linux/kernel/bpf/syscall.c

1530 lines
34 KiB
C
Raw Normal View History

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#include <linux/bpf.h>
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
#include <linux/bpf_trace.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/vmalloc.h>
#include <linux/mmzone.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
#include <linux/license.h>
#include <linux/filter.h>
tracing, perf: Implement BPF programs attached to kprobes BPF programs, attached to kprobes, provide a safe way to execute user-defined BPF byte-code programs without being able to crash or hang the kernel in any way. The BPF engine makes sure that such programs have a finite execution time and that they cannot break out of their sandbox. The user interface is to attach to a kprobe via the perf syscall: struct perf_event_attr attr = { .type = PERF_TYPE_TRACEPOINT, .config = event_id, ... }; event_fd = perf_event_open(&attr,...); ioctl(event_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); 'prog_fd' is a file descriptor associated with BPF program previously loaded. 'event_id' is an ID of the kprobe created. Closing 'event_fd': close(event_fd); ... automatically detaches BPF program from it. BPF programs can call in-kernel helper functions to: - lookup/update/delete elements in maps - probe_read - wraper of probe_kernel_read() used to access any kernel data structures BPF programs receive 'struct pt_regs *' as an input ('struct pt_regs' is architecture dependent) and return 0 to ignore the event and 1 to store kprobe event into the ring buffer. Note, kprobes are a fundamentally _not_ a stable kernel ABI, so BPF programs attached to kprobes must be recompiled for every kernel version and user must supply correct LINUX_VERSION_CODE in attr.kern_version during bpf_prog_load() call. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David S. Miller <davem@davemloft.net> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1427312966-8434-4-git-send-email-ast@plumgrid.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-25 19:49:20 +00:00
#include <linux/version.h>
#include <linux/kernel.h>
#include <linux/idr.h>
#define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \
(map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)
#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
DEFINE_PER_CPU(int, bpf_prog_active);
static DEFINE_IDR(prog_idr);
static DEFINE_SPINLOCK(prog_idr_lock);
static DEFINE_IDR(map_idr);
static DEFINE_SPINLOCK(map_idr_lock);
bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 05:23:21 +00:00
int sysctl_unprivileged_bpf_disabled __read_mostly;
static const struct bpf_map_ops * const bpf_map_types[] = {
#define BPF_PROG_TYPE(_id, _ops)
#define BPF_MAP_TYPE(_id, _ops) \
[_id] = &_ops,
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};
/*
* If we're handed a bigger struct than we know of, ensure all the unknown bits
* are 0 - i.e. new user-space does not rely on any kernel feature extensions
* we don't know about yet.
*
* There is a ToCToU between this function call and the following
* copy_from_user() call. However, this is not a concern since this function is
* meant to be a future-proofing of bits.
*/
static int check_uarg_tail_zero(void __user *uaddr,
size_t expected_size,
size_t actual_size)
{
unsigned char __user *addr;
unsigned char __user *end;
unsigned char val;
int err;
if (unlikely(actual_size > PAGE_SIZE)) /* silly large */
return -E2BIG;
if (unlikely(!access_ok(VERIFY_READ, uaddr, actual_size)))
return -EFAULT;
if (actual_size <= expected_size)
return 0;
addr = uaddr + expected_size;
end = uaddr + actual_size;
for (; addr < end; addr++) {
err = get_user(val, addr);
if (err)
return err;
if (val)
return -E2BIG;
}
return 0;
}
static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
struct bpf_map *map;
if (attr->map_type >= ARRAY_SIZE(bpf_map_types) ||
!bpf_map_types[attr->map_type])
return ERR_PTR(-EINVAL);
map = bpf_map_types[attr->map_type]->map_alloc(attr);
if (IS_ERR(map))
return map;
map->ops = bpf_map_types[attr->map_type];
map->map_type = attr->map_type;
return map;
}
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
void *bpf_map_area_alloc(size_t size, int numa_node)
{
/* We definitely need __GFP_NORETRY, so OOM killer doesn't
* trigger under memory pressure as we really just want to
* fail instead.
*/
const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
void *area;
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
area = kmalloc_node(size, GFP_USER | flags, numa_node);
if (area != NULL)
return area;
}
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags,
__builtin_return_address(0));
}
void bpf_map_area_free(void *area)
{
kvfree(area);
}
bpf: pre-allocate hash map elements If kprobe is placed on spin_unlock then calling kmalloc/kfree from bpf programs is not safe, since the following dead lock is possible: kfree->spin_lock(kmem_cache_node->lock)...spin_unlock->kprobe-> bpf_prog->map_update->kmalloc->spin_lock(of the same kmem_cache_node->lock) and deadlocks. The following solutions were considered and some implemented, but eventually discarded - kmem_cache_create for every map - add recursion check to slow-path of slub - use reserved memory in bpf_map_update for in_irq or in preempt_disabled - kmalloc via irq_work At the end pre-allocation of all map elements turned out to be the simplest solution and since the user is charged upfront for all the memory, such pre-allocation doesn't affect the user space visible behavior. Since it's impossible to tell whether kprobe is triggered in a safe location from kmalloc point of view, use pre-allocation by default and introduce new BPF_F_NO_PREALLOC flag. While testing of per-cpu hash maps it was discovered that alloc_percpu(GFP_ATOMIC) has odd corner cases and often fails to allocate memory even when 90% of it is free. The pre-allocation of per-cpu hash elements solves this problem as well. Turned out that bpf_map_update() quickly followed by bpf_map_lookup()+bpf_map_delete() is very common pattern used in many of iovisor/bcc/tools, so there is additional benefit of pre-allocation, since such use cases are must faster. Since all hash map elements are now pre-allocated we can remove atomic increment of htab->count and save few more cycles. Also add bpf_map_precharge_memlock() to check rlimit_memlock early to avoid large malloc/free done by users who don't have sufficient limits. Pre-allocation is done with vmalloc and alloc/free is done via percpu_freelist. Here are performance numbers for different pre-allocation algorithms that were implemented, but discarded in favor of percpu_freelist: 1 cpu: pcpu_ida 2.1M pcpu_ida nolock 2.3M bt 2.4M kmalloc 1.8M hlist+spinlock 2.3M pcpu_freelist 2.6M 4 cpu: pcpu_ida 1.5M pcpu_ida nolock 1.8M bt w/smp_align 1.7M bt no/smp_align 1.1M kmalloc 0.7M hlist+spinlock 0.2M pcpu_freelist 2.0M 8 cpu: pcpu_ida 0.7M bt w/smp_align 0.8M kmalloc 0.4M pcpu_freelist 1.5M 32 cpu: kmalloc 0.13M pcpu_freelist 0.49M pcpu_ida nolock is a modified percpu_ida algorithm without percpu_ida_cpu locks and without cross-cpu tag stealing. It's faster than existing percpu_ida, but not as fast as pcpu_freelist. bt is a variant of block/blk-mq-tag.c simlified and customized for bpf use case. bt w/smp_align is using cache line for every 'long' (similar to blk-mq-tag). bt no/smp_align allocates 'long' bitmasks continuously to save memory. It's comparable to percpu_ida and in some cases faster, but slower than percpu_freelist hlist+spinlock is the simplest free list with single spinlock. As expeceted it has very bad scaling in SMP. kmalloc is existing implementation which is still available via BPF_F_NO_PREALLOC flag. It's significantly slower in single cpu and in 8 cpu setup it's 3 times slower than pre-allocation with pcpu_freelist, but saves memory, so in cases where map->max_entries can be large and number of map update/delete per second is low, it may make sense to use it. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-08 05:57:15 +00:00
int bpf_map_precharge_memlock(u32 pages)
{
struct user_struct *user = get_current_user();
unsigned long memlock_limit, cur;
memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
cur = atomic_long_read(&user->locked_vm);
free_uid(user);
if (cur + pages > memlock_limit)
return -EPERM;
return 0;
}
static int bpf_map_charge_memlock(struct bpf_map *map)
{
struct user_struct *user = get_current_user();
unsigned long memlock_limit;
memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
atomic_long_add(map->pages, &user->locked_vm);
if (atomic_long_read(&user->locked_vm) > memlock_limit) {
atomic_long_sub(map->pages, &user->locked_vm);
free_uid(user);
return -EPERM;
}
map->user = user;
return 0;
}
static void bpf_map_uncharge_memlock(struct bpf_map *map)
{
struct user_struct *user = map->user;
atomic_long_sub(map->pages, &user->locked_vm);
free_uid(user);
}
static int bpf_map_alloc_id(struct bpf_map *map)
{
int id;
spin_lock_bh(&map_idr_lock);
id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC);
if (id > 0)
map->id = id;
spin_unlock_bh(&map_idr_lock);
if (WARN_ON_ONCE(!id))
return -ENOSPC;
return id > 0 ? 0 : id;
}
static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
{
bpf: do not disable/enable BH in bpf_map_free_id() syzkaller reported following splat [1] Since hard irq are disabled by the caller, bpf_map_free_id() should not try to enable/disable BH. Another solution would be to change htab_map_delete_elem() to defer the free_htab_elem() call after raw_spin_unlock_irqrestore(&b->lock, flags), but this might be not enough to cover other code paths. [1] WARNING: CPU: 1 PID: 8052 at kernel/softirq.c:161 __local_bh_enable_ip +0x1e/0x160 kernel/softirq.c:161 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 8052 Comm: syz-executor1 Not tainted 4.13.0-next-20170915+ #23 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:181 __warn+0x1c4/0x1d9 kernel/panic.c:542 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:261 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905 RIP: 0010:__local_bh_enable_ip+0x1e/0x160 kernel/softirq.c:161 RSP: 0018:ffff8801cdcd7748 EFLAGS: 00010046 RAX: 0000000000000082 RBX: 0000000000000201 RCX: 0000000000000000 RDX: 1ffffffff0b5933c RSI: 0000000000000201 RDI: ffffffff85ac99e0 RBP: ffff8801cdcd7758 R08: ffffffff85b87158 R09: 1ffff10039b9aec6 R10: ffff8801c99f24c0 R11: 0000000000000002 R12: ffffffff817b0b47 R13: dffffc0000000000 R14: ffff8801cdcd77e8 R15: 0000000000000001 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:176 [inline] _raw_spin_unlock_bh+0x30/0x40 kernel/locking/spinlock.c:207 spin_unlock_bh include/linux/spinlock.h:361 [inline] bpf_map_free_id kernel/bpf/syscall.c:197 [inline] __bpf_map_put+0x267/0x320 kernel/bpf/syscall.c:227 bpf_map_put+0x1a/0x20 kernel/bpf/syscall.c:235 bpf_map_fd_put_ptr+0x15/0x20 kernel/bpf/map_in_map.c:96 free_htab_elem+0xc3/0x1b0 kernel/bpf/hashtab.c:658 htab_map_delete_elem+0x74d/0x970 kernel/bpf/hashtab.c:1063 map_delete_elem kernel/bpf/syscall.c:633 [inline] SYSC_bpf kernel/bpf/syscall.c:1479 [inline] SyS_bpf+0x2188/0x46a0 kernel/bpf/syscall.c:1451 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: f3f1c054c288 ("bpf: Introduce bpf_map ID") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 16:15:59 +00:00
unsigned long flags;
if (do_idr_lock)
bpf: do not disable/enable BH in bpf_map_free_id() syzkaller reported following splat [1] Since hard irq are disabled by the caller, bpf_map_free_id() should not try to enable/disable BH. Another solution would be to change htab_map_delete_elem() to defer the free_htab_elem() call after raw_spin_unlock_irqrestore(&b->lock, flags), but this might be not enough to cover other code paths. [1] WARNING: CPU: 1 PID: 8052 at kernel/softirq.c:161 __local_bh_enable_ip +0x1e/0x160 kernel/softirq.c:161 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 8052 Comm: syz-executor1 Not tainted 4.13.0-next-20170915+ #23 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:181 __warn+0x1c4/0x1d9 kernel/panic.c:542 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:261 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905 RIP: 0010:__local_bh_enable_ip+0x1e/0x160 kernel/softirq.c:161 RSP: 0018:ffff8801cdcd7748 EFLAGS: 00010046 RAX: 0000000000000082 RBX: 0000000000000201 RCX: 0000000000000000 RDX: 1ffffffff0b5933c RSI: 0000000000000201 RDI: ffffffff85ac99e0 RBP: ffff8801cdcd7758 R08: ffffffff85b87158 R09: 1ffff10039b9aec6 R10: ffff8801c99f24c0 R11: 0000000000000002 R12: ffffffff817b0b47 R13: dffffc0000000000 R14: ffff8801cdcd77e8 R15: 0000000000000001 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:176 [inline] _raw_spin_unlock_bh+0x30/0x40 kernel/locking/spinlock.c:207 spin_unlock_bh include/linux/spinlock.h:361 [inline] bpf_map_free_id kernel/bpf/syscall.c:197 [inline] __bpf_map_put+0x267/0x320 kernel/bpf/syscall.c:227 bpf_map_put+0x1a/0x20 kernel/bpf/syscall.c:235 bpf_map_fd_put_ptr+0x15/0x20 kernel/bpf/map_in_map.c:96 free_htab_elem+0xc3/0x1b0 kernel/bpf/hashtab.c:658 htab_map_delete_elem+0x74d/0x970 kernel/bpf/hashtab.c:1063 map_delete_elem kernel/bpf/syscall.c:633 [inline] SYSC_bpf kernel/bpf/syscall.c:1479 [inline] SyS_bpf+0x2188/0x46a0 kernel/bpf/syscall.c:1451 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: f3f1c054c288 ("bpf: Introduce bpf_map ID") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 16:15:59 +00:00
spin_lock_irqsave(&map_idr_lock, flags);
else
__acquire(&map_idr_lock);
idr_remove(&map_idr, map->id);
if (do_idr_lock)
bpf: do not disable/enable BH in bpf_map_free_id() syzkaller reported following splat [1] Since hard irq are disabled by the caller, bpf_map_free_id() should not try to enable/disable BH. Another solution would be to change htab_map_delete_elem() to defer the free_htab_elem() call after raw_spin_unlock_irqrestore(&b->lock, flags), but this might be not enough to cover other code paths. [1] WARNING: CPU: 1 PID: 8052 at kernel/softirq.c:161 __local_bh_enable_ip +0x1e/0x160 kernel/softirq.c:161 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 8052 Comm: syz-executor1 Not tainted 4.13.0-next-20170915+ #23 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:181 __warn+0x1c4/0x1d9 kernel/panic.c:542 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:178 do_trap_no_signal arch/x86/kernel/traps.c:212 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:261 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:298 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:311 invalid_op+0x18/0x20 arch/x86/entry/entry_64.S:905 RIP: 0010:__local_bh_enable_ip+0x1e/0x160 kernel/softirq.c:161 RSP: 0018:ffff8801cdcd7748 EFLAGS: 00010046 RAX: 0000000000000082 RBX: 0000000000000201 RCX: 0000000000000000 RDX: 1ffffffff0b5933c RSI: 0000000000000201 RDI: ffffffff85ac99e0 RBP: ffff8801cdcd7758 R08: ffffffff85b87158 R09: 1ffff10039b9aec6 R10: ffff8801c99f24c0 R11: 0000000000000002 R12: ffffffff817b0b47 R13: dffffc0000000000 R14: ffff8801cdcd77e8 R15: 0000000000000001 __raw_spin_unlock_bh include/linux/spinlock_api_smp.h:176 [inline] _raw_spin_unlock_bh+0x30/0x40 kernel/locking/spinlock.c:207 spin_unlock_bh include/linux/spinlock.h:361 [inline] bpf_map_free_id kernel/bpf/syscall.c:197 [inline] __bpf_map_put+0x267/0x320 kernel/bpf/syscall.c:227 bpf_map_put+0x1a/0x20 kernel/bpf/syscall.c:235 bpf_map_fd_put_ptr+0x15/0x20 kernel/bpf/map_in_map.c:96 free_htab_elem+0xc3/0x1b0 kernel/bpf/hashtab.c:658 htab_map_delete_elem+0x74d/0x970 kernel/bpf/hashtab.c:1063 map_delete_elem kernel/bpf/syscall.c:633 [inline] SYSC_bpf kernel/bpf/syscall.c:1479 [inline] SyS_bpf+0x2188/0x46a0 kernel/bpf/syscall.c:1451 entry_SYSCALL_64_fastpath+0x1f/0xbe Fixes: f3f1c054c288 ("bpf: Introduce bpf_map ID") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-19 16:15:59 +00:00
spin_unlock_irqrestore(&map_idr_lock, flags);
else
__release(&map_idr_lock);
}
/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
struct bpf_map *map = container_of(work, struct bpf_map, work);
bpf_map_uncharge_memlock(map);
/* implementation dependent freeing */
map->ops->map_free(map);
}
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
static void bpf_map_put_uref(struct bpf_map *map)
{
if (atomic_dec_and_test(&map->usercnt)) {
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY)
bpf_fd_array_map_clear(map);
}
}
/* decrement map refcnt and schedule it for freeing via workqueue
* (unrelying map implementation ops->map_free() might sleep)
*/
static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock)
{
if (atomic_dec_and_test(&map->refcnt)) {
/* bpf_map_free_id() must be called first */
bpf_map_free_id(map, do_idr_lock);
INIT_WORK(&map->work, bpf_map_free_deferred);
schedule_work(&map->work);
}
}
void bpf_map_put(struct bpf_map *map)
{
__bpf_map_put(map, true);
}
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
void bpf_map_put_with_uref(struct bpf_map *map)
{
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
bpf_map_put_uref(map);
bpf_map_put(map);
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
}
static int bpf_map_release(struct inode *inode, struct file *filp)
{
struct bpf_map *map = filp->private_data;
if (map->ops->map_release)
map->ops->map_release(map, filp);
bpf_map_put_with_uref(map);
return 0;
}
#ifdef CONFIG_PROC_FS
static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_map *map = filp->private_data;
const struct bpf_array *array;
u32 owner_prog_type = 0;
u32 owner_jited = 0;
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
owner_prog_type = array->owner_prog_type;
owner_jited = array->owner_jited;
}
seq_printf(m,
"map_type:\t%u\n"
"key_size:\t%u\n"
"value_size:\t%u\n"
"max_entries:\t%u\n"
"map_flags:\t%#x\n"
"memlock:\t%llu\n",
map->map_type,
map->key_size,
map->value_size,
map->max_entries,
map->map_flags,
map->pages * 1ULL << PAGE_SHIFT);
if (owner_prog_type) {
seq_printf(m, "owner_prog_type:\t%u\n",
owner_prog_type);
seq_printf(m, "owner_jited:\t%u\n",
owner_jited);
}
}
#endif
static const struct file_operations bpf_map_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = bpf_map_show_fdinfo,
#endif
.release = bpf_map_release,
};
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
int bpf_map_new_fd(struct bpf_map *map)
{
return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
O_RDWR | O_CLOEXEC);
}
/* helper macro to check that unused fields 'union bpf_attr' are zero */
#define CHECK_ATTR(CMD) \
memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
sizeof(attr->CMD##_LAST_FIELD), 0, \
sizeof(*attr) - \
offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
sizeof(attr->CMD##_LAST_FIELD)) != NULL
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
#define BPF_MAP_CREATE_LAST_FIELD numa_node
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
int numa_node = bpf_map_attr_numa_node(attr);
struct bpf_map *map;
int err;
err = CHECK_ATTR(BPF_MAP_CREATE);
if (err)
return -EINVAL;
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
if (numa_node != NUMA_NO_NODE &&
bpf: fix numa_node validation syzkaller reported crashes in bpf map creation or map update [1] Problem is that nr_node_ids is a signed integer, NUMA_NO_NODE is also an integer, so it is very tempting to declare numa_node as a signed integer. This means the typical test to validate a user provided value : if (numa_node != NUMA_NO_NODE && (numa_node >= nr_node_ids || !node_online(numa_node))) must be written : if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) [1] kernel BUG at mm/slab.c:3256! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 0 PID: 2946 Comm: syzkaller916108 Not tainted 4.13.0-rc7+ #35 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 task: ffff8801d2bc60c0 task.stack: ffff8801c0c90000 RIP: 0010:____cache_alloc_node+0x1d4/0x1e0 mm/slab.c:3292 RSP: 0018:ffff8801c0c97638 EFLAGS: 00010096 RAX: ffffffffffff8b7b RBX: 0000000001080220 RCX: 0000000000000000 RDX: 00000000ffff8b7b RSI: 0000000001080220 RDI: ffff8801dac00040 RBP: ffff8801c0c976c0 R08: 0000000000000000 R09: 0000000000000000 R10: ffff8801c0c97620 R11: 0000000000000001 R12: ffff8801dac00040 R13: ffff8801dac00040 R14: 0000000000000000 R15: 00000000ffff8b7b FS: 0000000002119940(0000) GS:ffff8801db200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001fec CR3: 00000001d2980000 CR4: 00000000001406f0 Call Trace: __do_kmalloc_node mm/slab.c:3688 [inline] __kmalloc_node+0x33/0x70 mm/slab.c:3696 kmalloc_node include/linux/slab.h:535 [inline] alloc_htab_elem+0x2a8/0x480 kernel/bpf/hashtab.c:740 htab_map_update_elem+0x740/0xb80 kernel/bpf/hashtab.c:820 map_update_elem kernel/bpf/syscall.c:587 [inline] SYSC_bpf kernel/bpf/syscall.c:1468 [inline] SyS_bpf+0x20c5/0x4c40 kernel/bpf/syscall.c:1443 entry_SYSCALL_64_fastpath+0x1f/0xbe RIP: 0033:0x440409 RSP: 002b:00007ffd1f1792b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000141 RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 0000000000440409 RDX: 0000000000000020 RSI: 0000000020006000 RDI: 0000000000000002 RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401d70 R13: 0000000000401e00 R14: 0000000000000000 R15: 0000000000000000 Code: 83 c2 01 89 50 18 4c 03 70 08 e8 38 f4 ff ff 4d 85 f6 0f 85 3e ff ff ff 44 89 fe 4c 89 ef e8 94 fb ff ff 49 89 c6 e9 2b ff ff ff <0f> 0b 0f 0b 0f 0b 66 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 41 RIP: ____cache_alloc_node+0x1d4/0x1e0 mm/slab.c:3292 RSP: ffff8801c0c97638 ---[ end trace d745f355da2e33ce ]--- Kernel panic - not syncing: Fatal exception Fixes: 96eabe7a40aa ("bpf: Allow selecting numa node during map creation") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Alexei Starovoitov <ast@fb.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-05 05:41:02 +00:00
((unsigned int)numa_node >= nr_node_ids ||
!node_online(numa_node)))
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 18:28:00 +00:00
return -EINVAL;
/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
map = find_and_alloc_map(attr);
if (IS_ERR(map))
return PTR_ERR(map);
atomic_set(&map->refcnt, 1);
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
atomic_set(&map->usercnt, 1);
err = bpf_map_charge_memlock(map);
if (err)
goto free_map_nouncharge;
err = bpf_map_alloc_id(map);
if (err)
goto free_map;
err = bpf_map_new_fd(map);
if (err < 0) {
/* failed to allocate fd.
* bpf_map_put() is needed because the above
* bpf_map_alloc_id() has published the map
* to the userspace and the userspace may
* have refcnt-ed it through BPF_MAP_GET_FD_BY_ID.
*/
bpf_map_put(map);
return err;
}
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
trace_bpf_map_create(map, err);
return err;
free_map:
bpf_map_uncharge_memlock(map);
free_map_nouncharge:
map->ops->map_free(map);
return err;
}
/* if error is returned, fd is released.
* On success caller should complete fd access with matching fdput()
*/
struct bpf_map *__bpf_map_get(struct fd f)
{
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_map_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
return f.file->private_data;
}
/* prog's and map's refcnt limit */
#define BPF_MAX_REFCNT 32768
struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref)
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
{
if (atomic_inc_return(&map->refcnt) > BPF_MAX_REFCNT) {
atomic_dec(&map->refcnt);
return ERR_PTR(-EBUSY);
}
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
if (uref)
atomic_inc(&map->usercnt);
return map;
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 20:28:15 +00:00
}
struct bpf_map *bpf_map_get_with_uref(u32 ufd)
{
struct fd f = fdget(ufd);
struct bpf_map *map;
map = __bpf_map_get(f);
if (IS_ERR(map))
return map;
map = bpf_map_inc(map, true);
fdput(f);
return map;
}
/* map_idr_lock should have been held */
static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
bool uref)
{
int refold;
refold = __atomic_add_unless(&map->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_map_put(map, false);
return ERR_PTR(-EBUSY);
}
if (!refold)
return ERR_PTR(-ENOENT);
if (uref)
atomic_inc(&map->usercnt);
return map;
}
int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value)
{
return -ENOTSUPP;
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value
static int map_lookup_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
u32 value_size;
struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
return -EINVAL;
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
}
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else if (IS_FD_MAP(map))
value_size = sizeof(u32);
else
value_size = map->value_size;
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_copy(map, key, value);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_copy(map, key, value);
bpf: convert stackmap to pre-allocation It was observed that calling bpf_get_stackid() from a kprobe inside slub or from spin_unlock causes similar deadlock as with hashmap, therefore convert stackmap to use pre-allocated memory. The call_rcu is no longer feasible mechanism, since delayed freeing causes bpf_get_stackid() to fail unpredictably when number of actual stacks is significantly less than user requested max_entries. Since elements are no longer freed into slub, we can push elements into freelist immediately and let them be recycled. However the very unlikley race between user space map_lookup() and program-side recycling is possible: cpu0 cpu1 ---- ---- user does lookup(stackidX) starts copying ips into buffer delete(stackidX) calls bpf_get_stackid() which recyles the element and overwrites with new stack trace To avoid user space seeing a partial stack trace consisting of two merged stack traces, do bucket = xchg(, NULL); copy; xchg(,bucket); to preserve consistent stack trace delivery to user space. Now we can move memset(,0) of left-over element value from critical path of bpf_get_stackid() into slow-path of user space lookup. Also disallow lookup() from bpf program, since it's useless and program shouldn't be messing with collected stack trace. Note that similar race between user space lookup and kernel side updates is also present in hashmap, but it's not a new race. bpf programs were always allowed to modify hash and array map elements while user space is copying them. Fixes: d5a3b1f69186 ("bpf: introduce BPF_MAP_TYPE_STACK_TRACE") Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-08 05:57:17 +00:00
} else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) {
err = bpf_stackmap_copy(map, key, value);
} else if (IS_FD_ARRAY(map)) {
err = bpf_fd_array_map_lookup_elem(map, key, value);
} else if (IS_FD_HASH(map)) {
err = bpf_fd_htab_map_lookup_elem(map, key, value);
} else {
rcu_read_lock();
ptr = map->ops->map_lookup_elem(map, key);
if (ptr)
memcpy(value, ptr, value_size);
rcu_read_unlock();
err = ptr ? 0 : -ENOENT;
}
if (err)
goto free_value;
err = -EFAULT;
if (copy_to_user(uvalue, value, value_size) != 0)
goto free_value;
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
trace_bpf_map_lookup_elem(map, ufd, key, value);
err = 0;
free_value:
kfree(value);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
static int map_update_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *uvalue = u64_to_user_ptr(attr->value);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
u32 value_size;
struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM))
return -EINVAL;
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
}
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
value_size = round_up(map->value_size, 8) * num_possible_cpus();
else
value_size = map->value_size;
err = -ENOMEM;
value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
err = -EFAULT;
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
preempt_disable();
__this_cpu_inc(bpf_prog_active);
if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
err = bpf_percpu_hash_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
err = bpf_percpu_array_update(map, key, value, attr->flags);
} else if (map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY ||
map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
bpf: Add array of maps support This patch adds a few helper funcs to enable map-in-map support (i.e. outer_map->inner_map). The first outer_map type BPF_MAP_TYPE_ARRAY_OF_MAPS is also added in this patch. The next patch will introduce a hash of maps type. Any bpf map type can be acted as an inner_map. The exception is BPF_MAP_TYPE_PROG_ARRAY because the extra level of indirection makes it harder to verify the owner_prog_type and owner_jited. Multi-level map-in-map is not supported (i.e. map->map is ok but not map->map->map). When adding an inner_map to an outer_map, it currently checks the map_type, key_size, value_size, map_flags, max_entries and ops. The verifier also uses those map's properties to do static analysis. map_flags is needed because we need to ensure BPF_PROG_TYPE_PERF_EVENT is using a preallocated hashtab for the inner_hash also. ops and max_entries are needed to generate inlined map-lookup instructions. For simplicity reason, a simple '==' test is used for both map_flags and max_entries. The equality of ops is implied by the equality of map_type. During outer_map creation time, an inner_map_fd is needed to create an outer_map. However, the inner_map_fd's life time does not depend on the outer_map. The inner_map_fd is merely used to initialize the inner_map_meta of the outer_map. Also, for the outer_map: * It allows element update and delete from syscall * It allows element lookup from bpf_prog The above is similar to the current fd_array pattern. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-22 17:00:33 +00:00
map->map_type == BPF_MAP_TYPE_CGROUP_ARRAY ||
map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_array_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
} else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) {
rcu_read_lock();
err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
attr->flags);
rcu_read_unlock();
} else {
rcu_read_lock();
err = map->ops->map_update_elem(map, key, value, attr->flags);
rcu_read_unlock();
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
if (!err)
trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
kfree(value);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
#define BPF_MAP_DELETE_ELEM_LAST_FIELD key
static int map_delete_elem(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
int ufd = attr->map_fd;
struct bpf_map *map;
struct fd f;
void *key;
int err;
if (CHECK_ATTR(BPF_MAP_DELETE_ELEM))
return -EINVAL;
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
}
preempt_disable();
__this_cpu_inc(bpf_prog_active);
rcu_read_lock();
err = map->ops->map_delete_elem(map, key);
rcu_read_unlock();
__this_cpu_dec(bpf_prog_active);
preempt_enable();
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
if (!err)
trace_bpf_map_delete_elem(map, ufd, key);
kfree(key);
err_put:
fdput(f);
return err;
}
/* last field in 'union bpf_attr' used by this command */
#define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key
static int map_get_next_key(union bpf_attr *attr)
{
void __user *ukey = u64_to_user_ptr(attr->key);
void __user *unext_key = u64_to_user_ptr(attr->next_key);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *next_key;
struct fd f;
int err;
if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY))
return -EINVAL;
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
if (ukey) {
key = memdup_user(ukey, map->key_size);
if (IS_ERR(key)) {
err = PTR_ERR(key);
goto err_put;
}
} else {
key = NULL;
}
err = -ENOMEM;
next_key = kmalloc(map->key_size, GFP_USER);
if (!next_key)
goto free_key;
rcu_read_lock();
err = map->ops->map_get_next_key(map, key, next_key);
rcu_read_unlock();
if (err)
goto free_next_key;
err = -EFAULT;
if (copy_to_user(unext_key, next_key, map->key_size) != 0)
goto free_next_key;
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
trace_bpf_map_next_key(map, ufd, key, next_key);
err = 0;
free_next_key:
kfree(next_key);
free_key:
kfree(key);
err_put:
fdput(f);
return err;
}
static const struct bpf_verifier_ops * const bpf_prog_types[] = {
#define BPF_PROG_TYPE(_id, _ops) \
[_id] = &_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};
static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog)
{
if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type])
return -EINVAL;
prog->aux->ops = bpf_prog_types[type];
prog->type = type;
return 0;
}
/* drop refcnt on maps used by eBPF program and free auxilary data */
static void free_used_maps(struct bpf_prog_aux *aux)
{
int i;
for (i = 0; i < aux->used_map_cnt; i++)
bpf_map_put(aux->used_maps[i]);
kfree(aux->used_maps);
}
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
int __bpf_prog_charge(struct user_struct *user, u32 pages)
{
unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
unsigned long user_bufs;
if (user) {
user_bufs = atomic_long_add_return(pages, &user->locked_vm);
if (user_bufs > memlock_limit) {
atomic_long_sub(pages, &user->locked_vm);
return -EPERM;
}
}
return 0;
}
void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
{
if (user)
atomic_long_sub(pages, &user->locked_vm);
}
static int bpf_prog_charge_memlock(struct bpf_prog *prog)
{
struct user_struct *user = get_current_user();
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
int ret;
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
ret = __bpf_prog_charge(user, prog->pages);
if (ret) {
free_uid(user);
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
return ret;
}
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
prog->aux->user = user;
return 0;
}
static void bpf_prog_uncharge_memlock(struct bpf_prog *prog)
{
struct user_struct *user = prog->aux->user;
bpf: fix overflow in prog accounting Commit aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") made a wrong assumption of charging against prog->pages. Unlike map->pages, prog->pages are still subject to change when we need to expand the program through bpf_prog_realloc(). This can for example happen during verification stage when we need to expand and rewrite parts of the program. Should the required space cross a page boundary, then prog->pages is not the same anymore as its original value that we used to bpf_prog_charge_memlock() on. Thus, we'll hit a wrap-around during bpf_prog_uncharge_memlock() when prog is freed eventually. I noticed this that despite having unlimited memlock, programs suddenly refused to load with EPERM error due to insufficient memlock. There are two ways to fix this issue. One would be to add a cached variable to struct bpf_prog that takes a snapshot of prog->pages at the time of charging. The other approach is to also account for resizes. I chose to go with the latter for a couple of reasons: i) We want accounting rather to be more accurate instead of further fooling limits, ii) adding yet another page counter on struct bpf_prog would also be a waste just for this purpose. We also do want to charge as early as possible to avoid going into the verifier just to find out later on that we crossed limits. The only place that needs to be fixed is bpf_prog_realloc(), since only here we expand the program, so we try to account for the needed delta and should we fail, call-sites check for outcome anyway. On cBPF to eBPF migrations, we don't grab a reference to the user as they are charged differently. With that in place, my test case worked fine. Fixes: aaac3ba95e4c ("bpf: charge user for creation of BPF maps and programs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-18 00:52:58 +00:00
__bpf_prog_uncharge(user, prog->pages);
free_uid(user);
}
static int bpf_prog_alloc_id(struct bpf_prog *prog)
{
int id;
spin_lock_bh(&prog_idr_lock);
id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC);
if (id > 0)
prog->aux->id = id;
spin_unlock_bh(&prog_idr_lock);
/* id is in [1, INT_MAX) */
if (WARN_ON_ONCE(!id))
return -ENOSPC;
return id > 0 ? 0 : id;
}
static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock)
{
/* cBPF to eBPF migrations are currently not in the idr store. */
if (!prog->aux->id)
return;
if (do_idr_lock)
spin_lock_bh(&prog_idr_lock);
else
__acquire(&prog_idr_lock);
idr_remove(&prog_idr, prog->aux->id);
if (do_idr_lock)
spin_unlock_bh(&prog_idr_lock);
else
__release(&prog_idr_lock);
}
bpf: generally move prog destruction to RCU deferral Jann Horn reported following analysis that could potentially result in a very hard to trigger (if not impossible) UAF race, to quote his event timeline: - Set up a process with threads T1, T2 and T3 - Let T1 set up a socket filter F1 that invokes another filter F2 through a BPF map [tail call] - Let T1 trigger the socket filter via a unix domain socket write, don't wait for completion - Let T2 call PERF_EVENT_IOC_SET_BPF with F2, don't wait for completion - Now T2 should be behind bpf_prog_get(), but before bpf_prog_put() - Let T3 close the file descriptor for F2, dropping the reference count of F2 to 2 - At this point, T1 should have looked up F2 from the map, but not finished executing it - Let T3 remove F2 from the BPF map, dropping the reference count of F2 to 1 - Now T2 should call bpf_prog_put() (wrong BPF program type), dropping the reference count of F2 to 0 and scheduling bpf_prog_free_deferred() via schedule_work() - At this point, the BPF program could be freed - BPF execution is still running in a freed BPF program While at PERF_EVENT_IOC_SET_BPF time it's only guaranteed that the perf event fd we're doing the syscall on doesn't disappear from underneath us for whole syscall time, it may not be the case for the bpf fd used as an argument only after we did the put. It needs to be a valid fd pointing to a BPF program at the time of the call to make the bpf_prog_get() and while T2 gets preempted, F2 must have dropped reference to 1 on the other CPU. The fput() from the close() in T3 should also add additionally delay to the reference drop via exit_task_work() when bpf_prog_release() gets called as well as scheduling bpf_prog_free_deferred(). That said, it makes nevertheless sense to move the BPF prog destruction generally after RCU grace period to guarantee that such scenario above, but also others as recently fixed in ceb56070359b ("bpf, perf: delay release of BPF prog after grace period") with regards to tail calls won't happen. Integrating bpf_prog_free_deferred() directly into the RCU callback is not allowed since the invocation might happen from either softirq or process context, so we're not permitted to block. Reviewing all bpf_prog_put() invocations from eBPF side (note, cBPF -> eBPF progs don't use this for their destruction) with call_rcu() look good to me. Since we don't know whether at the time of attaching the program, we're already part of a tail call map, we need to use RCU variant. However, due to this, there won't be severely more stress on the RCU callback queue: situations with above bpf_prog_get() and bpf_prog_put() combo in practice normally won't lead to releases, but even if they would, enough effort/ cycles have to be put into loading a BPF program into the kernel already. Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-30 15:24:43 +00:00
static void __bpf_prog_put_rcu(struct rcu_head *rcu)
{
struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
free_used_maps(aux);
bpf_prog_uncharge_memlock(aux->prog);
bpf_prog_free(aux->prog);
}
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
if (atomic_dec_and_test(&prog->aux->refcnt)) {
trace_bpf_prog_put_rcu(prog);
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-16 21:24:50 +00:00
bpf_prog_kallsyms_del(prog);
bpf: generally move prog destruction to RCU deferral Jann Horn reported following analysis that could potentially result in a very hard to trigger (if not impossible) UAF race, to quote his event timeline: - Set up a process with threads T1, T2 and T3 - Let T1 set up a socket filter F1 that invokes another filter F2 through a BPF map [tail call] - Let T1 trigger the socket filter via a unix domain socket write, don't wait for completion - Let T2 call PERF_EVENT_IOC_SET_BPF with F2, don't wait for completion - Now T2 should be behind bpf_prog_get(), but before bpf_prog_put() - Let T3 close the file descriptor for F2, dropping the reference count of F2 to 2 - At this point, T1 should have looked up F2 from the map, but not finished executing it - Let T3 remove F2 from the BPF map, dropping the reference count of F2 to 1 - Now T2 should call bpf_prog_put() (wrong BPF program type), dropping the reference count of F2 to 0 and scheduling bpf_prog_free_deferred() via schedule_work() - At this point, the BPF program could be freed - BPF execution is still running in a freed BPF program While at PERF_EVENT_IOC_SET_BPF time it's only guaranteed that the perf event fd we're doing the syscall on doesn't disappear from underneath us for whole syscall time, it may not be the case for the bpf fd used as an argument only after we did the put. It needs to be a valid fd pointing to a BPF program at the time of the call to make the bpf_prog_get() and while T2 gets preempted, F2 must have dropped reference to 1 on the other CPU. The fput() from the close() in T3 should also add additionally delay to the reference drop via exit_task_work() when bpf_prog_release() gets called as well as scheduling bpf_prog_free_deferred(). That said, it makes nevertheless sense to move the BPF prog destruction generally after RCU grace period to guarantee that such scenario above, but also others as recently fixed in ceb56070359b ("bpf, perf: delay release of BPF prog after grace period") with regards to tail calls won't happen. Integrating bpf_prog_free_deferred() directly into the RCU callback is not allowed since the invocation might happen from either softirq or process context, so we're not permitted to block. Reviewing all bpf_prog_put() invocations from eBPF side (note, cBPF -> eBPF progs don't use this for their destruction) with call_rcu() look good to me. Since we don't know whether at the time of attaching the program, we're already part of a tail call map, we need to use RCU variant. However, due to this, there won't be severely more stress on the RCU callback queue: situations with above bpf_prog_get() and bpf_prog_put() combo in practice normally won't lead to releases, but even if they would, enough effort/ cycles have to be put into loading a BPF program into the kernel already. Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-30 15:24:43 +00:00
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
}
}
void bpf_prog_put(struct bpf_prog *prog)
{
__bpf_prog_put(prog, true);
}
cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include <linux/ip.h> #include <linux/if_ether.h> #include <linux/bpf.h> #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-01 11:31:48 +00:00
EXPORT_SYMBOL_GPL(bpf_prog_put);
static int bpf_prog_release(struct inode *inode, struct file *filp)
{
struct bpf_prog *prog = filp->private_data;
bpf: generally move prog destruction to RCU deferral Jann Horn reported following analysis that could potentially result in a very hard to trigger (if not impossible) UAF race, to quote his event timeline: - Set up a process with threads T1, T2 and T3 - Let T1 set up a socket filter F1 that invokes another filter F2 through a BPF map [tail call] - Let T1 trigger the socket filter via a unix domain socket write, don't wait for completion - Let T2 call PERF_EVENT_IOC_SET_BPF with F2, don't wait for completion - Now T2 should be behind bpf_prog_get(), but before bpf_prog_put() - Let T3 close the file descriptor for F2, dropping the reference count of F2 to 2 - At this point, T1 should have looked up F2 from the map, but not finished executing it - Let T3 remove F2 from the BPF map, dropping the reference count of F2 to 1 - Now T2 should call bpf_prog_put() (wrong BPF program type), dropping the reference count of F2 to 0 and scheduling bpf_prog_free_deferred() via schedule_work() - At this point, the BPF program could be freed - BPF execution is still running in a freed BPF program While at PERF_EVENT_IOC_SET_BPF time it's only guaranteed that the perf event fd we're doing the syscall on doesn't disappear from underneath us for whole syscall time, it may not be the case for the bpf fd used as an argument only after we did the put. It needs to be a valid fd pointing to a BPF program at the time of the call to make the bpf_prog_get() and while T2 gets preempted, F2 must have dropped reference to 1 on the other CPU. The fput() from the close() in T3 should also add additionally delay to the reference drop via exit_task_work() when bpf_prog_release() gets called as well as scheduling bpf_prog_free_deferred(). That said, it makes nevertheless sense to move the BPF prog destruction generally after RCU grace period to guarantee that such scenario above, but also others as recently fixed in ceb56070359b ("bpf, perf: delay release of BPF prog after grace period") with regards to tail calls won't happen. Integrating bpf_prog_free_deferred() directly into the RCU callback is not allowed since the invocation might happen from either softirq or process context, so we're not permitted to block. Reviewing all bpf_prog_put() invocations from eBPF side (note, cBPF -> eBPF progs don't use this for their destruction) with call_rcu() look good to me. Since we don't know whether at the time of attaching the program, we're already part of a tail call map, we need to use RCU variant. However, due to this, there won't be severely more stress on the RCU callback queue: situations with above bpf_prog_get() and bpf_prog_put() combo in practice normally won't lead to releases, but even if they would, enough effort/ cycles have to be put into loading a BPF program into the kernel already. Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-30 15:24:43 +00:00
bpf_prog_put(prog);
return 0;
}
#ifdef CONFIG_PROC_FS
static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp)
{
const struct bpf_prog *prog = filp->private_data;
bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 22:38:15 +00:00
char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 22:38:15 +00:00
bin2hex(prog_tag, prog->tag, sizeof(prog->tag));
seq_printf(m,
"prog_type:\t%u\n"
"prog_jited:\t%u\n"
bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 22:38:15 +00:00
"prog_tag:\t%s\n"
"memlock:\t%llu\n",
prog->type,
prog->jited,
bpf: rework prog_digest into prog_tag Commit 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") was recently discussed, partially due to admittedly suboptimal name of "prog_digest" in combination with sha1 hash usage, thus inevitably and rightfully concerns about its security in terms of collision resistance were raised with regards to use-cases. The intended use cases are for debugging resp. introspection only for providing a stable "tag" over the instruction sequence that both kernel and user space can calculate independently. It's not usable at all for making a security relevant decision. So collisions where two different instruction sequences generate the same tag can happen, but ideally at a rather low rate. The "tag" will be dumped in hex and is short enough to introspect in tracepoints or kallsyms output along with other data such as stack trace, etc. Thus, this patch performs a rename into prog_tag and truncates the tag to a short output (64 bits) to make it obvious it's not collision-free. Should in future a hash or facility be needed with a security relevant focus, then we can think about requirements, constraints, etc that would fit to that situation. For now, rework the exposed parts for the current use cases as long as nothing has been released yet. Tested on x86_64 and s390x. Fixes: 7bd509e311f4 ("bpf: add prog_digest and expose it via fdinfo/netlink") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-13 22:38:15 +00:00
prog_tag,
prog->pages * 1ULL << PAGE_SHIFT);
}
#endif
static const struct file_operations bpf_prog_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = bpf_prog_show_fdinfo,
#endif
.release = bpf_prog_release,
};
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
int bpf_prog_new_fd(struct bpf_prog *prog)
{
return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog,
O_RDWR | O_CLOEXEC);
}
static struct bpf_prog *____bpf_prog_get(struct fd f)
{
if (!f.file)
return ERR_PTR(-EBADF);
if (f.file->f_op != &bpf_prog_fops) {
fdput(f);
return ERR_PTR(-EINVAL);
}
return f.file->private_data;
}
struct bpf_prog *bpf_prog_add(struct bpf_prog *prog, int i)
{
if (atomic_add_return(i, &prog->aux->refcnt) > BPF_MAX_REFCNT) {
atomic_sub(i, &prog->aux->refcnt);
return ERR_PTR(-EBUSY);
}
return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_add);
void bpf_prog_sub(struct bpf_prog *prog, int i)
{
/* Only to be used for undoing previous bpf_prog_add() in some
* error path. We still know that another entity in our call
* path holds a reference to the program, thus atomic_sub() can
* be safely used in such cases!
*/
WARN_ON(atomic_sub_return(i, &prog->aux->refcnt) == 0);
}
EXPORT_SYMBOL_GPL(bpf_prog_sub);
struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
{
return bpf_prog_add(prog, 1);
}
EXPORT_SYMBOL_GPL(bpf_prog_inc);
/* prog_idr_lock should have been held */
struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
int refold;
refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
if (refold >= BPF_MAX_REFCNT) {
__bpf_prog_put(prog, false);
return ERR_PTR(-EBUSY);
}
if (!refold)
return ERR_PTR(-ENOENT);
return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);
static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type)
{
struct fd f = fdget(ufd);
struct bpf_prog *prog;
prog = ____bpf_prog_get(f);
if (IS_ERR(prog))
return prog;
if (type && prog->type != *type) {
prog = ERR_PTR(-EINVAL);
goto out;
}
prog = bpf_prog_inc(prog);
out:
fdput(f);
return prog;
}
struct bpf_prog *bpf_prog_get(u32 ufd)
{
return __bpf_prog_get(ufd, NULL);
}
struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type)
{
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
struct bpf_prog *prog = __bpf_prog_get(ufd, &type);
if (!IS_ERR(prog))
trace_bpf_prog_get_type(prog);
return prog;
}
EXPORT_SYMBOL_GPL(bpf_prog_get_type);
/* last field in 'union bpf_attr' used by this command */
#define BPF_PROG_LOAD_LAST_FIELD prog_flags
static int bpf_prog_load(union bpf_attr *attr)
{
enum bpf_prog_type type = attr->prog_type;
struct bpf_prog *prog;
int err;
char license[128];
bool is_gpl;
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
return -EINVAL;
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
return -EFAULT;
license[sizeof(license) - 1] = 0;
/* eBPF programs must be GPL compatible to use GPL-ed functions */
is_gpl = license_is_gpl_compatible(license);
if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
return -E2BIG;
tracing, perf: Implement BPF programs attached to kprobes BPF programs, attached to kprobes, provide a safe way to execute user-defined BPF byte-code programs without being able to crash or hang the kernel in any way. The BPF engine makes sure that such programs have a finite execution time and that they cannot break out of their sandbox. The user interface is to attach to a kprobe via the perf syscall: struct perf_event_attr attr = { .type = PERF_TYPE_TRACEPOINT, .config = event_id, ... }; event_fd = perf_event_open(&attr,...); ioctl(event_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); 'prog_fd' is a file descriptor associated with BPF program previously loaded. 'event_id' is an ID of the kprobe created. Closing 'event_fd': close(event_fd); ... automatically detaches BPF program from it. BPF programs can call in-kernel helper functions to: - lookup/update/delete elements in maps - probe_read - wraper of probe_kernel_read() used to access any kernel data structures BPF programs receive 'struct pt_regs *' as an input ('struct pt_regs' is architecture dependent) and return 0 to ignore the event and 1 to store kprobe event into the ring buffer. Note, kprobes are a fundamentally _not_ a stable kernel ABI, so BPF programs attached to kprobes must be recompiled for every kernel version and user must supply correct LINUX_VERSION_CODE in attr.kern_version during bpf_prog_load() call. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: David S. Miller <davem@davemloft.net> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1427312966-8434-4-git-send-email-ast@plumgrid.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-03-25 19:49:20 +00:00
if (type == BPF_PROG_TYPE_KPROBE &&
attr->kern_version != LINUX_VERSION_CODE)
return -EINVAL;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
!capable(CAP_SYS_ADMIN))
bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 05:23:21 +00:00
return -EPERM;
/* plain bpf_prog allocation */
prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER);
if (!prog)
return -ENOMEM;
err = bpf_prog_charge_memlock(prog);
if (err)
goto free_prog_nouncharge;
prog->len = attr->insn_cnt;
err = -EFAULT;
if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns),
bpf_prog_insn_size(prog)) != 0)
goto free_prog;
prog->orig_prog = NULL;
prog->jited = 0;
atomic_set(&prog->aux->refcnt, 1);
prog->gpl_compatible = is_gpl ? 1 : 0;
/* find program type: socket_filter vs tracing_filter */
err = find_prog_type(type, prog);
if (err < 0)
goto free_prog;
/* run eBPF verifier */
err = bpf_check(&prog, attr);
if (err < 0)
goto free_used_maps;
/* eBPF program is ready to be JITed */
prog = bpf_prog_select_runtime(prog, &err);
bpf: allow bpf programs to tail-call other bpf programs introduce bpf_tail_call(ctx, &jmp_table, index) helper function which can be used from BPF programs like: int bpf_prog(struct pt_regs *ctx) { ... bpf_tail_call(ctx, &jmp_table, index); ... } that is roughly equivalent to: int bpf_prog(struct pt_regs *ctx) { ... if (jmp_table[index]) return (*jmp_table[index])(ctx); ... } The important detail that it's not a normal call, but a tail call. The kernel stack is precious, so this helper reuses the current stack frame and jumps into another BPF program without adding extra call frame. It's trivially done in interpreter and a bit trickier in JITs. In case of x64 JIT the bigger part of generated assembler prologue is common for all programs, so it is simply skipped while jumping. Other JITs can do similar prologue-skipping optimization or do stack unwind before jumping into the next program. bpf_tail_call() arguments: ctx - context pointer jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table index - index in the jump table Since all BPF programs are idenitified by file descriptor, user space need to populate the jmp_table with FDs of other BPF programs. If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere and program execution continues as normal. New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can populate this jmp_table array with FDs of other bpf programs. Programs can share the same jmp_table array or use multiple jmp_tables. The chain of tail calls can form unpredictable dynamic loops therefore tail_call_cnt is used to limit the number of calls and currently is set to 32. Use cases: Acked-by: Daniel Borkmann <daniel@iogearbox.net> ========== - simplify complex programs by splitting them into a sequence of small programs - dispatch routine For tracing and future seccomp the program may be triggered on all system calls, but processing of syscall arguments will be different. It's more efficient to implement them as: int syscall_entry(struct seccomp_data *ctx) { bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */); ... default: process unknown syscall ... } int sys_write_event(struct seccomp_data *ctx) {...} int sys_read_event(struct seccomp_data *ctx) {...} syscall_jmp_table[__NR_write] = sys_write_event; syscall_jmp_table[__NR_read] = sys_read_event; For networking the program may call into different parsers depending on packet format, like: int packet_parser(struct __sk_buff *skb) { ... parse L2, L3 here ... __u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol)); bpf_tail_call(skb, &ipproto_jmp_table, ipproto); ... default: process unknown protocol ... } int parse_tcp(struct __sk_buff *skb) {...} int parse_udp(struct __sk_buff *skb) {...} ipproto_jmp_table[IPPROTO_TCP] = parse_tcp; ipproto_jmp_table[IPPROTO_UDP] = parse_udp; - for TC use case, bpf_tail_call() allows to implement reclassify-like logic - bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table are atomic, so user space can build chains of BPF programs on the fly Implementation details: ======================= - high performance of bpf_tail_call() is the goal. It could have been implemented without JIT changes as a wrapper on top of BPF_PROG_RUN() macro, but with two downsides: . all programs would have to pay performance penalty for this feature and tail call itself would be slower, since mandatory stack unwind, return, stack allocate would be done for every tailcall. . tailcall would be limited to programs running preempt_disabled, since generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would need to be either global per_cpu variable accessed by helper and by wrapper or global variable protected by locks. In this implementation x64 JIT bypasses stack unwind and jumps into the callee program after prologue. - bpf_prog_array_compatible() ensures that prog_type of callee and caller are the same and JITed/non-JITed flag is the same, since calling JITed program from non-JITed is invalid, since stack frames are different. Similarly calling kprobe type program from socket type program is invalid. - jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map' abstraction, its user space API and all of verifier logic. It's in the existing arraymap.c file, since several functions are shared with regular array map. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-19 23:59:03 +00:00
if (err < 0)
goto free_used_maps;
err = bpf_prog_alloc_id(prog);
if (err)
goto free_used_maps;
err = bpf_prog_new_fd(prog);
if (err < 0) {
/* failed to allocate fd.
* bpf_prog_put() is needed because the above
* bpf_prog_alloc_id() has published the prog
* to the userspace and the userspace may
* have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
*/
bpf_prog_put(prog);
return err;
}
bpf: make jited programs visible in traces Long standing issue with JITed programs is that stack traces from function tracing check whether a given address is kernel code through {__,}kernel_text_address(), which checks for code in core kernel, modules and dynamically allocated ftrace trampolines. But what is still missing is BPF JITed programs (interpreted programs are not an issue as __bpf_prog_run() will be attributed to them), thus when a stack trace is triggered, the code walking the stack won't see any of the JITed ones. The same for address correlation done from user space via reading /proc/kallsyms. This is read by tools like perf, but the latter is also useful for permanent live tracing with eBPF itself in combination with stack maps when other eBPF types are part of the callchain. See offwaketime example on dumping stack from a map. This work tries to tackle that issue by making the addresses and symbols known to the kernel. The lookup from *kernel_text_address() is implemented through a latched RB tree that can be read under RCU in fast-path that is also shared for symbol/size/offset lookup for a specific given address in kallsyms. The slow-path iteration through all symbols in the seq file done via RCU list, which holds a tiny fraction of all exported ksyms, usually below 0.1 percent. Function symbols are exported as bpf_prog_<tag>, in order to aide debugging and attribution. This facility is currently enabled for root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening is active in any mode. The rationale behind this is that still a lot of systems ship with world read permissions on kallsyms thus addresses should not get suddenly exposed for them. If that situation gets much better in future, we always have the option to change the default on this. Likewise, unprivileged programs are not allowed to add entries there either, but that is less of a concern as most such programs types relevant in this context are for root-only anyway. If enabled, call graphs and stack traces will then show a correct attribution; one example is illustrated below, where the trace is now visible in tooling such as perf script --kallsyms=/proc/kallsyms and friends. Before: 7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so) After: 7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux) [...] 7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux) 7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux) f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so) Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-16 21:24:50 +00:00
bpf_prog_kallsyms_add(prog);
bpf: add initial bpf tracepoints This work adds a number of tracepoints to paths that are either considered slow-path or exception-like states, where monitoring or inspecting them would be desirable. For bpf(2) syscall, tracepoints have been placed for main commands when they succeed. In XDP case, tracepoint is for exceptions, that is, f.e. on abnormal BPF program exit such as unknown or XDP_ABORTED return code, or when error occurs during XDP_TX action and the packet could not be forwarded. Both have been split into separate event headers, and can be further extended. Worst case, if they unexpectedly should get into our way in future, they can also removed [1]. Of course, these tracepoints (like any other) can be analyzed by eBPF itself, etc. Example output: # ./perf record -a -e bpf:* sleep 10 # ./perf script sock_example 6197 [005] 283.980322: bpf:bpf_map_create: map type=ARRAY ufd=4 key=4 val=8 max=256 flags=0 sock_example 6197 [005] 283.980721: bpf:bpf_prog_load: prog=a5ea8fa30ea6849c type=SOCKET_FILTER ufd=5 sock_example 6197 [005] 283.988423: bpf:bpf_prog_get_type: prog=a5ea8fa30ea6849c type=SOCKET_FILTER sock_example 6197 [005] 283.988443: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[06 00 00 00] val=[00 00 00 00 00 00 00 00] [...] sock_example 6197 [005] 288.990868: bpf:bpf_map_lookup_elem: map type=ARRAY ufd=4 key=[01 00 00 00] val=[14 00 00 00 00 00 00 00] swapper 0 [005] 289.338243: bpf:bpf_prog_put_rcu: prog=a5ea8fa30ea6849c type=SOCKET_FILTER [1] https://lwn.net/Articles/705270/ Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-01-25 01:28:18 +00:00
trace_bpf_prog_load(prog, err);
return err;
free_used_maps:
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
free_prog_nouncharge:
bpf_prog_free(prog);
return err;
}
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
#define BPF_OBJ_LAST_FIELD bpf_fd
static int bpf_obj_pin(const union bpf_attr *attr)
{
if (CHECK_ATTR(BPF_OBJ))
return -EINVAL;
return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
}
static int bpf_obj_get(const union bpf_attr *attr)
{
if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
return -EINVAL;
return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
}
#ifdef CONFIG_CGROUP_BPF
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach)
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
{
struct bpf_prog *prog = NULL;
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
int ufd = attr->target_fd;
struct bpf_map *map;
struct fd f;
int err;
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
if (attach) {
prog = bpf_prog_get_type(attr->attach_bpf_fd,
BPF_PROG_TYPE_SK_SKB);
if (IS_ERR(prog)) {
fdput(f);
return PTR_ERR(prog);
}
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
}
err = sock_map_prog(map, prog, attr->attach_type);
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
if (err) {
fdput(f);
if (prog)
bpf_prog_put(prog);
return err;
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
}
fdput(f);
return 0;
bpf: sockmap with sk redirect support Recently we added a new map type called dev map used to forward XDP packets between ports (6093ec2dc313). This patches introduces a similar notion for sockets. A sockmap allows users to add participating sockets to a map. When sockets are added to the map enough context is stored with the map entry to use the entry with a new helper bpf_sk_redirect_map(map, key, flags) This helper (analogous to bpf_redirect_map in XDP) is given the map and an entry in the map. When called from a sockmap program, discussed below, the skb will be sent on the socket using skb_send_sock(). With the above we need a bpf program to call the helper from that will then implement the send logic. The initial site implemented in this series is the recv_sock hook. For this to work we implemented a map attach command to add attributes to a map. In sockmap we add two programs a parse program and a verdict program. The parse program uses strparser to build messages and pass them to the verdict program. The parse programs use the normal strparser semantics. The verdict program is of type SK_SKB. The verdict program returns a verdict SK_DROP, or SK_REDIRECT for now. Additional actions may be added later. When SK_REDIRECT is returned, expected when bpf program uses bpf_sk_redirect_map(), the sockmap logic will consult per cpu variables set by the helper routine and pull the sock entry out of the sock map. This pattern follows the existing redirect logic in cls and xdp programs. This gives the flow, recv_sock -> str_parser (parse_prog) -> verdict_prog -> skb_send_sock \ -> kfree_skb As an example use case a message based load balancer may use specific logic in the verdict program to select the sock to send on. Sample programs are provided in future patches that hopefully illustrate the user interfaces. Also selftests are in follow-on patches. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 05:32:47 +00:00
}
static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
return -EINVAL;
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
ptype = BPF_PROG_TYPE_CGROUP_SKB;
break;
case BPF_CGROUP_INET_SOCK_CREATE:
ptype = BPF_PROG_TYPE_CGROUP_SOCK;
break;
bpf: BPF support for sock_ops Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding struct that allows BPF programs of this type to access some of the socket's fields (such as IP addresses, ports, etc.). It uses the existing bpf cgroups infrastructure so the programs can be attached per cgroup with full inheritance support. The program will be called at appropriate times to set relevant connections parameters such as buffer sizes, SYN and SYN-ACK RTOs, etc., based on connection information such as IP addresses, port numbers, etc. Alghough there are already 3 mechanisms to set parameters (sysctls, route metrics and setsockopts), this new mechanism provides some distinct advantages. Unlike sysctls, it can set parameters per connection. In contrast to route metrics, it can also use port numbers and information provided by a user level program. In addition, it could set parameters probabilistically for evaluation purposes (i.e. do something different on 10% of the flows and compare results with the other 90% of the flows). Also, in cases where IPv6 addresses contain geographic information, the rules to make changes based on the distance (or RTT) between the hosts are much easier than route metric rules and can be global. Finally, unlike setsockopt, it oes not require application changes and it can be updated easily at any time. Although the bpf cgroup framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called only once during the connections's lifetime. In contrast, the new program type will be called multiple times from different places in the network stack code. For example, before sending SYN and SYN-ACKs to set an appropriate timeout, when the connection is established to set congestion control, etc. As a result it has "op" field to specify the type of operation requested. The purpose of this new program type is to simplify setting connection parameters, such as buffer sizes, TCP's SYN RTO, etc. For example, it is easy to use facebook's internal IPv6 addresses to determine if both hosts of a connection are in the same datacenter. Therefore, it is easy to write a BPF program to choose a small SYN RTO value when both hosts are in the same datacenter. This patch only contains the framework to support the new BPF program type, following patches add the functionality to set various connection parameters. This patch defines a new BPF program type: BPF_PROG_TYPE_SOCKET_OPS and a new bpf syscall command to load a new program of this type: BPF_PROG_LOAD_SOCKET_OPS. Two new corresponding structs (one for the kernel one for the user/BPF program): /* kernel version */ struct bpf_sock_ops_kern { struct sock *sk; __u32 op; union { __u32 reply; __u32 replylong[4]; }; }; /* user version * Some fields are in network byte order reflecting the sock struct * Use the bpf_ntohl helper macro in samples/bpf/bpf_endian.h to * convert them to host byte order. */ struct bpf_sock_ops { __u32 op; union { __u32 reply; __u32 replylong[4]; }; __u32 family; __u32 remote_ip4; /* In network byte order */ __u32 local_ip4; /* In network byte order */ __u32 remote_ip6[4]; /* In network byte order */ __u32 local_ip6[4]; /* In network byte order */ __u32 remote_port; /* In network byte order */ __u32 local_port; /* In host byte horder */ }; Currently there are two types of ops. The first type expects the BPF program to return a value which is then used by the caller (or a negative value to indicate the operation is not supported). The second type expects state changes to be done by the BPF program, for example through a setsockopt BPF helper function, and they ignore the return value. The reply fields of the bpf_sockt_ops struct are there in case a bpf program needs to return a value larger than an integer. Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-01 03:02:40 +00:00
case BPF_CGROUP_SOCK_OPS:
ptype = BPF_PROG_TYPE_SOCK_OPS;
break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
return sockmap_get_from_fd(attr, true);
default:
return -EINVAL;
}
prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
if (IS_ERR(prog))
return PTR_ERR(prog);
cgrp = cgroup_get_from_fd(attr->target_fd);
if (IS_ERR(cgrp)) {
bpf_prog_put(prog);
return PTR_ERR(cgrp);
}
ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
if (ret)
bpf_prog_put(prog);
cgroup_put(cgrp);
return ret;
}
#define BPF_PROG_DETACH_LAST_FIELD attach_type
static int bpf_prog_detach(const union bpf_attr *attr)
{
struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_DETACH))
return -EINVAL;
switch (attr->attach_type) {
case BPF_CGROUP_INET_INGRESS:
case BPF_CGROUP_INET_EGRESS:
case BPF_CGROUP_INET_SOCK_CREATE:
bpf: BPF support for sock_ops Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding struct that allows BPF programs of this type to access some of the socket's fields (such as IP addresses, ports, etc.). It uses the existing bpf cgroups infrastructure so the programs can be attached per cgroup with full inheritance support. The program will be called at appropriate times to set relevant connections parameters such as buffer sizes, SYN and SYN-ACK RTOs, etc., based on connection information such as IP addresses, port numbers, etc. Alghough there are already 3 mechanisms to set parameters (sysctls, route metrics and setsockopts), this new mechanism provides some distinct advantages. Unlike sysctls, it can set parameters per connection. In contrast to route metrics, it can also use port numbers and information provided by a user level program. In addition, it could set parameters probabilistically for evaluation purposes (i.e. do something different on 10% of the flows and compare results with the other 90% of the flows). Also, in cases where IPv6 addresses contain geographic information, the rules to make changes based on the distance (or RTT) between the hosts are much easier than route metric rules and can be global. Finally, unlike setsockopt, it oes not require application changes and it can be updated easily at any time. Although the bpf cgroup framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called only once during the connections's lifetime. In contrast, the new program type will be called multiple times from different places in the network stack code. For example, before sending SYN and SYN-ACKs to set an appropriate timeout, when the connection is established to set congestion control, etc. As a result it has "op" field to specify the type of operation requested. The purpose of this new program type is to simplify setting connection parameters, such as buffer sizes, TCP's SYN RTO, etc. For example, it is easy to use facebook's internal IPv6 addresses to determine if both hosts of a connection are in the same datacenter. Therefore, it is easy to write a BPF program to choose a small SYN RTO value when both hosts are in the same datacenter. This patch only contains the framework to support the new BPF program type, following patches add the functionality to set various connection parameters. This patch defines a new BPF program type: BPF_PROG_TYPE_SOCKET_OPS and a new bpf syscall command to load a new program of this type: BPF_PROG_LOAD_SOCKET_OPS. Two new corresponding structs (one for the kernel one for the user/BPF program): /* kernel version */ struct bpf_sock_ops_kern { struct sock *sk; __u32 op; union { __u32 reply; __u32 replylong[4]; }; }; /* user version * Some fields are in network byte order reflecting the sock struct * Use the bpf_ntohl helper macro in samples/bpf/bpf_endian.h to * convert them to host byte order. */ struct bpf_sock_ops { __u32 op; union { __u32 reply; __u32 replylong[4]; }; __u32 family; __u32 remote_ip4; /* In network byte order */ __u32 local_ip4; /* In network byte order */ __u32 remote_ip6[4]; /* In network byte order */ __u32 local_ip6[4]; /* In network byte order */ __u32 remote_port; /* In network byte order */ __u32 local_port; /* In host byte horder */ }; Currently there are two types of ops. The first type expects the BPF program to return a value which is then used by the caller (or a negative value to indicate the operation is not supported). The second type expects state changes to be done by the BPF program, for example through a setsockopt BPF helper function, and they ignore the return value. The reply fields of the bpf_sockt_ops struct are there in case a bpf program needs to return a value larger than an integer. Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-01 03:02:40 +00:00
case BPF_CGROUP_SOCK_OPS:
cgrp = cgroup_get_from_fd(attr->target_fd);
if (IS_ERR(cgrp))
return PTR_ERR(cgrp);
ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
cgroup_put(cgrp);
break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
ret = sockmap_get_from_fd(attr, false);
break;
default:
return -EINVAL;
}
return ret;
}
bpf: BPF support for sock_ops Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding struct that allows BPF programs of this type to access some of the socket's fields (such as IP addresses, ports, etc.). It uses the existing bpf cgroups infrastructure so the programs can be attached per cgroup with full inheritance support. The program will be called at appropriate times to set relevant connections parameters such as buffer sizes, SYN and SYN-ACK RTOs, etc., based on connection information such as IP addresses, port numbers, etc. Alghough there are already 3 mechanisms to set parameters (sysctls, route metrics and setsockopts), this new mechanism provides some distinct advantages. Unlike sysctls, it can set parameters per connection. In contrast to route metrics, it can also use port numbers and information provided by a user level program. In addition, it could set parameters probabilistically for evaluation purposes (i.e. do something different on 10% of the flows and compare results with the other 90% of the flows). Also, in cases where IPv6 addresses contain geographic information, the rules to make changes based on the distance (or RTT) between the hosts are much easier than route metric rules and can be global. Finally, unlike setsockopt, it oes not require application changes and it can be updated easily at any time. Although the bpf cgroup framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called only once during the connections's lifetime. In contrast, the new program type will be called multiple times from different places in the network stack code. For example, before sending SYN and SYN-ACKs to set an appropriate timeout, when the connection is established to set congestion control, etc. As a result it has "op" field to specify the type of operation requested. The purpose of this new program type is to simplify setting connection parameters, such as buffer sizes, TCP's SYN RTO, etc. For example, it is easy to use facebook's internal IPv6 addresses to determine if both hosts of a connection are in the same datacenter. Therefore, it is easy to write a BPF program to choose a small SYN RTO value when both hosts are in the same datacenter. This patch only contains the framework to support the new BPF program type, following patches add the functionality to set various connection parameters. This patch defines a new BPF program type: BPF_PROG_TYPE_SOCKET_OPS and a new bpf syscall command to load a new program of this type: BPF_PROG_LOAD_SOCKET_OPS. Two new corresponding structs (one for the kernel one for the user/BPF program): /* kernel version */ struct bpf_sock_ops_kern { struct sock *sk; __u32 op; union { __u32 reply; __u32 replylong[4]; }; }; /* user version * Some fields are in network byte order reflecting the sock struct * Use the bpf_ntohl helper macro in samples/bpf/bpf_endian.h to * convert them to host byte order. */ struct bpf_sock_ops { __u32 op; union { __u32 reply; __u32 replylong[4]; }; __u32 family; __u32 remote_ip4; /* In network byte order */ __u32 local_ip4; /* In network byte order */ __u32 remote_ip6[4]; /* In network byte order */ __u32 local_ip6[4]; /* In network byte order */ __u32 remote_port; /* In network byte order */ __u32 local_port; /* In host byte horder */ }; Currently there are two types of ops. The first type expects the BPF program to return a value which is then used by the caller (or a negative value to indicate the operation is not supported). The second type expects state changes to be done by the BPF program, for example through a setsockopt BPF helper function, and they ignore the return value. The reply fields of the bpf_sockt_ops struct are there in case a bpf program needs to return a value larger than an integer. Signed-off-by: Lawrence Brakmo <brakmo@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-01 03:02:40 +00:00
#endif /* CONFIG_CGROUP_BPF */
bpf: introduce BPF_PROG_TEST_RUN command development and testing of networking bpf programs is quite cumbersome. Despite availability of user space bpf interpreters the kernel is the ultimate authority and execution environment. Current test frameworks for TC include creation of netns, veth, qdiscs and use of various packet generators just to test functionality of a bpf program. XDP testing is even more complicated, since qemu needs to be started with gro/gso disabled and precise queue configuration, transferring of xdp program from host into guest, attaching to virtio/eth0 and generating traffic from the host while capturing the results from the guest. Moreover analyzing performance bottlenecks in XDP program is impossible in virtio environment, since cost of running the program is tiny comparing to the overhead of virtio packet processing, so performance testing can only be done on physical nic with another server generating traffic. Furthermore ongoing changes to user space control plane of production applications cannot be run on the test servers leaving bpf programs stubbed out for testing. Last but not least, the upstream llvm changes are validated by the bpf backend testsuite which has no ability to test the code generated. To improve this situation introduce BPF_PROG_TEST_RUN command to test and performance benchmark bpf programs. Joint work with Daniel Borkmann. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-31 04:45:38 +00:00
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
static int bpf_prog_test_run(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
struct bpf_prog *prog;
int ret = -ENOTSUPP;
if (CHECK_ATTR(BPF_PROG_TEST_RUN))
return -EINVAL;
prog = bpf_prog_get(attr->test.prog_fd);
if (IS_ERR(prog))
return PTR_ERR(prog);
if (prog->aux->ops->test_run)
ret = prog->aux->ops->test_run(prog, attr, uattr);
bpf_prog_put(prog);
return ret;
}
#define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id
static int bpf_obj_get_next_id(const union bpf_attr *attr,
union bpf_attr __user *uattr,
struct idr *idr,
spinlock_t *lock)
{
u32 next_id = attr->start_id;
int err = 0;
if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
next_id++;
spin_lock_bh(lock);
if (!idr_get_next(idr, &next_id))
err = -ENOENT;
spin_unlock_bh(lock);
if (!err)
err = put_user(next_id, &uattr->next_id);
return err;
}
#define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id
static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
{
struct bpf_prog *prog;
u32 id = attr->prog_id;
int fd;
if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
spin_lock_bh(&prog_idr_lock);
prog = idr_find(&prog_idr, id);
if (prog)
prog = bpf_prog_inc_not_zero(prog);
else
prog = ERR_PTR(-ENOENT);
spin_unlock_bh(&prog_idr_lock);
if (IS_ERR(prog))
return PTR_ERR(prog);
fd = bpf_prog_new_fd(prog);
if (fd < 0)
bpf_prog_put(prog);
return fd;
}
#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
{
struct bpf_map *map;
u32 id = attr->map_id;
int fd;
if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
spin_lock_bh(&map_idr_lock);
map = idr_find(&map_idr, id);
if (map)
map = bpf_map_inc_not_zero(map, true);
else
map = ERR_PTR(-ENOENT);
spin_unlock_bh(&map_idr_lock);
if (IS_ERR(map))
return PTR_ERR(map);
fd = bpf_map_new_fd(map);
if (fd < 0)
bpf_map_put(map);
return fd;
}
static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info);
struct bpf_prog_info info = {};
u32 info_len = attr->info.info_len;
char __user *uinsns;
u32 ulen;
int err;
err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
if (err)
return err;
info_len = min_t(u32, sizeof(info), info_len);
if (copy_from_user(&info, uinfo, info_len))
return -EFAULT;
info.type = prog->type;
info.id = prog->aux->id;
memcpy(info.tag, prog->tag, sizeof(prog->tag));
if (!capable(CAP_SYS_ADMIN)) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
goto done;
}
ulen = info.jited_prog_len;
info.jited_prog_len = prog->jited_len;
if (info.jited_prog_len && ulen) {
uinsns = u64_to_user_ptr(info.jited_prog_insns);
ulen = min_t(u32, info.jited_prog_len, ulen);
if (copy_to_user(uinsns, prog->bpf_func, ulen))
return -EFAULT;
}
ulen = info.xlated_prog_len;
info.xlated_prog_len = bpf_prog_insn_size(prog);
if (info.xlated_prog_len && ulen) {
uinsns = u64_to_user_ptr(info.xlated_prog_insns);
ulen = min_t(u32, info.xlated_prog_len, ulen);
if (copy_to_user(uinsns, prog->insnsi, ulen))
return -EFAULT;
}
done:
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
return -EFAULT;
return 0;
}
static int bpf_map_get_info_by_fd(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info);
struct bpf_map_info info = {};
u32 info_len = attr->info.info_len;
int err;
err = check_uarg_tail_zero(uinfo, sizeof(info), info_len);
if (err)
return err;
info_len = min_t(u32, sizeof(info), info_len);
info.type = map->map_type;
info.id = map->id;
info.key_size = map->key_size;
info.value_size = map->value_size;
info.max_entries = map->max_entries;
info.map_flags = map->map_flags;
if (copy_to_user(uinfo, &info, info_len) ||
put_user(info_len, &uattr->info.info_len))
return -EFAULT;
return 0;
}
#define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
int ufd = attr->info.bpf_fd;
struct fd f;
int err;
if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD))
return -EINVAL;
f = fdget(ufd);
if (!f.file)
return -EBADFD;
if (f.file->f_op == &bpf_prog_fops)
err = bpf_prog_get_info_by_fd(f.file->private_data, attr,
uattr);
else if (f.file->f_op == &bpf_map_fops)
err = bpf_map_get_info_by_fd(f.file->private_data, attr,
uattr);
else
err = -EINVAL;
fdput(f);
return err;
}
SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
union bpf_attr attr = {};
int err;
bpf: enable non-root eBPF programs In order to let unprivileged users load and execute eBPF programs teach verifier to prevent pointer leaks. Verifier will prevent - any arithmetic on pointers (except R10+Imm which is used to compute stack addresses) - comparison of pointers (except if (map_value_ptr == 0) ... ) - passing pointers to helper functions - indirectly passing pointers in stack to helper functions - returning pointer from bpf program - storing pointers into ctx or maps Spill/fill of pointers into stack is allowed, but mangling of pointers stored in the stack or reading them byte by byte is not. Within bpf programs the pointers do exist, since programs need to be able to access maps, pass skb pointer to LD_ABS insns, etc but programs cannot pass such pointer values to the outside or obfuscate them. Only allow BPF_PROG_TYPE_SOCKET_FILTER unprivileged programs, so that socket filters (tcpdump), af_packet (quic acceleration) and future kcm can use it. tracing and tc cls/act program types still require root permissions, since tracing actually needs to be able to see all kernel pointers and tc is for root only. For example, the following unprivileged socket filter program is allowed: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += skb->len; return 0; } but the following program is not: int bpf_prog1(struct __sk_buff *skb) { u32 index = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol)); u64 *value = bpf_map_lookup_elem(&my_map, &index); if (value) *value += (u64) skb; return 0; } since it would leak the kernel address into the map. Unprivileged socket filter bpf programs have access to the following helper functions: - map lookup/update/delete (but they cannot store kernel pointers into them) - get_random (it's already exposed to unprivileged user space) - get_smp_processor_id - tail_call into another socket filter program - ktime_get_ns The feature is controlled by sysctl kernel.unprivileged_bpf_disabled. This toggle defaults to off (0), but can be set true (1). Once true, bpf programs and maps cannot be accessed from unprivileged process, and the toggle cannot be set back to false. Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 05:23:21 +00:00
if (!capable(CAP_SYS_ADMIN) && sysctl_unprivileged_bpf_disabled)
return -EPERM;
err = check_uarg_tail_zero(uattr, sizeof(attr), size);
if (err)
return err;
size = min_t(u32, size, sizeof(attr));
/* copy attributes from user space, may be less than sizeof(bpf_attr) */
if (copy_from_user(&attr, uattr, size) != 0)
return -EFAULT;
switch (cmd) {
case BPF_MAP_CREATE:
err = map_create(&attr);
break;
case BPF_MAP_LOOKUP_ELEM:
err = map_lookup_elem(&attr);
break;
case BPF_MAP_UPDATE_ELEM:
err = map_update_elem(&attr);
break;
case BPF_MAP_DELETE_ELEM:
err = map_delete_elem(&attr);
break;
case BPF_MAP_GET_NEXT_KEY:
err = map_get_next_key(&attr);
break;
case BPF_PROG_LOAD:
err = bpf_prog_load(&attr);
break;
bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-29 13:58:09 +00:00
case BPF_OBJ_PIN:
err = bpf_obj_pin(&attr);
break;
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
case BPF_PROG_DETACH:
err = bpf_prog_detach(&attr);
break;
#endif
bpf: introduce BPF_PROG_TEST_RUN command development and testing of networking bpf programs is quite cumbersome. Despite availability of user space bpf interpreters the kernel is the ultimate authority and execution environment. Current test frameworks for TC include creation of netns, veth, qdiscs and use of various packet generators just to test functionality of a bpf program. XDP testing is even more complicated, since qemu needs to be started with gro/gso disabled and precise queue configuration, transferring of xdp program from host into guest, attaching to virtio/eth0 and generating traffic from the host while capturing the results from the guest. Moreover analyzing performance bottlenecks in XDP program is impossible in virtio environment, since cost of running the program is tiny comparing to the overhead of virtio packet processing, so performance testing can only be done on physical nic with another server generating traffic. Furthermore ongoing changes to user space control plane of production applications cannot be run on the test servers leaving bpf programs stubbed out for testing. Last but not least, the upstream llvm changes are validated by the bpf backend testsuite which has no ability to test the code generated. To improve this situation introduce BPF_PROG_TEST_RUN command to test and performance benchmark bpf programs. Joint work with Daniel Borkmann. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-31 04:45:38 +00:00
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
case BPF_PROG_GET_NEXT_ID:
err = bpf_obj_get_next_id(&attr, uattr,
&prog_idr, &prog_idr_lock);
break;
case BPF_MAP_GET_NEXT_ID:
err = bpf_obj_get_next_id(&attr, uattr,
&map_idr, &map_idr_lock);
break;
case BPF_PROG_GET_FD_BY_ID:
err = bpf_prog_get_fd_by_id(&attr);
break;
case BPF_MAP_GET_FD_BY_ID:
err = bpf_map_get_fd_by_id(&attr);
break;
case BPF_OBJ_GET_INFO_BY_FD:
err = bpf_obj_get_info_by_fd(&attr, uattr);
break;
default:
err = -EINVAL;
break;
}
return err;
}