--- /dev/null
+From 058ec4a7d9cf77238c73ad9f1e1a3ed9a29afcab Mon Sep 17 00:00:00 2001
+From: Jakub Sitnicki <jakub@cloudflare.com>
+Date: Sat, 19 Mar 2022 19:33:54 +0100
+Subject: bpf: Treat bpf_sk_lookup remote_port as a 2-byte field
+
+From: Jakub Sitnicki <jakub@cloudflare.com>
+
+commit 058ec4a7d9cf77238c73ad9f1e1a3ed9a29afcab upstream.
+
+In commit 9a69e2b385f4 ("bpf: Make remote_port field in struct
+bpf_sk_lookup 16-bit wide") the remote_port field has been split up and
+re-declared from u32 to be16.
+
+However, the accompanying changes to the context access converter have not
+been well thought through when it comes big-endian platforms.
+
+Today 2-byte wide loads from offsetof(struct bpf_sk_lookup, remote_port)
+are handled as narrow loads from a 4-byte wide field.
+
+This by itself is not enough to create a problem, but when we combine
+
+ 1. 32-bit wide access to ->remote_port backed by a 16-wide wide load, with
+ 2. inherent difference between litte- and big-endian in how narrow loads
+ need have to be handled (see bpf_ctx_narrow_access_offset),
+
+we get inconsistent results for a 2-byte loads from &ctx->remote_port on LE
+and BE architectures. This in turn makes BPF C code for the common case of
+2-byte load from ctx->remote_port not portable.
+
+To rectify it, inform the context access converter that remote_port is
+2-byte wide field, and only 1-byte loads need to be treated as narrow
+loads.
+
+At the same time, we special-case the 4-byte load from &ctx->remote_port to
+continue handling it the same way as do today, in order to keep the
+existing BPF programs working.
+
+Fixes: 9a69e2b385f4 ("bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide")
+Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+Acked-by: Martin KaFai Lau <kafai@fb.com>
+Link: https://lore.kernel.org/bpf/20220319183356.233666-2-jakub@cloudflare.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ net/core/filter.c | 20 ++++++++++++++++++--
+ 1 file changed, 18 insertions(+), 2 deletions(-)
+
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -10621,13 +10621,24 @@ static bool sk_lookup_is_valid_access(in
+ case bpf_ctx_range(struct bpf_sk_lookup, local_ip4):
+ case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]):
+ case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]):
+- case offsetof(struct bpf_sk_lookup, remote_port) ...
+- offsetof(struct bpf_sk_lookup, local_ip4) - 1:
+ case bpf_ctx_range(struct bpf_sk_lookup, local_port):
+ case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex):
+ bpf_ctx_record_field_size(info, sizeof(__u32));
+ return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32));
+
++ case bpf_ctx_range(struct bpf_sk_lookup, remote_port):
++ /* Allow 4-byte access to 2-byte field for backward compatibility */
++ if (size == sizeof(__u32))
++ return true;
++ bpf_ctx_record_field_size(info, sizeof(__be16));
++ return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16));
++
++ case offsetofend(struct bpf_sk_lookup, remote_port) ...
++ offsetof(struct bpf_sk_lookup, local_ip4) - 1:
++ /* Allow access to zero padding for backward compatibility */
++ bpf_ctx_record_field_size(info, sizeof(__u16));
++ return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16));
++
+ default:
+ return false;
+ }
+@@ -10709,6 +10720,11 @@ static u32 sk_lookup_convert_ctx_access(
+ sport, 2, target_size));
+ break;
+
++ case offsetofend(struct bpf_sk_lookup, remote_port):
++ *target_size = 2;
++ *insn++ = BPF_MOV32_IMM(si->dst_reg, 0);
++ break;
++
+ case offsetof(struct bpf_sk_lookup, local_port):
+ *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg,
+ bpf_target_off(struct bpf_sk_lookup_kern,
--- /dev/null
+From 3c69611b8926f8e74fcf76bd97ae0e5dafbeb26a Mon Sep 17 00:00:00 2001
+From: Jakub Sitnicki <jakub@cloudflare.com>
+Date: Sat, 19 Mar 2022 19:33:55 +0100
+Subject: selftests/bpf: Fix u8 narrow load checks for bpf_sk_lookup remote_port
+
+From: Jakub Sitnicki <jakub@cloudflare.com>
+
+commit 3c69611b8926f8e74fcf76bd97ae0e5dafbeb26a upstream.
+
+In commit 9a69e2b385f4 ("bpf: Make remote_port field in struct
+bpf_sk_lookup 16-bit wide") ->remote_port field changed from __u32 to
+__be16.
+
+However, narrow load tests which exercise 1-byte sized loads from
+offsetof(struct bpf_sk_lookup, remote_port) were not adopted to reflect the
+change.
+
+As a result, on little-endian we continue testing loads from addresses:
+
+ - (__u8 *)&ctx->remote_port + 3
+ - (__u8 *)&ctx->remote_port + 4
+
+which map to the zero padding following the remote_port field, and don't
+break the tests because there is no observable change.
+
+While on big-endian, we observe breakage because tests expect to see zeros
+for values loaded from:
+
+ - (__u8 *)&ctx->remote_port - 1
+ - (__u8 *)&ctx->remote_port - 2
+
+Above addresses map to ->remote_ip6 field, which precedes ->remote_port,
+and are populated during the bpf_sk_lookup IPv6 tests.
+
+Unsurprisingly, on s390x we observe:
+
+ #136/38 sk_lookup/narrow access to ctx v4:OK
+ #136/39 sk_lookup/narrow access to ctx v6:FAIL
+
+Fix it by removing the checks for 1-byte loads from offsets outside of the
+->remote_port field.
+
+Fixes: 9a69e2b385f4 ("bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide")
+Suggested-by: Ilya Leoshkevich <iii@linux.ibm.com>
+Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
+Signed-off-by: Alexei Starovoitov <ast@kernel.org>
+Acked-by: Martin KaFai Lau <kafai@fb.com>
+Link: https://lore.kernel.org/bpf/20220319183356.233666-3-jakub@cloudflare.com
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ tools/testing/selftests/bpf/progs/test_sk_lookup.c | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
++++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+@@ -412,8 +412,7 @@ int ctx_narrow_access(struct bpf_sk_look
+
+ /* Narrow loads from remote_port field. Expect SRC_PORT. */
+ if (LSB(ctx->remote_port, 0) != ((SRC_PORT >> 0) & 0xff) ||
+- LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff) ||
+- LSB(ctx->remote_port, 2) != 0 || LSB(ctx->remote_port, 3) != 0)
++ LSB(ctx->remote_port, 1) != ((SRC_PORT >> 8) & 0xff))
+ return SK_DROP;
+ if (LSW(ctx->remote_port, 0) != SRC_PORT)
+ return SK_DROP;