[PATCH AUTOSEL 4.19 06/48] bpf: only adjust gso_size on bytestream protocols

[PATCH AUTOSEL 4.19 06/48] bpf: only adjust gso_size on bytestream protocols

[Sasha Levin]

From: Willem de Bruijn <willemb@google.com>

[ Upstream commit b90efd2258749e04e1b3f71ef0d716f2ac2337e0 ]

bpf_skb_change_proto and bpf_skb_adjust_room change skb header length.
For GSO packets they adjust gso_size to maintain the same MTU.

The gso size can only be safely adjusted on bytestream protocols.
Commit d02f51cbcf12 ("bpf: fix bpf_skb_adjust_net/bpf_skb_proto_xlat
to deal with gso sctp skbs") excluded SKB_GSO_SCTP.

Since then type SKB_GSO_UDP_L4 has been added, whose contents are one
gso_size unit per datagram. Also exclude these.

Move from a blacklist to a whitelist check to future proof against
additional such new GSO types, e.g., for fraglist based GRO.

Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/skbuff.h |  6 ++++++
 net/core/filter.c      | 12 ++++--------
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a404d475acee..3b0a25bb7c6f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4086,6 +4086,12 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP;
 }
 
+static inline bool skb_is_gso_tcp(const struct sk_buff *skb)
+{
+	return skb_is_gso(skb) &&
+	       skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6);
+}
+
 static inline void skb_gso_reset(struct sk_buff *skb)
 {
 	skb_shinfo(skb)->gso_size = 0;
diff --git a/net/core/filter.c b/net/core/filter.c
index fb0080e84bd4..cb792b344b5e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2614,8 +2614,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_cow(skb, len_diff);
@@ -2656,8 +2655,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
 	u32 off = skb_mac_header_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_unclone(skb, GFP_ATOMIC);
@@ -2782,8 +2780,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff)
 	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_cow(skb, len_diff);
@@ -2812,8 +2809,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
 	u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb);
 	int ret;
 
-	/* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */
-	if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb)))
+	if (!skb_is_gso_tcp(skb))
 		return -ENOTSUPP;
 
 	ret = skb_unclone(skb, GFP_ATOMIC);
-- 
2.19.1

[PATCH AUTOSEL 4.19 07/48] bpf: fix lockdep false positive in stackmap

[Sasha Levin]

From: Alexei Starovoitov <ast@kernel.org>

[ Upstream commit 3defaf2f15b2bfd86c6664181ac009e91985f8ac ]

Lockdep warns about false positive:
[   11.211460] ------------[ cut here ]------------
[   11.211936] DEBUG_LOCKS_WARN_ON(depth <= 0)
[   11.211985] WARNING: CPU: 0 PID: 141 at ../kernel/locking/lockdep.c:3592 lock_release+0x1ad/0x280
[   11.213134] Modules linked in:
[   11.214954] RIP: 0010:lock_release+0x1ad/0x280
[   11.223508] Call Trace:
[   11.223705]  <IRQ>
[   11.223874]  ? __local_bh_enable+0x7a/0x80
[   11.224199]  up_read+0x1c/0xa0
[   11.224446]  do_up_read+0x12/0x20
[   11.224713]  irq_work_run_list+0x43/0x70
[   11.225030]  irq_work_run+0x26/0x50
[   11.225310]  smp_irq_work_interrupt+0x57/0x1f0
[   11.225662]  irq_work_interrupt+0xf/0x20

since rw_semaphore is released in a different task vs task that locked the sema.
It is expected behavior.
Fix the warning with up_read_non_owner() and rwsem_release() annotation.

Fixes: bae77c5eb5b2 ("bpf: enable stackmap with build_id in nmi context")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/stackmap.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 6a32933cae4f..7cb7a7f98a37 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry)
 	struct stack_map_irq_work *work;
 
 	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	up_read(work->sem);
+	up_read_non_owner(work->sem);
 	work->sem = NULL;
 }
 
@@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 	} else {
 		work->sem = &current->mm->mmap_sem;
 		irq_work_queue(&work->irq_work);
+		/*
+		 * The irq_work will release the mmap_sem with
+		 * up_read_non_owner(). The rwsem_release() is called
+		 * here to release the lock from lockdep's perspective.
+		 */
+		rwsem_release(&current->mm->mmap_sem.dep_map, 1, _RET_IP_);
 	}
 }
 
-- 
2.19.1

[PATCH AUTOSEL 4.19 39/48] bpf, lpm: fix lookup bug in map_delete_elem

[Sasha Levin]

From: Alban Crequy <alban@kinvolk.io>

[ Upstream commit 7c0cdf0b3940f63d9777c3fcf250a2f83859ca54 ]

trie_delete_elem() was deleting an entry even though it was not matching
if the prefixlen was correct. This patch adds a check on matchlen.

Reproducer:

$ sudo bpftool map create /sys/fs/bpf/mylpm type lpm_trie key 8 value 1 entries 128 name mylpm flags 1
$ sudo bpftool map update pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 aa bb cc dd value hex 01
$ sudo bpftool map dump pinned /sys/fs/bpf/mylpm
key: 10 00 00 00 aa bb cc dd  value: 01
Found 1 element
$ sudo bpftool map delete pinned /sys/fs/bpf/mylpm key hex 10 00 00 00 ff ff ff ff
$ echo $?
0
$ sudo bpftool map dump pinned /sys/fs/bpf/mylpm
Found 0 elements

A similar reproducer is added in the selftests.

Without the patch:

$ sudo ./tools/testing/selftests/bpf/test_lpm_map
test_lpm_map: test_lpm_map.c:485: test_lpm_delete: Assertion `bpf_map_delete_elem(map_fd, key) == -1 && errno == ENOENT' failed.
Aborted

With the patch: test_lpm_map runs without errors.

Fixes: e454cf595853 ("bpf: Implement map_delete_elem for BPF_MAP_TYPE_LPM_TRIE")
Cc: Craig Gallek <kraig@google.com>
Signed-off-by: Alban Crequy <alban@kinvolk.io>
Acked-by: Craig Gallek <kraig@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/lpm_trie.c                      |  1 +
 tools/testing/selftests/bpf/test_lpm_map.c | 10 ++++++++++
 2 files changed, 11 insertions(+)

diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 9058317ba9de..4f3138e6ecb2 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -432,6 +432,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 	}
 
 	if (!node || node->prefixlen != key->prefixlen ||
+	    node->prefixlen != matchlen ||
 	    (node->flags & LPM_TREE_NODE_FLAG_IM)) {
 		ret = -ENOENT;
 		goto out;
diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c
index 147e34cfceb7..02d7c871862a 100644
--- a/tools/testing/selftests/bpf/test_lpm_map.c
+++ b/tools/testing/selftests/bpf/test_lpm_map.c
@@ -474,6 +474,16 @@ static void test_lpm_delete(void)
 	assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 &&
 		errno == ENOENT);
 
+	key->prefixlen = 30; // unused prefix so far
+	inet_pton(AF_INET, "192.255.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == -1 &&
+		errno == ENOENT);
+
+	key->prefixlen = 16; // same prefix as the root node
+	inet_pton(AF_INET, "192.255.0.0", key->data);
+	assert(bpf_map_delete_elem(map_fd, key) == -1 &&
+		errno == ENOENT);
+
 	/* assert initial lookup */
 	key->prefixlen = 32;
 	inet_pton(AF_INET, "192.168.0.1", key->data);
-- 
2.19.1

[PATCH AUTOSEL 4.19 42/48] nfp: bpf: fix code-gen bug on BPF_ALU | BPF_XOR | BPF_K

[Sasha Levin]

From: Jiong Wang <jiong.wang@netronome.com>

[ Upstream commit 71c190249f0ced5b26377ea6bf829ab3af77a40c ]

The intended optimization should be A ^ 0 = A, not A ^ -1 = A.

Fixes: cd7df56ed3e6 ("nfp: add BPF to NFP code translator")
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index eff57f7d056a..0a934296ea53 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -2306,7 +2306,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !meta->insn.imm);
 }
 
 static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-- 
2.19.1

[PATCH AUTOSEL 4.19 43/48] nfp: bpf: fix ALU32 high bits clearance bug

[Sasha Levin]

From: Jiong Wang <jiong.wang@netronome.com>

[ Upstream commit f036ebd9bfbe1e91a3d855e85e05fc5ff156b641 ]

NFP BPF JIT compiler is doing a couple of small optimizations when jitting
ALU imm instructions, some of these optimizations could save code-gen, for
example:

  A & -1 =  A
  A |  0 =  A
  A ^  0 =  A

However, for ALU32, high 32-bit of the 64-bit register should still be
cleared according to ISA semantics.

Fixes: cd7df56ed3e6 ("nfp: add BPF to NFP code translator")
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 0a934296ea53..4e18d95e548f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1288,15 +1288,10 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 static int
 wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-	      enum alu_op alu_op, bool skip)
+	      enum alu_op alu_op)
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (skip) {
-		meta->skip = true;
-		return 0;
-	}
-
 	wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm);
 	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
 
@@ -2306,7 +2301,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR);
 }
 
 static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2316,7 +2311,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND);
 }
 
 static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2326,7 +2321,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR);
 }
 
 static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2336,7 +2331,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD);
 }
 
 static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2346,7 +2341,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB);
 }
 
 static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
-- 
2.19.1