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

Daniel Borkmann says:

====================
pull-request: bpf-next 2021-11-15

We've added 72 non-merge commits during the last 13 day(s) which contain
a total of 171 files changed, 2728 insertions(+), 1143 deletions(-).

The main changes are:

1) Add btf_type_tag attributes to bring kernel annotations like __user/__rcu to
   BTF such that BPF verifier will be able to detect misuse, from Yonghong Song.

2) Big batch of libbpf improvements including various fixes, future proofing APIs,
   and adding a unified, OPTS-based bpf_prog_load() low-level API, from Andrii Nakryiko.

3) Add ingress_ifindex to BPF_SK_LOOKUP program type for selectively applying the
   programmable socket lookup logic to packets from a given netdev, from Mark Pashmfouroush.

4) Remove the 128M upper JIT limit for BPF programs on arm64 and add selftest to
   ensure exception handling still works, from Russell King and Alan Maguire.

5) Add a new bpf_find_vma() helper for tracing to map an address to the backing
   file such as shared library, from Song Liu.

6) Batch of various misc fixes to bpftool, fixing a memory leak in BPF program dump,
   updating documentation and bash-completion among others, from Quentin Monnet.

7) Deprecate libbpf bpf_program__get_prog_info_linear() API and migrate its users as
   the API is heavily tailored around perf and is non-generic, from Dave Marchevsky.

8) Enable libbpf's strict mode by default in bpftool and add a --legacy option as an
   opt-out for more relaxed BPF program requirements, from Stanislav Fomichev.

9) Fix bpftool to use libbpf_get_error() to check for errors, from Hengqi Chen.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (72 commits)
  bpftool: Use libbpf_get_error() to check error
  bpftool: Fix mixed indentation in documentation
  bpftool: Update the lists of names for maps and prog-attach types
  bpftool: Fix indent in option lists in the documentation
  bpftool: Remove inclusion of utilities.mak from Makefiles
  bpftool: Fix memory leak in prog_dump()
  selftests/bpf: Fix a tautological-constant-out-of-range-compare compiler warning
  selftests/bpf: Fix an unused-but-set-variable compiler warning
  bpf: Introduce btf_tracing_ids
  bpf: Extend BTF_ID_LIST_GLOBAL with parameter for number of IDs
  bpftool: Enable libbpf's strict mode by default
  docs/bpf: Update documentation for BTF_KIND_TYPE_TAG support
  selftests/bpf: Clarify llvm dependency with btf_tag selftest
  selftests/bpf: Add a C test for btf_type_tag
  selftests/bpf: Rename progs/tag.c to progs/btf_decl_tag.c
  selftests/bpf: Test BTF_KIND_DECL_TAG for deduplication
  selftests/bpf: Add BTF_KIND_TYPE_TAG unit tests
  selftests/bpf: Test libbpf API function btf__add_type_tag()
  bpftool: Support BTF_KIND_TYPE_TAG
  libbpf: Support BTF_KIND_TYPE_TAG
  ...
====================

Link: https://lore.kernel.org/r/20211115162008.25916-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 198 insertions, 88 deletions

diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c
index ebfa8bc90892..bb69aea1a777 100644
--- a/kernel/bpf/bpf_task_storage.c
+++ b/kernel/bpf/bpf_task_storage.c
@@ -323,7 +323,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = {
 	.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id = &btf_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type = ARG_ANYTHING,
 };
@@ -334,5 +334,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = {
 	.ret_type = RET_INTEGER,
 	.arg1_type = ARG_CONST_MAP_PTR,
 	.arg2_type = ARG_PTR_TO_BTF_ID,
-	.arg2_btf_id = &btf_task_struct_ids[0],
+	.arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 };
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index dbc3ad07e21b..6b9d23be1e99 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -282,6 +282,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
 	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
+	[BTF_KIND_TYPE_TAG]	= "TYPE_TAG",
 };
 
 const char *btf_type_str(const struct btf_type *t)
@@ -418,6 +419,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 	case BTF_KIND_VOLATILE:
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
+	case BTF_KIND_TYPE_TAG:
 		return true;
 	}
 
@@ -1737,6 +1739,7 @@ __btf_resolve_size(const struct btf *btf, const struct btf_type *type,
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
+		case BTF_KIND_TYPE_TAG:
 			id = type->type;
 			type = btf_type_by_id(btf, type->type);
 			break;
@@ -2345,6 +2348,8 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 				   const struct btf_type *t,
 				   u32 meta_left)
 {
+	const char *value;
+
 	if (btf_type_vlen(t)) {
 		btf_verifier_log_type(env, t, "vlen != 0");
 		return -EINVAL;
@@ -2360,7 +2365,7 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	/* typedef type must have a valid name, and other ref types,
+	/* typedef/type_tag type must have a valid name, and other ref types,
 	 * volatile, const, restrict, should have a null name.
 	 */
 	if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF) {
@@ -2369,6 +2374,12 @@ static int btf_ref_type_check_meta(struct btf_verifier_env *env,
 			btf_verifier_log_type(env, t, "Invalid name");
 			return -EINVAL;
 		}
+	} else if (BTF_INFO_KIND(t->info) == BTF_KIND_TYPE_TAG) {
+		value = btf_name_by_offset(env->btf, t->name_off);
+		if (!value || !value[0]) {
+			btf_verifier_log_type(env, t, "Invalid name");
+			return -EINVAL;
+		}
 	} else {
 		if (t->name_off) {
 			btf_verifier_log_type(env, t, "Invalid name");
@@ -4059,6 +4070,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_DATASEC] = &datasec_ops,
 	[BTF_KIND_FLOAT] = &float_ops,
 	[BTF_KIND_DECL_TAG] = &decl_tag_ops,
+	[BTF_KIND_TYPE_TAG] = &modifier_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -6342,7 +6354,10 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = {
 	.arg4_type	= ARG_ANYTHING,
 };
 
-BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct)
+BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE)
+#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type)
+BTF_TRACING_TYPE_xxx
+#undef BTF_TRACING_TYPE
 
 /* BTF ID set registration API for modules */
 
diff --git a/kernel/bpf/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h
new file mode 100644
index 000000000000..5d18d7d85bef
--- /dev/null
+++ b/kernel/bpf/mmap_unlock_work.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2021 Facebook
+ */
+
+#ifndef __MMAP_UNLOCK_WORK_H__
+#define __MMAP_UNLOCK_WORK_H__
+#include <linux/irq_work.h>
+
+/* irq_work to run mmap_read_unlock() in irq_work */
+struct mmap_unlock_irq_work {
+	struct irq_work irq_work;
+	struct mm_struct *mm;
+};
+
+DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
+
+/*
+ * We cannot do mmap_read_unlock() when the irq is disabled, because of
+ * risk to deadlock with rq_lock. To look up vma when the irqs are
+ * disabled, we need to run mmap_read_unlock() in irq_work. We use a
+ * percpu variable to do the irq_work. If the irq_work is already used
+ * by another lookup, we fall over.
+ */
+static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr)
+{
+	struct mmap_unlock_irq_work *work = NULL;
+	bool irq_work_busy = false;
+
+	if (irqs_disabled()) {
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			work = this_cpu_ptr(&mmap_unlock_work);
+			if (irq_work_is_busy(&work->irq_work)) {
+				/* cannot queue more up_read, fallback */
+				irq_work_busy = true;
+			}
+		} else {
+			/*
+			 * PREEMPT_RT does not allow to trylock mmap sem in
+			 * interrupt disabled context. Force the fallback code.
+			 */
+			irq_work_busy = true;
+		}
+	}
+
+	*work_ptr = work;
+	return irq_work_busy;
+}
+
+static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm)
+{
+	if (!work) {
+		mmap_read_unlock(mm);
+	} else {
+		work->mm = mm;
+
+		/* The lock will be released once we're out of interrupt
+		 * context. Tell lockdep that we've released it now so
+		 * it doesn't complain that we forgot to release it.
+		 */
+		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);
+		irq_work_queue(&work->irq_work);
+	}
+}
+
+#endif /* __MMAP_UNLOCK_WORK_H__ */
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 6e75bbee39f0..49e567209c6b 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,10 +7,10 @@
 #include <linux/kernel.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
-#include <linux/irq_work.h>
 #include <linux/btf_ids.h>
 #include <linux/buildid.h>
 #include "percpu_freelist.h"
+#include "mmap_unlock_work.h"
 
 #define STACK_CREATE_FLAG_MASK					\
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
@@ -31,25 +31,6 @@ struct bpf_stack_map {
 	struct stack_map_bucket *buckets[];
 };
 
-/* irq_work to run up_read() for build_id lookup in nmi context */
-struct stack_map_irq_work {
-	struct irq_work irq_work;
-	struct mm_struct *mm;
-};
-
-static void do_up_read(struct irq_work *entry)
-{
-	struct stack_map_irq_work *work;
-
-	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
-		return;
-
-	work = container_of(entry, struct stack_map_irq_work, irq_work);
-	mmap_read_unlock_non_owner(work->mm);
-}
-
-static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
-
 static inline bool stack_map_use_build_id(struct bpf_map *map)
 {
 	return (map->map_flags & BPF_F_STACK_BUILD_ID);
@@ -149,35 +130,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 					  u64 *ips, u32 trace_nr, bool user)
 {
 	int i;
+	struct mmap_unlock_irq_work *work = NULL;
+	bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
 	struct vm_area_struct *vma;
-	bool irq_work_busy = false;
-	struct stack_map_irq_work *work = NULL;
-
-	if (irqs_disabled()) {
-		if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-			work = this_cpu_ptr(&up_read_work);
-			if (irq_work_is_busy(&work->irq_work)) {
-				/* cannot queue more up_read, fallback */
-				irq_work_busy = true;
-			}
-		} else {
-			/*
-			 * PREEMPT_RT does not allow to trylock mmap sem in
-			 * interrupt disabled context. Force the fallback code.
-			 */
-			irq_work_busy = true;
-		}
-	}
 
-	/*
-	 * We cannot do up_read() when the irq is disabled, because of
-	 * risk to deadlock with rq_lock. To do build_id lookup when the
-	 * irqs are disabled, we need to run up_read() in irq_work. We use
-	 * a percpu variable to do the irq_work. If the irq_work is
-	 * already used by another lookup, we fall back to report ips.
-	 *
-	 * Same fallback is used for kernel stack (!user) on a stackmap
-	 * with build_id.
+	/* If the irq_work is in use, fall back to report ips. Same
+	 * fallback is used for kernel stack (!user) on a stackmap with
+	 * build_id.
 	 */
 	if (!user || !current || !current->mm || irq_work_busy ||
 	    !mmap_read_trylock(current->mm)) {
@@ -203,19 +162,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			- vma->vm_start;
 		id_offs[i].status = BPF_STACK_BUILD_ID_VALID;
 	}
-
-	if (!work) {
-		mmap_read_unlock(current->mm);
-	} else {
-		work->mm = current->mm;
-
-		/* The lock will be released once we're out of interrupt
-		 * context. Tell lockdep that we've released it now so
-		 * it doesn't complain that we forgot to release it.
-		 */
-		rwsem_release(&current->mm->mmap_lock.dep_map, _RET_IP_);
-		irq_work_queue(&work->irq_work);
-	}
+	bpf_mmap_unlock_mm(work, current->mm);
 }
 
 static struct perf_callchain_entry *
@@ -542,7 +489,7 @@ const struct bpf_func_proto bpf_get_task_stack_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
-	.arg1_btf_id	= &btf_task_struct_ids[0],
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
 	.arg2_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg4_type	= ARG_ANYTHING,
@@ -719,16 +666,3 @@ const struct bpf_map_ops stack_trace_map_ops = {
 	.map_btf_name = "bpf_stack_map",
 	.map_btf_id = &stack_trace_map_btf_id,
 };
-
-static int __init stack_map_init(void)
-{
-	int cpu;
-	struct stack_map_irq_work *work;
-
-	for_each_possible_cpu(cpu) {
-		work = per_cpu_ptr(&up_read_work, cpu);
-		init_irq_work(&work->irq_work, do_up_read);
-	}
-	return 0;
-}
-subsys_initcall(stack_map_init);
diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index b48750bfba5a..d94696198ef8 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -8,6 +8,7 @@
 #include <linux/fdtable.h>
 #include <linux/filter.h>
 #include <linux/btf_ids.h>
+#include "mmap_unlock_work.h"
 
 struct bpf_iter_seq_task_common {
 	struct pid_namespace *ns;
@@ -524,10 +525,6 @@ static const struct seq_operations task_vma_seq_ops = {
 	.show	= task_vma_seq_show,
 };
 
-BTF_ID_LIST(btf_task_file_ids)
-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,
 	.init_seq_private	= init_seq_pidns,
@@ -586,23 +583,88 @@ static struct bpf_iter_reg task_vma_reg_info = {
 	.seq_info		= &task_vma_seq_info,
 };
 
+BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
+	   bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags)
+{
+	struct mmap_unlock_irq_work *work = NULL;
+	struct vm_area_struct *vma;
+	bool irq_work_busy = false;
+	struct mm_struct *mm;
+	int ret = -ENOENT;
+
+	if (flags)
+		return -EINVAL;
+
+	if (!task)
+		return -ENOENT;
+
+	mm = task->mm;
+	if (!mm)
+		return -ENOENT;
+
+	irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
+
+	if (irq_work_busy || !mmap_read_trylock(mm))
+		return -EBUSY;
+
+	vma = find_vma(mm, start);
+
+	if (vma && vma->vm_start <= start && vma->vm_end > start) {
+		callback_fn((u64)(long)task, (u64)(long)vma,
+			    (u64)(long)callback_ctx, 0, 0);
+		ret = 0;
+	}
+	bpf_mmap_unlock_mm(work, mm);
+	return ret;
+}
+
+const struct bpf_func_proto bpf_find_vma_proto = {
+	.func		= bpf_find_vma,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_FUNC,
+	.arg4_type	= ARG_PTR_TO_STACK_OR_NULL,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
+
+static void do_mmap_read_unlock(struct irq_work *entry)
+{
+	struct mmap_unlock_irq_work *work;
+
+	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
+		return;
+
+	work = container_of(entry, struct mmap_unlock_irq_work, irq_work);
+	mmap_read_unlock_non_owner(work->mm);
+}
+
 static int __init task_iter_init(void)
 {
-	int ret;
+	struct mmap_unlock_irq_work *work;
+	int ret, cpu;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&mmap_unlock_work, cpu);
+		init_irq_work(&work->irq_work, do_mmap_read_unlock);
+	}
 
-	task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0];
+	task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
 	ret = bpf_iter_reg_target(&task_reg_info);
 	if (ret)
 		return ret;
 
-	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0];
-	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0];
+	task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
+	task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE];
 	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_struct_ids[0];
-	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
+	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
+	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
 	return bpf_iter_reg_target(&task_vma_reg_info);
 }
 late_initcall(task_iter_init);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 890b3ec375a3..0763cca139a7 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6114,6 +6114,33 @@ static int set_timer_callback_state(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int set_find_vma_callback_state(struct bpf_verifier_env *env,
+				       struct bpf_func_state *caller,
+				       struct bpf_func_state *callee,
+				       int insn_idx)
+{
+	/* bpf_find_vma(struct task_struct *task, u64 addr,
+	 *               void *callback_fn, void *callback_ctx, u64 flags)
+	 * (callback_fn)(struct task_struct *task,
+	 *               struct vm_area_struct *vma, void *callback_ctx);
+	 */
+	callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];
+
+	callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
+	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
+	callee->regs[BPF_REG_2].btf =  btf_vmlinux;
+	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA],
+
+	/* pointer to stack or null */
+	callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];
+
+	/* unused */
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
+	__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
+	callee->in_callback_fn = true;
+	return 0;
+}
+
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 {
 	struct bpf_verifier_state *state = env->cur_state;
@@ -6471,6 +6498,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return -EINVAL;
 	}
 
+	if (func_id == BPF_FUNC_find_vma) {
+		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
+					set_find_vma_callback_state);
+		if (err < 0)
+			return -EINVAL;
+	}
+
 	if (func_id == BPF_FUNC_snprintf) {
 		err = check_bpf_snprintf_call(env, regs);
 		if (err < 0)