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

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-02-16

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

There's a small merge conflict between 7eeba1706e ("tcp: Add receive timestamp
support for receive zerocopy.") from net-next tree and 9cacf81f81 ("bpf: Remove
extra lock_sock for TCP_ZEROCOPY_RECEIVE") from bpf-next tree. Resolve as follows:

  [...]
                lock_sock(sk);
                err = tcp_zerocopy_receive(sk, &zc, &tss);
                err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
                                                          &zc, &len, err);
                release_sock(sk);
  [...]

We've added 116 non-merge commits during the last 27 day(s) which contain
a total of 156 files changed, 5662 insertions(+), 1489 deletions(-).

The main changes are:

1) Adds support of pointers to types with known size among global function
   args to overcome the limit on max # of allowed args, from Dmitrii Banshchikov.

2) Add bpf_iter for task_vma which can be used to generate information similar
   to /proc/pid/maps, from Song Liu.

3) Enable bpf_{g,s}etsockopt() from all sock_addr related program hooks. Allow
   rewriting bind user ports from BPF side below the ip_unprivileged_port_start
   range, both from Stanislav Fomichev.

4) Prevent recursion on fentry/fexit & sleepable programs and allow map-in-map
   as well as per-cpu maps for the latter, from Alexei Starovoitov.

5) Add selftest script to run BPF CI locally. Also enable BPF ringbuffer
   for sleepable programs, both from KP Singh.

6) Extend verifier to enable variable offset read/write access to the BPF
   program stack, from Andrei Matei.

7) Improve tc & XDP MTU handling and add a new bpf_check_mtu() helper to
   query device MTU from programs, from Jesper Dangaard Brouer.

8) Allow bpf_get_socket_cookie() helper also be called from [sleepable] BPF
   tracing programs, from Florent Revest.

9) Extend x86 JIT to pad JMPs with NOPs for helping image to converge when
   otherwise too many passes are required, from Gary Lin.

10) Verifier fixes on atomics with BPF_FETCH as well as function-by-function
    verification both related to zero-extension handling, from Ilya Leoshkevich.

11) Better kernel build integration of resolve_btfids tool, from Jiri Olsa.

12) Batch of AF_XDP selftest cleanups and small performance improvement
    for libbpf's xsk map redirect for newer kernels, from Björn Töpel.

13) Follow-up BPF doc and verifier improvements around atomics with
    BPF_FETCH, from Brendan Jackman.

14) Permit zero-sized data sections e.g. if ELF .rodata section contains
    read-only data from local variables, from Yonghong Song.

15) veth driver skb bulk-allocation for ndo_xdp_xmit, from Lorenzo Bianconi.
====================

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

kernel/bpf/bpf_iter.c

@@ -287,7 +287,7 @@ int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info)
 {
 	struct bpf_iter_target_info *tinfo;
 
-	tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
+	tinfo = kzalloc(sizeof(*tinfo), GFP_KERNEL);
 	if (!tinfo)
 		return -ENOMEM;
 

kernel/bpf/bpf_lru_list.c

@@ -502,13 +502,14 @@ struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash)
 static void bpf_common_lru_push_free(struct bpf_lru *lru,
 				     struct bpf_lru_node *node)
 {
+	u8 node_type = READ_ONCE(node->type);
 	unsigned long flags;
 
-	if (WARN_ON_ONCE(node->type == BPF_LRU_LIST_T_FREE) ||
-	    WARN_ON_ONCE(node->type == BPF_LRU_LOCAL_LIST_T_FREE))
+	if (WARN_ON_ONCE(node_type == BPF_LRU_LIST_T_FREE) ||
+	    WARN_ON_ONCE(node_type == BPF_LRU_LOCAL_LIST_T_FREE))
 		return;
 
-	if (node->type == BPF_LRU_LOCAL_LIST_T_PENDING) {
+	if (node_type == BPF_LRU_LOCAL_LIST_T_PENDING) {
 		struct bpf_lru_locallist *loc_l;
 
 		loc_l = per_cpu_ptr(lru->common_lru.local_list, node->cpu);

kernel/bpf/btf.c

@@ -3540,11 +3540,6 @@ static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	if (!btf_type_vlen(t)) {
-		btf_verifier_log_type(env, t, "vlen == 0");
-		return -EINVAL;
-	}
-
 	if (!t->size) {
 		btf_verifier_log_type(env, t, "size == 0");
 		return -EINVAL;
@@ -5296,15 +5291,16 @@ int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *pr
  * Only PTR_TO_CTX and SCALAR_VALUE states are recognized.
  */
 int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
-			     struct bpf_reg_state *reg)
+			     struct bpf_reg_state *regs)
 {
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
 	struct btf *btf = prog->aux->btf;
 	const struct btf_param *args;
-	const struct btf_type *t;
-	u32 i, nargs, btf_id;
+	const struct btf_type *t, *ref_t;
+	u32 i, nargs, btf_id, type_size;
 	const char *tname;
+	bool is_global;
 
 	if (!prog->aux->func_info)
 		return -EINVAL;
@@ -5338,38 +5334,57 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
 		bpf_log(log, "Function %s has %d > 5 args\n", tname, nargs);
 		goto out;
 	}
+
+	is_global = prog->aux->func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
 	/* check that BTF function arguments match actual types that the
 	 * verifier sees.
 	 */
 	for (i = 0; i < nargs; i++) {
+		struct bpf_reg_state *reg = &regs[i + 1];
+
 		t = btf_type_by_id(btf, args[i].type);
 		while (btf_type_is_modifier(t))
 			t = btf_type_by_id(btf, t->type);
 		if (btf_type_is_int(t) || btf_type_is_enum(t)) {
-			if (reg[i + 1].type == SCALAR_VALUE)
+			if (reg->type == SCALAR_VALUE)
 				continue;
 			bpf_log(log, "R%d is not a scalar\n", i + 1);
 			goto out;
 		}
 		if (btf_type_is_ptr(t)) {
-			if (reg[i + 1].type == SCALAR_VALUE) {
-				bpf_log(log, "R%d is not a pointer\n", i + 1);
-				goto out;
-			}
 			/* If function expects ctx type in BTF check that caller
 			 * is passing PTR_TO_CTX.
 			 */
 			if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) {
-				if (reg[i + 1].type != PTR_TO_CTX) {
+				if (reg->type != PTR_TO_CTX) {
 					bpf_log(log,
 						"arg#%d expected pointer to ctx, but got %s\n",
 						i, btf_kind_str[BTF_INFO_KIND(t->info)]);
 					goto out;
 				}
-				if (check_ctx_reg(env, &reg[i + 1], i + 1))
+				if (check_ctx_reg(env, reg, i + 1))
 					goto out;
 				continue;
 			}
+
+			if (!is_global)
+				goto out;
+
+			t = btf_type_skip_modifiers(btf, t->type, NULL);
+
+			ref_t = btf_resolve_size(btf, t, &type_size);
+			if (IS_ERR(ref_t)) {
+				bpf_log(log,
+				    "arg#%d reference type('%s %s') size cannot be determined: %ld\n",
+				    i, btf_type_str(t), btf_name_by_offset(btf, t->name_off),
+					PTR_ERR(ref_t));
+				goto out;
+			}
+
+			if (check_mem_reg(env, reg, i + 1, type_size))
+				goto out;
+
+			continue;
 		}
 		bpf_log(log, "Unrecognized arg#%d type %s\n",
 			i, btf_kind_str[BTF_INFO_KIND(t->info)]);
@@ -5393,14 +5408,14 @@ out:
  * (either PTR_TO_CTX or SCALAR_VALUE).
  */
 int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg)
+			  struct bpf_reg_state *regs)
 {
 	struct bpf_verifier_log *log = &env->log;
 	struct bpf_prog *prog = env->prog;
 	enum bpf_prog_type prog_type = prog->type;
 	struct btf *btf = prog->aux->btf;
 	const struct btf_param *args;
-	const struct btf_type *t;
+	const struct btf_type *t, *ref_t;
 	u32 i, nargs, btf_id;
 	const char *tname;
 
@@ -5464,16 +5479,35 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
 	 * Only PTR_TO_CTX and SCALAR are supported atm.
 	 */
 	for (i = 0; i < nargs; i++) {
+		struct bpf_reg_state *reg = &regs[i + 1];
+
 		t = btf_type_by_id(btf, args[i].type);
 		while (btf_type_is_modifier(t))
 			t = btf_type_by_id(btf, t->type);
 		if (btf_type_is_int(t) || btf_type_is_enum(t)) {
-			reg[i + 1].type = SCALAR_VALUE;
+			reg->type = SCALAR_VALUE;
 			continue;
 		}
-		if (btf_type_is_ptr(t) &&
-		    btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
-			reg[i + 1].type = PTR_TO_CTX;
+		if (btf_type_is_ptr(t)) {
+			if (btf_get_prog_ctx_type(log, btf, t, prog_type, i)) {
+				reg->type = PTR_TO_CTX;
+				continue;
+			}
+
+			t = btf_type_skip_modifiers(btf, t->type, NULL);
+
+			ref_t = btf_resolve_size(btf, t, &reg->mem_size);
+			if (IS_ERR(ref_t)) {
+				bpf_log(log,
+				    "arg#%d reference type('%s %s') size cannot be determined: %ld\n",
+				    i, btf_type_str(t), btf_name_by_offset(btf, t->name_off),
+					PTR_ERR(ref_t));
+				return -EINVAL;
+			}
+
+			reg->type = PTR_TO_MEM_OR_NULL;
+			reg->id = ++env->id_gen;
+
 			continue;
 		}
 		bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n",

kernel/bpf/cgroup.c

@@ -19,7 +19,7 @@
 
 #include "../cgroup/cgroup-internal.h"
 
-DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key);
+DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_BPF_ATTACH_TYPE);
 EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 
 void cgroup_bpf_offline(struct cgroup *cgrp)
@@ -128,7 +128,7 @@ static void cgroup_bpf_release(struct work_struct *work)
 			if (pl->link)
 				bpf_cgroup_link_auto_detach(pl->link);
 			kfree(pl);
-			static_branch_dec(&cgroup_bpf_enabled_key);
+			static_branch_dec(&cgroup_bpf_enabled_key[type]);
 		}
 		old_array = rcu_dereference_protected(
 				cgrp->bpf.effective[type],
@@ -499,7 +499,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 	else
-		static_branch_inc(&cgroup_bpf_enabled_key);
+		static_branch_inc(&cgroup_bpf_enabled_key[type]);
 	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
 
@@ -698,7 +698,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		cgrp->bpf.flags[type] = 0;
 	if (old_prog)
 		bpf_prog_put(old_prog);
-	static_branch_dec(&cgroup_bpf_enabled_key);
+	static_branch_dec(&cgroup_bpf_enabled_key[type]);
 	return 0;
 
 cleanup:
@@ -1055,6 +1055,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  * @uaddr: sockaddr struct provided by user
  * @type: The type of program to be exectuted
  * @t_ctx: Pointer to attach type specific context
+ * @flags: Pointer to u32 which contains higher bits of BPF program
+ *         return value (OR'ed together).
  *
  * socket is expected to be of type INET or INET6.
  *
@@ -1064,7 +1066,8 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
 int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 				      struct sockaddr *uaddr,
 				      enum bpf_attach_type type,
-				      void *t_ctx)
+				      void *t_ctx,
+				      u32 *flags)
 {
 	struct bpf_sock_addr_kern ctx = {
 		.sk = sk,
@@ -1087,7 +1090,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
 	}
 
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN);
+	ret = BPF_PROG_RUN_ARRAY_FLAGS(cgrp->bpf.effective[type], &ctx,
+				       BPF_PROG_RUN, flags);
 
 	return ret == 1 ? 0 : -EPERM;
 }
@@ -1298,7 +1302,8 @@ static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp,
 	return empty;
 }
 
-static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
+static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen,
+			     struct bpf_sockopt_buf *buf)
 {
 	if (unlikely(max_optlen < 0))
 		return -EINVAL;
@@ -1310,6 +1315,15 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 		max_optlen = PAGE_SIZE;
 	}
 
+	if (max_optlen <= sizeof(buf->data)) {
+		/* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE
+		 * bytes avoid the cost of kzalloc.
+		 */
+		ctx->optval = buf->data;
+		ctx->optval_end = ctx->optval + max_optlen;
+		return max_optlen;
+	}
+
 	ctx->optval = kzalloc(max_optlen, GFP_USER);
 	if (!ctx->optval)
 		return -ENOMEM;
@@ -1319,16 +1333,26 @@ static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen)
 	return max_optlen;
 }
 
-static void sockopt_free_buf(struct bpf_sockopt_kern *ctx)
+static void sockopt_free_buf(struct bpf_sockopt_kern *ctx,
+			     struct bpf_sockopt_buf *buf)
 {
+	if (ctx->optval == buf->data)
+		return;
 	kfree(ctx->optval);
 }
 
+static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx,
+				  struct bpf_sockopt_buf *buf)
+{
+	return ctx->optval != buf->data;
+}
+
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 				       int *optname, char __user *optval,
 				       int *optlen, char **kernel_optval)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_buf buf = {};
 	struct bpf_sockopt_kern ctx = {
 		.sk = sk,
 		.level = *level,
@@ -1340,8 +1364,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 * attached to the hook so we don't waste time allocating
 	 * memory and locking the socket.
 	 */
-	if (!cgroup_bpf_enabled ||
-	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
+	if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT))
 		return 0;
 
 	/* Allocate a bit more than the initial user buffer for
@@ -1350,7 +1373,7 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 	 */
 	max_optlen = max_t(int, 16, *optlen);
 
-	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
 	if (max_optlen < 0)
 		return max_optlen;
 
@@ -1390,14 +1413,31 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		 */
 		if (ctx.optlen != 0) {
 			*optlen = ctx.optlen;
-			*kernel_optval = ctx.optval;
+			/* We've used bpf_sockopt_kern->buf as an intermediary
+			 * storage, but the BPF program indicates that we need
+			 * to pass this data to the kernel setsockopt handler.
+			 * No way to export on-stack buf, have to allocate a
+			 * new buffer.
+			 */
+			if (!sockopt_buf_allocated(&ctx, &buf)) {
+				void *p = kmalloc(ctx.optlen, GFP_USER);
+
+				if (!p) {
+					ret = -ENOMEM;
+					goto out;
+				}
+				memcpy(p, ctx.optval, ctx.optlen);
+				*kernel_optval = p;
+			} else {
+				*kernel_optval = ctx.optval;
+			}
 			/* export and don't free sockopt buf */
 			return 0;
 		}
 	}
 
 out:
-	sockopt_free_buf(&ctx);
+	sockopt_free_buf(&ctx, &buf);
 	return ret;
 }
 
@@ -1407,6 +1447,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 				       int retval)
 {
 	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_buf buf = {};
 	struct bpf_sockopt_kern ctx = {
 		.sk = sk,
 		.level = level,
@@ -1419,13 +1460,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	 * attached to the hook so we don't waste time allocating
 	 * memory and locking the socket.
 	 */
-	if (!cgroup_bpf_enabled ||
-	    __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
+	if (__cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT))
 		return retval;
 
 	ctx.optlen = max_optlen;
 
-	max_optlen = sockopt_alloc_buf(&ctx, max_optlen);
+	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
 	if (max_optlen < 0)
 		return max_optlen;
 
@@ -1488,9 +1528,55 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	ret = ctx.retval;
 
 out:
-	sockopt_free_buf(&ctx);
+	sockopt_free_buf(&ctx, &buf);
 	return ret;
 }
+
+int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
+					    int optname, void *optval,
+					    int *optlen, int retval)
+{
+	struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	struct bpf_sockopt_kern ctx = {
+		.sk = sk,
+		.level = level,
+		.optname = optname,
+		.retval = retval,
+		.optlen = *optlen,
+		.optval = optval,
+		.optval_end = optval + *optlen,
+	};
+	int ret;
+
+	/* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy
+	 * user data back into BPF buffer when reval != 0. This is
+	 * done as an optimization to avoid extra copy, assuming
+	 * kernel won't populate the data in case of an error.
+	 * Here we always pass the data and memset() should
+	 * be called if that data shouldn't be "exported".
+	 */
+
+	ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT],
+				 &ctx, BPF_PROG_RUN);
+	if (!ret)
+		return -EPERM;
+
+	if (ctx.optlen > *optlen)
+		return -EFAULT;
+
+	/* BPF programs only allowed to set retval to 0, not some
+	 * arbitrary value.
+	 */
+	if (ctx.retval != 0 && ctx.retval != retval)
+		return -EFAULT;
+
+	/* BPF programs can shrink the buffer, export the modifications.
+	 */
+	if (ctx.optlen != 0)
+		*optlen = ctx.optlen;
+
+	return ctx.retval;
+}
 #endif
 
 static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp,

kernel/bpf/core.c

@@ -91,6 +91,12 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 		vfree(fp);
 		return NULL;
 	}
+	fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags);
+	if (!fp->active) {
+		vfree(fp);
+		kfree(aux);
+		return NULL;
+	}
 
 	fp->pages = size / PAGE_SIZE;
 	fp->aux = aux;
@@ -114,8 +120,9 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	if (!prog)
 		return NULL;
 
-	prog->aux->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
-	if (!prog->aux->stats) {
+	prog->stats = alloc_percpu_gfp(struct bpf_prog_stats, gfp_flags);
+	if (!prog->stats) {
+		free_percpu(prog->active);
 		kfree(prog->aux);
 		vfree(prog);
 		return NULL;
@@ -124,7 +131,7 @@ struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags)
 	for_each_possible_cpu(cpu) {
 		struct bpf_prog_stats *pstats;
 
-		pstats = per_cpu_ptr(prog->aux->stats, cpu);
+		pstats = per_cpu_ptr(prog->stats, cpu);
 		u64_stats_init(&pstats->syncp);
 	}
 	return prog;
@@ -238,6 +245,8 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
 		 * reallocated structure.
 		 */
 		fp_old->aux = NULL;
+		fp_old->stats = NULL;
+		fp_old->active = NULL;
 		__bpf_prog_free(fp_old);
 	}
 
@@ -249,10 +258,11 @@ void __bpf_prog_free(struct bpf_prog *fp)
 	if (fp->aux) {
 		mutex_destroy(&fp->aux->used_maps_mutex);
 		mutex_destroy(&fp->aux->dst_mutex);
-		free_percpu(fp->aux->stats);
 		kfree(fp->aux->poke_tab);
 		kfree(fp->aux);
 	}
+	free_percpu(fp->stats);
+	free_percpu(fp->active);
 	vfree(fp);
 }
 

kernel/bpf/cpumap.c

@@ -141,49 +141,6 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 	kthread_stop(rcpu->kthread);
 }
 
-static struct sk_buff *cpu_map_build_skb(struct xdp_frame *xdpf,
-					 struct sk_buff *skb)
-{
-	unsigned int hard_start_headroom;
-	unsigned int frame_size;
-	void *pkt_data_start;
-
-	/* Part of headroom was reserved to xdpf */
-	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
-
-	/* Memory size backing xdp_frame data already have reserved
-	 * room for build_skb to place skb_shared_info in tailroom.
-	 */
-	frame_size = xdpf->frame_sz;
-
-	pkt_data_start = xdpf->data - hard_start_headroom;
-	skb = build_skb_around(skb, pkt_data_start, frame_size);
-	if (unlikely(!skb))
-		return NULL;
-
-	skb_reserve(skb, hard_start_headroom);
-	__skb_put(skb, xdpf->len);
-	if (xdpf->metasize)
-		skb_metadata_set(skb, xdpf->metasize);
-
-	/* Essential SKB info: protocol and skb->dev */
-	skb->protocol = eth_type_trans(skb, xdpf->dev_rx);
-
-	/* Optional SKB info, currently missing:
-	 * - HW checksum info		(skb->ip_summed)
-	 * - HW RX hash			(skb_set_hash)
-	 * - RX ring dev queue index	(skb_record_rx_queue)
-	 */
-
-	/* Until page_pool get SKB return path, release DMA here */
-	xdp_release_frame(xdpf);
-
-	/* Allow SKB to reuse area used by xdp_frame */
-	xdp_scrub_frame(xdpf);
-
-	return skb;
-}
-
 static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 {
 	/* The tear-down procedure should have made sure that queue is
@@ -350,7 +307,8 @@ static int cpu_map_kthread_run(void *data)
 			struct sk_buff *skb = skbs[i];
 			int ret;
 
-			skb = cpu_map_build_skb(xdpf, skb);
+			skb = __xdp_build_skb_from_frame(xdpf, skb,
+							 xdpf->dev_rx);
 			if (!skb) {
 				xdp_return_frame(xdpf);
 				continue;

kernel/bpf/devmap.c

@@ -802,9 +802,7 @@ static int dev_map_notification(struct notifier_block *notifier,
 			break;
 
 		/* will be freed in free_netdev() */
-		netdev->xdp_bulkq =
-			__alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue),
-					   sizeof(void *), GFP_ATOMIC);
+		netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue);
 		if (!netdev->xdp_bulkq)
 			return NOTIFY_BAD;
 

kernel/bpf/disasm.c

@@ -161,7 +161,7 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 				insn->dst_reg,
 				insn->off, insn->src_reg);
 		else if (BPF_MODE(insn->code) == BPF_ATOMIC &&
-			 (insn->imm == BPF_ADD || insn->imm == BPF_ADD ||
+			 (insn->imm == BPF_ADD || insn->imm == BPF_AND ||
 			  insn->imm == BPF_OR || insn->imm == BPF_XOR)) {
 			verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) %s r%d\n",
 				insn->code,

kernel/bpf/hashtab.c

@@ -1148,7 +1148,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 
@@ -1202,7 +1202,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key,
 		/* unknown flags */
 		return -EINVAL;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_trace_held());
 
 	key_size = map->key_size;
 

kernel/bpf/helpers.c

@@ -720,14 +720,6 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_spin_lock_proto;
 	case BPF_FUNC_spin_unlock:
 		return &bpf_spin_unlock_proto;
-	case BPF_FUNC_trace_printk:
-		if (!perfmon_capable())
-			return NULL;
-		return bpf_get_trace_printk_proto();
-	case BPF_FUNC_snprintf_btf:
-		if (!perfmon_capable())
-			return NULL;
-		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	case BPF_FUNC_per_cpu_ptr:
@@ -742,6 +734,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return NULL;
 
 	switch (func_id) {
+	case BPF_FUNC_trace_printk:
+		return bpf_get_trace_printk_proto();
 	case BPF_FUNC_get_current_task:
 		return &bpf_get_current_task_proto;
 	case BPF_FUNC_probe_read_user:
@@ -752,6 +746,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_probe_read_user_str_proto;
 	case BPF_FUNC_probe_read_kernel_str:
 		return &bpf_probe_read_kernel_str_proto;
+	case BPF_FUNC_snprintf_btf:
+		return &bpf_snprintf_btf_proto;
 	default:
 		return NULL;
 	}

kernel/bpf/syscall.c

@@ -1731,25 +1731,28 @@ static int bpf_prog_release(struct inode *inode, struct file *filp)
 static void bpf_prog_get_stats(const struct bpf_prog *prog,
 			       struct bpf_prog_stats *stats)
 {
-	u64 nsecs = 0, cnt = 0;
+	u64 nsecs = 0, cnt = 0, misses = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
 		const struct bpf_prog_stats *st;
 		unsigned int start;
-		u64 tnsecs, tcnt;
+		u64 tnsecs, tcnt, tmisses;
 
-		st = per_cpu_ptr(prog->aux->stats, cpu);
+		st = per_cpu_ptr(prog->stats, cpu);
 		do {
 			start = u64_stats_fetch_begin_irq(&st->syncp);
 			tnsecs = st->nsecs;
 			tcnt = st->cnt;
+			tmisses = st->misses;
 		} while (u64_stats_fetch_retry_irq(&st->syncp, start));
 		nsecs += tnsecs;
 		cnt += tcnt;
+		misses += tmisses;
 	}
 	stats->nsecs = nsecs;
 	stats->cnt = cnt;
+	stats->misses = misses;
 }
 
 #ifdef CONFIG_PROC_FS
@@ -1768,14 +1771,16 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "memlock:\t%llu\n"
 		   "prog_id:\t%u\n"
 		   "run_time_ns:\t%llu\n"
-		   "run_cnt:\t%llu\n",
+		   "run_cnt:\t%llu\n"
+		   "recursion_misses:\t%llu\n",
 		   prog->type,
 		   prog->jited,
 		   prog_tag,
 		   prog->pages * 1ULL << PAGE_SHIFT,
 		   prog->aux->id,
 		   stats.nsecs,
-		   stats.cnt);
+		   stats.cnt,
+		   stats.misses);
 }
 #endif
 
@@ -3438,6 +3443,7 @@ static int bpf_prog_get_info_by_fd(struct file *file,
 	bpf_prog_get_stats(prog, &stats);
 	info.run_time_ns = stats.nsecs;
 	info.run_cnt = stats.cnt;
+	info.recursion_misses = stats.misses;
 
 	if (!bpf_capable()) {
 		info.jited_prog_len = 0;

kernel/bpf/task_iter.c

@@ -286,9 +286,248 @@ static const struct seq_operations task_file_seq_ops = {
 	.show	= task_file_seq_show,
 };
 
+struct bpf_iter_seq_task_vma_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	struct task_struct *task;
+	struct vm_area_struct *vma;
+	u32 tid;
+	unsigned long prev_vm_start;
+	unsigned long prev_vm_end;
+};
+
+enum bpf_task_vma_iter_find_op {
+	task_vma_iter_first_vma,   /* use mm->mmap */
+	task_vma_iter_next_vma,    /* use curr_vma->vm_next */
+	task_vma_iter_find_vma,    /* use find_vma() to find next vma */
+};
+
+static struct vm_area_struct *
+task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
+{
+	struct pid_namespace *ns = info->common.ns;
+	enum bpf_task_vma_iter_find_op op;
+	struct vm_area_struct *curr_vma;
+	struct task_struct *curr_task;
+	u32 curr_tid = info->tid;
+
+	/* If this function returns a non-NULL vma, it holds a reference to
+	 * the task_struct, and holds read lock on vma->mm->mmap_lock.
+	 * If this function returns NULL, it does not hold any reference or
+	 * lock.
+	 */
+	if (info->task) {
+		curr_task = info->task;
+		curr_vma = info->vma;
+		/* In case of lock contention, drop mmap_lock to unblock
+		 * the writer.
+		 *
+		 * After relock, call find(mm, prev_vm_end - 1) to find
+		 * new vma to process.
+		 *
+		 *   +------+------+-----------+
+		 *   | VMA1 | VMA2 | VMA3      |
+		 *   +------+------+-----------+
+		 *   |      |      |           |
+		 *  4k     8k     16k         400k
+		 *
+		 * For example, curr_vma == VMA2. Before unlock, we set
+		 *
+		 *    prev_vm_start = 8k
+		 *    prev_vm_end   = 16k
+		 *
+		 * There are a few cases:
+		 *
+		 * 1) VMA2 is freed, but VMA3 exists.
+		 *
+		 *    find_vma() will return VMA3, just process VMA3.
+		 *
+		 * 2) VMA2 still exists.
+		 *
+		 *    find_vma() will return VMA2, process VMA2->next.
+		 *
+		 * 3) no more vma in this mm.
+		 *
+		 *    Process the next task.
+		 *
+		 * 4) find_vma() returns a different vma, VMA2'.
+		 *
+		 *    4.1) If VMA2 covers same range as VMA2', skip VMA2',
+		 *         because we already covered the range;
+		 *    4.2) VMA2 and VMA2' covers different ranges, process
+		 *         VMA2'.
+		 */
+		if (mmap_lock_is_contended(curr_task->mm)) {
+			info->prev_vm_start = curr_vma->vm_start;
+			info->prev_vm_end = curr_vma->vm_end;
+			op = task_vma_iter_find_vma;
+			mmap_read_unlock(curr_task->mm);
+			if (mmap_read_lock_killable(curr_task->mm))
+				goto finish;
+		} else {
+			op = task_vma_iter_next_vma;
+		}
+	} else {
+again:
+		curr_task = task_seq_get_next(ns, &curr_tid, true);
+		if (!curr_task) {
+			info->tid = curr_tid + 1;
+			goto finish;
+		}
+
+		if (curr_tid != info->tid) {
+			info->tid = curr_tid;
+			/* new task, process the first vma */
+			op = task_vma_iter_first_vma;
+		} else {
+			/* Found the same tid, which means the user space
+			 * finished data in previous buffer and read more.
+			 * We dropped mmap_lock before returning to user
+			 * space, so it is necessary to use find_vma() to
+			 * find the next vma to process.
+			 */
+			op = task_vma_iter_find_vma;
+		}
+
+		if (!curr_task->mm)
+			goto next_task;
+
+		if (mmap_read_lock_killable(curr_task->mm))
+			goto finish;
+	}
+
+	switch (op) {
+	case task_vma_iter_first_vma:
+		curr_vma = curr_task->mm->mmap;
+		break;
+	case task_vma_iter_next_vma:
+		curr_vma = curr_vma->vm_next;
+		break;
+	case task_vma_iter_find_vma:
+		/* We dropped mmap_lock so it is necessary to use find_vma
+		 * to find the next vma. This is similar to the  mechanism
+		 * in show_smaps_rollup().
+		 */
+		curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+		/* case 1) and 4.2) above just use curr_vma */
+
+		/* check for case 2) or case 4.1) above */
+		if (curr_vma &&
+		    curr_vma->vm_start == info->prev_vm_start &&
+		    curr_vma->vm_end == info->prev_vm_end)
+			curr_vma = curr_vma->vm_next;
+		break;
+	}
+	if (!curr_vma) {
+		/* case 3) above, or case 2) 4.1) with vma->next == NULL */
+		mmap_read_unlock(curr_task->mm);
+		goto next_task;
+	}
+	info->task = curr_task;
+	info->vma = curr_vma;
+	return curr_vma;
+
+next_task:
+	put_task_struct(curr_task);
+	info->task = NULL;
+	curr_tid++;
+	goto again;
+
+finish:
+	if (curr_task)
+		put_task_struct(curr_task);
+	info->task = NULL;
+	info->vma = NULL;
+	return NULL;
+}
+
+static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+	struct vm_area_struct *vma;
+
+	vma = task_vma_seq_get_next(info);
+	if (vma && *pos == 0)
+		++*pos;
+
+	return vma;
+}
+
+static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+
+	++*pos;
+	return task_vma_seq_get_next(info);
+}
+
+struct bpf_iter__task_vma {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+	__bpf_md_ptr(struct vm_area_struct *, vma);
+};
+
+DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta,
+		     struct task_struct *task, struct vm_area_struct *vma)
+
+static int __task_vma_seq_show(struct seq_file *seq, bool in_stop)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+	struct bpf_iter__task_vma ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.task = info->task;
+	ctx.vma = info->vma;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_vma_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_vma_seq_show(seq, false);
+}
+
+static void task_vma_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+
+	if (!v) {
+		(void)__task_vma_seq_show(seq, true);
+	} else {
+		/* info->vma has not been seen by the BPF program. If the
+		 * user space reads more, task_vma_seq_get_next should
+		 * return this vma again. Set prev_vm_start to ~0UL,
+		 * so that we don't skip the vma returned by the next
+		 * find_vma() (case task_vma_iter_find_vma in
+		 * task_vma_seq_get_next()).
+		 */
+		info->prev_vm_start = ~0UL;
+		info->prev_vm_end = info->vma->vm_end;
+		mmap_read_unlock(info->task->mm);
+		put_task_struct(info->task);
+		info->task = NULL;
+	}
+}
+
+static const struct seq_operations task_vma_seq_ops = {
+	.start	= task_vma_seq_start,
+	.next	= task_vma_seq_next,
+	.stop	= task_vma_seq_stop,
+	.show	= task_vma_seq_show,
+};
+
 BTF_ID_LIST(btf_task_file_ids)
 BTF_ID(struct, task_struct)
 BTF_ID(struct, file)
+BTF_ID(struct, vm_area_struct)
 
 static const struct bpf_iter_seq_info task_seq_info = {
 	.seq_ops		= &task_seq_ops,
@@ -328,6 +567,26 @@ static struct bpf_iter_reg task_file_reg_info = {
 	.seq_info		= &task_file_seq_info,
 };
 
+static const struct bpf_iter_seq_info task_vma_seq_info = {
+	.seq_ops		= &task_vma_seq_ops,
+	.init_seq_private	= init_seq_pidns,
+	.fini_seq_private	= fini_seq_pidns,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_vma_info),
+};
+
+static struct bpf_iter_reg task_vma_reg_info = {
+	.target			= "task_vma",
+	.feature		= BPF_ITER_RESCHED,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__task_vma, task),
+		  PTR_TO_BTF_ID_OR_NULL },
+		{ offsetof(struct bpf_iter__task_vma, vma),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &task_vma_seq_info,
+};
+
 static int __init task_iter_init(void)
 {
 	int ret;
@@ -339,6 +598,12 @@ static int __init task_iter_init(void)
 
 	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
 	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
-	return bpf_iter_reg_target(&task_file_reg_info);
+	ret =  bpf_iter_reg_target(&task_file_reg_info);
+	if (ret)
+		return ret;
+
+	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
+	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[2];
+	return bpf_iter_reg_target(&task_vma_reg_info);
 }
 late_initcall(task_iter_init);

kernel/bpf/trampoline.c

@@ -381,55 +381,100 @@ out:
 	mutex_unlock(&trampoline_mutex);
 }
 
-/* The logic is similar to BPF_PROG_RUN, but with an explicit
- * rcu_read_lock() and migrate_disable() which are required
- * for the trampoline. The macro is split into
- * call _bpf_prog_enter
- * call prog->bpf_func
- * call __bpf_prog_exit
- */
-u64 notrace __bpf_prog_enter(void)
-	__acquires(RCU)
+#define NO_START_TIME 1
+static u64 notrace bpf_prog_start_time(void)
 {
-	u64 start = 0;
+	u64 start = NO_START_TIME;
 
-	rcu_read_lock();
-	migrate_disable();
-	if (static_branch_unlikely(&bpf_stats_enabled_key))
+	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
 		start = sched_clock();
+		if (unlikely(!start))
+			start = NO_START_TIME;
+	}
 	return start;
 }
 
-void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
-	__releases(RCU)
+static void notrace inc_misses_counter(struct bpf_prog *prog)
+{
+	struct bpf_prog_stats *stats;
+
+	stats = this_cpu_ptr(prog->stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->misses++;
+	u64_stats_update_end(&stats->syncp);
+}
+
+/* The logic is similar to BPF_PROG_RUN, but with an explicit
+ * rcu_read_lock() and migrate_disable() which are required
+ * for the trampoline. The macro is split into
+ * call __bpf_prog_enter
+ * call prog->bpf_func
+ * call __bpf_prog_exit
+ *
+ * __bpf_prog_enter returns:
+ * 0 - skip execution of the bpf prog
+ * 1 - execute bpf prog
+ * [2..MAX_U64] - excute bpf prog and record execution time.
+ *     This is start time.
+ */
+u64 notrace __bpf_prog_enter(struct bpf_prog *prog)
+	__acquires(RCU)
+{
+	rcu_read_lock();
+	migrate_disable();
+	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
+		inc_misses_counter(prog);
+		return 0;
+	}
+	return bpf_prog_start_time();
+}
+
+static void notrace update_prog_stats(struct bpf_prog *prog,
+				      u64 start)
 {
 	struct bpf_prog_stats *stats;
 
 	if (static_branch_unlikely(&bpf_stats_enabled_key) &&
-	    /* static_key could be enabled in __bpf_prog_enter
-	     * and disabled in __bpf_prog_exit.
+	    /* static_key could be enabled in __bpf_prog_enter*
+	     * and disabled in __bpf_prog_exit*.
 	     * And vice versa.
-	     * Hence check that 'start' is not zero.
+	     * Hence check that 'start' is valid.
 	     */
-	    start) {
-		stats = this_cpu_ptr(prog->aux->stats);
+	    start > NO_START_TIME) {
+		stats = this_cpu_ptr(prog->stats);
 		u64_stats_update_begin(&stats->syncp);
 		stats->cnt++;
 		stats->nsecs += sched_clock() - start;
 		u64_stats_update_end(&stats->syncp);
 	}
+}
+
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start)
+	__releases(RCU)
+{
+	update_prog_stats(prog, start);
+	__this_cpu_dec(*(prog->active));
 	migrate_enable();
 	rcu_read_unlock();
 }
 
-void notrace __bpf_prog_enter_sleepable(void)
+u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog)
 {
 	rcu_read_lock_trace();
+	migrate_disable();
 	might_fault();
+	if (unlikely(__this_cpu_inc_return(*(prog->active)) != 1)) {
+		inc_misses_counter(prog);
+		return 0;
+	}
+	return bpf_prog_start_time();
 }
 
-void notrace __bpf_prog_exit_sleepable(void)
+void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start)
 {
+	update_prog_stats(prog, start);
+	__this_cpu_dec(*(prog->active));
+	migrate_enable();
 	rcu_read_unlock_trace();
 }