[PATCH ghak124 v3] audit: log nftables configuration change events
by Richard Guy Briggs
iptables, ip6tables, arptables and ebtables table registration,
replacement and unregistration configuration events are logged for the
native (legacy) iptables setsockopt api, but not for the
nftables netlink api which is used by the nft-variant of iptables in
addition to nftables itself.
Add calls to log the configuration actions in the nftables netlink api.
This uses the same NETFILTER_CFG record format but overloads the table
field.
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=?:0;?:0 family=unspecified entries=2 op=nft_register_gen pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
...
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.878:162) : table=firewalld:1;?:0 family=inet entries=0 op=nft_register_table pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
...
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=8 op=nft_register_chain pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
...
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;filter_FORWARD:85 family=inet entries=101 op=nft_register_rule pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
...
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=87 op=nft_register_setelem pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
...
type=NETFILTER_CFG msg=audit(2020-05-28 17:46:41.911:163) : table=firewalld:1;__set0:87 family=inet entries=0 op=nft_register_set pid=396 subj=system_u:system_r:firewalld_t:s0 comm=firewalld
For further information please see issue
https://github.com/linux-audit/audit-kernel/issues/124
Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com>
---
Changelog:
v3:
- inline message type rather than table
v2:
- differentiate between xtables and nftables
- add set, setelem, obj, flowtable, gen
- use nentries field as appropriate per type
- overload the "tables" field with table handle and chain/set/flowtable
include/linux/audit.h | 18 ++++++++
kernel/auditsc.c | 24 ++++++++--
net/netfilter/nf_tables_api.c | 103 ++++++++++++++++++++++++++++++++++++++++++
3 files changed, 142 insertions(+), 3 deletions(-)
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 3fcd9ee49734..604ede630580 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -12,6 +12,7 @@
#include <linux/sched.h>
#include <linux/ptrace.h>
#include <uapi/linux/audit.h>
+#include <uapi/linux/netfilter/nf_tables.h>
#define AUDIT_INO_UNSET ((unsigned long)-1)
#define AUDIT_DEV_UNSET ((dev_t)-1)
@@ -98,6 +99,23 @@ enum audit_nfcfgop {
AUDIT_XT_OP_REGISTER,
AUDIT_XT_OP_REPLACE,
AUDIT_XT_OP_UNREGISTER,
+ AUDIT_NFT_OP_TABLE_REGISTER,
+ AUDIT_NFT_OP_TABLE_UNREGISTER,
+ AUDIT_NFT_OP_CHAIN_REGISTER,
+ AUDIT_NFT_OP_CHAIN_UNREGISTER,
+ AUDIT_NFT_OP_RULE_REGISTER,
+ AUDIT_NFT_OP_RULE_UNREGISTER,
+ AUDIT_NFT_OP_SET_REGISTER,
+ AUDIT_NFT_OP_SET_UNREGISTER,
+ AUDIT_NFT_OP_SETELEM_REGISTER,
+ AUDIT_NFT_OP_SETELEM_UNREGISTER,
+ AUDIT_NFT_OP_GEN_REGISTER,
+ AUDIT_NFT_OP_OBJ_REGISTER,
+ AUDIT_NFT_OP_OBJ_UNREGISTER,
+ AUDIT_NFT_OP_OBJ_RESET,
+ AUDIT_NFT_OP_FLOWTABLE_REGISTER,
+ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+ AUDIT_NFT_OP_INVALID,
};
extern int is_audit_feature_set(int which);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 468a23390457..3a9100e95fda 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -75,6 +75,7 @@
#include <linux/uaccess.h>
#include <linux/fsnotify_backend.h>
#include <uapi/linux/limits.h>
+#include <uapi/linux/netfilter/nf_tables.h>
#include "audit.h"
@@ -136,9 +137,26 @@ struct audit_nfcfgop_tab {
};
static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
- { AUDIT_XT_OP_REGISTER, "register" },
- { AUDIT_XT_OP_REPLACE, "replace" },
- { AUDIT_XT_OP_UNREGISTER, "unregister" },
+ { AUDIT_XT_OP_REGISTER, "xt_register" },
+ { AUDIT_XT_OP_REPLACE, "xt_replace" },
+ { AUDIT_XT_OP_UNREGISTER, "xt_unregister" },
+ { AUDIT_NFT_OP_TABLE_REGISTER, "nft_register_table" },
+ { AUDIT_NFT_OP_TABLE_UNREGISTER, "nft_unregister_table" },
+ { AUDIT_NFT_OP_CHAIN_REGISTER, "nft_register_chain" },
+ { AUDIT_NFT_OP_CHAIN_UNREGISTER, "nft_unregister_chain" },
+ { AUDIT_NFT_OP_RULE_REGISTER, "nft_register_rule" },
+ { AUDIT_NFT_OP_RULE_UNREGISTER, "nft_unregister_rule" },
+ { AUDIT_NFT_OP_SET_REGISTER, "nft_register_set" },
+ { AUDIT_NFT_OP_SET_UNREGISTER, "nft_unregister_set" },
+ { AUDIT_NFT_OP_SETELEM_REGISTER, "nft_register_setelem" },
+ { AUDIT_NFT_OP_SETELEM_UNREGISTER, "nft_unregister_setelem" },
+ { AUDIT_NFT_OP_GEN_REGISTER, "nft_register_gen" },
+ { AUDIT_NFT_OP_OBJ_REGISTER, "nft_register_obj" },
+ { AUDIT_NFT_OP_OBJ_UNREGISTER, "nft_unregister_obj" },
+ { AUDIT_NFT_OP_OBJ_RESET, "nft_reset_obj" },
+ { AUDIT_NFT_OP_FLOWTABLE_REGISTER, "nft_register_flowtable" },
+ { AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, "nft_unregister_flowtable" },
+ { AUDIT_NFT_OP_INVALID, "nft_invalid" },
};
static int audit_match_perm(struct audit_context *ctx, int mask)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3558e76e2733..b9e7440cc87d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -12,6 +12,7 @@
#include <linux/netlink.h>
#include <linux/vmalloc.h>
#include <linux/rhashtable.h>
+#include <linux/audit.h>
#include <linux/netfilter.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nf_tables.h>
@@ -693,6 +694,16 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event)
{
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+ ctx->table->name, ctx->table->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ ctx->table->use,
+ event == NFT_MSG_NEWTABLE ?
+ AUDIT_NFT_OP_TABLE_REGISTER :
+ AUDIT_NFT_OP_TABLE_UNREGISTER);
+ kfree(buf);
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -1428,6 +1439,17 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event)
{
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+ ctx->table->name, ctx->table->handle,
+ ctx->chain->name, ctx->chain->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ ctx->chain->use,
+ event == NFT_MSG_NEWCHAIN ?
+ AUDIT_NFT_OP_CHAIN_REGISTER :
+ AUDIT_NFT_OP_CHAIN_UNREGISTER);
+ kfree(buf);
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -2691,6 +2713,17 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
{
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+ ctx->table->name, ctx->table->handle,
+ ctx->chain->name, ctx->chain->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ rule->handle,
+ event == NFT_MSG_NEWRULE ?
+ AUDIT_NFT_OP_RULE_REGISTER :
+ AUDIT_NFT_OP_RULE_UNREGISTER);
+ kfree(buf);
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -3693,6 +3726,17 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx,
struct sk_buff *skb;
u32 portid = ctx->portid;
int err;
+ char *buf = kasprintf(gfp_flags, "%s:%llu;%s:%llu",
+ ctx->table->name, ctx->table->handle,
+ set->name, set->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ set->field_count,
+ event == NFT_MSG_NEWSET ?
+ AUDIT_NFT_OP_SET_REGISTER :
+ AUDIT_NFT_OP_SET_UNREGISTER);
+ kfree(buf);
if (!ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -4809,6 +4853,17 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx,
u32 portid = ctx->portid;
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+ ctx->table->name, ctx->table->handle,
+ set->name, set->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ set->handle,
+ event == NFT_MSG_NEWSETELEM ?
+ AUDIT_NFT_OP_SETELEM_REGISTER :
+ AUDIT_NFT_OP_SETELEM_UNREGISTER);
+ kfree(buf);
if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
return;
@@ -5890,6 +5945,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
obj->ops->type->type != filter->type)
goto cont;
+ if (reset) {
+ char *buf = kasprintf(GFP_KERNEL,
+ "%s:%llu;?:0",
+ table->name,
+ table->handle);
+
+ audit_log_nfcfg(buf,
+ family,
+ obj->handle,
+ AUDIT_NFT_OP_OBJ_RESET);
+ kfree(buf);
+ }
+
if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NFT_MSG_NEWOBJ,
@@ -6000,6 +6068,17 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
if (NFNL_MSG_TYPE(nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
reset = true;
+ if (reset) {
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+ table->name, table->handle);
+
+ audit_log_nfcfg(buf,
+ family,
+ obj->handle,
+ AUDIT_NFT_OP_OBJ_RESET);
+ kfree(buf);
+ }
+
err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
family, table, obj, reset);
@@ -6075,6 +6154,16 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
{
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;?:0",
+ table->name, table->handle);
+
+ audit_log_nfcfg(buf,
+ family,
+ obj->handle,
+ event == NFT_MSG_NEWOBJ ?
+ AUDIT_NFT_OP_OBJ_REGISTER :
+ AUDIT_NFT_OP_OBJ_UNREGISTER);
+ kfree(buf);
if (!report &&
!nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
@@ -6701,6 +6790,17 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
{
struct sk_buff *skb;
int err;
+ char *buf = kasprintf(GFP_KERNEL, "%s:%llu;%s:%llu",
+ flowtable->table->name, flowtable->table->handle,
+ flowtable->name, flowtable->handle);
+
+ audit_log_nfcfg(buf,
+ ctx->family,
+ flowtable->hooknum,
+ event == NFT_MSG_NEWFLOWTABLE ?
+ AUDIT_NFT_OP_FLOWTABLE_REGISTER :
+ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER);
+ kfree(buf);
if (ctx->report &&
!nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
@@ -6822,6 +6922,9 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
struct sk_buff *skb2;
int err;
+ audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
+ AUDIT_NFT_OP_GEN_REGISTER);
+
if (nlmsg_report(nlh) &&
!nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
return;
--
1.8.3.1
3 years, 8 months
[PATCH v2] audit: report audit wait metric in audit status reply
by Max Englander
In environments where the preservation of audit events and predictable
usage of system memory are prioritized, admins may use a combination of
--backlog_wait_time and -b options at the risk of degraded performance
resulting from backlog waiting. In some cases, this risk may be
preferred to lost events or unbounded memory usage. Ideally, this risk
can be mitigated by making adjustments when backlog waiting is detected.
However, detection can be diffult using the currently available metrics.
For example, an admin attempting to debug degraded performance may
falsely believe a full backlog indicates backlog waiting. It may turn
out the backlog frequently fills up but drains quickly.
To make it easier to reliably track degraded performance to backlog
waiting, this patch makes the following changes:
Add a new field backlog_wait_sum to the audit status reply. Initialize
this field to zero. Add to this field the total time spent by the
current task on scheduled timeouts while the backlog limit is exceeded.
Tested on Ubuntu 18.04 using complementary changes to the audit
userspace: https://github.com/linux-audit/audit-userspace/pull/134.
Signed-off-by: Max Englander <max.englander(a)gmail.com>
---
Patch changelogs between v1 and v2:
- Instead of printing a warning when backlog waiting occurs, add
duration of backlog waiting to cumulative sum, and report this
sum in audit status reply.
include/uapi/linux/audit.h | 7 ++++++-
kernel/audit.c | 9 +++++++++
2 files changed, 15 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index a534d71e689a..ea0cc364beca 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -340,6 +340,7 @@ enum {
#define AUDIT_STATUS_BACKLOG_LIMIT 0x0010
#define AUDIT_STATUS_BACKLOG_WAIT_TIME 0x0020
#define AUDIT_STATUS_LOST 0x0040
+#define AUDIT_STATUS_BACKLOG_WAIT_SUM 0x0080
#define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT 0x00000001
#define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME 0x00000002
@@ -348,6 +349,7 @@ enum {
#define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010
#define AUDIT_FEATURE_BITMAP_LOST_RESET 0x00000020
#define AUDIT_FEATURE_BITMAP_FILTER_FS 0x00000040
+#define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_SUM 0x00000080
#define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \
AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \
@@ -355,12 +357,14 @@ enum {
AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND | \
AUDIT_FEATURE_BITMAP_SESSIONID_FILTER | \
AUDIT_FEATURE_BITMAP_LOST_RESET | \
- AUDIT_FEATURE_BITMAP_FILTER_FS)
+ AUDIT_FEATURE_BITMAP_FILTER_FS | \
+ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_SUM)
/* deprecated: AUDIT_VERSION_* */
#define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL
#define AUDIT_VERSION_BACKLOG_LIMIT AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT
#define AUDIT_VERSION_BACKLOG_WAIT_TIME AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME
+#define AUDIT_VERSION_BACKLOG_WAIT_SUM AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_SUM
/* Failure-to-log actions */
#define AUDIT_FAIL_SILENT 0
@@ -466,6 +470,7 @@ struct audit_status {
__u32 feature_bitmap; /* bitmap of kernel audit features */
};
__u32 backlog_wait_time;/* message queue wait timeout */
+ __u32 backlog_wait_sum;/* time spent waiting while message limit exceeded */
};
struct audit_features {
diff --git a/kernel/audit.c b/kernel/audit.c
index 87f31bf1f0a0..301ea4f3d750 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -136,6 +136,11 @@ u32 audit_sig_sid = 0;
*/
static atomic_t audit_lost = ATOMIC_INIT(0);
+/* Monotonically increasing sum of time the kernel has spent
+ * waiting while the backlog limit is exceeded.
+ */
+static atomic_t audit_backlog_wait_sum = ATOMIC_INIT(0);
+
/* Hash for inode-based rules */
struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];
@@ -1204,6 +1209,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
s.backlog = skb_queue_len(&audit_queue);
s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL;
s.backlog_wait_time = audit_backlog_wait_time;
+ s.backlog_wait_sum = atomic_read(&audit_backlog_wait_sum);
audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
break;
}
@@ -1794,6 +1800,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
return NULL;
}
}
+
+ if (stime != audit_backlog_wait_time)
+ atomic_add(audit_backlog_wait_time - stime, &audit_backlog_wait_sum);
}
ab = audit_buffer_alloc(ctx, gfp_mask, type);
--
2.17.1
3 years, 10 months
[PATCH ghak90 V9 00/13] audit: implement container identifier
by Richard Guy Briggs
Implement kernel audit container identifier.
This patchset is an eighth based on the proposal document (V4) posted:
https://www.redhat.com/archives/linux-audit/2019-September/msg00052.html
The first patch was the last patch from ghak81 that was absorbed into
this patchset since its primary justification is the rest of this
patchset.
The second patch implements the proc fs write to set the audit container
identifier of a process, emitting an AUDIT_CONTAINER_OP record to
announce the registration of that audit container identifier on that
process. This patch requires userspace support for record acceptance
and proper type display. This patch now includes the conversion
over from a simple u64 to a list member that includes owner information
to check for descendancy, allow process injection into a container and
prevent id reuse by other orchestrators.
The third implements reading the audit container identifier from the
proc filesystem for debugging. This patch wasn't planned for upstream
inclusion but is starting to become more likely.
The fourth logs the drop of an audit container identifier once all tasks
using that audit container identifier have exited.
The 5th implements the auxiliary record AUDIT_CONTAINER_ID if an audit
container identifier is associated with an event. This patch requires
userspace support for proper type display.
The 6th adds audit daemon signalling provenance through audit_sig_info2.
The 7th creates a local audit context to be able to bind a standalone
record with a locally created auxiliary record.
The 8th patch adds audit container identifier records to the user
standalone records.
The 9th adds audit container identifier filtering to the exit,
exclude and user lists. This patch adds the AUDIT_CONTID field and
requires auditctl userspace support for the --contid option.
The 10th adds network namespace audit container identifier labelling
based on member tasks' audit container identifier labels which supports
standalone netfilter records that don't have a task context and lists
each container to which that net namespace belongs.
The 11th checks that the target is a descendant for nesting and
refactors to avoid a duplicate of the copied function.
The 12th adds tracking and reporting for container nesting.
This enables kernel filtering and userspace searches of nested audit
container identifiers.
The 13th adds a mechanism to allow a process to be designated as a
container orchestrator/engine in non-init user namespaces.
Example: Set an audit container identifier of 123456 to the "sleep" task:
sleep 2&
child=$!
echo 123456 > /proc/$child/audit_containerid; echo $?
ausearch -ts recent -m container_op
echo child:$child contid:$( cat /proc/$child/audit_containerid)
This should produce a record such as:
type=CONTAINER_OP msg=audit(2018-06-06 12:39:29.636:26949) : op=set opid=2209 contid=123456 old-contid=18446744073709551615
Example: Set a filter on an audit container identifier 123459 on /tmp/tmpcontainerid:
contid=123459
key=tmpcontainerid
auditctl -a exit,always -F dir=/tmp -F perm=wa -F contid=$contid -F key=$key
perl -e "sleep 1; open(my \$tmpfile, '>', \"/tmp/$key\"); close(\$tmpfile);" &
child=$!
echo $contid > /proc/$child/audit_containerid
sleep 2
ausearch -i -ts recent -k $key
auditctl -d exit,always -F dir=/tmp -F perm=wa -F contid=$contid -F key=$key
rm -f /tmp/$key
This should produce an event such as:
type=CONTAINER_ID msg=audit(2018-06-06 12:46:31.707:26953) : contid=123459
type=PROCTITLE msg=audit(2018-06-06 12:46:31.707:26953) : proctitle=perl -e sleep 1; open(my $tmpfile, '>', "/tmp/tmpcontainerid"); close($tmpfile);
type=PATH msg=audit(2018-06-06 12:46:31.707:26953) : item=1 name=/tmp/tmpcontainerid inode=25656 dev=00:26 mode=file,644 ouid=root ogid=root rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=none cap_fi=none cap_fe=0 cap_fver=0
type=PATH msg=audit(2018-06-06 12:46:31.707:26953) : item=0 name=/tmp/ inode=8985 dev=00:26 mode=dir,sticky,777 ouid=root ogid=root rdev=00:00 obj=system_u:object_r:tmp_t:s0 nametype=PARENT cap_fp=none cap_fi=none cap_fe=0 cap_fver=0
type=CWD msg=audit(2018-06-06 12:46:31.707:26953) : cwd=/root
type=SYSCALL msg=audit(2018-06-06 12:46:31.707:26953) : arch=x86_64 syscall=openat success=yes exit=3 a0=0xffffffffffffff9c a1=0x5621f2b81900 a2=O_WRONLY|O_CREAT|O_TRUNC a3=0x1b6 items=2 ppid=628 pid=2232 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=ttyS0 ses=1 comm=perl exe=/usr/bin/perl subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=tmpcontainerid
Example: Test multiple containers on one netns:
sleep 5 &
child1=$!
containerid1=123451
echo $containerid1 > /proc/$child1/audit_containerid
sleep 5 &
child2=$!
containerid2=123452
echo $containerid2 > /proc/$child2/audit_containerid
iptables -I INPUT -i lo -p icmp --icmp-type echo-request -j AUDIT --type accept
iptables -I INPUT -t mangle -i lo -p icmp --icmp-type echo-request -j MARK --set-mark 0x12345555
sleep 1;
bash -c "ping -q -c 1 127.0.0.1 >/dev/null 2>&1"
sleep 1;
ausearch -i -m NETFILTER_PKT -ts boot|grep mark=0x12345555
ausearch -i -m NETFILTER_PKT -ts boot|grep contid=|grep $containerid1|grep $containerid2
This would produce an event such as:
type=NETFILTER_PKT msg=audit(03/15/2019 14:16:13.369:244) : mark=0x12345555 saddr=127.0.0.1 daddr=127.0.0.1 proto=icmp
type=CONTAINER_ID msg=audit(03/15/2019 14:16:13.369:244) : contid=123452,123451
Includes the last patch of https://github.com/linux-audit/audit-kernel/issues/81
Please see the github audit kernel issue for the main feature:
https://github.com/linux-audit/audit-kernel/issues/90
and the kernel filter code:
https://github.com/linux-audit/audit-kernel/issues/91
and the network support:
https://github.com/linux-audit/audit-kernel/issues/92
Please see the github audit userspace issue for supporting record types:
https://github.com/linux-audit/audit-userspace/issues/51
and filter code:
https://github.com/linux-audit/audit-userspace/issues/40
Please see the github audit testsuiite issue for the test case:
https://github.com/linux-audit/audit-testsuite/issues/64
https://github.com/rgbriggs/audit-testsuite/tree/ghat64-contid
https://githu.com/linux-audit/audit-testsuite/pull/91
Please see the github audit wiki for the feature overview:
https://github.com/linux-audit/audit-kernel/wiki/RFE-Audit-Container-ID
The code is also posted at:
git://toccata2.tricolour.ca/linux-2.6-rgb.git ghak90-audit-containerID.v9
Changelog:
v9
- rebase on v5.8-rc1
- fix whitespace and oversize lines where practicable
- remove harmless duplicate S_IRUSR in capcontid
- return -EBUSY for both threading and children (drop -EALREADY)
- return -EEXIST if already set and not nesting (drop -ECHILD)
- fix unbalanced brace and remove elseif ladder
- drop check for same contid set again as redundant (drop -EADDRINUSE)
- get reference to contobj's parent taskstruct
- protect all contid list updates with audit_contobj_list_lock
- protect refcounts with rcu read lock
- convert _audit_contobj to _audit_contobj_get, which calls _audit_contobj_hold
- convert audit_log_container_id() and audit_log_contid() from u64 to contobj, simplifying
- issue death certificate on contid after exit of last task
- keep contobj ref to block reuse with -ESHUTDOWN until auditd exit or signal info
- report all contids nested
- rework sig_info2 format to accomodate contid list
- fix zero-length array in include/linux/audit.h struct audit_sig_info2 data[]
- found bug in audit_alloc_local, don't check audit_ever_enabled, since all callers check audit_enabled
- remove warning at declaration of audit_sig_cid of reuse since reuse is now blocked
- report descendancy checking errcodes under -EXDEV (drop -EBADSLT)
- add missed check, replace audit_contid_isowner with audit_contid_isnesting
- limit calls to audit_log_format() with if(iter->parent) ...
- list only one contid in contid, nested in old-contid to avoid duplication
- switch to comma delimiter, carrat modifier in nested contid list
- special case -1 for AUDIT_CID_UNSET printing
- drop contid depth limit and netns contid limit patches
- enforce capcontid policy on contid write and read
- squash conversion to contobj into contid intro patch
v8
- rebase on v5.5-rc1 audit/next
- remove subject attrs in CONTAINER_OP record
- group audit_contid_list_lock with audit_contid_hash
- in audit_{set,log}_contid(), break out of loop after finding target
- use target var to size kmalloc
- rework audit_cont_owner() to bool audit_contid_isowner() and move to where used
- create static void audit_cont_hold(struct audit_contobj *cont) { refcount_inc(&cont->refcount); }
- rename audit_cont{,_*} refs to audit_contobj{,_*}
- prefix special local functions with _ [audit_contobj*()]
- protect contid list traversals with rcu_read_lock() and updates with audit_contid_list_lock
- protect real_parent in audit_contid_depth() with rcu_dereference
- give new contid field nesting format in patch description
- squash task_is_descendant()
- squash support for NETFILTER_PKT into network namespaces
- limit nesting depth based on record length overflow, bandwidth and storage
- implent control for audit container identifier nesting depth limit
- make room for audit_bpf patches (bump CONTAINER_ID to 1335)
- squash proc interface into capcontid
- remove netlink access to loginuid/sessionid/contid/capcontid
- delete 32k contid limit patch
- document potential overlap between signal delivery and contid reuse
- document audit_contobj_list_lock coverage
- document disappearing orch task injection limitation
- limit the number of containers that can be associated with a network namespace
- implent control for audit container identifier netns count limit
v7
- remove BUG() in audit_comparator64()
- rebase on v5.2-rc1 audit/next
- resolve merge conflict with ghak111 (signal_info regardless syscall)
- resolve merge conflict with ghak73 (audit_field_valid)
- resolve merge conflict with ghak64 (saddr_fam filter)
- resolve merge conflict with ghak10 (ntp audit) change AUDIT_CONTAINER_ID from 1332 to 1334
- rebase on v5.3-rc1 audit/next
- track container owner
- only permit setting contid of descendants for nesting
- track drop of contid and permit reuse
- track and report container nesting
- permit filtering on any nested contid
- set/get contid and loginuid/sessionid via netlink
- implement capcontid to enable orchestrators in non-init user
namespaces
- limit number of containers
- limit depth of container nesting
v6
- change TMPBUFLEN from 11 to 21 to cover the decimal value of contid
u64 (nhorman)
- fix bug overwriting ctx in struct audit_sig_info, move cid above
ctx[0] (nhorman)
- fix bug skipping remaining fields and not advancing bufp when copying
out contid in audit_krule_to_data (omosnacec)
- add acks, tidy commit descriptions, other formatting fixes (checkpatch
wrong on audit_log_lost)
- cast ull for u64 prints
- target_cid tracking was moved from the ptrace/signal patch to
container_op
- target ptrace and signal records were moved from the ptrace/signal
patch to container_id
- auditd signaller tracking was moved to a new AUDIT_SIGNAL_INFO2
request and record
- ditch unnecessary list_empty() checks
- check for null net and aunet in audit_netns_contid_add()
- swap CONTAINER_OP contid/old-contid order to ease parsing
v5
- address loginuid and sessionid syscall scope in ghak104
- address audit_context in CONFIG_AUDIT vs CONFIG_AUDITSYSCALL in ghak105
- remove tty patch, addressed in ghak106
- rebase on audit/next v5.0-rc1
w/ghak59/ghak104/ghak103/ghak100/ghak107/ghak105/ghak106/ghak105sup
- update CONTAINER_ID to CONTAINER_OP in patch description
- move audit_context in audit_task_info to CONFIG_AUDITSYSCALL
- move audit_alloc() and audit_free() out of CONFIG_AUDITSYSCALL and into
CONFIG_AUDIT and create audit_{alloc,free}_syscall
- use plain kmem_cache_alloc() rather than kmem_cache_zalloc() in audit_alloc()
- fix audit_get_contid() declaration type error
- move audit_set_contid() from auditsc.c to audit.c
- audit_log_contid() returns void
- audit_log_contid() handed contid rather than tsk
- switch from AUDIT_CONTAINER to AUDIT_CONTAINER_ID for aux record
- move audit_log_contid(tsk/contid) & audit_contid_set(tsk)/audit_contid_valid(contid)
- switch from tsk to current
- audit_alloc_local() calls audit_log_lost() on failure to allocate a context
- add AUDIT_USER* non-syscall contid record
- cosmetic cleanup double parens, goto out on err
- ditch audit_get_ns_contid_list_lock(), fix aunet lock race
- switch from all-cpu read spinlock to rcu, keep spinlock for write
- update audit_alloc_local() to use ktime_get_coarse_real_ts64()
- add nft_log support
- add call from do_exit() in audit_free() to remove contid from netns
- relegate AUDIT_CONTAINER ref= field (was op=) to debug patch
v4
- preface set with ghak81:"collect audit task parameters"
- add shallyn and sgrubb acks
- rename feature bitmap macro
- rename cid_valid() to audit_contid_valid()
- rename AUDIT_CONTAINER_ID to AUDIT_CONTAINER_OP
- delete audit_get_contid_list() from headers
- move work into inner if, delete "found"
- change netns contid list function names
- move exports for audit_log_contid audit_alloc_local audit_free_context to non-syscall patch
- list contids CSV
- pass in gfp flags to audit_alloc_local() (fix audit_alloc_context callers)
- use "local" in lieu of abusing in_syscall for auditsc_get_stamp()
- read_lock(&tasklist_lock) around children and thread check
- task_lock(tsk) should be taken before first check of tsk->audit
- add spin lock to contid list in aunet
- restrict /proc read to CAP_AUDIT_CONTROL
- remove set again prohibition and inherited flag
- delete contidion spelling fix from patchset, send to netdev/linux-wireless
v3
- switched from containerid in task_struct to audit_task_info (depends on ghak81)
- drop INVALID_CID in favour of only AUDIT_CID_UNSET
- check for !audit_task_info, throw -ENOPROTOOPT on set
- changed -EPERM to -EEXIST for parent check
- return AUDIT_CID_UNSET if !audit_enabled
- squash child/thread check patch into AUDIT_CONTAINER_ID patch
- changed -EPERM to -EBUSY for child check
- separate child and thread checks, use -EALREADY for latter
- move addition of op= from ptrace/signal patch to AUDIT_CONTAINER patch
- fix && to || bashism in ptrace/signal patch
- uninline and export function for audit_free_context()
- drop CONFIG_CHANGE, FEATURE_CHANGE, ANOM_ABEND, ANOM_SECCOMP patches
- move audit_enabled check (xt_AUDIT)
- switched from containerid list in struct net to net_generic's struct audit_net
- move containerid list iteration into audit (xt_AUDIT)
- create function to move namespace switch into audit
- switched /proc/PID/ entry from containerid to audit_containerid
- call kzalloc with GFP_ATOMIC on in_atomic() in audit_alloc_context()
- call kzalloc with GFP_ATOMIC on in_atomic() in audit_log_container_info()
- use xt_net(par) instead of sock_net(skb->sk) to get net
- switched record and field names: initial CONTAINER_ID, aux CONTAINER, field CONTID
- allow to set own contid
- open code audit_set_containerid
- add contid inherited flag
- ccontainerid and pcontainerid eliminated due to inherited flag
- change name of container list funcitons
- rename containerid to contid
- convert initial container record to syscall aux
- fix spelling mistake of contidion in net/rfkill/core.c to avoid contid name collision
v2
- add check for children and threads
- add network namespace container identifier list
- add NETFILTER_PKT audit container identifier logging
- patch description and documentation clean-up and example
- reap unused ppid
Richard Guy Briggs (13):
audit: collect audit task parameters
audit: add container id
audit: read container ID of a process
audit: log drop of contid on exit of last task
audit: log container info of syscalls
audit: add contid support for signalling the audit daemon
audit: add support for non-syscall auxiliary records
audit: add containerid support for user records
audit: add containerid filtering
audit: add support for containerid to network namespaces
audit: contid check descendancy and nesting
audit: track container nesting
audit: add capcontid to set contid outside init_user_ns
fs/proc/base.c | 112 +++++++-
include/linux/audit.h | 135 +++++++++-
include/linux/sched.h | 10 +-
include/uapi/linux/audit.h | 10 +-
init/init_task.c | 3 +-
init/main.c | 2 +
kernel/audit.c | 621 +++++++++++++++++++++++++++++++++++++++++++-
kernel/audit.h | 23 ++
kernel/auditfilter.c | 61 +++++
kernel/auditsc.c | 110 ++++++--
kernel/fork.c | 1 -
kernel/nsproxy.c | 4 +
kernel/sched/core.c | 33 +++
net/netfilter/nft_log.c | 11 +-
net/netfilter/xt_AUDIT.c | 11 +-
security/selinux/nlmsgtab.c | 1 +
security/yama/yama_lsm.c | 33 ---
17 files changed, 1085 insertions(+), 96 deletions(-)
--
1.8.3.1
4 years
[PATCH ghak120 V5] audit: trigger accompanying records when no rules present
by Richard Guy Briggs
When there are no audit rules registered, mandatory records (config,
etc.) are missing their accompanying records (syscall, proctitle, etc.).
This is due to audit context dummy set on syscall entry based on absence
of rules that signals that no other records are to be printed. Clear the dummy
bit if any record is generated, open coding this in audit_log_start().
The proctitle context and dummy checks are pointless since the
proctitle record will not be printed if no syscall records are printed.
The fds array is reset to -1 after the first syscall to indicate it
isn't valid any more, but was never set to -1 when the context was
allocated to indicate it wasn't yet valid.
Check ctx->pwd in audit_log_name().
The audit_inode* functions can be called without going through
getname_flags() or getname_kernel() that sets audit_names and cwd, so
set the cwd in audit_alloc_name() if it has not already been done so due to
audit_names being valid and purge all other audit_getcwd() calls.
Revert the LSM dump_common_audit_data() LSM_AUDIT_DATA_* cases from the
ghak96 patch since they are no longer necessary due to cwd coverage in
audit_alloc_name().
Thanks to bauen1 <j2468h(a)googlemail.com> for reporting LSM situations in
which context->cwd is not valid, inadvertantly fixed by the ghak96 patch.
Please see upstream github issue
https://github.com/linux-audit/audit-kernel/issues/120
This is also related to upstream github issue
https://github.com/linux-audit/audit-kernel/issues/96
Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com>
---
Chagelog:
v5:
- open code audit_clear_dummy() in audit_log_start()
- fix check for ctx->pwd in audit_log_name()
- open code _audit_getcwd() contents in audit_alloc_name()
- ditch all *audit_getcwd() calls
v4:
- resubmit after revert
v3:
- initialize fds[0] to -1
- init cwd for ghak96 LSM_AUDIT_DATA_NET:AF_UNIX case
- init cwd for audit_inode{,_child}
v2:
- unconditionally clear dummy
- create audit_clear_dummy accessor function
- remove proctitle context and dummy checks
include/linux/audit.h | 8 --------
kernel/audit.c | 3 +++
kernel/auditsc.c | 27 +++++++--------------------
security/lsm_audit.c | 5 -----
4 files changed, 10 insertions(+), 33 deletions(-)
diff --git a/include/linux/audit.h b/include/linux/audit.h
index b3d859831a31..82b7c1116a85 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -292,7 +292,6 @@ extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1,
extern void __audit_syscall_exit(int ret_success, long ret_value);
extern struct filename *__audit_reusename(const __user char *uptr);
extern void __audit_getname(struct filename *name);
-extern void __audit_getcwd(void);
extern void __audit_inode(struct filename *name, const struct dentry *dentry,
unsigned int flags);
extern void __audit_file(const struct file *);
@@ -351,11 +350,6 @@ static inline void audit_getname(struct filename *name)
if (unlikely(!audit_dummy_context()))
__audit_getname(name);
}
-static inline void audit_getcwd(void)
-{
- if (unlikely(audit_context()))
- __audit_getcwd();
-}
static inline void audit_inode(struct filename *name,
const struct dentry *dentry,
unsigned int aflags) {
@@ -584,8 +578,6 @@ static inline struct filename *audit_reusename(const __user char *name)
}
static inline void audit_getname(struct filename *name)
{ }
-static inline void audit_getcwd(void)
-{ }
static inline void audit_inode(struct filename *name,
const struct dentry *dentry,
unsigned int aflags)
diff --git a/kernel/audit.c b/kernel/audit.c
index 68cee3bc8cfe..dd9d22ba4fd2 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1865,6 +1865,9 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
}
audit_get_stamp(ab->ctx, &t, &serial);
+ /* cancel dummy context to enable supporting records */
+ if (ctx)
+ ctx->dummy = 0;
audit_log_format(ab, "audit(%llu.%03lu:%u): ",
(unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dba8f0983b5..183d79cc2e12 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -929,6 +929,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state)
context->prio = state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
INIT_LIST_HEAD(&context->killed_trees);
INIT_LIST_HEAD(&context->names_list);
+ context->fds[0] = -1;
return context;
}
@@ -1367,7 +1368,10 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n,
/* name was specified as a relative path and the
* directory component is the cwd
*/
- audit_log_d_path(ab, " name=", &context->pwd);
+ if (context->pwd.dentry && context->pwd.mnt)
+ audit_log_d_path(ab, " name=", &context->pwd);
+ else
+ audit_log_format(ab, " name=(null)");
break;
default:
/* log the name's directory component */
@@ -1435,9 +1439,6 @@ static void audit_log_proctitle(void)
struct audit_context *context = audit_context();
struct audit_buffer *ab;
- if (!context || context->dummy)
- return;
-
ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE);
if (!ab)
return; /* audit_panic or being filtered */
@@ -1866,6 +1867,8 @@ static struct audit_names *audit_alloc_name(struct audit_context *context,
list_add_tail(&aname->list, &context->names_list);
context->name_count++;
+ if (!context->pwd.dentry)
+ get_fs_pwd(current->fs, &context->pwd);
return aname;
}
@@ -1894,20 +1897,6 @@ __audit_reusename(const __user char *uptr)
return NULL;
}
-inline void _audit_getcwd(struct audit_context *context)
-{
- if (!context->pwd.dentry)
- get_fs_pwd(current->fs, &context->pwd);
-}
-
-void __audit_getcwd(void)
-{
- struct audit_context *context = audit_context();
-
- if (context->in_syscall)
- _audit_getcwd(context);
-}
-
/**
* __audit_getname - add a name to the list
* @name: name to add
@@ -1931,8 +1920,6 @@ void __audit_getname(struct filename *name)
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
name->refcnt++;
-
- _audit_getcwd(context);
}
static inline int audit_copy_fcaps(struct audit_names *name,
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 53d0d183db8f..221370794d14 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -241,7 +241,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
}
- audit_getcwd();
break;
}
case LSM_AUDIT_DATA_FILE: {
@@ -255,7 +254,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
}
- audit_getcwd();
break;
}
case LSM_AUDIT_DATA_IOCTL_OP: {
@@ -271,7 +269,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
}
audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd);
- audit_getcwd();
break;
}
case LSM_AUDIT_DATA_DENTRY: {
@@ -286,7 +283,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
}
- audit_getcwd();
break;
}
case LSM_AUDIT_DATA_INODE: {
@@ -304,7 +300,6 @@ static void dump_common_audit_data(struct audit_buffer *ab,
audit_log_format(ab, " dev=");
audit_log_untrustedstring(ab, inode->i_sb->s_id);
audit_log_format(ab, " ino=%lu", inode->i_ino);
- audit_getcwd();
break;
}
case LSM_AUDIT_DATA_TASK: {
--
2.18.4
4 years
auditing signals
by Richard Guy Briggs
Hello auditors and auditees...
Have you got any rules or tests to test audit logging signals or ptrace?
I thought I understood how it worked, but it appears I need to signal a task group.
I was a little less sure of how to trigger a ptrace audit log, but also figured that out.
I wrote up an audit-testsuite test case to test it and it made two seperate sys_kill calls which generated two events rather than the one I was looking for to fill the aux_pids structure.
https://github.com/linux-audit/audit-testsuite/compare/master...rgbriggs:...
It is essentially:
sleep 5& t1=$!
sleep 5& t2=$!
auditctl -a always,exit -F arch=b64 -S kill -F key=testkill
kill -TERM $t1 $t2
sleep 1
auditctl -d always,exit -F arch=b64 -S kill -F key=testkill
sleep 2 # let the queue drain
ausearch -ts recent -i -k testkill
The output looks something like this when I was hoping for one event with two OBJ_PID records.
type=PROCTITLE msg=audit(04/08/2019 06:58:12.308:277) : proctitle=bash -l
type=OBJ_PID msg=audit(04/08/2019 06:58:12.308:277) : opid=6104 oauid=root ouid=root oses=3 obj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 ocomm=sleep
type=SYSCALL msg=audit(04/08/2019 06:58:12.308:277) : arch=x86_64 syscall=kill success=yes exit=0 a0=0x17d8 a1=SIGTERM a2=0x0 a3=0x7f119b4919c0 items=0 ppid=6066 pid=6083 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=pts0 ses=3 comm=bash exe=/usr/bin/bash subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=testkill
----
type=PROCTITLE msg=audit(04/08/2019 06:58:12.308:278) : proctitle=bash -l
type=OBJ_PID msg=audit(04/08/2019 06:58:12.308:278) : opid=6105 oauid=root ouid=root oses=3 obj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 ocomm=sleep
type=SYSCALL msg=audit(04/08/2019 06:58:12.308:278) : arch=x86_64 syscall=kill success=yes exit=0 a0=0x17d9 a1=SIGTERM a2=0x0 a3=0x7f119b4919c0 items=0 ppid=6066 pid=6083 auid=root uid=root gid=root euid=root suid=root fsuid=root egid=root sgid=root fsgid=root tty=pts0 ses=3 comm=bash exe=/usr/bin/bash subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=testkill
Now the trick is how to trigger more than one OBJ_PID record in a single syscall, which was the original goal of the exercise. It looks like it might need to be a signal sent to a process group with more than one task or a task that has threaded.
Can anyone suggest a simple test preferrably using our audit-testsuite perl infrasructure to get more than one OBJ_PID record?
The code in question was introduced:
c2f0c7c356dc <sgrubb(a)redhat.com> 2005-05-06 audit_signal_info AUDIT_TERM_INFO (single pid)
e54dc2431d74 <amy.griffis(a)hp.com> 2007-03-29 ("[PATCH] audit signal recipients") (multi-pid)
When auditing syscalls that send signals, log the pid and security context for each target process.
Optimize the data collection by adding a counter for signal-related rules, and avoiding allocating an aux struct unless we have more than one target process.
For process groups, collect pid/context data in blocks of 16.
Move the audit_signal_info() hook up in check_kill_permission() so we audit attempts where permission is denied.
a5cb013da773 <viro(a)zeniv.linux.org.uk> 2007-03-20 ("[PATCH] auditing ptrace")
As a bit of an aside, it occurs to me that there could be information overwritten if signal information was stored before ptrace information stored since ptrace uses the context->target_* slot directly whereas signals check to see if that slot is used first and then overflows to the context->aux_pids structure. If the ptrace information is always guaranteed to come first or alone, there is no issue.
If you are still reading this far, the interest in this arose from trying to find a way to connect potentially multiple OBJ_PID records with different CONTAINER_ID records in the ghak90 Audit Container ID patchset rather than using the op= field.
Thanks!
- RGB
--
Richard Guy Briggs <rgb(a)redhat.com>
Sr. S/W Engineer, Kernel Security, Base Operating Systems
Remote, Ottawa, Red Hat Canada
IRC: rgb, SunRaycer
Voice: +1.647.777.2635, Internal: (81) 32635
4 years
[PATCH 2/3] fanotify: define bit map fields to hold response decision context
by Steve Grubb
This patch defines 2 bit maps within the response variable returned from
user space on a permission event. The first field is 3 bits for the context
type. The context type will describe what the meaning is of the second bit
field. The default is none. The patch defines one additional context type
which means that the second field is a rule number. This will allow for the
creation of 6 other context types in the future if other users of the API
identify different needs. The second field is 10 bits wide and can be used
to pass along the data described by the context. Neither of these bit maps
are directly adjacent and could be expanded if the need arises.
To support this, several macros were created to facilitate storing and
retrieving the values. There is also a macro for user space to check that
the data being sent is valid. Of course, without this check, anything that
overflows the bit field will trigger an EINVAL based on the use of
of INVALID_RESPONSE_MASK in process_access_response().
Signed-off-by: Steve Grubb <sgrubb(a)redhat.com>
---
fs/notify/fanotify/fanotify.c | 3 +--
fs/notify/fanotify/fanotify_user.c | 7 +------
include/linux/fanotify.h | 5 +++++
include/uapi/linux/fanotify.h | 31 ++++++++++++++++++++++++++++++
4 files changed, 38 insertions(+), 8 deletions(-)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 85eda539b35f..e72b7e59aa24 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -178,11 +178,10 @@ static int fanotify_get_response(struct fsnotify_group *group,
}
/* userspace responded, convert to something usable */
- switch (event->response & ~FAN_AUDIT) {
+ switch (FAN_DEC_MASK(event->response)) {
case FAN_ALLOW:
ret = 0;
break;
- case FAN_DENY:
default:
ret = -EPERM;
}
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c8da9ea1e76e..3b8e515904fc 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -187,13 +187,8 @@ static int process_access_response(struct fsnotify_group *group,
* userspace can send a valid response or we will clean it up after the
* timeout
*/
- switch (response & ~FAN_AUDIT) {
- case FAN_ALLOW:
- case FAN_DENY:
- break;
- default:
+ if (FAN_INVALID_RESPONSE_MASK(response))
return -EINVAL;
- }
if (fd < 0)
return -EINVAL;
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index b79fa9bb7359..b3281d0e1b55 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -72,6 +72,11 @@
#define ALL_FANOTIFY_EVENT_BITS (FANOTIFY_OUTGOING_EVENTS | \
FANOTIFY_EVENT_FLAGS)
+/* This mask is to check for invalid bits of a user space permission response */
+#define FAN_INVALID_RESPONSE_MASK(x) ((x) & ~(FAN_ALLOW | FAN_DENY | \
+ FAN_AUDIT | FAN_DEC_CONTEXT_TYPE | \
+ FAN_DEC_CONTEXT))
+
/* Do not use these old uapi constants internally */
#undef FAN_ALL_CLASS_BITS
#undef FAN_ALL_INIT_FLAGS
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index a88c7c6d0692..785d68ebcb58 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -152,6 +152,37 @@ struct fanotify_response {
#define FAN_DENY 0x02
#define FAN_AUDIT 0x10 /* Bit mask to create audit record for result */
+/*
+ * User space may need to record additional information about its decision.
+ * The context type records what kind of information is included. A bit mask
+ * defines the type of information included and then the context of the
+ * decision. The context type is 3 bits allowing for 8 kinds of context.
+ * The default is none. We also define 10 bits to allow up to 1024 kinds of
+ * context to be returned.
+ *
+ * If the context type is Rule, then the context following is the rule number
+ * that triggered the user space decision.
+ *
+ * There are helper macros defined so that it can be standardized across tools.
+ * A full example of how user space can use this looks like this:
+ *
+ * if (FAN_DEC_CONTEXT_VALUE_VALID(rule_number))
+ * response.response = FAN_DENY | FAN_AUDIT | FAN_DEC_CONTEXT_TYPE_RULE |
+ * FAN_DEC_CONTEXT_VALUE(rule_number);
+ */
+#define FAN_DEC_MASK(x) ((x) & (FAN_ALLOW|FAN_DENY))
+#define FAN_DEC_CONTEXT_TYPE 0x70000000
+#define FAN_DEC_CONTEXT 0x00FFC000
+
+#define FAN_DEC_CONTEXT_TYPE_VALUE(x) (((x) & 0x07) << 28)
+#define FAN_DEC_CONTEXT_TYPE_TO_VALUE(x) (((x) & FAN_DEC_CONTEXT_TYPE) >> 28)
+#define FAN_DEC_CONTEXT_VALUE(x) (((x) & 0x3FF) << 14)
+#define FAN_DEC_CONTEXT_TO_VALUE(x) (((x) & FAN_DEC_CONTEXT) >> 14)
+#define FAN_DEC_CONTEXT_VALUE_VALID(x) ((x) >= 0 && (x) < 1024)
+
+#define FAN_DEC_CONTEXT_TYPE_NONE FAN_DEC_CONTEXT_TYPE_VALUE(0)
+#define FAN_DEC_CONTEXT_TYPE_RULE FAN_DEC_CONTEXT_TYPE_VALUE(1)
+
/* No fd set in event */
#define FAN_NOFD -1
--
2.26.2
4 years, 1 month
[PATCH 1/3] fanotify: Ensure consistent variable type for response
by Steve Grubb
The user space API for the response variable is __u32. This patch makes
sure that the whole path through the kernel uses __u32 so that there is
no sign extension or truncation of the user space response.
Signed-off-by: Steve Grubb <sgrubb(a)redhat.com>
---
fs/notify/fanotify/fanotify.h | 2 +-
fs/notify/fanotify/fanotify_user.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 8ce7ccfc4b0d..c397993830ac 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -165,7 +165,7 @@ FANOTIFY_PE(struct fanotify_event *event)
struct fanotify_perm_event {
struct fanotify_event fae;
struct path path;
- unsigned short response; /* userspace answer to the event */
+ __u32 response; /* userspace answer to the event */
unsigned short state; /* state of the event */
int fd; /* fd we passed to userspace for this event */
};
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 63b5dffdca9e..c8da9ea1e76e 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -157,7 +157,7 @@ static int create_fd(struct fsnotify_group *group, struct path *path,
*/
static void finish_permission_event(struct fsnotify_group *group,
struct fanotify_perm_event *event,
- unsigned int response)
+ __u32 response)
__releases(&group->notification_lock)
{
bool destroy = false;
@@ -178,7 +178,7 @@ static int process_access_response(struct fsnotify_group *group,
{
struct fanotify_perm_event *event;
int fd = response_struct->fd;
- int response = response_struct->response;
+ __u32 response = response_struct->response;
pr_debug("%s: group=%p fd=%d response=%d\n", __func__, group,
fd, response);
--
2.26.2
4 years, 1 month
[PATCH 3/3] fanotify: Allow audit to use the full permission event response
by Steve Grubb
This patch unmasks the full value so that the audit function can use all
of it. The audit function was updated to log the additional information in
the AUDIT_FANOTIFY record. The following is an example of the new record
format:
type=FANOTIFY msg=audit(1600385147.372:590): resp=2 ctx_type=1 fan_ctx=17
Signed-off-by: Steve Grubb <sgrubb(a)redhat.com>
---
fs/notify/fanotify/fanotify.c | 2 +-
kernel/auditsc.c | 7 +++++--
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index e72b7e59aa24..a9278e983e30 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -188,7 +188,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
/* Check if the response should be audited */
if (event->response & FAN_AUDIT)
- audit_fanotify(event->response & ~FAN_AUDIT);
+ audit_fanotify(event->response);
pr_debug("%s: group=%p event=%p about to return ret=%d\n", __func__,
group, event, ret);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fd840c40abf7..9d6a3ad2037d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -75,6 +75,7 @@
#include <linux/uaccess.h>
#include <linux/fsnotify_backend.h>
#include <uapi/linux/limits.h>
+#include <uapi/linux/fanotify.h>
#include "audit.h"
@@ -2523,8 +2524,10 @@ void __audit_log_kern_module(char *name)
void __audit_fanotify(unsigned int response)
{
- audit_log(audit_context(), GFP_KERNEL,
- AUDIT_FANOTIFY, "resp=%u", response);
+ audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY,
+ "resp=%u ctx_type=%u fan_ctx=%u", FAN_DEC_MASK(response),
+ FAN_DEC_CONTEXT_TYPE_TO_VALUE(response),
+ FAN_DEC_CONTEXT_TO_VALUE(response));
}
void __audit_tk_injoffset(struct timespec64 offset)
--
2.26.2
4 years, 1 month
[PATCH 0/3] fanotify: Allow user space to pass back additional audit info
by Steve Grubb
The Fanotify API can be used for access control by requesting permission
event notification. The user space tooling that uses it may have a
complicated policy that inherently contains additional context for the
decision. If this information were available in the audit trail, policy
writers can close the loop on debugging policy. Also, if this additional
information were available, it would enable the creation of tools that
can suggest changes to the policy similar to how audit2allow can help
refine labeled security.
This patch defines 2 bit maps within the response variable returned from
user space on a permission event. The first field is 3 bits for the
context type. The context type will describe what the meaning is of the
second bit field. The audit system will separate the pieces and log them
individually.
The audit function was updated to log the additional information in the
AUDIT_FANOTIFY record. The following is an example of the new record
format:
type=FANOTIFY msg=audit(1600385147.372:590): resp=2 ctx_type=1 fan_ctx=17
Steve Grubb (3):
fanotify: Ensure consistent variable type for response
fanotify: define bit map fields to hold response decision context
fanotify: Allow audit to use the full permission event response
fs/notify/fanotify/fanotify.c | 5 ++---
fs/notify/fanotify/fanotify.h | 2 +-
fs/notify/fanotify/fanotify_user.c | 11 +++--------
include/linux/fanotify.h | 5 +++++
include/uapi/linux/fanotify.h | 31 ++++++++++++++++++++++++++++++
kernel/auditsc.c | 7 +++++--
6 files changed, 47 insertions(+), 14 deletions(-)
--
2.26.2
4 years, 1 month
augenrules --load
by Joe Wulf
When building a new RHEL v7.8 VM manually, I set up the rules desired in /etc/audit/rulesd/audit.rules, no other changes (because I've wanted to narrow down the issue). After subsequent reboots, with no further changes to any audit rules either; I monitor /var/log/messages and I see occurrences like this:
Sep 22 09:04:24 hostxyz augenrules: /sbin/augenrules: No change
Sep 22 09:04:24 hostxyz augenrules: No rulesSep 22 09:04:24 hostxyz augenrules: enabled 1Sep 22 09:04:24 hostxyz augenrules: failure 1Sep 22 09:04:24 hostxyz augenrules: pid 1242Sep 22 09:04:24 hostxyz augenrules: rate_limit 0Sep 22 09:04:24 hostxyz augenrules: backlog_limit 16384Sep 22 09:04:24 hostxyz augenrules: lost 56Sep 22 09:04:24 hostxyz augenrules: backlog 1Sep 22 09:04:24 hostxyz augenrules: enabled 1Sep 22 09:04:24 hostxyz augenrules: failure 2Sep 22 09:04:24 hostxyz augenrules: pid 1242Sep 22 09:04:24 hostxyz augenrules: rate_limit 0Sep 22 09:04:24 hostxyz augenrules: backlog_limit 16384Sep 22 09:04:24 hostxyz augenrules: lost 56Sep 22 09:04:24 hostxyz augenrules: backlog 0Sep 22 09:04:24 hostxyz augenrules: usage: auditctl [options]Sep 22 09:04:24 hostxyz augenrules: -a <l,a> Append rule to end of <l>ist with <a>ctionSep 22 09:04:24 hostxyz augenrules: -A <l,a> Add rule at beginning of <l>ist with <a>ctionSep 22 09:04:24 hostxyz augenrules: -b <backlog> Set max number of outstanding audit buffersSep 22 09:04:24 hostxyz augenrules: allowed Default=64Sep 22 09:04:24 hostxyz augenrules: -c Continue through errors in rulesSep 22 09:04:24 hostxyz augenrules: -C f=f Compare collected fields if available:Sep 22 09:04:24 hostxyz augenrules: Field name, operator(=,!=), field nameSep 22 09:04:24 hostxyz augenrules: -d <l,a> Delete rule from <l>ist with <a>ctionSep 22 09:04:24 hostxyz augenrules: l=task,exit,user,excludeSep 22 09:04:24 hostxyz augenrules: a=never,alwaysSep 22 09:04:24 hostxyz augenrules: -D Delete all rules and watchesSep 22 09:04:24 hostxyz augenrules: -e [0..2] Set enabled flagSep 22 09:04:24 hostxyz augenrules: -f [0..2] Set failure flagSep 22 09:04:24 hostxyz augenrules: 0=silent 1=printk 2=panicSep 22 09:04:24 hostxyz augenrules: -F f=v Build rule: field name, operator(=,!=,<,>,<=,Sep 22 09:04:24 hostxyz augenrules: >=,&,&=) valueSep 22 09:04:24 hostxyz augenrules: -h HelpSep 22 09:04:24 hostxyz augenrules: -i Ignore errors when reading rules from fileSep 22 09:04:24 hostxyz augenrules: -k <key> Set filter key on audit ruleSep 22 09:04:24 hostxyz augenrules: -l List rulesSep 22 09:04:24 hostxyz augenrules: -m text Send a user-space messageSep 22 09:04:24 hostxyz augenrules: -p [r|w|x|a] Set permissions filter on watchSep 22 09:04:24 hostxyz augenrules: r=read, w=write, x=execute, a=attributeSep 22 09:04:24 hostxyz augenrules: -q <mount,subtree> make subtree part of mount point's dir watchesSep 22 09:04:24 hostxyz augenrules: -r <rate> Set limit in messages/sec (0=none)Sep 22 09:04:24 hostxyz augenrules: -R <file> read rules from fileSep 22 09:04:24 hostxyz augenrules: -s Report statusSep 22 09:04:24 hostxyz augenrules: -S syscall Build rule: syscall name or numberSep 22 09:04:24 hostxyz augenrules: -t Trim directory watchesSep 22 09:04:24 hostxyz augenrules: -v VersionSep 22 09:04:24 hostxyz augenrules: -w <path> Insert watch at <path>Sep 22 09:04:24 hostxyz augenrules: -W <path> Remove watch at <path>Sep 22 09:04:24 hostxyz augenrules: --loginuid-immutable Make loginuids unchangeable once setSep 22 09:04:24 hostxyz augenrules: --reset-lost Reset the lost record counterSep 22 09:04:24 hostxyz systemd: Started Security Auditing Service.
The 'usage' of auditctl is invoked the one time in the 'try_load' function of augenrules. Manual executions of "/sbin/auditctl -R /etc/audit/audit.rules', results in essentially the same behavior on the terminal as found in /var/log/messages.
Should execution of augenrules seemingly error-out on invocation of auditctl like this?
Thank you.
R,-Joe Wulf
4 years, 1 month