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

Alexei Starovoitov says:

====================
pull-request: bpf 2020-08-21

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

We've added 11 non-merge commits during the last 5 day(s) which contain
a total of 12 files changed, 78 insertions(+), 24 deletions(-).

The main changes are:

1) three fixes in BPF task iterator logic, from Yonghong.

2) fix for compressed dwarf sections in vmlinux, from Jiri.

3) fix xdp attach regression, from Andrii.
====================

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

Author: davem330

include/uapi/linux/bpf.h

@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.

kernel/bpf/bpf_iter.c

@@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq)
 	iter_priv->done_stop = true;
 }
 
+/* maximum visited objects before bailing out */
+#define MAX_ITER_OBJECTS	1000000
+
 /* bpf_seq_read, a customized and simpler version for bpf iterator.
  * no_llseek is assumed for this file.
  * The following are differences from seq_read():
@@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 {
 	struct seq_file *seq = file->private_data;
 	size_t n, offs, copied = 0;
-	int err = 0;
+	int err = 0, num_objs = 0;
 	void *p;
 
 	mutex_lock(&seq->lock);
@@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 	while (1) {
 		loff_t pos = seq->index;
 
+		num_objs++;
 		offs = seq->count;
 		p = seq->op->next(seq, p, &seq->index);
 		if (pos == seq->index) {
@@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size,
 		if (seq->count >= size)
 			break;
 
+		if (num_objs >= MAX_ITER_OBJECTS) {
+			if (offs == 0) {
+				err = -EAGAIN;
+				seq->op->stop(seq, p);
+				goto done;
+			}
+			break;
+		}
+
 		err = seq->op->show(seq, p);
 		if (err > 0) {
 			bpf_iter_dec_seq_num(seq);

kernel/bpf/task_iter.c

@@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns,
 
 	rcu_read_lock();
 retry:
-	pid = idr_get_next(&ns->idr, tid);
+	pid = find_ge_pid(*tid, ns);
 	if (pid) {
+		*tid = pid_nr_ns(pid, ns);
 		task = get_pid_task(pid, PIDTYPE_PID);
 		if (!task) {
 			++*tid;
@@ -178,10 +179,11 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info,
 		f = fcheck_files(curr_files, curr_fd);
 		if (!f)
 			continue;
+		if (!get_file_rcu(f))
+			continue;
 
 		/* set info->fd */
 		info->fd = curr_fd;
-		get_file(f);
 		rcu_read_unlock();
 		return f;
 	}

net/core/dev.c

@@ -8742,13 +8742,15 @@ struct bpf_xdp_link {
 	int flags;
 };
 
-static enum bpf_xdp_mode dev_xdp_mode(u32 flags)
+static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags)
 {
 	if (flags & XDP_FLAGS_HW_MODE)
 		return XDP_MODE_HW;
 	if (flags & XDP_FLAGS_DRV_MODE)
 		return XDP_MODE_DRV;
-	return XDP_MODE_SKB;
+	if (flags & XDP_FLAGS_SKB_MODE)
+		return XDP_MODE_SKB;
+	return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB;
 }
 
 static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
@@ -8896,7 +8898,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EINVAL;
 	}
 
-	mode = dev_xdp_mode(flags);
+	mode = dev_xdp_mode(dev, flags);
 	/* can't replace attached link */
 	if (dev_xdp_link(dev, mode)) {
 		NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link");
@@ -8984,7 +8986,7 @@ static int dev_xdp_detach_link(struct net_device *dev,
 
 	ASSERT_RTNL();
 
-	mode = dev_xdp_mode(link->flags);
+	mode = dev_xdp_mode(dev, link->flags);
 	if (dev_xdp_link(dev, mode) != link)
 		return -EINVAL;
 
@@ -9080,7 +9082,7 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 		goto out_unlock;
 	}
 
-	mode = dev_xdp_mode(xdp_link->flags);
+	mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags);
 	bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode);
 	err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL,
 			      xdp_link->flags, new_prog);
@@ -9164,7 +9166,7 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags)
 {
-	enum bpf_xdp_mode mode = dev_xdp_mode(flags);
+	enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags);
 	struct bpf_prog *new_prog = NULL, *old_prog = NULL;
 	int err;
 

tools/bpf/bpftool/pids.c

@@ -134,6 +134,8 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 	while (true) {
 		ret = read(fd, buf, sizeof(buf));
 		if (ret < 0) {
+			if (errno == EAGAIN)
+				continue;
 			err = -errno;
 			p_err("failed to read PID iterator output: %d", err);
 			goto out;

tools/bpf/resolve_btfids/main.c

@@ -233,6 +233,39 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size)
 	return btf_id__add(root, id, false);
 }
 
+/*
+ * The data of compressed section should be aligned to 4
+ * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld
+ * sets sh_addralign to 1, which makes libelf fail with
+ * misaligned section error during the update:
+ *    FAILED elf_update(WRITE): invalid section alignment
+ *
+ * While waiting for ld fix, we fix the compressed sections
+ * sh_addralign value manualy.
+ */
+static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh)
+{
+	int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8;
+
+	if (!(sh->sh_flags & SHF_COMPRESSED))
+		return 0;
+
+	if (sh->sh_addralign == expected)
+		return 0;
+
+	pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n",
+		  sh->sh_addralign, expected);
+
+	sh->sh_addralign = expected;
+
+	if (gelf_update_shdr(scn, sh) == 0) {
+		printf("FAILED cannot update section header: %s\n",
+			elf_errmsg(-1));
+		return -1;
+	}
+	return 0;
+}
+
 static int elf_collect(struct object *obj)
 {
 	Elf_Scn *scn = NULL;
@@ -309,6 +342,9 @@ static int elf_collect(struct object *obj)
 			obj->efile.idlist_shndx = idx;
 			obj->efile.idlist_addr  = sh.sh_addr;
 		}
+
+		if (compressed_section_fix(elf, scn, &sh))
+			return -1;
 	}
 
 	return 0;

tools/include/uapi/linux/bpf.h

@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.

tools/lib/bpf/btf_dump.c

@@ -879,7 +879,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d,
 			btf_dump_printf(d, ": %d", m_sz);
 			off = m_off + m_sz;
 		} else {
-			m_sz = max(0LL, btf__resolve_size(d->btf, m->type));
+			m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type));
 			off = m_off + m_sz * 8;
 		}
 		btf_dump_printf(d, ";");

tools/lib/bpf/libbpf.c

@@ -2264,7 +2264,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		data = elf_getdata(scn, NULL);
 	if (!scn || !data) {
 		pr_warn("failed to get Elf_Data from map section %d (%s)\n",
-			obj->efile.maps_shndx, MAPS_ELF_SEC);
+			obj->efile.btf_maps_shndx, MAPS_ELF_SEC);
 		return -EINVAL;
 	}
 

tools/testing/selftests/bpf/.gitignore

@@ -6,7 +6,6 @@ test_lpm_map
 test_tag
 FEATURE-DUMP.libbpf
 fixdep
-test_align
 test_dev_cgroup
 /test_progs*
 test_tcpbpf_user