All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access
@ 2018-10-18 16:06 Song Liu
  2018-10-18 16:06 ` [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB Song Liu
                   ` (2 more replies)
  0 siblings, 3 replies; 8+ messages in thread
From: Song Liu @ 2018-10-18 16:06 UTC (permalink / raw)
  To: netdev; +Cc: ast, daniel, kernel-team, Song Liu

Changes v3 -> v4:
1. Fixed crash issue reported by Alexei.

Changes v2 -> v3:
1. Added helper function bpf_compute_and_save_data_pointers() and
   bpf_restore_data_pointers().

Changes v1 -> v2:
1. Updated the list of read-only fields, and read-write fields.
2. Added dummy sk to bpf_prog_test_run_skb().

This set enables BPF program of type BPF_PROG_TYPE_CGROUP_SKB to access
some __skb_buff data directly.

Song Liu (2):
  bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
  bpf: add tests for direct packet access from CGROUP_SKB

 include/linux/filter.h                      |  24 +++
 kernel/bpf/cgroup.c                         |   6 +
 net/bpf/test_run.c                          |   7 +
 net/core/filter.c                           |  36 ++++-
 tools/testing/selftests/bpf/test_verifier.c | 170 ++++++++++++++++++++
 5 files changed, 242 insertions(+), 1 deletion(-)

^ permalink raw reply	[flat|nested] 8+ messages in thread

* [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
  2018-10-18 16:06 [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Song Liu
@ 2018-10-18 16:06 ` Song Liu
  2018-10-19  0:14   ` Daniel Borkmann
  2018-10-18 16:06 ` [PATCH v4 bpf-next 2/2] bpf: add tests for direct packet access from CGROUP_SKB Song Liu
  2018-10-18 23:34 ` [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Alexei Starovoitov
  2 siblings, 1 reply; 8+ messages in thread
From: Song Liu @ 2018-10-18 16:06 UTC (permalink / raw)
  To: netdev; +Cc: ast, daniel, kernel-team, Song Liu

BPF programs of BPF_PROG_TYPE_CGROUP_SKB need to access headers in the
skb. This patch enables direct access of skb for these programs.

Two helper functions bpf_compute_and_save_data_pointers() and
bpf_restore_data_pointers() are introduced. There are used in
__cgroup_bpf_run_filter_skb(), to compute proper data_end for the
BPF program, and restore original data afterwards.

Signed-off-by: Song Liu <songliubraving@fb.com>
---
 include/linux/filter.h | 24 ++++++++++++++++++++++++
 kernel/bpf/cgroup.c    |  6 ++++++
 net/core/filter.c      | 36 +++++++++++++++++++++++++++++++++++-
 3 files changed, 65 insertions(+), 1 deletion(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5771874bc01e..96b3ee7f14c9 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -548,6 +548,30 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb)
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
+/* Similar to bpf_compute_data_pointers(), except that save orginal
+ * data in cb->data and cb->meta_data for restore.
+ */
+static inline void bpf_compute_and_save_data_pointers(
+	struct sk_buff *skb, void *saved_pointers[2])
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	saved_pointers[0] = cb->data_meta;
+	saved_pointers[1] = cb->data_end;
+	cb->data_meta = skb->data - skb_metadata_len(skb);
+	cb->data_end  = skb->data + skb_headlen(skb);
+}
+
+/* Restore data saved by bpf_compute_data_pointers(). */
+static inline void bpf_restore_data_pointers(
+	struct sk_buff *skb, void *saved_pointers[2])
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	cb->data_meta = saved_pointers[0];
+	cb->data_end = saved_pointers[1];;
+}
+
 static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 {
 	/* eBPF programs may read/write skb->cb[] area to transfer meta
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 00f6ed2e4f9a..5f5180104ddc 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -554,6 +554,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	unsigned int offset = skb->data - skb_network_header(skb);
 	struct sock *save_sk;
 	struct cgroup *cgrp;
+	void *saved_pointers[2];
 	int ret;
 
 	if (!sk || !sk_fullsock(sk))
@@ -566,8 +567,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	save_sk = skb->sk;
 	skb->sk = sk;
 	__skb_push(skb, offset);
+
+	/* compute pointers for the bpf prog */
+	bpf_compute_and_save_data_pointers(skb, saved_pointers);
+
 	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
 				 bpf_prog_run_save_cb);
+	bpf_restore_data_pointers(skb, saved_pointers);
 	__skb_pull(skb, offset);
 	skb->sk = save_sk;
 	return ret == 1 ? 0 : -EPERM;
diff --git a/net/core/filter.c b/net/core/filter.c
index 1a3ac6c46873..e3ca30bd6840 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5346,6 +5346,40 @@ static bool sk_filter_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, prog, info);
 }
 
+static bool cg_skb_is_valid_access(int off, int size,
+				   enum bpf_access_type type,
+				   const struct bpf_prog *prog,
+				   struct bpf_insn_access_aux *info)
+{
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, tc_classid):
+	case bpf_ctx_range(struct __sk_buff, data_meta):
+	case bpf_ctx_range(struct __sk_buff, flow_keys):
+		return false;
+	}
+	if (type == BPF_WRITE) {
+		switch (off) {
+		case bpf_ctx_range(struct __sk_buff, mark):
+		case bpf_ctx_range(struct __sk_buff, priority):
+		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
+			break;
+		default:
+			return false;
+		}
+	}
+
+	switch (off) {
+	case bpf_ctx_range(struct __sk_buff, data):
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	return bpf_skb_is_valid_access(off, size, type, prog, info);
+}
+
 static bool lwt_is_valid_access(int off, int size,
 				enum bpf_access_type type,
 				const struct bpf_prog *prog,
@@ -7038,7 +7072,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
 
 const struct bpf_verifier_ops cg_skb_verifier_ops = {
 	.get_func_proto		= cg_skb_func_proto,
-	.is_valid_access	= sk_filter_is_valid_access,
+	.is_valid_access	= cg_skb_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
 
-- 
2.17.1

^ permalink raw reply related	[flat|nested] 8+ messages in thread

* [PATCH v4 bpf-next 2/2] bpf: add tests for direct packet access from CGROUP_SKB
  2018-10-18 16:06 [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Song Liu
  2018-10-18 16:06 ` [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB Song Liu
@ 2018-10-18 16:06 ` Song Liu
  2018-10-18 23:34 ` [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Alexei Starovoitov
  2 siblings, 0 replies; 8+ messages in thread
From: Song Liu @ 2018-10-18 16:06 UTC (permalink / raw)
  To: netdev; +Cc: ast, daniel, kernel-team, Song Liu

Tests are added to make sure CGROUP_SKB cannot access:
  tc_classid, data_meta, flow_keys

and can read and write:
  mark, prority, and cb[0-4]

and can read other fields.

To make selftest with skb->sk work, a dummy sk is added in
bpf_prog_test_run_skb().

Signed-off-by: Song Liu <songliubraving@fb.com>
---
 net/bpf/test_run.c                          |   7 +
 tools/testing/selftests/bpf/test_verifier.c | 170 ++++++++++++++++++++
 2 files changed, 177 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 0c423b8cd75c..8dccac305268 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -10,6 +10,8 @@
 #include <linux/etherdevice.h>
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
+#include <net/sock.h>
+#include <net/tcp.h>
 
 static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
 		struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE])
@@ -115,6 +117,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
+	struct sock sk = {0};
 	void *data;
 	int ret;
 
@@ -137,11 +140,15 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		break;
 	}
 
+	sock_net_set(&sk, &init_net);
+	sock_init_data(NULL, &sk);
+
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
 		return -ENOMEM;
 	}
+	skb->sk = &sk;
 
 	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
 	__skb_put(skb, size);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index cf4cd32b6772..5bfba7e8afd7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4862,6 +4862,176 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"direct packet read test#1 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_end)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, len)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+			    	    offsetof(struct __sk_buff, pkt_type)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, queue_mapping)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, protocol)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_present)),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_2, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#2 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, vlan_tci)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+			    	    offsetof(struct __sk_buff, vlan_proto)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, priority)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, ingress_ifindex)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_index)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, hash)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#3 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+			    	    offsetof(struct __sk_buff, cb[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_4,
+				    offsetof(struct __sk_buff, cb[0])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_5,
+				    offsetof(struct __sk_buff, cb[1])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+				    offsetof(struct __sk_buff, cb[2])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7,
+				    offsetof(struct __sk_buff, cb[3])),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_8,
+				    offsetof(struct __sk_buff, cb[4])),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"direct packet read test#4 for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct __sk_buff, family)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip4)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_5, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[0])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[1])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[2])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_ip6[3])),
+			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct __sk_buff, remote_port)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
+				    offsetof(struct __sk_buff, local_port)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of tc_classid for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, tc_classid)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of data_meta for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, data_meta)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid access of flow_keys for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, flow_keys)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid write access to napi_id for CGROUP_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_1,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_9,
+				    offsetof(struct __sk_buff, napi_id)),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "invalid bpf_context access",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"valid cgroup storage access",
 		.insns = {
-- 
2.17.1

^ permalink raw reply related	[flat|nested] 8+ messages in thread

* Re: [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access
  2018-10-18 16:06 [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Song Liu
  2018-10-18 16:06 ` [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB Song Liu
  2018-10-18 16:06 ` [PATCH v4 bpf-next 2/2] bpf: add tests for direct packet access from CGROUP_SKB Song Liu
@ 2018-10-18 23:34 ` Alexei Starovoitov
  2018-10-19  1:46   ` Alexei Starovoitov
  2 siblings, 1 reply; 8+ messages in thread
From: Alexei Starovoitov @ 2018-10-18 23:34 UTC (permalink / raw)
  To: Song Liu; +Cc: netdev, ast, daniel, kernel-team

On Thu, Oct 18, 2018 at 09:06:47AM -0700, Song Liu wrote:
> Changes v3 -> v4:
> 1. Fixed crash issue reported by Alexei.
> 
> Changes v2 -> v3:
> 1. Added helper function bpf_compute_and_save_data_pointers() and
>    bpf_restore_data_pointers().
> 
> Changes v1 -> v2:
> 1. Updated the list of read-only fields, and read-write fields.
> 2. Added dummy sk to bpf_prog_test_run_skb().
> 
> This set enables BPF program of type BPF_PROG_TYPE_CGROUP_SKB to access
> some __skb_buff data directly.

Applied, Thanks

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
  2018-10-18 16:06 ` [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB Song Liu
@ 2018-10-19  0:14   ` Daniel Borkmann
  2018-10-19  1:33     ` Alexei Starovoitov
  0 siblings, 1 reply; 8+ messages in thread
From: Daniel Borkmann @ 2018-10-19  0:14 UTC (permalink / raw)
  To: Song Liu, netdev; +Cc: ast, kernel-team

On 10/18/2018 06:06 PM, Song Liu wrote:
> BPF programs of BPF_PROG_TYPE_CGROUP_SKB need to access headers in the
> skb. This patch enables direct access of skb for these programs.
> 
> Two helper functions bpf_compute_and_save_data_pointers() and
> bpf_restore_data_pointers() are introduced. There are used in
> __cgroup_bpf_run_filter_skb(), to compute proper data_end for the
> BPF program, and restore original data afterwards.
> 
> Signed-off-by: Song Liu <songliubraving@fb.com>
> ---
>  include/linux/filter.h | 24 ++++++++++++++++++++++++
>  kernel/bpf/cgroup.c    |  6 ++++++
>  net/core/filter.c      | 36 +++++++++++++++++++++++++++++++++++-
>  3 files changed, 65 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 5771874bc01e..96b3ee7f14c9 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -548,6 +548,30 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb)
>  	cb->data_end  = skb->data + skb_headlen(skb);
>  }
>  
> +/* Similar to bpf_compute_data_pointers(), except that save orginal
> + * data in cb->data and cb->meta_data for restore.
> + */
> +static inline void bpf_compute_and_save_data_pointers(
> +	struct sk_buff *skb, void *saved_pointers[2])
> +{
> +	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
> +
> +	saved_pointers[0] = cb->data_meta;
> +	saved_pointers[1] = cb->data_end;
> +	cb->data_meta = skb->data - skb_metadata_len(skb);
> +	cb->data_end  = skb->data + skb_headlen(skb);

Hmm, can you elaborate why populating data_meta here ...

> +}
> +
> +/* Restore data saved by bpf_compute_data_pointers(). */
> +static inline void bpf_restore_data_pointers(
> +	struct sk_buff *skb, void *saved_pointers[2])
> +{
> +	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
> +
> +	cb->data_meta = saved_pointers[0];
> +	cb->data_end = saved_pointers[1];;
> +}
> +
>  static inline u8 *bpf_skb_cb(struct sk_buff *skb)
>  {
>  	/* eBPF programs may read/write skb->cb[] area to transfer meta
> diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
> index 00f6ed2e4f9a..5f5180104ddc 100644
> --- a/kernel/bpf/cgroup.c
> +++ b/kernel/bpf/cgroup.c
> @@ -554,6 +554,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
>  	unsigned int offset = skb->data - skb_network_header(skb);
>  	struct sock *save_sk;
>  	struct cgroup *cgrp;
> +	void *saved_pointers[2];
>  	int ret;
>  
>  	if (!sk || !sk_fullsock(sk))
> @@ -566,8 +567,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
>  	save_sk = skb->sk;
>  	skb->sk = sk;
>  	__skb_push(skb, offset);
> +
> +	/* compute pointers for the bpf prog */
> +	bpf_compute_and_save_data_pointers(skb, saved_pointers);
> +
>  	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb,
>  				 bpf_prog_run_save_cb);
> +	bpf_restore_data_pointers(skb, saved_pointers);
>  	__skb_pull(skb, offset);
>  	skb->sk = save_sk;
>  	return ret == 1 ? 0 : -EPERM;
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 1a3ac6c46873..e3ca30bd6840 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5346,6 +5346,40 @@ static bool sk_filter_is_valid_access(int off, int size,
>  	return bpf_skb_is_valid_access(off, size, type, prog, info);
>  }
>  
> +static bool cg_skb_is_valid_access(int off, int size,
> +				   enum bpf_access_type type,
> +				   const struct bpf_prog *prog,
> +				   struct bpf_insn_access_aux *info)
> +{
> +	switch (off) {
> +	case bpf_ctx_range(struct __sk_buff, tc_classid):
> +	case bpf_ctx_range(struct __sk_buff, data_meta):
> +	case bpf_ctx_range(struct __sk_buff, flow_keys):
> +		return false;

... if it's disallowed anyway (disallowing it is the right thing to do,
but no need to save/restore then..)?

> +	}
> +	if (type == BPF_WRITE) {
> +		switch (off) {
> +		case bpf_ctx_range(struct __sk_buff, mark):
> +		case bpf_ctx_range(struct __sk_buff, priority):
> +		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
> +			break;
> +		default:
> +			return false;
> +		}
> +	}
> +
> +	switch (off) {
> +	case bpf_ctx_range(struct __sk_buff, data):
> +		info->reg_type = PTR_TO_PACKET;
> +		break;
> +	case bpf_ctx_range(struct __sk_buff, data_end):
> +		info->reg_type = PTR_TO_PACKET_END;
> +		break;
> +	}
> +
> +	return bpf_skb_is_valid_access(off, size, type, prog, info);
> +}
> +
>  static bool lwt_is_valid_access(int off, int size,
>  				enum bpf_access_type type,
>  				const struct bpf_prog *prog,
> @@ -7038,7 +7072,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
>  
>  const struct bpf_verifier_ops cg_skb_verifier_ops = {
>  	.get_func_proto		= cg_skb_func_proto,
> -	.is_valid_access	= sk_filter_is_valid_access,
> +	.is_valid_access	= cg_skb_is_valid_access,
>  	.convert_ctx_access	= bpf_convert_ctx_access,
>  };
>  
> 

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
  2018-10-19  0:14   ` Daniel Borkmann
@ 2018-10-19  1:33     ` Alexei Starovoitov
  2018-10-19  2:03       ` Alexei Starovoitov
  0 siblings, 1 reply; 8+ messages in thread
From: Alexei Starovoitov @ 2018-10-19  1:33 UTC (permalink / raw)
  To: Daniel Borkmann, Song Liu, netdev; +Cc: ast, Kernel Team

On 10/18/18 5:14 PM, Daniel Borkmann wrote:
>> +	case bpf_ctx_range(struct __sk_buff, data_meta):
>> +	case bpf_ctx_range(struct __sk_buff, flow_keys):
>> +		return false;
> ... if it's disallowed anyway (disallowing it is the right thing to do,
> but no need to save/restore then..)?
>

that's a good point.
why shouldn't we allow cg_skb to access data_meta?
xdp can set it and cgroup_skb_ingress will consume it here.


^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access
  2018-10-18 23:34 ` [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Alexei Starovoitov
@ 2018-10-19  1:46   ` Alexei Starovoitov
  0 siblings, 0 replies; 8+ messages in thread
From: Alexei Starovoitov @ 2018-10-19  1:46 UTC (permalink / raw)
  To: Alexei Starovoitov, Song Liu; +Cc: netdev, ast, daniel, Kernel Team

On 10/18/18 4:34 PM, Alexei Starovoitov wrote:
> On Thu, Oct 18, 2018 at 09:06:47AM -0700, Song Liu wrote:
>> Changes v3 -> v4:
>> 1. Fixed crash issue reported by Alexei.
>>
>> Changes v2 -> v3:
>> 1. Added helper function bpf_compute_and_save_data_pointers() and
>>    bpf_restore_data_pointers().
>>
>> Changes v1 -> v2:
>> 1. Updated the list of read-only fields, and read-write fields.
>> 2. Added dummy sk to bpf_prog_test_run_skb().
>>
>> This set enables BPF program of type BPF_PROG_TYPE_CGROUP_SKB to access
>> some __skb_buff data directly.
>
> Applied, Thanks

Daniel brought up good point re: data_meta. Let's address it one way
or the other and respin the series instead of adding follow up patches.
So I tossed this series out of bpf-next.

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
  2018-10-19  1:33     ` Alexei Starovoitov
@ 2018-10-19  2:03       ` Alexei Starovoitov
  0 siblings, 0 replies; 8+ messages in thread
From: Alexei Starovoitov @ 2018-10-19  2:03 UTC (permalink / raw)
  To: Daniel Borkmann, Song Liu, netdev; +Cc: ast, Kernel Team

On 10/18/18 6:33 PM, Alexei Starovoitov wrote:
> On 10/18/18 5:14 PM, Daniel Borkmann wrote:
>>> +    case bpf_ctx_range(struct __sk_buff, data_meta):
>>> +    case bpf_ctx_range(struct __sk_buff, flow_keys):
>>> +        return false;
>> ... if it's disallowed anyway (disallowing it is the right thing to do,
>> but no need to save/restore then..)?
>>
>
> that's a good point.
> why shouldn't we allow cg_skb to access data_meta?
> xdp can set it and cgroup_skb_ingress will consume it here.

I'll take it back.
When xdp doesn't set meta_data it will be zero and
bpf_compute_data_pointers() will point data_meta to skb->data.
On ingress that's eth header, but for tx it will point
to reserved space for future eth header.
So we cannot do that.
Let's keep it disabled and adjust
bpf_compute_and_save_data_pointers() to save only 'data' pointer.


^ permalink raw reply	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2018-10-19 10:07 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-10-18 16:06 [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Song Liu
2018-10-18 16:06 ` [PATCH v4 bpf-next 1/2] bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB Song Liu
2018-10-19  0:14   ` Daniel Borkmann
2018-10-19  1:33     ` Alexei Starovoitov
2018-10-19  2:03       ` Alexei Starovoitov
2018-10-18 16:06 ` [PATCH v4 bpf-next 2/2] bpf: add tests for direct packet access from CGROUP_SKB Song Liu
2018-10-18 23:34 ` [PATCH v4 bpf-next 0/2] bpf: add cg_skb_is_valid_access Alexei Starovoitov
2018-10-19  1:46   ` Alexei Starovoitov

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.