Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2019-01-20

The following pull-request contains BPF updates for your *net* tree.

The main changes are:

1) Fix a out-of-bounds access in __bpf_redirect_no_mac, from Willem.

2) Fix bpf_setsockopt to reset sock dst on SO_MARK changes, from Peter.

3) Fix map in map masking to prevent out-of-bounds access under
   speculative execution, from Daniel.

4) Fix bpf_setsockopt's SO_MAX_PACING_RATE to support TCP internal
   pacing, from Yuchung.

5) Fix json writer license in bpftool, from Thomas.

6) Fix AF_XDP to check if an actually queue exists during umem
   setup, from Krzysztof.

7) Several fixes to BPF stackmap's build id handling. Another fix
   for bpftool build to account for libbfd variations wrt linking
   requirements, from Stanislav.

8) Fix BPF samples build with clang by working around missing asm
   goto, from Yonghong.

9) Fix libbpf to retry program load on signal interrupt, from Lorenz.

10) Various minor compile warning fixes in BPF code, from Mathieu.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

16 files changed, 1293 insertions, 36 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index a2f53642592b..befe570be5ba 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -467,7 +467,7 @@ static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 	return kind_ops[BTF_INFO_KIND(t->info)];
 }
 
-bool btf_name_offset_valid(const struct btf *btf, u32 offset)
+static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 {
 	return BTF_STR_OFFSET_VALID(offset) &&
 		offset < btf->hdr.str_len;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9425c2fb872f..ab612fe9862f 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -718,6 +718,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_trace_printk:
 		if (capable(CAP_SYS_ADMIN))
 			return bpf_get_trace_printk_proto();
+		/* fall through */
 	default:
 		return NULL;
 	}
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 99d243e1ad6e..52378d3e34b3 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -12,6 +12,7 @@
 struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 {
 	struct bpf_map *inner_map, *inner_map_meta;
+	u32 inner_map_meta_size;
 	struct fd f;
 
 	f = fdget(inner_map_ufd);
@@ -36,7 +37,12 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 		return ERR_PTR(-EINVAL);
 	}
 
-	inner_map_meta = kzalloc(sizeof(*inner_map_meta), GFP_USER);
+	inner_map_meta_size = sizeof(*inner_map_meta);
+	/* In some cases verifier needs to access beyond just base map. */
+	if (inner_map->ops == &array_map_ops)
+		inner_map_meta_size = sizeof(struct bpf_array);
+
+	inner_map_meta = kzalloc(inner_map_meta_size, GFP_USER);
 	if (!inner_map_meta) {
 		fdput(f);
 		return ERR_PTR(-ENOMEM);
@@ -46,9 +52,16 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	inner_map_meta->key_size = inner_map->key_size;
 	inner_map_meta->value_size = inner_map->value_size;
 	inner_map_meta->map_flags = inner_map->map_flags;
-	inner_map_meta->ops = inner_map->ops;
 	inner_map_meta->max_entries = inner_map->max_entries;
 
+	/* Misc members not needed in bpf_map_meta_equal() check. */
+	inner_map_meta->ops = inner_map->ops;
+	if (inner_map->ops == &array_map_ops) {
+		inner_map_meta->unpriv_array = inner_map->unpriv_array;
+		container_of(inner_map_meta, struct bpf_array, map)->index_mask =
+		     container_of(inner_map, struct bpf_array, map)->index_mask;
+	}
+
 	fdput(f);
 	return inner_map_meta;
 }
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d9e2483669d0..d43b14535827 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -180,11 +180,14 @@ static inline int stack_map_parse_build_id(void *page_addr,
 
 		if (nhdr->n_type == BPF_BUILD_ID &&
 		    nhdr->n_namesz == sizeof("GNU") &&
-		    nhdr->n_descsz == BPF_BUILD_ID_SIZE) {
+		    nhdr->n_descsz > 0 &&
+		    nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
 			memcpy(build_id,
 			       note_start + note_offs +
 			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
-			       BPF_BUILD_ID_SIZE);
+			       nhdr->n_descsz);
+			memset(build_id + nhdr->n_descsz, 0,
+			       BPF_BUILD_ID_SIZE - nhdr->n_descsz);
 			return 0;
 		}
 		new_offs = note_offs + sizeof(Elf32_Nhdr) +
@@ -311,6 +314,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
 			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
 		}
 		return;
 	}
@@ -321,6 +325,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			/* per entry fall back to ips */
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
 			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
 			continue;
 		}
 		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
diff --git a/net/core/filter.c b/net/core/filter.c
index 2b3b436ef545..7559d6835ecb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2020,18 +2020,19 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb)
 static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev,
 				 u32 flags)
 {
-	/* skb->mac_len is not set on normal egress */
-	unsigned int mlen = skb->network_header - skb->mac_header;
+	unsigned int mlen = skb_network_offset(skb);
 
-	__skb_pull(skb, mlen);
+	if (mlen) {
+		__skb_pull(skb, mlen);
 
-	/* At ingress, the mac header has already been pulled once.
-	 * At egress, skb_pospull_rcsum has to be done in case that
-	 * the skb is originated from ingress (i.e. a forwarded skb)
-	 * to ensure that rcsum starts at net header.
-	 */
-	if (!skb_at_tc_ingress(skb))
-		skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+		/* At ingress, the mac header has already been pulled once.
+		 * At egress, skb_pospull_rcsum has to be done in case that
+		 * the skb is originated from ingress (i.e. a forwarded skb)
+		 * to ensure that rcsum starts at net header.
+		 */
+		if (!skb_at_tc_ingress(skb))
+			skb_postpull_rcsum(skb, skb_mac_header(skb), mlen);
+	}
 	skb_pop_mac_header(skb);
 	skb_reset_mac_len(skb);
 	return flags & BPF_F_INGRESS ?
@@ -4119,6 +4120,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
 			break;
 		case SO_MAX_PACING_RATE: /* 32bit version */
+			if (val != ~0U)
+				cmpxchg(&sk->sk_pacing_status,
+					SK_PACING_NONE,
+					SK_PACING_NEEDED);
 			sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val;
 			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
 						 sk->sk_max_pacing_rate);
@@ -4132,7 +4137,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			sk->sk_rcvlowat = val ? : 1;
 			break;
 		case SO_MARK:
-			sk->sk_mark = val;
+			if (sk->sk_mark != val) {
+				sk->sk_mark = val;
+				sk_dst_reset(sk);
+			}
 			break;
 		default:
 			ret = -EINVAL;
@@ -5309,7 +5317,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_trace_printk:
 		if (capable(CAP_SYS_ADMIN))
 			return bpf_get_trace_printk_proto();
-		/* else: fall through */
+		/* else, fall through */
 	default:
 		return NULL;
 	}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 3e85437f7106..a648568c5e8f 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -63,6 +63,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 				     lwt->name ? : "<unknown>");
 			ret = BPF_OK;
 		} else {
+			skb_reset_mac_header(skb);
 			ret = skb_do_redirect(skb);
 			if (ret == 0)
 				ret = BPF_REDIRECT;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index a264cf2accd0..d4de871e7d4d 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -41,13 +41,20 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
  * not know if the device has more tx queues than rx, or the opposite.
  * This might also change during run time.
  */
-static void xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
-				u16 queue_id)
+static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
+			       u16 queue_id)
 {
+	if (queue_id >= max_t(unsigned int,
+			      dev->real_num_rx_queues,
+			      dev->real_num_tx_queues))
+		return -EINVAL;
+
 	if (queue_id < dev->real_num_rx_queues)
 		dev->_rx[queue_id].umem = umem;
 	if (queue_id < dev->real_num_tx_queues)
 		dev->_tx[queue_id].umem = umem;
+
+	return 0;
 }
 
 struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
@@ -88,7 +95,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 		goto out_rtnl_unlock;
 	}
 
-	xdp_reg_umem_at_qid(dev, umem, queue_id);
+	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
+	if (err)
+		goto out_rtnl_unlock;
+
 	umem->dev = dev;
 	umem->queue_id = queue_id;
 	if (force_copy)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 66ae15f27c70..db1a91dfa702 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -279,6 +279,7 @@ $(obj)/%.o: $(src)/%.c
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+		-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
 		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
new file mode 100644
index 000000000000..5cd7c1d1a5d5
--- /dev/null
+++ b/samples/bpf/asm_goto_workaround.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+#ifndef __ASM_GOTO_WORKAROUND_H
+#define __ASM_GOTO_WORKAROUND_H
+
+/* this will bring in asm_volatile_goto macro definition
+ * if enabled by compiler and config options.
+ */
+#include <linux/types.h>
+
+#ifdef asm_volatile_goto
+#undef asm_volatile_goto
+#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#endif
+
+#endif
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 492f0f24e2d3..4ad1f0894d53 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -93,9 +93,16 @@ BFD_SRCS = jit_disasm.c
 SRCS = $(filter-out $(BFD_SRCS),$(wildcard *.c))
 
 ifeq ($(feature-libbfd),1)
+  LIBS += -lbfd -ldl -lopcodes
+else ifeq ($(feature-libbfd-liberty),1)
+  LIBS += -lbfd -ldl -lopcodes -liberty
+else ifeq ($(feature-libbfd-liberty-z),1)
+  LIBS += -lbfd -ldl -lopcodes -liberty -lz
+endif
+
+ifneq ($(filter -lbfd,$(LIBS)),)
 CFLAGS += -DHAVE_LIBBFD_SUPPORT
 SRCS += $(BFD_SRCS)
-LIBS += -lbfd -lopcodes
 endif
 
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
diff --git a/tools/bpf/bpftool/json_writer.c b/tools/bpf/bpftool/json_writer.c
index bff7ee026680..6046dcab51cc 100644
--- a/tools/bpf/bpftool/json_writer.c
+++ b/tools/bpf/bpftool/json_writer.c
@@ -1,15 +1,10 @@
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause)
 /*
  * Simple streaming JSON writer
  *
  * This takes care of the annoying bits of JSON syntax like the commas
  * after elements
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * Authors:	Stephen Hemminger <stephen@networkplumber.org>
  */
 
diff --git a/tools/bpf/bpftool/json_writer.h b/tools/bpf/bpftool/json_writer.h
index c1ab51aed99c..cb9a1993681c 100644
--- a/tools/bpf/bpftool/json_writer.h
+++ b/tools/bpf/bpftool/json_writer.h
@@ -5,11 +5,6 @@
  * This takes care of the annoying bits of JSON syntax like the commas
  * after elements
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
  * Authors:	Stephen Hemminger <stephen@networkplumber.org>
  */
 
diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
new file mode 100644
index 000000000000..0d18b1d1fbbc
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -0,0 +1,1163 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+   Every scheduler will map them to real traffic classes, if it has
+   no more precise mechanism to classify packets.
+
+   These numbers have no special meaning, though their coincidence
+   with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+   preferred full anarchy inspired by diffserv group.
+
+   Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+   class, actually, as rule it will be handled with more care than
+   filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT		0
+#define TC_PRIO_FILLER			1
+#define TC_PRIO_BULK			2
+#define TC_PRIO_INTERACTIVE_BULK	4
+#define TC_PRIO_INTERACTIVE		6
+#define TC_PRIO_CONTROL			7
+
+#define TC_PRIO_MAX			15
+
+/* Generic queue statistics, available for all the elements.
+   Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+	__u64	bytes;			/* Number of enqueued bytes */
+	__u32	packets;		/* Number of enqueued packets	*/
+	__u32	drops;			/* Packets dropped because of lack of resources */
+	__u32	overlimits;		/* Number of throttle events when this
+					 * flow goes out of allocated bandwidth */
+	__u32	bps;			/* Current flow byte rate */
+	__u32	pps;			/* Current flow packet rate */
+	__u32	qlen;
+	__u32	backlog;
+};
+
+struct tc_estimator {
+	signed char	interval;
+	unsigned char	ewma_log;
+};
+
+/* "Handles"
+   ---------
+
+    All the traffic control objects have 32bit identifiers, or "handles".
+
+    They can be considered as opaque numbers from user API viewpoint,
+    but actually they always consist of two fields: major and
+    minor numbers, which are interpreted by kernel specially,
+    that may be used by applications, though not recommended.
+
+    F.e. qdisc handles always have minor number equal to zero,
+    classes (or flows) have major equal to parent qdisc major, and
+    minor uniquely identifying class inside qdisc.
+
+    Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC	(0U)
+#define TC_H_ROOT	(0xFFFFFFFFU)
+#define TC_H_INGRESS    (0xFFFFFFF1U)
+#define TC_H_CLSACT	TC_H_INGRESS
+
+#define TC_H_MIN_PRIORITY	0xFFE0U
+#define TC_H_MIN_INGRESS	0xFFF2U
+#define TC_H_MIN_EGRESS		0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+	TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+	TC_LINKLAYER_ETHERNET,
+	TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+	unsigned char	cell_log;
+	__u8		linklayer; /* lower 4 bits */
+	unsigned short	overhead;
+	short		cell_align;
+	unsigned short	mpu;
+	__u32		rate;
+};
+
+#define TC_RTAB_SIZE	1024
+
+struct tc_sizespec {
+	unsigned char	cell_log;
+	unsigned char	size_log;
+	short		cell_align;
+	int		overhead;
+	unsigned int	linklayer;
+	unsigned int	mpu;
+	unsigned int	mtu;
+	unsigned int	tsize;
+};
+
+enum {
+	TCA_STAB_UNSPEC,
+	TCA_STAB_BASE,
+	TCA_STAB_DATA,
+	__TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+	__u32	limit;	/* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+	__u32	limit;		/* Queue length in packets. */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS	16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+	int	bands;			/* Number of bands */
+	__u8	priomap[TC_PRIO_MAX+1];	/* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+	__u16	bands;			/* Number of bands */
+	__u16	max_bands;		/* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER                0
+#define TCQ_PLUG_RELEASE_ONE           1
+#define TCQ_PLUG_RELEASE_INDEFINITE    2
+#define TCQ_PLUG_LIMIT                 3
+
+struct tc_plug_qopt {
+	/* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+	 *  buffer any incoming packets
+	 * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+	 *   to beginning of the next plug.
+	 * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+	 *   Stop buffering packets until the next TCQ_PLUG_BUFFER
+	 *   command is received (just act as a pass-thru queue).
+	 * TCQ_PLUG_LIMIT: Increase/decrease queue size
+	 */
+	int             action;
+	__u32           limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+	struct tc_ratespec rate;
+	struct tc_ratespec peakrate;
+	__u32		limit;
+	__u32		buffer;
+	__u32		mtu;
+};
+
+enum {
+	TCA_TBF_UNSPEC,
+	TCA_TBF_PARMS,
+	TCA_TBF_RTAB,
+	TCA_TBF_PTAB,
+	TCA_TBF_RATE64,
+	TCA_TBF_PRATE64,
+	TCA_TBF_BURST,
+	TCA_TBF_PBURST,
+	TCA_TBF_PAD,
+	__TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+	unsigned	quantum;	/* Bytes per round allocated to flow */
+	int		perturb_period;	/* Period of hash perturbation */
+	__u32		limit;		/* Maximal packets in queue */
+	unsigned	divisor;	/* Hash divisor  */
+	unsigned	flows;		/* Maximal number of flows  */
+};
+
+struct tc_sfqred_stats {
+	__u32           prob_drop;      /* Early drops, below max threshold */
+	__u32           forced_drop;	/* Early drops, after max threshold */
+	__u32           prob_mark;      /* Marked packets, below max threshold */
+	__u32           forced_mark;    /* Marked packets, after max threshold */
+	__u32           prob_mark_head; /* Marked packets, below max threshold */
+	__u32           forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+	struct tc_sfq_qopt v0;
+	unsigned int	depth;		/* max number of packets per flow */
+	unsigned int	headdrop;
+/* SFQRED parameters */
+	__u32		limit;		/* HARD maximal flow queue length (bytes) */
+	__u32		qth_min;	/* Min average length threshold (bytes) */
+	__u32		qth_max;	/* Max average length threshold (bytes) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;
+	__u32		max_P;		/* probability, high resolution */
+/* SFQRED stats */
+	struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+	__s32		allot;
+};
+
+/* RED section */
+
+enum {
+	TCA_RED_UNSPEC,
+	TCA_RED_PARMS,
+	TCA_RED_STAB,
+	TCA_RED_MAX_P,
+	__TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+	__u32		limit;		/* HARD maximal queue length (bytes)	*/
+	__u32		qth_min;	/* Min average length threshold (bytes) */
+	__u32		qth_max;	/* Max average length threshold (bytes) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;
+#define TC_RED_ECN		1
+#define TC_RED_HARDDROP		2
+#define TC_RED_ADAPTATIVE	4
+};
+
+struct tc_red_xstats {
+	__u32           early;          /* Early drops */
+	__u32           pdrop;          /* Drops due to queue limits */
+	__u32           other;          /* Drops due to drop() calls */
+	__u32           marked;         /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+       TCA_GRED_UNSPEC,
+       TCA_GRED_PARMS,
+       TCA_GRED_STAB,
+       TCA_GRED_DPS,
+       TCA_GRED_MAX_P,
+       TCA_GRED_LIMIT,
+       TCA_GRED_VQ_LIST,	/* nested TCA_GRED_VQ_ENTRY */
+       __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+enum {
+	TCA_GRED_VQ_ENTRY_UNSPEC,
+	TCA_GRED_VQ_ENTRY,	/* nested TCA_GRED_VQ_* */
+	__TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+	TCA_GRED_VQ_UNSPEC,
+	TCA_GRED_VQ_PAD,
+	TCA_GRED_VQ_DP,			/* u32 */
+	TCA_GRED_VQ_STAT_BYTES,		/* u64 */
+	TCA_GRED_VQ_STAT_PACKETS,	/* u32 */
+	TCA_GRED_VQ_STAT_BACKLOG,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_PDROP,		/* u32 */
+	TCA_GRED_VQ_STAT_OTHER,		/* u32 */
+	TCA_GRED_VQ_FLAGS,		/* u32 */
+	__TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
+struct tc_gred_qopt {
+	__u32		limit;        /* HARD maximal queue length (bytes)    */
+	__u32		qth_min;      /* Min average length threshold (bytes) */
+	__u32		qth_max;      /* Max average length threshold (bytes) */
+	__u32		DP;           /* up to 2^32 DPs */
+	__u32		backlog;
+	__u32		qave;
+	__u32		forced;
+	__u32		early;
+	__u32		other;
+	__u32		pdrop;
+	__u8		Wlog;         /* log(W)               */
+	__u8		Plog;         /* log(P_max/(qth_max-qth_min)) */
+	__u8		Scell_log;    /* cell size for idle damping */
+	__u8		prio;         /* prio of this VQ */
+	__u32		packets;
+	__u32		bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+	__u32		DPs;
+	__u32		def_DP;
+	__u8		grio;
+	__u8		flags;
+	__u16		pad1;
+};
+
+/* CHOKe section */
+
+enum {
+	TCA_CHOKE_UNSPEC,
+	TCA_CHOKE_PARMS,
+	TCA_CHOKE_STAB,
+	TCA_CHOKE_MAX_P,
+	__TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+	__u32		limit;		/* Hard queue length (packets)	*/
+	__u32		qth_min;	/* Min average threshold (packets) */
+	__u32		qth_max;	/* Max average threshold (packets) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;		/* see RED flags */
+};
+
+struct tc_choke_xstats {
+	__u32		early;          /* Early drops */
+	__u32		pdrop;          /* Drops due to queue limits */
+	__u32		other;          /* Drops due to drop() calls */
+	__u32		marked;         /* Marked packets */
+	__u32		matched;	/* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO		8
+#define TC_HTB_MAXDEPTH		8
+#define TC_HTB_PROTOVER		3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+	struct tc_ratespec 	rate;
+	struct tc_ratespec 	ceil;
+	__u32	buffer;
+	__u32	cbuffer;
+	__u32	quantum;
+	__u32	level;		/* out only */
+	__u32	prio;
+};
+struct tc_htb_glob {
+	__u32 version;		/* to match HTB/TC */
+    	__u32 rate2quantum;	/* bps->quantum divisor */
+    	__u32 defcls;		/* default class number */
+	__u32 debug;		/* debug flags */
+
+	/* stats */
+	__u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+	TCA_HTB_UNSPEC,
+	TCA_HTB_PARMS,
+	TCA_HTB_INIT,
+	TCA_HTB_CTAB,
+	TCA_HTB_RTAB,
+	TCA_HTB_DIRECT_QLEN,
+	TCA_HTB_RATE64,
+	TCA_HTB_CEIL64,
+	TCA_HTB_PAD,
+	__TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+	__u32 lends;
+	__u32 borrows;
+	__u32 giants;	/* unused since 'Make HTB scheduler work with TSO.' */
+	__s32 tokens;
+	__s32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+	__u16	defcls;		/* default class */
+};
+
+struct tc_service_curve {
+	__u32	m1;		/* slope of the first segment in bps */
+	__u32	d;		/* x-projection of the first segment in us */
+	__u32	m2;		/* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+	__u64	work;		/* total work done */
+	__u64	rtwork;		/* work done by real-time criteria */
+	__u32	period;		/* current period */
+	__u32	level;		/* class level in hierarchy */
+};
+
+enum {
+	TCA_HFSC_UNSPEC,
+	TCA_HFSC_RSC,
+	TCA_HFSC_FSC,
+	TCA_HFSC_USC,
+	__TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO		8
+#define TC_CBQ_MAXLEVEL		8
+#define TC_CBQ_DEF_EWMA		5
+
+struct tc_cbq_lssopt {
+	unsigned char	change;
+	unsigned char	flags;
+#define TCF_CBQ_LSS_BOUNDED	1
+#define TCF_CBQ_LSS_ISOLATED	2
+	unsigned char  	ewma_log;
+	unsigned char  	level;
+#define TCF_CBQ_LSS_FLAGS	1
+#define TCF_CBQ_LSS_EWMA	2
+#define TCF_CBQ_LSS_MAXIDLE	4
+#define TCF_CBQ_LSS_MINIDLE	8
+#define TCF_CBQ_LSS_OFFTIME	0x10
+#define TCF_CBQ_LSS_AVPKT	0x20
+	__u32		maxidle;
+	__u32		minidle;
+	__u32		offtime;
+	__u32		avpkt;
+};
+
+struct tc_cbq_wrropt {
+	unsigned char	flags;
+	unsigned char	priority;
+	unsigned char	cpriority;
+	unsigned char	__reserved;
+	__u32		allot;
+	__u32		weight;
+};
+
+struct tc_cbq_ovl {
+	unsigned char	strategy;
+#define	TC_CBQ_OVL_CLASSIC	0
+#define	TC_CBQ_OVL_DELAY	1
+#define	TC_CBQ_OVL_LOWPRIO	2
+#define	TC_CBQ_OVL_DROP		3
+#define	TC_CBQ_OVL_RCLASSIC	4
+	unsigned char	priority2;
+	__u16		pad;
+	__u32		penalty;
+};
+
+struct tc_cbq_police {
+	unsigned char	police;
+	unsigned char	__res1;
+	unsigned short	__res2;
+};
+
+struct tc_cbq_fopt {
+	__u32		split;
+	__u32		defmap;
+	__u32		defchange;
+};
+
+struct tc_cbq_xstats {
+	__u32		borrows;
+	__u32		overactions;
+	__s32		avgidle;
+	__s32		undertime;
+};
+
+enum {
+	TCA_CBQ_UNSPEC,
+	TCA_CBQ_LSSOPT,
+	TCA_CBQ_WRROPT,
+	TCA_CBQ_FOPT,
+	TCA_CBQ_OVL_STRATEGY,
+	TCA_CBQ_RATE,
+	TCA_CBQ_RTAB,
+	TCA_CBQ_POLICE,
+	__TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+	TCA_DSMARK_UNSPEC,
+	TCA_DSMARK_INDICES,
+	TCA_DSMARK_DEFAULT_INDEX,
+	TCA_DSMARK_SET_TC_INDEX,
+	TCA_DSMARK_MASK,
+	TCA_DSMARK_VALUE,
+	__TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM  section */
+
+enum {
+	TCA_ATM_UNSPEC,
+	TCA_ATM_FD,		/* file/socket descriptor */
+	TCA_ATM_PTR,		/* pointer to descriptor - later */
+	TCA_ATM_HDR,		/* LL header */
+	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
+	TCA_ATM_ADDR,		/* PVC address (for output only) */
+	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
+	__TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
+
+/* Network emulator */
+
+enum {
+	TCA_NETEM_UNSPEC,
+	TCA_NETEM_CORR,
+	TCA_NETEM_DELAY_DIST,
+	TCA_NETEM_REORDER,
+	TCA_NETEM_CORRUPT,
+	TCA_NETEM_LOSS,
+	TCA_NETEM_RATE,
+	TCA_NETEM_ECN,
+	TCA_NETEM_RATE64,
+	TCA_NETEM_PAD,
+	TCA_NETEM_LATENCY64,
+	TCA_NETEM_JITTER64,
+	TCA_NETEM_SLOT,
+	TCA_NETEM_SLOT_DIST,
+	__TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+	__u32	latency;	/* added delay (us) */
+	__u32   limit;		/* fifo limit (packets) */
+	__u32	loss;		/* random packet loss (0=none ~0=100%) */
+	__u32	gap;		/* re-ordering gap (0 for none) */
+	__u32   duplicate;	/* random packet dup  (0=none ~0=100%) */
+	__u32	jitter;		/* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+	__u32	delay_corr;	/* delay correlation */
+	__u32	loss_corr;	/* packet loss correlation */
+	__u32	dup_corr;	/* duplicate correlation  */
+};
+
+struct tc_netem_reorder {
+	__u32	probability;
+	__u32	correlation;
+};
+
+struct tc_netem_corrupt {
+	__u32	probability;
+	__u32	correlation;
+};
+
+struct tc_netem_rate {
+	__u32	rate;	/* byte/s */
+	__s32	packet_overhead;
+	__u32	cell_size;
+	__s32	cell_overhead;
+};
+
+struct tc_netem_slot {
+	__s64   min_delay; /* nsec */
+	__s64   max_delay;
+	__s32   max_packets;
+	__s32   max_bytes;
+	__s64	dist_delay; /* nsec */
+	__s64	dist_jitter; /* nsec */
+};
+
+enum {
+	NETEM_LOSS_UNSPEC,
+	NETEM_LOSS_GI,		/* General Intuitive - 4 state model */
+	NETEM_LOSS_GE,		/* Gilbert Elliot models */
+	__NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+	__u32	p13;
+	__u32	p31;