OpenCloudOS-Kernel/include/linux/bpf.h

1063 lines
33 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#ifndef _LINUX_BPF_H
#define _LINUX_BPF_H 1
#include <uapi/linux/bpf.h>
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>
2017-02-17 05:24:50 +08:00
#include <linux/workqueue.h>
#include <linux/file.h>
#include <linux/percpu.h>
bpf: fix missing header inclusion Commit 0fc174dea545 ("ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs") introduced usage of ERR_PTR() in bpf_prog_get(), however did not include linux/err.h. Without this patch, when compiling arm64 BPF without CONFIG_BPF_SYSCALL: ... In file included from arch/arm64/net/bpf_jit_comp.c:21:0: include/linux/bpf.h: In function 'bpf_prog_get': include/linux/bpf.h:235:9: error: implicit declaration of function 'ERR_PTR' [-Werror=implicit-function-declaration] return ERR_PTR(-EOPNOTSUPP); ^ include/linux/bpf.h:235:9: warning: return makes pointer from integer without a cast [-Wint-conversion] In file included from include/linux/rwsem.h:17:0, from include/linux/mm_types.h:10, from include/linux/sched.h:27, from arch/arm64/include/asm/compat.h:25, from arch/arm64/include/asm/stat.h:23, from include/linux/stat.h:5, from include/linux/compat.h:12, from include/linux/filter.h:10, from arch/arm64/net/bpf_jit_comp.c:22: include/linux/err.h: At top level: include/linux/err.h:23:35: error: conflicting types for 'ERR_PTR' static inline void * __must_check ERR_PTR(long error) ^ In file included from arch/arm64/net/bpf_jit_comp.c:21:0: include/linux/bpf.h:235:9: note: previous implicit declaration of 'ERR_PTR' was here return ERR_PTR(-EOPNOTSUPP); ^ ... Fixes: 0fc174dea545 ("ebpf: make internal bpf API independent of CONFIG_BPF_SYSCALL ifdefs") Suggested-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Zi Shen Lim <zlim.lnx@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-09 12:18:47 +08:00
#include <linux/err.h>
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>
2017-02-17 05:24:50 +08:00
#include <linux/rbtree_latch.h>
#include <linux/numa.h>
#include <linux/wait.h>
#include <linux/u64_stats_sync.h>
struct bpf_verifier_env;
bpf, maps: flush own entries on perf map release The behavior of perf event arrays are quite different from all others as they are tightly coupled to perf event fds, f.e. shown recently by commit e03e7ee34fdd ("perf/bpf: Convert perf_event_array to use struct file") to make refcounting on perf event more robust. A remaining issue that the current code still has is that since additions to the perf event array take a reference on the struct file via perf_event_get() and are only released via fput() (that cleans up the perf event eventually via perf_event_release_kernel()) when the element is either manually removed from the map from user space or automatically when the last reference on the perf event map is dropped. However, this leads us to dangling struct file's when the map gets pinned after the application owning the perf event descriptor exits, and since the struct file reference will in such case only be manually dropped or via pinned file removal, it leads to the perf event living longer than necessary, consuming needlessly resources for that time. Relations between perf event fds and bpf perf event map fds can be rather complex. F.e. maps can act as demuxers among different perf event fds that can possibly be owned by different threads and based on the index selection from the program, events get dispatched to one of the per-cpu fd endpoints. One perf event fd (or, rather a per-cpu set of them) can also live in multiple perf event maps at the same time, listening for events. Also, another requirement is that perf event fds can get closed from application side after they have been attached to the perf event map, so that on exit perf event map will take care of dropping their references eventually. Likewise, when such maps are pinned, the intended behavior is that a user application does bpf_obj_get(), puts its fds in there and on exit when fd is released, they are dropped from the map again, so the map acts rather as connector endpoint. This also makes perf event maps inherently different from program arrays as described in more detail in commit c9da161c6517 ("bpf: fix clearing on persistent program array maps"). To tackle this, map entries are marked by the map struct file that added the element to the map. And when the last reference to that map struct file is released from user space, then the tracked entries are purged from the map. This is okay, because new map struct files instances resp. frontends to the anon inode are provided via bpf_map_new_fd() that is called when we invoke bpf_obj_get_user() for retrieving a pinned map, but also when an initial instance is created via map_create(). The rest is resolved by the vfs layer automatically for us by keeping reference count on the map's struct file. Any concurrent updates on the map slot are fine as well, it just means that perf_event_fd_array_release() needs to delete less of its own entires. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-16 04:47:14 +08:00
struct perf_event;
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 13:32:47 +08:00
struct bpf_prog;
struct bpf_map;
bpf: create tcp_bpf_ulp allowing BPF to monitor socket TX/RX data This implements a BPF ULP layer to allow policy enforcement and monitoring at the socket layer. In order to support this a new program type BPF_PROG_TYPE_SK_MSG is used to run the policy at the sendmsg/sendpage hook. To attach the policy to sockets a sockmap is used with a new program attach type BPF_SK_MSG_VERDICT. Similar to previous sockmap usages when a sock is added to a sockmap, via a map update, if the map contains a BPF_SK_MSG_VERDICT program type attached then the BPF ULP layer is created on the socket and the attached BPF_PROG_TYPE_SK_MSG program is run for every msg in sendmsg case and page/offset in sendpage case. BPF_PROG_TYPE_SK_MSG Semantics/API: BPF_PROG_TYPE_SK_MSG supports only two return codes SK_PASS and SK_DROP. Returning SK_DROP free's the copied data in the sendmsg case and in the sendpage case leaves the data untouched. Both cases return -EACESS to the user. Returning SK_PASS will allow the msg to be sent. In the sendmsg case data is copied into kernel space buffers before running the BPF program. The kernel space buffers are stored in a scatterlist object where each element is a kernel memory buffer. Some effort is made to coalesce data from the sendmsg call here. For example a sendmsg call with many one byte iov entries will likely be pushed into a single entry. The BPF program is run with data pointers (start/end) pointing to the first sg element. In the sendpage case data is not copied. We opt not to copy the data by default here, because the BPF infrastructure does not know what bytes will be needed nor when they will be needed. So copying all bytes may be wasteful. Because of this the initial start/end data pointers are (0,0). Meaning no data can be read or written. This avoids reading data that may be modified by the user. A new helper is added later in this series if reading and writing the data is needed. The helper call will do a copy by default so that the page is exclusively owned by the BPF call. The verdict from the BPF_PROG_TYPE_SK_MSG applies to the entire msg in the sendmsg() case and the entire page/offset in the sendpage case. This avoids ambiguity on how to handle mixed return codes in the sendmsg case. Again a helper is added later in the series if a verdict needs to apply to multiple system calls and/or only a subpart of the currently being processed message. The helper msg_redirect_map() can be used to select the socket to send the data on. This is used similar to existing redirect use cases. This allows policy to redirect msgs. Pseudo code simple example: The basic logic to attach a program to a socket is as follows, // load the programs bpf_prog_load(SOCKMAP_TCP_MSG_PROG, BPF_PROG_TYPE_SK_MSG, &obj, &msg_prog); // lookup the sockmap bpf_map_msg = bpf_object__find_map_by_name(obj, "my_sock_map"); // get fd for sockmap map_fd_msg = bpf_map__fd(bpf_map_msg); // attach program to sockmap bpf_prog_attach(msg_prog, map_fd_msg, BPF_SK_MSG_VERDICT, 0); Adding sockets to the map is done in the normal way, // Add a socket 'fd' to sockmap at location 'i' bpf_map_update_elem(map_fd_msg, &i, fd, BPF_ANY); After the above any socket attached to "my_sock_map", in this case 'fd', will run the BPF msg verdict program (msg_prog) on every sendmsg and sendpage system call. For a complete example see BPF selftests or sockmap samples. Implementation notes: It seemed the simplest, to me at least, to use a refcnt to ensure psock is not lost across the sendmsg copy into the sg, the bpf program running on the data in sg_data, and the final pass to the TCP stack. Some performance testing may show a better method to do this and avoid the refcnt cost, but for now use the simpler method. Another item that will come after basic support is in place is supporting MSG_MORE flag. At the moment we call sendpages even if the MSG_MORE flag is set. An enhancement would be to collect the pages into a larger scatterlist and pass down the stack. Notice that bpf_tcp_sendmsg() could support this with some additional state saved across sendmsg calls. I built the code to support this without having to do refactoring work. Other features TBD include ZEROCOPY and the TCP_RECV_QUEUE/TCP_NO_QUEUE support. This will follow initial series shortly. Future work could improve size limits on the scatterlist rings used here. Currently, we use MAX_SKB_FRAGS simply because this was being used already in the TLS case. Future work could extend the kernel sk APIs to tune this depending on workload. This is a trade-off between memory usage and throughput performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-19 03:57:10 +08:00
struct sock;
struct seq_file;
struct btf;
struct btf_type;
/* map is generic key/value storage optionally accesible by eBPF programs */
struct bpf_map_ops {
/* funcs callable from userspace (via syscall) */
int (*map_alloc_check)(union bpf_attr *attr);
struct bpf_map *(*map_alloc)(union bpf_attr *attr);
void (*map_release)(struct bpf_map *map, struct file *map_file);
void (*map_free)(struct bpf_map *map);
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
void (*map_release_uref)(struct bpf_map *map);
void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
/* funcs callable from userspace and from eBPF programs */
void *(*map_lookup_elem)(struct bpf_map *map, void *key);
int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
int (*map_delete_elem)(struct bpf_map *map, void *key);
int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
int (*map_pop_elem)(struct bpf_map *map, void *value);
int (*map_peek_elem)(struct bpf_map *map, void *value);
/* funcs called by prog_array and perf_event_array map */
void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
int fd);
void (*map_fd_put_ptr)(void *ptr);
u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
u32 (*map_fd_sys_lookup_elem)(void *ptr);
void (*map_seq_show_elem)(struct bpf_map *map, void *key,
struct seq_file *m);
int (*map_check_btf)(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
bpf: implement lookup-free direct value access for maps This generic extension to BPF maps allows for directly loading an address residing inside a BPF map value as a single BPF ldimm64 instruction! The idea is similar to what BPF_PSEUDO_MAP_FD does today, which is a special src_reg flag for ldimm64 instruction that indicates that inside the first part of the double insns's imm field is a file descriptor which the verifier then replaces as a full 64bit address of the map into both imm parts. For the newly added BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following: the first part of the double insns's imm field is again a file descriptor corresponding to the map, and the second part of the imm field is an offset into the value. The verifier will then replace both imm parts with an address that points into the BPF map value at the given value offset for maps that support this operation. Currently supported is array map with single entry. It is possible to support more than just single map element by reusing both 16bit off fields of the insns as a map index, so full array map lookup could be expressed that way. It hasn't been implemented here due to lack of concrete use case, but could easily be done so in future in a compatible way, since both off fields right now have to be 0 and would correctly denote a map index 0. The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of map pointer versus load of map's value at offset 0, and changing BPF_PSEUDO_MAP_FD's encoding into off by one to differ between regular map pointer and map value pointer would add unnecessary complexity and increases barrier for debugability thus less suitable. Using the second part of the imm field as an offset into the value does /not/ come with limitations since maximum possible value size is in u32 universe anyway. This optimization allows for efficiently retrieving an address to a map value memory area without having to issue a helper call which needs to prepare registers according to calling convention, etc, without needing the extra NULL test, and without having to add the offset in an additional instruction to the value base pointer. The verifier then treats the destination register as PTR_TO_MAP_VALUE with constant reg->off from the user passed offset from the second imm field, and guarantees that this is within bounds of the map value. Any subsequent operations are normally treated as typical map value handling without anything extra needed from verification side. The two map operations for direct value access have been added to array map for now. In future other types could be supported as well depending on the use case. The main use case for this commit is to allow for BPF loader support for global variables that reside in .data/.rodata/.bss sections such that we can directly load the address of them with minimal additional infrastructure required. Loader support has been added in subsequent commits for libbpf library. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:03 +08:00
/* Direct value access helpers. */
int (*map_direct_value_addr)(const struct bpf_map *map,
u64 *imm, u32 off);
int (*map_direct_value_meta)(const struct bpf_map *map,
u64 imm, u32 *off);
};
struct bpf_map {
/* The first two cachelines with read-mostly members of which some
bpf: avoid false sharing of map refcount with max_entries In addition to commit b2157399cc98 ("bpf: prevent out-of-bounds speculation") also change the layout of struct bpf_map such that false sharing of fast-path members like max_entries is avoided when the maps reference counter is altered. Therefore enforce them to be placed into separate cachelines. pahole dump after change: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ u32 pages; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ bool unpriv_array; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ struct user_struct * user; /* 64 8 */ atomic_t refcnt; /* 72 4 */ atomic_t usercnt; /* 76 4 */ struct work_struct work; /* 80 32 */ char name[16]; /* 112 16 */ /* --- cacheline 2 boundary (128 bytes) --- */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 121, holes: 1, sum holes: 7 */ }; Now all entries in the first cacheline are read only throughout the life time of the map, set up once during map creation. Overall struct size and number of cachelines doesn't change from the reordering. struct bpf_map is usually first member and embedded in map structs in specific map implementations, so also avoid those members to sit at the end where it could potentially share the cacheline with first map values e.g. in the array since remote CPUs could trigger map updates just as well for those (easily dirtying members like max_entries intentionally as well) while having subsequent values in cache. Quoting from Google's Project Zero blog [1]: Additionally, at least on the Intel machine on which this was tested, bouncing modified cache lines between cores is slow, apparently because the MESI protocol is used for cache coherence [8]. Changing the reference counter of an eBPF array on one physical CPU core causes the cache line containing the reference counter to be bounced over to that CPU core, making reads of the reference counter on all other CPU cores slow until the changed reference counter has been written back to memory. Because the length and the reference counter of an eBPF array are stored in the same cache line, this also means that changing the reference counter on one physical CPU core causes reads of the eBPF array's length to be slow on other physical CPU cores (intentional false sharing). While this doesn't 'control' the out-of-bounds speculation through masking the index as in commit b2157399cc98, triggering a manipulation of the map's reference counter is really trivial, so lets not allow to easily affect max_entries from it. Splitting to separate cachelines also generally makes sense from a performance perspective anyway in that fast-path won't have a cache miss if the map gets pinned, reused in other progs, etc out of control path, thus also avoids unintentional false sharing. [1] https://googleprojectzero.blogspot.ch/2018/01/reading-privileged-memory-with-side.html Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-01-09 20:17:44 +08:00
* are also accessed in fast-path (e.g. ops, max_entries).
*/
const struct bpf_map_ops *ops ____cacheline_aligned;
struct bpf_map *inner_map_meta;
#ifdef CONFIG_SECURITY
void *security;
#endif
enum bpf_map_type map_type;
u32 key_size;
u32 value_size;
u32 max_entries;
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 13:57:15 +08:00
u32 map_flags;
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
int spin_lock_off; /* >=0 valid offset, <0 error */
u32 id;
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>
2017-08-19 02:28:00 +08:00
int numa_node;
u32 btf_key_type_id;
u32 btf_value_type_id;
struct btf *btf;
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
u32 pages;
bpf: prevent out-of-bounds speculation Under speculation, CPUs may mis-predict branches in bounds checks. Thus, memory accesses under a bounds check may be speculated even if the bounds check fails, providing a primitive for building a side channel. To avoid leaking kernel data round up array-based maps and mask the index after bounds check, so speculated load with out of bounds index will load either valid value from the array or zero from the padded area. Unconditionally mask index for all array types even when max_entries are not rounded to power of 2 for root user. When map is created by unpriv user generate a sequence of bpf insns that includes AND operation to make sure that JITed code includes the same 'index & index_mask' operation. If prog_array map is created by unpriv user replace bpf_tail_call(ctx, map, index); with if (index >= max_entries) { index &= map->index_mask; bpf_tail_call(ctx, map, index); } (along with roundup to power 2) to prevent out-of-bounds speculation. There is secondary redundant 'if (index >= max_entries)' in the interpreter and in all JITs, but they can be optimized later if necessary. Other array-like maps (cpumap, devmap, sockmap, perf_event_array, cgroup_array) cannot be used by unpriv, so no changes there. That fixes bpf side of "Variant 1: bounds check bypass (CVE-2017-5753)" on all architectures with and without JIT. v2->v3: Daniel noticed that attack potentially can be crafted via syscall commands without loading the program, so add masking to those paths as well. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-01-08 09:33:02 +08:00
bool unpriv_array;
bpf: add syscall side map freeze support This patch adds a new BPF_MAP_FREEZE command which allows to "freeze" the map globally as read-only / immutable from syscall side. Map permission handling has been refactored into map_get_sys_perms() and drops FMODE_CAN_WRITE in case of locked map. Main use case is to allow for setting up .rodata sections from the BPF ELF which are loaded into the kernel, meaning BPF loader first allocates map, sets up map value by copying .rodata section into it and once complete, it calls BPF_MAP_FREEZE on the map fd to prevent further modifications. Right now BPF_MAP_FREEZE only takes map fd as argument while remaining bpf_attr members are required to be zero. I didn't add write-only locking here as counterpart since I don't have a concrete use-case for it on my side, and I think it makes probably more sense to wait once there is actually one. In that case bpf_attr can be extended as usual with a flag field and/or others where flag 0 means that we lock the map read-only hence this doesn't prevent to add further extensions to BPF_MAP_FREEZE upon need. A map creation flag like BPF_F_WRONCE was not considered for couple of reasons: i) in case of a generic implementation, a map can consist of more than just one element, thus there could be multiple map updates needed to set the map into a state where it can then be made immutable, ii) WRONCE indicates exact one-time write before it is then set immutable. A generic implementation would set a bit atomically on map update entry (if unset), indicating that every subsequent update from then onwards will need to bail out there. However, map updates can fail, so upon failure that flag would need to be unset again and the update attempt would need to be repeated for it to be eventually made immutable. While this can be made race-free, this approach feels less clean and in combination with reason i), it's not generic enough. A dedicated BPF_MAP_FREEZE command directly sets the flag and caller has the guarantee that map is immutable from syscall side upon successful return for any future syscall invocations that would alter the map state, which is also more intuitive from an API point of view. A command name such as BPF_MAP_LOCK has been avoided as it's too close with BPF map spin locks (which already has BPF_F_LOCK flag). BPF_MAP_FREEZE is so far only enabled for privileged users. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:06 +08:00
bool frozen; /* write-once */
/* 48 bytes hole */
bpf: avoid false sharing of map refcount with max_entries In addition to commit b2157399cc98 ("bpf: prevent out-of-bounds speculation") also change the layout of struct bpf_map such that false sharing of fast-path members like max_entries is avoided when the maps reference counter is altered. Therefore enforce them to be placed into separate cachelines. pahole dump after change: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ u32 pages; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ bool unpriv_array; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ struct user_struct * user; /* 64 8 */ atomic_t refcnt; /* 72 4 */ atomic_t usercnt; /* 76 4 */ struct work_struct work; /* 80 32 */ char name[16]; /* 112 16 */ /* --- cacheline 2 boundary (128 bytes) --- */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 121, holes: 1, sum holes: 7 */ }; Now all entries in the first cacheline are read only throughout the life time of the map, set up once during map creation. Overall struct size and number of cachelines doesn't change from the reordering. struct bpf_map is usually first member and embedded in map structs in specific map implementations, so also avoid those members to sit at the end where it could potentially share the cacheline with first map values e.g. in the array since remote CPUs could trigger map updates just as well for those (easily dirtying members like max_entries intentionally as well) while having subsequent values in cache. Quoting from Google's Project Zero blog [1]: Additionally, at least on the Intel machine on which this was tested, bouncing modified cache lines between cores is slow, apparently because the MESI protocol is used for cache coherence [8]. Changing the reference counter of an eBPF array on one physical CPU core causes the cache line containing the reference counter to be bounced over to that CPU core, making reads of the reference counter on all other CPU cores slow until the changed reference counter has been written back to memory. Because the length and the reference counter of an eBPF array are stored in the same cache line, this also means that changing the reference counter on one physical CPU core causes reads of the eBPF array's length to be slow on other physical CPU cores (intentional false sharing). While this doesn't 'control' the out-of-bounds speculation through masking the index as in commit b2157399cc98, triggering a manipulation of the map's reference counter is really trivial, so lets not allow to easily affect max_entries from it. Splitting to separate cachelines also generally makes sense from a performance perspective anyway in that fast-path won't have a cache miss if the map gets pinned, reused in other progs, etc out of control path, thus also avoids unintentional false sharing. [1] https://googleprojectzero.blogspot.ch/2018/01/reading-privileged-memory-with-side.html Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-01-09 20:17:44 +08:00
/* The 3rd and 4th cacheline with misc members to avoid false sharing
bpf: avoid false sharing of map refcount with max_entries In addition to commit b2157399cc98 ("bpf: prevent out-of-bounds speculation") also change the layout of struct bpf_map such that false sharing of fast-path members like max_entries is avoided when the maps reference counter is altered. Therefore enforce them to be placed into separate cachelines. pahole dump after change: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ u32 pages; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ bool unpriv_array; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ struct user_struct * user; /* 64 8 */ atomic_t refcnt; /* 72 4 */ atomic_t usercnt; /* 76 4 */ struct work_struct work; /* 80 32 */ char name[16]; /* 112 16 */ /* --- cacheline 2 boundary (128 bytes) --- */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 121, holes: 1, sum holes: 7 */ }; Now all entries in the first cacheline are read only throughout the life time of the map, set up once during map creation. Overall struct size and number of cachelines doesn't change from the reordering. struct bpf_map is usually first member and embedded in map structs in specific map implementations, so also avoid those members to sit at the end where it could potentially share the cacheline with first map values e.g. in the array since remote CPUs could trigger map updates just as well for those (easily dirtying members like max_entries intentionally as well) while having subsequent values in cache. Quoting from Google's Project Zero blog [1]: Additionally, at least on the Intel machine on which this was tested, bouncing modified cache lines between cores is slow, apparently because the MESI protocol is used for cache coherence [8]. Changing the reference counter of an eBPF array on one physical CPU core causes the cache line containing the reference counter to be bounced over to that CPU core, making reads of the reference counter on all other CPU cores slow until the changed reference counter has been written back to memory. Because the length and the reference counter of an eBPF array are stored in the same cache line, this also means that changing the reference counter on one physical CPU core causes reads of the eBPF array's length to be slow on other physical CPU cores (intentional false sharing). While this doesn't 'control' the out-of-bounds speculation through masking the index as in commit b2157399cc98, triggering a manipulation of the map's reference counter is really trivial, so lets not allow to easily affect max_entries from it. Splitting to separate cachelines also generally makes sense from a performance perspective anyway in that fast-path won't have a cache miss if the map gets pinned, reused in other progs, etc out of control path, thus also avoids unintentional false sharing. [1] https://googleprojectzero.blogspot.ch/2018/01/reading-privileged-memory-with-side.html Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-01-09 20:17:44 +08:00
* particularly with refcounting.
*/
struct user_struct *user ____cacheline_aligned;
atomic_t refcnt;
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>
2015-11-25 04:28:15 +08:00
atomic_t usercnt;
bpf: avoid false sharing of map refcount with max_entries In addition to commit b2157399cc98 ("bpf: prevent out-of-bounds speculation") also change the layout of struct bpf_map such that false sharing of fast-path members like max_entries is avoided when the maps reference counter is altered. Therefore enforce them to be placed into separate cachelines. pahole dump after change: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ u32 pages; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ bool unpriv_array; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ struct user_struct * user; /* 64 8 */ atomic_t refcnt; /* 72 4 */ atomic_t usercnt; /* 76 4 */ struct work_struct work; /* 80 32 */ char name[16]; /* 112 16 */ /* --- cacheline 2 boundary (128 bytes) --- */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 121, holes: 1, sum holes: 7 */ }; Now all entries in the first cacheline are read only throughout the life time of the map, set up once during map creation. Overall struct size and number of cachelines doesn't change from the reordering. struct bpf_map is usually first member and embedded in map structs in specific map implementations, so also avoid those members to sit at the end where it could potentially share the cacheline with first map values e.g. in the array since remote CPUs could trigger map updates just as well for those (easily dirtying members like max_entries intentionally as well) while having subsequent values in cache. Quoting from Google's Project Zero blog [1]: Additionally, at least on the Intel machine on which this was tested, bouncing modified cache lines between cores is slow, apparently because the MESI protocol is used for cache coherence [8]. Changing the reference counter of an eBPF array on one physical CPU core causes the cache line containing the reference counter to be bounced over to that CPU core, making reads of the reference counter on all other CPU cores slow until the changed reference counter has been written back to memory. Because the length and the reference counter of an eBPF array are stored in the same cache line, this also means that changing the reference counter on one physical CPU core causes reads of the eBPF array's length to be slow on other physical CPU cores (intentional false sharing). While this doesn't 'control' the out-of-bounds speculation through masking the index as in commit b2157399cc98, triggering a manipulation of the map's reference counter is really trivial, so lets not allow to easily affect max_entries from it. Splitting to separate cachelines also generally makes sense from a performance perspective anyway in that fast-path won't have a cache miss if the map gets pinned, reused in other progs, etc out of control path, thus also avoids unintentional false sharing. [1] https://googleprojectzero.blogspot.ch/2018/01/reading-privileged-memory-with-side.html Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-01-09 20:17:44 +08:00
struct work_struct work;
char name[BPF_OBJ_NAME_LEN];
};
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
static inline bool map_value_has_spin_lock(const struct bpf_map *map)
{
return map->spin_lock_off >= 0;
}
static inline void check_and_init_map_lock(struct bpf_map *map, void *dst)
{
if (likely(!map_value_has_spin_lock(map)))
return;
*(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
(struct bpf_spin_lock){};
}
/* copy everything but bpf_spin_lock */
static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
{
if (unlikely(map_value_has_spin_lock(map))) {
u32 off = map->spin_lock_off;
memcpy(dst, src, off);
memcpy(dst + off + sizeof(struct bpf_spin_lock),
src + off + sizeof(struct bpf_spin_lock),
map->value_size - off - sizeof(struct bpf_spin_lock));
} else {
memcpy(dst, src, map->value_size);
}
}
void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
bool lock_src);
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
struct bpf_offload_dev;
struct bpf_offloaded_map;
struct bpf_map_dev_ops {
int (*map_get_next_key)(struct bpf_offloaded_map *map,
void *key, void *next_key);
int (*map_lookup_elem)(struct bpf_offloaded_map *map,
void *key, void *value);
int (*map_update_elem)(struct bpf_offloaded_map *map,
void *key, void *value, u64 flags);
int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key);
};
struct bpf_offloaded_map {
struct bpf_map map;
struct net_device *netdev;
const struct bpf_map_dev_ops *dev_ops;
void *dev_priv;
struct list_head offloads;
};
static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
{
return container_of(map, struct bpf_offloaded_map, map);
}
static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
{
return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return map->btf && map->ops->map_seq_show_elem;
}
int map_check_no_btf(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
extern const struct bpf_map_ops bpf_map_offload_ops;
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
/* function argument constraints */
enum bpf_arg_type {
ARG_DONTCARE = 0, /* unused argument in helper function */
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
/* the following constraints used to prototype
* bpf_map_lookup/update/delete_elem() functions
*/
ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */
ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */
bpf: Introduce bpf sk local storage After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-27 07:39:39 +08:00
ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
/* the following constraints used to prototype bpf_memcmp() and other
* functions that access data on eBPF program stack
*/
ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */
ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */
ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized,
* helper function must fill all bytes or clear
* them in error case.
bpf, verifier: add ARG_PTR_TO_RAW_STACK type When passing buffers from eBPF stack space into a helper function, we have ARG_PTR_TO_STACK argument type for helpers available. The verifier makes sure that such buffers are initialized, within boundaries, etc. However, the downside with this is that we have a couple of helper functions such as bpf_skb_load_bytes() that fill out the passed buffer in the expected success case anyway, so zero initializing them prior to the helper call is unneeded/wasted instructions in the eBPF program that can be avoided. Therefore, add a new helper function argument type called ARG_PTR_TO_RAW_STACK. The idea is to skip the STACK_MISC check in check_stack_boundary() and color the related stack slots as STACK_MISC after we checked all call arguments. Helper functions using ARG_PTR_TO_RAW_STACK must make sure that every path of the helper function will fill the provided buffer area, so that we cannot leak any uninitialized stack memory. This f.e. means that error paths need to memset() the buffers, but the expected fast-path doesn't have to do this anymore. Since there's no such helper needing more than at most one ARG_PTR_TO_RAW_STACK argument, we can keep it simple and don't need to check for multiple areas. Should in future such a use-case really appear, we have check_raw_mode() that will make sure we implement support for it first. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-13 06:10:51 +08:00
*/
ARG_CONST_SIZE, /* number of bytes accessed from memory */
ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */
ARG_PTR_TO_CTX, /* pointer to context */
ARG_ANYTHING, /* any (initialized) argument is ok */
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
bpf: Add a bpf_sock pointer to __sk_buff and a bpf_sk_fullsock helper In kernel, it is common to check "skb->sk && sk_fullsock(skb->sk)" before accessing the fields in sock. For example, in __netdev_pick_tx: static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* ... */ struct sock *sk = skb->sk; if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); /* ... */ return queue_index; } This patch adds a "struct bpf_sock *sk" pointer to the "struct __sk_buff" where a few of the convert_ctx_access() in filter.c has already been accessing the skb->sk sock_common's fields, e.g. sock_ops_convert_ctx_access(). "__sk_buff->sk" is a PTR_TO_SOCK_COMMON_OR_NULL in the verifier. Some of the fileds in "bpf_sock" will not be directly accessible through the "__sk_buff->sk" pointer. It is limited by the new "bpf_sock_common_is_valid_access()". e.g. The existing "type", "protocol", "mark" and "priority" in bpf_sock are not allowed. The newly added "struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)" can be used to get a sk with all accessible fields in "bpf_sock". This helper is added to both cg_skb and sched_(cls|act). int cg_skb_foo(struct __sk_buff *skb) { struct bpf_sock *sk; sk = skb->sk; if (!sk) return 1; sk = bpf_sk_fullsock(sk); if (!sk) return 1; if (sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP) return 1; /* some_traffic_shaping(); */ return 1; } (1) The sk is read only (2) There is no new "struct bpf_sock_common" introduced. (3) Future kernel sock's members could be added to bpf_sock only instead of repeatedly adding at multiple places like currently in bpf_sock_ops_md, bpf_sock_addr_md, sk_reuseport_md...etc. (4) After "sk = skb->sk", the reg holding sk is in type PTR_TO_SOCK_COMMON_OR_NULL. (5) After bpf_sk_fullsock(), the return type will be in type PTR_TO_SOCKET_OR_NULL which is the same as the return type of bpf_sk_lookup_xxx(). However, bpf_sk_fullsock() does not take refcnt. The acquire_reference_state() is only depending on the return type now. To avoid it, a new is_acquire_function() is checked before calling acquire_reference_state(). (6) The WARN_ON in "release_reference_state()" is no longer an internal verifier bug. When reg->id is not found in state->refs[], it means the bpf_prog does something wrong like "bpf_sk_release(bpf_sk_fullsock(skb->sk))" where reference has never been acquired by calling "bpf_sk_fullsock(skb->sk)". A -EINVAL and a verbose are done instead of WARN_ON. A test is added to the test_verifier in a later patch. Since the WARN_ON in "release_reference_state()" is no longer needed, "__release_reference_state()" is folded into "release_reference_state()" also. Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-02-10 15:22:20 +08:00
ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
ARG_PTR_TO_INT, /* pointer to int */
ARG_PTR_TO_LONG, /* pointer to long */
bpf: Introduce bpf sk local storage After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-27 07:39:39 +08:00
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
};
/* type of values returned from helper functions */
enum bpf_return_type {
RET_INTEGER, /* function returns integer */
RET_VOID, /* function doesn't return anything */
RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */
RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */
RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */
RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
};
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
* to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
* instructions after verifying
*/
struct bpf_func_proto {
u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
bool gpl_only;
bpf: direct packet write and access for helpers for clsact progs This work implements direct packet access for helpers and direct packet write in a similar fashion as already available for XDP types via commits 4acf6c0b84c9 ("bpf: enable direct packet data write for xdp progs") and 6841de8b0d03 ("bpf: allow helpers access the packet directly"), and as a complementary feature to the already available direct packet read for tc (cls/act) programs. For enabling this, we need to introduce two helpers, bpf_skb_pull_data() and bpf_csum_update(). The first is generally needed for both, read and write, because they would otherwise only be limited to the current linear skb head. Usually, when the data_end test fails, programs just bail out, or, in the direct read case, use bpf_skb_load_bytes() as an alternative to overcome this limitation. If such data sits in non-linear parts, we can just pull them in once with the new helper, retest and eventually access them. At the same time, this also makes sure the skb is uncloned, which is, of course, a necessary condition for direct write. As this needs to be an invariant for the write part only, the verifier detects writes and adds a prologue that is calling bpf_skb_pull_data() to effectively unclone the skb from the very beginning in case it is indeed cloned. The heuristic makes use of a similar trick that was done in 233577a22089 ("net: filter: constify detection of pkt_type_offset"). This comes at zero cost for other programs that do not use the direct write feature. Should a program use this feature only sparsely and has read access for the most parts with, for example, drop return codes, then such write action can be delegated to a tail called program for mitigating this cost of potential uncloning to a late point in time where it would have been paid similarly with the bpf_skb_store_bytes() as well. Advantage of direct write is that the writes are inlined whereas the helper cannot make any length assumptions and thus needs to generate a call to memcpy() also for small sizes, as well as cost of helper call itself with sanity checks are avoided. Plus, when direct read is already used, we don't need to cache or perform rechecks on the data boundaries (due to verifier invalidating previous checks for helpers that change skb->data), so more complex programs using rewrites can benefit from switching to direct read plus write. For direct packet access to helpers, we save the otherwise needed copy into a temp struct sitting on stack memory when use-case allows. Both facilities are enabled via may_access_direct_pkt_data() in verifier. For now, we limit this to map helpers and csum_diff, and can successively enable other helpers where we find it makes sense. Helpers that definitely cannot be allowed for this are those part of bpf_helper_changes_skb_data() since they can change underlying data, and those that write into memory as this could happen for packet typed args when still cloned. bpf_csum_update() helper accommodates for the fact that we need to fixup checksum_complete when using direct write instead of bpf_skb_store_bytes(), meaning the programs can use available helpers like bpf_csum_diff(), and implement csum_add(), csum_sub(), csum_block_add(), csum_block_sub() equivalents in eBPF together with the new helper. A usage example will be provided for iproute2's examples/bpf/ directory. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 06:26:13 +08:00
bool pkt_access;
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
enum bpf_return_type ret_type;
enum bpf_arg_type arg1_type;
enum bpf_arg_type arg2_type;
enum bpf_arg_type arg3_type;
enum bpf_arg_type arg4_type;
enum bpf_arg_type arg5_type;
};
/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
* the first argument to eBPF programs.
* For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
*/
struct bpf_context;
enum bpf_access_type {
BPF_READ = 1,
BPF_WRITE = 2
};
/* types of values stored in eBPF registers */
/* Pointer types represent:
* pointer
* pointer + imm
* pointer + (u16) var
* pointer + (u16) var + imm
* if (range > 0) then [ptr, ptr + range - off) is safe to access
* if (id > 0) means that some 'var' was added
* if (off > 0) means that 'imm' was added
*/
enum bpf_reg_type {
NOT_INIT = 0, /* nothing was written into register */
SCALAR_VALUE, /* reg doesn't contain a valid pointer */
PTR_TO_CTX, /* reg points to bpf_context */
CONST_PTR_TO_MAP, /* reg points to struct bpf_map */
PTR_TO_MAP_VALUE, /* reg points to map element value */
PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
PTR_TO_STACK, /* reg == frame_pointer + offset */
bpf: add meta pointer for direct access This work enables generic transfer of metadata from XDP into skb. The basic idea is that we can make use of the fact that the resulting skb must be linear and already comes with a larger headroom for supporting bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work on a similar principle and introduce a small helper bpf_xdp_adjust_meta() for adjusting a new pointer called xdp->data_meta. Thus, the packet has a flexible and programmable room for meta data, followed by the actual packet data. struct xdp_buff is therefore laid out that we first point to data_hard_start, then data_meta directly prepended to data followed by data_end marking the end of packet. bpf_xdp_adjust_head() takes into account whether we have meta data already prepended and if so, memmove()s this along with the given offset provided there's enough room. xdp->data_meta is optional and programs are not required to use it. The rationale is that when we process the packet in XDP (e.g. as DoS filter), we can push further meta data along with it for the XDP_PASS case, and give the guarantee that a clsact ingress BPF program on the same device can pick this up for further post-processing. Since we work with skb there, we can also set skb->mark, skb->priority or other skb meta data out of BPF, thus having this scratch space generic and programmable allows for more flexibility than defining a direct 1:1 transfer of potentially new XDP members into skb (it's also more efficient as we don't need to initialize/handle each of such new members). The facility also works together with GRO aggregation. The scratch space at the head of the packet can be multiple of 4 byte up to 32 byte large. Drivers not yet supporting xdp->data_meta can simply be set up with xdp->data_meta as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out, such that the subsequent match against xdp->data for later access is guaranteed to fail. The verifier treats xdp->data_meta/xdp->data the same way as we treat xdp->data/xdp->data_end pointer comparisons. The requirement for doing the compare against xdp->data is that it hasn't been modified from it's original address we got from ctx access. It may have a range marking already from prior successful xdp->data/xdp->data_end pointer comparisons though. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-25 08:25:51 +08:00
PTR_TO_PACKET_META, /* skb->data - meta_len */
PTR_TO_PACKET, /* reg points to skb->data */
PTR_TO_PACKET_END, /* skb->data + headlen */
PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */
PTR_TO_SOCKET, /* reg points to struct bpf_sock */
PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */
bpf: Add a bpf_sock pointer to __sk_buff and a bpf_sk_fullsock helper In kernel, it is common to check "skb->sk && sk_fullsock(skb->sk)" before accessing the fields in sock. For example, in __netdev_pick_tx: static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* ... */ struct sock *sk = skb->sk; if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); /* ... */ return queue_index; } This patch adds a "struct bpf_sock *sk" pointer to the "struct __sk_buff" where a few of the convert_ctx_access() in filter.c has already been accessing the skb->sk sock_common's fields, e.g. sock_ops_convert_ctx_access(). "__sk_buff->sk" is a PTR_TO_SOCK_COMMON_OR_NULL in the verifier. Some of the fileds in "bpf_sock" will not be directly accessible through the "__sk_buff->sk" pointer. It is limited by the new "bpf_sock_common_is_valid_access()". e.g. The existing "type", "protocol", "mark" and "priority" in bpf_sock are not allowed. The newly added "struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)" can be used to get a sk with all accessible fields in "bpf_sock". This helper is added to both cg_skb and sched_(cls|act). int cg_skb_foo(struct __sk_buff *skb) { struct bpf_sock *sk; sk = skb->sk; if (!sk) return 1; sk = bpf_sk_fullsock(sk); if (!sk) return 1; if (sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP) return 1; /* some_traffic_shaping(); */ return 1; } (1) The sk is read only (2) There is no new "struct bpf_sock_common" introduced. (3) Future kernel sock's members could be added to bpf_sock only instead of repeatedly adding at multiple places like currently in bpf_sock_ops_md, bpf_sock_addr_md, sk_reuseport_md...etc. (4) After "sk = skb->sk", the reg holding sk is in type PTR_TO_SOCK_COMMON_OR_NULL. (5) After bpf_sk_fullsock(), the return type will be in type PTR_TO_SOCKET_OR_NULL which is the same as the return type of bpf_sk_lookup_xxx(). However, bpf_sk_fullsock() does not take refcnt. The acquire_reference_state() is only depending on the return type now. To avoid it, a new is_acquire_function() is checked before calling acquire_reference_state(). (6) The WARN_ON in "release_reference_state()" is no longer an internal verifier bug. When reg->id is not found in state->refs[], it means the bpf_prog does something wrong like "bpf_sk_release(bpf_sk_fullsock(skb->sk))" where reference has never been acquired by calling "bpf_sk_fullsock(skb->sk)". A -EINVAL and a verbose are done instead of WARN_ON. A test is added to the test_verifier in a later patch. Since the WARN_ON in "release_reference_state()" is no longer needed, "__release_reference_state()" is folded into "release_reference_state()" also. Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-02-10 15:22:20 +08:00
PTR_TO_SOCK_COMMON, /* reg points to sock_common */
PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */
PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */
};
/* The information passed from prog-specific *_is_valid_access
* back to the verifier.
*/
struct bpf_insn_access_aux {
enum bpf_reg_type reg_type;
int ctx_field_size;
};
bpf: simplify narrower ctx access This work tries to make the semantics and code around the narrower ctx access a bit easier to follow. Right now everything is done inside the .is_valid_access(). Offset matching is done differently for read/write types, meaning writes don't support narrower access and thus matching only on offsetof(struct foo, bar) is enough whereas for read case that supports narrower access we must check for offsetof(struct foo, bar) + offsetof(struct foo, bar) + sizeof(<bar>) - 1 for each of the cases. For read cases of individual members that don't support narrower access (like packet pointers or skb->cb[] case which has its own narrow access logic), we check as usual only offsetof(struct foo, bar) like in write case. Then, for the case where narrower access is allowed, we also need to set the aux info for the access. Meaning, ctx_field_size and converted_op_size have to be set. First is the original field size e.g. sizeof(<bar>) as in above example from the user facing ctx, and latter one is the target size after actual rewrite happened, thus for the kernel facing ctx. Also here we need the range match and we need to keep track changing convert_ctx_access() and converted_op_size from is_valid_access() as both are not at the same location. We can simplify the code a bit: check_ctx_access() becomes simpler in that we only store ctx_field_size as a meta data and later in convert_ctx_accesses() we fetch the target_size right from the location where we do convert. Should the verifier be misconfigured we do reject for BPF_WRITE cases or target_size that are not provided. For the subsystems, we always work on ranges in is_valid_access() and add small helpers for ranges and narrow access, convert_ctx_accesses() sets target_size for the relevant instruction. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Cc: Yonghong Song <yhs@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-02 08:13:27 +08:00
static inline void
bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
{
aux->ctx_field_size = size;
}
struct bpf_prog_ops {
int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
};
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
bpf: Check attach type at prog load time == The problem == There are use-cases when a program of some type can be attached to multiple attach points and those attach points must have different permissions to access context or to call helpers. E.g. context structure may have fields for both IPv4 and IPv6 but it doesn't make sense to read from / write to IPv6 field when attach point is somewhere in IPv4 stack. Same applies to BPF-helpers: it may make sense to call some helper from some attach point, but not from other for same prog type. == The solution == Introduce `expected_attach_type` field in in `struct bpf_attr` for `BPF_PROG_LOAD` command. If scenario described in "The problem" section is the case for some prog type, the field will be checked twice: 1) At load time prog type is checked to see if attach type for it must be known to validate program permissions correctly. Prog will be rejected with EINVAL if it's the case and `expected_attach_type` is not specified or has invalid value. 2) At attach time `attach_type` is compared with `expected_attach_type`, if prog type requires to have one, and, if they differ, attach will be rejected with EINVAL. The `expected_attach_type` is now available as part of `struct bpf_prog` in both `bpf_verifier_ops->is_valid_access()` and `bpf_verifier_ops->get_func_proto()` () and can be used to check context accesses and calls to helpers correspondingly. Initially the idea was discussed by Alexei Starovoitov <ast@fb.com> and Daniel Borkmann <daniel@iogearbox.net> here: https://marc.info/?l=linux-netdev&m=152107378717201&w=2 Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-31 06:08:00 +08:00
const struct bpf_func_proto *
(*get_func_proto)(enum bpf_func_id func_id,
const struct bpf_prog *prog);
bpf: verifier (add verifier core) This patch adds verifier core which simulates execution of every insn and records the state of registers and program stack. Every branch instruction seen during simulation is pushed into state stack. When verifier reaches BPF_EXIT, it pops the state from the stack and continues until it reaches BPF_EXIT again. For program: 1: bpf_mov r1, xxx 2: if (r1 == 0) goto 5 3: bpf_mov r0, 1 4: goto 6 5: bpf_mov r0, 2 6: bpf_exit The verifier will walk insns: 1, 2, 3, 4, 6 then it will pop the state recorded at insn#2 and will continue: 5, 6 This way it walks all possible paths through the program and checks all possible values of registers. While doing so, it checks for: - invalid instructions - uninitialized register access - uninitialized stack access - misaligned stack access - out of range stack access - invalid calling convention - instruction encoding is not using reserved fields Kernel subsystem configures the verifier with two callbacks: - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); that provides information to the verifer which fields of 'ctx' are accessible (remember 'ctx' is the first argument to eBPF program) - const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); returns argument constraints of kernel helper functions that eBPF program may call, so that verifier can checks that R1-R5 types match the prototype More details in Documentation/networking/filter.txt and in kernel/bpf/verifier.c Signed-off-by: Alexei Starovoitov <ast@plumgrid.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-26 15:17:06 +08:00
/* return true if 'size' wide access at offset 'off' within bpf_context
* with 'type' (read or write) is allowed
*/
bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
bpf: Check attach type at prog load time == The problem == There are use-cases when a program of some type can be attached to multiple attach points and those attach points must have different permissions to access context or to call helpers. E.g. context structure may have fields for both IPv4 and IPv6 but it doesn't make sense to read from / write to IPv6 field when attach point is somewhere in IPv4 stack. Same applies to BPF-helpers: it may make sense to call some helper from some attach point, but not from other for same prog type. == The solution == Introduce `expected_attach_type` field in in `struct bpf_attr` for `BPF_PROG_LOAD` command. If scenario described in "The problem" section is the case for some prog type, the field will be checked twice: 1) At load time prog type is checked to see if attach type for it must be known to validate program permissions correctly. Prog will be rejected with EINVAL if it's the case and `expected_attach_type` is not specified or has invalid value. 2) At attach time `attach_type` is compared with `expected_attach_type`, if prog type requires to have one, and, if they differ, attach will be rejected with EINVAL. The `expected_attach_type` is now available as part of `struct bpf_prog` in both `bpf_verifier_ops->is_valid_access()` and `bpf_verifier_ops->get_func_proto()` () and can be used to check context accesses and calls to helpers correspondingly. Initially the idea was discussed by Alexei Starovoitov <ast@fb.com> and Daniel Borkmann <daniel@iogearbox.net> here: https://marc.info/?l=linux-netdev&m=152107378717201&w=2 Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-03-31 06:08:00 +08:00
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
bpf: direct packet write and access for helpers for clsact progs This work implements direct packet access for helpers and direct packet write in a similar fashion as already available for XDP types via commits 4acf6c0b84c9 ("bpf: enable direct packet data write for xdp progs") and 6841de8b0d03 ("bpf: allow helpers access the packet directly"), and as a complementary feature to the already available direct packet read for tc (cls/act) programs. For enabling this, we need to introduce two helpers, bpf_skb_pull_data() and bpf_csum_update(). The first is generally needed for both, read and write, because they would otherwise only be limited to the current linear skb head. Usually, when the data_end test fails, programs just bail out, or, in the direct read case, use bpf_skb_load_bytes() as an alternative to overcome this limitation. If such data sits in non-linear parts, we can just pull them in once with the new helper, retest and eventually access them. At the same time, this also makes sure the skb is uncloned, which is, of course, a necessary condition for direct write. As this needs to be an invariant for the write part only, the verifier detects writes and adds a prologue that is calling bpf_skb_pull_data() to effectively unclone the skb from the very beginning in case it is indeed cloned. The heuristic makes use of a similar trick that was done in 233577a22089 ("net: filter: constify detection of pkt_type_offset"). This comes at zero cost for other programs that do not use the direct write feature. Should a program use this feature only sparsely and has read access for the most parts with, for example, drop return codes, then such write action can be delegated to a tail called program for mitigating this cost of potential uncloning to a late point in time where it would have been paid similarly with the bpf_skb_store_bytes() as well. Advantage of direct write is that the writes are inlined whereas the helper cannot make any length assumptions and thus needs to generate a call to memcpy() also for small sizes, as well as cost of helper call itself with sanity checks are avoided. Plus, when direct read is already used, we don't need to cache or perform rechecks on the data boundaries (due to verifier invalidating previous checks for helpers that change skb->data), so more complex programs using rewrites can benefit from switching to direct read plus write. For direct packet access to helpers, we save the otherwise needed copy into a temp struct sitting on stack memory when use-case allows. Both facilities are enabled via may_access_direct_pkt_data() in verifier. For now, we limit this to map helpers and csum_diff, and can successively enable other helpers where we find it makes sense. Helpers that definitely cannot be allowed for this are those part of bpf_helper_changes_skb_data() since they can change underlying data, and those that write into memory as this could happen for packet typed args when still cloned. bpf_csum_update() helper accommodates for the fact that we need to fixup checksum_complete when using direct write instead of bpf_skb_store_bytes(), meaning the programs can use available helpers like bpf_csum_diff(), and implement csum_add(), csum_sub(), csum_block_add(), csum_block_sub() equivalents in eBPF together with the new helper. A usage example will be provided for iproute2's examples/bpf/ directory. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-20 06:26:13 +08:00
int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
const struct bpf_prog *prog);
bpf: implement ld_abs/ld_ind in native bpf The main part of this work is to finally allow removal of LD_ABS and LD_IND from the BPF core by reimplementing them through native eBPF instead. Both LD_ABS/LD_IND were carried over from cBPF and keeping them around in native eBPF caused way more trouble than actually worth it. To just list some of the security issues in the past: * fdfaf64e7539 ("x86: bpf_jit: support negative offsets") * 35607b02dbef ("sparc: bpf_jit: fix loads from negative offsets") * e0ee9c12157d ("x86: bpf_jit: fix two bugs in eBPF JIT compiler") * 07aee9439454 ("bpf, sparc: fix usage of wrong reg for load_skb_regs after call") * 6d59b7dbf72e ("bpf, s390x: do not reload skb pointers in non-skb context") * 87338c8e2cbb ("bpf, ppc64: do not reload skb pointers in non-skb context") For programs in native eBPF, LD_ABS/LD_IND are pretty much legacy these days due to their limitations and more efficient/flexible alternatives that have been developed over time such as direct packet access. LD_ABS/LD_IND only cover 1/2/4 byte loads into a register, the load happens in host endianness and its exception handling can yield unexpected behavior. The latter is explained in depth in f6b1b3bf0d5f ("bpf: fix subprog verifier bypass by div/mod by 0 exception") with similar cases of exceptions we had. In native eBPF more recent program types will disable LD_ABS/LD_IND altogether through may_access_skb() in verifier, and given the limitations in terms of exception handling, it's also disabled in programs that use BPF to BPF calls. In terms of cBPF, the LD_ABS/LD_IND is used in networking programs to access packet data. It is not used in seccomp-BPF but programs that use it for socket filtering or reuseport for demuxing with cBPF. This is mostly relevant for applications that have not yet migrated to native eBPF. The main complexity and source of bugs in LD_ABS/LD_IND is coming from their implementation in the various JITs. Most of them keep the model around from cBPF times by implementing a fastpath written in asm. They use typically two from the BPF program hidden CPU registers for caching the skb's headlen (skb->len - skb->data_len) and skb->data. Throughout the JIT phase this requires to keep track whether LD_ABS/LD_IND are used and if so, the two registers need to be recached each time a BPF helper would change the underlying packet data in native eBPF case. At least in eBPF case, available CPU registers are rare and the additional exit path out of the asm written JIT helper makes it also inflexible since not all parts of the JITer are in control from plain C. A LD_ABS/LD_IND implementation in eBPF therefore allows to significantly reduce the complexity in JITs with comparable performance results for them, e.g.: test_bpf tcpdump port 22 tcpdump complex x64 - before 15 21 10 14 19 18 - after 7 10 10 7 10 15 arm64 - before 40 91 92 40 91 151 - after 51 64 73 51 62 113 For cBPF we now track any usage of LD_ABS/LD_IND in bpf_convert_filter() and cache the skb's headlen and data in the cBPF prologue. The BPF_REG_TMP gets remapped from R8 to R2 since it's mainly just used as a local temporary variable. This allows to shrink the image on x86_64 also for seccomp programs slightly since mapping to %rsi is not an ereg. In callee-saved R8 and R9 we now track skb data and headlen, respectively. For normal prologue emission in the JITs this does not add any extra instructions since R8, R9 are pushed to stack in any case from eBPF side. cBPF uses the convert_bpf_ld_abs() emitter which probes the fast path inline already and falls back to bpf_skb_load_helper_{8,16,32}() helper relying on the cached skb data and headlen as well. R8 and R9 never need to be reloaded due to bpf_helper_changes_pkt_data() since all skb access in cBPF is read-only. Then, for the case of native eBPF, we use the bpf_gen_ld_abs() emitter, which calls the bpf_skb_load_helper_{8,16,32}_no_cache() helper unconditionally, does neither cache skb data and headlen nor has an inlined fast path. The reason for the latter is that native eBPF does not have any extra registers available anyway, but even if there were, it avoids any reload of skb data and headlen in the first place. Additionally, for the negative offsets, we provide an alternative bpf_skb_load_bytes_relative() helper in eBPF which operates similarly as bpf_skb_load_bytes() and allows for more flexibility. Tested myself on x64, arm64, s390x, from Sandipan on ppc64. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-05-04 07:08:14 +08:00
int (*gen_ld_abs)(const struct bpf_insn *orig,
struct bpf_insn *insn_buf);
u32 (*convert_ctx_access)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
bpf: simplify narrower ctx access This work tries to make the semantics and code around the narrower ctx access a bit easier to follow. Right now everything is done inside the .is_valid_access(). Offset matching is done differently for read/write types, meaning writes don't support narrower access and thus matching only on offsetof(struct foo, bar) is enough whereas for read case that supports narrower access we must check for offsetof(struct foo, bar) + offsetof(struct foo, bar) + sizeof(<bar>) - 1 for each of the cases. For read cases of individual members that don't support narrower access (like packet pointers or skb->cb[] case which has its own narrow access logic), we check as usual only offsetof(struct foo, bar) like in write case. Then, for the case where narrower access is allowed, we also need to set the aux info for the access. Meaning, ctx_field_size and converted_op_size have to be set. First is the original field size e.g. sizeof(<bar>) as in above example from the user facing ctx, and latter one is the target size after actual rewrite happened, thus for the kernel facing ctx. Also here we need the range match and we need to keep track changing convert_ctx_access() and converted_op_size from is_valid_access() as both are not at the same location. We can simplify the code a bit: check_ctx_access() becomes simpler in that we only store ctx_field_size as a meta data and later in convert_ctx_accesses() we fetch the target_size right from the location where we do convert. Should the verifier be misconfigured we do reject for BPF_WRITE cases or target_size that are not provided. For the subsystems, we always work on ranges in is_valid_access() and add small helpers for ranges and narrow access, convert_ctx_accesses() sets target_size for the relevant instruction. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Cc: Yonghong Song <yhs@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-02 08:13:27 +08:00
struct bpf_prog *prog, u32 *target_size);
};
struct bpf_prog_offload_ops {
/* verifier basic callbacks */
int (*insn_hook)(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int (*finalize)(struct bpf_verifier_env *env);
/* verifier optimization callbacks (called after .finalize) */
int (*replace_insn)(struct bpf_verifier_env *env, u32 off,
struct bpf_insn *insn);
int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt);
/* program management callbacks */
int (*prepare)(struct bpf_prog *prog);
int (*translate)(struct bpf_prog *prog);
void (*destroy)(struct bpf_prog *prog);
};
struct bpf_prog_offload {
struct bpf_prog *prog;
struct net_device *netdev;
struct bpf_offload_dev *offdev;
void *dev_priv;
struct list_head offloads;
bool dev_state;
bool opt_failed;
void *jited_image;
u32 jited_len;
};
enum bpf_cgroup_storage_type {
BPF_CGROUP_STORAGE_SHARED,
BPF_CGROUP_STORAGE_PERCPU,
__BPF_CGROUP_STORAGE_MAX
};
#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
struct bpf_prog_stats {
u64 cnt;
u64 nsecs;
struct u64_stats_sync syncp;
};
struct bpf_prog_aux {
atomic_t refcnt;
u32 used_map_cnt;
u32 max_ctx_offset;
u32 max_pkt_offset;
u32 max_tp_access;
u32 stack_depth;
u32 id;
u32 func_cnt; /* used by non-func prog as the number of func progs */
u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
bool offload_requested;
bpf: x64: add JIT support for multi-function programs Typical JIT does several passes over bpf instructions to compute total size and relative offsets of jumps and calls. With multitple bpf functions calling each other all relative calls will have invalid offsets intially therefore we need to additional last pass over the program to emit calls with correct offsets. For example in case of three bpf functions: main: call foo call bpf_map_lookup exit foo: call bar exit bar: exit We will call bpf_int_jit_compile() indepedently for main(), foo() and bar() x64 JIT typically does 4-5 passes to converge. After these initial passes the image for these 3 functions will be good except call targets, since start addresses of foo() and bar() are unknown when we were JITing main() (note that call bpf_map_lookup will be resolved properly during initial passes). Once start addresses of 3 functions are known we patch call_insn->imm to point to right functions and call bpf_int_jit_compile() again which needs only one pass. Additional safety checks are done to make sure this last pass doesn't produce image that is larger or smaller than previous pass. When constant blinding is on it's applied to all functions at the first pass, since doing it once again at the last pass can change size of the JITed code. Tested on x64 and arm64 hw with JIT on/off, blinding on/off. x64 jits bpf-to-bpf calls correctly while arm64 falls back to interpreter. All other JITs that support normal BPF_CALL will behave the same way since bpf-to-bpf call is equivalent to bpf-to-kernel call from JITs point of view. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:15 +08:00
struct bpf_prog **func;
void *jit_data; /* JIT specific data. arch dependent */
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>
2017-02-17 05:24:50 +08:00
struct latch_tree_node ksym_tnode;
struct list_head ksym_lnode;
const struct bpf_prog_ops *ops;
struct bpf_map **used_maps;
struct bpf_prog *prog;
struct user_struct *user;
u64 load_time; /* ns since boottime */
struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
char name[BPF_OBJ_NAME_LEN];
#ifdef CONFIG_SECURITY
void *security;
#endif
struct bpf_prog_offload *offload;
bpf: Introduce bpf_func_info This patch added interface to load a program with the following additional information: . prog_btf_fd . func_info, func_info_rec_size and func_info_cnt where func_info will provide function range and type_id corresponding to each function. The func_info_rec_size is introduced in the UAPI to specify struct bpf_func_info size passed from user space. This intends to make bpf_func_info structure growable in the future. If the kernel gets a different bpf_func_info size from userspace, it will try to handle user request with part of bpf_func_info it can understand. In this patch, kernel can understand struct bpf_func_info { __u32 insn_offset; __u32 type_id; }; If user passed a bpf func_info record size of 16 bytes, the kernel can still handle part of records with the above definition. If verifier agrees with function range provided by the user, the bpf_prog ksym for each function will use the func name provided in the type_id, which is supposed to provide better encoding as it is not limited by 16 bytes program name limitation and this is better for bpf program which contains multiple subprograms. The bpf_prog_info interface is also extended to return btf_id, func_info, func_info_rec_size and func_info_cnt to userspace, so userspace can print out the function prototype for each xlated function. The insn_offset in the returned func_info corresponds to the insn offset for xlated functions. With other jit related fields in bpf_prog_info, userspace can also print out function prototypes for each jited function. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-11-20 07:29:11 +08:00
struct btf *btf;
struct bpf_func_info *func_info;
bpf: Add bpf_line_info support This patch adds bpf_line_info support. It accepts an array of bpf_line_info objects during BPF_PROG_LOAD. The "line_info", "line_info_cnt" and "line_info_rec_size" are added to the "union bpf_attr". The "line_info_rec_size" makes bpf_line_info extensible in the future. The new "check_btf_line()" ensures the userspace line_info is valid for the kernel to use. When the verifier is translating/patching the bpf_prog (through "bpf_patch_insn_single()"), the line_infos' insn_off is also adjusted by the newly added "bpf_adj_linfo()". If the bpf_prog is jited, this patch also provides the jited addrs (in aux->jited_linfo) for the corresponding line_info.insn_off. "bpf_prog_fill_jited_linfo()" is added to fill the aux->jited_linfo. It is currently called by the x86 jit. Other jits can also use "bpf_prog_fill_jited_linfo()" and it will be done in the followup patches. In the future, if it deemed necessary, a particular jit could also provide its own "bpf_prog_fill_jited_linfo()" implementation. A few "*line_info*" fields are added to the bpf_prog_info such that the user can get the xlated line_info back (i.e. the line_info with its insn_off reflecting the translated prog). The jited_line_info is available if the prog is jited. It is an array of __u64. If the prog is not jited, jited_line_info_cnt is 0. The verifier's verbose log with line_info will be done in a follow up patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-12-08 08:42:25 +08:00
/* bpf_line_info loaded from userspace. linfo->insn_off
* has the xlated insn offset.
* Both the main and sub prog share the same linfo.
* The subprog can access its first linfo by
* using the linfo_idx.
*/
struct bpf_line_info *linfo;
/* jited_linfo is the jited addr of the linfo. It has a
* one to one mapping to linfo:
* jited_linfo[i] is the jited addr for the linfo[i]->insn_off.
* Both the main and sub prog share the same jited_linfo.
* The subprog can access its first jited_linfo by
* using the linfo_idx.
*/
void **jited_linfo;
u32 func_info_cnt;
bpf: Add bpf_line_info support This patch adds bpf_line_info support. It accepts an array of bpf_line_info objects during BPF_PROG_LOAD. The "line_info", "line_info_cnt" and "line_info_rec_size" are added to the "union bpf_attr". The "line_info_rec_size" makes bpf_line_info extensible in the future. The new "check_btf_line()" ensures the userspace line_info is valid for the kernel to use. When the verifier is translating/patching the bpf_prog (through "bpf_patch_insn_single()"), the line_infos' insn_off is also adjusted by the newly added "bpf_adj_linfo()". If the bpf_prog is jited, this patch also provides the jited addrs (in aux->jited_linfo) for the corresponding line_info.insn_off. "bpf_prog_fill_jited_linfo()" is added to fill the aux->jited_linfo. It is currently called by the x86 jit. Other jits can also use "bpf_prog_fill_jited_linfo()" and it will be done in the followup patches. In the future, if it deemed necessary, a particular jit could also provide its own "bpf_prog_fill_jited_linfo()" implementation. A few "*line_info*" fields are added to the bpf_prog_info such that the user can get the xlated line_info back (i.e. the line_info with its insn_off reflecting the translated prog). The jited_line_info is available if the prog is jited. It is an array of __u64. If the prog is not jited, jited_line_info_cnt is 0. The verifier's verbose log with line_info will be done in a follow up patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-12-08 08:42:25 +08:00
u32 nr_linfo;
/* subprog can use linfo_idx to access its first linfo and
* jited_linfo.
* main prog always has linfo_idx == 0
*/
u32 linfo_idx;
struct bpf_prog_stats __percpu *stats;
union {
struct work_struct work;
struct rcu_head rcu;
};
};
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>
2015-05-20 07:59:03 +08:00
struct bpf_array {
struct bpf_map map;
u32 elem_size;
bpf: prevent out-of-bounds speculation Under speculation, CPUs may mis-predict branches in bounds checks. Thus, memory accesses under a bounds check may be speculated even if the bounds check fails, providing a primitive for building a side channel. To avoid leaking kernel data round up array-based maps and mask the index after bounds check, so speculated load with out of bounds index will load either valid value from the array or zero from the padded area. Unconditionally mask index for all array types even when max_entries are not rounded to power of 2 for root user. When map is created by unpriv user generate a sequence of bpf insns that includes AND operation to make sure that JITed code includes the same 'index & index_mask' operation. If prog_array map is created by unpriv user replace bpf_tail_call(ctx, map, index); with if (index >= max_entries) { index &= map->index_mask; bpf_tail_call(ctx, map, index); } (along with roundup to power 2) to prevent out-of-bounds speculation. There is secondary redundant 'if (index >= max_entries)' in the interpreter and in all JITs, but they can be optimized later if necessary. Other array-like maps (cpumap, devmap, sockmap, perf_event_array, cgroup_array) cannot be used by unpriv, so no changes there. That fixes bpf side of "Variant 1: bounds check bypass (CVE-2017-5753)" on all architectures with and without JIT. v2->v3: Daniel noticed that attack potentially can be crafted via syscall commands without loading the program, so add masking to those paths as well. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-01-08 09:33:02 +08:00
u32 index_mask;
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>
2015-05-20 07:59:03 +08:00
/* 'ownership' of prog_array is claimed by the first program that
* is going to use this map or by the first program which FD is stored
* in the map to make sure that all callers and callees have the same
* prog_type and JITed flag
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
union {
char value[0] __aligned(8);
void *ptrs[0] __aligned(8);
void __percpu *pptrs[0] __aligned(8);
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>
2015-05-20 07:59:03 +08:00
};
};
bpf, maps: flush own entries on perf map release The behavior of perf event arrays are quite different from all others as they are tightly coupled to perf event fds, f.e. shown recently by commit e03e7ee34fdd ("perf/bpf: Convert perf_event_array to use struct file") to make refcounting on perf event more robust. A remaining issue that the current code still has is that since additions to the perf event array take a reference on the struct file via perf_event_get() and are only released via fput() (that cleans up the perf event eventually via perf_event_release_kernel()) when the element is either manually removed from the map from user space or automatically when the last reference on the perf event map is dropped. However, this leads us to dangling struct file's when the map gets pinned after the application owning the perf event descriptor exits, and since the struct file reference will in such case only be manually dropped or via pinned file removal, it leads to the perf event living longer than necessary, consuming needlessly resources for that time. Relations between perf event fds and bpf perf event map fds can be rather complex. F.e. maps can act as demuxers among different perf event fds that can possibly be owned by different threads and based on the index selection from the program, events get dispatched to one of the per-cpu fd endpoints. One perf event fd (or, rather a per-cpu set of them) can also live in multiple perf event maps at the same time, listening for events. Also, another requirement is that perf event fds can get closed from application side after they have been attached to the perf event map, so that on exit perf event map will take care of dropping their references eventually. Likewise, when such maps are pinned, the intended behavior is that a user application does bpf_obj_get(), puts its fds in there and on exit when fd is released, they are dropped from the map again, so the map acts rather as connector endpoint. This also makes perf event maps inherently different from program arrays as described in more detail in commit c9da161c6517 ("bpf: fix clearing on persistent program array maps"). To tackle this, map entries are marked by the map struct file that added the element to the map. And when the last reference to that map struct file is released from user space, then the tracked entries are purged from the map. This is okay, because new map struct files instances resp. frontends to the anon inode are provided via bpf_map_new_fd() that is called when we invoke bpf_obj_get_user() for retrieving a pinned map, but also when an initial instance is created via map_create(). The rest is resolved by the vfs layer automatically for us by keeping reference count on the map's struct file. Any concurrent updates on the map slot are fine as well, it just means that perf_event_fd_array_release() needs to delete less of its own entires. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-16 04:47:14 +08:00
bpf: increase complexity limit and maximum program size Large verifier speed improvements allow to increase verifier complexity limit. Now regardless of the program composition and its size it takes little time for the verifier to hit insn_processed limit. On typical x86 machine non-debug kernel processes 1M instructions in 1/10 of a second. (before these speed improvements specially crafted programs could be hitting multi-second verification times) Full kasan kernel with debug takes ~1 second for the same 1M insns. Hence bump the BPF_COMPLEXITY_LIMIT_INSNS limit to 1M. Also increase the number of instructions per program from 4k to internal BPF_COMPLEXITY_LIMIT_INSNS limit. 4k limit was confusing to users, since small programs with hundreds of insns could be hitting BPF_COMPLEXITY_LIMIT_INSNS limit. Sometimes adding more insns and bpf_trace_printk debug statements would make the verifier accept the program while removing code would make the verifier reject it. Some user space application started to add #define MAX_FOO to their programs and do: MAX_FOO=100; again: compile with MAX_FOO; try to load; if (fails_to_load) { reduce MAX_FOO; goto again; } to be able to fit maximum amount of processing into single program. Other users artificially split their single program into a set of programs and use all 32 iterations of tail_calls to increase compute limits. And the most advanced folks used unlimited tc-bpf filter list to execute many bpf programs. Essentially the users managed to workaround 4k insn limit. This patch removes the limit for root programs from uapi. BPF_COMPLEXITY_LIMIT_INSNS is the kernel internal limit and success to load the program no longer depends on program size, but on 'smartness' of the verifier only. The verifier will continue to get smarter with every kernel release. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-04-02 12:27:45 +08:00
#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */
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>
2015-05-20 07:59:03 +08:00
#define MAX_TAIL_CALL_CNT 32
#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \
BPF_F_RDONLY_PROG | \
BPF_F_WRONLY | \
BPF_F_WRONLY_PROG)
#define BPF_MAP_CAN_READ BIT(0)
#define BPF_MAP_CAN_WRITE BIT(1)
static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
{
u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
* not possible.
*/
if (access_flags & BPF_F_RDONLY_PROG)
return BPF_MAP_CAN_READ;
else if (access_flags & BPF_F_WRONLY_PROG)
return BPF_MAP_CAN_WRITE;
else
return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
}
static inline bool bpf_map_flags_access_ok(u32 access_flags)
{
return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
(BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
}
bpf, maps: flush own entries on perf map release The behavior of perf event arrays are quite different from all others as they are tightly coupled to perf event fds, f.e. shown recently by commit e03e7ee34fdd ("perf/bpf: Convert perf_event_array to use struct file") to make refcounting on perf event more robust. A remaining issue that the current code still has is that since additions to the perf event array take a reference on the struct file via perf_event_get() and are only released via fput() (that cleans up the perf event eventually via perf_event_release_kernel()) when the element is either manually removed from the map from user space or automatically when the last reference on the perf event map is dropped. However, this leads us to dangling struct file's when the map gets pinned after the application owning the perf event descriptor exits, and since the struct file reference will in such case only be manually dropped or via pinned file removal, it leads to the perf event living longer than necessary, consuming needlessly resources for that time. Relations between perf event fds and bpf perf event map fds can be rather complex. F.e. maps can act as demuxers among different perf event fds that can possibly be owned by different threads and based on the index selection from the program, events get dispatched to one of the per-cpu fd endpoints. One perf event fd (or, rather a per-cpu set of them) can also live in multiple perf event maps at the same time, listening for events. Also, another requirement is that perf event fds can get closed from application side after they have been attached to the perf event map, so that on exit perf event map will take care of dropping their references eventually. Likewise, when such maps are pinned, the intended behavior is that a user application does bpf_obj_get(), puts its fds in there and on exit when fd is released, they are dropped from the map again, so the map acts rather as connector endpoint. This also makes perf event maps inherently different from program arrays as described in more detail in commit c9da161c6517 ("bpf: fix clearing on persistent program array maps"). To tackle this, map entries are marked by the map struct file that added the element to the map. And when the last reference to that map struct file is released from user space, then the tracked entries are purged from the map. This is okay, because new map struct files instances resp. frontends to the anon inode are provided via bpf_map_new_fd() that is called when we invoke bpf_obj_get_user() for retrieving a pinned map, but also when an initial instance is created via map_create(). The rest is resolved by the vfs layer automatically for us by keeping reference count on the map's struct file. Any concurrent updates on the map slot are fine as well, it just means that perf_event_fd_array_release() needs to delete less of its own entires. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-16 04:47:14 +08:00
struct bpf_event_entry {
struct perf_event *event;
struct file *perf_file;
struct file *map_file;
struct rcu_head rcu;
};
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>
2015-05-20 07:59:03 +08:00
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
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>
2017-01-14 06:38:15 +08:00
int bpf_prog_calc_tag(struct bpf_prog *fp);
bpf: add event output helper for notifications/sampling/logging This patch adds a new helper for cls/act programs that can push events to user space applications. For networking, this can be f.e. for sampling, debugging, logging purposes or pushing of arbitrary wake-up events. The idea is similar to a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") and 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example"). The eBPF program utilizes a perf event array map that user space populates with fds from perf_event_open(), the eBPF program calls into the helper f.e. as skb_event_output(skb, &my_map, BPF_F_CURRENT_CPU, raw, sizeof(raw)) so that the raw data is pushed into the fd f.e. at the map index of the current CPU. User space can poll/mmap/etc on this and has a data channel for receiving events that can be post-processed. The nice thing is that since the eBPF program and user space application making use of it are tightly coupled, they can define their own arbitrary raw data format and what/when they want to push. While f.e. packet headers could be one part of the meta data that is being pushed, this is not a substitute for things like packet sockets as whole packet is not being pushed and push is only done in a single direction. Intention is more of a generically usable, efficient event pipe to applications. Workflow is that tc can pin the map and applications can attach themselves e.g. after cls/act setup to one or multiple map slots, demuxing is done by the eBPF program. Adding this facility is with minimal effort, it reuses the helper introduced in a43eec304259 ("bpf: introduce bpf_perf_event_output() helper") and we get its functionality for free by overloading its BPF_FUNC_ identifier for cls/act programs, ctx is currently unused, but will be made use of in future. Example will be added to iproute2's BPF example files. 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>
2016-04-19 03:01:24 +08:00
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
bpf: avoid stack copy and use skb ctx for event output This work addresses a couple of issues bpf_skb_event_output() helper currently has: i) We need two copies instead of just a single one for the skb data when it should be part of a sample. The data can be non-linear and thus needs to be extracted via bpf_skb_load_bytes() helper first, and then copied once again into the ring buffer slot. ii) Since bpf_skb_load_bytes() currently needs to be used first, the helper needs to see a constant size on the passed stack buffer to make sure BPF verifier can do sanity checks on it during verification time. Thus, just passing skb->len (or any other non-constant value) wouldn't work, but changing bpf_skb_load_bytes() is also not the proper solution, since the two copies are generally still needed. iii) bpf_skb_load_bytes() is just for rather small buffers like headers, since they need to sit on the limited BPF stack anyway. Instead of working around in bpf_skb_load_bytes(), this work improves the bpf_skb_event_output() helper to address all 3 at once. We can make use of the passed in skb context that we have in the helper anyway, and use some of the reserved flag bits as a length argument. The helper will use the new __output_custom() facility from perf side with bpf_skb_copy() as callback helper to walk and extract the data. It will pass the data for setup to bpf_event_output(), which generates and pushes the raw record with an additional frag part. The linear data used in the first frag of the record serves as programmatically defined meta data passed along with the appended sample. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 00:08:05 +08:00
typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
unsigned long off, unsigned long len);
typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog,
u32 *target_size);
bpf: avoid stack copy and use skb ctx for event output This work addresses a couple of issues bpf_skb_event_output() helper currently has: i) We need two copies instead of just a single one for the skb data when it should be part of a sample. The data can be non-linear and thus needs to be extracted via bpf_skb_load_bytes() helper first, and then copied once again into the ring buffer slot. ii) Since bpf_skb_load_bytes() currently needs to be used first, the helper needs to see a constant size on the passed stack buffer to make sure BPF verifier can do sanity checks on it during verification time. Thus, just passing skb->len (or any other non-constant value) wouldn't work, but changing bpf_skb_load_bytes() is also not the proper solution, since the two copies are generally still needed. iii) bpf_skb_load_bytes() is just for rather small buffers like headers, since they need to sit on the limited BPF stack anyway. Instead of working around in bpf_skb_load_bytes(), this work improves the bpf_skb_event_output() helper to address all 3 at once. We can make use of the passed in skb context that we have in the helper anyway, and use some of the reserved flag bits as a length argument. The helper will use the new __output_custom() facility from perf side with bpf_skb_copy() as callback helper to walk and extract the data. It will pass the data for setup to bpf_event_output(), which generates and pushes the raw record with an additional frag part. The linear data used in the first frag of the record serves as programmatically defined meta data passed along with the appended sample. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 00:08:05 +08:00
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
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>
2015-05-20 07:59:03 +08:00
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
/* an array of programs to be executed under rcu_lock.
*
* Typical usage:
* ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
*
* the structure returned by bpf_prog_array_alloc() should be populated
* with program pointers and the last pointer must be NULL.
* The user has to keep refcnt on the program and make sure the program
* is removed from the array before bpf_prog_put().
* The 'struct bpf_prog_array *' should only be replaced with xchg()
* since other cpus are walking the array of pointers in parallel.
*/
struct bpf_prog_array_item {
struct bpf_prog *prog;
struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
};
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
struct bpf_prog_array {
struct rcu_head rcu;
struct bpf_prog_array_item items[0];
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
};
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
__u32 __user *prog_ids, u32 cnt);
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
struct bpf_prog *old_prog);
bpf/tracing: allow user space to query prog array on the same tp Commit e87c6bc3852b ("bpf: permit multiple bpf attachments for a single perf event") added support to attach multiple bpf programs to a single perf event. Although this provides flexibility, users may want to know what other bpf programs attached to the same tp interface. Besides getting visibility for the underlying bpf system, such information may also help consolidate multiple bpf programs, understand potential performance issues due to a large array, and debug (e.g., one bpf program which overwrites return code may impact subsequent program results). Commit 2541517c32be ("tracing, perf: Implement BPF programs attached to kprobes") utilized the existing perf ioctl interface and added the command PERF_EVENT_IOC_SET_BPF to attach a bpf program to a tracepoint. This patch adds a new ioctl command, given a perf event fd, to query the bpf program array attached to the same perf tracepoint event. The new uapi ioctl command: PERF_EVENT_IOC_QUERY_BPF The new uapi/linux/perf_event.h structure: struct perf_event_query_bpf { __u32 ids_len; __u32 prog_cnt; __u32 ids[0]; }; User space provides buffer "ids" for kernel to copy to. When returning from the kernel, the number of available programs in the array is set in "prog_cnt". The usage: struct perf_event_query_bpf *query = malloc(sizeof(*query) + sizeof(u32) * ids_len); query.ids_len = ids_len; err = ioctl(pmu_efd, PERF_EVENT_IOC_QUERY_BPF, query); if (err == 0) { /* query.prog_cnt is the number of available progs, * number of progs in ids: (ids_len == 0) ? 0 : query.prog_cnt */ } else if (errno == ENOSPC) { /* query.ids_len number of progs copied, * query.prog_cnt is the number of available progs */ } else { /* other errors */ } Signed-off-by: Yonghong Song <yhs@fb.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2017-12-12 03:39:02 +08:00
int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
bpf/tracing: fix a deadlock in perf_event_detach_bpf_prog syzbot reported a possible deadlock in perf_event_detach_bpf_prog. The error details: ====================================================== WARNING: possible circular locking dependency detected 4.16.0-rc7+ #3 Not tainted ------------------------------------------------------ syz-executor7/24531 is trying to acquire lock: (bpf_event_mutex){+.+.}, at: [<000000008a849b07>] perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 but task is already holding lock: (&mm->mmap_sem){++++}, at: [<0000000038768f87>] vm_mmap_pgoff+0x198/0x280 mm/util.c:353 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&mm->mmap_sem){++++}: __might_fault+0x13a/0x1d0 mm/memory.c:4571 _copy_to_user+0x2c/0xc0 lib/usercopy.c:25 copy_to_user include/linux/uaccess.h:155 [inline] bpf_prog_array_copy_info+0xf2/0x1c0 kernel/bpf/core.c:1694 perf_event_query_prog_array+0x1c7/0x2c0 kernel/trace/bpf_trace.c:891 _perf_ioctl kernel/events/core.c:4750 [inline] perf_ioctl+0x3e1/0x1480 kernel/events/core.c:4770 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:686 SYSC_ioctl fs/ioctl.c:701 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:692 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 -> #0 (bpf_event_mutex){+.+.}: lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920 __mutex_lock_common kernel/locking/mutex.c:756 [inline] __mutex_lock+0x16f/0x1a80 kernel/locking/mutex.c:893 mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908 perf_event_detach_bpf_prog+0x92/0x3d0 kernel/trace/bpf_trace.c:854 perf_event_free_bpf_prog kernel/events/core.c:8147 [inline] _free_event+0xbdb/0x10f0 kernel/events/core.c:4116 put_event+0x24/0x30 kernel/events/core.c:4204 perf_mmap_close+0x60d/0x1010 kernel/events/core.c:5172 remove_vma+0xb4/0x1b0 mm/mmap.c:172 remove_vma_list mm/mmap.c:2490 [inline] do_munmap+0x82a/0xdf0 mm/mmap.c:2731 mmap_region+0x59e/0x15a0 mm/mmap.c:1646 do_mmap+0x6c0/0xe00 mm/mmap.c:1483 do_mmap_pgoff include/linux/mm.h:2223 [inline] vm_mmap_pgoff+0x1de/0x280 mm/util.c:355 SYSC_mmap_pgoff mm/mmap.c:1533 [inline] SyS_mmap_pgoff+0x462/0x5f0 mm/mmap.c:1491 SYSC_mmap arch/x86/kernel/sys_x86_64.c:100 [inline] SyS_mmap+0x16/0x20 arch/x86/kernel/sys_x86_64.c:91 do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x42/0xb7 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&mm->mmap_sem); lock(bpf_event_mutex); lock(&mm->mmap_sem); lock(bpf_event_mutex); *** DEADLOCK *** ====================================================== The bug is introduced by Commit f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") where copy_to_user, which requires mm->mmap_sem, is called inside bpf_event_mutex lock. At the same time, during perf_event file descriptor close, mm->mmap_sem is held first and then subsequent perf_event_detach_bpf_prog needs bpf_event_mutex lock. Such a senario caused a deadlock. As suggested by Daniel, moving copy_to_user out of the bpf_event_mutex lock should fix the problem. Fixes: f371b304f12e ("bpf/tracing: allow user space to query prog array on the same tp") Reported-by: syzbot+dc5ca0e4c9bfafaf2bae@syzkaller.appspotmail.com Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-04-11 00:37:32 +08:00
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
struct bpf_prog_array **new_array);
#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
({ \
struct bpf_prog_array_item *_item; \
struct bpf_prog *_prog; \
struct bpf_prog_array *_array; \
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
u32 _ret = 1; \
preempt_disable(); \
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
rcu_read_lock(); \
_array = rcu_dereference(array); \
if (unlikely(check_non_null && !_array))\
goto _out; \
_item = &_array->items[0]; \
while ((_prog = READ_ONCE(_item->prog))) { \
bpf_cgroup_storage_set(_item->cgroup_storage); \
_ret &= func(_prog, ctx); \
_item++; \
} \
_out: \
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
rcu_read_unlock(); \
preempt_enable(); \
bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Martin KaFai Lau <kafai@fb.com> for cgroup bits Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-03 13:50:21 +08:00
_ret; \
})
#define BPF_PROG_RUN_ARRAY(array, ctx, func) \
__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \
__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern const struct file_operations bpf_map_fops;
extern const struct file_operations bpf_prog_fops;
#define BPF_PROG_TYPE(_id, _name) \
extern const struct bpf_prog_ops _name ## _prog_ops; \
extern const struct bpf_verifier_ops _name ## _verifier_ops;
#define BPF_MAP_TYPE(_id, _ops) \
extern const struct bpf_map_ops _ops;
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
extern const struct bpf_prog_ops bpf_offload_prog_ops;
extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
extern const struct bpf_verifier_ops xdp_analyzer_ops;
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
bool attach_drv);
struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
void bpf_prog_sub(struct bpf_prog *prog, int i);
struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog);
struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
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 08:52:58 +08:00
int __bpf_prog_charge(struct user_struct *user, u32 pages);
void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
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>
2015-11-25 04:28:15 +08:00
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
struct bpf_map * __must_check 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>
2015-11-25 04:28:15 +08:00
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
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 13:57:15 +08:00
int bpf_map_precharge_memlock(u32 pages);
int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
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>
2017-08-19 02:28:00 +08:00
void *bpf_map_area_alloc(size_t size, int numa_node);
void bpf_map_area_free(void *base);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
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 13:23:21 +08:00
extern int sysctl_unprivileged_bpf_disabled;
extern int sysctl_bpf_stats_enabled;
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 13:23:21 +08:00
int bpf_map_new_fd(struct bpf_map *map, int flags);
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 21:58:09 +08:00
int bpf_prog_new_fd(struct bpf_prog *prog);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname, int flags);
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 21:58:09 +08:00
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 flags);
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 13:57:17 +08:00
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_get_file_flag(int flags);
int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size,
size_t actual_size);
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
* Best-effort only. No barriers here, since it _will_ race with concurrent
* updates from BPF programs. Called from bpf syscall and mostly used with
* size 8 or 16 bytes, so ask compiler to inline it.
*/
static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
{
const long *lsrc = src;
long *ldst = dst;
size /= sizeof(long);
while (size--)
*ldst++ = *lsrc++;
}
/* verify correctness of eBPF program */
bpf: Introduce bpf_func_info This patch added interface to load a program with the following additional information: . prog_btf_fd . func_info, func_info_rec_size and func_info_cnt where func_info will provide function range and type_id corresponding to each function. The func_info_rec_size is introduced in the UAPI to specify struct bpf_func_info size passed from user space. This intends to make bpf_func_info structure growable in the future. If the kernel gets a different bpf_func_info size from userspace, it will try to handle user request with part of bpf_func_info it can understand. In this patch, kernel can understand struct bpf_func_info { __u32 insn_offset; __u32 type_id; }; If user passed a bpf func_info record size of 16 bytes, the kernel can still handle part of records with the above definition. If verifier agrees with function range provided by the user, the bpf_prog ksym for each function will use the func name provided in the type_id, which is supposed to provide better encoding as it is not limited by 16 bytes program name limitation and this is better for bpf program which contains multiple subprograms. The bpf_prog_info interface is also extended to return btf_id, func_info, func_info_rec_size and func_info_cnt to userspace, so userspace can print out the function prototype for each xlated function. The insn_offset in the returned func_info corresponds to the insn offset for xlated functions. With other jit related fields in bpf_prog_info, userspace can also print out function prototypes for each jited function. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-11-20 07:29:11 +08:00
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
union bpf_attr __user *uattr);
void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
/* Map specifics */
struct xdp_buff;
struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
void __cpu_map_flush(struct bpf_map *map);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx);
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>
2017-08-19 02:28:00 +08:00
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
return (attr->map_flags & BPF_F_NUMA_NODE) ?
attr->numa_node : NUMA_NO_NODE;
}
struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY. To unleash the full potential of a bpf prog, it is essential for the userspace to be capable of directly setting up a bpf map which can then be consumed by the bpf prog to make decision. In this case, decide which SO_REUSEPORT sk to serve the incoming request. By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control and visibility on where a SO_REUSEPORT sk should be located in a bpf map. The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that the bpf prog can directly select a sk from the bpf map. That will raise the programmability of the bpf prog attached to a reuseport group (a group of sk serving the same IP:PORT). For example, in UDP, the bpf prog can peek into the payload (e.g. through the "data" pointer introduced in the later patch) to learn the application level's connection information and then decide which sk to pick from a bpf map. The userspace can tightly couple the sk's location in a bpf map with the application logic in generating the UDP payload's connection information. This connection info contact/API stays within the userspace. Also, when used with map-in-map, the userspace can switch the old-server-process's inner map to a new-server-process's inner map in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)". The bpf prog will then direct incoming requests to the new process instead of the old process. The old process can finish draining the pending requests (e.g. by "accept()") before closing the old-fds. [Note that deleting a fd from a bpf map does not necessary mean the fd is closed] During map_update_elem(), Only SO_REUSEPORT sk (i.e. which has already been added to a reuse->socks[]) can be used. That means a SO_REUSEPORT sk that is "bind()" for UDP or "bind()+listen()" for TCP. These conditions are ensured in "reuseport_array_update_check()". A SO_REUSEPORT sk can only be added once to a map (i.e. the same sk cannot be added twice even to the same map). SO_REUSEPORT already allows another sk to be created for the same IP:PORT. There is no need to re-create a similar usage in the BPF side. When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"), it will notify the bpf map to remove it from the map also. It is done through "bpf_sk_reuseport_detach()" and it will only be called if >=1 of the "reuse->sock[]" has ever been added to a bpf map. The map_update()/map_delete() has to be in-sync with the "reuse->socks[]". Hence, the same "reuseport_lock" used by "reuse->socks[]" has to be used here also. Care has been taken to ensure the lock is only acquired when the adding sk passes some strict tests. and freeing the map does not require the reuseport_lock. The reuseport_array will also support lookup from the syscall side. It will return a sock_gen_cookie(). The sock_gen_cookie() is on-demand (i.e. a sk's cookie is not generated until the very first map_lookup_elem()). The lookup cookie is 64bits but it goes against the logical userspace expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also). It may catch user in surprise if we enforce value_size=8 while userspace still pass a 32bits fd during update. Supporting different value_size between lookup and update seems unintuitive also. We also need to consider what if other existing fd based maps want to return 64bits value from syscall's lookup in the future. Hence, reuseport_array supports both value_size 4 and 8, and assuming user will usually use value_size=4. The syscall's lookup will return ENOSPC on value_size=4. It will will only return 64bits value from sock_gen_cookie() when user consciously choose value_size=8 (as a signal that lookup is desired) which then requires a 64bits value in both lookup and update. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-08 16:01:24 +08:00
int array_map_alloc_check(union bpf_attr *attr);
int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
enum bpf_prog_type type,
bool attach_drv)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog,
int i)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
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 08:52:58 +08:00
static inline struct bpf_prog *__must_check
bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
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 08:52:58 +08:00
static inline int __bpf_prog_charge(struct user_struct *user, u32 pages)
{
return 0;
}
static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
{
}
static inline int bpf_obj_get_user(const char __user *pathname, int flags)
netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder <rafi@rbk.ms> Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com> Acked-by: Willem de Bruijn <willemb@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2017-10-09 20:27:15 +08:00
{
return -EOPNOTSUPP;
}
static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
{
}
static inline void __dev_map_flush(struct bpf_map *map)
{
}
struct xdp_buff;
struct bpf_dtab_netdev;
static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
return 0;
}
static inline
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
return NULL;
}
static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
{
}
static inline void __cpu_map_flush(struct bpf_map *map)
{
}
static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
enum bpf_prog_type type)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
#endif /* CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
enum bpf_prog_type type)
{
return bpf_prog_get_type_dev(ufd, type, false);
}
bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
int bpf_prog_offload_compile(struct bpf_prog *prog);
void bpf_prog_offload_destroy(struct bpf_prog *prog);
int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
struct bpf_prog *prog);
int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map);
int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value);
int bpf_map_offload_update_elem(struct bpf_map *map,
void *key, void *value, u64 flags);
int bpf_map_offload_delete_elem(struct bpf_map *map, void *key);
int bpf_map_offload_get_next_key(struct bpf_map *map,
void *key, void *next_key);
bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
struct bpf_offload_dev *
bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv);
void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev);
int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
struct net_device *netdev);
void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
struct net_device *netdev);
bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
{
return aux->offload_requested;
}
static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
{
return unlikely(map->ops == &bpf_map_offload_ops);
}
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
void bpf_map_offload_map_free(struct bpf_map *map);
#else
static inline int bpf_prog_offload_init(struct bpf_prog *prog,
union bpf_attr *attr)
{
return -EOPNOTSUPP;
}
static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
{
return false;
}
static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
{
return false;
}
static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_map_offload_map_free(struct bpf_map *map)
{
}
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 08:45:58 +08:00
#if defined(CONFIG_BPF_STREAM_PARSER)
int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
#else
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 08:45:58 +08:00
static inline int sock_map_prog_update(struct bpf_map *map,
struct bpf_prog *prog, u32 which)
{
return -EOPNOTSUPP;
}
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 08:45:58 +08:00
static inline int sock_map_get_from_fd(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
#endif
#if defined(CONFIG_XDP_SOCKETS)
struct xdp_sock;
struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
struct xdp_sock *xs);
void __xsk_map_flush(struct bpf_map *map);
#else
struct xdp_sock;
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
struct xdp_sock *xs)
{
return -EOPNOTSUPP;
}
static inline void __xsk_map_flush(struct bpf_map *map)
{
}
#endif
bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY. To unleash the full potential of a bpf prog, it is essential for the userspace to be capable of directly setting up a bpf map which can then be consumed by the bpf prog to make decision. In this case, decide which SO_REUSEPORT sk to serve the incoming request. By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control and visibility on where a SO_REUSEPORT sk should be located in a bpf map. The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that the bpf prog can directly select a sk from the bpf map. That will raise the programmability of the bpf prog attached to a reuseport group (a group of sk serving the same IP:PORT). For example, in UDP, the bpf prog can peek into the payload (e.g. through the "data" pointer introduced in the later patch) to learn the application level's connection information and then decide which sk to pick from a bpf map. The userspace can tightly couple the sk's location in a bpf map with the application logic in generating the UDP payload's connection information. This connection info contact/API stays within the userspace. Also, when used with map-in-map, the userspace can switch the old-server-process's inner map to a new-server-process's inner map in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)". The bpf prog will then direct incoming requests to the new process instead of the old process. The old process can finish draining the pending requests (e.g. by "accept()") before closing the old-fds. [Note that deleting a fd from a bpf map does not necessary mean the fd is closed] During map_update_elem(), Only SO_REUSEPORT sk (i.e. which has already been added to a reuse->socks[]) can be used. That means a SO_REUSEPORT sk that is "bind()" for UDP or "bind()+listen()" for TCP. These conditions are ensured in "reuseport_array_update_check()". A SO_REUSEPORT sk can only be added once to a map (i.e. the same sk cannot be added twice even to the same map). SO_REUSEPORT already allows another sk to be created for the same IP:PORT. There is no need to re-create a similar usage in the BPF side. When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"), it will notify the bpf map to remove it from the map also. It is done through "bpf_sk_reuseport_detach()" and it will only be called if >=1 of the "reuse->sock[]" has ever been added to a bpf map. The map_update()/map_delete() has to be in-sync with the "reuse->socks[]". Hence, the same "reuseport_lock" used by "reuse->socks[]" has to be used here also. Care has been taken to ensure the lock is only acquired when the adding sk passes some strict tests. and freeing the map does not require the reuseport_lock. The reuseport_array will also support lookup from the syscall side. It will return a sock_gen_cookie(). The sock_gen_cookie() is on-demand (i.e. a sk's cookie is not generated until the very first map_lookup_elem()). The lookup cookie is 64bits but it goes against the logical userspace expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also). It may catch user in surprise if we enforce value_size=8 while userspace still pass a 32bits fd during update. Supporting different value_size between lookup and update seems unintuitive also. We also need to consider what if other existing fd based maps want to return 64bits value from syscall's lookup in the future. Hence, reuseport_array supports both value_size 4 and 8, and assuming user will usually use value_size=4. The syscall's lookup will return ENOSPC on value_size=4. It will will only return 64bits value from sock_gen_cookie() when user consciously choose value_size=8 (as a signal that lookup is desired) which then requires a 64bits value in both lookup and update. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-08-08 16:01:24 +08:00
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
void bpf_sk_reuseport_detach(struct sock *sk);
int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
void *value);
int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags);
#else
static inline void bpf_sk_reuseport_detach(struct sock *sk)
{
}
#ifdef CONFIG_BPF_SYSCALL
static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
void *key, void *value)
{
return -EOPNOTSUPP;
}
static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
void *key, void *value,
u64 map_flags)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_BPF_SYSCALL */
#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
/* verifier prototypes for helper functions called from eBPF programs */
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
extern const struct bpf_func_proto bpf_map_delete_elem_proto;
extern const struct bpf_func_proto bpf_map_push_elem_proto;
extern const struct bpf_func_proto bpf_map_pop_elem_proto;
extern const struct bpf_func_proto bpf_map_peek_elem_proto;
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
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>
2015-05-20 07:59:03 +08:00
extern const struct bpf_func_proto bpf_tail_call_proto;
extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto;
extern const struct bpf_func_proto bpf_get_stack_proto;
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 13:32:47 +08:00
extern const struct bpf_func_proto bpf_sock_map_update_proto;
extern const struct bpf_func_proto bpf_sock_hash_update_proto;
extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
bpf, sockmap: convert to generic sk_msg interface Add a generic sk_msg layer, and convert current sockmap and later kTLS over to make use of it. While sk_buff handles network packet representation from netdevice up to socket, sk_msg handles data representation from application to socket layer. This means that sk_msg framework spans across ULP users in the kernel, and enables features such as introspection or filtering of data with the help of BPF programs that operate on this data structure. Latter becomes in particular useful for kTLS where data encryption is deferred into the kernel, and as such enabling the kernel to perform L7 introspection and policy based on BPF for TLS connections where the record is being encrypted after BPF has run and came to a verdict. In order to get there, first step is to transform open coding of scatter-gather list handling into a common core framework that subsystems can use. The code itself has been split and refactored into three bigger pieces: i) the generic sk_msg API which deals with managing the scatter gather ring, providing helpers for walking and mangling, transferring application data from user space into it, and preparing it for BPF pre/post-processing, ii) the plain sock map itself where sockets can be attached to or detached from; these bits are independent of i) which can now be used also without sock map, and iii) the integration with plain TCP as one protocol to be used for processing L7 application data (later this could e.g. also be extended to other protocols like UDP). The semantics are the same with the old sock map code and therefore no change of user facing behavior or APIs. While pursuing this work it also helped finding a number of bugs in the old sockmap code that we've fixed already in earlier commits. The test_sockmap kselftest suite passes through fine as well. Joint work with John. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-10-13 08:45:58 +08:00
extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
extern const struct bpf_func_proto bpf_spin_lock_proto;
extern const struct bpf_func_proto bpf_spin_unlock_proto;
extern const struct bpf_func_proto bpf_get_local_storage_proto;
bpf: Introduce bpf_strtol and bpf_strtoul helpers Add bpf_strtol and bpf_strtoul to convert a string to long and unsigned long correspondingly. It's similar to user space strtol(3) and strtoul(3) with a few changes to the API: * instead of NUL-terminated C string the helpers expect buffer and buffer length; * resulting long or unsigned long is returned in a separate result-argument; * return value is used to indicate success or failure, on success number of consumed bytes is returned that can be used to identify position to read next if the buffer is expected to contain multiple integers; * instead of *base* argument, *flags* is used that provides base in 5 LSB, other bits are reserved for future use; * number of supported bases is limited. Documentation for the new helpers is provided in bpf.h UAPI. The helpers are made available to BPF_PROG_TYPE_CGROUP_SYSCTL programs to be able to convert string input to e.g. "ulongvec" output. E.g. "net/ipv4/tcp_mem" consists of three ulong integers. They can be parsed by calling to bpf_strtoul three times. Implementation notes: Implementation includes "../../lib/kstrtox.h" to reuse integer parsing functions. It's done exactly same way as fs/proc/base.c already does. Unfortunately existing kstrtoX function can't be used directly since they fail if any invalid character is present right after integer in the string. Existing simple_strtoX functions can't be used either since they're obsolete and don't handle overflow properly. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-03-19 08:55:26 +08:00
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
bpf: split state from prandom_u32() and consolidate {c, e}BPF prngs While recently arguing on a seccomp discussion that raw prandom_u32() access shouldn't be exposed to unpriviledged user space, I forgot the fact that SKF_AD_RANDOM extension actually already does it for some time in cBPF via commit 4cd3675ebf74 ("filter: added BPF random opcode"). Since prandom_u32() is being used in a lot of critical networking code, lets be more conservative and split their states. Furthermore, consolidate eBPF and cBPF prandom handlers to use the new internal PRNG. For eBPF, bpf_get_prandom_u32() was only accessible for priviledged users, but should that change one day, we also don't want to leak raw sequences through things like eBPF maps. One thought was also to have own per bpf_prog states, but due to ABI reasons this is not easily possible, i.e. the program code currently cannot access bpf_prog itself, and copying the rnd_state to/from the stack scratch space whenever a program uses the prng seems not really worth the trouble and seems too hacky. If needed, taus113 could in such cases be implemented within eBPF using a map entry to keep the state space, or get_random_bytes() could become a second helper in cases where performance would not be critical. Both sides can trigger a one-time late init via prandom_init_once() on the shared state. Performance-wise, there should even be a tiny gain as bpf_user_rnd_u32() saves one function call. The PRNG needs to live inside the BPF core since kernels could have a NET-less config as well. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Alexei Starovoitov <ast@plumgrid.com> Cc: Chema Gonzalez <chema@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-08 07:20:39 +08:00
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
#if defined(CONFIG_NET)
bpf: Add a bpf_sock pointer to __sk_buff and a bpf_sk_fullsock helper In kernel, it is common to check "skb->sk && sk_fullsock(skb->sk)" before accessing the fields in sock. For example, in __netdev_pick_tx: static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* ... */ struct sock *sk = skb->sk; if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); /* ... */ return queue_index; } This patch adds a "struct bpf_sock *sk" pointer to the "struct __sk_buff" where a few of the convert_ctx_access() in filter.c has already been accessing the skb->sk sock_common's fields, e.g. sock_ops_convert_ctx_access(). "__sk_buff->sk" is a PTR_TO_SOCK_COMMON_OR_NULL in the verifier. Some of the fileds in "bpf_sock" will not be directly accessible through the "__sk_buff->sk" pointer. It is limited by the new "bpf_sock_common_is_valid_access()". e.g. The existing "type", "protocol", "mark" and "priority" in bpf_sock are not allowed. The newly added "struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)" can be used to get a sk with all accessible fields in "bpf_sock". This helper is added to both cg_skb and sched_(cls|act). int cg_skb_foo(struct __sk_buff *skb) { struct bpf_sock *sk; sk = skb->sk; if (!sk) return 1; sk = bpf_sk_fullsock(sk); if (!sk) return 1; if (sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP) return 1; /* some_traffic_shaping(); */ return 1; } (1) The sk is read only (2) There is no new "struct bpf_sock_common" introduced. (3) Future kernel sock's members could be added to bpf_sock only instead of repeatedly adding at multiple places like currently in bpf_sock_ops_md, bpf_sock_addr_md, sk_reuseport_md...etc. (4) After "sk = skb->sk", the reg holding sk is in type PTR_TO_SOCK_COMMON_OR_NULL. (5) After bpf_sk_fullsock(), the return type will be in type PTR_TO_SOCKET_OR_NULL which is the same as the return type of bpf_sk_lookup_xxx(). However, bpf_sk_fullsock() does not take refcnt. The acquire_reference_state() is only depending on the return type now. To avoid it, a new is_acquire_function() is checked before calling acquire_reference_state(). (6) The WARN_ON in "release_reference_state()" is no longer an internal verifier bug. When reg->id is not found in state->refs[], it means the bpf_prog does something wrong like "bpf_sk_release(bpf_sk_fullsock(skb->sk))" where reference has never been acquired by calling "bpf_sk_fullsock(skb->sk)". A -EINVAL and a verbose are done instead of WARN_ON. A test is added to the test_verifier in a later patch. Since the WARN_ON in "release_reference_state()" is no longer needed, "__release_reference_state()" is folded into "release_reference_state()" also. Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-02-10 15:22:20 +08:00
bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info);
bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
#else
bpf: Add a bpf_sock pointer to __sk_buff and a bpf_sk_fullsock helper In kernel, it is common to check "skb->sk && sk_fullsock(skb->sk)" before accessing the fields in sock. For example, in __netdev_pick_tx: static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { /* ... */ struct sock *sk = skb->sk; if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); /* ... */ return queue_index; } This patch adds a "struct bpf_sock *sk" pointer to the "struct __sk_buff" where a few of the convert_ctx_access() in filter.c has already been accessing the skb->sk sock_common's fields, e.g. sock_ops_convert_ctx_access(). "__sk_buff->sk" is a PTR_TO_SOCK_COMMON_OR_NULL in the verifier. Some of the fileds in "bpf_sock" will not be directly accessible through the "__sk_buff->sk" pointer. It is limited by the new "bpf_sock_common_is_valid_access()". e.g. The existing "type", "protocol", "mark" and "priority" in bpf_sock are not allowed. The newly added "struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)" can be used to get a sk with all accessible fields in "bpf_sock". This helper is added to both cg_skb and sched_(cls|act). int cg_skb_foo(struct __sk_buff *skb) { struct bpf_sock *sk; sk = skb->sk; if (!sk) return 1; sk = bpf_sk_fullsock(sk); if (!sk) return 1; if (sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP) return 1; /* some_traffic_shaping(); */ return 1; } (1) The sk is read only (2) There is no new "struct bpf_sock_common" introduced. (3) Future kernel sock's members could be added to bpf_sock only instead of repeatedly adding at multiple places like currently in bpf_sock_ops_md, bpf_sock_addr_md, sk_reuseport_md...etc. (4) After "sk = skb->sk", the reg holding sk is in type PTR_TO_SOCK_COMMON_OR_NULL. (5) After bpf_sk_fullsock(), the return type will be in type PTR_TO_SOCKET_OR_NULL which is the same as the return type of bpf_sk_lookup_xxx(). However, bpf_sk_fullsock() does not take refcnt. The acquire_reference_state() is only depending on the return type now. To avoid it, a new is_acquire_function() is checked before calling acquire_reference_state(). (6) The WARN_ON in "release_reference_state()" is no longer an internal verifier bug. When reg->id is not found in state->refs[], it means the bpf_prog does something wrong like "bpf_sk_release(bpf_sk_fullsock(skb->sk))" where reference has never been acquired by calling "bpf_sk_fullsock(skb->sk)". A -EINVAL and a verbose are done instead of WARN_ON. A test is added to the test_verifier in a later patch. Since the WARN_ON in "release_reference_state()" is no longer needed, "__release_reference_state()" is folded into "release_reference_state()" also. Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-02-10 15:22:20 +08:00
static inline bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline bool bpf_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
#endif
#ifdef CONFIG_INET
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
#else
static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
#endif /* CONFIG_INET */
#endif /* _LINUX_BPF_H */