[PATCH AUTOSEL 5.17 019/149] selftests, xsk: Fix bpf_res cleanup test

[PATCH AUTOSEL 5.17 019/149] selftests, xsk: Fix bpf_res cleanup test

[Sasha Levin]

From: Magnus Karlsson <magnus.karlsson@intel.com>

[ Upstream commit 3b22523bca02b0d5618c08b93d8fd1fb578e1cc3 ]

After commit 710ad98c363a ("veth: Do not record rx queue hint in veth_xmit"),
veth no longer receives traffic on the same queue as it was sent on. This
breaks the bpf_res test for the AF_XDP selftests as the socket tied to
queue 1 will not receive traffic anymore.

Modify the test so that two sockets are tied to queue id 0 using a shared
umem instead. When killing the first socket enter the second socket into
the xskmap so that traffic will flow to it. This will still test that the
resources are not cleaned up until after the second socket dies, without
having to rely on veth supporting rx_queue hints.

Reported-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220125082945.26179-1-magnus.karlsson@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/xdpxceiver.c | 80 +++++++++++++++---------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 +-
 2 files changed, 50 insertions(+), 32 deletions(-)

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 0a5d23da486d..4686897181b6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -266,22 +266,24 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 }
 
 static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
-				struct ifobject *ifobject, u32 qid)
+				struct ifobject *ifobject, bool shared)
 {
-	struct xsk_socket_config cfg;
+	struct xsk_socket_config cfg = {};
 	struct xsk_ring_cons *rxr;
 	struct xsk_ring_prod *txr;
 
 	xsk->umem = umem;
 	cfg.rx_size = xsk->rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
-	cfg.libbpf_flags = 0;
+	cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
 	cfg.xdp_flags = ifobject->xdp_flags;
 	cfg.bind_flags = ifobject->bind_flags;
+	if (shared)
+		cfg.bind_flags |= XDP_SHARED_UMEM;
 
 	txr = ifobject->tx_on ? &xsk->tx : NULL;
 	rxr = ifobject->rx_on ? &xsk->rx : NULL;
-	return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg);
+	return xsk_socket__create(&xsk->xsk, ifobject->ifname, 0, umem->umem, rxr, txr, &cfg);
 }
 
 static struct option long_options[] = {
@@ -387,7 +389,6 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	for (i = 0; i < MAX_INTERFACES; i++) {
 		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
 
-		ifobj->umem = &ifobj->umem_arr[0];
 		ifobj->xsk = &ifobj->xsk_arr[0];
 		ifobj->use_poll = false;
 		ifobj->pacing_on = true;
@@ -401,11 +402,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 			ifobj->tx_on = false;
 		}
 
+		memset(ifobj->umem, 0, sizeof(*ifobj->umem));
+		ifobj->umem->num_frames = DEFAULT_UMEM_BUFFERS;
+		ifobj->umem->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+
 		for (j = 0; j < MAX_SOCKETS; j++) {
-			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
-			ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS;
-			ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		}
 	}
@@ -947,7 +949,10 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 {
+	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+	int ret, ifindex;
+	void *bufs;
 	u32 i;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
@@ -955,23 +960,20 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	if (ifobject->umem->unaligned_mode)
 		mmap_flags |= MAP_HUGETLB;
 
-	for (i = 0; i < test->nb_sockets; i++) {
-		u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
-		u32 ctr = 0;
-		void *bufs;
-		int ret;
+	bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	if (bufs == MAP_FAILED)
+		exit_with_error(errno);
 
-		bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
-		if (bufs == MAP_FAILED)
-			exit_with_error(errno);
+	ret = xsk_configure_umem(ifobject->umem, bufs, umem_sz);
+	if (ret)
+		exit_with_error(-ret);
 
-		ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz);
-		if (ret)
-			exit_with_error(-ret);
+	for (i = 0; i < test->nb_sockets; i++) {
+		u32 ctr = 0;
 
 		while (ctr++ < SOCK_RECONF_CTR) {
-			ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i],
-						   ifobject, i);
+			ret = xsk_configure_socket(&ifobject->xsk_arr[i], ifobject->umem,
+						   ifobject, !!i);
 			if (!ret)
 				break;
 
@@ -982,8 +984,22 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 		}
 	}
 
-	ifobject->umem = &ifobject->umem_arr[0];
 	ifobject->xsk = &ifobject->xsk_arr[0];
+
+	if (!ifobject->rx_on)
+		return;
+
+	ifindex = if_nametoindex(ifobject->ifname);
+	if (!ifindex)
+		exit_with_error(errno);
+
+	ret = xsk_setup_xdp_prog(ifindex, &ifobject->xsk_map_fd);
+	if (ret)
+		exit_with_error(-ret);
+
+	ret = xsk_socket__update_xskmap(ifobject->xsk->xsk, ifobject->xsk_map_fd);
+	if (ret)
+		exit_with_error(-ret);
 }
 
 static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
@@ -1139,14 +1155,16 @@ static void testapp_bidi(struct test_spec *test)
 
 static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
 {
+	int ret;
+
 	xsk_socket__delete(ifobj_tx->xsk->xsk);
-	xsk_umem__delete(ifobj_tx->umem->umem);
 	xsk_socket__delete(ifobj_rx->xsk->xsk);
-	xsk_umem__delete(ifobj_rx->umem->umem);
-	ifobj_tx->umem = &ifobj_tx->umem_arr[1];
 	ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
-	ifobj_rx->umem = &ifobj_rx->umem_arr[1];
 	ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
+
+	ret = xsk_socket__update_xskmap(ifobj_rx->xsk->xsk, ifobj_rx->xsk_map_fd);
+	if (ret)
+		exit_with_error(-ret);
 }
 
 static void testapp_bpf_res(struct test_spec *test)
@@ -1405,13 +1423,13 @@ static struct ifobject *ifobject_create(void)
 	if (!ifobj->xsk_arr)
 		goto out_xsk_arr;
 
-	ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr));
-	if (!ifobj->umem_arr)
-		goto out_umem_arr;
+	ifobj->umem = calloc(1, sizeof(*ifobj->umem));
+	if (!ifobj->umem)
+		goto out_umem;
 
 	return ifobj;
 
-out_umem_arr:
+out_umem:
 	free(ifobj->xsk_arr);
 out_xsk_arr:
 	free(ifobj);
@@ -1420,7 +1438,7 @@ static struct ifobject *ifobject_create(void)
 
 static void ifobject_delete(struct ifobject *ifobj)
 {
-	free(ifobj->umem_arr);
+	free(ifobj->umem);
 	free(ifobj->xsk_arr);
 	free(ifobj);
 }
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 2f705f44b748..62a3e6388632 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -125,10 +125,10 @@ struct ifobject {
 	struct xsk_socket_info *xsk;
 	struct xsk_socket_info *xsk_arr;
 	struct xsk_umem_info *umem;
-	struct xsk_umem_info *umem_arr;
 	thread_func_t func_ptr;
 	struct pkt_stream *pkt_stream;
 	int ns_fd;
+	int xsk_map_fd;
 	u32 dst_ip;
 	u32 src_ip;
 	u32 xdp_flags;
-- 
2.34.1

[PATCH AUTOSEL 5.17 034/149] bpf: Make dst_port field in struct bpf_sock 16-bit wide

[Sasha Levin]

From: Jakub Sitnicki <jakub@cloudflare.com>

[ Upstream commit 4421a582718ab81608d8486734c18083b822390d ]

Menglong Dong reports that the documentation for the dst_port field in
struct bpf_sock is inaccurate and confusing. From the BPF program PoV, the
field is a zero-padded 16-bit integer in network byte order. The value
appears to the BPF user as if laid out in memory as so:

  offsetof(struct bpf_sock, dst_port) + 0  <port MSB>
                                      + 8  <port LSB>
                                      +16  0x00
                                      +24  0x00

32-, 16-, and 8-bit wide loads from the field are all allowed, but only if
the offset into the field is 0.

32-bit wide loads from dst_port are especially confusing. The loaded value,
after converting to host byte order with bpf_ntohl(dst_port), contains the
port number in the upper 16-bits.

Remove the confusion by splitting the field into two 16-bit fields. For
backward compatibility, allow 32-bit wide loads from offsetof(struct
bpf_sock, dst_port).

While at it, allow loads 8-bit loads at offset [0] and [1] from dst_port.

Reported-by: Menglong Dong <imagedong@tencent.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/r/20220130115518.213259-2-jakub@cloudflare.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/uapi/linux/bpf.h |  3 ++-
 net/core/filter.c        | 10 +++++++++-
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b0383d371b9a..1275b08e9deb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5500,7 +5500,8 @@ struct bpf_sock {
 	__u32 src_ip4;
 	__u32 src_ip6[4];
 	__u32 src_port;		/* host byte order */
-	__u32 dst_port;		/* network byte order */
+	__be16 dst_port;	/* network byte order */
+	__u16 :16;		/* zero padding */
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
diff --git a/net/core/filter.c b/net/core/filter.c
index 9eb785842258..82fcb7533663 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8033,6 +8033,7 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 			      struct bpf_insn_access_aux *info)
 {
 	const int size_default = sizeof(__u32);
+	int field_size;
 
 	if (off < 0 || off >= sizeof(struct bpf_sock))
 		return false;
@@ -8044,7 +8045,6 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 	case offsetof(struct bpf_sock, family):
 	case offsetof(struct bpf_sock, type):
 	case offsetof(struct bpf_sock, protocol):
-	case offsetof(struct bpf_sock, dst_port):
 	case offsetof(struct bpf_sock, src_port):
 	case offsetof(struct bpf_sock, rx_queue_mapping):
 	case bpf_ctx_range(struct bpf_sock, src_ip4):
@@ -8053,6 +8053,14 @@ bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 	case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]):
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
+	case bpf_ctx_range(struct bpf_sock, dst_port):
+		field_size = size == size_default ?
+			size_default : sizeof_field(struct bpf_sock, dst_port);
+		bpf_ctx_record_field_size(info, field_size);
+		return bpf_ctx_narrow_access_ok(off, size, field_size);
+	case offsetofend(struct bpf_sock, dst_port) ...
+	     offsetof(struct bpf_sock, dst_ip4) - 1:
+		return false;
 	}
 
 	return size == size_default;
-- 
2.34.1

[PATCH AUTOSEL 5.17 043/149] libbpf: Fix build issue with llvm-readelf

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit 0908a66ad1124c1634c33847ac662106f7f2c198 ]

There are cases where clang compiler is packaged in a way
readelf is a symbolic link to llvm-readelf. In such cases,
llvm-readelf will be used instead of default binutils readelf,
and the following error will appear during libbpf build:

  Warning: Num of global symbols in
   /home/yhs/work/bpf-next/tools/testing/selftests/bpf/tools/build/libbpf/sharedobjs/libbpf-in.o (367)
   does NOT match with num of versioned symbols in
   /home/yhs/work/bpf-next/tools/testing/selftests/bpf/tools/build/libbpf/libbpf.so libbpf.map (383).
   Please make sure all LIBBPF_API symbols are versioned in libbpf.map.
  --- /home/yhs/work/bpf-next/tools/testing/selftests/bpf/tools/build/libbpf/libbpf_global_syms.tmp ...
  +++ /home/yhs/work/bpf-next/tools/testing/selftests/bpf/tools/build/libbpf/libbpf_versioned_syms.tmp ...
  @@ -324,6 +324,22 @@
   btf__str_by_offset
   btf__type_by_id
   btf__type_cnt
  +LIBBPF_0.0.1
  +LIBBPF_0.0.2
  +LIBBPF_0.0.3
  +LIBBPF_0.0.4
  +LIBBPF_0.0.5
  +LIBBPF_0.0.6
  +LIBBPF_0.0.7
  +LIBBPF_0.0.8
  +LIBBPF_0.0.9
  +LIBBPF_0.1.0
  +LIBBPF_0.2.0
  +LIBBPF_0.3.0
  +LIBBPF_0.4.0
  +LIBBPF_0.5.0
  +LIBBPF_0.6.0
  +LIBBPF_0.7.0
   libbpf_attach_type_by_name
   libbpf_find_kernel_btf
   libbpf_find_vmlinux_btf_id
  make[2]: *** [Makefile:184: check_abi] Error 1
  make[1]: *** [Makefile:140: all] Error 2

The above failure is due to different printouts for some ABS
versioned symbols. For example, with the same libbpf.so,
  $ /bin/readelf --dyn-syms --wide tools/lib/bpf/libbpf.so | grep "LIBBPF" | grep ABS
     134: 0000000000000000     0 OBJECT  GLOBAL DEFAULT  ABS LIBBPF_0.5.0
     202: 0000000000000000     0 OBJECT  GLOBAL DEFAULT  ABS LIBBPF_0.6.0
     ...
  $ /opt/llvm/bin/readelf --dyn-syms --wide tools/lib/bpf/libbpf.so | grep "LIBBPF" | grep ABS
     134: 0000000000000000     0 OBJECT  GLOBAL DEFAULT   ABS LIBBPF_0.5.0@@LIBBPF_0.5.0
     202: 0000000000000000     0 OBJECT  GLOBAL DEFAULT   ABS LIBBPF_0.6.0@@LIBBPF_0.6.0
     ...
The binutils readelf doesn't print out the symbol LIBBPF_* version and llvm-readelf does.
Such a difference caused libbpf build failure with llvm-readelf.

The proposed fix filters out all ABS symbols as they are not part of the comparison.
This works for both binutils readelf and llvm-readelf.

Reported-by: Delyan Kratunov <delyank@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220204214355.502108-1-yhs@fb.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index f947b61b2107..b8b37fe76006 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -131,7 +131,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \
 			   sort -u | wc -l)
 VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \
 			      sed 's/\[.*\]//' | \
-			      awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \
+			      awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}' | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
 CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
@@ -194,7 +194,7 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 		    sort -u > $(OUTPUT)libbpf_global_syms.tmp;		 \
 		readelf --dyn-syms --wide $(OUTPUT)libbpf.so |		 \
 		    sed 's/\[.*\]//' |					 \
-		    awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'|  \
+		    awk '/GLOBAL/ && /DEFAULT/ && !/UND|ABS/ {print $$NF}'|  \
 		    grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 |		 \
 		    sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; 	 \
 		diff -u $(OUTPUT)libbpf_global_syms.tmp			 \
-- 
2.34.1

[PATCH AUTOSEL 5.17 060/149] libbpf: Fix accessing syscall arguments on powerpc

[Sasha Levin]

From: Ilya Leoshkevich <iii@linux.ibm.com>

[ Upstream commit f07f1503469b11b739892d50c836992ffbe026ee ]

powerpc does not select ARCH_HAS_SYSCALL_WRAPPER, so its syscall
handlers take "unpacked" syscall arguments. Indicate this to libbpf
using PT_REGS_SYSCALL_REGS macro.

Reported-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Link: https://lore.kernel.org/bpf/20220209021745.2215452-5-iii@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/bpf_tracing.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index 90f56b0f585f..d40b87c0e4b9 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -178,6 +178,8 @@
 #define __PT_RC_REG gpr[3]
 #define __PT_SP_REG sp
 #define __PT_IP_REG nip
+/* powerpc does not select ARCH_HAS_SYSCALL_WRAPPER. */
+#define PT_REGS_SYSCALL_REGS(ctx) ctx
 
 #elif defined(bpf_target_sparc)
 
-- 
2.34.1

[PATCH AUTOSEL 5.17 061/149] libbpf: Fix accessing the first syscall argument on arm64

[Sasha Levin]

From: Ilya Leoshkevich <iii@linux.ibm.com>

[ Upstream commit fbca4a2f649730b67488a8b36140ce4d2cf13c63 ]

On arm64, the first syscall argument should be accessed via orig_x0
(see arch/arm64/include/asm/syscall.h). Currently regs[0] is used
instead, leading to bpf_syscall_macro test failure.

orig_x0 cannot be added to struct user_pt_regs, since its layout is a
part of the ABI. Therefore provide access to it only through
PT_REGS_PARM1_CORE_SYSCALL() by using a struct pt_regs flavor.

Reported-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220209021745.2215452-10-iii@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/bpf_tracing.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index d40b87c0e4b9..ad62c17919cf 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -140,6 +140,10 @@
 
 #elif defined(bpf_target_arm64)
 
+struct pt_regs___arm64 {
+	unsigned long orig_x0;
+};
+
 /* arm64 provides struct user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const struct user_pt_regs *)(x))
 #define __PT_PARM1_REG regs[0]
@@ -152,6 +156,8 @@
 #define __PT_RC_REG regs[0]
 #define __PT_SP_REG sp
 #define __PT_IP_REG pc
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___arm64 *)(x), orig_x0)
 
 #elif defined(bpf_target_mips)
 
-- 
2.34.1

[PATCH AUTOSEL 5.17 062/149] libbpf: Fix accessing the first syscall argument on s390

[Sasha Levin]

From: Ilya Leoshkevich <iii@linux.ibm.com>

[ Upstream commit 1f22a6f9f9a0f50218a11a0554709fd34a821fa3 ]

On s390, the first syscall argument should be accessed via orig_gpr2
(see arch/s390/include/asm/syscall.h). Currently gpr[2] is used
instead, leading to bpf_syscall_macro test failure.

orig_gpr2 cannot be added to user_pt_regs, since its layout is a part
of the ABI. Therefore provide access to it only through
PT_REGS_PARM1_CORE_SYSCALL() by using a struct pt_regs flavor.

Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220209021745.2215452-11-iii@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/bpf_tracing.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index ad62c17919cf..92bf90e716ea 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -112,6 +112,10 @@
 
 #elif defined(bpf_target_s390)
 
+struct pt_regs___s390 {
+	unsigned long orig_gpr2;
+};
+
 /* s390 provides user_pt_regs instead of struct pt_regs to userspace */
 #define __PT_REGS_CAST(x) ((const user_pt_regs *)(x))
 #define __PT_PARM1_REG gprs[2]
@@ -124,6 +128,8 @@
 #define __PT_RC_REG gprs[2]
 #define __PT_SP_REG gprs[15]
 #define __PT_IP_REG psw.addr
+#define PT_REGS_PARM1_SYSCALL(x) ({ _Pragma("GCC error \"use PT_REGS_PARM1_CORE_SYSCALL() instead\""); 0l; })
+#define PT_REGS_PARM1_CORE_SYSCALL(x) BPF_CORE_READ((const struct pt_regs___s390 *)(x), orig_gpr2)
 
 #elif defined(bpf_target_arm)
 
-- 
2.34.1

[PATCH AUTOSEL 5.17 114/149] tuntap: add sanity checks about msg_controllen in sendmsg

[Sasha Levin]

From: Harold Huang <baymaxhuang@gmail.com>

[ Upstream commit 74a335a07a17d131b9263bfdbdcb5e40673ca9ca ]

In patch [1], tun_msg_ctl was added to allow pass batched xdp buffers to
tun_sendmsg. Although we donot use msg_controllen in this path, we should
check msg_controllen to make sure the caller pass a valid msg_ctl.

[1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fe8dd45bb7556246c6b76277b1ba4296c91c2505

Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Harold Huang <baymaxhuang@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/r/20220303022441.383865-1-baymaxhuang@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/tap.c   | 3 ++-
 drivers/net/tun.c   | 3 ++-
 drivers/vhost/net.c | 1 +
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 8e3a28ba6b28..ba2ef5437e16 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1198,7 +1198,8 @@ static int tap_sendmsg(struct socket *sock, struct msghdr *m,
 	struct xdp_buff *xdp;
 	int i;
 
-	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+	if (m->msg_controllen == sizeof(struct tun_msg_ctl) &&
+	    ctl && ctl->type == TUN_MSG_PTR) {
 		for (i = 0; i < ctl->num; i++) {
 			xdp = &((struct xdp_buff *)ctl->ptr)[i];
 			tap_get_user_xdp(q, xdp);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index fed85447701a..de999e0fedbc 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2489,7 +2489,8 @@ static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 	if (!tun)
 		return -EBADFD;
 
-	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+	if (m->msg_controllen == sizeof(struct tun_msg_ctl) &&
+	    ctl && ctl->type == TUN_MSG_PTR) {
 		struct tun_page tpage;
 		int n = ctl->num;
 		int flush = 0;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 28ef323882fb..792ab5f23647 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -473,6 +473,7 @@ static void vhost_tx_batch(struct vhost_net *net,
 		goto signal_used;
 
 	msghdr->msg_control = &ctl;
+	msghdr->msg_controllen = sizeof(ctl);
 	err = sock->ops->sendmsg(sock, msghdr, 0);
 	if (unlikely(err < 0)) {
 		vq_err(&nvq->vq, "Fail to batch sending packets\n");
-- 
2.34.1

[PATCH AUTOSEL 5.17 123/149] powerpc/64e: Tie PPC_BOOK3E_64 to PPC_FSL_BOOK3E

[Sasha Levin]

From: Michael Ellerman <mpe@ellerman.id.au>

[ Upstream commit 1a76e520ee1831a81dabf8a9a58c6453f700026e ]

Since the IBM A2 CPU support was removed, see commit
fb5a515704d7 ("powerpc: Remove platforms/wsp and associated pieces"),
the only 64-bit Book3E CPUs we support are Freescale (NXP) ones.

However our Kconfig still allows configurating a kernel that has 64-bit
Book3E support, but no Freescale CPU support enabled. Such a kernel
would never boot, it doesn't know about any CPUs.

It also causes build errors, as reported by lkp, because
PPC_BARRIER_NOSPEC is not enabled in such a configuration:

  powerpc64-linux-ld: arch/powerpc/net/bpf_jit_comp64.o:(.toc+0x0):
  undefined reference to `powerpc_security_features'

To fix this, force PPC_FSL_BOOK3E to be selected whenever we are
building a 64-bit Book3E kernel.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Suggested-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220304061222.2478720-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/platforms/Kconfig.cputype | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 87bc1929ee5a..e2e1fec91c6e 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -107,6 +107,7 @@ config PPC_BOOK3S_64
 
 config PPC_BOOK3E_64
 	bool "Embedded processors"
+	select PPC_FSL_BOOK3E
 	select PPC_FPU # Make it a choice ?
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
@@ -295,7 +296,7 @@ config FSL_BOOKE
 config PPC_FSL_BOOK3E
 	bool
 	select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64
-	select FSL_EMB_PERFMON
+	imply FSL_EMB_PERFMON
 	select PPC_SMP_MUXED_IPI
 	select PPC_DOORBELL
 	select PPC_KUEP
-- 
2.34.1