* [PATCH iproute2-next] ipaddress: Add support for address metric
From: dsahern @ 2018-05-27 15:10 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add support for IFA_RT_PRIORITY using the same keywords as iproute for
RTA_PRIORITY.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/uapi/linux/if_addr.h | 1 +
ip/ipaddress.c | 15 ++++++++++++++-
man/man8/ip-address.8.in | 6 ++++++
3 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h
index c4899e22cdaa..a924606f36e5 100644
--- a/include/uapi/linux/if_addr.h
+++ b/include/uapi/linux/if_addr.h
@@ -33,6 +33,7 @@ enum {
IFA_CACHEINFO,
IFA_MULTICAST,
IFA_FLAGS,
+ IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */
__IFA_MAX,
};
diff --git a/ip/ipaddress.c b/ip/ipaddress.c
index 75539e057f6a..6b53b753ead9 100644
--- a/ip/ipaddress.c
+++ b/ip/ipaddress.c
@@ -63,7 +63,7 @@ static void usage(void)
fprintf(stderr, " ip address {showdump|restore}\n");
fprintf(stderr, "IFADDR := PREFIX | ADDR peer PREFIX\n");
fprintf(stderr, " [ broadcast ADDR ] [ anycast ADDR ]\n");
- fprintf(stderr, " [ label IFNAME ] [ scope SCOPE-ID ]\n");
+ fprintf(stderr, " [ label IFNAME ] [ scope SCOPE-ID ] [ metric METRIC ]\n");
fprintf(stderr, "SCOPE-ID := [ host | link | global | NUMBER ]\n");
fprintf(stderr, "FLAG-LIST := [ FLAG-LIST ] FLAG\n");
fprintf(stderr, "FLAG := [ permanent | dynamic | secondary | primary |\n");
@@ -1328,6 +1328,10 @@ int print_addrinfo(const struct sockaddr_nl *who, struct nlmsghdr *n,
rta_tb[IFA_ADDRESS]));
}
print_int(PRINT_ANY, "prefixlen", "/%d ", ifa->ifa_prefixlen);
+
+ if (rta_tb[IFA_RT_PRIORITY])
+ print_uint(PRINT_ANY, "metric", "metric %u ",
+ rta_getattr_u32(rta_tb[IFA_RT_PRIORITY]));
}
if (brief)
@@ -2119,6 +2123,15 @@ static int ipaddr_modify(int cmd, int flags, int argc, char **argv)
NEXT_ARG();
l = *argv;
addattr_l(&req.n, sizeof(req), IFA_LABEL, l, strlen(l)+1);
+ } else if (matches(*argv, "metric") == 0 ||
+ matches(*argv, "priority") == 0 ||
+ matches(*argv, "preference") == 0) {
+ __u32 metric;
+
+ NEXT_ARG();
+ if (get_u32(&metric, *argv, 0))
+ invarg("\"metric\" value is invalid\n", *argv);
+ addattr32(&req.n, sizeof(req), IFA_RT_PRIORITY, metric);
} else if (matches(*argv, "valid_lft") == 0) {
if (valid_lftp)
duparg("valid_lft", *argv);
diff --git a/man/man8/ip-address.8.in b/man/man8/ip-address.8.in
index 7ebf0bc98dcd..c3861b3725cc 100644
--- a/man/man8/ip-address.8.in
+++ b/man/man8/ip-address.8.in
@@ -27,6 +27,8 @@ ip-address \- protocol address management
.IR IFNAME " ] [ "
.B scope
.IR SCOPE-ID " ] [ "
+.B metric
+.IR METRIC " ] [ "
.B to
.IR PREFIX " ] [ " FLAG-LIST " ] [ "
.B label
@@ -215,6 +217,10 @@ valid inside this site.
.in -8
.TP
+.BI metric " NUMBER"
+priority of prefix route associated with address.
+
+.TP
.BI valid_lft " LFT"
the valid lifetime of this address; see section 5.5.4 of
RFC 4862. When it expires, the address is removed by the kernel.
--
2.11.0
^ permalink raw reply related
* [PATCH net-next 7/7] selftests: fib_tests: Add prefix route tests with metric
From: dsahern @ 2018-05-27 15:09 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20180527151000.30488-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add tests verifying prefix routes are inserted with expected metric.
IPv6 prefix route tests
TEST: Default metric [ OK ]
TEST: User specified metric on first device [ OK ]
TEST: User specified metric on second device [ OK ]
TEST: Delete of address on first device [ OK ]
TEST: Modify metric of address [ OK ]
TEST: Prefix route removed on link down [ OK ]
TEST: Prefix route with metric on link up [ OK ]
IPv4 prefix route tests
TEST: Default metric [ OK ]
TEST: User specified metric on first device [ OK ]
TEST: User specified metric on second device [ OK ]
TEST: Delete of address on first device [ OK ]
TEST: Modify metric of address [ OK ]
TEST: Prefix route removed on link down [ OK ]
TEST: Prefix route with metric on link up [ OK ]
Signed-off-by: David Ahern <dsahern@gmail.com>
---
tools/testing/selftests/net/fib_tests.sh | 181 ++++++++++++++++++++++++++++++-
1 file changed, 180 insertions(+), 1 deletion(-)
mode change 100755 => 100644 tools/testing/selftests/net/fib_tests.sh
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
old mode 100755
new mode 100644
index e7d76fbc36e9..9780c5a2d73f
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -6,7 +6,8 @@
ret=0
-TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt"
+# all tests in this script. Can be overridden with -t option
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
VERBOSE=0
PAUSE_ON_FAIL=no
PAUSE=no
@@ -642,6 +643,8 @@ check_route6()
local rc=0
out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
+ [ "${out}" = "${expected}" ] && return 0
+
if [ -z "${out}" ]; then
if [ "$VERBOSE" = "1" ]; then
printf "\nNo route entry found\n"
@@ -911,6 +914,98 @@ ipv6_route_test()
route_cleanup
}
+ip_addr_metric_check()
+{
+ ip addr help 2>&1 | grep -q metric
+ if [ $? -ne 0 ]; then
+ echo "iproute2 command does not support metric for addresses. Skipping test"
+ return 1
+ fi
+
+ return 0
+}
+
+ipv6_addr_metric_test()
+{
+ local rc
+
+ echo
+ echo "IPv6 prefix route tests"
+
+ ip_addr_metric_check || return 1
+
+ setup
+
+ set -e
+ $IP li add dummy1 type dummy
+ $IP li add dummy2 type dummy
+ $IP li set dummy1 up
+ $IP li set dummy2 up
+
+ # default entry is metric 256
+ run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64"
+ run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256"
+ log_test $? 0 "Default metric"
+
+ set -e
+ run_cmd "$IP -6 addr flush dev dummy1"
+ run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257"
+ log_test $? 0 "User specified metric on first device"
+
+ set -e
+ run_cmd "$IP -6 addr flush dev dummy2"
+ run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+ log_test $? 0 "User specified metric on second device"
+
+ run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+ rc=$?
+ fi
+ log_test $rc 0 "Delete of address on first device"
+
+ run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Modify metric of address"
+
+ # verify prefix route removed on down
+ run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+ run_cmd "$IP li set dev dummy2 down"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 ""
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route removed on link down"
+
+ # verify prefix route re-inserted with assigned metric
+ run_cmd "$IP li set dev dummy2 up"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route with metric on link up"
+
+ $IP li del dummy1
+ $IP li del dummy2
+ cleanup
+}
+
# add route for a prefix, flushing any existing routes first
# expected to be the first step of a test
add_route()
@@ -955,6 +1050,8 @@ check_route()
local rc=0
out=$($IP ro ls match ${pfx})
+ [ "${out}" = "${expected}" ] && return 0
+
if [ -z "${out}" ]; then
if [ "$VERBOSE" = "1" ]; then
printf "\nNo route entry found\n"
@@ -1181,6 +1278,86 @@ ipv4_route_test()
route_cleanup
}
+ipv4_addr_metric_test()
+{
+ local rc
+
+ echo
+ echo "IPv4 prefix route tests"
+
+ ip_addr_metric_check || return 1
+
+ setup
+
+ set -e
+ $IP li add dummy1 type dummy
+ $IP li add dummy2 type dummy
+ $IP li set dummy1 up
+ $IP li set dummy2 up
+
+ # default entry is metric 256
+ run_cmd "$IP addr add dev dummy1 172.16.104.1/24"
+ run_cmd "$IP addr add dev dummy2 172.16.104.2/24"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2"
+ log_test $? 0 "Default metric"
+
+ set -e
+ run_cmd "$IP addr flush dev dummy1"
+ run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257"
+ log_test $? 0 "User specified metric on first device"
+
+ set -e
+ run_cmd "$IP addr flush dev dummy2"
+ run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+ log_test $? 0 "User specified metric on second device"
+
+ run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+ rc=$?
+ fi
+ log_test $rc 0 "Delete of address on first device"
+
+ run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Modify metric of address"
+
+ # verify prefix route removed on down
+ run_cmd "$IP li set dev dummy2 down"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route ""
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route removed on link down"
+
+ # verify prefix route re-inserted with assigned metric
+ run_cmd "$IP li set dev dummy2 up"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route with metric on link up"
+
+ $IP li del dummy1
+ $IP li del dummy2
+ cleanup
+}
+
################################################################################
# usage
@@ -1245,6 +1422,8 @@ do
fib_nexthop_test|nexthop) fib_nexthop_test;;
ipv6_route_test|ipv6_rt) ipv6_route_test;;
ipv4_route_test|ipv4_rt) ipv4_route_test;;
+ ipv6_addr_metric) ipv6_addr_metric_test;;
+ ipv4_addr_metric) ipv4_addr_metric_test;;
help) echo "Test names: $TESTS"; exit 0;;
esac
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net] VSOCK: check sk state before receive
From: Hangbin Liu @ 2018-05-27 15:29 UTC (permalink / raw)
To: netdev; +Cc: Stefan Hajnoczi, Jorgen Hansen, David S. Miller
In-Reply-To: <1527382936-4850-1-git-send-email-liuhangbin@gmail.com>
Hmm...Although I won't reproduce this bug with my reproducer after
apply my patch. I could still get a similiar issue with syzkaller sock vnet test.
It looks this patch is not complete. Here is the KASAN call trace with my patch.
I can also reproduce it without my patch.
==================================================================
BUG: KASAN: use-after-free in vmci_transport_allow_dgram.part.7+0x155/0x1a0 [vmw_vsock_vmci_transport]
Read of size 4 at addr ffff880026a3a914 by task kworker/0:2/96
CPU: 0 PID: 96 Comm: kworker/0:2 Not tainted 4.17.0-rc6.vsock+ #28
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Workqueue: events dg_delayed_dispatch [vmw_vmci]
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0xdd/0x18e lib/dump_stack.c:113
print_address_description+0x7a/0x3e0 mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report+0x1dd/0x460 mm/kasan/report.c:412
vmci_transport_allow_dgram.part.7+0x155/0x1a0 [vmw_vsock_vmci_transport]
vmci_transport_recv_dgram_cb+0x5d/0x200 [vmw_vsock_vmci_transport]
dg_delayed_dispatch+0x99/0x1b0 [vmw_vmci]
process_one_work+0xa4e/0x1720 kernel/workqueue.c:2145
worker_thread+0x1df/0x1400 kernel/workqueue.c:2279
kthread+0x343/0x4b0 kernel/kthread.c:240
ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:412
Allocated by task 2684:
set_track mm/kasan/kasan.c:460 [inline]
kasan_kmalloc+0xa0/0xd0 mm/kasan/kasan.c:553
slab_post_alloc_hook mm/slab.h:444 [inline]
slab_alloc_node mm/slub.c:2741 [inline]
slab_alloc mm/slub.c:2749 [inline]
kmem_cache_alloc+0x105/0x330 mm/slub.c:2754
sk_prot_alloc+0x6a/0x2c0 net/core/sock.c:1468
sk_alloc+0xc9/0xbb0 net/core/sock.c:1528
__vsock_create+0xc8/0x9b0 [vsock]
vsock_create+0xfd/0x1a0 [vsock]
__sock_create+0x310/0x690 net/socket.c:1285
sock_create net/socket.c:1325 [inline]
__sys_socket+0x101/0x240 net/socket.c:1355
__do_sys_socket net/socket.c:1364 [inline]
__se_sys_socket net/socket.c:1362 [inline]
__x64_sys_socket+0x7d/0xd0 net/socket.c:1362
do_syscall_64+0x175/0x630 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Freed by task 2684:
set_track mm/kasan/kasan.c:460 [inline]
__kasan_slab_free+0x130/0x180 mm/kasan/kasan.c:521
slab_free_hook mm/slub.c:1388 [inline]
slab_free_freelist_hook mm/slub.c:1415 [inline]
slab_free mm/slub.c:2988 [inline]
kmem_cache_free+0xce/0x410 mm/slub.c:3004
sk_prot_free net/core/sock.c:1509 [inline]
__sk_destruct+0x629/0x940 net/core/sock.c:1593
sk_destruct+0x4e/0x90 net/core/sock.c:1601
__sk_free+0xd3/0x320 net/core/sock.c:1612
sk_free+0x2a/0x30 net/core/sock.c:1623
__vsock_release+0x431/0x610 [vsock]
vsock_release+0x3c/0xc0 [vsock]
sock_release+0x91/0x200 net/socket.c:594
sock_close+0x17/0x20 net/socket.c:1149
__fput+0x368/0xa20 fs/file_table.c:209
task_work_run+0x1c5/0x2a0 kernel/task_work.c:113
exit_task_work include/linux/task_work.h:22 [inline]
do_exit+0x1876/0x26c0 kernel/exit.c:865
do_group_exit+0x159/0x3e0 kernel/exit.c:968
get_signal+0x65a/0x1780 kernel/signal.c:2482
do_signal+0xa4/0x1fe0 arch/x86/kernel/signal.c:810
exit_to_usermode_loop+0x1b8/0x260 arch/x86/entry/common.c:162
prepare_exit_to_usermode arch/x86/entry/common.c:196 [inline]
syscall_return_slowpath arch/x86/entry/common.c:265 [inline]
do_syscall_64+0x505/0x630 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The buggy address belongs to the object at ffff880026a3a600
which belongs to the cache AF_VSOCK of size 1056
The buggy address is located 788 bytes inside of
1056-byte region [ffff880026a3a600, ffff880026a3aa20)
The buggy address belongs to the page:
page:ffffea00009a8e00 count:1 mapcount:0 mapping:0000000000000000 index:0x0 compound_mapcount: 0
flags: 0xfffffc0008100(slab|head)
raw: 000fffffc0008100 0000000000000000 0000000000000000 00000001000d000d
raw: dead000000000100 dead000000000200 ffff880034471a40 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff880026a3a800: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff880026a3a880: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff880026a3a900: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff880026a3a980: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff880026a3aa00: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
==================================================================
^ permalink raw reply
* [PATCH v2 0/5] build warnings cleanup
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
Build warnings cleanup reported for
- using only 128b key
- wait for buffer in sendmsg/sendpage
- check for null before using skb
- free rspq_skb_cache in error path
- indentation
v2:
Added bug report description for 0002
Incorported comments from Dan Carpenter
Atul Gupta (5):
crypto:chtls: key len correction
crypto: chtls: wait for memory sendmsg, sendpage
crypto: chtls: dereference null variable
crypto: chtls: kbuild warnings
crypto: chtls: free beyond end rspq_skb_cache
drivers/crypto/chelsio/chtls/chtls.h | 1 +
drivers/crypto/chelsio/chtls/chtls_hw.c | 6 +-
drivers/crypto/chelsio/chtls/chtls_io.c | 104 +++++++++++++++++++++++++++---
drivers/crypto/chelsio/chtls/chtls_main.c | 3 +-
4 files changed, 98 insertions(+), 16 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH v2 1/5] crypto:chtls: key len correction
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1527435922-6727-1-git-send-email-atul.gupta@chelsio.com>
corrected the key length to copy 128b key. Removed 192b and 256b
key as user input supports key of size 128b in gcm_ctx
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_hw.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index 54a13aa9..55d5014 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -213,7 +213,7 @@ static int chtls_key_info(struct chtls_sock *csk,
struct _key_ctx *kctx,
u32 keylen, u32 optname)
{
- unsigned char key[CHCR_KEYCTX_CIPHER_KEY_SIZE_256];
+ unsigned char key[AES_KEYSIZE_128];
struct tls12_crypto_info_aes_gcm_128 *gcm_ctx;
unsigned char ghash_h[AEAD_H_SIZE];
struct crypto_cipher *cipher;
@@ -228,10 +228,6 @@ static int chtls_key_info(struct chtls_sock *csk,
if (keylen == AES_KEYSIZE_128) {
ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_128;
- } else if (keylen == AES_KEYSIZE_192) {
- ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_192;
- } else if (keylen == AES_KEYSIZE_256) {
- ck_size = CHCR_KEYCTX_CIPHER_KEY_SIZE_256;
} else {
pr_err("GCM: Invalid key length %d\n", keylen);
return -EINVAL;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 2/5] crypto: chtls: wait for memory sendmsg, sendpage
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1527435922-6727-1-git-send-email-atul.gupta@chelsio.com>
address suspicious code <gustavo@embeddedor.com>
1210 set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
1211 }
The issue is that in the code above, set_bit is never reached
due to the 'continue' statement at line 1208.
Also reported by bug report:<dan.carpenter@oracle.com>
1210 set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Not reachable.
Its required to wait for buffer in the send path and takes care of
unaddress and un-handled SOCK_NOSPACE.
v2: use csk_mem_free where appropriate
proper indent of goto do_nonblock
replace out with do_rm_wq
Reported-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls.h | 1 +
drivers/crypto/chelsio/chtls/chtls_io.c | 90 +++++++++++++++++++++++++++++--
drivers/crypto/chelsio/chtls/chtls_main.c | 1 +
3 files changed, 89 insertions(+), 3 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h
index 1b2f43c..a53a0e6 100644
--- a/drivers/crypto/chelsio/chtls/chtls.h
+++ b/drivers/crypto/chelsio/chtls/chtls.h
@@ -144,6 +144,7 @@ struct chtls_dev {
struct list_head rcu_node;
struct list_head na_node;
unsigned int send_page_order;
+ int max_host_sndbuf;
struct key_map kmap;
};
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 840dd01..7aa5d90 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -914,6 +914,78 @@ static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
return (__force u16)cpu_to_be16(thdr->length);
}
+static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
+{
+ return (cdev->max_host_sndbuf - sk->sk_wmem_queued);
+}
+
+static int csk_wait_memory(struct chtls_dev *cdev,
+ struct sock *sk, long *timeo_p)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int sndbuf, err = 0;
+ long current_timeo;
+ long vm_wait = 0;
+ bool noblock;
+
+ current_timeo = *timeo_p;
+ noblock = (*timeo_p ? false : true);
+ sndbuf = cdev->max_host_sndbuf;
+ if (csk_mem_free(cdev, sk)) {
+ current_timeo = (prandom_u32() % (HZ / 5)) + 2;
+ vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+ }
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ while (1) {
+ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+ if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+ goto do_error;
+ if (!*timeo_p) {
+ if (noblock)
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ goto do_nonblock;
+ }
+ if (signal_pending(current))
+ goto do_interrupted;
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+ if (csk_mem_free(cdev, sk) && !vm_wait)
+ break;
+
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ sk->sk_write_pending++;
+ sk_wait_event(sk, ¤t_timeo, sk->sk_err ||
+ (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ (csk_mem_free(cdev, sk) && !vm_wait), &wait);
+ sk->sk_write_pending--;
+
+ if (vm_wait) {
+ vm_wait -= current_timeo;
+ current_timeo = *timeo_p;
+ if (current_timeo != MAX_SCHEDULE_TIMEOUT) {
+ current_timeo -= vm_wait;
+ if (current_timeo < 0)
+ current_timeo = 0;
+ }
+ vm_wait = 0;
+ }
+ *timeo_p = current_timeo;
+ }
+do_rm_wq:
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return err;
+do_error:
+ err = -EPIPE;
+ goto do_rm_wq;
+do_nonblock:
+ err = -EAGAIN;
+ goto do_rm_wq;
+do_interrupted:
+ err = sock_intr_errno(*timeo_p);
+ goto do_rm_wq;
+}
+
int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct chtls_sock *csk = rcu_dereference_sk_user_data(sk);
@@ -952,6 +1024,8 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
copy = mss - skb->len;
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
+ if (!csk_mem_free(cdev, sk))
+ goto wait_for_sndbuf;
if (is_tls_tx(csk) && !csk->tlshws.txleft) {
struct tls_hdr hdr;
@@ -1099,8 +1173,10 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
if (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND)
push_frames_if_head(sk);
continue;
+wait_for_sndbuf:
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
- err = sk_stream_wait_memory(sk, &timeo);
+ err = csk_wait_memory(cdev, sk, &timeo);
if (err)
goto do_error;
}
@@ -1131,6 +1207,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags)
{
struct chtls_sock *csk;
+ struct chtls_dev *cdev;
int mss, err, copied;
struct tcp_sock *tp;
long timeo;
@@ -1138,6 +1215,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
tp = tcp_sk(sk);
copied = 0;
csk = rcu_dereference_sk_user_data(sk);
+ cdev = csk->cdev;
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
err = sk_stream_wait_connect(sk, &timeo);
@@ -1156,6 +1234,8 @@ int chtls_sendpage(struct sock *sk, struct page *page,
if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
copy <= 0) {
new_buf:
+ if (!csk_mem_free(cdev, sk))
+ goto wait_for_sndbuf;
if (is_tls_tx(csk)) {
skb = get_record_skb(sk,
@@ -1167,7 +1247,7 @@ int chtls_sendpage(struct sock *sk, struct page *page,
skb = get_tx_skb(sk, 0);
}
if (!skb)
- goto do_error;
+ goto wait_for_memory;
copy = mss;
}
if (copy > size)
@@ -1206,8 +1286,12 @@ int chtls_sendpage(struct sock *sk, struct page *page,
if (unlikely(ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND))
push_frames_if_head(sk);
continue;
-
+wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+wait_for_memory:
+ err = csk_wait_memory(cdev, sk, &timeo);
+ if (err)
+ goto do_error;
}
out:
csk_reset_flag(csk, CSK_TX_MORE_DATA);
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index 53ffb00..273afd3 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -238,6 +238,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
spin_lock_init(&cdev->idr_lock);
cdev->send_page_order = min_t(uint, get_order(32768),
send_page_order);
+ cdev->max_host_sndbuf = 48 * 1024;
if (lldi->vr->key.size)
if (chtls_init_kmap(cdev, lldi))
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 3/5] crypto: chtls: dereference null variable
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1527435922-6727-1-git-send-email-atul.gupta@chelsio.com>
skb dereferenced before check in sendpage
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_io.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 7aa5d90..8cfc27b 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1230,9 +1230,8 @@ int chtls_sendpage(struct sock *sk, struct page *page,
struct sk_buff *skb = skb_peek_tail(&csk->txq);
int copy, i;
- copy = mss - skb->len;
if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
- copy <= 0) {
+ (copy = mss - skb->len) <= 0) {
new_buf:
if (!csk_mem_free(cdev, sk))
goto wait_for_sndbuf;
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 4/5] crypto: chtls: kbuild warnings
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1527435922-6727-1-git-send-email-atul.gupta@chelsio.com>
- unindented continue
- check for null page
- signed return
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_io.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 8cfc27b..51fc682 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -907,11 +907,11 @@ static int chtls_skb_copy_to_page_nocache(struct sock *sk,
}
/* Read TLS header to find content type and data length */
-static u16 tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
+static int tls_header_read(struct tls_hdr *thdr, struct iov_iter *from)
{
if (copy_from_iter(thdr, sizeof(*thdr), from) != sizeof(*thdr))
return -EFAULT;
- return (__force u16)cpu_to_be16(thdr->length);
+ return (__force int)cpu_to_be16(thdr->length);
}
static int csk_mem_free(struct chtls_dev *cdev, struct sock *sk)
@@ -1083,9 +1083,10 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
int off = TCP_OFF(sk);
bool merge;
- if (page)
- pg_size <<= compound_order(page);
+ if (!page)
+ goto wait_for_memory;
+ pg_size <<= compound_order(page);
if (off < pg_size &&
skb_can_coalesce(skb, i, page, off)) {
merge = 1;
@@ -1492,7 +1493,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
break;
chtls_cleanup_rbuf(sk, copied);
sk_wait_data(sk, &timeo, NULL);
- continue;
+ continue;
found_ok_skb:
if (!skb->len) {
skb_dst_set(skb, NULL);
--
1.8.3.1
^ permalink raw reply related
* [PATCH v2 5/5] crypto: chtls: free beyond end rspq_skb_cache
From: Atul Gupta @ 2018-05-27 15:45 UTC (permalink / raw)
To: herbert, linux-crypto; +Cc: gustavo, dan.carpenter, netdev, davem, atul.gupta
In-Reply-To: <1527435922-6727-1-git-send-email-atul.gupta@chelsio.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Atul Gupta <atul.gupta@chelsio.com>
---
drivers/crypto/chelsio/chtls/chtls_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c
index 273afd3..9b07f91 100644
--- a/drivers/crypto/chelsio/chtls/chtls_main.c
+++ b/drivers/crypto/chelsio/chtls/chtls_main.c
@@ -250,7 +250,7 @@ static void *chtls_uld_add(const struct cxgb4_lld_info *info)
return cdev;
out_rspq_skb:
- for (j = 0; j <= i; j++)
+ for (j = 0; j < i; j++)
kfree_skb(cdev->rspq_skb_cache[j]);
kfree_skb(cdev->askb);
out_skb:
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH rdma-next v1 00/13] Verbs flow counters support
From: Leon Romanovsky @ 2018-05-27 16:22 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: RDMA mailing list, Boris Pismenny, Matan Barak, Raed Salem,
Yishai Hadas, Saeed Mahameed, linux-netdev
In-Reply-To: <20180527102346.15149-1-leon@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 904 bytes --]
On Sun, May 27, 2018 at 01:23:33PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> Changelog v0->v1:
> * Decouple from DevX submission
> * Use uverbs_attr_get_obj at counters read method
> * Added define for max read buffer size (MAX_COUNTERS_BUFF_SIZE)
> * Removed the struct mlx5_ib_flow_counter basic_flow_cnts and
> the related structs used, used define instead
> * Took Matan's patch from DevX
> * uverbs_free_counters removed void* casting
> * Added check to bound ncounters value (added define
> * Changed user supplied data buffer structure to be array of
> struct <desc,index> pair (applied this change to user space also)
>
> Not changed:
> * UAPI files
> * Addition of uhw to flow
>
> Thanks
Sorry for the noise, but please drop this series.
We found improper locking sequence in one of error paths which can be
triggered by the user.
Thanks
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 801 bytes --]
^ permalink raw reply
* [PATCH v2 04/11] net: sched: always take reference to action
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Without rtnl lock protection it is no longer safe to use pointer to tc
action without holding reference to it. (it can be destroyed concurrently)
Remove unsafe action idr lookup function. Instead of it, implement safe tcf
idr check function that atomically looks up action in idr and increments
its reference and bind counters. Implement both action search and check
using new safe function
Reference taken by idr check is temporal and should not be accounted by
userspace clients (both logically and to preserver current API behavior).
Subtract temporal reference when dumping action to userspace using existing
tca_get_fill function arguments.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
net/sched/act_api.c | 46 ++++++++++++++++++++--------------------------
1 file changed, 20 insertions(+), 26 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 256b0c93916c..aa304d36fee0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -284,44 +284,38 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
}
EXPORT_SYMBOL(tcf_generic_walker);
-static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo)
+static bool __tcf_idr_check(struct tc_action_net *tn, u32 index,
+ struct tc_action **a, int bind)
{
- struct tc_action *p = NULL;
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+ struct tc_action *p;
spin_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
+ if (p) {
+ refcount_inc(&p->tcfa_refcnt);
+ if (bind)
+ atomic_inc(&p->tcfa_bindcnt);
+ }
spin_unlock(&idrinfo->lock);
- return p;
+ if (p) {
+ *a = p;
+ return true;
+ }
+ return false;
}
int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index)
{
- struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct tc_action *p = tcf_idr_lookup(index, idrinfo);
-
- if (p) {
- *a = p;
- return 1;
- }
- return 0;
+ return __tcf_idr_check(tn, index, a, 0);
}
EXPORT_SYMBOL(tcf_idr_search);
bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
int bind)
{
- struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct tc_action *p = tcf_idr_lookup(index, idrinfo);
-
- if (index && p) {
- if (bind)
- atomic_inc(&p->tcfa_bindcnt);
- refcount_inc(&p->tcfa_refcnt);
- *a = p;
- return true;
- }
- return false;
+ return __tcf_idr_check(tn, index, a, bind);
}
EXPORT_SYMBOL(tcf_idr_check);
@@ -932,7 +926,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
if (!skb)
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
- 0, 0) <= 0) {
+ 0, 1) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
kfree_skb(skb);
return -EINVAL;
@@ -1072,7 +1066,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
return -ENOBUFS;
if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
- 0, 1) <= 0) {
+ 0, 2) <= 0) {
NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes");
kfree_skb(skb);
return -EINVAL;
@@ -1131,14 +1125,14 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
if (event == RTM_GETACTION)
ret = tcf_get_notify(net, portid, n, &actions, event, extack);
else { /* delete */
+ cleanup_a(&actions, 1); /* lookup took reference */
ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
if (ret)
goto err;
return ret;
}
err:
- if (event != RTM_GETACTION)
- tcf_action_destroy(&actions, 0);
+ tcf_action_destroy(&actions, 0);
return ret;
}
--
2.7.5
^ permalink raw reply related
* [PATCH v2 09/11] net: sched: use reference counting action init
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Change action API to assume that action init function always takes
reference to action, even when overwriting existing action. This is
necessary because action API continues to use action pointer after init
function is done. At this point action becomes accessible for concurrent
modifications, so user must always hold reference to it.
Implement helper put list function to atomically release list of actions
after action API init code is done using them.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
net/sched/act_api.c | 35 +++++++++++++++++------------------
1 file changed, 17 insertions(+), 18 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f019f0464cec..eefe8c2fe667 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -627,6 +627,18 @@ static int tcf_action_put(struct tc_action *p)
return __tcf_action_put(p, false);
}
+static void tcf_action_put_lst(struct list_head *actions)
+{
+ struct tc_action *a, *tmp;
+
+ list_for_each_entry_safe(a, tmp, actions, list) {
+ const struct tc_action_ops *ops = a->ops;
+
+ if (tcf_action_put(a))
+ module_put(ops->owner);
+ }
+}
+
int
tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
@@ -835,17 +847,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
return ERR_PTR(err);
}
-static void cleanup_a(struct list_head *actions, int ovr)
-{
- struct tc_action *a;
-
- if (!ovr)
- return;
-
- list_for_each_entry(a, actions, list)
- refcount_dec(&a->tcfa_refcnt);
-}
-
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
struct list_head *actions, size_t *attr_size,
@@ -874,11 +875,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
}
*attr_size = tcf_action_full_attrs_size(sz);
-
- /* Remove the temp refcnt which was necessary to protect against
- * destroying an existing action which was being replaced
- */
- cleanup_a(actions, ovr);
return 0;
err:
@@ -1209,7 +1205,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
return ret;
}
err:
- tcf_action_destroy(&actions, 0);
+ tcf_action_put_lst(&actions);
return ret;
}
@@ -1251,8 +1247,11 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
&attr_size, true, extack);
if (ret)
return ret;
+ ret = tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+ if (ovr)
+ tcf_action_put_lst(&actions);
- return tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+ return ret;
}
static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
--
2.7.5
^ permalink raw reply related
* [PATCH v2 00/11] Modify action API for implementing lockless actions
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a first step to remove
rtnl lock dependency from TC rules update path.
Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in action API that
prevents it from being executed concurrently.
As a preparation for executing TC rules update handlers without rtnl
lock, action API code was audited to determine areas that assume
external synchronization with rtnl lock and must be changed to allow
safe concurrent access with following results:
1. Action idr is already protected with spinlock. However, some code
paths assume that idr state is not changes between several
consecutive tcf_idr_* function calls.
2. tc_action reference and bind counters are implemented as plain
integers. They purpose was to allow single actions to be shared
between multiple filters, not to provide means for concurrent
modification.
3. tc_action 'cookie' pointer field is not protected against
modification.
4. Action API functions, that work with set of actions, use intrusive
linked list, which cannot be used concurrently without additional
synchronization.
5. Action API functions don't take reference to actions while using
them, assuming external synchronization with rtnl lock.
Following solutions to these problems are implemented:
1. To remove assumption that idr state doesn't change between tcf_idr_*
calls, implement new functions that atomically perform several
operations on idr without releasing idr spinlock. (function to
atomically lookup and delete action by index, function to atomically
check if action exists and allocate new one if necessary, etc.)
2. Use atomic operations on counters to make them suitable for
concurrent get/put operations.
3. Data that 'cookie' points to is never modified, so it enough to
refactor it to rcu pointer to prevent concurrent de-allocation.
4. Action API doesn't actually use any linked list specific operations
on actions intrusive linked list, so it can be refactored to array in
straightforward manner.
5. Always take reference to action while accessing it in action API.
tcf_idr_search function modified to take reference to action before
returning it, so there is no way to lookup an action without
incrementing its reference counter. All users of this function are
modified to release the reference, after they done using action. With
all users using reference counting, it is now safe to concurrently
delete actions.
Since only shared state in action API module are actions themselves and
action idr, these changes are sufficient to not to rely on global rtnl
lock for protection of internal action API data structures.
Changes from V1 to V2:
- Removed redundant actions ops lookup during delete.
- Merge action ops delete definition and implementation.
- Assume all actions have delete implemented and don't check for it
explicitly.
- Resplit action lookup/release code to prevent memory leaks in
individual patches.
- Make __tcf_idr_check function static
- Remove unique idr insertion function. Change original idr insert to do
the same thing.
- Merge changes that take reference to action when performing lookup and
changes that account for this additional reference when dumping action
to user space into single patch.
- Change convoluted commit message.
- Rename "unlocked" to "rtnl_held" for clarity.
- Remove estimator lock add patch.
- Refactor action check-alloc code into standalone function.
- Rename tcf_idr_find_delete to tcf_idr_delete_index.
- Rearrange variable definitions in tc_action_delete.
- Add patch that refactors action API code to use array of pointers to
actions instead of intrusive linked list.
- Expand cover letter.
Vlad Buslov (11):
net: sched: use rcu for action cookie update
net: sched: change type of reference and bind counters
net: sched: implement unlocked action init API
net: sched: always take reference to action
net: sched: implement action API that deletes action by index
net: sched: add 'delete' function to action ops
net: sched: implement reference counted action release
net: sched: don't release reference on action overwrite
net: sched: use reference counting action init
net: sched: atomically check-allocate action
net: sched: change action API to use array of pointers to actions
include/net/act_api.h | 25 ++-
include/net/pkt_cls.h | 1 +
net/sched/act_api.c | 408 +++++++++++++++++++++++++++++++--------------
net/sched/act_bpf.c | 34 ++--
net/sched/act_connmark.c | 29 +++-
net/sched/act_csum.c | 34 ++--
net/sched/act_gact.c | 31 +++-
net/sched/act_ife.c | 33 ++--
net/sched/act_ipt.c | 44 ++++-
net/sched/act_mirred.c | 38 +++--
net/sched/act_nat.c | 30 +++-
net/sched/act_pedit.c | 35 +++-
net/sched/act_police.c | 31 ++--
net/sched/act_sample.c | 34 ++--
net/sched/act_simple.c | 31 +++-
net/sched/act_skbedit.c | 31 +++-
net/sched/act_skbmod.c | 34 ++--
net/sched/act_tunnel_key.c | 32 ++--
net/sched/act_vlan.c | 40 +++--
net/sched/cls_api.c | 25 +--
20 files changed, 704 insertions(+), 296 deletions(-)
--
2.7.5
^ permalink raw reply
* [PATCH v2 05/11] net: sched: implement action API that deletes action by index
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Implement new action API function that atomically finds and deletes action
from idr by index. Intended to be used by lockless actions that do not rely
on rtnl lock.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
include/net/act_api.h | 1 +
net/sched/act_api.c | 39 +++++++++++++++++++++++++++++++++++++++
2 files changed, 40 insertions(+)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 888ff471bbf6..d94ec6400673 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -153,6 +153,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
int bind, bool cpustats);
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index);
int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
static inline int tcf_idr_release(struct tc_action *a, bool bind)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index aa304d36fee0..0f31f09946ab 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -319,6 +319,45 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
}
EXPORT_SYMBOL(tcf_idr_check);
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index)
+{
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+ struct tc_action *p;
+ int ret = 0;
+
+ spin_lock(&idrinfo->lock);
+ p = idr_find(&idrinfo->action_idr, index);
+ if (!p) {
+ spin_unlock(&idrinfo->lock);
+ return -ENOENT;
+ }
+
+ if (!atomic_read(&p->tcfa_bindcnt)) {
+ if (refcount_dec_and_test(&p->tcfa_refcnt)) {
+ struct module *owner = p->ops->owner;
+
+ WARN_ON(p != idr_remove(&idrinfo->action_idr,
+ p->tcfa_index));
+ spin_unlock(&idrinfo->lock);
+
+ if (p->ops->cleanup)
+ p->ops->cleanup(p);
+
+ gen_kill_estimator(&p->tcfa_rate_est);
+ free_tcf(p);
+ module_put(owner);
+ return 0;
+ }
+ ret = 0;
+ } else {
+ ret = -EPERM;
+ }
+
+ spin_unlock(&idrinfo->lock);
+ return ret;
+}
+EXPORT_SYMBOL(tcf_idr_delete_index);
+
int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
struct tc_action **a, const struct tc_action_ops *ops,
int bind, bool cpustats)
--
2.7.5
^ permalink raw reply related
* [PATCH v2 11/11] net: sched: change action API to use array of pointers to actions
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Act API used linked list to pass set of actions to functions. It is
intrusive data structure that stores list nodes inside action structure
itself, which means it is not safe to modify such list concurrently.
However, action API doesn't use any linked list specific operations on this
set of actions, so it can be safely refactored into plain pointer array.
Refactor action API to use array of pointers to tc_actions instead of
linked list. Change argument 'actions' type of exported action init,
destroy and dump functions.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
include/net/act_api.h | 7 ++---
net/sched/act_api.c | 74 ++++++++++++++++++++++++++++-----------------------
net/sched/cls_api.c | 21 +++++----------
3 files changed, 50 insertions(+), 52 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index cd4547476074..43dfa5e1b3b3 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -168,19 +168,20 @@ static inline int tcf_idr_release(struct tc_action *a, bool bind)
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
struct pernet_operations *ops);
-int tcf_action_destroy(struct list_head *actions, int bind);
+int tcf_action_destroy(struct tc_action *actions[], int bind);
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions, size_t *attr_size,
+ struct tc_action *actions[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
bool rtnl_held,
struct netlink_ext_ack *extack);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
+ int ref);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9511502e1cbb..7f904bb84aab 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -657,13 +657,14 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
}
EXPORT_SYMBOL(tcf_action_exec);
-int tcf_action_destroy(struct list_head *actions, int bind)
+int tcf_action_destroy(struct tc_action *actions[], int bind)
{
const struct tc_action_ops *ops;
- struct tc_action *a, *tmp;
- int ret = 0;
+ struct tc_action *a;
+ int ret = 0, i;
- list_for_each_entry_safe(a, tmp, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ a = actions[i];
ops = a->ops;
ret = __tcf_idr_release(a, bind, true);
if (ret == ACT_P_DELETED)
@@ -679,11 +680,12 @@ static int tcf_action_put(struct tc_action *p)
return __tcf_action_put(p, false);
}
-static void tcf_action_put_lst(struct list_head *actions)
+static void tcf_action_put_many(struct tc_action *actions[])
{
- struct tc_action *a, *tmp;
+ int i;
- list_for_each_entry_safe(a, tmp, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ struct tc_action *a = actions[i];
const struct tc_action_ops *ops = a->ops;
if (tcf_action_put(a))
@@ -735,14 +737,15 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
}
EXPORT_SYMBOL(tcf_action_dump_1);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
int bind, int ref)
{
struct tc_action *a;
- int err = -EINVAL;
+ int err = -EINVAL, i;
struct nlattr *nest;
- list_for_each_entry(a, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ a = actions[i];
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
@@ -878,10 +881,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
err = tcf_action_goto_chain_init(a, tp);
if (err) {
- LIST_HEAD(actions);
+ struct tc_action *actions[TCA_ACT_MAX_PRIO] = { a };
- list_add_tail(&a->list, &actions);
- tcf_action_destroy(&actions, bind);
+ tcf_action_destroy(actions, bind);
NL_SET_ERR_MSG(extack, "Failed to init TC action chain");
return ERR_PTR(err);
}
@@ -899,9 +901,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
return ERR_PTR(err);
}
+/* Returns numbers of initialized actions or negative error. */
+
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions, size_t *attr_size,
+ struct tc_action *actions[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
@@ -923,11 +927,12 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
}
act->order = i;
sz += tcf_action_fill_size(act);
- list_add_tail(&act->list, actions);
+ /* Start from index 0 */
+ actions[i - 1] = act;
}
*attr_size = tcf_action_full_attrs_size(sz);
- return 0;
+ return i - 1;
err:
tcf_action_destroy(actions, bind);
@@ -978,7 +983,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
return -1;
}
-static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
+static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[],
u32 portid, u32 seq, u16 flags, int event, int bind,
int ref)
{
@@ -1014,7 +1019,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
static int
tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
- struct list_head *actions, int event,
+ struct tc_action *actions[], int event,
struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
@@ -1150,14 +1155,14 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
return err;
}
-static int tcf_action_delete(struct net *net, struct list_head *actions,
+static int tcf_action_delete(struct net *net, struct tc_action *actions[],
struct netlink_ext_ack *extack)
{
- struct tc_action *a, *tmp;
u32 act_index;
- int ret;
+ int ret, i;
- list_for_each_entry_safe(a, tmp, actions, list) {
+ for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+ struct tc_action *a = actions[i];
const struct tc_action_ops *ops = a->ops;
/* Actions can be deleted concurrently so we must save their
@@ -1180,7 +1185,7 @@ static int tcf_action_delete(struct net *net, struct list_head *actions,
}
static int
-tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
{
int ret;
@@ -1221,7 +1226,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
size_t attr_size = 0;
- LIST_HEAD(actions);
+ struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
if (ret < 0)
@@ -1243,26 +1248,27 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
}
act->order = i;
attr_size += tcf_action_fill_size(act);
- list_add_tail(&act->list, &actions);
+ actions[i - 1] = act;
}
attr_size = tcf_action_full_attrs_size(attr_size);
if (event == RTM_GETACTION)
- ret = tcf_get_notify(net, portid, n, &actions, event, extack);
+ ret = tcf_get_notify(net, portid, n, actions, event, extack);
else { /* delete */
- ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
+ ret = tcf_del_notify(net, n, actions, portid, attr_size,
+ extack);
if (ret)
goto err;
return ret;
}
err:
- tcf_action_put_lst(&actions);
+ tcf_action_put_many(actions);
return ret;
}
static int
-tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
{
struct sk_buff *skb;
@@ -1293,15 +1299,15 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
{
size_t attr_size = 0;
int ret = 0;
- LIST_HEAD(actions);
+ struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
- ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
+ ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
&attr_size, true, extack);
- if (ret)
+ if (ret < 0)
return ret;
- ret = tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+ ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
if (ovr)
- tcf_action_put_lst(&actions);
+ tcf_action_put_many(actions);
return ret;
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index dd37d0ae3fce..b2bb6b7b038a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1415,10 +1415,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
- LIST_HEAD(actions);
-
- tcf_exts_to_list(exts, &actions);
- tcf_action_destroy(&actions, TCA_ACT_UNBIND);
+ tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
kfree(exts->actions);
exts->nr_actions = 0;
#endif
@@ -1445,18 +1442,15 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
exts->actions[0] = act;
exts->nr_actions = 1;
} else if (exts->action && tb[exts->action]) {
- LIST_HEAD(actions);
- int err, i = 0;
+ int err;
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- &actions, &attr_size, true,
+ exts->actions, &attr_size, true,
extack);
- if (err)
+ if (err < 0)
return err;
- list_for_each_entry(act, &actions, list)
- exts->actions[i++] = act;
- exts->nr_actions = i;
+ exts->nr_actions = err;
}
exts->net = net;
}
@@ -1505,14 +1499,11 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
* tc data even if iproute2 was newer - jhs
*/
if (exts->type != TCA_OLD_COMPAT) {
- LIST_HEAD(actions);
-
nest = nla_nest_start(skb, exts->action);
if (nest == NULL)
goto nla_put_failure;
- tcf_exts_to_list(exts, &actions);
- if (tcf_action_dump(skb, &actions, 0, 0) < 0)
+ if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (exts->police) {
--
2.7.5
^ permalink raw reply related
* [PATCH v2 08/11] net: sched: don't release reference on action overwrite
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Return from action init function with reference to action taken,
even when overwriting existing action.
Action init API initializes its fourth argument (pointer to pointer to tc
action) to either existing action with same index or newly created action.
In case of existing index(and bind argument is zero), init function returns
without incrementing action reference counter. Caller of action init then
proceeds working with action, without actually holding reference to it.
This means that action could be deleted concurrently.
Change action init behavior to always take reference to action before
returning successfully, in order to protect from concurrent deletion.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
net/sched/act_api.c | 2 --
net/sched/act_bpf.c | 8 ++++----
net/sched/act_connmark.c | 5 +++--
net/sched/act_csum.c | 8 ++++----
net/sched/act_gact.c | 5 +++--
net/sched/act_ife.c | 12 +++++-------
net/sched/act_ipt.c | 5 +++--
net/sched/act_mirred.c | 5 ++---
net/sched/act_nat.c | 5 +++--
net/sched/act_pedit.c | 5 +++--
net/sched/act_police.c | 8 +++-----
net/sched/act_sample.c | 8 +++-----
net/sched/act_simple.c | 5 +++--
net/sched/act_skbedit.c | 5 +++--
net/sched/act_skbmod.c | 8 +++-----
net/sched/act_tunnel_key.c | 8 +++-----
net/sched/act_vlan.c | 8 +++-----
17 files changed, 51 insertions(+), 59 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a023873db713..f019f0464cec 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -870,8 +870,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
}
act->order = i;
sz += tcf_action_fill_size(act);
- if (ovr)
- refcount_inc(&act->tcfa_refcnt);
list_add_tail(&act->list, actions);
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 7941dd66ff83..d3f4ac6f2c4b 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -311,9 +311,10 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
if (bind)
return 0;
- tcf_idr_release(*act, bind);
- if (!replace)
+ if (!replace) {
+ tcf_idr_release(*act, bind);
return -EEXIST;
+ }
}
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
@@ -356,8 +357,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
return res;
out:
- if (res == ACT_P_CREATED)
- tcf_idr_release(*act, bind);
+ tcf_idr_release(*act, bind);
return ret;
}
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 143c2d3de723..701e90244eff 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -135,9 +135,10 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
ci = to_connmark(*a);
if (bind)
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
/* replacing action and zone */
ci->tcf_action = parm->action;
ci->zone = parm->zone;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 3768539340e0..5dbee136b0a1 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -76,9 +76,10 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
p = to_tcf_csum(*a);
@@ -86,8 +87,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
params_old = rtnl_dereference(p->params);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index a431a711f0dd..11c4de3f344e 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -100,9 +100,10 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
gact = to_gact(*a);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 027c305dcb37..3dd3d79c5a4b 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -497,12 +497,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
return ret;
}
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr) {
- kfree(p);
- return -EEXIST;
- }
+ kfree(p);
+ return -EEXIST;
}
ife = to_ife(*a);
@@ -544,13 +542,13 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
NULL, NULL);
if (err) {
metadata_parse_err:
- if (exists)
- tcf_idr_release(*a, bind);
if (ret == ACT_P_CREATED)
_tcf_ife_cleanup(*a);
if (exists)
spin_unlock_bh(&ife->tcf_lock);
+ tcf_idr_release(*a, bind);
+
kfree(p);
return err;
}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 6c234411c771..85e85dfba401 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -145,10 +145,11 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
} else {
if (bind)/* dont override defaults */
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
hook = nla_get_u32(tb[TCA_IPT_HOOK]);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 3d8300bce7e4..e08aed06d7f8 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -132,10 +132,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
if (ret)
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
m = to_mirred(*a);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 9eb27c89dc46..1f91e8e66c0f 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -66,9 +66,10 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
} else {
if (bind)
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
p = to_tcf_nat(*a);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index b8857035e3f8..fbf283f2ac34 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -185,9 +185,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
} else {
if (bind)
return 0;
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
p = to_pedit(*a);
if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
keys = kmalloc(ksize, GFP_KERNEL);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index c955fb0d4f3f..99335cca739e 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -111,10 +111,9 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
if (ret)
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
police = to_police(*a);
@@ -195,8 +194,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
failure:
qdisc_put_rtab(P_tab);
qdisc_put_rtab(R_tab);
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return err;
}
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 6f79d2afcba2..a8582e1347db 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -69,10 +69,9 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
if (ret)
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
s = to_sample(*a);
@@ -81,8 +80,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
psample_group = psample_group_get(net, s->psample_group_num);
if (!psample_group) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
RCU_INIT_POINTER(s->psample_group, psample_group);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index b570e7ca7e33..78fffd329ed9 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -130,9 +130,10 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
} else {
d = to_defact(*a);
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
reset_policy(d, defdata, parm);
}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index dc0cb350aa45..c0607d1319eb 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -137,9 +137,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
ret = ACT_P_CREATED;
} else {
d = to_skbedit(*a);
- tcf_idr_release(*a, bind);
- if (!ovr)
+ if (!ovr) {
+ tcf_idr_release(*a, bind);
return -EEXIST;
+ }
}
spin_lock_bh(&d->tcf_lock);
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 30be3f767495..e844381af066 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -145,10 +145,9 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
d = to_skbmod(*a);
@@ -156,8 +155,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
ASSERT_RTNL();
p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
if (unlikely(!p)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 4b7f9a3b47d7..bd53f39a345b 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -165,10 +165,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
t = to_tunnel_key(*a);
@@ -176,8 +175,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
ASSERT_RTNL();
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index b44377c951b6..4ac0d565e437 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -185,10 +185,9 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
return ret;
ret = ACT_P_CREATED;
- } else {
+ } else if (!ovr) {
tcf_idr_release(*a, bind);
- if (!ovr)
- return -EEXIST;
+ return -EEXIST;
}
v = to_vlan(*a);
@@ -196,8 +195,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
ASSERT_RTNL();
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p) {
- if (ret == ACT_P_CREATED)
- tcf_idr_release(*a, bind);
+ tcf_idr_release(*a, bind);
return -ENOMEM;
}
--
2.7.5
^ permalink raw reply related
* [PATCH v2 01/11] net: sched: use rcu for action cookie update
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Implement functions to atomically update and free action cookie
using rcu mechanism.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/act_api.h | 2 +-
include/net/pkt_cls.h | 1 +
net/sched/act_api.c | 44 ++++++++++++++++++++++++++++++--------------
3 files changed, 32 insertions(+), 15 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9e59ebfded62..f7b59ef7303d 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -37,7 +37,7 @@ struct tc_action {
spinlock_t tcfa_lock;
struct gnet_stats_basic_cpu __percpu *cpu_bstats;
struct gnet_stats_queue __percpu *cpu_qstats;
- struct tc_cookie *act_cookie;
+ struct tc_cookie __rcu *act_cookie;
struct tcf_chain *goto_chain;
};
#define tcf_index common.tcfa_index
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e828d31be5da..3068cc8aa0f1 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -769,6 +769,7 @@ struct tc_mqprio_qopt_offload {
struct tc_cookie {
u8 *data;
u32 len;
+ struct rcu_head rcu;
};
struct tc_qopt_offload_stats {
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3f4cf930f809..02670c7489e3 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -55,6 +55,24 @@ static void tcf_action_goto_chain_exec(const struct tc_action *a,
res->goto_tp = rcu_dereference_bh(chain->filter_chain);
}
+static void tcf_free_cookie_rcu(struct rcu_head *p)
+{
+ struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu);
+
+ kfree(cookie->data);
+ kfree(cookie);
+}
+
+static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
+ struct tc_cookie *new_cookie)
+{
+ struct tc_cookie *old;
+
+ old = xchg(old_cookie, new_cookie);
+ if (old)
+ call_rcu(&old->rcu, tcf_free_cookie_rcu);
+}
+
/* XXX: For standalone actions, we don't need a RCU grace period either, because
* actions are always connected to filters and filters are already destroyed in
* RCU callbacks, so after a RCU grace period actions are already disconnected
@@ -65,10 +83,7 @@ static void free_tcf(struct tc_action *p)
free_percpu(p->cpu_bstats);
free_percpu(p->cpu_qstats);
- if (p->act_cookie) {
- kfree(p->act_cookie->data);
- kfree(p->act_cookie);
- }
+ tcf_set_action_cookie(&p->act_cookie, NULL);
if (p->goto_chain)
tcf_action_goto_chain_fini(p);
@@ -567,16 +582,22 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
int err = -EINVAL;
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
+ struct tc_cookie *cookie;
if (nla_put_string(skb, TCA_KIND, a->ops->kind))
goto nla_put_failure;
if (tcf_action_copy_stats(skb, a, 0))
goto nla_put_failure;
- if (a->act_cookie) {
- if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len,
- a->act_cookie->data))
+
+ rcu_read_lock();
+ cookie = rcu_dereference(a->act_cookie);
+ if (cookie) {
+ if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+ rcu_read_unlock();
goto nla_put_failure;
+ }
}
+ rcu_read_unlock();
nest = nla_nest_start(skb, TCA_OPTIONS);
if (nest == NULL)
@@ -719,13 +740,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (err < 0)
goto err_mod;
- if (name == NULL && tb[TCA_ACT_COOKIE]) {
- if (a->act_cookie) {
- kfree(a->act_cookie->data);
- kfree(a->act_cookie);
- }
- a->act_cookie = cookie;
- }
+ if (!name && tb[TCA_ACT_COOKIE])
+ tcf_set_action_cookie(&a->act_cookie, cookie);
/* module count goes up only when brand new policy is created
* if it exists and is only bound to in a_o->init() then
--
2.7.5
^ permalink raw reply related
* [PATCH v2 10/11] net: sched: atomically check-allocate action
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Implement function that atomically checks if action exists and either takes
reference to it, or allocates idr slot for action index to prevent
concurrent allocations of actions with same index. Use EBUSY error pointer
to indicate that idr slot is reserved.
Implement cleanup helper function that removes temporary error pointer from
idr. (in case of error between idr allocation and insertion of newly
created action to specified index)
Refactor all action init functions to insert new action to idr using this
API.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
include/net/act_api.h | 3 ++
net/sched/act_api.c | 92 ++++++++++++++++++++++++++++++++++++----------
net/sched/act_bpf.c | 11 ++++--
net/sched/act_connmark.c | 10 +++--
net/sched/act_csum.c | 11 ++++--
net/sched/act_gact.c | 11 ++++--
net/sched/act_ife.c | 6 ++-
net/sched/act_ipt.c | 13 ++++++-
net/sched/act_mirred.c | 16 ++++++--
net/sched/act_nat.c | 11 ++++--
net/sched/act_pedit.c | 15 ++++++--
net/sched/act_police.c | 9 ++++-
net/sched/act_sample.c | 11 ++++--
net/sched/act_simple.c | 11 +++++-
net/sched/act_skbedit.c | 11 +++++-
net/sched/act_skbmod.c | 11 +++++-
net/sched/act_tunnel_key.c | 9 ++++-
net/sched/act_vlan.c | 17 ++++++++-
18 files changed, 218 insertions(+), 60 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index d256e20507b9..cd4547476074 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -154,6 +154,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
int bind, bool cpustats);
void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+ struct tc_action **a, int bind);
int tcf_idr_delete_index(struct tc_action_net *tn, u32 index);
int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index eefe8c2fe667..9511502e1cbb 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -303,7 +303,9 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index,
spin_lock(&idrinfo->lock);
p = idr_find(&idrinfo->action_idr, index);
- if (p) {
+ if (IS_ERR(p)) {
+ p = NULL;
+ } else if (p) {
refcount_inc(&p->tcfa_refcnt);
if (bind)
atomic_inc(&p->tcfa_bindcnt);
@@ -371,7 +373,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
{
struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
struct tcf_idrinfo *idrinfo = tn->idrinfo;
- struct idr *idr = &idrinfo->action_idr;
int err = -ENOMEM;
if (unlikely(!p))
@@ -389,20 +390,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
goto err2;
}
spin_lock_init(&p->tcfa_lock);
- idr_preload(GFP_KERNEL);
- spin_lock(&idrinfo->lock);
- /* user doesn't specify an index */
- if (!index) {
- index = 1;
- err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC);
- } else {
- err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC);
- }
- spin_unlock(&idrinfo->lock);
- idr_preload_end();
- if (err)
- goto err3;
-
p->tcfa_index = index;
p->tcfa_tm.install = jiffies;
p->tcfa_tm.lastuse = jiffies;
@@ -412,7 +399,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
&p->tcfa_rate_est,
&p->tcfa_lock, NULL, est);
if (err)
- goto err4;
+ goto err3;
}
p->idrinfo = idrinfo;
@@ -420,8 +407,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
INIT_LIST_HEAD(&p->list);
*a = p;
return 0;
-err4:
- idr_remove(idr, index);
err3:
free_percpu(p->cpu_qstats);
err2:
@@ -437,11 +422,78 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
struct tcf_idrinfo *idrinfo = tn->idrinfo;
spin_lock(&idrinfo->lock);
- idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
+ /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+ WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
spin_unlock(&idrinfo->lock);
}
EXPORT_SYMBOL(tcf_idr_insert);
+/* Cleanup idr index that was allocated but not initialized. */
+
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
+{
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+
+ spin_lock(&idrinfo->lock);
+ /* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+ WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index)));
+ spin_unlock(&idrinfo->lock);
+}
+EXPORT_SYMBOL(tcf_idr_cleanup);
+
+/* Check if action with specified index exists. If actions is found, increments
+ * its reference and bind counters, and return 1. Otherwise insert temporary
+ * error pointer (to prevent concurrent users from inserting actions with same
+ * index) and return 0.
+ */
+
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+ struct tc_action **a, int bind)
+{
+ struct tcf_idrinfo *idrinfo = tn->idrinfo;
+ struct tc_action *p;
+ int ret;
+
+again:
+ spin_lock(&idrinfo->lock);
+ if (*index) {
+ p = idr_find(&idrinfo->action_idr, *index);
+ if (IS_ERR(p)) {
+ /* This means that another process allocated
+ * index but did not assign the pointer yet.
+ */
+ spin_unlock(&idrinfo->lock);
+ goto again;
+ }
+
+ if (p) {
+ refcount_inc(&p->tcfa_refcnt);
+ if (bind)
+ atomic_inc(&p->tcfa_bindcnt);
+ *a = p;
+ ret = 1;
+ } else {
+ *a = NULL;
+ ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+ *index, GFP_ATOMIC);
+ if (!ret)
+ idr_replace(&idrinfo->action_idr,
+ ERR_PTR(-EBUSY), *index);
+ }
+ } else {
+ *index = 1;
+ *a = NULL;
+ ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+ UINT_MAX, GFP_ATOMIC);
+ if (!ret)
+ idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
+ *index);
+ }
+ spin_unlock(&idrinfo->lock);
+ return ret;
+}
+EXPORT_SYMBOL(tcf_idr_check_alloc);
+
void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
struct tcf_idrinfo *idrinfo)
{
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index d3f4ac6f2c4b..06f743d8ed41 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -299,14 +299,17 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
- if (!tcf_idr_check(tn, parm->index, act, bind)) {
+ ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+ if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, act,
&act_bpf_ops, bind, true);
- if (ret < 0)
+ if (ret < 0) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
res = ACT_P_CREATED;
- } else {
+ } else if (ret > 0) {
/* Don't override defaults. */
if (bind)
return 0;
@@ -315,6 +318,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
tcf_idr_release(*act, bind);
return -EEXIST;
}
+ } else {
+ return ret;
}
is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 701e90244eff..1e31f0e448e2 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -118,11 +118,14 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_connmark_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ci = to_connmark(*a);
ci->tcf_action = parm->action;
@@ -131,7 +134,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
- } else {
+ } else if (ret > 0) {
ci = to_connmark(*a);
if (bind)
return 0;
@@ -142,6 +145,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
/* replacing action and zone */
ci->tcf_action = parm->action;
ci->zone = parm->zone;
+ ret = 0;
}
return ret;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 5dbee136b0a1..bd232d3bd022 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -67,19 +67,24 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
return -EINVAL;
parm = nla_data(tb[TCA_CSUM_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_csum_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)/* dont override defaults */
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
+ } else {
+ return err;
}
p = to_tcf_csum(*a);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 11c4de3f344e..661b72b9147d 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -91,19 +91,24 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
}
#endif
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_gact_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)/* dont override defaults */
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
+ } else {
+ return err;
}
gact = to_gact(*a);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3dd3d79c5a4b..5bf0e79796c0 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -483,7 +483,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
if (!p)
return -ENOMEM;
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind) {
kfree(p);
return 0;
@@ -493,6 +496,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
bind, true);
if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
kfree(p);
return ret;
}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 85e85dfba401..0dc787a57798 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -119,13 +119,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
if (tb[TCA_IPT_INDEX] != NULL)
index = nla_get_u32(tb[TCA_IPT_INDEX]);
- exists = tcf_idr_check(tn, index, a, bind);
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
@@ -133,14 +138,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, index, est, a, ops, bind,
false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, index);
return ret;
+ }
ret = ACT_P_CREATED;
} else {
if (bind)/* dont override defaults */
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index e08aed06d7f8..6afd89a36c69 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -79,7 +79,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
struct tcf_mirred *m;
struct net_device *dev;
bool exists = false;
- int ret;
+ int ret, err;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
@@ -94,7 +94,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
}
parm = nla_data(tb[TCA_MIRRED_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
@@ -107,6 +110,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
default:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
return -EINVAL;
}
@@ -115,6 +120,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
if (dev == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -ENODEV;
}
mac_header_xmit = dev_is_mac_header_xmit(dev);
@@ -124,13 +131,16 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
if (!exists) {
if (!dev) {
+ tcf_idr_cleanup(tn, parm->index);
NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
return -EINVAL;
}
ret = tcf_idr_create(tn, parm->index, est, a,
&act_mirred_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 1f91e8e66c0f..4dd9188a72fd 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -57,19 +57,24 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
return -EINVAL;
parm = nla_data(tb[TCA_NAT_PARMS]);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_nat_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
+ } else {
+ return err;
}
p = to_tcf_nat(*a);
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index fbf283f2ac34..2bd1d3f61488 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -167,13 +167,18 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
if (IS_ERR(keys_ex))
return PTR_ERR(keys_ex);
- if (!tcf_idr_check(tn, parm->index, a, bind)) {
- if (!parm->nkeys)
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (!err) {
+ if (!parm->nkeys) {
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
+ }
ret = tcf_idr_create(tn, parm->index, est, a,
&act_pedit_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
p = to_pedit(*a);
keys = kmalloc(ksize, GFP_KERNEL);
if (keys == NULL) {
@@ -182,7 +187,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
return -ENOMEM;
}
ret = ACT_P_CREATED;
- } else {
+ } else if (err > 0) {
if (bind)
return 0;
if (!ovr) {
@@ -197,6 +202,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
return -ENOMEM;
}
}
+ } else {
+ return err;
}
spin_lock_bh(&p->tcf_lock);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 99335cca739e..1f3192ea8df7 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -101,15 +101,20 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
return -EINVAL;
parm = nla_data(tb[TCA_POLICE_TBF]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, NULL, a,
&act_police_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index a8582e1347db..3079e7be5bde 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -46,7 +46,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct tc_sample *parm;
struct tcf_sample *s;
bool exists = false;
- int ret;
+ int ret, err;
if (!nla)
return -EINVAL;
@@ -59,15 +59,20 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_SAMPLE_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_sample_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 78fffd329ed9..2cc874f791df 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -101,13 +101,18 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
return -EINVAL;
parm = nla_data(tb[TCA_DEF_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (tb[TCA_DEF_DATA] == NULL) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
@@ -116,8 +121,10 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_simp_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
d = to_defact(*a);
ret = alloc_defdata(d, defdata);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index c0607d1319eb..29a15172a99d 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -117,21 +117,28 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!flags) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_skbedit_ops, bind, false);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
d = to_skbedit(*a);
ret = ACT_P_CREATED;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e844381af066..cdc6bacfb190 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -128,21 +128,28 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
if (!lflags) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_skbmod_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
} else if (!ovr) {
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index bd53f39a345b..4679b620af12 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -99,7 +99,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
return -EINVAL;
parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
@@ -162,7 +165,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
ret = tcf_idr_create(tn, parm->index, est, a,
&act_tunnel_key_ops, bind, true);
if (ret)
- return ret;
+ goto err_out;
ret = ACT_P_CREATED;
} else if (!ovr) {
@@ -198,6 +201,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
err_out:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return ret;
}
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 4ac0d565e437..bae9822837d7 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -134,7 +134,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
if (!tb[TCA_VLAN_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_VLAN_PARMS]);
- exists = tcf_idr_check(tn, parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ if (err < 0)
+ return err;
+ exists = err;
if (exists && bind)
return 0;
@@ -146,12 +149,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
if (push_vid >= VLAN_VID_MASK) {
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -ERANGE;
}
@@ -162,6 +169,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
case htons(ETH_P_8021AD):
break;
default:
+ if (!exists)
+ tcf_idr_cleanup(tn, parm->index);
return -EPROTONOSUPPORT;
}
} else {
@@ -174,6 +183,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
default:
if (exists)
tcf_idr_release(*a, bind);
+ else
+ tcf_idr_cleanup(tn, parm->index);
return -EINVAL;
}
action = parm->v_action;
@@ -181,8 +192,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
if (!exists) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_vlan_ops, bind, true);
- if (ret)
+ if (ret) {
+ tcf_idr_cleanup(tn, parm->index);
return ret;
+ }
ret = ACT_P_CREATED;
} else if (!ovr) {
--
2.7.5
^ permalink raw reply related
* [PATCH v2 03/11] net: sched: implement unlocked action init API
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Add additional 'rtnl_held' argument to act API init functions. It is
required to implement actions that need to release rtnl lock before loading
kernel module and reacquire if afterwards.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
include/net/act_api.h | 6 ++++--
net/sched/act_api.c | 18 +++++++++++-------
net/sched/act_bpf.c | 3 ++-
net/sched/act_connmark.c | 2 +-
net/sched/act_csum.c | 3 ++-
net/sched/act_gact.c | 3 ++-
net/sched/act_ife.c | 3 ++-
net/sched/act_ipt.c | 6 ++++--
net/sched/act_mirred.c | 5 +++--
net/sched/act_nat.c | 2 +-
net/sched/act_pedit.c | 3 ++-
net/sched/act_police.c | 2 +-
net/sched/act_sample.c | 3 ++-
net/sched/act_simple.c | 3 ++-
net/sched/act_skbedit.c | 3 ++-
net/sched/act_skbmod.c | 3 ++-
net/sched/act_tunnel_key.c | 3 ++-
net/sched/act_vlan.c | 3 ++-
net/sched/cls_api.c | 5 +++--
19 files changed, 50 insertions(+), 29 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index e634014605cb..888ff471bbf6 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -92,7 +92,8 @@ struct tc_action_ops {
struct netlink_ext_ack *extack);
int (*init)(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act, int ovr,
- int bind, struct netlink_ext_ack *extack);
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack);
int (*walk)(struct net *, struct sk_buff *,
struct netlink_callback *, int,
const struct tc_action_ops *,
@@ -168,10 +169,11 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
struct list_head *actions, size_t *attr_size,
- struct netlink_ext_ack *extack);
+ bool rtnl_held, struct netlink_ext_ack *extack);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
+ bool rtnl_held,
struct netlink_ext_ack *extack);
int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4f064ecab882..256b0c93916c 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -671,6 +671,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
+ bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action *a;
@@ -721,9 +722,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
a_o = tc_lookup_action_n(act_name);
if (a_o == NULL) {
#ifdef CONFIG_MODULES
- rtnl_unlock();
+ if (rtnl_held)
+ rtnl_unlock();
request_module("act_%s", act_name);
- rtnl_lock();
+ if (rtnl_held)
+ rtnl_lock();
a_o = tc_lookup_action_n(act_name);
@@ -746,9 +749,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
/* backward compatibility for policer */
if (name == NULL)
err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
- extack);
+ rtnl_held, extack);
else
- err = a_o->init(net, nla, est, &a, ovr, bind, extack);
+ err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
+ extack);
if (err < 0)
goto err_mod;
@@ -800,7 +804,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
struct list_head *actions, size_t *attr_size,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
@@ -814,7 +818,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
- extack);
+ rtnl_held, extack);
if (IS_ERR(act)) {
err = PTR_ERR(act);
goto err;
@@ -1173,7 +1177,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
LIST_HEAD(actions);
ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
- &attr_size, extack);
+ &attr_size, true, extack);
if (ret)
return ret;
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 15a2a53cbde1..8ebf40a3506c 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -276,7 +276,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
static int tcf_bpf_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **act,
- int replace, int bind, struct netlink_ext_ack *extack)
+ int replace, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, bpf_net_id);
struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 188865034f9a..e3787aa0025a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -96,7 +96,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind,
+ int ovr, int bind, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index da865f7b390a..334261943f9f 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -46,7 +46,8 @@ static struct tc_action_ops act_csum_ops;
static int tcf_csum_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
struct tcf_csum_params *params_old, *params_new;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index ca83debd5a70..b4dfb2b4addc 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -56,7 +56,8 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
static int tcf_gact_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
struct nlattr *tb[TCA_GACT_MAX + 1];
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 706e84d6f912..3dccc4e1d378 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -447,7 +447,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
static int tcf_ife_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ife_net_id);
struct nlattr *tb[TCA_IFE_MAX + 1];
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 7bce88dc11c9..9c21663a86a6 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -196,7 +196,8 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
static int tcf_ipt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
bind);
@@ -204,7 +205,8 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla,
static int tcf_xt_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool unlocked,
+ struct netlink_ext_ack *extack)
{
return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
bind);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 82a8bdd67c47..5434f08f2eb7 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -68,8 +68,9 @@ static unsigned int mirred_net_id;
static struct tc_action_ops act_mirred_ops;
static int tcf_mirred_init(struct net *net, struct nlattr *nla,
- struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ struct nlattr *est, struct tc_action **a,
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
struct nlattr *tb[TCA_MIRRED_MAX + 1];
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 457c2ae3de46..e6487ad1e4a8 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -38,7 +38,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
struct tc_action **a, int ovr, int bind,
- struct netlink_ext_ack *extack)
+ bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, nat_net_id);
struct nlattr *tb[TCA_NAT_MAX + 1];
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 0102b2935fdb..7c9a3f24edba 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -132,7 +132,8 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
static int tcf_pedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
struct nlattr *tb[TCA_PEDIT_MAX + 1];
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index a789b8060968..0e1c2fb0ebea 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -75,7 +75,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
static int tcf_act_police_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind,
+ int ovr, int bind, bool rtnl_held,
struct netlink_ext_ack *extack)
{
int ret = 0, err;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 4a46978db092..316fc645595d 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -37,7 +37,8 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
static int tcf_sample_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a, int ovr,
- int bind, struct netlink_ext_ack *extack)
+ int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 95d5985b8d67..23fa893ea092 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -79,7 +79,8 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
static int tcf_simp_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, simp_net_id);
struct nlattr *tb[TCA_DEF_MAX + 1];
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index d418ec3b0ab9..85ed9d603dc1 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -66,7 +66,8 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index ff90d720eda3..026d6f58eda1 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -84,7 +84,8 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
struct nlattr *tb[TCA_SKBMOD_MAX + 1];
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index c6e50695414b..ed698fcb0e5a 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -70,7 +70,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
static int tunnel_key_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 8dda78473004..72d2d78fb942 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -109,7 +109,8 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
static int tcf_vlan_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
- int ovr, int bind, struct netlink_ext_ack *extack)
+ int ovr, int bind, bool rtnl_held,
+ struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
struct nlattr *tb[TCA_VLAN_MAX + 1];
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 963e4bf0aab8..efbf01ce14c2 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1438,7 +1438,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
if (exts->police && tb[exts->police]) {
act = tcf_action_init_1(net, tp, tb[exts->police],
rate_tlv, "police", ovr,
- TCA_ACT_BIND, extack);
+ TCA_ACT_BIND, true, extack);
if (IS_ERR(act))
return PTR_ERR(act);
@@ -1451,7 +1451,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- &actions, &attr_size, extack);
+ &actions, &attr_size, true,
+ extack);
if (err)
return err;
list_for_each_entry(act, &actions, list)
--
2.7.5
^ permalink raw reply related
* [PATCH v2 06/11] net: sched: add 'delete' function to action ops
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Extend action ops with 'delete' function. Each action type to implements
its own delete function that doesn't depend on rtnl lock.
Implement delete function that is required to delete actions without
holding rtnl lock. Use action API function that atomically deletes action
only if it is still in action idr. This implementation prevents concurrent
threads from deleting same action twice.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
include/net/act_api.h | 1 +
net/sched/act_bpf.c | 8 ++++++++
net/sched/act_connmark.c | 8 ++++++++
net/sched/act_csum.c | 8 ++++++++
net/sched/act_gact.c | 8 ++++++++
net/sched/act_ife.c | 8 ++++++++
net/sched/act_ipt.c | 16 ++++++++++++++++
net/sched/act_mirred.c | 8 ++++++++
net/sched/act_nat.c | 8 ++++++++
net/sched/act_pedit.c | 8 ++++++++
net/sched/act_police.c | 8 ++++++++
net/sched/act_sample.c | 8 ++++++++
net/sched/act_simple.c | 8 ++++++++
net/sched/act_skbedit.c | 8 ++++++++
net/sched/act_skbmod.c | 8 ++++++++
net/sched/act_tunnel_key.c | 8 ++++++++
net/sched/act_vlan.c | 8 ++++++++
17 files changed, 137 insertions(+)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index d94ec6400673..d256e20507b9 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -101,6 +101,7 @@ struct tc_action_ops {
void (*stats_update)(struct tc_action *, u64, u32, u64);
size_t (*get_fill_size)(const struct tc_action *act);
struct net_device *(*get_dev)(const struct tc_action *a);
+ int (*delete)(struct net *net, u32 index);
};
struct tc_action_net {
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 8ebf40a3506c..7941dd66ff83 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -388,6 +388,13 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_bpf_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, bpf_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_bpf_ops __read_mostly = {
.kind = "bpf",
.type = TCA_ACT_BPF,
@@ -398,6 +405,7 @@ static struct tc_action_ops act_bpf_ops __read_mostly = {
.init = tcf_bpf_init,
.walk = tcf_bpf_walker,
.lookup = tcf_bpf_search,
+ .delete = tcf_bpf_delete,
.size = sizeof(struct tcf_bpf),
};
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index e3787aa0025a..143c2d3de723 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -193,6 +193,13 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_connmark_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, connmark_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_connmark_ops = {
.kind = "connmark",
.type = TCA_ACT_CONNMARK,
@@ -202,6 +209,7 @@ static struct tc_action_ops act_connmark_ops = {
.init = tcf_connmark_init,
.walk = tcf_connmark_walker,
.lookup = tcf_connmark_search,
+ .delete = tcf_connmark_delete,
.size = sizeof(struct tcf_connmark_info),
};
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 334261943f9f..3768539340e0 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -654,6 +654,13 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act)
return nla_total_size(sizeof(struct tc_csum));
}
+static int tcf_csum_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, csum_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_csum_ops = {
.kind = "csum",
.type = TCA_ACT_CSUM,
@@ -665,6 +672,7 @@ static struct tc_action_ops act_csum_ops = {
.walk = tcf_csum_walker,
.lookup = tcf_csum_search,
.get_fill_size = tcf_csum_get_fill_size,
+ .delete = tcf_csum_delete,
.size = sizeof(struct tcf_csum),
};
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b4dfb2b4addc..a431a711f0dd 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -231,6 +231,13 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act)
return sz;
}
+static int tcf_gact_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, gact_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_gact_ops = {
.kind = "gact",
.type = TCA_ACT_GACT,
@@ -242,6 +249,7 @@ static struct tc_action_ops act_gact_ops = {
.walk = tcf_gact_walker,
.lookup = tcf_gact_search,
.get_fill_size = tcf_gact_get_fill_size,
+ .delete = tcf_gact_delete,
.size = sizeof(struct tcf_gact),
};
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3dccc4e1d378..027c305dcb37 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -846,6 +846,13 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_ife_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ife_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_ife_ops = {
.kind = "ife",
.type = TCA_ACT_IFE,
@@ -856,6 +863,7 @@ static struct tc_action_ops act_ife_ops = {
.init = tcf_ife_init,
.walk = tcf_ife_walker,
.lookup = tcf_ife_search,
+ .delete = tcf_ife_delete,
.size = sizeof(struct tcf_ife_info),
};
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 9c21663a86a6..6c234411c771 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -324,6 +324,13 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_ipt_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, ipt_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_ipt_ops = {
.kind = "ipt",
.type = TCA_ACT_IPT,
@@ -334,6 +341,7 @@ static struct tc_action_ops act_ipt_ops = {
.init = tcf_ipt_init,
.walk = tcf_ipt_walker,
.lookup = tcf_ipt_search,
+ .delete = tcf_ipt_delete,
.size = sizeof(struct tcf_ipt),
};
@@ -374,6 +382,13 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_xt_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, xt_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_xt_ops = {
.kind = "xt",
.type = TCA_ACT_XT,
@@ -384,6 +399,7 @@ static struct tc_action_ops act_xt_ops = {
.init = tcf_xt_init,
.walk = tcf_xt_walker,
.lookup = tcf_xt_search,
+ .delete = tcf_xt_delete,
.size = sizeof(struct tcf_ipt),
};
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 5434f08f2eb7..3d8300bce7e4 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -322,6 +322,13 @@ static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
return rtnl_dereference(m->tcfm_dev);
}
+static int tcf_mirred_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, mirred_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_mirred_ops = {
.kind = "mirred",
.type = TCA_ACT_MIRRED,
@@ -335,6 +342,7 @@ static struct tc_action_ops act_mirred_ops = {
.lookup = tcf_mirred_search,
.size = sizeof(struct tcf_mirred),
.get_dev = tcf_mirred_get_dev,
+ .delete = tcf_mirred_delete,
};
static __net_init int mirred_init_net(struct net *net)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index e6487ad1e4a8..9eb27c89dc46 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -294,6 +294,13 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_nat_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, nat_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_nat_ops = {
.kind = "nat",
.type = TCA_ACT_NAT,
@@ -303,6 +310,7 @@ static struct tc_action_ops act_nat_ops = {
.init = tcf_nat_init,
.walk = tcf_nat_walker,
.lookup = tcf_nat_search,
+ .delete = tcf_nat_delete,
.size = sizeof(struct tcf_nat),
};
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 7c9a3f24edba..b8857035e3f8 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -436,6 +436,13 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_pedit_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, pedit_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_pedit_ops = {
.kind = "pedit",
.type = TCA_ACT_PEDIT,
@@ -446,6 +453,7 @@ static struct tc_action_ops act_pedit_ops = {
.init = tcf_pedit_init,
.walk = tcf_pedit_walker,
.lookup = tcf_pedit_search,
+ .delete = tcf_pedit_delete,
.size = sizeof(struct tcf_pedit),
};
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0e1c2fb0ebea..c955fb0d4f3f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -314,6 +314,13 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_police_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, police_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
MODULE_AUTHOR("Alexey Kuznetsov");
MODULE_DESCRIPTION("Policing actions");
MODULE_LICENSE("GPL");
@@ -327,6 +334,7 @@ static struct tc_action_ops act_police_ops = {
.init = tcf_act_police_init,
.walk = tcf_act_police_walker,
.lookup = tcf_police_search,
+ .delete = tcf_police_delete,
.size = sizeof(struct tcf_police),
};
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 316fc645595d..6f79d2afcba2 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -220,6 +220,13 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_sample_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_sample_ops = {
.kind = "sample",
.type = TCA_ACT_SAMPLE,
@@ -230,6 +237,7 @@ static struct tc_action_ops act_sample_ops = {
.cleanup = tcf_sample_cleanup,
.walk = tcf_sample_walker,
.lookup = tcf_sample_search,
+ .delete = tcf_sample_delete,
.size = sizeof(struct tcf_sample),
};
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 23fa893ea092..b570e7ca7e33 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -187,6 +187,13 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_simp_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, simp_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_simp_ops = {
.kind = "simple",
.type = TCA_ACT_SIMP,
@@ -197,6 +204,7 @@ static struct tc_action_ops act_simp_ops = {
.init = tcf_simp_init,
.walk = tcf_simp_walker,
.lookup = tcf_simp_search,
+ .delete = tcf_simp_delete,
.size = sizeof(struct tcf_defact),
};
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 85ed9d603dc1..dc0cb350aa45 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -226,6 +226,13 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_skbedit_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
.type = TCA_ACT_SKBEDIT,
@@ -235,6 +242,7 @@ static struct tc_action_ops act_skbedit_ops = {
.init = tcf_skbedit_init,
.walk = tcf_skbedit_walker,
.lookup = tcf_skbedit_search,
+ .delete = tcf_skbedit_delete,
.size = sizeof(struct tcf_skbedit),
};
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 026d6f58eda1..30be3f767495 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -253,6 +253,13 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_skbmod_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, skbmod_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_skbmod_ops = {
.kind = "skbmod",
.type = TCA_ACT_SKBMOD,
@@ -263,6 +270,7 @@ static struct tc_action_ops act_skbmod_ops = {
.cleanup = tcf_skbmod_cleanup,
.walk = tcf_skbmod_walker,
.lookup = tcf_skbmod_search,
+ .delete = tcf_skbmod_delete,
.size = sizeof(struct tcf_skbmod),
};
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index ed698fcb0e5a..4b7f9a3b47d7 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -310,6 +310,13 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tunnel_key_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_tunnel_key_ops = {
.kind = "tunnel_key",
.type = TCA_ACT_TUNNEL_KEY,
@@ -320,6 +327,7 @@ static struct tc_action_ops act_tunnel_key_ops = {
.cleanup = tunnel_key_release,
.walk = tunnel_key_walker,
.lookup = tunnel_key_search,
+ .delete = tunnel_key_delete,
.size = sizeof(struct tcf_tunnel_key),
};
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 72d2d78fb942..b44377c951b6 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -285,6 +285,13 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
return tcf_idr_search(tn, a, index);
}
+static int tcf_vlan_delete(struct net *net, u32 index)
+{
+ struct tc_action_net *tn = net_generic(net, vlan_net_id);
+
+ return tcf_idr_delete_index(tn, index);
+}
+
static struct tc_action_ops act_vlan_ops = {
.kind = "vlan",
.type = TCA_ACT_VLAN,
@@ -295,6 +302,7 @@ static struct tc_action_ops act_vlan_ops = {
.cleanup = tcf_vlan_cleanup,
.walk = tcf_vlan_walker,
.lookup = tcf_vlan_search,
+ .delete = tcf_vlan_delete,
.size = sizeof(struct tcf_vlan),
};
--
2.7.5
^ permalink raw reply related
* [PATCH v2 02/11] net: sched: change type of reference and bind counters
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Change type of action reference counter to refcount_t.
Change type of action bind counter to atomic_t.
This type is used to allow decrementing bind counter without testing
for 0 result.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
---
include/net/act_api.h | 5 +++--
net/sched/act_api.c | 32 ++++++++++++++++++++++----------
net/sched/act_bpf.c | 4 ++--
net/sched/act_connmark.c | 4 ++--
net/sched/act_csum.c | 4 ++--
net/sched/act_gact.c | 4 ++--
net/sched/act_ife.c | 4 ++--
net/sched/act_ipt.c | 4 ++--
net/sched/act_mirred.c | 4 ++--
net/sched/act_nat.c | 4 ++--
net/sched/act_pedit.c | 4 ++--
net/sched/act_police.c | 4 ++--
net/sched/act_sample.c | 4 ++--
net/sched/act_simple.c | 4 ++--
net/sched/act_skbedit.c | 4 ++--
net/sched/act_skbmod.c | 4 ++--
net/sched/act_tunnel_key.c | 4 ++--
net/sched/act_vlan.c | 4 ++--
18 files changed, 57 insertions(+), 44 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index f7b59ef7303d..e634014605cb 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -6,6 +6,7 @@
* Public action API for classifiers/qdiscs
*/
+#include <linux/refcount.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/net_namespace.h>
@@ -26,8 +27,8 @@ struct tc_action {
struct tcf_idrinfo *idrinfo;
u32 tcfa_index;
- int tcfa_refcnt;
- int tcfa_bindcnt;
+ refcount_t tcfa_refcnt;
+ atomic_t tcfa_bindcnt;
u32 tcfa_capab;
int tcfa_action;
struct tcf_t tcfa_tm;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 02670c7489e3..4f064ecab882 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -105,14 +105,26 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
ASSERT_RTNL();
+ /* Release with strict==1 and bind==0 is only called through act API
+ * interface (classifiers always bind). Only case when action with
+ * positive reference count and zero bind count can exist is when it was
+ * also created with act API (unbinding last classifier will destroy the
+ * action if it was created by classifier). So only case when bind count
+ * can be changed after initial check is when unbound action is
+ * destroyed by act API while classifier binds to action with same id
+ * concurrently. This result either creation of new action(same behavior
+ * as before), or reusing existing action if concurrent process
+ * increments reference count before action is deleted. Both scenarios
+ * are acceptable.
+ */
if (p) {
if (bind)
- p->tcfa_bindcnt--;
- else if (strict && p->tcfa_bindcnt > 0)
+ atomic_dec(&p->tcfa_bindcnt);
+ else if (strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
- p->tcfa_refcnt--;
- if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) {
+ if (atomic_read(&p->tcfa_bindcnt) <= 0 &&
+ refcount_dec_and_test(&p->tcfa_refcnt)) {
if (p->ops->cleanup)
p->ops->cleanup(p);
tcf_idr_remove(p->idrinfo, p);
@@ -304,8 +316,8 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
if (index && p) {
if (bind)
- p->tcfa_bindcnt++;
- p->tcfa_refcnt++;
+ atomic_inc(&p->tcfa_bindcnt);
+ refcount_inc(&p->tcfa_refcnt);
*a = p;
return true;
}
@@ -324,9 +336,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
if (unlikely(!p))
return -ENOMEM;
- p->tcfa_refcnt = 1;
+ refcount_set(&p->tcfa_refcnt, 1);
if (bind)
- p->tcfa_bindcnt = 1;
+ atomic_set(&p->tcfa_bindcnt, 1);
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
@@ -782,7 +794,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
return;
list_for_each_entry(a, actions, list)
- a->tcfa_refcnt--;
+ refcount_dec(&a->tcfa_refcnt);
}
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
@@ -810,7 +822,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
act->order = i;
sz += tcf_action_fill_size(act);
if (ovr)
- act->tcfa_refcnt++;
+ refcount_inc(&act->tcfa_refcnt);
list_add_tail(&act->list, actions);
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 18089c02e557..15a2a53cbde1 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -141,8 +141,8 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
struct tcf_bpf *prog = to_bpf(act);
struct tc_act_bpf opt = {
.index = prog->tcf_index,
- .refcnt = prog->tcf_refcnt - ref,
- .bindcnt = prog->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&prog->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
.action = prog->tcf_action,
};
struct tcf_t tm;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index e4b880fa51fe..188865034f9a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -154,8 +154,8 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
struct tc_connmark opt = {
.index = ci->tcf_index,
- .refcnt = ci->tcf_refcnt - ref,
- .bindcnt = ci->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&ci->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
.action = ci->tcf_action,
.zone = ci->zone,
};
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 526a8e491626..da865f7b390a 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -597,8 +597,8 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
struct tcf_csum_params *params;
struct tc_csum opt = {
.index = p->tcf_index,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 4dc4f153cad8..ca83debd5a70 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -169,8 +169,8 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_gact *gact = to_gact(a);
struct tc_gact opt = {
.index = gact->tcf_index,
- .refcnt = gact->tcf_refcnt - ref,
- .bindcnt = gact->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&gact->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
.action = gact->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 8527cfdc446d..706e84d6f912 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -598,8 +598,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
struct tcf_ife_params *p = rtnl_dereference(ife->params);
struct tc_ife opt = {
.index = ife->tcf_index,
- .refcnt = ife->tcf_refcnt - ref,
- .bindcnt = ife->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&ife->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
.action = ife->tcf_action,
.flags = p->flags,
};
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 14c312d7908f..7bce88dc11c9 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -280,8 +280,8 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
if (unlikely(!t))
goto nla_put_failure;
- c.bindcnt = ipt->tcf_bindcnt - bind;
- c.refcnt = ipt->tcf_refcnt - ref;
+ c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
+ c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index fd34015331ab..82a8bdd67c47 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -250,8 +250,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
struct tc_mirred opt = {
.index = m->tcf_index,
.action = m->tcf_action,
- .refcnt = m->tcf_refcnt - ref,
- .bindcnt = m->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&m->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
.eaction = m->tcfm_eaction,
.ifindex = dev ? dev->ifindex : 0,
};
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4b5848b6c252..457c2ae3de46 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -257,8 +257,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
.index = p->tcf_index,
.action = p->tcf_action,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 8a925c72db5f..0102b2935fdb 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -391,8 +391,8 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
opt->nkeys = p->tcfp_nkeys;
opt->flags = p->tcfp_flags;
opt->action = p->tcf_action;
- opt->refcnt = p->tcf_refcnt - ref;
- opt->bindcnt = p->tcf_bindcnt - bind;
+ opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
+ opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
if (p->tcfp_keys_ex) {
tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 4e72bc2a0dfb..a789b8060968 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -274,8 +274,8 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
.action = police->tcf_action,
.mtu = police->tcfp_mtu,
.burst = PSCHED_NS2TICKS(police->tcfp_burst),
- .refcnt = police->tcf_refcnt - ref,
- .bindcnt = police->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&police->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 5db358497c9e..4a46978db092 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -173,8 +173,8 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
struct tc_sample opt = {
.index = s->tcf_index,
.action = s->tcf_action,
- .refcnt = s->tcf_refcnt - ref,
- .bindcnt = s->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&s->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&s->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 9618b4a83cee..95d5985b8d67 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -148,8 +148,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_defact *d = to_defact(a);
struct tc_defact opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6138d1d71900..d418ec3b0ab9 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -173,8 +173,8 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_skbedit *d = to_skbedit(a);
struct tc_skbedit opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index ad050d7d4b46..ff90d720eda3 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -205,8 +205,8 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p);
struct tc_skbmod opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 626dac81a48a..c6e50695414b 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -252,8 +252,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_tunnel_key_params *params;
struct tc_tunnel_key opt = {
.index = t->tcf_index,
- .refcnt = t->tcf_refcnt - ref,
- .bindcnt = t->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&t->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&t->tcf_bindcnt) - bind,
};
struct tcf_t tm;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 853604685965..8dda78473004 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -237,8 +237,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
struct tc_vlan opt = {
.index = v->tcf_index,
- .refcnt = v->tcf_refcnt - ref,
- .bindcnt = v->tcf_bindcnt - bind,
+ .refcnt = refcount_read(&v->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&v->tcf_bindcnt) - bind,
.action = v->tcf_action,
.v_action = p->tcfv_action,
};
--
2.7.5
^ permalink raw reply related
* [PATCH v2 07/11] net: sched: implement reference counted action release
From: Vlad Buslov @ 2018-05-27 16:41 UTC (permalink / raw)
To: netdev; +Cc: davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn,
Vlad Buslov
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Implement helper delete function that uses new action ops 'delete', instead
of destroying action directly. This is required so act API could delete
actions by index, without holding any references to action that is being
deleted.
Implement function __tcf_action_put() that releases reference to action and
frees it, if necessary. Refactor action deletion code to use new put
function and not to rely on rtnl lock. Remove rtnl lock assertions that are
no longer needed.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
net/sched/act_api.c | 84 +++++++++++++++++++++++++++++++++++++++--------------
net/sched/cls_api.c | 1 -
2 files changed, 62 insertions(+), 23 deletions(-)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 0f31f09946ab..a023873db713 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -90,21 +90,39 @@ static void free_tcf(struct tc_action *p)
kfree(p);
}
-static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
+static void tcf_action_cleanup(struct tc_action *p)
{
- spin_lock(&idrinfo->lock);
- idr_remove(&idrinfo->action_idr, p->tcfa_index);
- spin_unlock(&idrinfo->lock);
+ if (p->ops->cleanup)
+ p->ops->cleanup(p);
+
gen_kill_estimator(&p->tcfa_rate_est);
free_tcf(p);
}
+static int __tcf_action_put(struct tc_action *p, bool bind)
+{
+ struct tcf_idrinfo *idrinfo = p->idrinfo;
+
+ if (refcount_dec_and_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
+ if (bind)
+ atomic_dec(&p->tcfa_bindcnt);
+ idr_remove(&idrinfo->action_idr, p->tcfa_index);
+ spin_unlock(&idrinfo->lock);
+
+ tcf_action_cleanup(p);
+ return 1;
+ }
+
+ if (bind)
+ atomic_dec(&p->tcfa_bindcnt);
+
+ return 0;
+}
+
int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
{
int ret = 0;
- ASSERT_RTNL();
-
/* Release with strict==1 and bind==0 is only called through act API
* interface (classifiers always bind). Only case when action with
* positive reference count and zero bind count can exist is when it was
@@ -118,18 +136,11 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
* are acceptable.
*/
if (p) {
- if (bind)
- atomic_dec(&p->tcfa_bindcnt);
- else if (strict && atomic_read(&p->tcfa_bindcnt) > 0)
+ if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
- if (atomic_read(&p->tcfa_bindcnt) <= 0 &&
- refcount_dec_and_test(&p->tcfa_refcnt)) {
- if (p->ops->cleanup)
- p->ops->cleanup(p);
- tcf_idr_remove(p->idrinfo, p);
+ if (__tcf_action_put(p, bind))
ret = ACT_P_DELETED;
- }
}
return ret;
@@ -340,11 +351,7 @@ int tcf_idr_delete_index(struct tc_action_net *tn, u32 index)
p->tcfa_index));
spin_unlock(&idrinfo->lock);
- if (p->ops->cleanup)
- p->ops->cleanup(p);
-
- gen_kill_estimator(&p->tcfa_rate_est);
- free_tcf(p);
+ tcf_action_cleanup(p);
module_put(owner);
return 0;
}
@@ -615,6 +622,11 @@ int tcf_action_destroy(struct list_head *actions, int bind)
return ret;
}
+static int tcf_action_put(struct tc_action *p)
+{
+ return __tcf_action_put(p, false);
+}
+
int
tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
@@ -1092,6 +1104,35 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
return err;
}
+static int tcf_action_delete(struct net *net, struct list_head *actions,
+ struct netlink_ext_ack *extack)
+{
+ struct tc_action *a, *tmp;
+ u32 act_index;
+ int ret;
+
+ list_for_each_entry_safe(a, tmp, actions, list) {
+ const struct tc_action_ops *ops = a->ops;
+
+ /* Actions can be deleted concurrently so we must save their
+ * type and id to search again after reference is released.
+ */
+ act_index = a->tcfa_index;
+
+ list_del(&a->list);
+ if (tcf_action_put(a)) {
+ /* last reference, action was deleted concurrently */
+ module_put(ops->owner);
+ } else {
+ /* now do the delete */
+ ret = ops->delete(net, act_index);
+ if (ret < 0)
+ return ret;
+ }
+ }
+ return 0;
+}
+
static int
tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
@@ -1112,7 +1153,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
}
/* now do the delete */
- ret = tcf_action_destroy(actions, 0);
+ ret = tcf_action_delete(net, actions, extack);
if (ret < 0) {
NL_SET_ERR_MSG(extack, "Failed to delete TC action");
kfree_skb(skb);
@@ -1164,7 +1205,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
if (event == RTM_GETACTION)
ret = tcf_get_notify(net, portid, n, &actions, event, extack);
else { /* delete */
- cleanup_a(&actions, 1); /* lookup took reference */
ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
if (ret)
goto err;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index efbf01ce14c2..dd37d0ae3fce 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1417,7 +1417,6 @@ void tcf_exts_destroy(struct tcf_exts *exts)
#ifdef CONFIG_NET_CLS_ACT
LIST_HEAD(actions);
- ASSERT_RTNL();
tcf_exts_to_list(exts, &actions);
tcf_action_destroy(&actions, TCA_ACT_UNBIND);
kfree(exts->actions);
--
2.7.5
^ permalink raw reply related
* Re: [PATCH v2 00/11] Modify action API for implementing lockless actions
From: Jiri Pirko @ 2018-05-27 17:57 UTC (permalink / raw)
To: Vlad Buslov
Cc: netdev, davem, jhs, xiyou.wangcong, jiri, ast, daniel, kliteyn
In-Reply-To: <1527439298-22306-1-git-send-email-vladbu@mellanox.com>
Sun, May 27, 2018 at 06:41:27PM CEST, vladbu@mellanox.com wrote:
[...]
>Changes from V1 to V2:
>- Removed redundant actions ops lookup during delete.
>- Merge action ops delete definition and implementation.
>- Assume all actions have delete implemented and don't check for it
> explicitly.
>- Resplit action lookup/release code to prevent memory leaks in
> individual patches.
>- Make __tcf_idr_check function static
>- Remove unique idr insertion function. Change original idr insert to do
> the same thing.
>- Merge changes that take reference to action when performing lookup and
> changes that account for this additional reference when dumping action
> to user space into single patch.
>- Change convoluted commit message.
>- Rename "unlocked" to "rtnl_held" for clarity.
>- Remove estimator lock add patch.
>- Refactor action check-alloc code into standalone function.
>- Rename tcf_idr_find_delete to tcf_idr_delete_index.
>- Rearrange variable definitions in tc_action_delete.
>- Add patch that refactors action API code to use array of pointers to
> actions instead of intrusive linked list.
>- Expand cover letter.
With 11 patches, I'm unable to follow the changes in this description.
Could you please write the changes to each individual patch?
What I do is I write changes for each patch under "---" (there are two
"---" lines in each patch then. Then I also copy the changes descriptions
to the cover letter.
[...]
^ permalink raw reply
* [PATCH] net: sched: split tc_ctl_tfilter into three handlers
From: Vlad Buslov @ 2018-05-27 19:55 UTC (permalink / raw)
To: netdev; +Cc: jhs, xiyou.wangcong, jiri, davem, kliteyn, Vlad Buslov
tc_ctl_tfilter handles three netlink message types: RTM_NEWTFILTER,
RTM_DELTFILTER, RTM_GETTFILTER. However, implementation of this function
involves a lot of branching on specific message type because most of the
code is message-specific. This significantly complicates adding new
functionality and doesn't provide much benefit of code reuse.
Split tc_ctl_tfilter to three standalone functions that handle filter new,
delete and get requests.
The only truly protocol independent part of tc_ctl_tfilter is code that
looks up queue, class, and block. Refactor this code to standalone
tcf_block_find function that is used by all three new handlers.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
---
net/sched/cls_api.c | 438 +++++++++++++++++++++++++++++++++++-----------------
1 file changed, 293 insertions(+), 145 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1ed673f501c2..8dfbad1bddf5 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -436,6 +436,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
return idr_find(&tn->idr, block_index);
}
+/* Find tcf block.
+ * Set q, parent, cl when appropriate.
+ */
+
+static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
+ u32 *parent, unsigned long *cl,
+ int ifindex, u32 block_index,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_block *block;
+
+ if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+ block = tcf_block_lookup(net, block_index);
+ if (!block) {
+ NL_SET_ERR_MSG(extack, "Block of given index was not found");
+ return ERR_PTR(-EINVAL);
+ }
+ } else {
+ const struct Qdisc_class_ops *cops;
+ struct net_device *dev;
+
+ /* Find link */
+ dev = __dev_get_by_index(net, ifindex);
+ if (!dev)
+ return ERR_PTR(-ENODEV);
+
+ /* Find qdisc */
+ if (!*parent) {
+ *q = dev->qdisc;
+ *parent = (*q)->handle;
+ } else {
+ *q = qdisc_lookup(dev, TC_H_MAJ(*parent));
+ if (!*q) {
+ NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ /* Is it classful? */
+ cops = (*q)->ops->cl_ops;
+ if (!cops) {
+ NL_SET_ERR_MSG(extack, "Qdisc not classful");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!cops->tcf_block) {
+ NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+
+ /* Do we search for filter, attached to class? */
+ if (TC_H_MIN(*parent)) {
+ *cl = cops->find(*q, *parent);
+ if (*cl == 0) {
+ NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
+ return ERR_PTR(-ENOENT);
+ }
+ }
+
+ /* And the last stroke */
+ block = cops->tcf_block(*q, *cl, extack);
+ if (!block)
+ return ERR_PTR(-EINVAL);
+ if (tcf_block_shared(block)) {
+ NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
+ return ERR_PTR(-EOPNOTSUPP);
+ }
+ }
+
+ return block;
+}
+
static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
{
return list_first_entry(&block->chain_list, struct tcf_chain, list);
@@ -1002,9 +1074,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
q, parent, 0, event, false);
}
-/* Add/change/delete/get a filter node */
-
-static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
@@ -1025,8 +1095,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
int err;
int tp_created;
- if ((n->nlmsg_type != RTM_GETTFILTER) &&
- !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
return -EPERM;
replay:
@@ -1044,24 +1113,13 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
cl = 0;
if (prio == 0) {
- switch (n->nlmsg_type) {
- case RTM_DELTFILTER:
- if (protocol || t->tcm_handle || tca[TCA_KIND]) {
- NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
- return -ENOENT;
- }
- break;
- case RTM_NEWTFILTER:
- /* If no priority is provided by the user,
- * we allocate one.
- */
- if (n->nlmsg_flags & NLM_F_CREATE) {
- prio = TC_H_MAKE(0x80000000U, 0U);
- prio_allocate = true;
- break;
- }
- /* fall-through */
- default:
+ /* If no priority is provided by the user,
+ * we allocate one.
+ */
+ if (n->nlmsg_flags & NLM_F_CREATE) {
+ prio = TC_H_MAKE(0x80000000U, 0U);
+ prio_allocate = true;
+ } else {
NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
return -ENOENT;
}
@@ -1069,66 +1127,11 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
/* Find head of filter chain. */
- if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
- block = tcf_block_lookup(net, t->tcm_block_index);
- if (!block) {
- NL_SET_ERR_MSG(extack, "Block of given index was not found");
- err = -EINVAL;
- goto errout;
- }
- } else {
- const struct Qdisc_class_ops *cops;
- struct net_device *dev;
-
- /* Find link */
- dev = __dev_get_by_index(net, t->tcm_ifindex);
- if (!dev)
- return -ENODEV;
-
- /* Find qdisc */
- if (!parent) {
- q = dev->qdisc;
- parent = q->handle;
- } else {
- q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
- if (!q) {
- NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
- return -EINVAL;
- }
- }
-
- /* Is it classful? */
- cops = q->ops->cl_ops;
- if (!cops) {
- NL_SET_ERR_MSG(extack, "Qdisc not classful");
- return -EINVAL;
- }
-
- if (!cops->tcf_block) {
- NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
- return -EOPNOTSUPP;
- }
-
- /* Do we search for filter, attached to class? */
- if (TC_H_MIN(parent)) {
- cl = cops->find(q, parent);
- if (cl == 0) {
- NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
- return -ENOENT;
- }
- }
-
- /* And the last stroke */
- block = cops->tcf_block(q, cl, extack);
- if (!block) {
- err = -EINVAL;
- goto errout;
- }
- if (tcf_block_shared(block)) {
- NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
- err = -EOPNOTSUPP;
- goto errout;
- }
+ block = tcf_block_find(net, &q, &parent, &cl,
+ t->tcm_ifindex, t->tcm_block_index, extack);
+ if (IS_ERR(block)) {
+ err = PTR_ERR(block);
+ goto errout;
}
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
@@ -1137,19 +1140,10 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
err = -EINVAL;
goto errout;
}
- chain = tcf_chain_get(block, chain_index,
- n->nlmsg_type == RTM_NEWTFILTER);
+ chain = tcf_chain_get(block, chain_index, true);
if (!chain) {
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
- err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL;
- goto errout;
- }
-
- if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
- tfilter_notify_chain(net, skb, block, q, parent, n,
- chain, RTM_DELTFILTER);
- tcf_chain_flush(chain);
- err = 0;
+ err = -ENOMEM;
goto errout;
}
@@ -1170,8 +1164,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
goto errout;
}
- if (n->nlmsg_type != RTM_NEWTFILTER ||
- !(n->nlmsg_flags & NLM_F_CREATE)) {
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
err = -ENOENT;
goto errout;
@@ -1196,56 +1189,15 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
fh = tp->ops->get(tp, t->tcm_handle);
if (!fh) {
- if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
- tcf_chain_tp_remove(chain, &chain_info, tp);
- tfilter_notify(net, skb, n, tp, block, q, parent, fh,
- RTM_DELTFILTER, false);
- tcf_proto_destroy(tp, extack);
- err = 0;
- goto errout;
- }
-
- if (n->nlmsg_type != RTM_NEWTFILTER ||
- !(n->nlmsg_flags & NLM_F_CREATE)) {
+ if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
err = -ENOENT;
goto errout;
}
- } else {
- bool last;
-
- switch (n->nlmsg_type) {
- case RTM_NEWTFILTER:
- if (n->nlmsg_flags & NLM_F_EXCL) {
- if (tp_created)
- tcf_proto_destroy(tp, NULL);
- NL_SET_ERR_MSG(extack, "Filter already exists");
- err = -EEXIST;
- goto errout;
- }
- break;
- case RTM_DELTFILTER:
- err = tfilter_del_notify(net, skb, n, tp, block,
- q, parent, fh, false, &last,
- extack);
- if (err)
- goto errout;
- if (last) {
- tcf_chain_tp_remove(chain, &chain_info, tp);
- tcf_proto_destroy(tp, extack);
- }
- goto errout;
- case RTM_GETTFILTER:
- err = tfilter_notify(net, skb, n, tp, block, q, parent,
- fh, RTM_NEWTFILTER, true);
- if (err < 0)
- NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
- goto errout;
- default:
- NL_SET_ERR_MSG(extack, "Invalid netlink message type");
- err = -EINVAL;
- goto errout;
- }
+ } else if (n->nlmsg_flags & NLM_F_EXCL) {
+ NL_SET_ERR_MSG(extack, "Filter already exists");
+ err = -EEXIST;
+ goto errout;
}
err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
@@ -1270,6 +1222,202 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
return err;
}
+static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tca[TCA_MAX + 1];
+ struct tcmsg *t;
+ u32 protocol;
+ u32 prio;
+ u32 parent;
+ u32 chain_index;
+ struct Qdisc *q = NULL;
+ struct tcf_chain_info chain_info;
+ struct tcf_chain *chain = NULL;
+ struct tcf_block *block;
+ struct tcf_proto *tp = NULL;
+ unsigned long cl = 0;
+ void *fh = NULL;
+ int err;
+
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ if (err < 0)
+ return err;
+
+ t = nlmsg_data(n);
+ protocol = TC_H_MIN(t->tcm_info);
+ prio = TC_H_MAJ(t->tcm_info);
+ parent = t->tcm_parent;
+
+ if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) {
+ NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
+ return -ENOENT;
+ }
+
+ /* Find head of filter chain. */
+
+ block = tcf_block_find(net, &q, &parent, &cl,
+ t->tcm_ifindex, t->tcm_block_index, extack);
+ if (IS_ERR(block)) {
+ err = PTR_ERR(block);
+ goto errout;
+ }
+
+ chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ if (chain_index > TC_ACT_EXT_VAL_MASK) {
+ NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+ err = -EINVAL;
+ goto errout;
+ }
+ chain = tcf_chain_get(block, chain_index, false);
+ if (!chain) {
+ NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+ err = -EINVAL;
+ goto errout;
+ }
+
+ if (prio == 0) {
+ tfilter_notify_chain(net, skb, block, q, parent, n,
+ chain, RTM_DELTFILTER);
+ tcf_chain_flush(chain);
+ err = 0;
+ goto errout;
+ }
+
+ tp = tcf_chain_tp_find(chain, &chain_info, protocol,
+ prio, false);
+ if (!tp || IS_ERR(tp)) {
+ NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
+ err = PTR_ERR(tp);
+ goto errout;
+ } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
+ NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
+ err = -EINVAL;
+ goto errout;
+ }
+
+ fh = tp->ops->get(tp, t->tcm_handle);
+
+ if (!fh) {
+ if (t->tcm_handle == 0) {
+ tcf_chain_tp_remove(chain, &chain_info, tp);
+ tfilter_notify(net, skb, n, tp, block, q, parent, fh,
+ RTM_DELTFILTER, false);
+ tcf_proto_destroy(tp, extack);
+ err = 0;
+ } else {
+ NL_SET_ERR_MSG(extack, "Specified filter handle not found");
+ err = -ENOENT;
+ }
+ } else {
+ bool last;
+
+ err = tfilter_del_notify(net, skb, n, tp, block,
+ q, parent, fh, false, &last,
+ extack);
+ if (err)
+ goto errout;
+ if (last) {
+ tcf_chain_tp_remove(chain, &chain_info, tp);
+ tcf_proto_destroy(tp, extack);
+ }
+ }
+
+errout:
+ if (chain)
+ tcf_chain_put(chain);
+ return err;
+}
+
+static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(skb->sk);
+ struct nlattr *tca[TCA_MAX + 1];
+ struct tcmsg *t;
+ u32 protocol;
+ u32 prio;
+ u32 parent;
+ u32 chain_index;
+ struct Qdisc *q = NULL;
+ struct tcf_chain_info chain_info;
+ struct tcf_chain *chain = NULL;
+ struct tcf_block *block;
+ struct tcf_proto *tp = NULL;
+ unsigned long cl = 0;
+ void *fh = NULL;
+ int err;
+
+ err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+ if (err < 0)
+ return err;
+
+ t = nlmsg_data(n);
+ protocol = TC_H_MIN(t->tcm_info);
+ prio = TC_H_MAJ(t->tcm_info);
+ parent = t->tcm_parent;
+
+ if (prio == 0) {
+ NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
+ return -ENOENT;
+ }
+
+ /* Find head of filter chain. */
+
+ block = tcf_block_find(net, &q, &parent, &cl,
+ t->tcm_ifindex, t->tcm_block_index, extack);
+ if (IS_ERR(block)) {
+ err = PTR_ERR(block);
+ goto errout;
+ }
+
+ chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+ if (chain_index > TC_ACT_EXT_VAL_MASK) {
+ NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+ err = -EINVAL;
+ goto errout;
+ }
+ chain = tcf_chain_get(block, chain_index, false);
+ if (!chain) {
+ NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+ err = -EINVAL;
+ goto errout;
+ }
+
+ tp = tcf_chain_tp_find(chain, &chain_info, protocol,
+ prio, false);
+ if (!tp || IS_ERR(tp)) {
+ NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
+ err = PTR_ERR(tp);
+ goto errout;
+ } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
+ NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
+ err = -EINVAL;
+ goto errout;
+ }
+
+ fh = tp->ops->get(tp, t->tcm_handle);
+
+ if (!fh) {
+ NL_SET_ERR_MSG(extack, "Specified filter handle not found");
+ err = -ENOENT;
+ } else {
+ err = tfilter_notify(net, skb, n, tp, block, q, parent,
+ fh, RTM_NEWTFILTER, true);
+ if (err < 0)
+ NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
+ }
+
+errout:
+ if (chain)
+ tcf_chain_put(chain);
+ return err;
+}
+
struct tcf_dump_args {
struct tcf_walker w;
struct sk_buff *skb;
@@ -1653,9 +1801,9 @@ static int __init tc_filter_init(void)
if (err)
goto err_register_pernet_subsys;
- rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0);
- rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
+ rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
+ rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
tc_dump_tfilter, 0);
return 0;
--
2.7.5
^ permalink raw reply related
* KASAN: use-after-free Write in bpf_tcp_close
From: syzbot @ 2018-05-27 20:06 UTC (permalink / raw)
To: ast, daniel, linux-kernel, netdev, syzkaller-bugs
Hello,
syzbot found the following crash on:
HEAD commit: ff4fb475cea8 Merge branch 'btf-uapi-cleanups'
git tree: bpf-next
console output: https://syzkaller.appspot.com/x/log.txt?x=12b3d577800000
kernel config: https://syzkaller.appspot.com/x/.config?x=b632d8e2c2ab2c1
dashboard link: https://syzkaller.appspot.com/bug?extid=31025a5f3f7650081204
compiler: gcc (GCC) 8.0.1 20180413 (experimental)
syzkaller repro:https://syzkaller.appspot.com/x/repro.syz?x=109a2f37800000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=171a727b800000
IMPORTANT: if you fix the bug, please add the following tag to the commit:
Reported-by: syzbot+31025a5f3f7650081204@syzkaller.appspotmail.com
==================================================================
BUG: KASAN: use-after-free in cmpxchg_size
include/asm-generic/atomic-instrumented.h:355 [inline]
BUG: KASAN: use-after-free in bpf_tcp_close+0x6f5/0xf80
kernel/bpf/sockmap.c:265
Write of size 8 at addr ffff8801ca277680 by task syz-executor749/9723
CPU: 0 PID: 9723 Comm: syz-executor749 Not tainted 4.17.0-rc4+ #19
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x1b9/0x294 lib/dump_stack.c:113
print_address_description+0x6c/0x20b mm/kasan/report.c:256
kasan_report_error mm/kasan/report.c:354 [inline]
kasan_report.cold.7+0x242/0x2fe mm/kasan/report.c:412
check_memory_region_inline mm/kasan/kasan.c:260 [inline]
check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
kasan_check_write+0x14/0x20 mm/kasan/kasan.c:278
cmpxchg_size include/asm-generic/atomic-instrumented.h:355 [inline]
bpf_tcp_close+0x6f5/0xf80 kernel/bpf/sockmap.c:265
inet_release+0x104/0x1f0 net/ipv4/af_inet.c:427
inet6_release+0x50/0x70 net/ipv6/af_inet6.c:459
sock_release+0x96/0x1b0 net/socket.c:594
sock_close+0x16/0x20 net/socket.c:1149
__fput+0x34d/0x890 fs/file_table.c:209
____fput+0x15/0x20 fs/file_table.c:243
task_work_run+0x1e4/0x290 kernel/task_work.c:113
exit_task_work include/linux/task_work.h:22 [inline]
do_exit+0x1aee/0x2730 kernel/exit.c:865
do_group_exit+0x16f/0x430 kernel/exit.c:968
__do_sys_exit_group kernel/exit.c:979 [inline]
__se_sys_exit_group kernel/exit.c:977 [inline]
__x64_sys_exit_group+0x3e/0x50 kernel/exit.c:977
do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x440a59
RSP: 002b:00007ffdadf92488 EFLAGS: 00000206 ORIG_RAX: 00000000000000e7
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000440a59
RDX: 0000000000440a59 RSI: 0000000000000020 RDI: 0000000000000000
RBP: 0000000000000000 R08: 00000000004002c8 R09: 0000000000401ea0
R10: 00000000004002c8 R11: 0000000000000206 R12: 000000000001b5ac
R13: 0000000000401ea0 R14: 0000000000000000 R15: 0000000000000000
Allocated by task 9723:
save_stack+0x43/0xd0 mm/kasan/kasan.c:448
set_track mm/kasan/kasan.c:460 [inline]
kasan_kmalloc+0xc4/0xe0 mm/kasan/kasan.c:553
__do_kmalloc_node mm/slab.c:3682 [inline]
__kmalloc_node+0x47/0x70 mm/slab.c:3689
kmalloc_node include/linux/slab.h:554 [inline]
bpf_map_area_alloc+0x3f/0x90 kernel/bpf/syscall.c:144
sock_map_alloc+0x376/0x410 kernel/bpf/sockmap.c:1555
find_and_alloc_map kernel/bpf/syscall.c:126 [inline]
map_create+0x393/0x1010 kernel/bpf/syscall.c:448
__do_sys_bpf kernel/bpf/syscall.c:2128 [inline]
__se_sys_bpf kernel/bpf/syscall.c:2105 [inline]
__x64_sys_bpf+0x300/0x4f0 kernel/bpf/syscall.c:2105
do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Freed by task 4521:
save_stack+0x43/0xd0 mm/kasan/kasan.c:448
set_track mm/kasan/kasan.c:460 [inline]
__kasan_slab_free+0x11a/0x170 mm/kasan/kasan.c:521
kasan_slab_free+0xe/0x10 mm/kasan/kasan.c:528
__cache_free mm/slab.c:3498 [inline]
kfree+0xd9/0x260 mm/slab.c:3813
kvfree+0x61/0x70 mm/util.c:440
bpf_map_area_free+0x15/0x20 kernel/bpf/syscall.c:155
sock_map_remove_complete kernel/bpf/sockmap.c:1443 [inline]
sock_map_free+0x408/0x540 kernel/bpf/sockmap.c:1619
bpf_map_free_deferred+0xba/0xf0 kernel/bpf/syscall.c:259
process_one_work+0xc1e/0x1b50 kernel/workqueue.c:2145
worker_thread+0x1cc/0x1440 kernel/workqueue.c:2279
kthread+0x345/0x410 kernel/kthread.c:238
ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412
The buggy address belongs to the object at ffff8801ca277680
which belongs to the cache kmalloc-1024 of size 1024
The buggy address is located 0 bytes inside of
1024-byte region [ffff8801ca277680, ffff8801ca277a80)
The buggy address belongs to the page:
page:ffffea0007289d80 count:1 mapcount:0 mapping:ffff8801ca276000 index:0x0
compound_mapcount: 0
flags: 0x2fffc0000008100(slab|head)
raw: 02fffc0000008100 ffff8801ca276000 0000000000000000 0000000100000007
raw: ffffea0006d12b20 ffffea000763bba0 ffff8801da800ac0 0000000000000000
page dumped because: kasan: bad access detected
Memory state around the buggy address:
ffff8801ca277580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
ffff8801ca277600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
> ffff8801ca277680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
^
ffff8801ca277700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
ffff8801ca277780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
==================================================================
---
This bug is generated by a bot. It may contain errors.
See https://goo.gl/tpsmEJ for more information about syzbot.
syzbot engineers can be reached at syzkaller@googlegroups.com.
syzbot will keep track of this bug report. See:
https://goo.gl/tpsmEJ#bug-status-tracking for how to communicate with
syzbot.
syzbot can test patches for this bug, for details see:
https://goo.gl/tpsmEJ#testing-patches
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox