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

Daniel Borkmann says:

====================
bpf-next 2018-11-30

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

(Getting out bit earlier this time to pull in a dependency from bpf.)

The main changes are:

1) Add libbpf ABI versioning and document API naming conventions
   as well as ABI versioning process, from Andrey.

2) Add a new sk_msg_pop_data() helper for sk_msg based BPF
   programs that is used in conjunction with sk_msg_push_data()
   for adding / removing meta data to the msg data, from John.

3) Optimize convert_bpf_ld_abs() for 0 offset and fix various
   lib and testsuite build failures on 32 bit, from David.

4) Make BPF prog dump for !JIT identical to how we dump subprogs
   when JIT is in use, from Yonghong.

5) Rename btf_get_from_id() to make it more conform with libbpf
   API naming conventions, from Martin.

6) Add a missing BPF kselftest config item, from Naresh.
====================

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

1 files changed, 173 insertions, 1 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index aa274679965d..bd0df75dc7b6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -463,7 +463,8 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 		bool ldx_off_ok = offset <= S16_MAX;
 
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
-		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
+		if (offset)
+			*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
 		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
 				      size, 2 + endian + (!ldx_off_ok * 2));
 		if (ldx_off_ok) {
@@ -2424,6 +2425,174 @@ static const struct bpf_func_proto bpf_msg_push_data_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
+static void sk_msg_shift_left(struct sk_msg *msg, int i)
+{
+	int prev;
+
+	do {
+		prev = i;
+		sk_msg_iter_var_next(i);
+		msg->sg.data[prev] = msg->sg.data[i];
+	} while (i != msg->sg.end);
+
+	sk_msg_iter_prev(msg, end);
+}
+
+static void sk_msg_shift_right(struct sk_msg *msg, int i)
+{
+	struct scatterlist tmp, sge;
+
+	sk_msg_iter_next(msg, end);
+	sge = sk_msg_elem_cpy(msg, i);
+	sk_msg_iter_var_next(i);
+	tmp = sk_msg_elem_cpy(msg, i);
+
+	while (i != msg->sg.end) {
+		msg->sg.data[i] = sge;
+		sk_msg_iter_var_next(i);
+		sge = tmp;
+		tmp = sk_msg_elem_cpy(msg, i);
+	}
+}
+
+BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
+	   u32, len, u64, flags)
+{
+	u32 i = 0, l, space, offset = 0;
+	u64 last = start + len;
+	int pop;
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg.start;
+	do {
+		l = sk_msg_elem(msg, i)->length;
+
+		if (start < offset + l)
+			break;
+		offset += l;
+		sk_msg_iter_var_next(i);
+	} while (i != msg->sg.end);
+
+	/* Bounds checks: start and pop must be inside message */
+	if (start >= offset + l || last >= msg->sg.size)
+		return -EINVAL;
+
+	space = MAX_MSG_FRAGS - sk_msg_elem_used(msg);
+
+	pop = len;
+	/* --------------| offset
+	 * -| start      |-------- len -------|
+	 *
+	 *  |----- a ----|-------- pop -------|----- b ----|
+	 *  |______________________________________________| length
+	 *
+	 *
+	 * a:   region at front of scatter element to save
+	 * b:   region at back of scatter element to save when length > A + pop
+	 * pop: region to pop from element, same as input 'pop' here will be
+	 *      decremented below per iteration.
+	 *
+	 * Two top-level cases to handle when start != offset, first B is non
+	 * zero and second B is zero corresponding to when a pop includes more
+	 * than one element.
+	 *
+	 * Then if B is non-zero AND there is no space allocate space and
+	 * compact A, B regions into page. If there is space shift ring to
+	 * the rigth free'ing the next element in ring to place B, leaving
+	 * A untouched except to reduce length.
+	 */
+	if (start != offset) {
+		struct scatterlist *nsge, *sge = sk_msg_elem(msg, i);
+		int a = start;
+		int b = sge->length - pop - a;
+
+		sk_msg_iter_var_next(i);
+
+		if (pop < sge->length - a) {
+			if (space) {
+				sge->length = a;
+				sk_msg_shift_right(msg, i);
+				nsge = sk_msg_elem(msg, i);
+				get_page(sg_page(sge));
+				sg_set_page(nsge,
+					    sg_page(sge),
+					    b, sge->offset + pop + a);
+			} else {
+				struct page *page, *orig;
+				u8 *to, *from;
+
+				page = alloc_pages(__GFP_NOWARN |
+						   __GFP_COMP   | GFP_ATOMIC,
+						   get_order(a + b));
+				if (unlikely(!page))
+					return -ENOMEM;
+
+				sge->length = a;
+				orig = sg_page(sge);
+				from = sg_virt(sge);
+				to = page_address(page);
+				memcpy(to, from, a);
+				memcpy(to + a, from + a + pop, b);
+				sg_set_page(sge, page, a + b, 0);
+				put_page(orig);
+			}
+			pop = 0;
+		} else if (pop >= sge->length - a) {
+			sge->length = a;
+			pop -= (sge->length - a);
+		}
+	}
+
+	/* From above the current layout _must_ be as follows,
+	 *
+	 * -| offset
+	 * -| start
+	 *
+	 *  |---- pop ---|---------------- b ------------|
+	 *  |____________________________________________| length
+	 *
+	 * Offset and start of the current msg elem are equal because in the
+	 * previous case we handled offset != start and either consumed the
+	 * entire element and advanced to the next element OR pop == 0.
+	 *
+	 * Two cases to handle here are first pop is less than the length
+	 * leaving some remainder b above. Simply adjust the element's layout
+	 * in this case. Or pop >= length of the element so that b = 0. In this
+	 * case advance to next element decrementing pop.
+	 */
+	while (pop) {
+		struct scatterlist *sge = sk_msg_elem(msg, i);
+
+		if (pop < sge->length) {
+			sge->length -= pop;
+			sge->offset += pop;
+			pop = 0;
+		} else {
+			pop -= sge->length;
+			sk_msg_shift_left(msg, i);
+		}
+		sk_msg_iter_var_next(i);
+	}
+
+	sk_mem_uncharge(msg->sk, len - pop);
+	msg->sg.size -= (len - pop);
+	sk_msg_compute_data_pointers(msg);
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_pop_data_proto = {
+	.func		= bpf_msg_pop_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -5097,6 +5266,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
 	    func == bpf_msg_push_data ||
+	    func == bpf_msg_pop_data ||
 	    func == bpf_xdp_adjust_tail ||
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
@@ -5393,6 +5563,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_pull_data_proto;
 	case BPF_FUNC_msg_push_data:
 		return &bpf_msg_push_data_proto;
+	case BPF_FUNC_msg_pop_data:
+		return &bpf_msg_pop_data_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}