flags;
++ u8 cap_sys_admin:1;
+ };
+
+ struct genl_ops;
+--- a/net/core/drop_monitor.c
++++ b/net/core/drop_monitor.c
+@@ -122,7 +122,7 @@ out:
+ }
+
+ static const struct genl_multicast_group dropmon_mcgrps[] = {
+- { .name = "events", },
++ { .name = "events", .cap_sys_admin = 1 },
+ };
+
+ static void send_dm_alert(struct work_struct *work)
+@@ -370,10 +370,12 @@ static const struct genl_ops dropmon_ops
+ {
+ .cmd = NET_DM_CMD_START,
+ .doit = net_dm_cmd_trace,
++ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NET_DM_CMD_STOP,
+ .doit = net_dm_cmd_trace,
++ .flags = GENL_ADMIN_PERM,
+ },
+ };
+
+--- a/net/netlink/genetlink.c
++++ b/net/netlink/genetlink.c
+@@ -982,6 +982,9 @@ static int genl_bind(struct net *net, in
+ if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
+ !ns_capable(net->user_ns, CAP_NET_ADMIN))
+ ret = -EPERM;
++ if (grp->cap_sys_admin &&
++ !ns_capable(net->user_ns, CAP_SYS_ADMIN))
++ ret = -EPERM;
+
+ break;
+ }
--- /dev/null
+From stable+bounces-5310-greg=kroah.com@vger.kernel.org Mon Dec 11 13:43:48 2023
+From: Ido Schimmel <idosch@nvidia.com>
+Date: Mon, 11 Dec 2023 14:42:59 +0200
+Subject: genetlink: add CAP_NET_ADMIN test for multicast bind
+To: <stable@vger.kernel.org>
+Cc: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>, <edumazet@google.com>, <nhorman@tuxdriver.com>, <yotam.gi@gmail.com>, <sashal@kernel.org>, <fw@strlen.de>, <jacob.e.keller@intel.com>, <jiri@nvidia.com>
+Message-ID: <20231211124301.822961-3-idosch@nvidia.com>
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+This is a partial backport of upstream commit 4d54cc32112d ("mptcp:
+avoid lock_fast usage in accept path"). It is only a partial backport
+because the patch in the link below was erroneously squash-merged into
+upstream commit 4d54cc32112d ("mptcp: avoid lock_fast usage in accept
+path"). Below is the original patch description from Florian Westphal:
+
+"
+genetlink sets NL_CFG_F_NONROOT_RECV for its netlink socket so anyone can
+subscribe to multicast messages.
+
+rtnetlink doesn't allow this unconditionally, rtnetlink_bind() restricts
+bind requests to CAP_NET_ADMIN for a few groups.
+
+This allows to set GENL_UNS_ADMIN_PERM flag on genl mcast groups to
+mandate CAP_NET_ADMIN.
+
+This will be used by the upcoming mptcp netlink event facility which
+exposes the token (mptcp connection identifier) to userspace.
+"
+
+Link: https://lore.kernel.org/mptcp/20210213000001.379332-8-mathew.j.martineau@linux.intel.com/
+Signed-off-by: Ido Schimmel <idosch@nvidia.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ include/net/genetlink.h | 1 +
+ net/netlink/genetlink.c | 32 ++++++++++++++++++++++++++++++++
+ 2 files changed, 33 insertions(+)
+
+--- a/include/net/genetlink.h
++++ b/include/net/genetlink.h
+@@ -14,6 +14,7 @@
+ */
+ struct genl_multicast_group {
+ char name[GENL_NAMSIZ];
++ u8 flags;
+ };
+
+ struct genl_ops;
+--- a/net/netlink/genetlink.c
++++ b/net/netlink/genetlink.c
+@@ -959,11 +959,43 @@ static struct genl_family genl_ctrl __ro
+ .netnsok = true,
+ };
+
++static int genl_bind(struct net *net, int group)
++{
++ const struct genl_family *family;
++ unsigned int id;
++ int ret = 0;
++
++ genl_lock_all();
++
++ idr_for_each_entry(&genl_fam_idr, family, id) {
++ const struct genl_multicast_group *grp;
++ int i;
++
++ if (family->n_mcgrps == 0)
++ continue;
++
++ i = group - family->mcgrp_offset;
++ if (i < 0 || i >= family->n_mcgrps)
++ continue;
++
++ grp = &family->mcgrps[i];
++ if ((grp->flags & GENL_UNS_ADMIN_PERM) &&
++ !ns_capable(net->user_ns, CAP_NET_ADMIN))
++ ret = -EPERM;
++
++ break;
++ }
++
++ genl_unlock_all();
++ return ret;
++}
++
+ static int __net_init genl_pernet_init(struct net *net)
+ {
+ struct netlink_kernel_cfg cfg = {
+ .input = genl_rcv,
+ .flags = NL_CFG_F_NONROOT_RECV,
++ .bind = genl_bind,
+ };
+
+ /* we'll bump the group number right afterwards */
--- /dev/null
+From stable+bounces-5309-greg=kroah.com@vger.kernel.org Mon Dec 11 13:43:47 2023
+From: Ido Schimmel <idosch@nvidia.com>
+Date: Mon, 11 Dec 2023 14:42:58 +0200
+Subject: netlink: don't call ->netlink_bind with table lock held
+To: <stable@vger.kernel.org>
+Cc: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>, <edumazet@google.com>, <nhorman@tuxdriver.com>, <yotam.gi@gmail.com>, <sashal@kernel.org>, <fw@strlen.de>, <jacob.e.keller@intel.com>, <jiri@nvidia.com>
+Message-ID: <20231211124301.822961-2-idosch@nvidia.com>
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+From: Florian Westphal <fw@strlen.de>
+
+commit f2764bd4f6a8dffaec3e220728385d9756b3c2cb upstream.
+
+When I added support to allow generic netlink multicast groups to be
+restricted to subscribers with CAP_NET_ADMIN I was unaware that a
+genl_bind implementation already existed in the past.
+
+It was reverted due to ABBA deadlock:
+
+1. ->netlink_bind gets called with the table lock held.
+2. genetlink bind callback is invoked, it grabs the genl lock.
+
+But when a new genl subsystem is (un)registered, these two locks are
+taken in reverse order.
+
+One solution would be to revert again and add a comment in genl
+referring 1e82a62fec613, "genetlink: remove genl_bind").
+
+This would need a second change in mptcp to not expose the raw token
+value anymore, e.g. by hashing the token with a secret key so userspace
+can still associate subflow events with the correct mptcp connection.
+
+However, Paolo Abeni reminded me to double-check why the netlink table is
+locked in the first place.
+
+I can't find one. netlink_bind() is already called without this lock
+when userspace joins a group via NETLINK_ADD_MEMBERSHIP setsockopt.
+Same holds for the netlink_unbind operation.
+
+Digging through the history, commit f773608026ee1
+("netlink: access nlk groups safely in netlink bind and getname")
+expanded the lock scope.
+
+commit 3a20773beeeeade ("net: netlink: cap max groups which will be considered in netlink_bind()")
+... removed the nlk->ngroups access that the lock scope
+extension was all about.
+
+Reduce the lock scope again and always call ->netlink_bind without
+the table lock.
+
+The Fixes tag should be vs. the patch mentioned in the link below,
+but that one got squash-merged into the patch that came earlier in the
+series.
+
+Fixes: 4d54cc32112d8d ("mptcp: avoid lock_fast usage in accept path")
+Link: https://lore.kernel.org/mptcp/20210213000001.379332-8-mathew.j.martineau@linux.intel.com/T/#u
+Cc: Cong Wang <xiyou.wangcong@gmail.com>
+Cc: Xin Long <lucien.xin@gmail.com>
+Cc: Johannes Berg <johannes.berg@intel.com>
+Cc: Sean Tranchetti <stranche@codeaurora.org>
+Cc: Paolo Abeni <pabeni@redhat.com>
+Cc: Pablo Neira Ayuso <pablo@netfilter.org>
+Signed-off-by: Florian Westphal <fw@strlen.de>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Ido Schimmel <idosch@nvidia.com>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/netlink/af_netlink.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+--- a/net/netlink/af_netlink.c
++++ b/net/netlink/af_netlink.c
+@@ -1001,7 +1001,6 @@ static int netlink_bind(struct socket *s
+ return -EINVAL;
+ }
+
+- netlink_lock_table();
+ if (nlk->netlink_bind && groups) {
+ int group;
+
+@@ -1013,13 +1012,14 @@ static int netlink_bind(struct socket *s
+ if (!err)
+ continue;
+ netlink_undo_bind(group, groups, sk);
+- goto unlock;
++ return err;
+ }
+ }
+
+ /* No need for barriers here as we return to user-space without
+ * using any of the bound attributes.
+ */
++ netlink_lock_table();
+ if (!bound) {
+ err = nladdr->nl_pid ?
+ netlink_insert(sk, nladdr->nl_pid) :
nilfs_release_super_block(nilfs);
- sb_set_blocksize(sb, blocksize);
+ if (!sb_set_blocksize(sb, blocksize)) {
-+ nilfs_error(sb, "bad blocksize %d", blocksize);
++ nilfs_msg(sb, KERN_ERR, "bad blocksize %d", blocksize);
+ err = -EINVAL;
+ goto out;
+ }
--- /dev/null
+From stable+bounces-5311-greg=kroah.com@vger.kernel.org Mon Dec 11 13:43:59 2023
+From: Ido Schimmel <idosch@nvidia.com>
+Date: Mon, 11 Dec 2023 14:43:00 +0200
+Subject: psample: Require 'CAP_NET_ADMIN' when joining "packets" group
+To: <stable@vger.kernel.org>
+Cc: <davem@davemloft.net>, <kuba@kernel.org>, <pabeni@redhat.com>, <edumazet@google.com>, <nhorman@tuxdriver.com>, <yotam.gi@gmail.com>, <sashal@kernel.org>, <fw@strlen.de>, <jacob.e.keller@intel.com>, <jiri@nvidia.com>
+Message-ID: <20231211124301.822961-4-idosch@nvidia.com>
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+commit 44ec98ea5ea9cfecd31a5c4cc124703cb5442832 upstream.
+
+The "psample" generic netlink family notifies sampled packets over the
+"packets" multicast group. This is problematic since by default generic
+netlink allows non-root users to listen to these notifications.
+
+Fix by marking the group with the 'GENL_UNS_ADMIN_PERM' flag. This will
+prevent non-root users or root without the 'CAP_NET_ADMIN' capability
+(in the user namespace owning the network namespace) from joining the
+group.
+
+Tested using [1].
+
+Before:
+
+ # capsh -- -c ./psample_repo
+ # capsh --drop=cap_net_admin -- -c ./psample_repo
+
+After:
+
+ # capsh -- -c ./psample_repo
+ # capsh --drop=cap_net_admin -- -c ./psample_repo
+ Failed to join "packets" multicast group
+
+[1]
+ $ cat psample.c
+ #include <stdio.h>
+ #include <netlink/genl/ctrl.h>
+ #include <netlink/genl/genl.h>
+ #include <netlink/socket.h>
+
+ int join_grp(struct nl_sock *sk, const char *grp_name)
+ {
+ int grp, err;
+
+ grp = genl_ctrl_resolve_grp(sk, "psample", grp_name);
+ if (grp < 0) {
+ fprintf(stderr, "Failed to resolve \"%s\" multicast group\n",
+ grp_name);
+ return grp;
+ }
+
+ err = nl_socket_add_memberships(sk, grp, NFNLGRP_NONE);
+ if (err) {
+ fprintf(stderr, "Failed to join \"%s\" multicast group\n",
+ grp_name);
+ return err;
+ }
+
+ return 0;
+ }
+
+ int main(int argc, char **argv)
+ {
+ struct nl_sock *sk;
+ int err;
+
+ sk = nl_socket_alloc();
+ if (!sk) {
+ fprintf(stderr, "Failed to allocate socket\n");
+ return -1;
+ }
+
+ err = genl_connect(sk);
+ if (err) {
+ fprintf(stderr, "Failed to connect socket\n");
+ return err;
+ }
+
+ err = join_grp(sk, "config");
+ if (err)
+ return err;
+
+ err = join_grp(sk, "packets");
+ if (err)
+ return err;
+
+ return 0;
+ }
+ $ gcc -I/usr/include/libnl3 -lnl-3 -lnl-genl-3 -o psample_repo psample.c
+
+Fixes: 6ae0a6286171 ("net: Introduce psample, a new genetlink channel for packet sampling")
+Reported-by: "The UK's National Cyber Security Centre (NCSC)" <security@ncsc.gov.uk>
+Signed-off-by: Ido Schimmel <idosch@nvidia.com>
+Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
+Reviewed-by: Jiri Pirko <jiri@nvidia.com>
+Link: https://lore.kernel.org/r/20231206213102.1824398-2-idosch@nvidia.com
+Signed-off-by: Jakub Kicinski <kuba@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/psample/psample.c | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+--- a/net/psample/psample.c
++++ b/net/psample/psample.c
+@@ -31,7 +31,8 @@ enum psample_nl_multicast_groups {
+
+ static const struct genl_multicast_group psample_nl_mcgrps[] = {
+ [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME },
+- [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME },
++ [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME,
++ .flags = GENL_UNS_ADMIN_PERM },
+ };
+
+ static struct genl_family psample_nl_family __ro_after_init;
tracing-fix-a-warning-when-allocating-buffered-event.patch
scsi-be2iscsi-fix-a-memleak-in-beiscsi_init_wrb_hand.patch
alsa-pcm-fix-out-of-bounds-in-snd_pcm_state_names.patch
-nilfs2-fix-missing-error-check-for-sb_set_blocksize-call.patch
nilfs2-prevent-warning-in-nilfs_sufile_set_segment_usage.patch
tracing-always-update-snapshot-buffer-size.patch
tracing-fix-incomplete-locking-when-disabling-buffered-events.patch
serial-sc16is7xx-address-rx-timeout-interrupt-errata.patch
serial-8250_omap-add-earlycon-support-for-the-am654-uart-controller.patch
kvm-s390-mm-properly-reset-no-dat.patch
+nilfs2-fix-missing-error-check-for-sb_set_blocksize-call.patch
+netlink-don-t-call-netlink_bind-with-table-lock-held.patch
+genetlink-add-cap_net_admin-test-for-multicast-bind.patch
+psample-require-cap_net_admin-when-joining-packets-group.patch
+drop_monitor-require-cap_sys_admin-when-joining-events-group.patch
projects / thirdparty / kernel / stable-queue.git / commitdiff
