rxq contains a pointer to the device from where the redirect happened. Currently, the BPF program that was executed after a redirect via BPF_MAP_TYPE_DEVMAP* does not have it set.

This is particularly bad since accessing ingress_ifindex, e.g.

SEC("xdp") int prog(struct xdp_md *pkt) { return bpf_redirect_map(&dev_redirect_map, 0, 0); }

SEC("xdp/devmap") int prog_after_redirect(struct xdp_md *pkt) { bpf_printk("ifindex %i", pkt->ingress_ifindex); return XDP_PASS; }

depends on access to rxq, so a NULL pointer gets dereferenced:

<1>[ 574.475170] BUG: kernel NULL pointer dereference, address: 0000000000000000 <1>[ 574.475188] #PF: supervisor read access in kernel mode <1>[ 574.475194] #PF: error_code(0x0000) - not-present page <6>[ 574.475199] PGD 0 P4D 0 <4>[ 574.475207] Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI <4>[ 574.475217] CPU: 4 UID: 0 PID: 217 Comm: kworker/4:1 Not tainted 6.11.0-rc5-reduced-00859-g780801200300 #23 <4>[ 574.475226] Hardware name: Intel(R) Client Systems NUC13ANHi7/NUC13ANBi7, BIOS ANRPL357.0026.2023.0314.1458 03/14/2023 <4>[ 574.475231] Workqueue: mld mld_ifc_work <4>[ 574.475247] RIP: 0010:bpf_prog_5e13354d9cf5018a_prog_after_redirect+0x17/0x3c <4>[ 574.475257] Code: cc cc cc cc cc cc cc 80 00 00 00 cc cc cc cc cc cc cc cc f3 0f 1e fa 0f 1f 44 00 00 66 90 55 48 89 e5 f3 0f 1e fa 48 8b 57 20 <48> 8b 52 00 8b 92 e0 00 00 00 48 bf f8 a6 d5 c4 5d a0 ff ff be 0b <4>[ 574.475263] RSP: 0018:ffffa62440280c98 EFLAGS: 00010206 <4>[ 574.475269] RAX: ffffa62440280cd8 RBX: 0000000000000001 RCX: 0000000000000000 <4>[ 574.475274] RDX: 0000000000000000 RSI: ffffa62440549048 RDI: ffffa62440280ce0 <4>[ 574.475278] RBP: ffffa62440280c98 R08: 0000000000000002 R09: 0000000000000001 <4>[ 574.475281] R10: ffffa05dc8b98000 R11: ffffa05f577fca40 R12: ffffa05dcab24000 <4>[ 574.475285] R13: ffffa62440280ce0 R14: ffffa62440549048 R15: ffffa62440549000 <4>[ 574.475289] FS: 0000000000000000(0000) GS:ffffa05f4f700000(0000) knlGS:0000000000000000 <4>[ 574.475294] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4>[ 574.475298] CR2: 0000000000000000 CR3: 000000025522e000 CR4: 0000000000f50ef0 <4>[ 574.475303] PKRU: 55555554 <4>[ 574.475306] Call Trace: <4>[ 574.475313] <IRQ> <4>[ 574.475318] ? __die+0x23/0x70 <4>[ 574.475329] ? page_fault_oops+0x180/0x4c0 <4>[ 574.475339] ? skb_pp_cow_data+0x34c/0x490 <4>[ 574.475346] ? kmem_cache_free+0x257/0x280 <4>[ 574.475357] ? exc_page_fault+0x67/0x150 <4>[ 574.475368] ? asm_exc_page_fault+0x26/0x30 <4>[ 574.475381] ? bpf_prog_5e13354d9cf5018a_prog_after_redirect+0x17/0x3c <4>[ 574.475386] bq_xmit_all+0x158/0x420 <4>[ 574.475397] __dev_flush+0x30/0x90 <4>[ 574.475407] veth_poll+0x216/0x250 [veth] <4>[ 574.475421] __napi_poll+0x28/0x1c0 <4>[ 574.475430] net_rx_action+0x32d/0x3a0 <4>[ 574.475441] handle_softirqs+0xcb/0x2c0 <4>[ 574.475451] do_softirq+0x40/0x60 <4>[ 574.475458] </IRQ> <4>[ 574.475461] <TASK> <4>[ 574.475464] __local_bh_enable_ip+0x66/0x70 <4>[ 574.475471] __dev_queue_xmit+0x268/0xe40 <4>[ 574.475480] ? selinux_ip_postroute+0x213/0x420 <4>[ 574.475491] ? alloc_skb_with_frags+0x4a/0x1d0 <4>[ 574.475502] ip6_finish_output2+0x2be/0x640 <4>[ 574.475512] ? nf_hook_slow+0x42/0xf0 <4>[ 574.475521] ip6_finish_output+0x194/0x300 <4>[ 574.475529] ? __pfx_ip6_finish_output+0x10/0x10 <4>[ 574.475538] mld_sendpack+0x17c/0x240 <4>[ 574.475548] mld_ifc_work+0x192/0x410 <4>[ 574.475557] process_one_work+0x15d/0x380 <4>[ 574.475566] worker_thread+0x29d/0x3a0 <4>[ 574.475573] ? __pfx_worker_thread+0x10/0x10 <4>[ 574.475580] ? __pfx_worker_thread+0x10/0x10 <4>[ 574.475587] kthread+0xcd/0x100 <4>[ 574.475597] ? __pfx_kthread+0x10/0x10 <4>[ 574.475606] ret_from_fork+0x31/0x50 <4>[ 574.475615] ? __pfx_kthread+0x10/0x10 <4>[ 574.475623] ret_from_fork_asm+0x1a/0x30 <4>[ 574.475635] </TASK> <4>[ 574.475637] Modules linked in: veth br_netfilter bridge stp llc iwlmvm x86_pkg_temp_thermal iwlwifi efivarfs nvme nvme_core <4>[ 574.475662] CR2: 0000000000000000 <4>[ 574.475668] ---[ end trace 0000000000000000 ]---

Therefore, provide it to the program by setting rxq properly.

Fixes: cb261b594b41 ("bpf: Run devmap xdp_prog on flush instead of bulk enqueue") Reviewed-by: Toke Høiland-Jørgensen toke@redhat.com Signed-off-by: Florian Kauer florian.kauer@linutronix.de --- kernel/bpf/devmap.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 9e0e3b0a18e4..7878be18e9d2 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -333,9 +333,11 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key,

static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, struct xdp_frame **frames, int n, - struct net_device *dev) + struct net_device *tx_dev, + struct net_device *rx_dev) { - struct xdp_txq_info txq = { .dev = dev }; + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; struct xdp_buff xdp; int i, nframes = 0;

@@ -346,6 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog,

xdp_convert_frame_to_buff(xdpf, &xdp); xdp.txq = &txq; + xdp.rxq = &rxq;

act = bpf_prog_run_xdp(xdp_prog, &xdp); switch (act) { @@ -360,7 +363,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: - trace_xdp_exception(dev, xdp_prog, act); + trace_xdp_exception(tx_dev, xdp_prog, act); fallthrough; case XDP_DROP: xdp_return_frame_rx_napi(xdpf); @@ -388,7 +391,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) }

if (bq->xdp_prog) { - to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev); + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); if (!to_send) goto out; }

The current xdp_devmap_attach test attaches a program that redirects to another program via devmap.

It is, however, never executed, so do that to catch any bugs that might occur during execution.

Also, execute the same for a veth pair so that we also cover the non-generic path.

Warning: Running this without the bugfix in this series will likely crash your system.

Signed-off-by: Florian Kauer florian.kauer@linutronix.de --- .../selftests/bpf/prog_tests/xdp_devmap_attach.c | 114 +++++++++++++++++++-- 1 file changed, 108 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index ce6812558287..b4f6718cf7eb 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 +#include <arpa/inet.h> #include <uapi/linux/bpf.h> #include <linux/if_link.h> +#include <network_helpers.h> +#include <net/if.h> #include <test_progs.h>

#include "test_xdp_devmap_helpers.skel.h" @@ -17,7 +20,7 @@ static void test_xdp_with_devmap_helpers(void) .ifindex = IFINDEX_LO, }; __u32 len = sizeof(info); - int err, dm_fd, map_fd; + int err, dm_fd, dm_fd_redir, map_fd; __u32 idx = 0;

@@ -25,14 +28,11 @@ static void test_xdp_with_devmap_helpers(void) if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) return;

- dm_fd = bpf_program__fd(skel->progs.xdp_redir_prog); - err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(IFINDEX_LO, dm_fd_redir, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_OK(err, "Generic attach of program with 8-byte devmap")) goto out_close;

- err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); - ASSERT_OK(err, "XDP program detach"); - dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); map_fd = bpf_map__fd(skel->maps.dm_ports); err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); @@ -47,6 +47,23 @@ static void test_xdp_with_devmap_helpers(void) ASSERT_OK(err, "Read devmap entry"); ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id");

+ /* send a packet to trigger any potential bugs in there */ + char data[10] = {}; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(IFINDEX_LO, XDP_FLAGS_SKB_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + /* can not attach BPF_XDP_DEVMAP program to a device */ err = bpf_xdp_attach(IFINDEX_LO, dm_fd, XDP_FLAGS_SKB_MODE, NULL); if (!ASSERT_NEQ(err, 0, "Attach of BPF_XDP_DEVMAP program")) @@ -124,6 +141,88 @@ static void test_xdp_with_devmap_frags_helpers(void) test_xdp_with_devmap_frags_helpers__destroy(skel); }

+static void test_xdp_with_devmap_helpers_veth(void) +{ + struct test_xdp_with_devmap_helpers *skel = NULL; + struct bpf_prog_info info = {}; + struct bpf_devmap_val val = {}; + struct nstoken *nstoken = NULL; + __u32 len = sizeof(info); + int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; + __u32 idx = 0; + + SYS(out_close, "ip netns add testns"); + nstoken = open_netns("testns"); + if (!ASSERT_OK_PTR(nstoken, "setns")) + goto out_close; + + SYS(out_close, "ip link add veth_src type veth peer name veth_dst"); + SYS(out_close, "ip link set dev veth_src up"); + SYS(out_close, "ip link set dev veth_dst up"); + + val.ifindex = if_nametoindex("veth_src"); + ifindex_dst = if_nametoindex("veth_dst"); + if (!ASSERT_NEQ(val.ifindex, 0, "val.ifindex") || + !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) + goto out_close; + + skel = test_xdp_with_devmap_helpers__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_xdp_with_devmap_helpers__open_and_load")) + goto out_close; + + dm_fd_redir = bpf_program__fd(skel->progs.xdp_redir_prog); + err = bpf_xdp_attach(val.ifindex, dm_fd_redir, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of program with 8-byte devmap")) + goto out_close; + + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_dm); + map_fd = bpf_map__fd(skel->maps.dm_ports); + err = bpf_prog_get_info_by_fd(dm_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + goto out_close; + + val.bpf_prog.fd = dm_fd; + err = bpf_map_update_elem(map_fd, &idx, &val, 0); + ASSERT_OK(err, "Add program to devmap entry"); + + err = bpf_map_lookup_elem(map_fd, &idx, &val); + ASSERT_OK(err, "Read devmap entry"); + ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to devmap entry prog_id"); + + /* attach dummy to other side to enable reception */ + dm_fd = bpf_program__fd(skel->progs.xdp_dummy_prog); + err = bpf_xdp_attach(ifindex_dst, dm_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "Attach of dummy XDP")) + goto out_close; + + /* send a packet to trigger any potential bugs in there */ + char data[10] = {}; + DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &data, + .data_size_in = 10, + .flags = BPF_F_TEST_XDP_LIVE_FRAMES, + .repeat = 1, + ); + err = bpf_prog_test_run_opts(dm_fd_redir, &opts); + ASSERT_OK(err, "XDP test run"); + + /* wait for the packets to be flushed */ + kern_sync_rcu(); + + err = bpf_xdp_detach(val.ifindex, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + + err = bpf_xdp_detach(ifindex_dst, XDP_FLAGS_DRV_MODE, NULL); + ASSERT_OK(err, "XDP program detach"); + +out_close: + if (nstoken) + close_netns(nstoken); + SYS_NOFAIL("ip netns del testns"); + + test_xdp_with_devmap_helpers__destroy(skel); +} + void serial_test_xdp_devmap_attach(void) { if (test__start_subtest("DEVMAP with programs in entries")) @@ -134,4 +233,7 @@ void serial_test_xdp_devmap_attach(void)

if (test__start_subtest("Verifier check of DEVMAP programs")) test_neg_xdp_devmap_helpers(); + + if (test__start_subtest("DEVMAP with programs in entries on veth")) + test_xdp_with_devmap_helpers_veth(); }