From 56ce7c25ae1525d83cf80a880cf506ead1914250 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 14 Dec 2020 15:38:32 +0200 Subject: xfrm: Fix oops in xfrm_replay_advance_bmp When setting xfrm replay_window to values higher than 32, a rare page-fault occurs in xfrm_replay_advance_bmp: BUG: unable to handle page fault for address: ffff8af350ad7920 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD ad001067 P4D ad001067 PUD 0 Oops: 0002 [#1] SMP PTI CPU: 3 PID: 30 Comm: ksoftirqd/3 Kdump: loaded Not tainted 5.4.52-050452-generic #202007160732 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.el7 04/01/2014 RIP: 0010:xfrm_replay_advance_bmp+0xbb/0x130 RSP: 0018:ffffa1304013ba40 EFLAGS: 00010206 RAX: 000000000000010d RBX: 0000000000000002 RCX: 00000000ffffff4b RDX: 0000000000000018 RSI: 00000000004c234c RDI: 00000000ffb3dbff RBP: ffffa1304013ba50 R08: ffff8af330ad7920 R09: 0000000007fffffa R10: 0000000000000800 R11: 0000000000000010 R12: ffff8af29d6258c0 R13: ffff8af28b95c700 R14: 0000000000000000 R15: ffff8af29d6258fc FS: 0000000000000000(0000) GS:ffff8af339ac0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffff8af350ad7920 CR3: 0000000015ee4000 CR4: 00000000001406e0 Call Trace: xfrm_input+0x4e5/0xa10 xfrm4_rcv_encap+0xb5/0xe0 xfrm4_udp_encap_rcv+0x140/0x1c0 Analysis revealed offending code is when accessing: replay_esn->bmp[nr] |= (1U << bitnr); with 'nr' being 0x07fffffa. This happened in an SMP system when reordering of packets was present; A packet arrived with a "too old" sequence number (outside the window, i.e 'diff > replay_window'), and therefore the following calculation: bitnr = replay_esn->replay_window - (diff - pos); yields a negative result, but since bitnr is u32 we get a large unsigned quantity (in crash dump above: 0xffffff4b seen in ecx). This was supposed to be protected by xfrm_input()'s former call to: if (x->repl->check(x, skb, seq)) { However, the state's spinlock x->lock is *released* after '->check()' is performed, and gets re-acquired before '->advance()' - which gives a chance for a different core to update the xfrm state, e.g. by advancing 'replay_esn->seq' when it encounters more packets - leading to a 'diff > replay_window' situation when original core continues to xfrm_replay_advance_bmp(). An attempt to fix this issue was suggested in commit bcf66bf54aab ("xfrm: Perform a replay check after return from async codepaths"), by calling 'x->repl->recheck()' after lock is re-acquired, but fix applied only to asyncronous crypto algorithms. Augment the fix, by *always* calling 'recheck()' - irrespective if we're using async crypto. Fixes: 0ebea8ef3559 ("[IPSEC]: Move state lock into x->type->input") Signed-off-by: Shmulik Ladkani Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 37456d022cfa..61e6220ddd5a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -660,7 +660,7 @@ resume: /* only the first xfrm gets the encap type */ encap_type = 0; - if (async && x->repl->recheck(x, skb, seq)) { + if (x->repl->recheck(x, skb, seq)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } -- cgit v1.2.3 From 9f8550e4bd9d78a8436c2061ad2530215f875376 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Wed, 23 Dec 2020 17:00:46 +0200 Subject: xfrm: fix disable_xfrm sysctl when used on xfrm interfaces The disable_xfrm flag signals that xfrm should not be performed during routing towards a device before reaching device xmit. For xfrm interfaces this is usually desired as they perform the outbound policy lookup as part of their xmit using their if_id. Before this change enabling this flag on xfrm interfaces prevented them from xmitting as xfrm_lookup_with_ifid() would not perform a policy lookup in case the original dst had the DST_NOXFRM flag. This optimization is incorrect when the lookup is done by the xfrm interface xmit logic. Fix by performing policy lookup when invoked by xfrmi as if_id != 0. Similarly it's unlikely for the 'no policy exists on net' check to yield any performance benefits when invoked from xfrmi. Fixes: f203b76d7809 ("xfrm: Add virtual xfrm interfaces") Signed-off-by: Eyal Birger Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d622c2548d22..2f84136af48a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3078,8 +3078,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, xflo.flags = flags; /* To accelerate a bit... */ - if ((dst_orig->flags & DST_NOXFRM) || - !net->xfrm.policy_count[XFRM_POLICY_OUT]) + if (!if_id && ((dst_orig->flags & DST_NOXFRM) || + !net->xfrm.policy_count[XFRM_POLICY_OUT])) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); -- cgit v1.2.3 From da64ae2d35d3673233f0403b035d4c6acbf71965 Mon Sep 17 00:00:00 2001 From: Visa Hankala Date: Wed, 30 Dec 2020 16:15:53 +0000 Subject: xfrm: Fix wraparound in xfrm_policy_addr_delta() Use three-way comparison for address components to avoid integer wraparound in the result of xfrm_policy_addr_delta(). This ensures that the search trees are built and traversed correctly. Treat IPv4 and IPv6 similarly by returning 0 when prefixlen == 0. Prefix /0 has only one equivalence class. Fixes: 9cf545ebd591d ("xfrm: policy: store inexact policies in a tree ordered by destination address") Signed-off-by: Visa Hankala Acked-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 26 ++++++++++++------ tools/testing/selftests/net/xfrm_policy.sh | 43 ++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+), 8 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2f84136af48a..b74f28cabe24 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -793,15 +793,22 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { + u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: - if (sizeof(long) == 4 && prefixlen == 0) - return ntohl(a->a4) - ntohl(b->a4); - return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) - - (ntohl(b->a4) & ((~0UL << (32 - prefixlen)))); + if (prefixlen == 0) + return 0; + mask = ~0U << (32 - prefixlen); + ma = ntohl(a->a4) & mask; + mb = ntohl(b->a4) & mask; + if (ma < mb) + delta = -1; + else if (ma > mb) + delta = 1; + break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; @@ -812,10 +819,13 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a, return delta; } if (pbi) { - u32 mask = ~0u << (32 - pbi); - - delta = (ntohl(a->a6[pdw]) & mask) - - (ntohl(b->a6[pdw]) & mask); + mask = ~0U << (32 - pbi); + ma = ntohl(a->a6[pdw]) & mask; + mb = ntohl(b->a6[pdw]) & mask; + if (ma < mb) + delta = -1; + else if (ma > mb) + delta = 1; } break; default: diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 5922941e70c6..bdf450eaf60c 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -287,6 +287,47 @@ check_hthresh_repeat() return 0 } +# insert non-overlapping policies in a random order and check that +# all of them can be fetched using the traffic selectors. +check_random_order() +{ + local ns=$1 + local log=$2 + + for i in $(seq 100); do + ip -net $ns xfrm policy flush + for j in $(seq 0 16 255 | sort -R); do + ip -net $ns xfrm policy add dst $j.0.0.0/24 dir out priority 10 action allow + done + for j in $(seq 0 16 255); do + if ! ip -net $ns xfrm policy get dst $j.0.0.0/24 dir out > /dev/null; then + echo "FAIL: $log" 1>&2 + return 1 + fi + done + done + + for i in $(seq 100); do + ip -net $ns xfrm policy flush + for j in $(seq 0 16 255 | sort -R); do + local addr=$(printf "e000:0000:%02x00::/56" $j) + ip -net $ns xfrm policy add dst $addr dir out priority 10 action allow + done + for j in $(seq 0 16 255); do + local addr=$(printf "e000:0000:%02x00::/56" $j) + if ! ip -net $ns xfrm policy get dst $addr dir out > /dev/null; then + echo "FAIL: $log" 1>&2 + return 1 + fi + done + done + + ip -net $ns xfrm policy flush + + echo "PASS: $log" + return 0 +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" @@ -438,6 +479,8 @@ check_exceptions "exceptions and block policies after htresh change to normal" check_hthresh_repeat "policies with repeated htresh change" +check_random_order ns3 "policies inserted in random order" + for i in 1 2 3 4;do ip netns del ns$i;done exit $ret -- cgit v1.2.3