path: root/kernel/bpf/stackmap.c

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 Facebook
 */
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/kernel.h>
#include <linux/stacktrace.h>
#include <linux/perf_event.h>
#include <linux/elf.h>
#include <linux/pagemap.h>
#include <linux/irq_work.h>
#include <linux/btf_ids.h>
#include "percpu_freelist.h"

#define STACK_CREATE_FLAG_MASK					\
	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY |	\
	 BPF_F_STACK_BUILD_ID)

struct stack_map_bucket {
	struct pcpu_freelist_node fnode;
	u32 hash;
	u32 nr;
	u64 data[];
};

struct bpf_stack_map {
	struct bpf_map map;
	void *elems;
	struct pcpu_freelist freelist;
	u32 n_buckets;
	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);
}

static inline int stack_map_data_size(struct bpf_map *map)
{
	return stack_map_use_build_id(map) ?
		sizeof(struct bpf_stack_build_id) : sizeof(u64);
}

static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
{
	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
	int err;

	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries,
					 smap->map.numa_node);
	if (!smap->elems)
		return -ENOMEM;

	err = pcpu_freelist_init(&smap->freelist);
	if (err)
		goto free_elems;

	pcpu_freelist_populate(&smap->freelist, smap->elems, elem_size,
			       smap->map.max_entries);
	return 0;

free_elems:
	bpf_map_area_free(smap->elems);
	return err;
}

/* Called from syscall */
static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
{
	u32 value_size = attr->value_size;
	struct bpf_stack_map *smap;
	struct bpf_map_memory mem;
	u64 cost, n_buckets;
	int err;

	if (!bpf_capable())
		return ERR_PTR(-EPERM);

	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
		return ERR_PTR(-EINVAL);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    value_size < 8 || value_size % 8)
		return ERR_PTR(-EINVAL);

	BUILD_BUG_ON(sizeof(struct bpf_stack_build_id) % sizeof(u64));
	if (attr->map_flags & BPF_F_STACK_BUILD_ID) {
		if (value_size % sizeof(struct bpf_stack_build_id) ||
		    value_size / sizeof(struct bpf_stack_build_id)
		    > sysctl_perf_event_max_stack)
			return ERR_PTR(-EINVAL);
	} else if (value_size / 8 > sysctl_perf_event_max_stack)
		return ERR_PTR(-EINVAL);

	/* hash table size must be power of 2 */
	n_buckets = roundup_pow_of_two(attr->max_entries);

	cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap);
	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
	err = bpf_map_charge_init(&mem, cost);
	if (err)
		return ERR_PTR(err);

	smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr));
	if (!smap) {
		bpf_map_charge_finish(&mem);
		return ERR_PTR(-ENOMEM);
	}

	bpf_map_init_from_attr(&smap->map, attr);
	smap->map.value_size = value_size;
	smap->n_buckets = n_buckets;

	err = get_callchain_buffers(sysctl_perf_event_max_stack);
	if (err)
		goto free_charge;

	err = prealloc_elems_and_freelist(smap);
	if (err)
		goto put_buffers;

	bpf_map_charge_move(&smap->map.memory, &mem);

	return &smap->map;

put_buffers:
	put_callchain_buffers();
free_charge:
	bpf_map_charge_finish(&mem);
	bpf_map_area_free(smap);
	return ERR_PTR(err);
}

#define BPF_BUILD_ID 3
/*
 * Parse build id from the note segment. This logic can be shared between
 * 32-bit and 64-bit system, because Elf32_Nhdr and Elf64_Nhdr are
 * identical.
 */
static inline int stack_map_parse_build_id(void *page_addr,
					   unsigned char *build_id,
					   void *note_start,
					   Elf32_Word note_size)
{
	Elf32_Word note_offs = 0, new_offs;

	/* check for overflow */
	if (note_start < page_addr || note_start + note_size < note_start)
		return -