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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-08-04

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

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 135 files changed, 4603 insertions(+), 1013 deletions(-).

The main changes are:

1) Implement bpf_link support for XDP. Also add LINK_DETACH operation for the BPF
   syscall allowing processes with BPF link FD to force-detach, from Andrii Nakryiko.

2) Add BPF iterator for map elements and to iterate all BPF programs for efficient
   in-kernel inspection, from Yonghong Song and Alexei Starovoitov.

3) Separate bpf_get_{stack,stackid}() helpers for perf events in BPF to avoid
   unwinder errors, from Song Liu.

4) Allow cgroup local storage map to be shared between programs on the same
   cgroup. Also extend BPF selftests with coverage, from YiFei Zhu.

5) Add BPF exception tables to ARM64 JIT in order to be able to JIT BPF_PROBE_MEM
   load instructions, from Jean-Philippe Brucker.

6) Follow-up fixes on BPF socket lookup in combination with reuseport group
   handling. Also add related BPF selftests, from Jakub Sitnicki.

7) Allow to use socket storage in BPF_PROG_TYPE_CGROUP_SOCK-typed programs for
   socket create/release as well as bind functions, from Stanislav Fomichev.

8) Fix an info leak in xsk_getsockopt() when retrieving XDP stats via old struct
   xdp_statistics, from Peilin Ye.

9) Fix PT_REGS_RC{,_CORE}() macros in libbpf for MIPS arch, from Jerry Crunchtime.

10) Extend BPF kernel test infra with skb->family and skb->{local,remote}_ip{4,6}
    fields and allow user space to specify skb->dev via ifindex, from Dmitry Yakunin.

11) Fix a bpftool segfault due to missing program type name and make it more robust
    to prevent them in future gaps, from Quentin Monnet.

12) Consolidate cgroup helper functions across selftests and fix a v6 localhost
    resolver issue, from John Fastabend.
====================

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

1 files changed, 53 insertions, 29 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac53102e244a..83ff127ef7ae 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -37,17 +37,34 @@ static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[])
 }
 
 static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[],
-				     struct bpf_prog *prog)
+				     struct bpf_cgroup_storage *new_storages[],
+				     enum bpf_attach_type type,
+				     struct bpf_prog *prog,
+				     struct cgroup *cgrp)
 {
 	enum bpf_cgroup_storage_type stype;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_map *map;
+
+	key.cgroup_inode_id = cgroup_id(cgrp);
+	key.attach_type = type;
 
 	for_each_cgroup_storage_type(stype) {
+		map = prog->aux->cgroup_storage[stype];
+		if (!map)
+			continue;
+
+		storages[stype] = cgroup_storage_lookup((void *)map, &key, false);
+		if (storages[stype])
+			continue;
+
 		storages[stype] = bpf_cgroup_storage_alloc(prog, stype);
 		if (IS_ERR(storages[stype])) {
-			storages[stype] = NULL;
-			bpf_cgroup_storages_free(storages);
+			bpf_cgroup_storages_free(new_storages);
 			return -ENOMEM;
 		}
+
+		new_storages[stype] = storages[stype];
 	}
 
 	return 0;
@@ -63,7 +80,7 @@ static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[],
 }
 
 static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
-				     struct cgroup* cgrp,
+				     struct cgroup *cgrp,
 				     enum bpf_attach_type attach_type)
 {
 	enum bpf_cgroup_storage_type stype;
@@ -72,14 +89,6 @@ static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[],
 		bpf_cgroup_storage_link(storages[stype], cgrp, attach_type);
 }
 
-static void bpf_cgroup_storages_unlink(struct bpf_cgroup_storage *storages[])
-{
-	enum bpf_cgroup_storage_type stype;
-
-	for_each_cgroup_storage_type(stype)
-		bpf_cgroup_storage_unlink(storages[stype]);
-}
-
 /* Called when bpf_cgroup_link is auto-detached from dying cgroup.
  * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It
  * doesn't free link memory, which will eventually be done by bpf_link's
@@ -101,22 +110,23 @@ static void cgroup_bpf_release(struct work_struct *work)
 	struct cgroup *p, *cgrp = container_of(work, struct cgroup,
 					       bpf.release_work);
 	struct bpf_prog_array *old_array;
+	struct list_head *storages = &cgrp->bpf.storages;
+	struct bpf_cgroup_storage *storage, *stmp;
+
 	unsigned int type;
 
 	mutex_lock(&cgroup_mutex);
 
 	for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) {
 		struct list_head *progs = &cgrp->bpf.progs[type];
-		struct bpf_prog_list *pl, *tmp;
+		struct bpf_prog_list *pl, *pltmp;
 
-		list_for_each_entry_safe(pl, tmp, progs, node) {
+		list_for_each_entry_safe(pl, pltmp, progs, node) {
 			list_del(&pl->node);
 			if (pl->prog)
 				bpf_prog_put(pl->prog);
 			if (pl->link)
 				bpf_cgroup_link_auto_detach(pl->link);
-			bpf_cgroup_storages_unlink(pl->storage);
-			bpf_cgroup_storages_free(pl->storage);
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
@@ -126,6 +136,11 @@ static void cgroup_bpf_release(struct work_struct *work)
 		bpf_prog_array_free(old_array);
 	}
 
+	list_for_each_entry_safe(storage, stmp, storages, list_cg) {
+		bpf_cgroup_storage_unlink(storage);
+		bpf_cgroup_storage_free(storage);
+	}
+
 	mutex_unlock(&cgroup_mutex);
 
 	for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p))
@@ -290,6 +305,8 @@ int cgroup_bpf_inherit(struct cgroup *cgrp)
 	for (i = 0; i < NR; i++)
 		INIT_LIST_HEAD(&cgrp->bpf.progs[i]);
 
+	INIT_LIST_HEAD(&cgrp->bpf.storages);
+
 	for (i = 0; i < NR; i++)
 		if (compute_effective_progs(cgrp, i, &arrays[i]))
 			goto cleanup;
@@ -422,7 +439,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
-	struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
 	struct bpf_prog_list *pl;
 	int err;
 
@@ -455,17 +472,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (IS_ERR(pl))
 		return PTR_ERR(pl);
 
-	if (bpf_cgroup_storages_alloc(storage, prog ? : link->link.prog))
+	if (bpf_cgroup_storages_alloc(storage, new_storage, type,
+				      prog ? : link->link.prog, cgrp))
 		return -ENOMEM;
 
 	if (pl) {
 		old_prog = pl->prog;
-		bpf_cgroup_storages_unlink(pl->storage);
-		bpf_cgroup_storages_assign(old_storage, pl->storage);
 	} else {
 		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
 		if (!pl) {
-			bpf_cgroup_storages_free(storage);
+			bpf_cgroup_storages_free(new_storage);
 			return -ENOMEM;
 		}
 		list_add_tail(&pl->node, progs);
@@ -480,12 +496,11 @@ int __cgroup_bpf_attach(struct cgroup *cgrp,
 	if (err)
 		goto cleanup;
 
-	bpf_cgroup_storages_free(old_storage);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 	else
 		static_branch_inc(&cgroup_bpf_enabled_key);
-	bpf_cgroup_storages_link(pl->storage, cgrp, type);
+	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
 
 cleanup:
@@ -493,9 +508,7 @@ cleanup:
 		pl->prog = old_prog;
 		pl->link = NULL;
 	}
-	bpf_cgroup_storages_free(pl->storage);
-	bpf_cgroup_storages_assign(pl->storage, old_storage);
-	bpf_cgroup_storages_link(pl->storage, cgrp, type);
+	bpf_cgroup_storages_free(new_storage);
 	if (!old_prog) {
 		list_del(&pl->node);
 		kfree(pl);
@@ -679,8 +692,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
-	bpf_cgroup_storages_unlink(pl->storage);
-	bpf_cgroup_storages_free(pl->storage);
 	kfree(pl);
 	if (list_empty(progs))
 		/* last program was detached, reset flags to zero */
@@ -803,6 +814,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 {
 	struct bpf_cgroup_link *cg_link =
 		container_of(link, struct bpf_cgroup_link, link);
+	struct cgroup *cg;
 
 	/* link might have been auto-detached by dying cgroup already,
 	 * in that case our work is done here
@@ -821,8 +833,12 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
 				    cg_link->type));
 
+	cg = cg_link->cgroup;
+	cg_link->cgroup = NULL;
+
 	mutex_unlock(&cgroup_mutex);
-	cgroup_put(cg_link->cgroup);
+
+	cgroup_put(cg);
 }
 
 static void bpf_cgroup_link_dealloc(struct bpf_link *link)
@@ -833,6 +849,13 @@ static void bpf_cgroup_link_dealloc(struct bpf_link *link)
 	kfree(cg_link);
 }
 
+static int bpf_cgroup_link_detach(struct bpf_link *link)
+{
+	bpf_cgroup_link_release(link);
+
+	return 0;
+}
+
 static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
 					struct seq_file *seq)
 {
@@ -872,6 +895,7 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
 static const struct bpf_link_ops bpf_cgroup_link_lops = {
 	.release = bpf_cgroup_link_release,
 	.dealloc = bpf_cgroup_link_dealloc,
+	.detach = bpf_cgroup_link_detach,
 	.update_prog = cgroup_bpf_replace,
 	.show_fdinfo = bpf_cgroup_link_show_fdinfo,
 	.fill_link_info = bpf_cgroup_link_fill_link_info,