WSL2-Linux-Kernel/include/linux/bpf.h

1960 строки
62 KiB
C
Исходник Обычный вид История

/* 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 00:24:50 +03:00
#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 07:18:47 +03:00
#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 00:24:50 +03:00
#include <linux/rbtree_latch.h>
#include <linux/numa.h>
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-17 20:28:04 +03:00
#include <linux/mm_types.h>
#include <linux/wait.h>
#include <linux/u64_stats_sync.h>
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
#include <linux/refcount.h>
#include <linux/mutex.h>
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/capability.h>
struct bpf_verifier_env;
bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
2019-10-16 06:25:00 +03:00
struct bpf_verifier_log;
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>
2016-06-15 23:47:14 +03:00
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 08:32:47 +03:00
struct bpf_prog;
struct bpf_prog_aux;
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>
2018-03-18 22:57:10 +03:00
struct sock;
struct seq_file;
struct btf;
struct btf_type;
bpf: Add support for BTF pointers to x86 JIT Pointer to BTF object is a pointer to kernel object or NULL. Such pointers can only be used by BPF_LDX instructions. The verifier changed their opcode from LDX|MEM|size to LDX|PROBE_MEM|size to make JITing easier. The number of entries in extable is the number of BPF_LDX insns that access kernel memory via "pointer to BTF type". Only these load instructions can fault. Since x86 extable is relative it has to be allocated in the same memory region as JITed code. Allocate it prior to last pass of JITing and let the last pass populate it. Pointer to extable in bpf_prog_aux is necessary to make page fault handling fast. Page fault handling is done in two steps: 1. bpf_prog_kallsyms_find() finds BPF program that page faulted. It's done by walking rb tree. 2. then extable for given bpf program is binary searched. This process is similar to how page faulting is done for kernel modules. The exception handler skips over faulting x86 instruction and initializes destination register with zero. This mimics exact behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed). JITs for other architectures can add support in similar way. Until then they will reject unknown opcode and fallback to interpreter. Since extable should be aligned and placed near JITed code make bpf_jit_binary_alloc() return 4 byte aligned image offset, so that extable aligning formula in bpf_int_jit_compile() doesn't need to rely on internal implementation of bpf_jit_binary_alloc(). On x86 gcc defaults to 16-byte alignment for regular kernel functions due to better performance. JITed code may be aligned to 16 in the future, but it will use 4 in the meantime. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org
2019-10-16 06:25:03 +03:00
struct exception_table_entry;
struct seq_operations;
struct bpf_iter_aux_info;
struct bpf_local_storage;
struct bpf_local_storage_map;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
typedef int (*bpf_iter_init_seq_priv_t)(void *private_data,
struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data);
struct bpf_iter_seq_info {
const struct seq_operations *seq_ops;
bpf_iter_init_seq_priv_t init_seq_private;
bpf_iter_fini_seq_priv_t fini_seq_private;
u32 seq_priv_size;
};
/* 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);
bpf: Add generic support for lookup batch op This commit introduces generic support for the bpf_map_lookup_batch. This implementation can be used by almost all the bpf maps since its core implementation is relying on the existing map_get_next_key and map_lookup_elem. The bpf syscall subcommand introduced is: BPF_MAP_LOOKUP_BATCH The UAPI attribute is: struct { /* struct used by BPF_MAP_*_BATCH commands */ __aligned_u64 in_batch; /* start batch, * NULL to start from beginning */ __aligned_u64 out_batch; /* output: next start batch */ __aligned_u64 keys; __aligned_u64 values; __u32 count; /* input/output: * input: # of key/value * elements * output: # of filled elements */ __u32 map_fd; __u64 elem_flags; __u64 flags; } batch; in_batch/out_batch are opaque values use to communicate between user/kernel space, in_batch/out_batch must be of key_size length. To start iterating from the beginning in_batch must be null, count is the # of key/value elements to retrieve. Note that the 'keys' buffer must be a buffer of key_size * count size and the 'values' buffer must be value_size * count, where value_size must be aligned to 8 bytes by userspace if it's dealing with percpu maps. 'count' will contain the number of keys/values successfully retrieved. Note that 'count' is an input/output variable and it can contain a lower value after a call. If there's no more entries to retrieve, ENOENT will be returned. If error is ENOENT, count might be > 0 in case it copied some values but there were no more entries to retrieve. Note that if the return code is an error and not -EFAULT, count indicates the number of elements successfully processed. Suggested-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com
2020-01-15 21:43:01 +03:00
int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
bpf: Add batch ops to all htab bpf map htab can't use generic batch support due some problematic behaviours inherent to the data structre, i.e. while iterating the bpf map a concurrent program might delete the next entry that batch was about to use, in that case there's no easy solution to retrieve the next entry, the issue has been discussed multiple times (see [1] and [2]). The only way hmap can be traversed without the problem previously exposed is by making sure that the map is traversing entire buckets. This commit implements those strict requirements for hmap, the implementation follows the same interaction that generic support with some exceptions: - If keys/values buffer are not big enough to traverse a bucket, ENOSPC will be returned. - out_batch contains the value of the next bucket in the iteration, not the next key, but this is transparent for the user since the user should never use out_batch for other than bpf batch syscalls. This commits implements BPF_MAP_LOOKUP_BATCH and adds support for new command BPF_MAP_LOOKUP_AND_DELETE_BATCH. Note that for update/delete batch ops it is possible to use the generic implementations. [1] https://lore.kernel.org/bpf/20190724165803.87470-1-brianvv@google.com/ [2] https://lore.kernel.org/bpf/20190906225434.3635421-1-yhs@fb.com/ Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115184308.162644-6-brianvv@google.com
2020-01-15 21:43:04 +03:00
int (*map_lookup_and_delete_batch)(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_update_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr,
union bpf_attr __user *uattr);
/* 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);
bpf: Allow for map-in-map with dynamic inner array map entries Recent work in f4d05259213f ("bpf: Add map_meta_equal map ops") and 134fede4eecf ("bpf: Relax max_entries check for most of the inner map types") added support for dynamic inner max elements for most map-in-map types. Exceptions were maps like array or prog array where the map_gen_lookup() callback uses the maps' max_entries field as a constant when emitting instructions. We recently implemented Maglev consistent hashing into Cilium's load balancer which uses map-in-map with an outer map being hash and inner being array holding the Maglev backend table for each service. This has been designed this way in order to reduce overall memory consumption given the outer hash map allows to avoid preallocating a large, flat memory area for all services. Also, the number of service mappings is not always known a-priori. The use case for dynamic inner array map entries is to further reduce memory overhead, for example, some services might just have a small number of back ends while others could have a large number. Right now the Maglev backend table for small and large number of backends would need to have the same inner array map entries which adds a lot of unneeded overhead. Dynamic inner array map entries can be realized by avoiding the inlined code generation for their lookup. The lookup will still be efficient since it will be calling into array_map_lookup_elem() directly and thus avoiding retpoline. The patch adds a BPF_F_INNER_MAP flag to map creation which therefore skips inline code generation and relaxes array_map_meta_equal() check to ignore both maps' max_entries. This also still allows to have faster lookups for map-in-map when BPF_F_INNER_MAP is not specified and hence dynamic max_entries not needed. Example code generation where inner map is dynamic sized array: # bpftool p d x i 125 int handle__sys_enter(void * ctx): ; int handle__sys_enter(void *ctx) 0: (b4) w1 = 0 ; int key = 0; 1: (63) *(u32 *)(r10 -4) = r1 2: (bf) r2 = r10 ; 3: (07) r2 += -4 ; inner_map = bpf_map_lookup_elem(&outer_arr_dyn, &key); 4: (18) r1 = map[id:468] 6: (07) r1 += 272 7: (61) r0 = *(u32 *)(r2 +0) 8: (35) if r0 >= 0x3 goto pc+5 9: (67) r0 <<= 3 10: (0f) r0 += r1 11: (79) r0 = *(u64 *)(r0 +0) 12: (15) if r0 == 0x0 goto pc+1 13: (05) goto pc+1 14: (b7) r0 = 0 15: (b4) w6 = -1 ; if (!inner_map) 16: (15) if r0 == 0x0 goto pc+6 17: (bf) r2 = r10 ; 18: (07) r2 += -4 ; val = bpf_map_lookup_elem(inner_map, &key); 19: (bf) r1 = r0 | No inlining but instead 20: (85) call array_map_lookup_elem#149280 | call to array_map_lookup_elem() ; return val ? *val : -1; | for inner array lookup. 21: (15) if r0 == 0x0 goto pc+1 ; return val ? *val : -1; 22: (61) r6 = *(u32 *)(r0 +0) ; } 23: (bc) w0 = w6 24: (95) exit Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201010234006.7075-4-daniel@iogearbox.net
2020-10-11 02:40:03 +03:00
int (*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 00:20:03 +03:00
/* Prog poke tracking helpers. */
int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux);
void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux);
void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old,
struct bpf_prog *new);
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 00:20:03 +03:00
/* 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);
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-17 20:28:04 +03:00
int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 10:54:20 +03:00
__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
struct poll_table_struct *pts);
bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
2020-06-20 00:11:43 +03:00
/* Functions called by bpf_local_storage maps */
int (*map_local_storage_charge)(struct bpf_local_storage_map *smap,
void *owner, u32 size);
void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap,
void *owner, u32 size);
struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner);
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 04:18:06 +03:00
/* map_meta_equal must be implemented for maps that can be
* used as an inner map. It is a runtime check to ensure
* an inner map can be inserted to an outer map.
*
* Some properties of the inner map has been used during the
* verification time. When inserting an inner map at the runtime,
* map_meta_equal has to ensure the inserting map has the same
* properties that the verifier has used earlier.
*/
bool (*map_meta_equal)(const struct bpf_map *meta0,
const struct bpf_map *meta1);
bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
2020-06-20 00:11:43 +03:00
/* BTF name and id of struct allocated by map_alloc */
const char * const map_btf_name;
int *map_btf_id;
bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com
2020-07-23 21:41:12 +03:00
/* bpf_iter info used to open a seq_file */
const struct bpf_iter_seq_info *iter_seq_info;
};
struct bpf_map_memory {
u32 pages;
struct user_struct *user;
};
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 15:17:44 +03:00
* 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 08:57:15 +03:00
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 02:40:04 +03:00
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>
2017-08-18 21:28:00 +03:00
int numa_node;
u32 btf_key_type_id;
u32 btf_value_type_id;
struct btf *btf;
struct bpf_map_memory memory;
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-17 20:28:04 +03:00
char name[BPF_OBJ_NAME_LEN];
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
u32 btf_vmlinux_value_type_id;
bool bypass_spec_v1;
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-17 20:28:04 +03:00
bool frozen; /* write-once; write-protected by freeze_mutex */
/* 22 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 15:17:44 +03:00
/* 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 15:17:44 +03:00
* particularly with refcounting.
*/
bpf: Switch bpf_map ref counter to atomic64_t so bpf_map_inc() never fails 92117d8443bc ("bpf: fix refcnt overflow") turned refcounting of bpf_map into potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit (32k). Due to using 32-bit counter, it's possible in practice to overflow refcounter and make it wrap around to 0, causing erroneous map free, while there are still references to it, causing use-after-free problems. But having a failing refcounting operations are problematic in some cases. One example is mmap() interface. After establishing initial memory-mapping, user is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily splitting it into multiple non-contiguous regions. All this happening without any control from the users of mmap subsystem. Rather mmap subsystem sends notifications to original creator of memory mapping through open/close callbacks, which are optionally specified during initial memory mapping creation. These callbacks are used to maintain accurate refcount for bpf_map (see next patch in this series). The problem is that open() callback is not supposed to fail, because memory-mapped resource is set up and properly referenced. This is posing a problem for using memory-mapping with BPF maps. One solution to this is to maintain separate refcount for just memory-mappings and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively. There are similar use cases in current work on tcp-bpf, necessitating extra counter as well. This seems like a rather unfortunate and ugly solution that doesn't scale well to various new use cases. Another approach to solve this is to use non-failing refcount_t type, which uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX, stays there. This utlimately causes memory leak, but prevents use after free. But given refcounting is not the most performance-critical operation with BPF maps (it's not used from running BPF program code), we can also just switch to 64-bit counter that can't overflow in practice, potentially disadvantaging 32-bit platforms a tiny bit. This simplifies semantics and allows above described scenarios to not worry about failing refcount increment operation. In terms of struct bpf_map size, we are still good and use the same amount of space: BEFORE (3 cache lines, 8 bytes of padding at the end): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 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 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic_t refcnt __attribute__((__aligned__(64))); /* 128 4 */ atomic_t usercnt; /* 132 4 */ struct work_struct work; /* 136 32 */ char name[16]; /* 168 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 146, holes: 1, sum holes: 38 */ /* padding: 8 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); AFTER (same 3 cache lines, no extra padding now): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 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 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */ atomic64_t usercnt; /* 136 8 */ struct work_struct work; /* 144 32 */ char name[16]; /* 176 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 154, holes: 1, sum holes: 38 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); This patch, while modifying all users of bpf_map_inc, also cleans up its interface to match bpf_map_put with separate operations for bpf_map_inc and bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref, respectively). Also, given there are no users of bpf_map_inc_not_zero specifying uref=true, remove uref flag and default to uref=false internally. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com
2019-11-17 20:28:02 +03:00
atomic64_t refcnt ____cacheline_aligned;
atomic64_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 15:17:44 +03:00
struct work_struct work;
bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY Add ability to memory-map contents of BPF array map. This is extremely useful for working with BPF global data from userspace programs. It allows to avoid typical bpf_map_{lookup,update}_elem operations, improving both performance and usability. There had to be special considerations for map freezing, to avoid having writable memory view into a frozen map. To solve this issue, map freezing and mmap-ing is happening under mutex now: - if map is already frozen, no writable mapping is allowed; - if map has writable memory mappings active (accounted in map->writecnt), map freezing will keep failing with -EBUSY; - once number of writable memory mappings drops to zero, map freezing can be performed again. Only non-per-CPU plain arrays are supported right now. Maps with spinlocks can't be memory mapped either. For BPF_F_MMAPABLE array, memory allocation has to be done through vmalloc() to be mmap()'able. We also need to make sure that array data memory is page-sized and page-aligned, so we over-allocate memory in such a way that struct bpf_array is at the end of a single page of memory with array->value being aligned with the start of the second page. On deallocation we need to accomodate this memory arrangement to free vmalloc()'ed memory correctly. One important consideration regarding how memory-mapping subsystem functions. Memory-mapping subsystem provides few optional callbacks, among them open() and close(). close() is called for each memory region that is unmapped, so that users can decrease their reference counters and free up resources, if necessary. open() is *almost* symmetrical: it's called for each memory region that is being mapped, **except** the very first one. So bpf_map_mmap does initial refcnt bump, while open() will do any extra ones after that. Thus number of close() calls is equal to number of open() calls plus one more. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Link: https://lore.kernel.org/bpf/20191117172806.2195367-4-andriin@fb.com
2019-11-17 20:28:04 +03:00
struct mutex freeze_mutex;
u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */
};
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 02:40:04 +03:00
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);
int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
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 02:40:04 +03:00
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)
{
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) &&
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);
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 04:18:06 +03:00
bool bpf_map_meta_equal(const struct bpf_map *meta0,
const struct bpf_map *meta1);
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 11:17:06 +04:00
/* 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 11:17:06 +04:00
/* 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 02:39:39 +03:00
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 11:17:06 +04:00
/* 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 01:10:51 +03:00
*/
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 */
bpf: Add netns cookie and enable it for bpf cgroup hooks In Cilium we're mainly using BPF cgroup hooks today in order to implement kube-proxy free Kubernetes service translation for ClusterIP, NodePort (*), ExternalIP, and LoadBalancer as well as HostPort mapping [0] for all traffic between Cilium managed nodes. While this works in its current shape and avoids packet-level NAT for inter Cilium managed node traffic, there is one major limitation we're facing today, that is, lack of netns awareness. In Kubernetes, the concept of Pods (which hold one or multiple containers) has been built around network namespaces, so while we can use the global scope of attaching to root BPF cgroup hooks also to our advantage (e.g. for exposing NodePort ports on loopback addresses), we also have the need to differentiate between initial network namespaces and non-initial one. For example, ExternalIP services mandate that non-local service IPs are not to be translated from the host (initial) network namespace as one example. Right now, we have an ugly work-around in place where non-local service IPs for ExternalIP services are not xlated from connect() and friends BPF hooks but instead via less efficient packet-level NAT on the veth tc ingress hook for Pod traffic. On top of determining whether we're in initial or non-initial network namespace we also have a need for a socket-cookie like mechanism for network namespaces scope. Socket cookies have the nice property that they can be combined as part of the key structure e.g. for BPF LRU maps without having to worry that the cookie could be recycled. We are planning to use this for our sessionAffinity implementation for services. Therefore, add a new bpf_get_netns_cookie() helper which would resolve both use cases at once: bpf_get_netns_cookie(NULL) would provide the cookie for the initial network namespace while passing the context instead of NULL would provide the cookie from the application's network namespace. We're using a hole, so no size increase; the assignment happens only once. Therefore this allows for a comparison on initial namespace as well as regular cookie usage as we have today with socket cookies. We could later on enable this helper for other program types as well as we would see need. (*) Both externalTrafficPolicy={Local|Cluster} types [0] https://github.com/cilium/cilium/blob/master/bpf/bpf_sock.c Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/c47d2346982693a9cf9da0e12690453aded4c788.1585323121.git.daniel@iogearbox.net
2020-03-27 18:58:52 +03:00
ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */
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 02:40:04 +03:00
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 10:22:20 +03:00
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 02:39:39 +03:00
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
bpf: Introduce SK_LOOKUP program type with a dedicated attach point Add a new program type BPF_PROG_TYPE_SK_LOOKUP with a dedicated attach type BPF_SK_LOOKUP. The new program kind is to be invoked by the transport layer when looking up a listening socket for a new connection request for connection oriented protocols, or when looking up an unconnected socket for a packet for connection-less protocols. When called, SK_LOOKUP BPF program can select a socket that will receive the packet. This serves as a mechanism to overcome the limits of what bind() API allows to express. Two use-cases driving this work are: (1) steer packets destined to an IP range, on fixed port to a socket 192.0.2.0/24, port 80 -> NGINX socket (2) steer packets destined to an IP address, on any port to a socket 198.51.100.1, any port -> L7 proxy socket In its run-time context program receives information about the packet that triggered the socket lookup. Namely IP version, L4 protocol identifier, and address 4-tuple. Context can be further extended to include ingress interface identifier. To select a socket BPF program fetches it from a map holding socket references, like SOCKMAP or SOCKHASH, and calls bpf_sk_assign(ctx, sk, ...) helper to record the selection. Transport layer then uses the selected socket as a result of socket lookup. In its basic form, SK_LOOKUP acts as a filter and hence must return either SK_PASS or SK_DROP. If the program returns with SK_PASS, transport should look for a socket to receive the packet, or use the one selected by the program if available, while SK_DROP informs the transport layer that the lookup should fail. This patch only enables the user to attach an SK_LOOKUP program to a network namespace. Subsequent patches hook it up to run on local delivery path in ipv4 and ipv6 stacks. Suggested-by: Marek Majkowski <marek@cloudflare.com> Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200717103536.397595-3-jakub@cloudflare.com
2020-07-17 13:35:23 +03:00
ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */
ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 10:54:20 +03:00
ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */
ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */
ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */
bpf: Enable bpf_skc_to_* sock casting helper to networking prog type There is a constant need to add more fields into the bpf_tcp_sock for the bpf programs running at tc, sock_ops...etc. A current workaround could be to use bpf_probe_read_kernel(). However, other than making another helper call for reading each field and missing CO-RE, it is also not as intuitive to use as directly reading "tp->lsndtime" for example. While already having perfmon cap to do bpf_probe_read_kernel(), it will be much easier if the bpf prog can directly read from the tcp_sock. This patch tries to do that by using the existing casting-helpers bpf_skc_to_*() whose func_proto returns a btf_id. For example, the func_proto of bpf_skc_to_tcp_sock returns the btf_id of the kernel "struct tcp_sock". These helpers are also added to is_ptr_cast_function(). It ensures the returning reg (BPF_REF_0) will also carries the ref_obj_id. That will keep the ref-tracking works properly. The bpf_skc_to_* helpers are made available to most of the bpf prog types in filter.c. The bpf_skc_to_* helpers will be limited by perfmon cap. This patch adds a ARG_PTR_TO_BTF_ID_SOCK_COMMON. The helper accepting this arg can accept a btf-id-ptr (PTR_TO_BTF_ID + &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON]) or a legacy-ctx-convert-skc-ptr (PTR_TO_SOCK_COMMON). The bpf_skc_to_*() helpers are changed to take ARG_PTR_TO_BTF_ID_SOCK_COMMON such that they will accept pointer obtained from skb->sk. Instead of specifying both arg_type and arg_btf_id in the same func_proto which is how the current ARG_PTR_TO_BTF_ID does, the arg_btf_id of the new ARG_PTR_TO_BTF_ID_SOCK_COMMON is specified in the compatible_reg_types[] in verifier.c. The reason is the arg_btf_id is always the same. Discussion in this thread: https://lore.kernel.org/bpf/20200922070422.1917351-1-kafai@fb.com/ The ARG_PTR_TO_BTF_ID_ part gives a clear expectation that the helper is expecting a PTR_TO_BTF_ID which could be NULL. This is the same behavior as the existing helper taking ARG_PTR_TO_BTF_ID. The _SOCK_COMMON part means the helper is also expecting the legacy SOCK_COMMON pointer. By excluding the _OR_NULL part, the bpf prog cannot call helper with a literal NULL which doesn't make sense in most cases. e.g. bpf_skc_to_tcp_sock(NULL) will be rejected. All PTR_TO_*_OR_NULL reg has to do a NULL check first before passing into the helper or else the bpf prog will be rejected. This behavior is nothing new and consistent with the current expectation during bpf-prog-load. [ ARG_PTR_TO_BTF_ID_SOCK_COMMON will be used to replace ARG_PTR_TO_SOCK* of other existing helpers later such that those existing helpers can take the PTR_TO_BTF_ID returned by the bpf_skc_to_*() helpers. The only special case is bpf_sk_lookup_assign() which can accept a literal NULL ptr. It has to be handled specially in another follow up patch if there is a need (e.g. by renaming ARG_PTR_TO_SOCKET_OR_NULL to ARG_PTR_TO_BTF_ID_SOCK_COMMON_OR_NULL). ] [ When converting the older helpers that take ARG_PTR_TO_SOCK* in the later patch, if the kernel does not support BTF, ARG_PTR_TO_BTF_ID_SOCK_COMMON will behave like ARG_PTR_TO_SOCK_COMMON because no reg->type could have PTR_TO_BTF_ID in this case. It is not a concern for the newer-btf-only helper like the bpf_skc_to_*() here though because these helpers must require BTF vmlinux to begin with. ] Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200925000350.3855720-1-kafai@fb.com
2020-09-25 03:03:50 +03:00
ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */
ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */
__BPF_ARG_TYPE_MAX,
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 11:17:06 +04:00
};
/* 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 11:17:06 +04:00
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: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 10:54:20 +03:00
RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */
RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */
RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */
RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */
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 11:17:06 +04:00
};
/* 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 01:26:13 +03:00
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 11:17:06 +04:00
enum bpf_return_type ret_type;
union {
struct {
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;
};
enum bpf_arg_type arg_type[5];
};
union {
struct {
u32 *arg1_btf_id;
u32 *arg2_btf_id;
u32 *arg3_btf_id;
u32 *arg4_btf_id;
u32 *arg5_btf_id;
};
u32 *arg_btf_id[5];
};
int *ret_btf_id; /* return value btf_id */
bool (*allowed)(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 11:17:06 +04:00
};
/* 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 03:25:51 +03:00
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 10:22:20 +03:00
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 */
PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */
/* PTR_TO_BTF_ID points to a kernel struct that does not need
* to be null checked by the BPF program. This does not imply the
* pointer is _not_ null and in practice this can easily be a null
* pointer when reading pointer chains. The assumption is program
* context will handle null pointer dereference typically via fault
* handling. The verifier must keep this in mind and can make no
* assumptions about null or non-null when doing branch analysis.
* Further, when passed into helpers the helpers can not, without
* additional context, assume the value is non-null.
*/
PTR_TO_BTF_ID,
/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
* been checked for null. Used primarily to inform the verifier
* an explicit null check is required for this struct.
*/
PTR_TO_BTF_ID_OR_NULL,
bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 10:54:20 +03:00
PTR_TO_MEM, /* reg points to valid memory region */
PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */
PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */
PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */
PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */
PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */
PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */
};
/* The information passed from prog-specific *_is_valid_access
* back to the verifier.
*/
struct bpf_insn_access_aux {
enum bpf_reg_type reg_type;
bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
2019-10-16 06:25:00 +03:00
union {
int ctx_field_size;
u32 btf_id;
};
struct bpf_verifier_log *log; /* for verbose logs */
};
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 03:13:27 +03:00
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 01:08:00 +03:00
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 11:17:06 +04:00
/* 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 01:08:00 +03:00
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 01:26:13 +03:00
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 02:08:14 +03:00
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 03:13:27 +03:00
struct bpf_prog *prog, u32 *target_size);
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
int (*btf_struct_access)(struct bpf_verifier_log *log,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
};
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
/* The longest tracepoint has 12 args.
* See include/trace/bpf_probe.h
*/
#define MAX_BPF_FUNC_ARGS 12
struct bpf_prog_stats {
u64 cnt;
u64 nsecs;
struct u64_stats_sync syncp;
} __aligned(2 * sizeof(u64));
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
struct btf_func_model {
u8 ret_size;
u8 nr_args;
u8 arg_size[MAX_BPF_FUNC_ARGS];
};
/* Restore arguments before returning from trampoline to let original function
* continue executing. This flag is used for fentry progs when there are no
* fexit progs.
*/
#define BPF_TRAMP_F_RESTORE_REGS BIT(0)
/* Call original function after fentry progs, but before fexit progs.
* Makes sense for fentry/fexit, normal calls and indirect calls.
*/
#define BPF_TRAMP_F_CALL_ORIG BIT(1)
/* Skip current frame and return to parent. Makes sense for fentry/fexit
* programs only. Should not be used with normal calls and indirect calls.
*/
#define BPF_TRAMP_F_SKIP_FRAME BIT(2)
/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
* bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2
*/
#define BPF_MAX_TRAMP_PROGS 40
struct bpf_tramp_progs {
struct bpf_prog *progs[BPF_MAX_TRAMP_PROGS];
int nr_progs;
};
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
/* Different use cases for BPF trampoline:
* 1. replace nop at the function entry (kprobe equivalent)
* flags = BPF_TRAMP_F_RESTORE_REGS
* fentry = a set of programs to run before returning from trampoline
*
* 2. replace nop at the function entry (kprobe + kretprobe equivalent)
* flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME
* orig_call = fentry_ip + MCOUNT_INSN_SIZE
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*
* 3. replace direct call instruction anywhere in the function body
* or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid)
* With flags = 0
* fentry = a set of programs to run before returning from trampoline
* With flags = BPF_TRAMP_F_CALL_ORIG
* orig_call = original callback addr or direct function addr
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*/
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
int arch_prepare_bpf_trampoline(void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_progs *tprogs,
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
void *orig_call);
/* these two functions are called from generated trampoline */
u64 notrace __bpf_prog_enter(void);
void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
bpf: Introduce sleepable BPF programs Introduce sleepable BPF programs that can request such property for themselves via BPF_F_SLEEPABLE flag at program load time. In such case they will be able to use helpers like bpf_copy_from_user() that might sleep. At present only fentry/fexit/fmod_ret and lsm programs can request to be sleepable and only when they are attached to kernel functions that are known to allow sleeping. The non-sleepable programs are relying on implicit rcu_read_lock() and migrate_disable() to protect life time of programs, maps that they use and per-cpu kernel structures used to pass info between bpf programs and the kernel. The sleepable programs cannot be enclosed into rcu_read_lock(). migrate_disable() maps to preempt_disable() in non-RT kernels, so the progs should not be enclosed in migrate_disable() as well. Therefore rcu_read_lock_trace is used to protect the life time of sleepable progs. There are many networking and tracing program types. In many cases the 'struct bpf_prog *' pointer itself is rcu protected within some other kernel data structure and the kernel code is using rcu_dereference() to load that program pointer and call BPF_PROG_RUN() on it. All these cases are not touched. Instead sleepable bpf programs are allowed with bpf trampoline only. The program pointers are hard-coded into generated assembly of bpf trampoline and synchronize_rcu_tasks_trace() is used to protect the life time of the program. The same trampoline can hold both sleepable and non-sleepable progs. When rcu_read_lock_trace is held it means that some sleepable bpf program is running from bpf trampoline. Those programs can use bpf arrays and preallocated hash/lru maps. These map types are waiting on programs to complete via synchronize_rcu_tasks_trace(); Updates to trampoline now has to do synchronize_rcu_tasks_trace() and synchronize_rcu_tasks() to wait for sleepable progs to finish and for trampoline assembly to finish. This is the first step of introducing sleepable progs. Eventually dynamically allocated hash maps can be allowed and networking program types can become sleepable too. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: KP Singh <kpsingh@google.com> Link: https://lore.kernel.org/bpf/20200827220114.69225-3-alexei.starovoitov@gmail.com
2020-08-28 01:01:11 +03:00
void notrace __bpf_prog_enter_sleepable(void);
void notrace __bpf_prog_exit_sleepable(void);
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
struct bpf_ksym {
unsigned long start;
unsigned long end;
char name[KSYM_NAME_LEN];
struct list_head lnode;
struct latch_tree_node tnode;
bool prog;
};
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
enum bpf_tramp_prog_type {
BPF_TRAMP_FENTRY,
BPF_TRAMP_FEXIT,
BPF_TRAMP_MODIFY_RETURN,
bpf: Introduce dynamic program extensions Introduce dynamic program extensions. The users can load additional BPF functions and replace global functions in previously loaded BPF programs while these programs are executing. Global functions are verified individually by the verifier based on their types only. Hence the global function in the new program which types match older function can safely replace that corresponding function. This new function/program is called 'an extension' of old program. At load time the verifier uses (attach_prog_fd, attach_btf_id) pair to identify the function to be replaced. The BPF program type is derived from the target program into extension program. Technically bpf_verifier_ops is copied from target program. The BPF_PROG_TYPE_EXT program type is a placeholder. It has empty verifier_ops. The extension program can call the same bpf helper functions as target program. Single BPF_PROG_TYPE_EXT type is used to extend XDP, SKB and all other program types. The verifier allows only one level of replacement. Meaning that the extension program cannot recursively extend an extension. That also means that the maximum stack size is increasing from 512 to 1024 bytes and maximum function nesting level from 8 to 16. The programs don't always consume that much. The stack usage is determined by the number of on-stack variables used by the program. The verifier could have enforced 512 limit for combined original plus extension program, but it makes for difficult user experience. The main use case for extensions is to provide generic mechanism to plug external programs into policy program or function call chaining. BPF trampoline is used to track both fentry/fexit and program extensions because both are using the same nop slot at the beginning of every BPF function. Attaching fentry/fexit to a function that was replaced is not allowed. The opposite is true as well. Replacing a function that currently being analyzed with fentry/fexit is not allowed. The executable page allocated by BPF trampoline is not used by program extensions. This inefficiency will be optimized in future patches. Function by function verification of global function supports scalars and pointer to context only. Hence program extensions are supported for such class of global functions only. In the future the verifier will be extended with support to pointers to structures, arrays with sizes, etc. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200121005348.2769920-2-ast@kernel.org
2020-01-21 03:53:46 +03:00
BPF_TRAMP_MAX,
BPF_TRAMP_REPLACE, /* more than MAX */
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
};
struct bpf_trampoline {
/* hlist for trampoline_table */
struct hlist_node hlist;
/* serializes access to fields of this trampoline */
struct mutex mutex;
refcount_t refcnt;
u64 key;
struct {
struct btf_func_model model;
void *addr;
bool ftrace_managed;
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
} func;
bpf: Introduce dynamic program extensions Introduce dynamic program extensions. The users can load additional BPF functions and replace global functions in previously loaded BPF programs while these programs are executing. Global functions are verified individually by the verifier based on their types only. Hence the global function in the new program which types match older function can safely replace that corresponding function. This new function/program is called 'an extension' of old program. At load time the verifier uses (attach_prog_fd, attach_btf_id) pair to identify the function to be replaced. The BPF program type is derived from the target program into extension program. Technically bpf_verifier_ops is copied from target program. The BPF_PROG_TYPE_EXT program type is a placeholder. It has empty verifier_ops. The extension program can call the same bpf helper functions as target program. Single BPF_PROG_TYPE_EXT type is used to extend XDP, SKB and all other program types. The verifier allows only one level of replacement. Meaning that the extension program cannot recursively extend an extension. That also means that the maximum stack size is increasing from 512 to 1024 bytes and maximum function nesting level from 8 to 16. The programs don't always consume that much. The stack usage is determined by the number of on-stack variables used by the program. The verifier could have enforced 512 limit for combined original plus extension program, but it makes for difficult user experience. The main use case for extensions is to provide generic mechanism to plug external programs into policy program or function call chaining. BPF trampoline is used to track both fentry/fexit and program extensions because both are using the same nop slot at the beginning of every BPF function. Attaching fentry/fexit to a function that was replaced is not allowed. The opposite is true as well. Replacing a function that currently being analyzed with fentry/fexit is not allowed. The executable page allocated by BPF trampoline is not used by program extensions. This inefficiency will be optimized in future patches. Function by function verification of global function supports scalars and pointer to context only. Hence program extensions are supported for such class of global functions only. In the future the verifier will be extended with support to pointers to structures, arrays with sizes, etc. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200121005348.2769920-2-ast@kernel.org
2020-01-21 03:53:46 +03:00
/* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF
* program by replacing one of its functions. func.addr is the address
* of the function it replaced.
*/
struct bpf_prog *extension_prog;
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
/* list of BPF programs using this trampoline */
struct hlist_head progs_hlist[BPF_TRAMP_MAX];
/* Number of attached programs. A counter per kind. */
int progs_cnt[BPF_TRAMP_MAX];
/* Executable image of trampoline */
void *image;
u64 selector;
struct bpf_ksym ksym;
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
};
struct bpf_attach_target_info {
struct btf_func_model fmodel;
long tgt_addr;
const char *tgt_name;
const struct btf_type *tgt_type;
};
#define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */
struct bpf_dispatcher_prog {
struct bpf_prog *prog;
refcount_t users;
};
struct bpf_dispatcher {
/* dispatcher mutex */
struct mutex mutex;
void *func;
struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX];
int num_progs;
void *image;
u32 image_off;
struct bpf_ksym ksym;
};
static __always_inline unsigned int bpf_dispatcher_nop_func(
const void *ctx,
const struct bpf_insn *insnsi,
unsigned int (*bpf_func)(const void *,
const struct bpf_insn *))
{
return bpf_func(ctx, insnsi);
}
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
#ifdef CONFIG_BPF_JIT
int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr);
struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
void bpf_trampoline_put(struct bpf_trampoline *tr);
#define BPF_DISPATCHER_INIT(_name) { \
.mutex = __MUTEX_INITIALIZER(_name.mutex), \
.func = &_name##_func, \
.progs = {}, \
.num_progs = 0, \
.image = NULL, \
.image_off = 0, \
.ksym = { \
.name = #_name, \
.lnode = LIST_HEAD_INIT(_name.ksym.lnode), \
}, \
}
#define DEFINE_BPF_DISPATCHER(name) \
noinline unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
unsigned int (*bpf_func)(const void *, \
const struct bpf_insn *)) \
{ \
return bpf_func(ctx, insnsi); \
} \
EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \
struct bpf_dispatcher bpf_dispatcher_##name = \
BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
#define DECLARE_BPF_DISPATCHER(name) \
unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
const struct bpf_insn *insnsi, \
unsigned int (*bpf_func)(const void *, \
const struct bpf_insn *)); \
extern struct bpf_dispatcher bpf_dispatcher_##name;
#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
#define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
struct bpf_prog *to);
/* Called only from JIT-enabled code, so there's no need for stubs. */
void *bpf_jit_alloc_exec_page(void);
void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
void bpf_image_ksym_del(struct bpf_ksym *ksym);
void bpf_ksym_add(struct bpf_ksym *ksym);
void bpf_ksym_del(struct bpf_ksym *ksym);
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
#else
static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
struct bpf_trampoline *tr)
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
{
return -ENOTSUPP;
}
static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog,
struct bpf_trampoline *tr)
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
{
return -ENOTSUPP;
}
static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info)
{
return ERR_PTR(-EOPNOTSUPP);
}
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
#define DEFINE_BPF_DISPATCHER(name)
#define DECLARE_BPF_DISPATCHER(name)
#define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func
#define BPF_DISPATCHER_PTR(name) NULL
static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d,
struct bpf_prog *from,
struct bpf_prog *to) {}
static inline bool is_bpf_image_address(unsigned long address)
{
return false;
}
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
#endif
struct bpf_func_info_aux {
bpf: Introduce function-by-function verification New llvm and old llvm with libbpf help produce BTF that distinguish global and static functions. Unlike arguments of static function the arguments of global functions cannot be removed or optimized away by llvm. The compiler has to use exactly the arguments specified in a function prototype. The argument type information allows the verifier validate each global function independently. For now only supported argument types are pointer to context and scalars. In the future pointers to structures, sizes, pointer to packet data can be supported as well. Consider the following example: static int f1(int ...) { ... } int f3(int b); int f2(int a) { f1(a) + f3(a); } int f3(int b) { ... } int main(...) { f1(...) + f2(...) + f3(...); } The verifier will start its safety checks from the first global function f2(). It will recursively descend into f1() because it's static. Then it will check that arguments match for the f3() invocation inside f2(). It will not descend into f3(). It will finish f2() that has to be successfully verified for all possible values of 'a'. Then it will proceed with f3(). That function also has to be safe for all possible values of 'b'. Then it will start subprog 0 (which is main() function). It will recursively descend into f1() and will skip full check of f2() and f3(), since they are global. The order of processing global functions doesn't affect safety, since all global functions must be proven safe based on their arguments only. Such function by function verification can drastically improve speed of the verification and reduce complexity. Note that the stack limit of 512 still applies to the call chain regardless whether functions were static or global. The nested level of 8 also still applies. The same recursion prevention checks are in place as well. The type information and static/global kind is preserved after the verification hence in the above example global function f2() and f3() can be replaced later by equivalent functions with the same types that are loaded and verified later without affecting safety of this main() program. Such replacement (re-linking) of global functions is a subject of future patches. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200110064124.1760511-3-ast@kernel.org
2020-01-10 09:41:20 +03:00
u16 linkage;
bool unreliable;
};
enum bpf_jit_poke_reason {
BPF_POKE_REASON_TAIL_CALL,
};
/* Descriptor of pokes pointing /into/ the JITed image. */
struct bpf_jit_poke_descriptor {
void *tailcall_target;
bpf, x64: rework pro/epilogue and tailcall handling in JIT This commit serves two things: 1) it optimizes BPF prologue/epilogue generation 2) it makes possible to have tailcalls within BPF subprogram Both points are related to each other since without 1), 2) could not be achieved. In [1], Alexei says: "The prologue will look like: nop5 xor eax,eax  // two new bytes if bpf_tail_call() is used in this // function push rbp mov rbp, rsp sub rsp, rounded_stack_depth push rax // zero init tail_call counter variable number of push rbx,r13,r14,r15 Then bpf_tail_call will pop variable number rbx,.. and final 'pop rax' Then 'add rsp, size_of_current_stack_frame' jmp to next function and skip over 'nop5; xor eax,eax; push rpb; mov rbp, rsp' This way new function will set its own stack size and will init tail call counter with whatever value the parent had. If next function doesn't use bpf_tail_call it won't have 'xor eax,eax'. Instead it would need to have 'nop2' in there." Implement that suggestion. Since the layout of stack is changed, tail call counter handling can not rely anymore on popping it to rbx just like it have been handled for constant prologue case and later overwrite of rbx with actual value of rbx pushed to stack. Therefore, let's use one of the register (%rcx) that is considered to be volatile/caller-saved and pop the value of tail call counter in there in the epilogue. Drop the BUILD_BUG_ON in emit_prologue and in emit_bpf_tail_call_indirect where instruction layout is not constant anymore. Introduce new poke target, 'tailcall_bypass' to poke descriptor that is dedicated for skipping the register pops and stack unwind that are generated right before the actual jump to target program. For case when the target program is not present, BPF program will skip the pop instructions and nop5 dedicated for jmpq $target. An example of such state when only R6 of callee saved registers is used by program: ffffffffc0513aa1: e9 0e 00 00 00 jmpq 0xffffffffc0513ab4 ffffffffc0513aa6: 5b pop %rbx ffffffffc0513aa7: 58 pop %rax ffffffffc0513aa8: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc0513aaf: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0513ab4: 48 89 df mov %rbx,%rdi When target program is inserted, the jump that was there to skip pops/nop5 will become the nop5, so CPU will go over pops and do the actual tailcall. One might ask why there simply can not be pushes after the nop5? In the following example snippet: ffffffffc037030c: 48 89 fb mov %rdi,%rbx (...) ffffffffc0370332: 5b pop %rbx ffffffffc0370333: 58 pop %rax ffffffffc0370334: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc037033b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0370340: 48 81 ec 00 00 00 00 sub $0x0,%rsp ffffffffc0370347: 50 push %rax ffffffffc0370348: 53 push %rbx ffffffffc0370349: 48 89 df mov %rbx,%rdi ffffffffc037034c: e8 f7 21 00 00 callq 0xffffffffc0372548 There is the bpf2bpf call (at ffffffffc037034c) right after the tailcall and jump target is not present. ctx is in %rbx register and BPF subprogram that we will call into on ffffffffc037034c is relying on it, e.g. it will pick ctx from there. Such code layout is therefore broken as we would overwrite the content of %rbx with the value that was pushed on the prologue. That is the reason for the 'bypass' approach. Special care needs to be taken during the install/update/remove of tailcall target. In case when target program is not present, the CPU must not execute the pop instructions that precede the tailcall. To address that, the following states can be defined: A nop, unwind, nop B nop, unwind, tail C skip, unwind, nop D skip, unwind, tail A is forbidden (lead to incorrectness). The state transitions between tailcall install/update/remove will work as follows: First install tail call f: C->D->B(f) * poke the tailcall, after that get rid of the skip Update tail call f to f': B(f)->B(f') * poke the tailcall (poke->tailcall_target) and do NOT touch the poke->tailcall_bypass Remove tail call: B(f')->C(f') * poke->tailcall_bypass is poked back to jump, then we wait the RCU grace period so that other programs will finish its execution and after that we are safe to remove the poke->tailcall_target Install new tail call (f''): C(f')->D(f'')->B(f''). * same as first step This way CPU can never be exposed to "unwind, tail" state. Last but not least, when tailcalls get mixed with bpf2bpf calls, it would be possible to encounter the endless loop due to clearing the tailcall counter if for example we would use the tailcall3-like from BPF selftests program that would be subprogram-based, meaning the tailcall would be present within the BPF subprogram. This test, broken down to particular steps, would do: entry -> set tailcall counter to 0, bump it by 1, tailcall to func0 func0 -> call subprog_tail (we are NOT skipping the first 11 bytes of prologue and this subprogram has a tailcall, therefore we clear the counter...) subprog -> do the same thing as entry and then loop forever. To address this, the idea is to go through the call chain of bpf2bpf progs and look for a tailcall presence throughout whole chain. If we saw a single tail call then each node in this call chain needs to be marked as a subprog that can reach the tailcall. We would later feed the JIT with this info and: - set eax to 0 only when tailcall is reachable and this is the entry prog - if tailcall is reachable but there's no tailcall in insns of currently JITed prog then push rax anyway, so that it will be possible to propagate further down the call chain - finally if tailcall is reachable, then we need to precede the 'call' insn with mov rax, [rbp - (stack_depth + 8)] Tail call related cases from test_verifier kselftest are also working fine. Sample BPF programs that utilize tail calls (sockex3, tracex5) work properly as well. [1]: https://lore.kernel.org/bpf/20200517043227.2gpq22ifoq37ogst@ast-mbp.dhcp.thefacebook.com/ Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-09-17 00:10:08 +03:00
void *tailcall_bypass;
void *bypass_addr;
union {
struct {
struct bpf_map *map;
u32 key;
} tail_call;
};
bool tailcall_target_stable;
u8 adj_off;
u16 reason;
u32 insn_idx;
};
/* reg_type info for ctx arguments */
struct bpf_ctx_arg_aux {
u32 offset;
enum bpf_reg_type reg_type;
u32 btf_id;
};
struct bpf_prog_aux {
atomic64_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 */
u32 attach_btf_id; /* in-kernel BTF type id to attach to */
u32 ctx_arg_info_size;
u32 max_rdonly_access;
u32 max_rdwr_access;
const struct bpf_ctx_arg_aux *ctx_arg_info;
struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
struct bpf_prog *dst_prog;
struct bpf_trampoline *dst_trampoline;
enum bpf_prog_type saved_dst_prog_type;
enum bpf_attach_type saved_dst_attach_type;
bpf: verifier: insert zero extension according to analysis result After previous patches, verifier will mark a insn if it really needs zero extension on dst_reg. It is then for back-ends to decide how to use such information to eliminate unnecessary zero extension code-gen during JIT compilation. One approach is verifier insert explicit zero extension for those insns that need zero extension in a generic way, JIT back-ends then do not generate zero extension for sub-register write at default. However, only those back-ends which do not have hardware zero extension want this optimization. Back-ends like x86_64 and AArch64 have hardware zero extension support that the insertion should be disabled. This patch introduces new target hook "bpf_jit_needs_zext" which returns false at default, meaning verifier zero extension insertion is disabled at default. A back-end could override this hook to return true if it doesn't have hardware support and want verifier insert zero extension explicitly. Offload targets do not use this native target hook, instead, they could get the optimization results using bpf_prog_offload_ops.finalize. NOTE: arches could have diversified features, it is possible for one arch to have hardware zero extension support for some sub-register write insns but not for all. For example, PowerPC, SPARC have zero extended loads, but not for alu32. So when verifier zero extension insertion enabled, these JIT back-ends need to peephole insns to remove those zero extension inserted for insn that actually has hardware zero extension support. The peephole could be as simple as looking the next insn, if it is a special zero extension insn then it is safe to eliminate it if the current insn has hardware zero extension support. Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Jiong Wang <jiong.wang@netronome.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-25 01:25:15 +03:00
bool verifier_zext; /* Zero extensions has been inserted by verifier. */
bool offload_requested;
bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
bool func_proto_unreliable;
bpf: Introduce sleepable BPF programs Introduce sleepable BPF programs that can request such property for themselves via BPF_F_SLEEPABLE flag at program load time. In such case they will be able to use helpers like bpf_copy_from_user() that might sleep. At present only fentry/fexit/fmod_ret and lsm programs can request to be sleepable and only when they are attached to kernel functions that are known to allow sleeping. The non-sleepable programs are relying on implicit rcu_read_lock() and migrate_disable() to protect life time of programs, maps that they use and per-cpu kernel structures used to pass info between bpf programs and the kernel. The sleepable programs cannot be enclosed into rcu_read_lock(). migrate_disable() maps to preempt_disable() in non-RT kernels, so the progs should not be enclosed in migrate_disable() as well. Therefore rcu_read_lock_trace is used to protect the life time of sleepable progs. There are many networking and tracing program types. In many cases the 'struct bpf_prog *' pointer itself is rcu protected within some other kernel data structure and the kernel code is using rcu_dereference() to load that program pointer and call BPF_PROG_RUN() on it. All these cases are not touched. Instead sleepable bpf programs are allowed with bpf trampoline only. The program pointers are hard-coded into generated assembly of bpf trampoline and synchronize_rcu_tasks_trace() is used to protect the life time of the program. The same trampoline can hold both sleepable and non-sleepable progs. When rcu_read_lock_trace is held it means that some sleepable bpf program is running from bpf trampoline. Those programs can use bpf arrays and preallocated hash/lru maps. These map types are waiting on programs to complete via synchronize_rcu_tasks_trace(); Updates to trampoline now has to do synchronize_rcu_tasks_trace() and synchronize_rcu_tasks() to wait for sleepable progs to finish and for trampoline assembly to finish. This is the first step of introducing sleepable progs. Eventually dynamically allocated hash maps can be allowed and networking program types can become sleepable too. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: KP Singh <kpsingh@google.com> Link: https://lore.kernel.org/bpf/20200827220114.69225-3-alexei.starovoitov@gmail.com
2020-08-28 01:01:11 +03:00
bool sleepable;
bpf, x64: rework pro/epilogue and tailcall handling in JIT This commit serves two things: 1) it optimizes BPF prologue/epilogue generation 2) it makes possible to have tailcalls within BPF subprogram Both points are related to each other since without 1), 2) could not be achieved. In [1], Alexei says: "The prologue will look like: nop5 xor eax,eax  // two new bytes if bpf_tail_call() is used in this // function push rbp mov rbp, rsp sub rsp, rounded_stack_depth push rax // zero init tail_call counter variable number of push rbx,r13,r14,r15 Then bpf_tail_call will pop variable number rbx,.. and final 'pop rax' Then 'add rsp, size_of_current_stack_frame' jmp to next function and skip over 'nop5; xor eax,eax; push rpb; mov rbp, rsp' This way new function will set its own stack size and will init tail call counter with whatever value the parent had. If next function doesn't use bpf_tail_call it won't have 'xor eax,eax'. Instead it would need to have 'nop2' in there." Implement that suggestion. Since the layout of stack is changed, tail call counter handling can not rely anymore on popping it to rbx just like it have been handled for constant prologue case and later overwrite of rbx with actual value of rbx pushed to stack. Therefore, let's use one of the register (%rcx) that is considered to be volatile/caller-saved and pop the value of tail call counter in there in the epilogue. Drop the BUILD_BUG_ON in emit_prologue and in emit_bpf_tail_call_indirect where instruction layout is not constant anymore. Introduce new poke target, 'tailcall_bypass' to poke descriptor that is dedicated for skipping the register pops and stack unwind that are generated right before the actual jump to target program. For case when the target program is not present, BPF program will skip the pop instructions and nop5 dedicated for jmpq $target. An example of such state when only R6 of callee saved registers is used by program: ffffffffc0513aa1: e9 0e 00 00 00 jmpq 0xffffffffc0513ab4 ffffffffc0513aa6: 5b pop %rbx ffffffffc0513aa7: 58 pop %rax ffffffffc0513aa8: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc0513aaf: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0513ab4: 48 89 df mov %rbx,%rdi When target program is inserted, the jump that was there to skip pops/nop5 will become the nop5, so CPU will go over pops and do the actual tailcall. One might ask why there simply can not be pushes after the nop5? In the following example snippet: ffffffffc037030c: 48 89 fb mov %rdi,%rbx (...) ffffffffc0370332: 5b pop %rbx ffffffffc0370333: 58 pop %rax ffffffffc0370334: 48 81 c4 00 00 00 00 add $0x0,%rsp ffffffffc037033b: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) ffffffffc0370340: 48 81 ec 00 00 00 00 sub $0x0,%rsp ffffffffc0370347: 50 push %rax ffffffffc0370348: 53 push %rbx ffffffffc0370349: 48 89 df mov %rbx,%rdi ffffffffc037034c: e8 f7 21 00 00 callq 0xffffffffc0372548 There is the bpf2bpf call (at ffffffffc037034c) right after the tailcall and jump target is not present. ctx is in %rbx register and BPF subprogram that we will call into on ffffffffc037034c is relying on it, e.g. it will pick ctx from there. Such code layout is therefore broken as we would overwrite the content of %rbx with the value that was pushed on the prologue. That is the reason for the 'bypass' approach. Special care needs to be taken during the install/update/remove of tailcall target. In case when target program is not present, the CPU must not execute the pop instructions that precede the tailcall. To address that, the following states can be defined: A nop, unwind, nop B nop, unwind, tail C skip, unwind, nop D skip, unwind, tail A is forbidden (lead to incorrectness). The state transitions between tailcall install/update/remove will work as follows: First install tail call f: C->D->B(f) * poke the tailcall, after that get rid of the skip Update tail call f to f': B(f)->B(f') * poke the tailcall (poke->tailcall_target) and do NOT touch the poke->tailcall_bypass Remove tail call: B(f')->C(f') * poke->tailcall_bypass is poked back to jump, then we wait the RCU grace period so that other programs will finish its execution and after that we are safe to remove the poke->tailcall_target Install new tail call (f''): C(f')->D(f'')->B(f''). * same as first step This way CPU can never be exposed to "unwind, tail" state. Last but not least, when tailcalls get mixed with bpf2bpf calls, it would be possible to encounter the endless loop due to clearing the tailcall counter if for example we would use the tailcall3-like from BPF selftests program that would be subprogram-based, meaning the tailcall would be present within the BPF subprogram. This test, broken down to particular steps, would do: entry -> set tailcall counter to 0, bump it by 1, tailcall to func0 func0 -> call subprog_tail (we are NOT skipping the first 11 bytes of prologue and this subprogram has a tailcall, therefore we clear the counter...) subprog -> do the same thing as entry and then loop forever. To address this, the idea is to go through the call chain of bpf2bpf progs and look for a tailcall presence throughout whole chain. If we saw a single tail call then each node in this call chain needs to be marked as a subprog that can reach the tailcall. We would later feed the JIT with this info and: - set eax to 0 only when tailcall is reachable and this is the entry prog - if tailcall is reachable but there's no tailcall in insns of currently JITed prog then push rax anyway, so that it will be possible to propagate further down the call chain - finally if tailcall is reachable, then we need to precede the 'call' insn with mov rax, [rbp - (stack_depth + 8)] Tail call related cases from test_verifier kselftest are also working fine. Sample BPF programs that utilize tail calls (sockex3, tracex5) work properly as well. [1]: https://lore.kernel.org/bpf/20200517043227.2gpq22ifoq37ogst@ast-mbp.dhcp.thefacebook.com/ Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-09-17 00:10:08 +03:00
bool tail_call_reachable;
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
enum bpf_tramp_prog_type trampoline_prog_type;
struct hlist_node tramp_hlist;
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
/* function name for valid attach_btf_id */
const char *attach_func_name;
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 04:55:15 +03:00
struct bpf_prog **func;
void *jit_data; /* JIT specific data. arch dependent */
struct bpf_jit_poke_descriptor *poke_tab;
u32 size_poke_tab;
struct bpf_ksym ksym;
const struct bpf_prog_ops *ops;
struct bpf_map **used_maps;
struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
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 02:29:11 +03:00
struct btf *btf;
struct bpf_func_info *func_info;
struct bpf_func_info_aux *func_info_aux;
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 03:42:25 +03:00
/* 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 03:42:25 +03:00
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;
bpf: Add support for BTF pointers to x86 JIT Pointer to BTF object is a pointer to kernel object or NULL. Such pointers can only be used by BPF_LDX instructions. The verifier changed their opcode from LDX|MEM|size to LDX|PROBE_MEM|size to make JITing easier. The number of entries in extable is the number of BPF_LDX insns that access kernel memory via "pointer to BTF type". Only these load instructions can fault. Since x86 extable is relative it has to be allocated in the same memory region as JITed code. Allocate it prior to last pass of JITing and let the last pass populate it. Pointer to extable in bpf_prog_aux is necessary to make page fault handling fast. Page fault handling is done in two steps: 1. bpf_prog_kallsyms_find() finds BPF program that page faulted. It's done by walking rb tree. 2. then extable for given bpf program is binary searched. This process is similar to how page faulting is done for kernel modules. The exception handler skips over faulting x86 instruction and initializes destination register with zero. This mimics exact behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed). JITs for other architectures can add support in similar way. Until then they will reject unknown opcode and fallback to interpreter. Since extable should be aligned and placed near JITed code make bpf_jit_binary_alloc() return 4 byte aligned image offset, so that extable aligning formula in bpf_int_jit_compile() doesn't need to rely on internal implementation of bpf_jit_binary_alloc(). On x86 gcc defaults to 16-byte alignment for regular kernel functions due to better performance. JITed code may be aligned to 16 in the future, but it will use 4 in the meantime. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org
2019-10-16 06:25:03 +03:00
u32 num_exentries;
struct exception_table_entry *extable;
struct bpf_prog_stats __percpu *stats;
union {
struct work_struct work;
struct rcu_head rcu;
};
};
struct bpf_array_aux {
/* '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 type;
bool jited;
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
struct mutex poke_mutex;
struct work_struct work;
};
struct bpf_link {
atomic64_t refcnt;
u32 id;
enum bpf_link_type type;
const struct bpf_link_ops *ops;
struct bpf_prog *prog;
struct work_struct work;
};
struct bpf_link_ops {
void (*release)(struct bpf_link *link);
void (*dealloc)(struct bpf_link *link);
int (*detach)(struct bpf_link *link);
int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
struct bpf_prog *old_prog);
void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
int (*fill_link_info)(const struct bpf_link *link,
struct bpf_link_info *info);
};
struct bpf_link_primer {
struct bpf_link *link;
struct file *file;
int fd;
u32 id;
};
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
struct bpf_struct_ops_value;
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
struct btf_type;
struct btf_member;
#define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
struct bpf_struct_ops {
const struct bpf_verifier_ops *verifier_ops;
int (*init)(struct btf *btf);
int (*check_member)(const struct btf_type *t,
const struct btf_member *member);
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
int (*init_member)(const struct btf_type *t,
const struct btf_member *member,
void *kdata, const void *udata);
int (*reg)(void *kdata);
void (*unreg)(void *kdata);
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
const struct btf_type *type;
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
const struct btf_type *value_type;
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
const char *name;
struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
u32 type_id;
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
u32 value_id;
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
};
#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
#define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log);
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
bool bpf_struct_ops_get(const void *kdata);
void bpf_struct_ops_put(const void *kdata);
int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
void *value);
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
return bpf_struct_ops_get(data);
else
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
if (owner == BPF_MODULE_OWNER)
bpf_struct_ops_put(data);
else
module_put(owner);
}
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
#else
static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
{
return NULL;
}
static inline void bpf_struct_ops_init(struct btf *btf,
struct bpf_verifier_log *log)
{
}
bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS The patch introduces BPF_MAP_TYPE_STRUCT_OPS. The map value is a kernel struct with its func ptr implemented in bpf prog. This new map is the interface to register/unregister/introspect a bpf implemented kernel struct. The kernel struct is actually embedded inside another new struct (or called the "value" struct in the code). For example, "struct tcp_congestion_ops" is embbeded in: struct bpf_struct_ops_tcp_congestion_ops { refcount_t refcnt; enum bpf_struct_ops_state state; struct tcp_congestion_ops data; /* <-- kernel subsystem struct here */ } The map value is "struct bpf_struct_ops_tcp_congestion_ops". The "bpftool map dump" will then be able to show the state ("inuse"/"tobefree") and the number of subsystem's refcnt (e.g. number of tcp_sock in the tcp_congestion_ops case). This "value" struct is created automatically by a macro. Having a separate "value" struct will also make extending "struct bpf_struct_ops_XYZ" easier (e.g. adding "void (*init)(void)" to "struct bpf_struct_ops_XYZ" to do some initialization works before registering the struct_ops to the kernel subsystem). The libbpf will take care of finding and populating the "struct bpf_struct_ops_XYZ" from "struct XYZ". Register a struct_ops to a kernel subsystem: 1. Load all needed BPF_PROG_TYPE_STRUCT_OPS prog(s) 2. Create a BPF_MAP_TYPE_STRUCT_OPS with attr->btf_vmlinux_value_type_id set to the btf id "struct bpf_struct_ops_tcp_congestion_ops" of the running kernel. Instead of reusing the attr->btf_value_type_id, btf_vmlinux_value_type_id s added such that attr->btf_fd can still be used as the "user" btf which could store other useful sysadmin/debug info that may be introduced in the furture, e.g. creation-date/compiler-details/map-creator...etc. 3. Create a "struct bpf_struct_ops_tcp_congestion_ops" object as described in the running kernel btf. Populate the value of this object. The function ptr should be populated with the prog fds. 4. Call BPF_MAP_UPDATE with the object created in (3) as the map value. The key is always "0". During BPF_MAP_UPDATE, the code that saves the kernel-func-ptr's args as an array of u64 is generated. BPF_MAP_UPDATE also allows the specific struct_ops to do some final checks in "st_ops->init_member()" (e.g. ensure all mandatory func ptrs are implemented). If everything looks good, it will register this kernel struct to the kernel subsystem. The map will not allow further update from this point. Unregister a struct_ops from the kernel subsystem: BPF_MAP_DELETE with key "0". Introspect a struct_ops: BPF_MAP_LOOKUP_ELEM with key "0". The map value returned will have the prog _id_ populated as the func ptr. The map value state (enum bpf_struct_ops_state) will transit from: INIT (map created) => INUSE (map updated, i.e. reg) => TOBEFREE (map value deleted, i.e. unreg) The kernel subsystem needs to call bpf_struct_ops_get() and bpf_struct_ops_put() to manage the "refcnt" in the "struct bpf_struct_ops_XYZ". This patch uses a separate refcnt for the purose of tracking the subsystem usage. Another approach is to reuse the map->refcnt and then "show" (i.e. during map_lookup) the subsystem's usage by doing map->refcnt - map->usercnt to filter out the map-fd/pinned-map usage. However, that will also tie down the future semantics of map->refcnt and map->usercnt. The very first subsystem's refcnt (during reg()) holds one count to map->refcnt. When the very last subsystem's refcnt is gone, it will also release the map->refcnt. All bpf_prog will be freed when the map->refcnt reaches 0 (i.e. during map_free()). Here is how the bpftool map command will look like: [root@arch-fb-vm1 bpf]# bpftool map show 6: struct_ops name dctcp flags 0x0 key 4B value 256B max_entries 1 memlock 4096B btf_id 6 [root@arch-fb-vm1 bpf]# bpftool map dump id 6 [{ "value": { "refcnt": { "refs": { "counter": 1 } }, "state": 1, "data": { "list": { "next": 0, "prev": 0 }, "key": 0, "flags": 2, "init": 24, "release": 0, "ssthresh": 25, "cong_avoid": 30, "set_state": 27, "cwnd_event": 28, "in_ack_event": 26, "undo_cwnd": 29, "pkts_acked": 0, "min_tso_segs": 0, "sndbuf_expand": 0, "cong_control": 0, "get_info": 0, "name": [98,112,102,95,100,99,116,99,112,0,0,0,0,0,0,0 ], "owner": 0 } } } ] Misc Notes: * bpf_struct_ops_map_sys_lookup_elem() is added for syscall lookup. It does an inplace update on "*value" instead returning a pointer to syscall.c. Otherwise, it needs a separate copy of "zero" value for the BPF_STRUCT_OPS_STATE_INIT to avoid races. * The bpf_struct_ops_map_delete_elem() is also called without preempt_disable() from map_delete_elem(). It is because the "->unreg()" may requires sleepable context, e.g. the "tcp_unregister_congestion_control()". * "const" is added to some of the existing "struct btf_func_model *" function arg to avoid a compiler warning caused by this patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003505.3855919-1-kafai@fb.com
2020-01-09 03:35:05 +03:00
static inline bool bpf_try_module_get(const void *data, struct module *owner)
{
return try_module_get(owner);
}
static inline void bpf_module_put(const void *data, struct module *owner)
{
module_put(owner);
}
static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
void *key,
void *value)
{
return -EINVAL;
}
bpf: Introduce BPF_PROG_TYPE_STRUCT_OPS This patch allows the kernel's struct ops (i.e. func ptr) to be implemented in BPF. The first use case in this series is the "struct tcp_congestion_ops" which will be introduced in a latter patch. This patch introduces a new prog type BPF_PROG_TYPE_STRUCT_OPS. The BPF_PROG_TYPE_STRUCT_OPS prog is verified against a particular func ptr of a kernel struct. The attr->attach_btf_id is the btf id of a kernel struct. The attr->expected_attach_type is the member "index" of that kernel struct. The first member of a struct starts with member index 0. That will avoid ambiguity when a kernel struct has multiple func ptrs with the same func signature. For example, a BPF_PROG_TYPE_STRUCT_OPS prog is written to implement the "init" func ptr of the "struct tcp_congestion_ops". The attr->attach_btf_id is the btf id of the "struct tcp_congestion_ops" of the _running_ kernel. The attr->expected_attach_type is 3. The ctx of BPF_PROG_TYPE_STRUCT_OPS is an array of u64 args saved by arch_prepare_bpf_trampoline that will be done in the next patch when introducing BPF_MAP_TYPE_STRUCT_OPS. "struct bpf_struct_ops" is introduced as a common interface for the kernel struct that supports BPF_PROG_TYPE_STRUCT_OPS prog. The supporting kernel struct will need to implement an instance of the "struct bpf_struct_ops". The supporting kernel struct also needs to implement a bpf_verifier_ops. During BPF_PROG_LOAD, bpf_struct_ops_find() will find the right bpf_verifier_ops by searching the attr->attach_btf_id. A new "btf_struct_access" is also added to the bpf_verifier_ops such that the supporting kernel struct can optionally provide its own specific check on accessing the func arg (e.g. provide limited write access). After btf_vmlinux is parsed, the new bpf_struct_ops_init() is called to initialize some values (e.g. the btf id of the supporting kernel struct) and it can only be done once the btf_vmlinux is available. The R0 checks at BPF_EXIT is excluded for the BPF_PROG_TYPE_STRUCT_OPS prog if the return type of the prog->aux->attach_func_proto is "void". Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200109003503.3855825-1-kafai@fb.com
2020-01-09 03:35:03 +03:00
#endif
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 02:59:03 +03:00
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 04:33:02 +03:00
u32 index_mask;
struct bpf_array_aux *aux;
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 02:59:03 +03:00
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 02:59:03 +03:00
};
};
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>
2016-06-15 23:47:14 +03:00
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 07:27:45 +03:00
#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 02:59:03 +03:00
#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>
2016-06-15 23:47:14 +03:00
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 02:59:03 +03:00
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 01:38:15 +03:00
int bpf_prog_calc_tag(struct bpf_prog *fp);
bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
2019-10-16 06:25:00 +03:00
const char *kernel_type_name(u32 btf_type_id);
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>
2016-04-18 22:01:24 +03:00
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>
2016-07-14 19:08:05 +03:00
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 02:19:42 +03:00
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>
2016-07-14 19:08:05 +03:00
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 02:59:03 +03:00
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 08:50:21 +03:00
/* 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 08:50:21 +03:00
struct bpf_prog_array {
struct rcu_head rcu;
struct bpf_prog_array_item items[];
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 08:50:21 +03:00
};
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] <asn:4> * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] <asn:4> * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin <guro@fb.com> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-29 00:14:41 +03:00
void bpf_prog_array_free(struct bpf_prog_array *progs);
int bpf_prog_array_length(struct bpf_prog_array *progs);
bpf: implement getsockopt and setsockopt hooks Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks. BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before passing them down to the kernel or bypass kernel completely. BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that kernel returns. Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure. The buffer memory is pre-allocated (because I don't think there is a precedent for working with __user memory from bpf). This might be slow to do for each {s,g}etsockopt call, that's why I've added __cgroup_bpf_prog_array_is_empty that exits early if there is nothing attached to a cgroup. Note, however, that there is a race between __cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup program layout might have changed; this should not be a problem because in general there is a race between multiple calls to {s,g}etsocktop and user adding/removing bpf progs from a cgroup. The return code of the BPF program is handled as follows: * 0: EPERM * 1: success, continue with next BPF program in the cgroup chain v9: * allow overwriting setsockopt arguments (Alexei Starovoitov): * use set_fs (same as kernel_setsockopt) * buffer is always kzalloc'd (no small on-stack buffer) v8: * use s32 for optlen (Andrii Nakryiko) v7: * return only 0 or 1 (Alexei Starovoitov) * always run all progs (Alexei Starovoitov) * use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov) (decided to use optval=-1 instead, optval=0 might be a valid input) * call getsockopt hook after kernel handlers (Alexei Starovoitov) v6: * rework cgroup chaining; stop as soon as bpf program returns 0 or 2; see patch with the documentation for the details * drop Andrii's and Martin's Acked-by (not sure they are comfortable with the new state of things) v5: * skip copy_to_user() and put_user() when ret == 0 (Martin Lau) v4: * don't export bpf_sk_fullsock helper (Martin Lau) * size != sizeof(__u64) for uapi pointers (Martin Lau) * offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau) v3: * typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko) * reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii Nakryiko) * use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau) * use BPF_FIELD_SIZEOF() for consistency (Martin Lau) * new CG_SOCKOPT_ACCESS macro to wrap repeated parts v2: * moved bpf_sockopt_kern fields around to remove a hole (Martin Lau) * aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau) * bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau) * added [0,2] return code check to verifier (Martin Lau) * dropped unused buf[64] from the stack (Martin Lau) * use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau) * dropped bpf_target_off from ctx rewrites (Martin Lau) * use return code for kernel bypass (Martin Lau & Andrii Nakryiko) Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-06-27 23:38:47 +03:00
bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] <asn:4> * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] <asn:4> * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin <guro@fb.com> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-29 00:14:41 +03:00
int bpf_prog_array_copy_to_user(struct bpf_prog_array *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 08:50:21 +03:00
bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] <asn:4> * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] <asn:4> * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin <guro@fb.com> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-29 00:14:41 +03:00
void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index);
int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
struct bpf_prog *prog);
bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] <asn:4> * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] <asn:4> * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin <guro@fb.com> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-29 00:14:41 +03:00
int bpf_prog_array_copy_info(struct bpf_prog_array *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>
2018-04-10 19:37:32 +03:00
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt);
bpf: remove __rcu annotations from bpf_prog_array Drop __rcu annotations and rcu read sections from bpf_prog_array helper functions. They are not needed since all existing callers call those helpers from the rcu update side while holding a mutex. This guarantees that use-after-free could not happen. In the next patches I'll fix the callers with missing rcu_dereference_protected to make sparse/lockdep happy, the proper way to use these helpers is: struct bpf_prog_array __rcu *progs = ...; struct bpf_prog_array *p; mutex_lock(&mtx); p = rcu_dereference_protected(progs, lockdep_is_held(&mtx)); bpf_prog_array_length(p); bpf_prog_array_copy_to_user(p, ...); bpf_prog_array_delete_safe(p, ...); bpf_prog_array_copy_info(p, ...); bpf_prog_array_copy(p, ...); bpf_prog_array_free(p); mutex_unlock(&mtx); No functional changes! rcu_dereference_protected with lockdep_is_held should catch any cases where we update prog array without a mutex (I've looked at existing call sites and I think we hold a mutex everywhere). Motivation is to fix sparse warnings: kernel/bpf/core.c:1803:9: warning: incorrect type in argument 1 (different address spaces) kernel/bpf/core.c:1803:9: expected struct callback_head *head kernel/bpf/core.c:1803:9: got struct callback_head [noderef] <asn:4> * kernel/bpf/core.c:1877:44: warning: incorrect type in initializer (different address spaces) kernel/bpf/core.c:1877:44: expected struct bpf_prog_array_item *item kernel/bpf/core.c:1877:44: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1901:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1901:26: expected struct bpf_prog_array_item *existing kernel/bpf/core.c:1901:26: got struct bpf_prog_array_item [noderef] <asn:4> * kernel/bpf/core.c:1935:26: warning: incorrect type in assignment (different address spaces) kernel/bpf/core.c:1935:26: expected struct bpf_prog_array_item *[assigned] existing kernel/bpf/core.c:1935:26: got struct bpf_prog_array_item [noderef] <asn:4> * v2: * remove comment about potential race; that can't happen because all callers are in rcu-update section Cc: Roman Gushchin <guro@fb.com> Acked-by: Roman Gushchin <guro@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-29 00:14:41 +03:00
int bpf_prog_array_copy(struct bpf_prog_array *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 08:50:21 +03:00
({ \
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 08:50:21 +03:00
u32 _ret = 1; \
migrate_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 08:50:21 +03:00
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 08:50:21 +03:00
rcu_read_unlock(); \
migrate_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 08:50:21 +03:00
_ret; \
})
/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
* so BPF programs can request cwr for TCP packets.
*
* Current cgroup skb programs can only return 0 or 1 (0 to drop the
* packet. This macro changes the behavior so the low order bit
* indicates whether the packet should be dropped (0) or not (1)
* and the next bit is a congestion notification bit. This could be
* used by TCP to call tcp_enter_cwr()
*
* Hence, new allowed return values of CGROUP EGRESS BPF programs are:
* 0: drop packet
* 1: keep packet
* 2: drop packet and cn
* 3: keep packet and cn
*
* This macro then converts it to one of the NET_XMIT or an error
* code that is then interpreted as drop packet (and no cn):
* 0: NET_XMIT_SUCCESS skb should be transmitted
* 1: NET_XMIT_DROP skb should be dropped and cn
* 2: NET_XMIT_CN skb should be transmitted and cn
* 3: -EPERM skb should be dropped
*/
#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \
({ \
struct bpf_prog_array_item *_item; \
struct bpf_prog *_prog; \
struct bpf_prog_array *_array; \
u32 ret; \
u32 _ret = 1; \
u32 _cn = 0; \
migrate_disable(); \
rcu_read_lock(); \
_array = rcu_dereference(array); \
_item = &_array->items[0]; \
while ((_prog = READ_ONCE(_item->prog))) { \
bpf_cgroup_storage_set(_item->cgroup_storage); \
ret = func(_prog, ctx); \
_ret &= (ret & 1); \
_cn |= (ret & 2); \
_item++; \
} \
rcu_read_unlock(); \
migrate_enable(); \
if (_ret) \
_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \
else \
_ret = (_cn ? NET_XMIT_DROP : -EPERM); \
_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 struct mutex bpf_stats_enabled_mutex;
/*
* Block execution of BPF programs attached to instrumentation (perf,
* kprobes, tracepoints) to prevent deadlocks on map operations as any of
* these events can happen inside a region which holds a map bucket lock
* and can deadlock on it.
*
* Use the preemption safe inc/dec variants on RT because migrate disable
* is preemptible on RT and preemption in the middle of the RMW operation
* might lead to inconsistent state. Use the raw variants for non RT
* kernels as migrate_disable() maps to preempt_disable() so the slightly
* more expensive save operation can be avoided.
*/
static inline void bpf_disable_instrumentation(void)
{
migrate_disable();
if (IS_ENABLED(CONFIG_PREEMPT_RT))
this_cpu_inc(bpf_prog_active);
else
__this_cpu_inc(bpf_prog_active);
}
static inline void bpf_enable_instrumentation(void)
{
if (IS_ENABLED(CONFIG_PREEMPT_RT))
this_cpu_dec(bpf_prog_active);
else
__this_cpu_dec(bpf_prog_active);
migrate_enable();
}
extern const struct file_operations bpf_map_fops;
extern const struct file_operations bpf_prog_fops;
extern const struct file_operations bpf_iter_fops;
#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
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;
#define BPF_LINK_TYPE(_id, _name)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
#undef BPF_LINK_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);
void bpf_prog_add(struct bpf_prog *prog, int i);
void bpf_prog_sub(struct bpf_prog *prog, int i);
void 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 03:52:58 +03:00
int __bpf_prog_charge(struct user_struct *user, u32 pages);
void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
void __bpf_free_used_maps(struct bpf_prog_aux *aux,
struct bpf_map **used_maps, u32 len);
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: INET_DIAG support in bpf_sk_storage This patch adds INET_DIAG support to bpf_sk_storage. 1. Although this series adds bpf_sk_storage diag capability to inet sk, bpf_sk_storage is in general applicable to all fullsock. Hence, the bpf_sk_storage logic will operate on SK_DIAG_* nlattr. The caller will pass in its specific nesting nlattr (e.g. INET_DIAG_*) as the argument. 2. The request will be like: INET_DIAG_REQ_SK_BPF_STORAGES (nla_nest) (defined in latter patch) SK_DIAG_BPF_STORAGE_REQ_MAP_FD (nla_put_u32) SK_DIAG_BPF_STORAGE_REQ_MAP_FD (nla_put_u32) ...... Considering there could have multiple bpf_sk_storages in a sk, instead of reusing INET_DIAG_INFO ("ss -i"), the user can select some specific bpf_sk_storage to dump by specifying an array of SK_DIAG_BPF_STORAGE_REQ_MAP_FD. If no SK_DIAG_BPF_STORAGE_REQ_MAP_FD is specified (i.e. an empty INET_DIAG_REQ_SK_BPF_STORAGES), it will dump all bpf_sk_storages of a sk. 3. The reply will be like: INET_DIAG_BPF_SK_STORAGES (nla_nest) (defined in latter patch) SK_DIAG_BPF_STORAGE (nla_nest) SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) SK_DIAG_BPF_STORAGE (nla_nest) SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) ...... 4. Unlike other INET_DIAG info of a sk which is pretty static, the size required to dump the bpf_sk_storage(s) of a sk is dynamic as the system adding more bpf_sk_storage_map. It is hard to set a static min_dump_alloc size. Hence, this series learns it at the runtime and adjust the cb->min_dump_alloc as it iterates all sk(s) of a system. The "unsigned int *res_diag_size" in bpf_sk_storage_diag_put() is for this purpose. The next patch will update the cb->min_dump_alloc as it iterates the sk(s). Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200225230421.1975729-1-kafai@fb.com
2020-02-26 02:04:21 +03:00
struct bpf_map *bpf_map_get(u32 ufd);
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 23:28:15 +03:00
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
bpf: Switch bpf_map ref counter to atomic64_t so bpf_map_inc() never fails 92117d8443bc ("bpf: fix refcnt overflow") turned refcounting of bpf_map into potentially failing operation, when refcount reaches BPF_MAX_REFCNT limit (32k). Due to using 32-bit counter, it's possible in practice to overflow refcounter and make it wrap around to 0, causing erroneous map free, while there are still references to it, causing use-after-free problems. But having a failing refcounting operations are problematic in some cases. One example is mmap() interface. After establishing initial memory-mapping, user is allowed to arbitrarily map/remap/unmap parts of mapped memory, arbitrarily splitting it into multiple non-contiguous regions. All this happening without any control from the users of mmap subsystem. Rather mmap subsystem sends notifications to original creator of memory mapping through open/close callbacks, which are optionally specified during initial memory mapping creation. These callbacks are used to maintain accurate refcount for bpf_map (see next patch in this series). The problem is that open() callback is not supposed to fail, because memory-mapped resource is set up and properly referenced. This is posing a problem for using memory-mapping with BPF maps. One solution to this is to maintain separate refcount for just memory-mappings and do single bpf_map_inc/bpf_map_put when it goes from/to zero, respectively. There are similar use cases in current work on tcp-bpf, necessitating extra counter as well. This seems like a rather unfortunate and ugly solution that doesn't scale well to various new use cases. Another approach to solve this is to use non-failing refcount_t type, which uses 32-bit counter internally, but, once reaching overflow state at UINT_MAX, stays there. This utlimately causes memory leak, but prevents use after free. But given refcounting is not the most performance-critical operation with BPF maps (it's not used from running BPF program code), we can also just switch to 64-bit counter that can't overflow in practice, potentially disadvantaging 32-bit platforms a tiny bit. This simplifies semantics and allows above described scenarios to not worry about failing refcount increment operation. In terms of struct bpf_map size, we are still good and use the same amount of space: BEFORE (3 cache lines, 8 bytes of padding at the end): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 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 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic_t refcnt __attribute__((__aligned__(64))); /* 128 4 */ atomic_t usercnt; /* 132 4 */ struct work_struct work; /* 136 32 */ char name[16]; /* 168 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 146, holes: 1, sum holes: 38 */ /* padding: 8 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); AFTER (same 3 cache lines, no extra padding now): struct bpf_map { const struct bpf_map_ops * ops __attribute__((__aligned__(64))); /* 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 */ int spin_lock_off; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ u32 btf_key_type_id; /* 56 4 */ u32 btf_value_type_id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ struct btf * btf; /* 64 8 */ struct bpf_map_memory memory; /* 72 16 */ bool unpriv_array; /* 88 1 */ bool frozen; /* 89 1 */ /* XXX 38 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ atomic64_t refcnt __attribute__((__aligned__(64))); /* 128 8 */ atomic64_t usercnt; /* 136 8 */ struct work_struct work; /* 144 32 */ char name[16]; /* 176 16 */ /* size: 192, cachelines: 3, members: 21 */ /* sum members: 154, holes: 1, sum holes: 38 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 38 */ } __attribute__((__aligned__(64))); This patch, while modifying all users of bpf_map_inc, also cleans up its interface to match bpf_map_put with separate operations for bpf_map_inc and bpf_map_inc_with_uref (to match bpf_map_put and bpf_map_put_with_uref, respectively). Also, given there are no users of bpf_map_inc_not_zero specifying uref=true, remove uref flag and default to uref=false internally. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191117172806.2195367-2-andriin@fb.com
2019-11-17 20:28:02 +03:00
void bpf_map_inc(struct bpf_map *map);
void bpf_map_inc_with_uref(struct bpf_map *map);
struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map);
bpf: fix clearing on persistent program array maps Currently, when having map file descriptors pointing to program arrays, there's still the issue that we unconditionally flush program array contents via bpf_fd_array_map_clear() in bpf_map_release(). This happens when such a file descriptor is released and is independent of the map's refcount. Having this flush independent of the refcount is for a reason: there can be arbitrary complex dependency chains among tail calls, also circular ones (direct or indirect, nesting limit determined during runtime), and we need to make sure that the map drops all references to eBPF programs it holds, so that the map's refcount can eventually drop to zero and initiate its freeing. Btw, a walk of the whole dependency graph would not be possible for various reasons, one being complexity and another one inconsistency, i.e. new programs can be added to parts of the graph at any time, so there's no guaranteed consistent state for the time of such a walk. Now, the program array pinning itself works, but the issue is that each derived file descriptor on close would nevertheless call unconditionally into bpf_fd_array_map_clear(). Instead, keep track of users and postpone this flush until the last reference to a user is dropped. As this only concerns a subset of references (f.e. a prog array could hold a program that itself has reference on the prog array holding it, etc), we need to track them separately. Short analysis on the refcounting: on map creation time usercnt will be one, so there's no change in behaviour for bpf_map_release(), if unpinned. If we already fail in map_create(), we are immediately freed, and no file descriptor has been made public yet. In bpf_obj_pin_user(), we need to probe for a possible map in bpf_fd_probe_obj() already with a usercnt reference, so before we drop the reference on the fd with fdput(). Therefore, if actual pinning fails, we need to drop that reference again in bpf_any_put(), otherwise we keep holding it. When last reference drops on the inode, the bpf_any_put() in bpf_evict_inode() will take care of dropping the usercnt again. In the bpf_obj_get_user() case, the bpf_any_get() will grab a reference on the usercnt, still at a time when we have the reference on the path. Should we later on fail to grab a new file descriptor, bpf_any_put() will drop it, otherwise we hold it until bpf_map_release() time. Joint work with Alexei. Fixes: b2197755b263 ("bpf: add support for persistent maps/progs") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-11-24 23:28:15 +03:00
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
bpf: rework memlock-based memory accounting for maps In order to unify the existing memlock charging code with the memcg-based memory accounting, which will be added later, let's rework the current scheme. Currently the following design is used: 1) .alloc() callback optionally checks if the allocation will likely succeed using bpf_map_precharge_memlock() 2) .alloc() performs actual allocations 3) .alloc() callback calculates map cost and sets map.memory.pages 4) map_create() calls bpf_map_init_memlock() which sets map.memory.user and performs actual charging; in case of failure the map is destroyed <map is in use> 1) bpf_map_free_deferred() calls bpf_map_release_memlock(), which performs uncharge and releases the user 2) .map_free() callback releases the memory The scheme can be simplified and made more robust: 1) .alloc() calculates map cost and calls bpf_map_charge_init() 2) bpf_map_charge_init() sets map.memory.user and performs actual charge 3) .alloc() performs actual allocations <map is in use> 1) .map_free() callback releases the memory 2) bpf_map_charge_finish() performs uncharge and releases the user The new scheme also allows to reuse bpf_map_charge_init()/finish() functions for memcg-based accounting. Because charges are performed before actual allocations and uncharges after freeing the memory, no bogus memory pressure can be created. In cases when the map structure is not available (e.g. it's not created yet, or is already destroyed), on-stack bpf_map_memory structure is used. The charge can be transferred with the bpf_map_charge_move() function. Signed-off-by: Roman Gushchin <guro@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-05-30 04:03:58 +03:00
void bpf_map_charge_finish(struct bpf_map_memory *mem);
void bpf_map_charge_move(struct bpf_map_memory *dst,
struct bpf_map_memory *src);
void *bpf_map_area_alloc(u64 size, int numa_node);
void *bpf_map_area_mmapable_alloc(u64 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: Add generic support for lookup batch op This commit introduces generic support for the bpf_map_lookup_batch. This implementation can be used by almost all the bpf maps since its core implementation is relying on the existing map_get_next_key and map_lookup_elem. The bpf syscall subcommand introduced is: BPF_MAP_LOOKUP_BATCH The UAPI attribute is: struct { /* struct used by BPF_MAP_*_BATCH commands */ __aligned_u64 in_batch; /* start batch, * NULL to start from beginning */ __aligned_u64 out_batch; /* output: next start batch */ __aligned_u64 keys; __aligned_u64 values; __u32 count; /* input/output: * input: # of key/value * elements * output: # of filled elements */ __u32 map_fd; __u64 elem_flags; __u64 flags; } batch; in_batch/out_batch are opaque values use to communicate between user/kernel space, in_batch/out_batch must be of key_size length. To start iterating from the beginning in_batch must be null, count is the # of key/value elements to retrieve. Note that the 'keys' buffer must be a buffer of key_size * count size and the 'values' buffer must be value_size * count, where value_size must be aligned to 8 bytes by userspace if it's dealing with percpu maps. 'count' will contain the number of keys/values successfully retrieved. Note that 'count' is an input/output variable and it can contain a lower value after a call. If there's no more entries to retrieve, ENOENT will be returned. If error is ENOENT, count might be > 0 in case it copied some values but there were no more entries to retrieve. Note that if the return code is an error and not -EFAULT, count indicates the number of elements successfully processed. Suggested-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com
2020-01-15 21:43:01 +03:00
int generic_map_lookup_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_update_batch(struct bpf_map *map,
const union bpf_attr *attr,
union bpf_attr __user *uattr);
int generic_map_delete_batch(struct bpf_map *map,
const union bpf_attr *attr,
bpf: Add generic support for lookup batch op This commit introduces generic support for the bpf_map_lookup_batch. This implementation can be used by almost all the bpf maps since its core implementation is relying on the existing map_get_next_key and map_lookup_elem. The bpf syscall subcommand introduced is: BPF_MAP_LOOKUP_BATCH The UAPI attribute is: struct { /* struct used by BPF_MAP_*_BATCH commands */ __aligned_u64 in_batch; /* start batch, * NULL to start from beginning */ __aligned_u64 out_batch; /* output: next start batch */ __aligned_u64 keys; __aligned_u64 values; __u32 count; /* input/output: * input: # of key/value * elements * output: # of filled elements */ __u32 map_fd; __u64 elem_flags; __u64 flags; } batch; in_batch/out_batch are opaque values use to communicate between user/kernel space, in_batch/out_batch must be of key_size length. To start iterating from the beginning in_batch must be null, count is the # of key/value elements to retrieve. Note that the 'keys' buffer must be a buffer of key_size * count size and the 'values' buffer must be value_size * count, where value_size must be aligned to 8 bytes by userspace if it's dealing with percpu maps. 'count' will contain the number of keys/values successfully retrieved. Note that 'count' is an input/output variable and it can contain a lower value after a call. If there's no more entries to retrieve, ENOENT will be returned. If error is ENOENT, count might be > 0 in case it copied some values but there were no more entries to retrieve. Note that if the return code is an error and not -EFAULT, count indicates the number of elements successfully processed. Suggested-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Brian Vazquez <brianvv@google.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com
2020-01-15 21:43:01 +03:00
union bpf_attr __user *uattr);
struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
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 08:23:21 +03:00
extern int sysctl_unprivileged_bpf_disabled;
static inline bool bpf_allow_ptr_leaks(void)
{
return perfmon_capable();
}
bpf: Support access to bpf map fields There are multiple use-cases when it's convenient to have access to bpf map fields, both `struct bpf_map` and map type specific struct-s such as `struct bpf_array`, `struct bpf_htab`, etc. For example while working with sock arrays it can be necessary to calculate the key based on map->max_entries (some_hash % max_entries). Currently this is solved by communicating max_entries via "out-of-band" channel, e.g. via additional map with known key to get info about target map. That works, but is not very convenient and error-prone while working with many maps. In other cases necessary data is dynamic (i.e. unknown at loading time) and it's impossible to get it at all. For example while working with a hash table it can be convenient to know how much capacity is already used (bpf_htab.count.counter for BPF_F_NO_PREALLOC case). At the same time kernel knows this info and can provide it to bpf program. Fill this gap by adding support to access bpf map fields from bpf program for both `struct bpf_map` and map type specific fields. Support is implemented via btf_struct_access() so that a user can define their own `struct bpf_map` or map type specific struct in their program with only necessary fields and preserve_access_index attribute, cast a map to this struct and use a field. For example: struct bpf_map { __u32 max_entries; } __attribute__((preserve_access_index)); struct bpf_array { struct bpf_map map; __u32 elem_size; } __attribute__((preserve_access_index)); struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 4); __type(key, __u32); __type(value, __u32); } m_array SEC(".maps"); SEC("cgroup_skb/egress") int cg_skb(void *ctx) { struct bpf_array *array = (struct bpf_array *)&m_array; struct bpf_map *map = (struct bpf_map *)&m_array; /* .. use map->max_entries or array->map.max_entries .. */ } Similarly to other btf_struct_access() use-cases (e.g. struct tcp_sock in net/ipv4/bpf_tcp_ca.c) the patch allows access to any fields of corresponding struct. Only reading from map fields is supported. For btf_struct_access() to work there should be a way to know btf id of a struct that corresponds to a map type. To get btf id there should be a way to get a stringified name of map-specific struct, such as "bpf_array", "bpf_htab", etc for a map type. Two new fields are added to `struct bpf_map_ops` to handle it: * .map_btf_name keeps a btf name of a struct returned by map_alloc(); * .map_btf_id is used to cache btf id of that struct. To make btf ids calculation cheaper they're calculated once while preparing btf_vmlinux and cached same way as it's done for btf_id field of `struct bpf_func_proto` While calculating btf ids, struct names are NOT checked for collision. Collisions will be checked as a part of the work to prepare btf ids used in verifier in compile time that should land soon. The only known collision for `struct bpf_htab` (kernel/bpf/hashtab.c vs net/core/sock_map.c) was fixed earlier. Both new fields .map_btf_name and .map_btf_id must be set for a map type for the feature to work. If neither is set for a map type, verifier will return ENOTSUPP on a try to access map_ptr of corresponding type. If just one of them set, it's verifier misconfiguration. Only `struct bpf_array` for BPF_MAP_TYPE_ARRAY and `struct bpf_htab` for BPF_MAP_TYPE_HASH are supported by this patch. Other map types will be supported separately. The feature is available only for CONFIG_DEBUG_INFO_BTF=y and gated by perfmon_capable() so that unpriv programs won't have access to bpf map fields. Signed-off-by: Andrey Ignatov <rdna@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/6479686a0cd1e9067993df57b4c3eef0e276fec9.1592600985.git.rdna@fb.com
2020-06-20 00:11:43 +03:00
static inline bool bpf_allow_ptr_to_map_access(void)
{
return perfmon_capable();
}
static inline bool bpf_bypass_spec_v1(void)
{
return perfmon_capable();
}
static inline bool bpf_bypass_spec_v4(void)
{
return perfmon_capable();
}
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 16:58:09 +03:00
int bpf_prog_new_fd(struct bpf_prog *prog);
void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
const struct bpf_link_ops *ops, struct bpf_prog *prog);
int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
int bpf_link_settle(struct bpf_link_primer *primer);
void bpf_link_cleanup(struct bpf_link_primer *primer);
void bpf_link_inc(struct bpf_link *link);
void bpf_link_put(struct bpf_link *link);
int bpf_link_new_fd(struct bpf_link *link);
bpf: Add bpf_link_new_file that doesn't install FD Add bpf_link_new_file() API for cases when we need to ensure anon_inode is successfully created before we proceed with expensive BPF program attachment procedure, which will require equally (if not more so) expensive and potentially failing compensation detachment procedure just because anon_inode creation failed. This API allows to simplify code by ensuring first that anon_inode is created and after BPF program is attached proceed with fd_install() that can't fail. After anon_inode file is created, link can't be just kfree()'d anymore, because its destruction will be performed by deferred file_operations->release call. For this, bpf_link API required specifying two separate operations: release() and dealloc(), former performing detachment only, while the latter frees memory used by bpf_link itself. dealloc() needs to be specified, because struct bpf_link is frequently embedded into link type-specific container struct (e.g., struct bpf_raw_tp_link), so bpf_link itself doesn't know how to properly free the memory. In case when anon_inode file was successfully created, but subsequent BPF attachment failed, bpf_link needs to be marked as "defunct", so that file's release() callback will perform only memory deallocation, but no detachment. Convert raw tracepoint and tracing attachment to new API and eliminate detachment from error handling path. Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200309231051.1270337-1-andriin@fb.com
2020-03-10 02:10:51 +03:00
struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
struct bpf_link *bpf_link_get_from_fd(u32 ufd);
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 16:58:09 +03:00
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 16:58:09 +03:00
#define BPF_ITER_FUNC_PREFIX "bpf_iter_"
#define DEFINE_BPF_ITER_FUNC(target, args...) \
extern int bpf_iter_ ## target(args); \
int __init bpf_iter_ ## target(args) { return 0; }
struct bpf_iter_aux_info {
bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com
2020-07-23 21:41:12 +03:00
struct bpf_map *map;
};
bpf: Change uapi for bpf iterator map elements Commit a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") added bpf iterator support for map elements. The map element bpf iterator requires info to identify a particular map. In the above commit, the attr->link_create.target_fd is used to carry map_fd and an enum bpf_iter_link_info is added to uapi to specify the target_fd actually representing a map_fd: enum bpf_iter_link_info { BPF_ITER_LINK_UNSPEC = 0, BPF_ITER_LINK_MAP_FD = 1, MAX_BPF_ITER_LINK_INFO, }; This is an extensible approach as we can grow enumerator for pid, cgroup_id, etc. and we can unionize target_fd for pid, cgroup_id, etc. But in the future, there are chances that more complex customization may happen, e.g., for tasks, it could be filtered based on both cgroup_id and user_id. This patch changed the uapi to have fields __aligned_u64 iter_info; __u32 iter_info_len; for additional iter_info for link_create. The iter_info is defined as union bpf_iter_link_info { struct { __u32 map_fd; } map; }; So future extension for additional customization will be easier. The bpf_iter_link_info will be passed to target callback to validate and generic bpf_iter framework does not need to deal it any more. Note that map_fd = 0 will be considered invalid and -EBADF will be returned to user space. Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com
2020-08-05 08:50:56 +03:00
typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux);
typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux,
struct seq_file *seq);
typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com
2020-07-23 21:41:12 +03:00
bpf: Permit cond_resched for some iterators Commit e679654a704e ("bpf: Fix a rcu_sched stall issue with bpf task/task_file iterator") tries to fix rcu stalls warning which is caused by bpf task_file iterator when running "bpftool prog". rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913 \x09(t=21031 jiffies g=2534773 q=179750) NMI backtrace for cpu 7 CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G W 5.8.0-00004-g68bfc7f8c1b4 #6 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019 Call Trace: <IRQ> dump_stack+0x57/0x70 nmi_cpu_backtrace.cold+0x14/0x53 ? lapic_can_unplug_cpu.cold+0x39/0x39 nmi_trigger_cpumask_backtrace+0xb7/0xc7 rcu_dump_cpu_stacks+0xa2/0xd0 rcu_sched_clock_irq.cold+0x1ff/0x3d9 ? tick_nohz_handler+0x100/0x100 update_process_times+0x5b/0x90 tick_sched_timer+0x5e/0xf0 __hrtimer_run_queues+0x12a/0x2a0 hrtimer_interrupt+0x10e/0x280 __sysvec_apic_timer_interrupt+0x51/0xe0 asm_call_on_stack+0xf/0x20 </IRQ> sysvec_apic_timer_interrupt+0x6f/0x80 ... task_file_seq_next+0x52/0xa0 bpf_seq_read+0xb9/0x320 vfs_read+0x9d/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x38/0x60 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The fix is to limit the number of bpf program runs to be one million. This fixed the program in most cases. But we also found under heavy load, which can increase the wallclock time for bpf_seq_read(), the warning may still be possible. For example, calling bpf_delay() in the "while" loop of bpf_seq_read(), which will introduce artificial delay, the warning will show up in my qemu run. static unsigned q; volatile unsigned *p = &q; volatile unsigned long long ll; static void bpf_delay(void) { int i, j; for (i = 0; i < 10000; i++) for (j = 0; j < 10000; j++) ll += *p; } There are two ways to fix this issue. One is to reduce the above one million threshold to say 100,000 and hopefully rcu warning will not show up any more. Another is to introduce a target feature which enables bpf_seq_read() calling cond_resched(). This patch took second approach as the first approach may cause more -EAGAIN failures for read() syscalls. Note that not all bpf_iter targets can permit cond_resched() in bpf_seq_read() as some, e.g., netlink seq iterator, rcu read lock critical section spans through seq_ops->next() -> seq_ops->show() -> seq_ops->next(). For the kernel code with the above hack, "bpftool p" roughly takes 38 seconds to finish on my VM with 184 bpf program runs. Using the following command, I am able to collect the number of context switches: perf stat -e context-switches -- ./bpftool p >& log Without this patch, 69 context-switches With this patch, 75 context-switches This patch added additional 6 context switches, roughly every 6 seconds to reschedule, to avoid lengthy no-rescheduling which may cause the above RCU warnings. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
2020-10-28 09:10:54 +03:00
enum bpf_iter_feature {
BPF_ITER_RESCHED = BIT(0),
};
#define BPF_ITER_CTX_ARG_MAX 2
struct bpf_iter_reg {
const char *target;
bpf: Change uapi for bpf iterator map elements Commit a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") added bpf iterator support for map elements. The map element bpf iterator requires info to identify a particular map. In the above commit, the attr->link_create.target_fd is used to carry map_fd and an enum bpf_iter_link_info is added to uapi to specify the target_fd actually representing a map_fd: enum bpf_iter_link_info { BPF_ITER_LINK_UNSPEC = 0, BPF_ITER_LINK_MAP_FD = 1, MAX_BPF_ITER_LINK_INFO, }; This is an extensible approach as we can grow enumerator for pid, cgroup_id, etc. and we can unionize target_fd for pid, cgroup_id, etc. But in the future, there are chances that more complex customization may happen, e.g., for tasks, it could be filtered based on both cgroup_id and user_id. This patch changed the uapi to have fields __aligned_u64 iter_info; __u32 iter_info_len; for additional iter_info for link_create. The iter_info is defined as union bpf_iter_link_info { struct { __u32 map_fd; } map; }; So future extension for additional customization will be easier. The bpf_iter_link_info will be passed to target callback to validate and generic bpf_iter framework does not need to deal it any more. Note that map_fd = 0 will be considered invalid and -EBADF will be returned to user space. Fixes: a5cbe05a6673 ("bpf: Implement bpf iterator for map elements") Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20200805055056.1457463-1-yhs@fb.com
2020-08-05 08:50:56 +03:00
bpf_iter_attach_target_t attach_target;
bpf_iter_detach_target_t detach_target;
bpf_iter_show_fdinfo_t show_fdinfo;
bpf_iter_fill_link_info_t fill_link_info;
u32 ctx_arg_info_size;
bpf: Permit cond_resched for some iterators Commit e679654a704e ("bpf: Fix a rcu_sched stall issue with bpf task/task_file iterator") tries to fix rcu stalls warning which is caused by bpf task_file iterator when running "bpftool prog". rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913 \x09(t=21031 jiffies g=2534773 q=179750) NMI backtrace for cpu 7 CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G W 5.8.0-00004-g68bfc7f8c1b4 #6 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019 Call Trace: <IRQ> dump_stack+0x57/0x70 nmi_cpu_backtrace.cold+0x14/0x53 ? lapic_can_unplug_cpu.cold+0x39/0x39 nmi_trigger_cpumask_backtrace+0xb7/0xc7 rcu_dump_cpu_stacks+0xa2/0xd0 rcu_sched_clock_irq.cold+0x1ff/0x3d9 ? tick_nohz_handler+0x100/0x100 update_process_times+0x5b/0x90 tick_sched_timer+0x5e/0xf0 __hrtimer_run_queues+0x12a/0x2a0 hrtimer_interrupt+0x10e/0x280 __sysvec_apic_timer_interrupt+0x51/0xe0 asm_call_on_stack+0xf/0x20 </IRQ> sysvec_apic_timer_interrupt+0x6f/0x80 ... task_file_seq_next+0x52/0xa0 bpf_seq_read+0xb9/0x320 vfs_read+0x9d/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x38/0x60 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The fix is to limit the number of bpf program runs to be one million. This fixed the program in most cases. But we also found under heavy load, which can increase the wallclock time for bpf_seq_read(), the warning may still be possible. For example, calling bpf_delay() in the "while" loop of bpf_seq_read(), which will introduce artificial delay, the warning will show up in my qemu run. static unsigned q; volatile unsigned *p = &q; volatile unsigned long long ll; static void bpf_delay(void) { int i, j; for (i = 0; i < 10000; i++) for (j = 0; j < 10000; j++) ll += *p; } There are two ways to fix this issue. One is to reduce the above one million threshold to say 100,000 and hopefully rcu warning will not show up any more. Another is to introduce a target feature which enables bpf_seq_read() calling cond_resched(). This patch took second approach as the first approach may cause more -EAGAIN failures for read() syscalls. Note that not all bpf_iter targets can permit cond_resched() in bpf_seq_read() as some, e.g., netlink seq iterator, rcu read lock critical section spans through seq_ops->next() -> seq_ops->show() -> seq_ops->next(). For the kernel code with the above hack, "bpftool p" roughly takes 38 seconds to finish on my VM with 184 bpf program runs. Using the following command, I am able to collect the number of context switches: perf stat -e context-switches -- ./bpftool p >& log Without this patch, 69 context-switches With this patch, 75 context-switches This patch added additional 6 context switches, roughly every 6 seconds to reschedule, to avoid lengthy no-rescheduling which may cause the above RCU warnings. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
2020-10-28 09:10:54 +03:00
u32 feature;
struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX];
const struct bpf_iter_seq_info *seq_info;
};
struct bpf_iter_meta {
__bpf_md_ptr(struct seq_file *, seq);
u64 session_id;
u64 seq_num;
};
bpf: Implement bpf iterator for map elements The bpf iterator for map elements are implemented. The bpf program will receive four parameters: bpf_iter_meta *meta: the meta data bpf_map *map: the bpf_map whose elements are traversed void *key: the key of one element void *value: the value of the same element Here, meta and map pointers are always valid, and key has register type PTR_TO_RDONLY_BUF_OR_NULL and value has register type PTR_TO_RDWR_BUF_OR_NULL. The kernel will track the access range of key and value during verification time. Later, these values will be compared against the values in the actual map to ensure all accesses are within range. A new field iter_seq_info is added to bpf_map_ops which is used to add map type specific information, i.e., seq_ops, init/fini seq_file func and seq_file private data size. Subsequent patches will have actual implementation for bpf_map_ops->iter_seq_info. In user space, BPF_ITER_LINK_MAP_FD needs to be specified in prog attr->link_create.flags, which indicates that attr->link_create.target_fd is a map_fd. The reason for such an explicit flag is for possible future cases where one bpf iterator may allow more than one possible customization, e.g., pid and cgroup id for task_file. Current kernel internal implementation only allows the target to register at most one required bpf_iter_link_info. To support the above case, optional bpf_iter_link_info's are needed, the target can be extended to register such link infos, and user provided link_info needs to match one of target supported ones. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184112.590360-1-yhs@fb.com
2020-07-23 21:41:12 +03:00
struct bpf_iter__bpf_map_elem {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct bpf_map *, map);
__bpf_md_ptr(void *, key);
__bpf_md_ptr(void *, value);
};
int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
bool bpf_iter_prog_supported(struct bpf_prog *prog);
int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
int bpf_iter_new_fd(struct bpf_link *link);
bool bpf_link_is_iter(struct bpf_link *link);
struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop);
int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux,
struct seq_file *seq);
int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux,
struct bpf_link_info *info);
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 08:57:17 +03:00
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 02:29:11 +03:00
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);
struct btf *bpf_get_btf_vmlinux(void);
/* Map specifics */
struct xdp_buff;
struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 18:14:45 +03:00
void __dev_flush(void);
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx);
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);
bool dev_map_can_have_prog(struct bpf_map *map);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_flush(void);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx);
bool cpu_map_prog_allowed(struct bpf_map *map);
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-18 21:28:00 +03:00
/* 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 11:01:24 +03:00
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_tracing(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);
int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
2019-10-16 06:25:00 +03:00
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
int btf_struct_access(struct bpf_verifier_log *log,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
bool btf_struct_ids_match(struct bpf_verifier_log *log,
int off, u32 id, u32 need_type_id);
bpf: Implement accurate raw_tp context access via BTF libbpf analyzes bpf C program, searches in-kernel BTF for given type name and stores it into expected_attach_type. The kernel verifier expects this btf_id to point to something like: typedef void (*btf_trace_kfree_skb)(void *, struct sk_buff *skb, void *loc); which represents signature of raw_tracepoint "kfree_skb". Then btf_ctx_access() matches ctx+0 access in bpf program with 'skb' and 'ctx+8' access with 'loc' arguments of "kfree_skb" tracepoint. In first case it passes btf_id of 'struct sk_buff *' back to the verifier core and 'void *' in second case. Then the verifier tracks PTR_TO_BTF_ID as any other pointer type. Like PTR_TO_SOCKET points to 'struct bpf_sock', PTR_TO_TCP_SOCK points to 'struct bpf_tcp_sock', and so on. PTR_TO_BTF_ID points to in-kernel structs. If 1234 is btf_id of 'struct sk_buff' in vmlinux's BTF then PTR_TO_BTF_ID#1234 points to one of in kernel skbs. When PTR_TO_BTF_ID#1234 is dereferenced (like r2 = *(u64 *)r1 + 32) the btf_struct_access() checks which field of 'struct sk_buff' is at offset 32. Checks that size of access matches type definition of the field and continues to track the dereferenced type. If that field was a pointer to 'struct net_device' the r2's type will be PTR_TO_BTF_ID#456. Where 456 is btf_id of 'struct net_device' in vmlinux's BTF. Such verifier analysis prevents "cheating" in BPF C program. The program cannot cast arbitrary pointer to 'struct sk_buff *' and access it. C compiler would allow type cast, of course, but the verifier will notice type mismatch based on BPF assembly and in-kernel BTF. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-7-ast@kernel.org
2019-10-16 06:25:00 +03:00
bpf: Introduce BPF trampoline Introduce BPF trampoline concept to allow kernel code to call into BPF programs with practically zero overhead. The trampoline generation logic is architecture dependent. It's converting native calling convention into BPF calling convention. BPF ISA is 64-bit (even on 32-bit architectures). The registers R1 to R5 are used to pass arguments into BPF functions. The main BPF program accepts only single argument "ctx" in R1. Whereas CPU native calling convention is different. x86-64 is passing first 6 arguments in registers and the rest on the stack. x86-32 is passing first 3 arguments in registers. sparc64 is passing first 6 in registers. And so on. The trampolines between BPF and kernel already exist. BPF_CALL_x macros in include/linux/filter.h statically compile trampolines from BPF into kernel helpers. They convert up to five u64 arguments into kernel C pointers and integers. On 64-bit architectures this BPF_to_kernel trampolines are nops. On 32-bit architecture they're meaningful. The opposite job kernel_to_BPF trampolines is done by CAST_TO_U64 macros and __bpf_trace_##call() shim functions in include/trace/bpf_probe.h. They convert kernel function arguments into array of u64s that BPF program consumes via R1=ctx pointer. This patch set is doing the same job as __bpf_trace_##call() static trampolines, but dynamically for any kernel function. There are ~22k global kernel functions that are attachable via nop at function entry. The function arguments and types are described in BTF. The job of btf_distill_func_proto() function is to extract useful information from BTF into "function model" that architecture dependent trampoline generators will use to generate assembly code to cast kernel function arguments into array of u64s. For example the kernel function eth_type_trans has two pointers. They will be casted to u64 and stored into stack of generated trampoline. The pointer to that stack space will be passed into BPF program in R1. On x86-64 such generated trampoline will consume 16 bytes of stack and two stores of %rdi and %rsi into stack. The verifier will make sure that only two u64 are accessed read-only by BPF program. The verifier will also recognize the precise type of the pointers being accessed and will not allow typecasting of the pointer to a different type within BPF program. The tracing use case in the datacenter demonstrated that certain key kernel functions have (like tcp_retransmit_skb) have 2 or more kprobes that are always active. Other functions have both kprobe and kretprobe. So it is essential to keep both kernel code and BPF programs executing at maximum speed. Hence generated BPF trampoline is re-generated every time new program is attached or detached to maintain maximum performance. To avoid the high cost of retpoline the attached BPF programs are called directly. __bpf_prog_enter/exit() are used to support per-program execution stats. In the future this logic will be optimized further by adding support for bpf_stats_enabled_key inside generated assembly code. Introduction of preemptible and sleepable BPF programs will completely remove the need to call to __bpf_prog_enter/exit(). Detach of a BPF program from the trampoline should not fail. To avoid memory allocation in detach path the half of the page is used as a reserve and flipped after each attach/detach. 2k bytes is enough to call 40+ BPF programs directly which is enough for BPF tracing use cases. This limit can be increased in the future. BPF_TRACE_FENTRY programs have access to raw kernel function arguments while BPF_TRACE_FEXIT programs have access to kernel return value as well. Often kprobe BPF program remembers function arguments in a map while kretprobe fetches arguments from a map and analyzes them together with return value. BPF_TRACE_FEXIT accelerates this typical use case. Recursion prevention for kprobe BPF programs is done via per-cpu bpf_prog_active counter. In practice that turned out to be a mistake. It caused programs to randomly skip execution. The tracing tools missed results they were looking for. Hence BPF trampoline doesn't provide builtin recursion prevention. It's a job of BPF program itself and will be addressed in the follow up patches. BPF trampoline is intended to be used beyond tracing and fentry/fexit use cases in the future. For example to remove retpoline cost from XDP programs. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20191114185720.1641606-5-ast@kernel.org
2019-11-14 21:57:04 +03:00
int btf_distill_func_proto(struct bpf_verifier_log *log,
struct btf *btf,
const struct btf_type *func_proto,
const char *func_name,
struct btf_func_model *m);
bpf: Introduce function-by-function verification New llvm and old llvm with libbpf help produce BTF that distinguish global and static functions. Unlike arguments of static function the arguments of global functions cannot be removed or optimized away by llvm. The compiler has to use exactly the arguments specified in a function prototype. The argument type information allows the verifier validate each global function independently. For now only supported argument types are pointer to context and scalars. In the future pointers to structures, sizes, pointer to packet data can be supported as well. Consider the following example: static int f1(int ...) { ... } int f3(int b); int f2(int a) { f1(a) + f3(a); } int f3(int b) { ... } int main(...) { f1(...) + f2(...) + f3(...); } The verifier will start its safety checks from the first global function f2(). It will recursively descend into f1() because it's static. Then it will check that arguments match for the f3() invocation inside f2(). It will not descend into f3(). It will finish f2() that has to be successfully verified for all possible values of 'a'. Then it will proceed with f3(). That function also has to be safe for all possible values of 'b'. Then it will start subprog 0 (which is main() function). It will recursively descend into f1() and will skip full check of f2() and f3(), since they are global. The order of processing global functions doesn't affect safety, since all global functions must be proven safe based on their arguments only. Such function by function verification can drastically improve speed of the verification and reduce complexity. Note that the stack limit of 512 still applies to the call chain regardless whether functions were static or global. The nested level of 8 also still applies. The same recursion prevention checks are in place as well. The type information and static/global kind is preserved after the verification hence in the above example global function f2() and f3() can be replaced later by equivalent functions with the same types that are loaded and verified later without affecting safety of this main() program. Such replacement (re-linking) of global functions is a subject of future patches. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Song Liu <songliubraving@fb.com> Link: https://lore.kernel.org/bpf/20200110064124.1760511-3-ast@kernel.org
2020-01-10 09:41:20 +03:00
struct bpf_reg_state;
int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *regs);
int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
struct bpf_reg_state *reg);
int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
bpf: Introduce dynamic program extensions Introduce dynamic program extensions. The users can load additional BPF functions and replace global functions in previously loaded BPF programs while these programs are executing. Global functions are verified individually by the verifier based on their types only. Hence the global function in the new program which types match older function can safely replace that corresponding function. This new function/program is called 'an extension' of old program. At load time the verifier uses (attach_prog_fd, attach_btf_id) pair to identify the function to be replaced. The BPF program type is derived from the target program into extension program. Technically bpf_verifier_ops is copied from target program. The BPF_PROG_TYPE_EXT program type is a placeholder. It has empty verifier_ops. The extension program can call the same bpf helper functions as target program. Single BPF_PROG_TYPE_EXT type is used to extend XDP, SKB and all other program types. The verifier allows only one level of replacement. Meaning that the extension program cannot recursively extend an extension. That also means that the maximum stack size is increasing from 512 to 1024 bytes and maximum function nesting level from 8 to 16. The programs don't always consume that much. The stack usage is determined by the number of on-stack variables used by the program. The verifier could have enforced 512 limit for combined original plus extension program, but it makes for difficult user experience. The main use case for extensions is to provide generic mechanism to plug external programs into policy program or function call chaining. BPF trampoline is used to track both fentry/fexit and program extensions because both are using the same nop slot at the beginning of every BPF function. Attaching fentry/fexit to a function that was replaced is not allowed. The opposite is true as well. Replacing a function that currently being analyzed with fentry/fexit is not allowed. The executable page allocated by BPF trampoline is not used by program extensions. This inefficiency will be optimized in future patches. Function by function verification of global function supports scalars and pointer to context only. Hence program extensions are supported for such class of global functions only. In the future the verifier will be extended with support to pointers to structures, arrays with sizes, etc. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20200121005348.2769920-2-ast@kernel.org
2020-01-21 03:53:46 +03:00
struct btf *btf, const struct btf_type *t);
struct bpf_prog *bpf_prog_by_id(u32 id);
struct bpf_link *bpf_link_by_id(u32 id);
const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
#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 void bpf_prog_add(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
static inline void bpf_prog_inc(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 03:52:58 +03:00
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 03:52:58 +03:00
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 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
const struct bpf_link_ops *ops,
struct bpf_prog *prog)
{
}
static inline int bpf_link_prime(struct bpf_link *link,
struct bpf_link_primer *primer)
{
return -EOPNOTSUPP;
}
static inline int bpf_link_settle(struct bpf_link_primer *primer)
{
return -EOPNOTSUPP;
}
static inline void bpf_link_cleanup(struct bpf_link_primer *primer)
{
}
static inline void bpf_link_inc(struct bpf_link *link)
{
}
static inline void bpf_link_put(struct bpf_link *link)
{
}
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 15:27:15 +03:00
{
return -EOPNOTSUPP;
}
static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline bool dev_map_can_have_prog(struct bpf_map *map)
{
return false;
}
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 18:14:45 +03:00
static inline void __dev_flush(void)
{
}
struct xdp_buff;
struct bpf_dtab_netdev;
xdp: Use bulking for non-map XDP_REDIRECT and consolidate code paths Since the bulk queue used by XDP_REDIRECT now lives in struct net_device, we can re-use the bulking for the non-map version of the bpf_redirect() helper. This is a simple matter of having xdp_do_redirect_slow() queue the frame on the bulk queue instead of sending it out with __bpf_tx_xdp(). Unfortunately we can't make the bpf_redirect() helper return an error if the ifindex doesn't exit (as bpf_redirect_map() does), because we don't have a reference to the network namespace of the ingress device at the time the helper is called. So we have to leave it as-is and keep the device lookup in xdp_do_redirect_slow(). Since this leaves less reason to have the non-map redirect code in a separate function, so we get rid of the xdp_do_redirect_slow() function entirely. This does lose us the tracepoint disambiguation, but fortunately the xdp_redirect and xdp_redirect_map tracepoints use the same tracepoint entry structures. This means both can contain a map index, so we can just amend the tracepoint definitions so we always emit the xdp_redirect(_err) tracepoints, but with the map ID only populated if a map is present. This means we retire the xdp_redirect_map(_err) tracepoints entirely, but keep the definitions around in case someone is still listening for them. With this change, the performance of the xdp_redirect sample program goes from 5Mpps to 8.4Mpps (a 68% increase). Since the flush functions are no longer map-specific, rename the flush() functions to drop _map from their names. One of the renamed functions is the xdp_do_flush_map() callback used in all the xdp-enabled drivers. To keep from having to update all drivers, use a #define to keep the old name working, and only update the virtual drivers in this patch. Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/157918768505.1458396.17518057312953572912.stgit@toke.dk
2020-01-16 18:14:45 +03:00
static inline
int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
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_flush(void)
{
}
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 bool cpu_map_prog_allowed(struct bpf_map *map)
{
return false;
}
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_tracing(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;
}
static inline void bpf_map_put(struct bpf_map *map)
{
}
static inline struct bpf_prog *bpf_prog_by_id(u32 id)
{
return ERR_PTR(-ENOTSUPP);
}
static inline const struct bpf_func_proto *
bpf_base_func_proto(enum bpf_func_id func_id)
{
return NULL;
}
#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 03:45:58 +03:00
#if defined(CONFIG_BPF_STREAM_PARSER)
int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
struct bpf_prog *old, u32 which);
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 03:45:58 +03:00
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
void sock_map_unhash(struct sock *sk);
void sock_map_close(struct sock *sk, long timeout);
#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 03:45:58 +03:00
static inline int sock_map_prog_update(struct bpf_map *map,
struct bpf_prog *prog,
struct bpf_prog *old, 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 03:45:58 +03:00
static inline int sock_map_get_from_fd(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
static inline int sock_map_prog_detach(const union bpf_attr *attr,
enum bpf_prog_type ptype)
{
return -EOPNOTSUPP;
}
static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
u64 flags)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_BPF_STREAM_PARSER */
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 11:01:24 +03:00
#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 02:59:03 +03:00
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_ktime_get_boot_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;
extern const struct bpf_func_proto bpf_get_task_stack_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
extern const struct bpf_func_proto bpf_get_stack_proto_pe;
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 08:32:47 +03:00
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;
extern const struct bpf_func_proto bpf_get_current_ancestor_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 03:45:58 +03:00
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 02:40:04 +03:00
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 03:55:26 +03:00
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
bpf: implement getsockopt and setsockopt hooks Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks. BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before passing them down to the kernel or bypass kernel completely. BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that kernel returns. Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure. The buffer memory is pre-allocated (because I don't think there is a precedent for working with __user memory from bpf). This might be slow to do for each {s,g}etsockopt call, that's why I've added __cgroup_bpf_prog_array_is_empty that exits early if there is nothing attached to a cgroup. Note, however, that there is a race between __cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup program layout might have changed; this should not be a problem because in general there is a race between multiple calls to {s,g}etsocktop and user adding/removing bpf progs from a cgroup. The return code of the BPF program is handled as follows: * 0: EPERM * 1: success, continue with next BPF program in the cgroup chain v9: * allow overwriting setsockopt arguments (Alexei Starovoitov): * use set_fs (same as kernel_setsockopt) * buffer is always kzalloc'd (no small on-stack buffer) v8: * use s32 for optlen (Andrii Nakryiko) v7: * return only 0 or 1 (Alexei Starovoitov) * always run all progs (Alexei Starovoitov) * use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov) (decided to use optval=-1 instead, optval=0 might be a valid input) * call getsockopt hook after kernel handlers (Alexei Starovoitov) v6: * rework cgroup chaining; stop as soon as bpf program returns 0 or 2; see patch with the documentation for the details * drop Andrii's and Martin's Acked-by (not sure they are comfortable with the new state of things) v5: * skip copy_to_user() and put_user() when ret == 0 (Martin Lau) v4: * don't export bpf_sk_fullsock helper (Martin Lau) * size != sizeof(__u64) for uapi pointers (Martin Lau) * offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau) v3: * typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko) * reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii Nakryiko) * use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau) * use BPF_FIELD_SIZEOF() for consistency (Martin Lau) * new CG_SOCKOPT_ACCESS macro to wrap repeated parts v2: * moved bpf_sockopt_kern fields around to remove a hole (Martin Lau) * aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau) * bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau) * added [0,2] return code check to verifier (Martin Lau) * dropped unused buf[64] from the stack (Martin Lau) * use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau) * dropped bpf_target_off from ctx rewrites (Martin Lau) * use return code for kernel bypass (Martin Lau & Andrii Nakryiko) Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-06-27 23:38:47 +03:00
extern const struct bpf_func_proto bpf_tcp_sock_proto;
extern const struct bpf_func_proto bpf_jiffies64_proto;
extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_event_output_data_proto;
bpf: Implement BPF ring buffer and verifier support for it This commit adds a new MPSC ring buffer implementation into BPF ecosystem, which allows multiple CPUs to submit data to a single shared ring buffer. On the consumption side, only single consumer is assumed. Motivation ---------- There are two distinctive motivators for this work, which are not satisfied by existing perf buffer, which prompted creation of a new ring buffer implementation. - more efficient memory utilization by sharing ring buffer across CPUs; - preserving ordering of events that happen sequentially in time, even across multiple CPUs (e.g., fork/exec/exit events for a task). These two problems are independent, but perf buffer fails to satisfy both. Both are a result of a choice to have per-CPU perf ring buffer. Both can be also solved by having an MPSC implementation of ring buffer. The ordering problem could technically be solved for perf buffer with some in-kernel counting, but given the first one requires an MPSC buffer, the same solution would solve the second problem automatically. Semantics and APIs ------------------ Single ring buffer is presented to BPF programs as an instance of BPF map of type BPF_MAP_TYPE_RINGBUF. Two other alternatives considered, but ultimately rejected. One way would be to, similar to BPF_MAP_TYPE_PERF_EVENT_ARRAY, make BPF_MAP_TYPE_RINGBUF could represent an array of ring buffers, but not enforce "same CPU only" rule. This would be more familiar interface compatible with existing perf buffer use in BPF, but would fail if application needed more advanced logic to lookup ring buffer by arbitrary key. HASH_OF_MAPS addresses this with current approach. Additionally, given the performance of BPF ringbuf, many use cases would just opt into a simple single ring buffer shared among all CPUs, for which current approach would be an overkill. Another approach could introduce a new concept, alongside BPF map, to represent generic "container" object, which doesn't necessarily have key/value interface with lookup/update/delete operations. This approach would add a lot of extra infrastructure that has to be built for observability and verifier support. It would also add another concept that BPF developers would have to familiarize themselves with, new syntax in libbpf, etc. But then would really provide no additional benefits over the approach of using a map. BPF_MAP_TYPE_RINGBUF doesn't support lookup/update/delete operations, but so doesn't few other map types (e.g., queue and stack; array doesn't support delete, etc). The approach chosen has an advantage of re-using existing BPF map infrastructure (introspection APIs in kernel, libbpf support, etc), being familiar concept (no need to teach users a new type of object in BPF program), and utilizing existing tooling (bpftool). For common scenario of using a single ring buffer for all CPUs, it's as simple and straightforward, as would be with a dedicated "container" object. On the other hand, by being a map, it can be combined with ARRAY_OF_MAPS and HASH_OF_MAPS map-in-maps to implement a wide variety of topologies, from one ring buffer for each CPU (e.g., as a replacement for perf buffer use cases), to a complicated application hashing/sharding of ring buffers (e.g., having a small pool of ring buffers with hashed task's tgid being a look up key to preserve order, but reduce contention). Key and value sizes are enforced to be zero. max_entries is used to specify the size of ring buffer and has to be a power of 2 value. There are a bunch of similarities between perf buffer (BPF_MAP_TYPE_PERF_EVENT_ARRAY) and new BPF ring buffer semantics: - variable-length records; - if there is no more space left in ring buffer, reservation fails, no blocking; - memory-mappable data area for user-space applications for ease of consumption and high performance; - epoll notifications for new incoming data; - but still the ability to do busy polling for new data to achieve the lowest latency, if necessary. BPF ringbuf provides two sets of APIs to BPF programs: - bpf_ringbuf_output() allows to *copy* data from one place to a ring buffer, similarly to bpf_perf_event_output(); - bpf_ringbuf_reserve()/bpf_ringbuf_commit()/bpf_ringbuf_discard() APIs split the whole process into two steps. First, a fixed amount of space is reserved. If successful, a pointer to a data inside ring buffer data area is returned, which BPF programs can use similarly to a data inside array/hash maps. Once ready, this piece of memory is either committed or discarded. Discard is similar to commit, but makes consumer ignore the record. bpf_ringbuf_output() has disadvantage of incurring extra memory copy, because record has to be prepared in some other place first. But it allows to submit records of the length that's not known to verifier beforehand. It also closely matches bpf_perf_event_output(), so will simplify migration significantly. bpf_ringbuf_reserve() avoids the extra copy of memory by providing a memory pointer directly to ring buffer memory. In a lot of cases records are larger than BPF stack space allows, so many programs have use extra per-CPU array as a temporary heap for preparing sample. bpf_ringbuf_reserve() avoid this needs completely. But in exchange, it only allows a known constant size of memory to be reserved, such that verifier can verify that BPF program can't access memory outside its reserved record space. bpf_ringbuf_output(), while slightly slower due to extra memory copy, covers some use cases that are not suitable for bpf_ringbuf_reserve(). The difference between commit and discard is very small. Discard just marks a record as discarded, and such records are supposed to be ignored by consumer code. Discard is useful for some advanced use-cases, such as ensuring all-or-nothing multi-record submission, or emulating temporary malloc()/free() within single BPF program invocation. Each reserved record is tracked by verifier through existing reference-tracking logic, similar to socket ref-tracking. It is thus impossible to reserve a record, but forget to submit (or discard) it. bpf_ringbuf_query() helper allows to query various properties of ring buffer. Currently 4 are supported: - BPF_RB_AVAIL_DATA returns amount of unconsumed data in ring buffer; - BPF_RB_RING_SIZE returns the size of ring buffer; - BPF_RB_CONS_POS/BPF_RB_PROD_POS returns current logical possition of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be off by the time helper returns, so this should be used only for debugging/reporting reasons or for implementing various heuristics, that take into account highly-changeable nature of some of those characteristics. One such heuristic might involve more fine-grained control over poll/epoll notifications about new data availability in ring buffer. Together with BPF_RB_NO_WAKEUP/BPF_RB_FORCE_WAKEUP flags for output/commit/discard helpers, it allows BPF program a high degree of control and, e.g., more efficient batched notifications. Default self-balancing strategy, though, should be adequate for most applications and will work reliable and efficiently already. Design and implementation ------------------------- This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This means that if BPF program was interruped by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during reservation, in NMI context, bpf_ringbuf_reserve() might fail to get a lock, in which case reservation will fail even if ring buffer is not full. The ring buffer itself internally is implemented as a power-of-2 sized circular buffer, with two logical and ever-increasing counters (which might wrap around on 32-bit architectures, that's not a problem): - consumer counter shows up to which logical position consumer consumed the data; - producer counter denotes amount of data reserved by all producers. Each time a record is reserved, producer that "owns" the record will successfully advance producer counter. At that point, data is still not yet ready to be consumed, though. Each record has 8 byte header, which contains the length of reserved record, as well as two extra bits: busy bit to denote that record is still being worked on, and discard bit, which might be set at commit time if record is discarded. In the latter case, consumer is supposed to skip the record and move on to the next one. Record header also encodes record's relative offset from the beginning of ring buffer data area (in pages). This allows bpf_ringbuf_commit()/bpf_ringbuf_discard() to accept only the pointer to the record itself, without requiring also the pointer to ring buffer itself. Ring buffer memory location will be restored from record metadata header. This significantly simplifies verifier, as well as improving API usability. Producer counter increments are serialized under spinlock, so there is a strict ordering between reservations. Commits, on the other hand, are completely lockless and independent. All records become available to consumer in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. Reservation/commit/consumer protocol is verified by litmus tests in Documentation/litmus-test/bpf-rb. One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This allows to not take any special measures for samples that have to wrap around at the end of the circular buffer data area, because the next page after the last data page would be first data page again, and thus the sample will still appear completely contiguous in virtual memory. See comment and a simple ASCII diagram showing this visually in bpf_ringbuf_area_alloc(). Another feature that distinguishes BPF ringbuf from perf ring buffer is a self-pacing notifications of new data being availability. bpf_ringbuf_commit() implementation will send a notification of new record being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of notifications, commit/discard/output helpers accept BPF_RB_NO_WAKEUP and BPF_RB_FORCE_WAKEUP flags, which give full control over notifications of data availability, but require extra caution and diligence in using this API. Comparison to alternatives -------------------------- Before considering implementing BPF ring buffer from scratch existing alternatives in kernel were evaluated, but didn't seem to meet the needs. They largely fell into few categores: - per-CPU buffers (perf, ftrace, etc), which don't satisfy two motivations outlined above (ordering and memory consumption); - linked list-based implementations; while some were multi-producer designs, consuming these from user-space would be very complicated and most probably not performant; memory-mapping contiguous piece of memory is simpler and more performant for user-space consumers; - io_uring is SPSC, but also requires fixed-sized elements. Naively turning SPSC queue into MPSC w/ lock would have subpar performance compared to locked reserve + lockless commit, as with BPF ring buffer. Fixed sized elements would be too limiting for BPF programs, given existing BPF programs heavily rely on variable-sized perf buffer already; - specialized implementations (like a new printk ring buffer, [0]) with lots of printk-specific limitations and implications, that didn't seem to fit well for intended use with BPF programs. [0] https://lwn.net/Articles/779550/ Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200529075424.3139988-2-andriin@fb.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2020-05-29 10:54:20 +03:00
extern const struct bpf_func_proto bpf_ringbuf_output_proto;
extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
extern const struct bpf_func_proto bpf_ringbuf_query_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
extern const struct bpf_func_proto bpf_copy_from_user_proto;
bpf: Add bpf_snprintf_btf helper A helper is added to support tracing kernel type information in BPF using the BPF Type Format (BTF). Its signature is long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags); struct btf_ptr * specifies - a pointer to the data to be traced - the BTF id of the type of data pointed to - a flags field is provided for future use; these flags are not to be confused with the BTF_F_* flags below that control how the btf_ptr is displayed; the flags member of the struct btf_ptr may be used to disambiguate types in kernel versus module BTF, etc; the main distinction is the flags relate to the type and information needed in identifying it; not how it is displayed. For example a BPF program with a struct sk_buff *skb could do the following: static struct btf_ptr b = { }; b.ptr = skb; b.type_id = __builtin_btf_type_id(struct sk_buff, 1); bpf_snprintf_btf(str, sizeof(str), &b, sizeof(b), 0, 0); Default output looks like this: (struct sk_buff){ .transport_header = (__u16)65535, .mac_header = (__u16)65535, .end = (sk_buff_data_t)192, .head = (unsigned char *)0x000000007524fd8b, .data = (unsigned char *)0x000000007524fd8b, .truesize = (unsigned int)768, .users = (refcount_t){ .refs = (atomic_t){ .counter = (int)1, }, }, } Flags modifying display are as follows: - BTF_F_COMPACT: no formatting around type information - BTF_F_NONAME: no struct/union member names/types - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values; equivalent to %px. - BTF_F_ZERO: show zero-valued struct/union members; they are not displayed by default Signed-off-by: Alan Maguire <alan.maguire@oracle.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/1601292670-1616-4-git-send-email-alan.maguire@oracle.com
2020-09-28 14:31:05 +03:00
extern const struct bpf_func_proto bpf_snprintf_btf_proto;
extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
const struct bpf_func_proto *bpf_tracing_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
const struct bpf_func_proto *tracing_prog_func_proto(
enum bpf_func_id func_id, const struct bpf_prog *prog);
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 02:20:39 +03:00
/* 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);
u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
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 02:20:39 +03:00
#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 10:22:20 +03:00
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 10:22:20 +03:00
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
struct sk_reuseport_kern {
struct sk_buff *skb;
struct sock *sk;
struct sock *selected_sk;
void *data_end;
u32 hash;
u32 reuseport_id;
bool bind_inany;
};
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);
bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_xdp_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;
}
static inline bool bpf_xdp_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_xdp_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 */
enum bpf_text_poke_type {
BPF_MOD_CALL,
BPF_MOD_JUMP,
};
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *addr1, void *addr2);
struct btf_id_set;
bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
#endif /* _LINUX_BPF_H */