OpenCloudOS-Kernel/include/linux/bpf_verifier.h

652 lines
23 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#ifndef _LINUX_BPF_VERIFIER_H
#define _LINUX_BPF_VERIFIER_H 1
#include <linux/bpf.h> /* for enum bpf_reg_type */
#include <linux/btf.h> /* for struct btf and btf_id() */
#include <linux/filter.h> /* for MAX_BPF_STACK */
#include <linux/tnum.h>
/* Maximum variable offset umax_value permitted when resolving memory accesses.
* In practice this is far bigger than any realistic pointer offset; this limit
* ensures that umax_value + (int)off + (int)size cannot overflow a u64.
*/
#define BPF_MAX_VAR_OFF (1 << 29)
/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures
* that converting umax_value to int cannot overflow.
*/
#define BPF_MAX_VAR_SIZ (1 << 29)
/* size of type_str_buf in bpf_verifier. */
#define TYPE_STR_BUF_LEN 64
/* Liveness marks, used for registers and spilled-regs (in stack slots).
* Read marks propagate upwards until they find a write mark; they record that
* "one of this state's descendants read this reg" (and therefore the reg is
* relevant for states_equal() checks).
* Write marks collect downwards and do not propagate; they record that "the
* straight-line code that reached this state (from its parent) wrote this reg"
* (and therefore that reads propagated from this state or its descendants
* should not propagate to its parent).
* A state with a write mark can receive read marks; it just won't propagate
* them to its parent, since the write mark is a property, not of the state,
* but of the link between it and its parent. See mark_reg_read() and
* mark_stack_slot_read() in kernel/bpf/verifier.c.
*/
enum bpf_reg_liveness {
REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
bpf: verifier: mark verified-insn with sub-register zext flag eBPF ISA specification requires high 32-bit cleared when low 32-bit sub-register is written. This applies to destination register of ALU32 etc. JIT back-ends must guarantee this semantic when doing code-gen. x86_64 and AArch64 ISA has the same semantics, so the corresponding JIT back-end doesn't need to do extra work. However, 32-bit arches (arm, x86, nfp etc.) and some other 64-bit arches (PowerPC, SPARC etc) need to do explicit zero extension to meet this requirement, otherwise code like the following will fail. u64_value = (u64) u32_value ... other uses of u64_value This is because compiler could exploit the semantic described above and save those zero extensions for extending u32_value to u64_value, these JIT back-ends are expected to guarantee this through inserting extra zero extensions which however could be a significant increase on the code size. Some benchmarks show there could be ~40% sub-register writes out of total insns, meaning at least ~40% extra code-gen. One observation is these extra zero extensions are not always necessary. Take above code snippet for example, it is possible u32_value will never be casted into a u64, the value of high 32-bit of u32_value then could be ignored and extra zero extension could be eliminated. This patch implements this idea, insns defining sub-registers will be marked when the high 32-bit of the defined sub-register matters. For those unmarked insns, it is safe to eliminate high 32-bit clearnace for them. Algo: - Split read flags into READ32 and READ64. - Record index of insn that does sub-register write. Keep the index inside reg state and update it during verifier insn walking. - A full register read on a sub-register marks its definition insn as needing zero extension on dst register. A new sub-register write overrides the old one. - When propagating read64 during path pruning, also mark any insn defining a sub-register that is read in the pruned path as full-register. 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 06:25:12 +08:00
REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */
REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */
REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64,
REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */
REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */
};
struct bpf_reg_state {
/* Ordering of fields matters. See states_equal() */
enum bpf_reg_type type;
/* Fixed part of pointer offset, pointer types only */
s32 off;
union {
/* valid when type == PTR_TO_PACKET */
int range;
/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
* PTR_TO_MAP_VALUE_OR_NULL
*/
struct {
struct bpf_map *map_ptr;
/* To distinguish map lookups from outer map
* the map_uid is non-zero for registers
* pointing to inner maps.
*/
u32 map_uid;
};
/* for PTR_TO_BTF_ID */
struct {
struct btf *btf;
u32 btf_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 11:25:00 +08:00
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 15:54:20 +08:00
u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
bpf: Add verifier support for dynptrs This patch adds the bulk of the verifier work for supporting dynamic pointers (dynptrs) in bpf. A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure defined internally as: struct bpf_dynptr_kern { void *data; u32 size; u32 offset; } __aligned(8); The upper 8 bits of *size* is reserved (it contains extra metadata about read-only status and dynptr type). Consequently, a dynptr only supports memory less than 16 MB. There are different types of dynptrs (eg malloc, ringbuf, ...). In this patchset, the most basic one, dynptrs to a bpf program's local memory, is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. In the verifier, dynptr state information will be tracked in stack slots. When the program passes in an uninitialized dynptr (ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding to the frame pointer where the dynptr resides at are marked STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg bpf_dynptr_read + bpf_dynptr_write which are added later in this patchset), the verifier enforces that the dynptr has been initialized properly by checking that their corresponding stack slots have been marked as STACK_DYNPTR. The 6th patch in this patchset adds test cases that the verifier should successfully reject, such as for example attempting to use a dynptr after doing a direct write into it inside the bpf program. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com
2022-05-24 05:07:07 +08:00
/* For dynptr stack slots */
struct {
enum bpf_dynptr_type type;
/* A dynptr is 16 bytes so it takes up 2 stack slots.
* We need to track which slot is the first slot
* to protect against cases where the user may try to
* pass in an address starting at the second slot of the
* dynptr.
*/
bool first_slot;
} dynptr;
/* Max size from any of the above. */
struct {
unsigned long raw1;
unsigned long raw2;
} raw;
bpf: Add bpf_for_each_map_elem() helper The bpf_for_each_map_elem() helper is introduced which iterates all map elements with a callback function. The helper signature looks like long bpf_for_each_map_elem(map, callback_fn, callback_ctx, flags) and for each map element, the callback_fn will be called. For example, like hashmap, the callback signature may look like long callback_fn(map, key, val, callback_ctx) There are two known use cases for this. One is from upstream ([1]) where a for_each_map_elem helper may help implement a timeout mechanism in a more generic way. Another is from our internal discussion for a firewall use case where a map contains all the rules. The packet data can be compared to all these rules to decide allow or deny the packet. For array maps, users can already use a bounded loop to traverse elements. Using this helper can avoid using bounded loop. For other type of maps (e.g., hash maps) where bounded loop is hard or impossible to use, this helper provides a convenient way to operate on all elements. For callback_fn, besides map and map element, a callback_ctx, allocated on caller stack, is also passed to the callback function. This callback_ctx argument can provide additional input and allow to write to caller stack for output. If the callback_fn returns 0, the helper will iterate through next element if available. If the callback_fn returns 1, the helper will stop iterating and returns to the bpf program. Other return values are not used for now. Currently, this helper is only available with jit. It is possible to make it work with interpreter with so effort but I leave it as the future work. [1]: https://lore.kernel.org/bpf/20210122205415.113822-1-xiyou.wangcong@gmail.com/ 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/20210226204925.3884923-1-yhs@fb.com
2021-02-27 04:49:25 +08:00
u32 subprogno; /* for PTR_TO_FUNC */
};
/* For PTR_TO_PACKET, used to find other pointers with the same variable
* offset, so they can share range knowledge.
* For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we
* came from, when one is tested for != 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 15:54:20 +08:00
* For PTR_TO_MEM_OR_NULL this is used to identify memory allocation
* for the purpose of tracking that it's freed.
* For PTR_TO_SOCKET this is used to share which pointers retain the
* same reference to the socket, to determine proper reference freeing.
* For stack slots that are dynptrs, this is used to track references to
* the dynptr to determine proper reference freeing.
*/
u32 id;
bpf: Fix bpf_tcp_sock and bpf_sk_fullsock issue related to bpf_sk_release Lorenz Bauer [thanks!] reported that a ptr returned by bpf_tcp_sock(sk) can still be accessed after bpf_sk_release(sk). Both bpf_tcp_sock() and bpf_sk_fullsock() have the same issue. This patch addresses them together. A simple reproducer looks like this: sk = bpf_sk_lookup_tcp(); /* if (!sk) ... */ tp = bpf_tcp_sock(sk); /* if (!tp) ... */ bpf_sk_release(sk); snd_cwnd = tp->snd_cwnd; /* oops! The verifier does not complain. */ The problem is the verifier did not scrub the register's states of the tcp_sock ptr (tp) after bpf_sk_release(sk). [ Note that when calling bpf_tcp_sock(sk), the sk is not always refcount-acquired. e.g. bpf_tcp_sock(skb->sk). The verifier works fine for this case. ] Currently, the verifier does not track if a helper's return ptr (in REG_0) is "carry"-ing one of its argument's refcount status. To carry this info, the reg1->id needs to be stored in reg0. One approach was tried, like "reg0->id = reg1->id", when calling "bpf_tcp_sock()". The main idea was to avoid adding another "ref_obj_id" for the same reg. However, overlapping the NULL marking and ref tracking purpose in one "id" does not work well: ref_sk = bpf_sk_lookup_tcp(); fullsock = bpf_sk_fullsock(ref_sk); tp = bpf_tcp_sock(ref_sk); if (!fullsock) { bpf_sk_release(ref_sk); return 0; } /* fullsock_reg->id is marked for NOT-NULL. * Same for tp_reg->id because they have the same id. */ /* oops. verifier did not complain about the missing !tp check */ snd_cwnd = tp->snd_cwnd; Hence, a new "ref_obj_id" is needed in "struct bpf_reg_state". With a new ref_obj_id, when bpf_sk_release(sk) is called, the verifier can scrub all reg states which has a ref_obj_id match. It is done with the changes in release_reg_references() in this patch. While fixing it, sk_to_full_sk() is removed from bpf_tcp_sock() and bpf_sk_fullsock() to avoid these helpers from returning another ptr. It will make bpf_sk_release(tp) possible: sk = bpf_sk_lookup_tcp(); /* if (!sk) ... */ tp = bpf_tcp_sock(sk); /* if (!tp) ... */ bpf_sk_release(tp); A separate helper "bpf_get_listener_sock()" will be added in a later patch to do sk_to_full_sk(). Misc change notes: - To allow bpf_sk_release(tp), the arg of bpf_sk_release() is changed from ARG_PTR_TO_SOCKET to ARG_PTR_TO_SOCK_COMMON. ARG_PTR_TO_SOCKET is removed from bpf.h since no helper is using it. - arg_type_is_refcounted() is renamed to arg_type_may_be_refcounted() because ARG_PTR_TO_SOCK_COMMON is the only one and skb->sk is not refcounted. All bpf_sk_release(), bpf_sk_fullsock() and bpf_tcp_sock() take ARG_PTR_TO_SOCK_COMMON. - check_refcount_ok() ensures is_acquire_function() cannot take arg_type_may_be_refcounted() as its argument. - The check_func_arg() can only allow one refcount-ed arg. It is guaranteed by check_refcount_ok() which ensures at most one arg can be refcounted. Hence, it is a verifier internal error if >1 refcount arg found in check_func_arg(). - In release_reference(), release_reference_state() is called first to ensure a match on "reg->ref_obj_id" can be found before scrubbing the reg states with release_reg_references(). - reg_is_refcounted() is no longer needed. 1. In mark_ptr_or_null_regs(), its usage is replaced by "ref_obj_id && ref_obj_id == id" because, when is_null == true, release_reference_state() should only be called on the ref_obj_id obtained by a acquire helper (i.e. is_acquire_function() == true). Otherwise, the following would happen: sk = bpf_sk_lookup_tcp(); /* if (!sk) { ... } */ fullsock = bpf_sk_fullsock(sk); if (!fullsock) { /* * release_reference_state(fullsock_reg->ref_obj_id) * where fullsock_reg->ref_obj_id == sk_reg->ref_obj_id. * * Hence, the following bpf_sk_release(sk) will fail * because the ref state has already been released in the * earlier release_reference_state(fullsock_reg->ref_obj_id). */ bpf_sk_release(sk); } 2. In release_reg_references(), the current reg_is_refcounted() call is unnecessary because the id check is enough. - The type_is_refcounted() and type_is_refcounted_or_null() are no longer needed also because reg_is_refcounted() is removed. Fixes: 655a51e536c0 ("bpf: Add struct bpf_tcp_sock and BPF_FUNC_tcp_sock") Reported-by: Lorenz Bauer <lmb@cloudflare.com> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-03-13 01:23:02 +08:00
/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
* from a pointer-cast helper, bpf_sk_fullsock() and
* bpf_tcp_sock().
*
* Consider the following where "sk" is a reference counted
* pointer returned from "sk = bpf_sk_lookup_tcp();":
*
* 1: sk = bpf_sk_lookup_tcp();
* 2: if (!sk) { return 0; }
* 3: fullsock = bpf_sk_fullsock(sk);
* 4: if (!fullsock) { bpf_sk_release(sk); return 0; }
* 5: tp = bpf_tcp_sock(fullsock);
* 6: if (!tp) { bpf_sk_release(sk); return 0; }
* 7: bpf_sk_release(sk);
* 8: snd_cwnd = tp->snd_cwnd; // verifier will complain
*
* After bpf_sk_release(sk) at line 7, both "fullsock" ptr and
* "tp" ptr should be invalidated also. In order to do that,
* the reg holding "fullsock" and "sk" need to remember
* the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id
* such that the verifier can reset all regs which have
* ref_obj_id matching the sk_reg->id.
*
* sk_reg->ref_obj_id is set to sk_reg->id at line 1.
* sk_reg->id will stay as NULL-marking purpose only.
* After NULL-marking is done, sk_reg->id can be reset to 0.
*
* After "fullsock = bpf_sk_fullsock(sk);" at line 3,
* fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id.
*
* After "tp = bpf_tcp_sock(fullsock);" at line 5,
* tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id
* which is the same as sk_reg->ref_obj_id.
*
* From the verifier perspective, if sk, fullsock and tp
* are not NULL, they are the same ptr with different
* reg->type. In particular, bpf_sk_release(tp) is also
* allowed and has the same effect as bpf_sk_release(sk).
*/
u32 ref_obj_id;
/* For scalar types (SCALAR_VALUE), this represents our knowledge of
* the actual value.
* For pointer types, this represents the variable part of the offset
* from the pointed-to object, and is shared with all bpf_reg_states
* with the same id as us.
*/
struct tnum var_off;
/* Used to determine if any memory access using this register will
* result in a bad access.
* These refer to the same value as var_off, not necessarily the actual
* contents of the register.
*/
s64 smin_value; /* minimum possible (s64)value */
s64 smax_value; /* maximum possible (s64)value */
u64 umin_value; /* minimum possible (u64)value */
u64 umax_value; /* maximum possible (u64)value */
bpf: Verifier, do explicit ALU32 bounds tracking It is not possible for the current verifier to track ALU32 and JMP ops correctly. This can result in the verifier aborting with errors even though the program should be verifiable. BPF codes that hit this can work around it by changin int variables to 64-bit types, marking variables volatile, etc. But this is all very ugly so it would be better to avoid these tricks. But, the main reason to address this now is do_refine_retval_range() was assuming return values could not be negative. Once we fixed this code that was previously working will no longer work. See do_refine_retval_range() patch for details. And we don't want to suddenly cause programs that used to work to fail. The simplest example code snippet that illustrates the problem is likely this, 53: w8 = w0 // r8 <- [0, S32_MAX], // w8 <- [-S32_MIN, X] 54: w8 <s 0 // r8 <- [0, U32_MAX] // w8 <- [0, X] The expected 64-bit and 32-bit bounds after each line are shown on the right. The current issue is without the w* bounds we are forced to use the worst case bound of [0, U32_MAX]. To resolve this type of case, jmp32 creating divergent 32-bit bounds from 64-bit bounds, we add explicit 32-bit register bounds s32_{min|max}_value and u32_{min|max}_value. Then from branch_taken logic creating new bounds we can track 32-bit bounds explicitly. The next case we observed is ALU ops after the jmp32, 53: w8 = w0 // r8 <- [0, S32_MAX], // w8 <- [-S32_MIN, X] 54: w8 <s 0 // r8 <- [0, U32_MAX] // w8 <- [0, X] 55: w8 += 1 // r8 <- [0, U32_MAX+1] // w8 <- [0, X+1] In order to keep the bounds accurate at this point we also need to track ALU32 ops. To do this we add explicit ALU32 logic for each of the ALU ops, mov, add, sub, etc. Finally there is a question of how and when to merge bounds. The cases enumerate here, 1. MOV ALU32 - zext 32-bit -> 64-bit 2. MOV ALU64 - copy 64-bit -> 32-bit 3. op ALU32 - zext 32-bit -> 64-bit 4. op ALU64 - n/a 5. jmp ALU32 - 64-bit: var32_off | upper_32_bits(var64_off) 6. jmp ALU64 - 32-bit: (>> (<< var64_off)) Details for each case, For "MOV ALU32" BPF arch zero extends so we simply copy the bounds from 32-bit into 64-bit ensuring we truncate var_off and 64-bit bounds correctly. See zext_32_to_64. For "MOV ALU64" copy all bounds including 32-bit into new register. If the src register had 32-bit bounds the dst register will as well. For "op ALU32" zero extend 32-bit into 64-bit the same as move, see zext_32_to_64. For "op ALU64" calculate both 32-bit and 64-bit bounds no merging is done here. Except we have a special case. When RSH or ARSH is done we can't simply ignore shifting bits from 64-bit reg into the 32-bit subreg. So currently just push bounds from 64-bit into 32-bit. This will be correct in the sense that they will represent a valid state of the register. However we could lose some accuracy if an ARSH is following a jmp32 operation. We can handle this special case in a follow up series. For "jmp ALU32" mark 64-bit reg unknown and recalculate 64-bit bounds from tnum by setting var_off to ((<<(>>var_off)) | var32_off). We special case if 64-bit bounds has zero'd upper 32bits at which point we can simply copy 32-bit bounds into 64-bit register. This catches a common compiler trick where upper 32-bits are zeroed and then 32-bit ops are used followed by a 64-bit compare or 64-bit op on a pointer. See __reg_combine_64_into_32(). For "jmp ALU64" cast the bounds of the 64bit to their 32-bit counterpart. For example s32_min_value = (s32)reg->smin_value. For tnum use only the lower 32bits via, (>>(<<var_off)). See __reg_combine_64_into_32(). Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/158560419880.10843.11448220440809118343.stgit@john-Precision-5820-Tower
2020-03-31 05:36:39 +08:00
s32 s32_min_value; /* minimum possible (s32)value */
s32 s32_max_value; /* maximum possible (s32)value */
u32 u32_min_value; /* minimum possible (u32)value */
u32 u32_max_value; /* maximum possible (u32)value */
/* parentage chain for liveness checking */
struct bpf_reg_state *parent;
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
/* Inside the callee two registers can be both PTR_TO_STACK like
* R1=fp-8 and R2=fp-8, but one of them points to this function stack
* while another to the caller's stack. To differentiate them 'frameno'
* is used which is an index in bpf_verifier_state->frame[] array
* pointing to bpf_func_state.
*/
u32 frameno;
bpf: verifier: mark verified-insn with sub-register zext flag eBPF ISA specification requires high 32-bit cleared when low 32-bit sub-register is written. This applies to destination register of ALU32 etc. JIT back-ends must guarantee this semantic when doing code-gen. x86_64 and AArch64 ISA has the same semantics, so the corresponding JIT back-end doesn't need to do extra work. However, 32-bit arches (arm, x86, nfp etc.) and some other 64-bit arches (PowerPC, SPARC etc) need to do explicit zero extension to meet this requirement, otherwise code like the following will fail. u64_value = (u64) u32_value ... other uses of u64_value This is because compiler could exploit the semantic described above and save those zero extensions for extending u32_value to u64_value, these JIT back-ends are expected to guarantee this through inserting extra zero extensions which however could be a significant increase on the code size. Some benchmarks show there could be ~40% sub-register writes out of total insns, meaning at least ~40% extra code-gen. One observation is these extra zero extensions are not always necessary. Take above code snippet for example, it is possible u32_value will never be casted into a u64, the value of high 32-bit of u32_value then could be ignored and extra zero extension could be eliminated. This patch implements this idea, insns defining sub-registers will be marked when the high 32-bit of the defined sub-register matters. For those unmarked insns, it is safe to eliminate high 32-bit clearnace for them. Algo: - Split read flags into READ32 and READ64. - Record index of insn that does sub-register write. Keep the index inside reg state and update it during verifier insn walking. - A full register read on a sub-register marks its definition insn as needing zero extension on dst register. A new sub-register write overrides the old one. - When propagating read64 during path pruning, also mark any insn defining a sub-register that is read in the pruned path as full-register. 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 06:25:12 +08:00
/* Tracks subreg definition. The stored value is the insn_idx of the
* writing insn. This is safe because subreg_def is used before any insn
* patching which only happens after main verification finished.
*/
s32 subreg_def;
enum bpf_reg_liveness live;
bpf: precise scalar_value tracking Introduce precision tracking logic that helps cilium programs the most: old clang old clang new clang new clang with all patches with all patches bpf_lb-DLB_L3.o 1838 2283 1923 1863 bpf_lb-DLB_L4.o 3218 2657 3077 2468 bpf_lb-DUNKNOWN.o 1064 545 1062 544 bpf_lxc-DDROP_ALL.o 26935 23045 166729 22629 bpf_lxc-DUNKNOWN.o 34439 35240 174607 28805 bpf_netdev.o 9721 8753 8407 6801 bpf_overlay.o 6184 7901 5420 4754 bpf_lxc_jit.o 39389 50925 39389 50925 Consider code: 654: (85) call bpf_get_hash_recalc#34 655: (bf) r7 = r0 656: (15) if r8 == 0x0 goto pc+29 657: (bf) r2 = r10 658: (07) r2 += -48 659: (18) r1 = 0xffff8881e41e1b00 661: (85) call bpf_map_lookup_elem#1 662: (15) if r0 == 0x0 goto pc+23 663: (69) r1 = *(u16 *)(r0 +0) 664: (15) if r1 == 0x0 goto pc+21 665: (bf) r8 = r7 666: (57) r8 &= 65535 667: (bf) r2 = r8 668: (3f) r2 /= r1 669: (2f) r2 *= r1 670: (bf) r1 = r8 671: (1f) r1 -= r2 672: (57) r1 &= 255 673: (25) if r1 > 0x1e goto pc+12 R0=map_value(id=0,off=0,ks=20,vs=64,imm=0) R1_w=inv(id=0,umax_value=30,var_off=(0x0; 0x1f)) 674: (67) r1 <<= 1 675: (0f) r0 += r1 At this point the verifier will notice that scalar R1 is used in map pointer adjustment. R1 has to be precise for later operations on R0 to be validated properly. The verifier will backtrack the above code in the following way: last_idx 675 first_idx 664 regs=2 stack=0 before 675: (0f) r0 += r1 // started backtracking R1 regs=2 is a bitmask regs=2 stack=0 before 674: (67) r1 <<= 1 regs=2 stack=0 before 673: (25) if r1 > 0x1e goto pc+12 regs=2 stack=0 before 672: (57) r1 &= 255 regs=2 stack=0 before 671: (1f) r1 -= r2 // now both R1 and R2 has to be precise -> regs=6 mask regs=6 stack=0 before 670: (bf) r1 = r8 // after this insn R8 and R2 has to be precise regs=104 stack=0 before 669: (2f) r2 *= r1 // after this one R8, R2, and R1 regs=106 stack=0 before 668: (3f) r2 /= r1 regs=106 stack=0 before 667: (bf) r2 = r8 regs=102 stack=0 before 666: (57) r8 &= 65535 regs=102 stack=0 before 665: (bf) r8 = r7 regs=82 stack=0 before 664: (15) if r1 == 0x0 goto pc+21 // this is the end of verifier state. The following regs will be marked precised: R1_rw=invP(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R7_rw=invP(id=0) parent didn't have regs=82 stack=0 marks // so backtracking continues into parent state last_idx 663 first_idx 655 regs=82 stack=0 before 663: (69) r1 = *(u16 *)(r0 +0) // R1 was assigned no need to track it further regs=80 stack=0 before 662: (15) if r0 == 0x0 goto pc+23 // keep tracking R7 regs=80 stack=0 before 661: (85) call bpf_map_lookup_elem#1 // keep tracking R7 regs=80 stack=0 before 659: (18) r1 = 0xffff8881e41e1b00 regs=80 stack=0 before 658: (07) r2 += -48 regs=80 stack=0 before 657: (bf) r2 = r10 regs=80 stack=0 before 656: (15) if r8 == 0x0 goto pc+29 regs=80 stack=0 before 655: (bf) r7 = r0 // here the assignment into R7 // mark R0 to be precise: R0_rw=invP(id=0) parent didn't have regs=1 stack=0 marks // regs=1 -> tracking R0 last_idx 654 first_idx 644 regs=1 stack=0 before 654: (85) call bpf_get_hash_recalc#34 // and in the parent frame it was a return value // nothing further to backtrack Two scalar registers not marked precise are equivalent from state pruning point of view. More details in the patch comments. It doesn't support bpf2bpf calls yet and enabled for root only. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-16 03:12:25 +08:00
/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
bool precise;
};
enum bpf_stack_slot_type {
STACK_INVALID, /* nothing was stored in this stack slot */
STACK_SPILL, /* register spilled into stack */
bpf: teach verifier to recognize zero initialized stack programs with function calls are often passing various pointers via stack. When all calls are inlined llvm flattens stack accesses and optimizes away extra branches. When functions are not inlined it becomes the job of the verifier to recognize zero initialized stack to avoid exploring paths that program will not take. The following program would fail otherwise: ptr = &buffer_on_stack; *ptr = 0; ... func_call(.., ptr, ...) { if (..) *ptr = bpf_map_lookup(); } ... if (*ptr != 0) { // Access (*ptr)->field is valid. // Without stack_zero tracking such (*ptr)->field access // will be rejected } since stack slots are no longer uniform invalid | spill | misc add liveness marking to all slots, but do it in 8 byte chunks. So if nothing was read or written in [fp-16, fp-9] range it will be marked as LIVE_NONE. If any byte in that range was read, it will be marked LIVE_READ and stacksafe() check will perform byte-by-byte verification. If all bytes in the range were written the slot will be marked as LIVE_WRITTEN. This significantly speeds up state equality comparison and reduces total number of states processed. before after bpf_lb-DLB_L3.o 2051 2003 bpf_lb-DLB_L4.o 3287 3164 bpf_lb-DUNKNOWN.o 1080 1080 bpf_lxc-DDROP_ALL.o 24980 12361 bpf_lxc-DUNKNOWN.o 34308 16605 bpf_netdev.o 15404 10962 bpf_overlay.o 7191 6679 Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:08 +08:00
STACK_MISC, /* BPF program wrote some data into this slot */
STACK_ZERO, /* BPF program wrote constant zero */
bpf: Add verifier support for dynptrs This patch adds the bulk of the verifier work for supporting dynamic pointers (dynptrs) in bpf. A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure defined internally as: struct bpf_dynptr_kern { void *data; u32 size; u32 offset; } __aligned(8); The upper 8 bits of *size* is reserved (it contains extra metadata about read-only status and dynptr type). Consequently, a dynptr only supports memory less than 16 MB. There are different types of dynptrs (eg malloc, ringbuf, ...). In this patchset, the most basic one, dynptrs to a bpf program's local memory, is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. In the verifier, dynptr state information will be tracked in stack slots. When the program passes in an uninitialized dynptr (ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding to the frame pointer where the dynptr resides at are marked STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg bpf_dynptr_read + bpf_dynptr_write which are added later in this patchset), the verifier enforces that the dynptr has been initialized properly by checking that their corresponding stack slots have been marked as STACK_DYNPTR. The 6th patch in this patchset adds test cases that the verifier should successfully reject, such as for example attempting to use a dynptr after doing a direct write into it inside the bpf program. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com
2022-05-24 05:07:07 +08:00
/* A dynptr is stored in this stack slot. The type of dynptr
* is stored in bpf_stack_state->spilled_ptr.dynptr.type
*/
STACK_DYNPTR,
};
#define BPF_REG_SIZE 8 /* size of eBPF register in bytes */
bpf: Add verifier support for dynptrs This patch adds the bulk of the verifier work for supporting dynamic pointers (dynptrs) in bpf. A bpf_dynptr is opaque to the bpf program. It is a 16-byte structure defined internally as: struct bpf_dynptr_kern { void *data; u32 size; u32 offset; } __aligned(8); The upper 8 bits of *size* is reserved (it contains extra metadata about read-only status and dynptr type). Consequently, a dynptr only supports memory less than 16 MB. There are different types of dynptrs (eg malloc, ringbuf, ...). In this patchset, the most basic one, dynptrs to a bpf program's local memory, is added. For now only local memory that is of reg type PTR_TO_MAP_VALUE is supported. In the verifier, dynptr state information will be tracked in stack slots. When the program passes in an uninitialized dynptr (ARG_PTR_TO_DYNPTR | MEM_UNINIT), the stack slots corresponding to the frame pointer where the dynptr resides at are marked STACK_DYNPTR. For helper functions that take in initialized dynptrs (eg bpf_dynptr_read + bpf_dynptr_write which are added later in this patchset), the verifier enforces that the dynptr has been initialized properly by checking that their corresponding stack slots have been marked as STACK_DYNPTR. The 6th patch in this patchset adds test cases that the verifier should successfully reject, such as for example attempting to use a dynptr after doing a direct write into it inside the bpf program. Signed-off-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: David Vernet <void@manifault.com> Link: https://lore.kernel.org/bpf/20220523210712.3641569-2-joannelkoong@gmail.com
2022-05-24 05:07:07 +08:00
#define BPF_DYNPTR_SIZE sizeof(struct bpf_dynptr_kern)
#define BPF_DYNPTR_NR_SLOTS (BPF_DYNPTR_SIZE / BPF_REG_SIZE)
struct bpf_stack_state {
struct bpf_reg_state spilled_ptr;
u8 slot_type[BPF_REG_SIZE];
};
struct bpf_reference_state {
/* Track each reference created with a unique id, even if the same
* instruction creates the reference multiple times (eg, via CALL).
*/
int id;
/* Instruction where the allocation of this reference occurred. This
* is used purely to inform the user of a reference leak.
*/
int insn_idx;
bpf: Fix reference state management for synchronous callbacks Currently, verifier verifies callback functions (sync and async) as if they will be executed once, (i.e. it explores execution state as if the function was being called once). The next insn to explore is set to start of subprog and the exit from nested frame is handled using curframe > 0 and prepare_func_exit. In case of async callback it uses a customized variant of push_stack simulating a kind of branch to set up custom state and execution context for the async callback. While this approach is simple and works when callback really will be executed only once, it is unsafe for all of our current helpers which are for_each style, i.e. they execute the callback multiple times. A callback releasing acquired references of the caller may do so multiple times, but currently verifier sees it as one call inside the frame, which then returns to caller. Hence, it thinks it released some reference that the cb e.g. got access through callback_ctx (register filled inside cb from spilled typed register on stack). Similarly, it may see that an acquire call is unpaired inside the callback, so the caller will copy the reference state of callback and then will have to release the register with new ref_obj_ids. But again, the callback may execute multiple times, but the verifier will only account for acquired references for a single symbolic execution of the callback, which will cause leaks. Note that for async callback case, things are different. While currently we have bpf_timer_set_callback which only executes it once, even for multiple executions it would be safe, as reference state is NULL and check_reference_leak would force program to release state before BPF_EXIT. The state is also unaffected by analysis for the caller frame. Hence async callback is safe. Since we want the reference state to be accessible, e.g. for pointers loaded from stack through callback_ctx's PTR_TO_STACK, we still have to copy caller's reference_state to callback's bpf_func_state, but we enforce that whatever references it adds to that reference_state has been released before it hits BPF_EXIT. This requires introducing a new callback_ref member in the reference state to distinguish between caller vs callee references. Hence, check_reference_leak now errors out if it sees we are in callback_fn and we have not released callback_ref refs. Since there can be multiple nested callbacks, like frame 0 -> cb1 -> cb2 etc. we need to also distinguish between whether this particular ref belongs to this callback frame or parent, and only error for our own, so we store state->frameno (which is always non-zero for callbacks). In short, callbacks can read parent reference_state, but cannot mutate it, to be able to use pointers acquired by the caller. They must only undo their changes (by releasing their own acquired_refs before BPF_EXIT) on top of caller reference_state before returning (at which point the caller and callback state will match anyway, so no need to copy it back to caller). Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20220823013125.24938-1-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-08-23 09:31:25 +08:00
/* There can be a case like:
* main (frame 0)
* cb (frame 1)
* func (frame 3)
* cb (frame 4)
* Hence for frame 4, if callback_ref just stored boolean, it would be
* impossible to distinguish nested callback refs. Hence store the
* frameno and compare that to callback_ref in check_reference_leak when
* exiting a callback function.
*/
int callback_ref;
};
/* state of the program:
* type of all registers and stack info
*/
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
struct bpf_func_state {
struct bpf_reg_state regs[MAX_BPF_REG];
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
/* index of call instruction that called into this func */
int callsite;
/* stack frame number of this function state from pov of
* enclosing bpf_verifier_state.
* 0 = main function, 1 = first callee.
*/
u32 frameno;
bpf: Allow variable-offset stack access Before this patch, variable offset access to the stack was dissalowed for regular instructions, but was allowed for "indirect" accesses (i.e. helpers). This patch removes the restriction, allowing reading and writing to the stack through stack pointers with variable offsets. This makes stack-allocated buffers more usable in programs, and brings stack pointers closer to other types of pointers. The motivation is being able to use stack-allocated buffers for data manipulation. When the stack size limit is sufficient, allocating buffers on the stack is simpler than per-cpu arrays, or other alternatives. In unpriviledged programs, variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them. Additionally, when writing through a variable-offset stack pointer, if any pointers are in the accessible range, there's possilibities of later leaking pointers because the write cannot be tracked precisely. Writes with variable offset mark the whole range as initialized, even though we don't know which stack slots are actually written. This is in order to not reject future reads to these slots. Note that this doesn't affect writes done through helpers; like before, helpers need the whole stack range to be initialized to begin with. All the stack slots are in range are considered scalars after the write; variable-offset register spills are not tracked. For reads, all the stack slots in the variable range needs to be initialized (but see above about what writes do), otherwise the read is rejected. All register spilled in stack slots that might be read are marked as having been read, however reads through such pointers don't do register filling; the target register will always be either a scalar or a constant zero. Signed-off-by: Andrei Matei <andreimatei1@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210207011027.676572-2-andreimatei1@gmail.com
2021-02-07 09:10:24 +08:00
/* subprog number == index within subprog_info
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
* zero == main subprog
*/
u32 subprogno;
bpf: Implement verifier support for validation of async callbacks. bpf_for_each_map_elem() and bpf_timer_set_callback() helpers are relying on PTR_TO_FUNC infra in the verifier to validate addresses to subprograms and pass them into the helpers as function callbacks. In case of bpf_for_each_map_elem() the callback is invoked synchronously and the verifier treats it as a normal subprogram call by adding another bpf_func_state and new frame in __check_func_call(). bpf_timer_set_callback() doesn't invoke the callback directly. The subprogram will be called asynchronously from bpf_timer_cb(). Teach the verifier to validate such async callbacks as special kind of jump by pushing verifier state into stack and let pop_stack() process it. Special care needs to be taken during state pruning. The call insn doing bpf_timer_set_callback has to be a prune_point. Otherwise short timer callbacks might not have prune points in front of bpf_timer_set_callback() which means is_state_visited() will be called after this call insn is processed in __check_func_call(). Which means that another async_cb state will be pushed to be walked later and the verifier will eventually hit BPF_COMPLEXITY_LIMIT_JMP_SEQ limit. Since push_async_cb() looks like another push_stack() branch the infinite loop detection will trigger false positive. To recognize this case mark such states as in_async_callback_fn. To distinguish infinite loop in async callback vs the same callback called with different arguments for different map and timer add async_entry_cnt to bpf_func_state. Enforce return zero from async callbacks. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210715005417.78572-9-alexei.starovoitov@gmail.com
2021-07-15 08:54:14 +08:00
/* Every bpf_timer_start will increment async_entry_cnt.
* It's used to distinguish:
* void foo(void) { for(;;); }
* void foo(void) { bpf_timer_set_callback(,foo); }
*/
u32 async_entry_cnt;
bool in_callback_fn;
struct tnum callback_ret_range;
bpf: Implement verifier support for validation of async callbacks. bpf_for_each_map_elem() and bpf_timer_set_callback() helpers are relying on PTR_TO_FUNC infra in the verifier to validate addresses to subprograms and pass them into the helpers as function callbacks. In case of bpf_for_each_map_elem() the callback is invoked synchronously and the verifier treats it as a normal subprogram call by adding another bpf_func_state and new frame in __check_func_call(). bpf_timer_set_callback() doesn't invoke the callback directly. The subprogram will be called asynchronously from bpf_timer_cb(). Teach the verifier to validate such async callbacks as special kind of jump by pushing verifier state into stack and let pop_stack() process it. Special care needs to be taken during state pruning. The call insn doing bpf_timer_set_callback has to be a prune_point. Otherwise short timer callbacks might not have prune points in front of bpf_timer_set_callback() which means is_state_visited() will be called after this call insn is processed in __check_func_call(). Which means that another async_cb state will be pushed to be walked later and the verifier will eventually hit BPF_COMPLEXITY_LIMIT_JMP_SEQ limit. Since push_async_cb() looks like another push_stack() branch the infinite loop detection will trigger false positive. To recognize this case mark such states as in_async_callback_fn. To distinguish infinite loop in async callback vs the same callback called with different arguments for different map and timer add async_entry_cnt to bpf_func_state. Enforce return zero from async callbacks. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Link: https://lore.kernel.org/bpf/20210715005417.78572-9-alexei.starovoitov@gmail.com
2021-07-15 08:54:14 +08:00
bool in_async_callback_fn;
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
/* The following fields should be last. See copy_func_state() */
int acquired_refs;
struct bpf_reference_state *refs;
int allocated_stack;
struct bpf_stack_state *stack;
};
bpf: precise scalar_value tracking Introduce precision tracking logic that helps cilium programs the most: old clang old clang new clang new clang with all patches with all patches bpf_lb-DLB_L3.o 1838 2283 1923 1863 bpf_lb-DLB_L4.o 3218 2657 3077 2468 bpf_lb-DUNKNOWN.o 1064 545 1062 544 bpf_lxc-DDROP_ALL.o 26935 23045 166729 22629 bpf_lxc-DUNKNOWN.o 34439 35240 174607 28805 bpf_netdev.o 9721 8753 8407 6801 bpf_overlay.o 6184 7901 5420 4754 bpf_lxc_jit.o 39389 50925 39389 50925 Consider code: 654: (85) call bpf_get_hash_recalc#34 655: (bf) r7 = r0 656: (15) if r8 == 0x0 goto pc+29 657: (bf) r2 = r10 658: (07) r2 += -48 659: (18) r1 = 0xffff8881e41e1b00 661: (85) call bpf_map_lookup_elem#1 662: (15) if r0 == 0x0 goto pc+23 663: (69) r1 = *(u16 *)(r0 +0) 664: (15) if r1 == 0x0 goto pc+21 665: (bf) r8 = r7 666: (57) r8 &= 65535 667: (bf) r2 = r8 668: (3f) r2 /= r1 669: (2f) r2 *= r1 670: (bf) r1 = r8 671: (1f) r1 -= r2 672: (57) r1 &= 255 673: (25) if r1 > 0x1e goto pc+12 R0=map_value(id=0,off=0,ks=20,vs=64,imm=0) R1_w=inv(id=0,umax_value=30,var_off=(0x0; 0x1f)) 674: (67) r1 <<= 1 675: (0f) r0 += r1 At this point the verifier will notice that scalar R1 is used in map pointer adjustment. R1 has to be precise for later operations on R0 to be validated properly. The verifier will backtrack the above code in the following way: last_idx 675 first_idx 664 regs=2 stack=0 before 675: (0f) r0 += r1 // started backtracking R1 regs=2 is a bitmask regs=2 stack=0 before 674: (67) r1 <<= 1 regs=2 stack=0 before 673: (25) if r1 > 0x1e goto pc+12 regs=2 stack=0 before 672: (57) r1 &= 255 regs=2 stack=0 before 671: (1f) r1 -= r2 // now both R1 and R2 has to be precise -> regs=6 mask regs=6 stack=0 before 670: (bf) r1 = r8 // after this insn R8 and R2 has to be precise regs=104 stack=0 before 669: (2f) r2 *= r1 // after this one R8, R2, and R1 regs=106 stack=0 before 668: (3f) r2 /= r1 regs=106 stack=0 before 667: (bf) r2 = r8 regs=102 stack=0 before 666: (57) r8 &= 65535 regs=102 stack=0 before 665: (bf) r8 = r7 regs=82 stack=0 before 664: (15) if r1 == 0x0 goto pc+21 // this is the end of verifier state. The following regs will be marked precised: R1_rw=invP(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R7_rw=invP(id=0) parent didn't have regs=82 stack=0 marks // so backtracking continues into parent state last_idx 663 first_idx 655 regs=82 stack=0 before 663: (69) r1 = *(u16 *)(r0 +0) // R1 was assigned no need to track it further regs=80 stack=0 before 662: (15) if r0 == 0x0 goto pc+23 // keep tracking R7 regs=80 stack=0 before 661: (85) call bpf_map_lookup_elem#1 // keep tracking R7 regs=80 stack=0 before 659: (18) r1 = 0xffff8881e41e1b00 regs=80 stack=0 before 658: (07) r2 += -48 regs=80 stack=0 before 657: (bf) r2 = r10 regs=80 stack=0 before 656: (15) if r8 == 0x0 goto pc+29 regs=80 stack=0 before 655: (bf) r7 = r0 // here the assignment into R7 // mark R0 to be precise: R0_rw=invP(id=0) parent didn't have regs=1 stack=0 marks // regs=1 -> tracking R0 last_idx 654 first_idx 644 regs=1 stack=0 before 654: (85) call bpf_get_hash_recalc#34 // and in the parent frame it was a return value // nothing further to backtrack Two scalar registers not marked precise are equivalent from state pruning point of view. More details in the patch comments. It doesn't support bpf2bpf calls yet and enabled for root only. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-16 03:12:25 +08:00
struct bpf_idx_pair {
u32 prev_idx;
u32 idx;
};
struct bpf_id_pair {
u32 old;
u32 cur;
};
/* Maximum number of register states that can exist at once */
#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE)
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
#define MAX_CALL_FRAMES 8
struct bpf_verifier_state {
/* call stack tracking */
struct bpf_func_state *frame[MAX_CALL_FRAMES];
struct bpf_verifier_state *parent;
/*
* 'branches' field is the number of branches left to explore:
* 0 - all possible paths from this state reached bpf_exit or
* were safely pruned
* 1 - at least one path is being explored.
* This state hasn't reached bpf_exit
* 2 - at least two paths are being explored.
* This state is an immediate parent of two children.
* One is fallthrough branch with branches==1 and another
* state is pushed into stack (to be explored later) also with
* branches==1. The parent of this state has branches==1.
* The verifier state tree connected via 'parent' pointer looks like:
* 1
* 1
* 2 -> 1 (first 'if' pushed into stack)
* 1
* 2 -> 1 (second 'if' pushed into stack)
* 1
* 1
* 1 bpf_exit.
*
* Once do_check() reaches bpf_exit, it calls update_branch_counts()
* and the verifier state tree will look:
* 1
* 1
* 2 -> 1 (first 'if' pushed into stack)
* 1
* 1 -> 1 (second 'if' pushed into stack)
* 0
* 0
* 0 bpf_exit.
* After pop_stack() the do_check() will resume at second 'if'.
*
* If is_state_visited() sees a state with branches > 0 it means
* there is a loop. If such state is exactly equal to the current state
* it's an infinite loop. Note states_equal() checks for states
* equivalency, so two states being 'states_equal' does not mean
* infinite loop. The exact comparison is provided by
* states_maybe_looping() function. It's a stronger pre-check and
* much faster than states_equal().
*
* This algorithm may not find all possible infinite loops or
* loop iteration count may be too high.
* In such cases BPF_COMPLEXITY_LIMIT_INSNS limit kicks in.
*/
u32 branches;
bpf: convert explored_states to hash table All prune points inside a callee bpf function most likely will have different callsites. For example, if function foo() is called from two callsites the half of explored states in all prune points in foo() will be useless for subsequent walking of one of those callsites. Fortunately explored_states pruning heuristics keeps the number of states per prune point small, but walking these states is still a waste of cpu time when the callsite of the current state is different from the callsite of the explored state. To improve pruning logic convert explored_states into hash table and use simple insn_idx ^ callsite hash to select hash bucket. This optimization has no effect on programs without bpf2bpf calls and drastically improves programs with calls. In the later case it reduces total memory consumption in 1M scale tests by almost 3 times (peak_states drops from 5752 to 2016). Care should be taken when comparing the states for equivalency. Since the same hash bucket can now contain states with different indices the insn_idx has to be part of verifier_state and compared. Different hash table sizes and different hash functions were explored, but the results were not significantly better vs this patch. They can be improved in the future. Hit/miss heuristic is not counting index miscompare as a miss. Otherwise verifier stats become unstable when experimenting with different hash functions. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-05-22 11:17:07 +08:00
u32 insn_idx;
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
u32 curframe;
bpf: introduce bpf_spin_lock Introduce 'struct bpf_spin_lock' and bpf_spin_lock/unlock() helpers to let bpf program serialize access to other variables. Example: struct hash_elem { int cnt; struct bpf_spin_lock lock; }; struct hash_elem * val = bpf_map_lookup_elem(&hash_map, &key); if (val) { bpf_spin_lock(&val->lock); val->cnt++; bpf_spin_unlock(&val->lock); } Restrictions and safety checks: - bpf_spin_lock is only allowed inside HASH and ARRAY maps. - BTF description of the map is mandatory for safety analysis. - bpf program can take one bpf_spin_lock at a time, since two or more can cause dead locks. - only one 'struct bpf_spin_lock' is allowed per map element. It drastically simplifies implementation yet allows bpf program to use any number of bpf_spin_locks. - when bpf_spin_lock is taken the calls (either bpf2bpf or helpers) are not allowed. - bpf program must bpf_spin_unlock() before return. - bpf program can access 'struct bpf_spin_lock' only via bpf_spin_lock()/bpf_spin_unlock() helpers. - load/store into 'struct bpf_spin_lock lock;' field is not allowed. - to use bpf_spin_lock() helper the BTF description of map value must be a struct and have 'struct bpf_spin_lock anyname;' field at the top level. Nested lock inside another struct is not allowed. - syscall map_lookup doesn't copy bpf_spin_lock field to user space. - syscall map_update and program map_update do not update bpf_spin_lock field. - bpf_spin_lock cannot be on the stack or inside networking packet. bpf_spin_lock can only be inside HASH or ARRAY map value. - bpf_spin_lock is available to root only and to all program types. - bpf_spin_lock is not allowed in inner maps of map-in-map. - ld_abs is not allowed inside spin_lock-ed region. - tracing progs and socket filter progs cannot use bpf_spin_lock due to insufficient preemption checks Implementation details: - cgroup-bpf class of programs can nest with xdp/tc programs. Hence bpf_spin_lock is equivalent to spin_lock_irqsave. Other solutions to avoid nested bpf_spin_lock are possible. Like making sure that all networking progs run with softirq disabled. spin_lock_irqsave is the simplest and doesn't add overhead to the programs that don't use it. - arch_spinlock_t is used when its implemented as queued_spin_lock - archs can force their own arch_spinlock_t - on architectures where queued_spin_lock is not available and sizeof(arch_spinlock_t) != sizeof(__u32) trivial lock is used. - presence of bpf_spin_lock inside map value could have been indicated via extra flag during map_create, but specifying it via BTF is cleaner. It provides introspection for map key/value and reduces user mistakes. Next steps: - allow bpf_spin_lock in other map types (like cgroup local storage) - introduce BPF_F_LOCK flag for bpf_map_update() syscall and helper to request kernel to grab bpf_spin_lock before rewriting the value. That will serialize access to map elements. Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-02-01 07:40:04 +08:00
u32 active_spin_lock;
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
bool speculative;
bpf: precise scalar_value tracking Introduce precision tracking logic that helps cilium programs the most: old clang old clang new clang new clang with all patches with all patches bpf_lb-DLB_L3.o 1838 2283 1923 1863 bpf_lb-DLB_L4.o 3218 2657 3077 2468 bpf_lb-DUNKNOWN.o 1064 545 1062 544 bpf_lxc-DDROP_ALL.o 26935 23045 166729 22629 bpf_lxc-DUNKNOWN.o 34439 35240 174607 28805 bpf_netdev.o 9721 8753 8407 6801 bpf_overlay.o 6184 7901 5420 4754 bpf_lxc_jit.o 39389 50925 39389 50925 Consider code: 654: (85) call bpf_get_hash_recalc#34 655: (bf) r7 = r0 656: (15) if r8 == 0x0 goto pc+29 657: (bf) r2 = r10 658: (07) r2 += -48 659: (18) r1 = 0xffff8881e41e1b00 661: (85) call bpf_map_lookup_elem#1 662: (15) if r0 == 0x0 goto pc+23 663: (69) r1 = *(u16 *)(r0 +0) 664: (15) if r1 == 0x0 goto pc+21 665: (bf) r8 = r7 666: (57) r8 &= 65535 667: (bf) r2 = r8 668: (3f) r2 /= r1 669: (2f) r2 *= r1 670: (bf) r1 = r8 671: (1f) r1 -= r2 672: (57) r1 &= 255 673: (25) if r1 > 0x1e goto pc+12 R0=map_value(id=0,off=0,ks=20,vs=64,imm=0) R1_w=inv(id=0,umax_value=30,var_off=(0x0; 0x1f)) 674: (67) r1 <<= 1 675: (0f) r0 += r1 At this point the verifier will notice that scalar R1 is used in map pointer adjustment. R1 has to be precise for later operations on R0 to be validated properly. The verifier will backtrack the above code in the following way: last_idx 675 first_idx 664 regs=2 stack=0 before 675: (0f) r0 += r1 // started backtracking R1 regs=2 is a bitmask regs=2 stack=0 before 674: (67) r1 <<= 1 regs=2 stack=0 before 673: (25) if r1 > 0x1e goto pc+12 regs=2 stack=0 before 672: (57) r1 &= 255 regs=2 stack=0 before 671: (1f) r1 -= r2 // now both R1 and R2 has to be precise -> regs=6 mask regs=6 stack=0 before 670: (bf) r1 = r8 // after this insn R8 and R2 has to be precise regs=104 stack=0 before 669: (2f) r2 *= r1 // after this one R8, R2, and R1 regs=106 stack=0 before 668: (3f) r2 /= r1 regs=106 stack=0 before 667: (bf) r2 = r8 regs=102 stack=0 before 666: (57) r8 &= 65535 regs=102 stack=0 before 665: (bf) r8 = r7 regs=82 stack=0 before 664: (15) if r1 == 0x0 goto pc+21 // this is the end of verifier state. The following regs will be marked precised: R1_rw=invP(id=0,umax_value=65535,var_off=(0x0; 0xffff)) R7_rw=invP(id=0) parent didn't have regs=82 stack=0 marks // so backtracking continues into parent state last_idx 663 first_idx 655 regs=82 stack=0 before 663: (69) r1 = *(u16 *)(r0 +0) // R1 was assigned no need to track it further regs=80 stack=0 before 662: (15) if r0 == 0x0 goto pc+23 // keep tracking R7 regs=80 stack=0 before 661: (85) call bpf_map_lookup_elem#1 // keep tracking R7 regs=80 stack=0 before 659: (18) r1 = 0xffff8881e41e1b00 regs=80 stack=0 before 658: (07) r2 += -48 regs=80 stack=0 before 657: (bf) r2 = r10 regs=80 stack=0 before 656: (15) if r8 == 0x0 goto pc+29 regs=80 stack=0 before 655: (bf) r7 = r0 // here the assignment into R7 // mark R0 to be precise: R0_rw=invP(id=0) parent didn't have regs=1 stack=0 marks // regs=1 -> tracking R0 last_idx 654 first_idx 644 regs=1 stack=0 before 654: (85) call bpf_get_hash_recalc#34 // and in the parent frame it was a return value // nothing further to backtrack Two scalar registers not marked precise are equivalent from state pruning point of view. More details in the patch comments. It doesn't support bpf2bpf calls yet and enabled for root only. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-06-16 03:12:25 +08:00
/* first and last insn idx of this verifier state */
u32 first_insn_idx;
u32 last_insn_idx;
/* jmp history recorded from first to last.
* backtracking is using it to go from last to first.
* For most states jmp_history_cnt is [0-3].
* For loops can go up to ~40.
*/
struct bpf_idx_pair *jmp_history;
u32 jmp_history_cnt;
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
};
#define bpf_get_spilled_reg(slot, frame) \
(((slot < frame->allocated_stack / BPF_REG_SIZE) && \
(frame->stack[slot].slot_type[0] == STACK_SPILL)) \
? &frame->stack[slot].spilled_ptr : NULL)
/* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */
#define bpf_for_each_spilled_reg(iter, frame, reg) \
for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \
iter < frame->allocated_stack / BPF_REG_SIZE; \
iter++, reg = bpf_get_spilled_reg(iter, frame))
/* Invoke __expr over regsiters in __vst, setting __state and __reg */
#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \
({ \
struct bpf_verifier_state *___vstate = __vst; \
int ___i, ___j; \
for (___i = 0; ___i <= ___vstate->curframe; ___i++) { \
struct bpf_reg_state *___regs; \
__state = ___vstate->frame[___i]; \
___regs = __state->regs; \
for (___j = 0; ___j < MAX_BPF_REG; ___j++) { \
__reg = &___regs[___j]; \
(void)(__expr); \
} \
bpf_for_each_spilled_reg(___j, __state, __reg) { \
if (!__reg) \
continue; \
(void)(__expr); \
} \
} \
})
/* linked list of verifier states used to prune search */
struct bpf_verifier_state_list {
struct bpf_verifier_state state;
struct bpf_verifier_state_list *next;
bpf: improve verification speed by droping states Branch instructions, branch targets and calls in a bpf program are the places where the verifier remembers states that led to successful verification of the program. These states are used to prune brute force program analysis. For unprivileged programs there is a limit of 64 states per such 'branching' instructions (maximum length is tracked by max_states_per_insn counter introduced in the previous patch). Simply reducing this threshold to 32 or lower increases insn_processed metric to the point that small valid programs get rejected. For root programs there is no limit and cilium programs can have max_states_per_insn to be 100 or higher. Walking 100+ states multiplied by number of 'branching' insns during verification consumes significant amount of cpu time. Turned out simple LRU-like mechanism can be used to remove states that unlikely will be helpful in future search pruning. This patch introduces hit_cnt and miss_cnt counters: hit_cnt - this many times this state successfully pruned the search miss_cnt - this many times this state was not equivalent to other states (and that other states were added to state list) The heuristic introduced in this patch is: if (sl->miss_cnt > sl->hit_cnt * 3 + 3) /* drop this state from future considerations */ Higher numbers increase max_states_per_insn (allow more states to be considered for pruning) and slow verification speed, but do not meaningfully reduce insn_processed metric. Lower numbers drop too many states and insn_processed increases too much. Many different formulas were considered. This one is simple and works well enough in practice. (the analysis was done on selftests/progs/* and on cilium programs) The end result is this heuristic improves verification speed by 10 times. Large synthetic programs that used to take a second more now take 1/10 of a second. In cases where max_states_per_insn used to be 100 or more, now it's ~10. There is a slight increase in insn_processed for cilium progs: before after bpf_lb-DLB_L3.o 1831 1838 bpf_lb-DLB_L4.o 3029 3218 bpf_lb-DUNKNOWN.o 1064 1064 bpf_lxc-DDROP_ALL.o 26309 26935 bpf_lxc-DUNKNOWN.o 33517 34439 bpf_netdev.o 9713 9721 bpf_overlay.o 6184 6184 bpf_lcx_jit.o 37335 39389 And 2-3 times improvement in the verification speed. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-04-02 12:27:41 +08:00
int miss_cnt, hit_cnt;
};
struct bpf_loop_inline_state {
unsigned int initialized:1; /* set to true upon first entry */
unsigned int fit_for_inline:1; /* true if callback function is the same
* at each call and flags are always zero
*/
u32 callback_subprogno; /* valid when fit_for_inline is true */
};
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
/* Possible states for alu_state member. */
bpf: Fix leakage of uninitialized bpf stack under speculation The current implemented mechanisms to mitigate data disclosure under speculation mainly address stack and map value oob access from the speculative domain. However, Piotr discovered that uninitialized BPF stack is not protected yet, and thus old data from the kernel stack, potentially including addresses of kernel structures, could still be extracted from that 512 bytes large window. The BPF stack is special compared to map values since it's not zero initialized for every program invocation, whereas map values /are/ zero initialized upon their initial allocation and thus cannot leak any prior data in either domain. In the non-speculative domain, the verifier ensures that every stack slot read must have a prior stack slot write by the BPF program to avoid such data leaking issue. However, this is not enough: for example, when the pointer arithmetic operation moves the stack pointer from the last valid stack offset to the first valid offset, the sanitation logic allows for any intermediate offsets during speculative execution, which could then be used to extract any restricted stack content via side-channel. Given for unprivileged stack pointer arithmetic the use of unknown but bounded scalars is generally forbidden, we can simply turn the register-based arithmetic operation into an immediate-based arithmetic operation without the need for masking. This also gives the benefit of reducing the needed instructions for the operation. Given after the work in 7fedb63a8307 ("bpf: Tighten speculative pointer arithmetic mask"), the aux->alu_limit already holds the final immediate value for the offset register with the known scalar. Thus, a simple mov of the immediate to AX register with using AX as the source for the original instruction is sufficient and possible now in this case. Reported-by: Piotr Krysiuk <piotras@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Piotr Krysiuk <piotras@gmail.com> Reviewed-by: Piotr Krysiuk <piotras@gmail.com> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Alexei Starovoitov <ast@kernel.org>
2021-04-29 23:19:37 +08:00
#define BPF_ALU_SANITIZE_SRC (1U << 0)
#define BPF_ALU_SANITIZE_DST (1U << 1)
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
#define BPF_ALU_NEG_VALUE (1U << 2)
#define BPF_ALU_NON_POINTER (1U << 3)
bpf: Fix leakage of uninitialized bpf stack under speculation The current implemented mechanisms to mitigate data disclosure under speculation mainly address stack and map value oob access from the speculative domain. However, Piotr discovered that uninitialized BPF stack is not protected yet, and thus old data from the kernel stack, potentially including addresses of kernel structures, could still be extracted from that 512 bytes large window. The BPF stack is special compared to map values since it's not zero initialized for every program invocation, whereas map values /are/ zero initialized upon their initial allocation and thus cannot leak any prior data in either domain. In the non-speculative domain, the verifier ensures that every stack slot read must have a prior stack slot write by the BPF program to avoid such data leaking issue. However, this is not enough: for example, when the pointer arithmetic operation moves the stack pointer from the last valid stack offset to the first valid offset, the sanitation logic allows for any intermediate offsets during speculative execution, which could then be used to extract any restricted stack content via side-channel. Given for unprivileged stack pointer arithmetic the use of unknown but bounded scalars is generally forbidden, we can simply turn the register-based arithmetic operation into an immediate-based arithmetic operation without the need for masking. This also gives the benefit of reducing the needed instructions for the operation. Given after the work in 7fedb63a8307 ("bpf: Tighten speculative pointer arithmetic mask"), the aux->alu_limit already holds the final immediate value for the offset register with the known scalar. Thus, a simple mov of the immediate to AX register with using AX as the source for the original instruction is sufficient and possible now in this case. Reported-by: Piotr Krysiuk <piotras@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Piotr Krysiuk <piotras@gmail.com> Reviewed-by: Piotr Krysiuk <piotras@gmail.com> Reviewed-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Alexei Starovoitov <ast@kernel.org>
2021-04-29 23:19:37 +08:00
#define BPF_ALU_IMMEDIATE (1U << 4)
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
#define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \
BPF_ALU_SANITIZE_DST)
struct bpf_insn_aux_data {
union {
enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
bpf: Constant map key tracking for prog array pokes Add tracking of constant keys into tail call maps. The signature of bpf_tail_call_proto is that arg1 is ctx, arg2 map pointer and arg3 is a index key. The direct call approach for tail calls can be enabled if the verifier asserted that for all branches leading to the tail call helper invocation, the map pointer and index key were both constant and the same. Tracking of map pointers we already do from prior work via c93552c443eb ("bpf: properly enforce index mask to prevent out-of-bounds speculation") and 09772d92cd5a ("bpf: avoid retpoline for lookup/update/ delete calls on maps"). Given the tail call map index key is not on stack but directly in the register, we can add similar tracking approach and later in fixup_bpf_calls() add a poke descriptor to the progs poke_tab with the relevant information for the JITing phase. We internally reuse insn->imm for the rewritten BPF_JMP | BPF_TAIL_CALL instruction in order to point into the prog's poke_tab, and keep insn->imm as 0 as indicator that current indirect tail call emission must be used. Note that publishing to the tracker must happen at the end of fixup_bpf_calls() since adding elements to the poke_tab reallocates its memory, so we need to wait until its in final state. Future work can generalize and add similar approach to optimize plain array map lookups. Difference there is that we need to look into the key value that sits on stack. For clarity in bpf_insn_aux_data, map_state has been renamed into map_ptr_state, so we get map_{ptr,key}_state as trackers. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/e8db37f6b2ae60402fa40216c96738ee9b316c32.1574452833.git.daniel@iogearbox.net
2019-11-23 04:07:59 +08:00
unsigned long map_ptr_state; /* pointer/poison value for maps */
bpf: x64: add JIT support for multi-function programs Typical JIT does several passes over bpf instructions to compute total size and relative offsets of jumps and calls. With multitple bpf functions calling each other all relative calls will have invalid offsets intially therefore we need to additional last pass over the program to emit calls with correct offsets. For example in case of three bpf functions: main: call foo call bpf_map_lookup exit foo: call bar exit bar: exit We will call bpf_int_jit_compile() indepedently for main(), foo() and bar() x64 JIT typically does 4-5 passes to converge. After these initial passes the image for these 3 functions will be good except call targets, since start addresses of foo() and bar() are unknown when we were JITing main() (note that call bpf_map_lookup will be resolved properly during initial passes). Once start addresses of 3 functions are known we patch call_insn->imm to point to right functions and call bpf_int_jit_compile() again which needs only one pass. Additional safety checks are done to make sure this last pass doesn't produce image that is larger or smaller than previous pass. When constant blinding is on it's applied to all functions at the first pass, since doing it once again at the last pass can change size of the JITed code. Tested on x64 and arm64 hw with JIT on/off, blinding on/off. x64 jits bpf-to-bpf calls correctly while arm64 falls back to interpreter. All other JITs that support normal BPF_CALL will behave the same way since bpf-to-bpf call is equivalent to bpf-to-kernel call from JITs point of view. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:15 +08:00
s32 call_imm; /* saved imm field of call insn */
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
u32 alu_limit; /* limit for add/sub register with pointer */
bpf: implement lookup-free direct value access for maps This generic extension to BPF maps allows for directly loading an address residing inside a BPF map value as a single BPF ldimm64 instruction! The idea is similar to what BPF_PSEUDO_MAP_FD does today, which is a special src_reg flag for ldimm64 instruction that indicates that inside the first part of the double insns's imm field is a file descriptor which the verifier then replaces as a full 64bit address of the map into both imm parts. For the newly added BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following: the first part of the double insns's imm field is again a file descriptor corresponding to the map, and the second part of the imm field is an offset into the value. The verifier will then replace both imm parts with an address that points into the BPF map value at the given value offset for maps that support this operation. Currently supported is array map with single entry. It is possible to support more than just single map element by reusing both 16bit off fields of the insns as a map index, so full array map lookup could be expressed that way. It hasn't been implemented here due to lack of concrete use case, but could easily be done so in future in a compatible way, since both off fields right now have to be 0 and would correctly denote a map index 0. The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of map pointer versus load of map's value at offset 0, and changing BPF_PSEUDO_MAP_FD's encoding into off by one to differ between regular map pointer and map value pointer would add unnecessary complexity and increases barrier for debugability thus less suitable. Using the second part of the imm field as an offset into the value does /not/ come with limitations since maximum possible value size is in u32 universe anyway. This optimization allows for efficiently retrieving an address to a map value memory area without having to issue a helper call which needs to prepare registers according to calling convention, etc, without needing the extra NULL test, and without having to add the offset in an additional instruction to the value base pointer. The verifier then treats the destination register as PTR_TO_MAP_VALUE with constant reg->off from the user passed offset from the second imm field, and guarantees that this is within bounds of the map value. Any subsequent operations are normally treated as typical map value handling without anything extra needed from verification side. The two map operations for direct value access have been added to array map for now. In future other types could be supported as well depending on the use case. The main use case for this commit is to allow for BPF loader support for global variables that reside in .data/.rodata/.bss sections such that we can directly load the address of them with minimal additional infrastructure required. Loader support has been added in subsequent commits for libbpf library. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:03 +08:00
struct {
u32 map_index; /* index into used_maps[] */
u32 map_off; /* offset from value base address */
};
struct {
enum bpf_reg_type reg_type; /* type of pseudo_btf_id */
union {
struct {
struct btf *btf;
u32 btf_id; /* btf_id for struct typed var */
};
u32 mem_size; /* mem_size for non-struct typed var */
};
} btf_var;
/* if instruction is a call to bpf_loop this field tracks
* the state of the relevant registers to make decision about inlining
*/
struct bpf_loop_inline_state loop_inline_state;
};
bpf: Constant map key tracking for prog array pokes Add tracking of constant keys into tail call maps. The signature of bpf_tail_call_proto is that arg1 is ctx, arg2 map pointer and arg3 is a index key. The direct call approach for tail calls can be enabled if the verifier asserted that for all branches leading to the tail call helper invocation, the map pointer and index key were both constant and the same. Tracking of map pointers we already do from prior work via c93552c443eb ("bpf: properly enforce index mask to prevent out-of-bounds speculation") and 09772d92cd5a ("bpf: avoid retpoline for lookup/update/ delete calls on maps"). Given the tail call map index key is not on stack but directly in the register, we can add similar tracking approach and later in fixup_bpf_calls() add a poke descriptor to the progs poke_tab with the relevant information for the JITing phase. We internally reuse insn->imm for the rewritten BPF_JMP | BPF_TAIL_CALL instruction in order to point into the prog's poke_tab, and keep insn->imm as 0 as indicator that current indirect tail call emission must be used. Note that publishing to the tracker must happen at the end of fixup_bpf_calls() since adding elements to the poke_tab reallocates its memory, so we need to wait until its in final state. Future work can generalize and add similar approach to optimize plain array map lookups. Difference there is that we need to look into the key value that sits on stack. For clarity in bpf_insn_aux_data, map_state has been renamed into map_ptr_state, so we get map_{ptr,key}_state as trackers. Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/e8db37f6b2ae60402fa40216c96738ee9b316c32.1574452833.git.daniel@iogearbox.net
2019-11-23 04:07:59 +08:00
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
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 14:41:20 +08:00
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
bpf: Fix leakage due to insufficient speculative store bypass mitigation Spectre v4 gadgets make use of memory disambiguation, which is a set of techniques that execute memory access instructions, that is, loads and stores, out of program order; Intel's optimization manual, section 2.4.4.5: A load instruction micro-op may depend on a preceding store. Many microarchitectures block loads until all preceding store addresses are known. The memory disambiguator predicts which loads will not depend on any previous stores. When the disambiguator predicts that a load does not have such a dependency, the load takes its data from the L1 data cache. Eventually, the prediction is verified. If an actual conflict is detected, the load and all succeeding instructions are re-executed. af86ca4e3088 ("bpf: Prevent memory disambiguation attack") tried to mitigate this attack by sanitizing the memory locations through preemptive "fast" (low latency) stores of zero prior to the actual "slow" (high latency) store of a pointer value such that upon dependency misprediction the CPU then speculatively executes the load of the pointer value and retrieves the zero value instead of the attacker controlled scalar value previously stored at that location, meaning, subsequent access in the speculative domain is then redirected to the "zero page". The sanitized preemptive store of zero prior to the actual "slow" store is done through a simple ST instruction based on r10 (frame pointer) with relative offset to the stack location that the verifier has been tracking on the original used register for STX, which does not have to be r10. Thus, there are no memory dependencies for this store, since it's only using r10 and immediate constant of zero; hence af86ca4e3088 /assumed/ a low latency operation. However, a recent attack demonstrated that this mitigation is not sufficient since the preemptive store of zero could also be turned into a "slow" store and is thus bypassed as well: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value 31: (7b) *(u64 *)(r10 -16) = r2 // r9 will remain "fast" register, r10 will become "slow" register below 32: (bf) r9 = r10 // JIT maps BPF reg to x86 reg: // r9 -> r15 (callee saved) // r10 -> rbp // train store forward prediction to break dependency link between both r9 // and r10 by evicting them from the predictor's LRU table. 33: (61) r0 = *(u32 *)(r7 +24576) 34: (63) *(u32 *)(r7 +29696) = r0 35: (61) r0 = *(u32 *)(r7 +24580) 36: (63) *(u32 *)(r7 +29700) = r0 37: (61) r0 = *(u32 *)(r7 +24584) 38: (63) *(u32 *)(r7 +29704) = r0 39: (61) r0 = *(u32 *)(r7 +24588) 40: (63) *(u32 *)(r7 +29708) = r0 [...] 543: (61) r0 = *(u32 *)(r7 +25596) 544: (63) *(u32 *)(r7 +30716) = r0 // prepare call to bpf_ringbuf_output() helper. the latter will cause rbp // to spill to stack memory while r13/r14/r15 (all callee saved regs) remain // in hardware registers. rbp becomes slow due to push/pop latency. below is // disasm of bpf_ringbuf_output() helper for better visual context: // // ffffffff8117ee20: 41 54 push r12 // ffffffff8117ee22: 55 push rbp // ffffffff8117ee23: 53 push rbx // ffffffff8117ee24: 48 f7 c1 fc ff ff ff test rcx,0xfffffffffffffffc // ffffffff8117ee2b: 0f 85 af 00 00 00 jne ffffffff8117eee0 <-- jump taken // [...] // ffffffff8117eee0: 49 c7 c4 ea ff ff ff mov r12,0xffffffffffffffea // ffffffff8117eee7: 5b pop rbx // ffffffff8117eee8: 5d pop rbp // ffffffff8117eee9: 4c 89 e0 mov rax,r12 // ffffffff8117eeec: 41 5c pop r12 // ffffffff8117eeee: c3 ret 545: (18) r1 = map[id:4] 547: (bf) r2 = r7 548: (b7) r3 = 0 549: (b7) r4 = 4 550: (85) call bpf_ringbuf_output#194288 // instruction 551 inserted by verifier \ 551: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here // storing map value pointer r7 at fp-16 | since value of r10 is "slow". 552: (7b) *(u64 *)(r10 -16) = r7 / // following "fast" read to the same memory location, but due to dependency // misprediction it will speculatively execute before insn 551/552 completes. 553: (79) r2 = *(u64 *)(r9 -16) // in speculative domain contains attacker controlled r2. in non-speculative // domain this contains r7, and thus accesses r7 +0 below. 554: (71) r3 = *(u8 *)(r2 +0) // leak r3 As can be seen, the current speculative store bypass mitigation which the verifier inserts at line 551 is insufficient since /both/, the write of the zero sanitation as well as the map value pointer are a high latency instruction due to prior memory access via push/pop of r10 (rbp) in contrast to the low latency read in line 553 as r9 (r15) which stays in hardware registers. Thus, architecturally, fp-16 is r7, however, microarchitecturally, fp-16 can still be r2. Initial thoughts to address this issue was to track spilled pointer loads from stack and enforce their load via LDX through r10 as well so that /both/ the preemptive store of zero /as well as/ the load use the /same/ register such that a dependency is created between the store and load. However, this option is not sufficient either since it can be bypassed as well under speculation. An updated attack with pointer spill/fills now _all_ based on r10 would look as follows: [...] // r2 = oob address (e.g. scalar) // r7 = pointer to map value [...] // longer store forward prediction training sequence than before. 2062: (61) r0 = *(u32 *)(r7 +25588) 2063: (63) *(u32 *)(r7 +30708) = r0 2064: (61) r0 = *(u32 *)(r7 +25592) 2065: (63) *(u32 *)(r7 +30712) = r0 2066: (61) r0 = *(u32 *)(r7 +25596) 2067: (63) *(u32 *)(r7 +30716) = r0 // store the speculative load address (scalar) this time after the store // forward prediction training. 2068: (7b) *(u64 *)(r10 -16) = r2 // preoccupy the CPU store port by running sequence of dummy stores. 2069: (63) *(u32 *)(r7 +29696) = r0 2070: (63) *(u32 *)(r7 +29700) = r0 2071: (63) *(u32 *)(r7 +29704) = r0 2072: (63) *(u32 *)(r7 +29708) = r0 2073: (63) *(u32 *)(r7 +29712) = r0 2074: (63) *(u32 *)(r7 +29716) = r0 2075: (63) *(u32 *)(r7 +29720) = r0 2076: (63) *(u32 *)(r7 +29724) = r0 2077: (63) *(u32 *)(r7 +29728) = r0 2078: (63) *(u32 *)(r7 +29732) = r0 2079: (63) *(u32 *)(r7 +29736) = r0 2080: (63) *(u32 *)(r7 +29740) = r0 2081: (63) *(u32 *)(r7 +29744) = r0 2082: (63) *(u32 *)(r7 +29748) = r0 2083: (63) *(u32 *)(r7 +29752) = r0 2084: (63) *(u32 *)(r7 +29756) = r0 2085: (63) *(u32 *)(r7 +29760) = r0 2086: (63) *(u32 *)(r7 +29764) = r0 2087: (63) *(u32 *)(r7 +29768) = r0 2088: (63) *(u32 *)(r7 +29772) = r0 2089: (63) *(u32 *)(r7 +29776) = r0 2090: (63) *(u32 *)(r7 +29780) = r0 2091: (63) *(u32 *)(r7 +29784) = r0 2092: (63) *(u32 *)(r7 +29788) = r0 2093: (63) *(u32 *)(r7 +29792) = r0 2094: (63) *(u32 *)(r7 +29796) = r0 2095: (63) *(u32 *)(r7 +29800) = r0 2096: (63) *(u32 *)(r7 +29804) = r0 2097: (63) *(u32 *)(r7 +29808) = r0 2098: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; same as before, also including the // sanitation store with 0 from the current mitigation by the verifier. 2099: (7a) *(u64 *)(r10 -16) = 0 | /both/ are now slow stores here 2100: (7b) *(u64 *)(r10 -16) = r7 | since store unit is still busy. // load from stack intended to bypass stores. 2101: (79) r2 = *(u64 *)(r10 -16) 2102: (71) r3 = *(u8 *)(r2 +0) // leak r3 [...] Looking at the CPU microarchitecture, the scheduler might issue loads (such as seen in line 2101) before stores (line 2099,2100) because the load execution units become available while the store execution unit is still busy with the sequence of dummy stores (line 2069-2098). And so the load may use the prior stored scalar from r2 at address r10 -16 for speculation. The updated attack may work less reliable on CPU microarchitectures where loads and stores share execution resources. This concludes that the sanitizing with zero stores from af86ca4e3088 ("bpf: Prevent memory disambiguation attack") is insufficient. Moreover, the detection of stack reuse from af86ca4e3088 where previously data (STACK_MISC) has been written to a given stack slot where a pointer value is now to be stored does not have sufficient coverage as precondition for the mitigation either; for several reasons outlined as follows: 1) Stack content from prior program runs could still be preserved and is therefore not "random", best example is to split a speculative store bypass attack between tail calls, program A would prepare and store the oob address at a given stack slot and then tail call into program B which does the "slow" store of a pointer to the stack with subsequent "fast" read. From program B PoV such stack slot type is STACK_INVALID, and therefore also must be subject to mitigation. 2) The STACK_SPILL must not be coupled to register_is_const(&stack->spilled_ptr) condition, for example, the previous content of that memory location could also be a pointer to map or map value. Without the fix, a speculative store bypass is not mitigated in such precondition and can then lead to a type confusion in the speculative domain leaking kernel memory near these pointer types. While brainstorming on various alternative mitigation possibilities, we also stumbled upon a retrospective from Chrome developers [0]: [...] For variant 4, we implemented a mitigation to zero the unused memory of the heap prior to allocation, which cost about 1% when done concurrently and 4% for scavenging. Variant 4 defeats everything we could think of. We explored more mitigations for variant 4 but the threat proved to be more pervasive and dangerous than we anticipated. For example, stack slots used by the register allocator in the optimizing compiler could be subject to type confusion, leading to pointer crafting. Mitigating type confusion for stack slots alone would have required a complete redesign of the backend of the optimizing compiler, perhaps man years of work, without a guarantee of completeness. [...] From BPF side, the problem space is reduced, however, options are rather limited. One idea that has been explored was to xor-obfuscate pointer spills to the BPF stack: [...] // preoccupy the CPU store port by running sequence of dummy stores. [...] 2106: (63) *(u32 *)(r7 +29796) = r0 2107: (63) *(u32 *)(r7 +29800) = r0 2108: (63) *(u32 *)(r7 +29804) = r0 2109: (63) *(u32 *)(r7 +29808) = r0 2110: (63) *(u32 *)(r7 +29812) = r0 // overwrite scalar with dummy pointer; xored with random 'secret' value // of 943576462 before store ... 2111: (b4) w11 = 943576462 2112: (af) r11 ^= r7 2113: (7b) *(u64 *)(r10 -16) = r11 2114: (79) r11 = *(u64 *)(r10 -16) 2115: (b4) w2 = 943576462 2116: (af) r2 ^= r11 // ... and restored with the same 'secret' value with the help of AX reg. 2117: (71) r3 = *(u8 *)(r2 +0) [...] While the above would not prevent speculation, it would make data leakage infeasible by directing it to random locations. In order to be effective and prevent type confusion under speculation, such random secret would have to be regenerated for each store. The additional complexity involved for a tracking mechanism that prevents jumps such that restoring spilled pointers would not get corrupted is not worth the gain for unprivileged. Hence, the fix in here eventually opted for emitting a non-public BPF_ST | BPF_NOSPEC instruction which the x86 JIT translates into a lfence opcode. Inserting the latter in between the store and load instruction is one of the mitigations options [1]. The x86 instruction manual notes: [...] An LFENCE that follows an instruction that stores to memory might complete before the data being stored have become globally visible. [...] The latter meaning that the preceding store instruction finished execution and the store is at minimum guaranteed to be in the CPU's store queue, but it's not guaranteed to be in that CPU's L1 cache at that point (globally visible). The latter would only be guaranteed via sfence. So the load which is guaranteed to execute after the lfence for that local CPU would have to rely on store-to-load forwarding. [2], in section 2.3 on store buffers says: [...] For every store operation that is added to the ROB, an entry is allocated in the store buffer. This entry requires both the virtual and physical address of the target. Only if there is no free entry in the store buffer, the frontend stalls until there is an empty slot available in the store buffer again. Otherwise, the CPU can immediately continue adding subsequent instructions to the ROB and execute them out of order. On Intel CPUs, the store buffer has up to 56 entries. [...] One small upside on the fix is that it lifts constraints from af86ca4e3088 where the sanitize_stack_off relative to r10 must be the same when coming from different paths. The BPF_ST | BPF_NOSPEC gets emitted after a BPF_STX or BPF_ST instruction. This happens either when we store a pointer or data value to the BPF stack for the first time, or upon later pointer spills. The former needs to be enforced since otherwise stale stack data could be leaked under speculation as outlined earlier. For non-x86 JITs the BPF_ST | BPF_NOSPEC mapping is currently optimized away, but others could emit a speculation barrier as well if necessary. For real-world unprivileged programs e.g. generated by LLVM, pointer spill/fill is only generated upon register pressure and LLVM only tries to do that for pointers which are not used often. The program main impact will be the initial BPF_ST | BPF_NOSPEC sanitation for the STACK_INVALID case when the first write to a stack slot occurs e.g. upon map lookup. In future we might refine ways to mitigate the latter cost. [0] https://arxiv.org/pdf/1902.05178.pdf [1] https://msrc-blog.microsoft.com/2018/05/21/analysis-and-mitigation-of-speculative-store-bypass-cve-2018-3639/ [2] https://arxiv.org/pdf/1905.05725.pdf Fixes: af86ca4e3088 ("bpf: Prevent memory disambiguation attack") Fixes: f7cf25b2026d ("bpf: track spill/fill of constants") Co-developed-by: Piotr Krysiuk <piotras@gmail.com> Co-developed-by: Benedict Schlueter <benedict.schlueter@rub.de> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Piotr Krysiuk <piotras@gmail.com> Signed-off-by: Benedict Schlueter <benedict.schlueter@rub.de> Acked-by: Alexei Starovoitov <ast@kernel.org>
2021-07-13 16:18:31 +08:00
bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
bpf: verifier: mark verified-insn with sub-register zext flag eBPF ISA specification requires high 32-bit cleared when low 32-bit sub-register is written. This applies to destination register of ALU32 etc. JIT back-ends must guarantee this semantic when doing code-gen. x86_64 and AArch64 ISA has the same semantics, so the corresponding JIT back-end doesn't need to do extra work. However, 32-bit arches (arm, x86, nfp etc.) and some other 64-bit arches (PowerPC, SPARC etc) need to do explicit zero extension to meet this requirement, otherwise code like the following will fail. u64_value = (u64) u32_value ... other uses of u64_value This is because compiler could exploit the semantic described above and save those zero extensions for extending u32_value to u64_value, these JIT back-ends are expected to guarantee this through inserting extra zero extensions which however could be a significant increase on the code size. Some benchmarks show there could be ~40% sub-register writes out of total insns, meaning at least ~40% extra code-gen. One observation is these extra zero extensions are not always necessary. Take above code snippet for example, it is possible u32_value will never be casted into a u64, the value of high 32-bit of u32_value then could be ignored and extra zero extension could be eliminated. This patch implements this idea, insns defining sub-registers will be marked when the high 32-bit of the defined sub-register matters. For those unmarked insns, it is safe to eliminate high 32-bit clearnace for them. Algo: - Split read flags into READ32 and READ64. - Record index of insn that does sub-register write. Keep the index inside reg state and update it during verifier insn walking. - A full register read on a sub-register marks its definition insn as needing zero extension on dst register. A new sub-register write overrides the old one. - When propagating read64 during path pruning, also mark any insn defining a sub-register that is read in the pruned path as full-register. 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 06:25:12 +08:00
bool zext_dst; /* this insn zero extends dst reg */
bpf: prevent out of bounds speculation on pointer arithmetic Jann reported that the original commit back in b2157399cc98 ("bpf: prevent out-of-bounds speculation") was not sufficient to stop CPU from speculating out of bounds memory access: While b2157399cc98 only focussed on masking array map access for unprivileged users for tail calls and data access such that the user provided index gets sanitized from BPF program and syscall side, there is still a more generic form affected from BPF programs that applies to most maps that hold user data in relation to dynamic map access when dealing with unknown scalars or "slow" known scalars as access offset, for example: - Load a map value pointer into R6 - Load an index into R7 - Do a slow computation (e.g. with a memory dependency) that loads a limit into R8 (e.g. load the limit from a map for high latency, then mask it to make the verifier happy) - Exit if R7 >= R8 (mispredicted branch) - Load R0 = R6[R7] - Load R0 = R6[R0] For unknown scalars there are two options in the BPF verifier where we could derive knowledge from in order to guarantee safe access to the memory: i) While </>/<=/>= variants won't allow to derive any lower or upper bounds from the unknown scalar where it would be safe to add it to the map value pointer, it is possible through ==/!= test however. ii) another option is to transform the unknown scalar into a known scalar, for example, through ALU ops combination such as R &= <imm> followed by R |= <imm> or any similar combination where the original information from the unknown scalar would be destroyed entirely leaving R with a constant. The initial slow load still precedes the latter ALU ops on that register, so the CPU executes speculatively from that point. Once we have the known scalar, any compare operation would work then. A third option only involving registers with known scalars could be crafted as described in [0] where a CPU port (e.g. Slow Int unit) would be filled with many dependent computations such that the subsequent condition depending on its outcome has to wait for evaluation on its execution port and thereby executing speculatively if the speculated code can be scheduled on a different execution port, or any other form of mistraining as described in [1], for example. Given this is not limited to only unknown scalars, not only map but also stack access is affected since both is accessible for unprivileged users and could potentially be used for out of bounds access under speculation. In order to prevent any of these cases, the verifier is now sanitizing pointer arithmetic on the offset such that any out of bounds speculation would be masked in a way where the pointer arithmetic result in the destination register will stay unchanged, meaning offset masked into zero similar as in array_index_nospec() case. With regards to implementation, there are three options that were considered: i) new insn for sanitation, ii) push/pop insn and sanitation as inlined BPF, iii) reuse of ax register and sanitation as inlined BPF. Option i) has the downside that we end up using from reserved bits in the opcode space, but also that we would require each JIT to emit masking as native arch opcodes meaning mitigation would have slow adoption till everyone implements it eventually which is counter-productive. Option ii) and iii) have both in common that a temporary register is needed in order to implement the sanitation as inlined BPF since we are not allowed to modify the source register. While a push / pop insn in ii) would be useful to have in any case, it requires once again that every JIT needs to implement it first. While possible, amount of changes needed would also be unsuitable for a -stable patch. Therefore, the path which has fewer changes, less BPF instructions for the mitigation and does not require anything to be changed in the JITs is option iii) which this work is pursuing. The ax register is already mapped to a register in all JITs (modulo arm32 where it's mapped to stack as various other BPF registers there) and used in constant blinding for JITs-only so far. It can be reused for verifier rewrites under certain constraints. The interpreter's tmp "register" has therefore been remapped into extending the register set with hidden ax register and reusing that for a number of instructions that needed the prior temporary variable internally (e.g. div, mod). This allows for zero increase in stack space usage in the interpreter, and enables (restricted) generic use in rewrites otherwise as long as such a patchlet does not make use of these instructions. The sanitation mask is dynamic and relative to the offset the map value or stack pointer currently holds. There are various cases that need to be taken under consideration for the masking, e.g. such operation could look as follows: ptr += val or val += ptr or ptr -= val. Thus, the value to be sanitized could reside either in source or in destination register, and the limit is different depending on whether the ALU op is addition or subtraction and depending on the current known and bounded offset. The limit is derived as follows: limit := max_value_size - (smin_value + off). For subtraction: limit := umax_value + off. This holds because we do not allow any pointer arithmetic that would temporarily go out of bounds or would have an unknown value with mixed signed bounds where it is unclear at verification time whether the actual runtime value would be either negative or positive. For example, we have a derived map pointer value with constant offset and bounded one, so limit based on smin_value works because the verifier requires that statically analyzed arithmetic on the pointer must be in bounds, and thus it checks if resulting smin_value + off and umax_value + off is still within map value bounds at time of arithmetic in addition to time of access. Similarly, for the case of stack access we derive the limit as follows: MAX_BPF_STACK + off for subtraction and -off for the case of addition where off := ptr_reg->off + ptr_reg->var_off.value. Subtraction is a special case for the masking which can be in form of ptr += -val, ptr -= -val, or ptr -= val. In the first two cases where we know that the value is negative, we need to temporarily negate the value in order to do the sanitation on a positive value where we later swap the ALU op, and restore original source register if the value was in source. The sanitation of pointer arithmetic alone is still not fully sufficient as is, since a scenario like the following could happen ... PTR += 0x1000 (e.g. K-based imm) PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON PTR += 0x1000 PTR -= BIG_NUMBER_WITH_SLOW_COMPARISON [...] ... which under speculation could end up as ... PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] PTR += 0x1000 PTR -= 0 [ truncated by mitigation ] [...] ... and therefore still access out of bounds. To prevent such case, the verifier is also analyzing safety for potential out of bounds access under speculative execution. Meaning, it is also simulating pointer access under truncation. We therefore "branch off" and push the current verification state after the ALU operation with known 0 to the verification stack for later analysis. Given the current path analysis succeeded it is likely that the one under speculation can be pruned. In any case, it is also subject to existing complexity limits and therefore anything beyond this point will be rejected. In terms of pruning, it needs to be ensured that the verification state from speculative execution simulation must never prune a non-speculative execution path, therefore, we mark verifier state accordingly at the time of push_stack(). If verifier detects out of bounds access under speculative execution from one of the possible paths that includes a truncation, it will reject such program. Given we mask every reg-based pointer arithmetic for unprivileged programs, we've been looking into how it could affect real-world programs in terms of size increase. As the majority of programs are targeted for privileged-only use case, we've unconditionally enabled masking (with its alu restrictions on top of it) for privileged programs for the sake of testing in order to check i) whether they get rejected in its current form, and ii) by how much the number of instructions and size will increase. We've tested this by using Katran, Cilium and test_l4lb from the kernel selftests. For Katran we've evaluated balancer_kern.o, Cilium bpf_lxc.o and an older test object bpf_lxc_opt_-DUNKNOWN.o and l4lb we've used test_l4lb.o as well as test_l4lb_noinline.o. We found that none of the programs got rejected by the verifier with this change, and that impact is rather minimal to none. balancer_kern.o had 13,904 bytes (1,738 insns) xlated and 7,797 bytes JITed before and after the change. Most complex program in bpf_lxc.o had 30,544 bytes (3,817 insns) xlated and 18,538 bytes JITed before and after and none of the other tail call programs in bpf_lxc.o had any changes either. For the older bpf_lxc_opt_-DUNKNOWN.o object we found a small increase from 20,616 bytes (2,576 insns) and 12,536 bytes JITed before to 20,664 bytes (2,582 insns) and 12,558 bytes JITed after the change. Other programs from that object file had similar small increase. Both test_l4lb.o had no change and remained at 6,544 bytes (817 insns) xlated and 3,401 bytes JITed and for test_l4lb_noinline.o constant at 5,080 bytes (634 insns) xlated and 3,313 bytes JITed. This can be explained in that LLVM typically optimizes stack based pointer arithmetic by using K-based operations and that use of dynamic map access is not overly frequent. However, in future we may decide to optimize the algorithm further under known guarantees from branch and value speculation. Latter seems also unclear in terms of prediction heuristics that today's CPUs apply as well as whether there could be collisions in e.g. the predictor's Value History/Pattern Table for triggering out of bounds access, thus masking is performed unconditionally at this point but could be subject to relaxation later on. We were generally also brainstorming various other approaches for mitigation, but the blocker was always lack of available registers at runtime and/or overhead for runtime tracking of limits belonging to a specific pointer. Thus, we found this to be minimally intrusive under given constraints. With that in place, a simple example with sanitized access on unprivileged load at post-verification time looks as follows: # bpftool prog dump xlated id 282 [...] 28: (79) r1 = *(u64 *)(r7 +0) 29: (79) r2 = *(u64 *)(r7 +8) 30: (57) r1 &= 15 31: (79) r3 = *(u64 *)(r0 +4608) 32: (57) r3 &= 1 33: (47) r3 |= 1 34: (2d) if r2 > r3 goto pc+19 35: (b4) (u32) r11 = (u32) 20479 | 36: (1f) r11 -= r2 | Dynamic sanitation for pointer 37: (4f) r11 |= r2 | arithmetic with registers 38: (87) r11 = -r11 | containing bounded or known 39: (c7) r11 s>>= 63 | scalars in order to prevent 40: (5f) r11 &= r2 | out of bounds speculation. 41: (0f) r4 += r11 | 42: (71) r4 = *(u8 *)(r4 +0) 43: (6f) r4 <<= r1 [...] For the case where the scalar sits in the destination register as opposed to the source register, the following code is emitted for the above example: [...] 16: (b4) (u32) r11 = (u32) 20479 17: (1f) r11 -= r2 18: (4f) r11 |= r2 19: (87) r11 = -r11 20: (c7) r11 s>>= 63 21: (5f) r2 &= r11 22: (0f) r2 += r0 23: (61) r0 = *(u32 *)(r2 +0) [...] JIT blinding example with non-conflicting use of r10: [...] d5: je 0x0000000000000106 _ d7: mov 0x0(%rax),%edi | da: mov $0xf153246,%r10d | Index load from map value and e0: xor $0xf153259,%r10 | (const blinded) mask with 0x1f. e7: and %r10,%rdi |_ ea: mov $0x2f,%r10d | f0: sub %rdi,%r10 | Sanitized addition. Both use r10 f3: or %rdi,%r10 | but do not interfere with each f6: neg %r10 | other. (Neither do these instructions f9: sar $0x3f,%r10 | interfere with the use of ax as temp fd: and %r10,%rdi | in interpreter.) 100: add %rax,%rdi |_ 103: mov 0x0(%rdi),%eax [...] Tested that it fixes Jann's reproducer, and also checked that test_verifier and test_progs suite with interpreter, JIT and JIT with hardening enabled on x86-64 and arm64 runs successfully. [0] Speculose: Analyzing the Security Implications of Speculative Execution in CPUs, Giorgi Maisuradze and Christian Rossow, https://arxiv.org/pdf/1801.04084.pdf [1] A Systematic Evaluation of Transient Execution Attacks and Defenses, Claudio Canella, Jo Van Bulck, Michael Schwarz, Moritz Lipp, Benjamin von Berg, Philipp Ortner, Frank Piessens, Dmitry Evtyushkin, Daniel Gruss, https://arxiv.org/pdf/1811.05441.pdf Fixes: b2157399cc98 ("bpf: prevent out-of-bounds speculation") Reported-by: Jann Horn <jannh@google.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-01-03 07:58:34 +08:00
u8 alu_state; /* used in combination with alu_limit */
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 14:41:20 +08:00
/* below fields are initialized once */
unsigned int orig_idx; /* original instruction index */
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 14:41:20 +08:00
bool prune_point;
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
#define MAX_USED_BTFS 64 /* max number of BTFs accessed by one BPF program */
#define BPF_VERIFIER_TMP_LOG_SIZE 1024
struct bpf_verifier_log {
u32 level;
char kbuf[BPF_VERIFIER_TMP_LOG_SIZE];
char __user *ubuf;
u32 len_used;
u32 len_total;
};
static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
{
return log->len_used >= log->len_total - 1;
}
#define BPF_LOG_LEVEL1 1
#define BPF_LOG_LEVEL2 2
#define BPF_LOG_STATS 4
#define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
#define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS)
#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */
bpf: Right align verifier states in verifier logs. Make the verifier logs more readable, print the verifier states on the corresponding instruction line. If the previous line was not a bpf instruction, then print the verifier states on its own line. Before: Validating test_pkt_access_subprog3() func#3... 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 87: R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 88: R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 89: R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 91: R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 92: R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) After: 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 ; R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 ; R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 ; R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 ; R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 ; R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) Signed-off-by: Christy Lee <christylee@fb.com> Acked-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2021-12-17 11:42:45 +08:00
#define BPF_LOG_MIN_ALIGNMENT 8U
#define BPF_LOG_ALIGNMENT 40U
static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
{
return log &&
((log->level && log->ubuf && !bpf_verifier_log_full(log)) ||
log->level == BPF_LOG_KERNEL);
}
static inline bool
bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log)
{
return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 &&
log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK);
}
bpf: introduce function calls (function boundaries) Allow arbitrary function calls from bpf function to another bpf function. Since the beginning of bpf all bpf programs were represented as a single function and program authors were forced to use always_inline for all functions in their C code. That was causing llvm to unnecessary inflate the code size and forcing developers to move code to header files with little code reuse. With a bit of additional complexity teach verifier to recognize arbitrary function calls from one bpf function to another as long as all of functions are presented to the verifier as a single bpf program. New program layout: r6 = r1 // some code .. r1 = .. // arg1 r2 = .. // arg2 call pc+1 // function call pc-relative exit .. = r1 // access arg1 .. = r2 // access arg2 .. call pc+20 // second level of function call ... It allows for better optimized code and finally allows to introduce the core bpf libraries that can be reused in different projects, since programs are no longer limited by single elf file. With function calls bpf can be compiled into multiple .o files. This patch is the first step. It detects programs that contain multiple functions and checks that calls between them are valid. It splits the sequence of bpf instructions (one program) into a set of bpf functions that call each other. Calls to only known functions are allowed. In the future the verifier may allow calls to unresolved functions and will do dynamic linking. This logic supports statically linked bpf functions only. Such function boundary detection could have been done as part of control flow graph building in check_cfg(), but it's cleaner to separate function boundary detection vs control flow checks within a subprogram (function) into logically indepedent steps. Follow up patches may split check_cfg() further, but not check_subprogs(). Only allow bpf-to-bpf calls for root only and for non-hw-offloaded programs. These restrictions can be relaxed in the future. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:05 +08:00
#define BPF_MAX_SUBPROGS 256
struct bpf_subprog_info {
/* 'start' has to be the first field otherwise find_subprog() won't work */
u32 start; /* insn idx of function entry point */
bpf: Add bpf_line_info support This patch adds bpf_line_info support. It accepts an array of bpf_line_info objects during BPF_PROG_LOAD. The "line_info", "line_info_cnt" and "line_info_rec_size" are added to the "union bpf_attr". The "line_info_rec_size" makes bpf_line_info extensible in the future. The new "check_btf_line()" ensures the userspace line_info is valid for the kernel to use. When the verifier is translating/patching the bpf_prog (through "bpf_patch_insn_single()"), the line_infos' insn_off is also adjusted by the newly added "bpf_adj_linfo()". If the bpf_prog is jited, this patch also provides the jited addrs (in aux->jited_linfo) for the corresponding line_info.insn_off. "bpf_prog_fill_jited_linfo()" is added to fill the aux->jited_linfo. It is currently called by the x86 jit. Other jits can also use "bpf_prog_fill_jited_linfo()" and it will be done in the followup patches. In the future, if it deemed necessary, a particular jit could also provide its own "bpf_prog_fill_jited_linfo()" implementation. A few "*line_info*" fields are added to the bpf_prog_info such that the user can get the xlated line_info back (i.e. the line_info with its insn_off reflecting the translated prog). The jited_line_info is available if the prog is jited. It is an array of __u64. If the prog is not jited, jited_line_info_cnt is 0. The verifier's verbose log with line_info will be done in a follow up patch. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2018-12-08 08:42:25 +08:00
u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
u16 stack_depth; /* max. stack depth used by this function */
bool has_tail_call;
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 05:10:08 +08:00
bool tail_call_reachable;
bool has_ld_abs;
bool is_async_cb;
};
/* single container for all structs
* one verifier_env per bpf_check() call
*/
struct bpf_verifier_env {
u32 insn_idx;
u32 prev_insn_idx;
struct bpf_prog *prog; /* eBPF program being verified */
const struct bpf_verifier_ops *ops;
struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
int stack_size; /* number of states to be processed */
bool strict_alignment; /* perform strict pointer alignment checks */
bool test_state_freq; /* test verifier with different pruning frequency */
struct bpf_verifier_state *cur_state; /* current verifier state */
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
bpf: improve verification speed by droping states Branch instructions, branch targets and calls in a bpf program are the places where the verifier remembers states that led to successful verification of the program. These states are used to prune brute force program analysis. For unprivileged programs there is a limit of 64 states per such 'branching' instructions (maximum length is tracked by max_states_per_insn counter introduced in the previous patch). Simply reducing this threshold to 32 or lower increases insn_processed metric to the point that small valid programs get rejected. For root programs there is no limit and cilium programs can have max_states_per_insn to be 100 or higher. Walking 100+ states multiplied by number of 'branching' insns during verification consumes significant amount of cpu time. Turned out simple LRU-like mechanism can be used to remove states that unlikely will be helpful in future search pruning. This patch introduces hit_cnt and miss_cnt counters: hit_cnt - this many times this state successfully pruned the search miss_cnt - this many times this state was not equivalent to other states (and that other states were added to state list) The heuristic introduced in this patch is: if (sl->miss_cnt > sl->hit_cnt * 3 + 3) /* drop this state from future considerations */ Higher numbers increase max_states_per_insn (allow more states to be considered for pruning) and slow verification speed, but do not meaningfully reduce insn_processed metric. Lower numbers drop too many states and insn_processed increases too much. Many different formulas were considered. This one is simple and works well enough in practice. (the analysis was done on selftests/progs/* and on cilium programs) The end result is this heuristic improves verification speed by 10 times. Large synthetic programs that used to take a second more now take 1/10 of a second. In cases where max_states_per_insn used to be 100 or more, now it's ~10. There is a slight increase in insn_processed for cilium progs: before after bpf_lb-DLB_L3.o 1831 1838 bpf_lb-DLB_L4.o 3029 3218 bpf_lb-DUNKNOWN.o 1064 1064 bpf_lxc-DDROP_ALL.o 26309 26935 bpf_lxc-DUNKNOWN.o 33517 34439 bpf_netdev.o 9713 9721 bpf_overlay.o 6184 6184 bpf_lcx_jit.o 37335 39389 And 2-3 times improvement in the verification speed. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2019-04-02 12:27:41 +08:00
struct bpf_verifier_state_list *free_list;
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */
u32 used_map_cnt; /* number of used maps */
u32 used_btf_cnt; /* number of used BTF objects */
u32 id_gen; /* used to generate unique reg IDs */
bool explore_alu_limits;
bool allow_ptr_leaks;
bpf: Allow variable-offset stack access Before this patch, variable offset access to the stack was dissalowed for regular instructions, but was allowed for "indirect" accesses (i.e. helpers). This patch removes the restriction, allowing reading and writing to the stack through stack pointers with variable offsets. This makes stack-allocated buffers more usable in programs, and brings stack pointers closer to other types of pointers. The motivation is being able to use stack-allocated buffers for data manipulation. When the stack size limit is sufficient, allocating buffers on the stack is simpler than per-cpu arrays, or other alternatives. In unpriviledged programs, variable-offset reads and writes are disallowed (they were already disallowed for the indirect access case) because the speculative execution checking code doesn't support them. Additionally, when writing through a variable-offset stack pointer, if any pointers are in the accessible range, there's possilibities of later leaking pointers because the write cannot be tracked precisely. Writes with variable offset mark the whole range as initialized, even though we don't know which stack slots are actually written. This is in order to not reject future reads to these slots. Note that this doesn't affect writes done through helpers; like before, helpers need the whole stack range to be initialized to begin with. All the stack slots are in range are considered scalars after the write; variable-offset register spills are not tracked. For reads, all the stack slots in the variable range needs to be initialized (but see above about what writes do), otherwise the read is rejected. All register spilled in stack slots that might be read are marked as having been read, however reads through such pointers don't do register filling; the target register will always be either a scalar or a constant zero. Signed-off-by: Andrei Matei <andreimatei1@gmail.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210207011027.676572-2-andreimatei1@gmail.com
2021-02-07 09:10:24 +08:00
bool allow_uninit_stack;
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 05:11:43 +08:00
bool allow_ptr_to_map_access;
bool bpf_capable;
bool bypass_spec_v1;
bool bypass_spec_v4;
bool seen_direct_write;
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
const struct bpf_line_info *prev_linfo;
struct bpf_verifier_log log;
struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE];
struct {
int *insn_state;
int *insn_stack;
int cur_stack;
} cfg;
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 14:41:20 +08:00
u32 pass_cnt; /* number of times do_check() was called */
bpf: introduce function calls (function boundaries) Allow arbitrary function calls from bpf function to another bpf function. Since the beginning of bpf all bpf programs were represented as a single function and program authors were forced to use always_inline for all functions in their C code. That was causing llvm to unnecessary inflate the code size and forcing developers to move code to header files with little code reuse. With a bit of additional complexity teach verifier to recognize arbitrary function calls from one bpf function to another as long as all of functions are presented to the verifier as a single bpf program. New program layout: r6 = r1 // some code .. r1 = .. // arg1 r2 = .. // arg2 call pc+1 // function call pc-relative exit .. = r1 // access arg1 .. = r2 // access arg2 .. call pc+20 // second level of function call ... It allows for better optimized code and finally allows to introduce the core bpf libraries that can be reused in different projects, since programs are no longer limited by single elf file. With function calls bpf can be compiled into multiple .o files. This patch is the first step. It detects programs that contain multiple functions and checks that calls between them are valid. It splits the sequence of bpf instructions (one program) into a set of bpf functions that call each other. Calls to only known functions are allowed. In the future the verifier may allow calls to unresolved functions and will do dynamic linking. This logic supports statically linked bpf functions only. Such function boundary detection could have been done as part of control flow graph building in check_cfg(), but it's cleaner to separate function boundary detection vs control flow checks within a subprogram (function) into logically indepedent steps. Follow up patches may split check_cfg() further, but not check_subprogs(). Only allow bpf-to-bpf calls for root only and for non-hw-offloaded programs. These restrictions can be relaxed in the future. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:05 +08:00
u32 subprog_cnt;
/* number of instructions analyzed by the verifier */
u32 prev_insn_processed, insn_processed;
/* number of jmps, calls, exits analyzed so far */
u32 prev_jmps_processed, jmps_processed;
/* total verification time */
u64 verification_time;
/* maximum number of verifier states kept in 'branching' instructions */
u32 max_states_per_insn;
/* total number of allocated verifier states */
u32 total_states;
/* some states are freed during program analysis.
* this is peak number of states. this number dominates kernel
* memory consumption during verification
*/
u32 peak_states;
/* longest register parentage chain walked for liveness marking */
u32 longest_mark_read_walk;
bpfptr_t fd_array;
bpf: Only print scratched registers and stack slots to verifier logs. When printing verifier state for any log level, print full verifier state only on function calls or on errors. Otherwise, only print the registers and stack slots that were accessed. Log size differences: verif_scale_loop6 before: 234566564 verif_scale_loop6 after: 72143943 69% size reduction kfree_skb before: 166406 kfree_skb after: 55386 69% size reduction Before: 156: (61) r0 = *(u32 *)(r1 +0) 157: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=ctx(id=0,off=0,imm=0) R2_w=invP0 R10=fp0 fp-8_w=00000000 fp-16_w=00\ 000000 fp-24_w=00000000 fp-32_w=00000000 fp-40_w=00000000 fp-48_w=00000000 fp-56_w=00000000 fp-64_w=00000000 fp-72_w=00000000 fp-80_w=00000\ 000 fp-88_w=00000000 fp-96_w=00000000 fp-104_w=00000000 fp-112_w=00000000 fp-120_w=00000000 fp-128_w=00000000 fp-136_w=00000000 fp-144_w=00\ 000000 fp-152_w=00000000 fp-160_w=00000000 fp-168_w=00000000 fp-176_w=00000000 fp-184_w=00000000 fp-192_w=00000000 fp-200_w=00000000 fp-208\ _w=00000000 fp-216_w=00000000 fp-224_w=00000000 fp-232_w=00000000 fp-240_w=00000000 fp-248_w=00000000 fp-256_w=00000000 fp-264_w=00000000 f\ p-272_w=00000000 fp-280_w=00000000 fp-288_w=00000000 fp-296_w=00000000 fp-304_w=00000000 fp-312_w=00000000 fp-320_w=00000000 fp-328_w=00000\ 000 fp-336_w=00000000 fp-344_w=00000000 fp-352_w=00000000 fp-360_w=00000000 fp-368_w=00000000 fp-376_w=00000000 fp-384_w=00000000 fp-392_w=\ 00000000 fp-400_w=00000000 fp-408_w=00000000 fp-416_w=00000000 fp-424_w=00000000 fp-432_w=00000000 fp-440_w=00000000 fp-448_w=00000000 ; return skb->len; 157: (95) exit Func#4 is safe for any args that match its prototype Validating get_constant() func#5... 158: R1=invP(id=0) R10=fp0 ; int get_constant(long val) 158: (bf) r0 = r1 159: R0_w=invP(id=1) R1=invP(id=1) R10=fp0 ; return val - 122; 159: (04) w0 += -122 160: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=invP(id=1) R10=fp0 ; return val - 122; 160: (95) exit Func#5 is safe for any args that match its prototype Validating get_skb_ifindex() func#6... 161: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 ; int get_skb_ifindex(int val, struct __sk_buff *skb, int var) 161: (bc) w0 = w3 162: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 After: 156: (61) r0 = *(u32 *)(r1 +0) 157: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=ctx(id=0,off=0,imm=0) ; return skb->len; 157: (95) exit Func#4 is safe for any args that match its prototype Validating get_constant() func#5... 158: R1=invP(id=0) R10=fp0 ; int get_constant(long val) 158: (bf) r0 = r1 159: R0_w=invP(id=1) R1=invP(id=1) ; return val - 122; 159: (04) w0 += -122 160: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return val - 122; 160: (95) exit Func#5 is safe for any args that match its prototype Validating get_skb_ifindex() func#6... 161: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 ; int get_skb_ifindex(int val, struct __sk_buff *skb, int var) 161: (bc) w0 = w3 162: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R3=invP(id=0) Signed-off-by: Christy Lee <christylee@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20211216213358.3374427-2-christylee@fb.com
2021-12-17 05:33:56 +08:00
/* bit mask to keep track of whether a register has been accessed
* since the last time the function state was printed
*/
u32 scratched_regs;
/* Same as scratched_regs but for stack slots */
u64 scratched_stack_slots;
bpf: Right align verifier states in verifier logs. Make the verifier logs more readable, print the verifier states on the corresponding instruction line. If the previous line was not a bpf instruction, then print the verifier states on its own line. Before: Validating test_pkt_access_subprog3() func#3... 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 87: R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 88: R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 89: R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 91: R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 92: R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) After: 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 ; R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 ; R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 ; R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 ; R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 ; R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) Signed-off-by: Christy Lee <christylee@fb.com> Acked-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2021-12-17 11:42:45 +08:00
u32 prev_log_len, prev_insn_print_len;
/* buffer used in reg_type_str() to generate reg_type string */
char type_str_buf[TYPE_STR_BUF_LEN];
};
__printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
const char *fmt, va_list args);
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
const char *fmt, ...);
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 11:25:00 +08:00
__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
const char *fmt, ...);
static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
{
bpf: introduce function calls (verification) Allow arbitrary function calls from bpf function to another bpf function. To recognize such set of bpf functions the verifier does: 1. runs control flow analysis to detect function boundaries 2. proceeds with verification of all functions starting from main(root) function It recognizes that the stack of the caller can be accessed by the callee (if the caller passed a pointer to its stack to the callee) and the callee can store map_value and other pointers into the stack of the caller. 3. keeps track of the stack_depth of each function to make sure that total stack depth is still less than 512 bytes 4. disallows pointers to the callee stack to be stored into the caller stack, since they will be invalid as soon as the callee returns 5. to reuse all of the existing state_pruning logic each function call is considered to be independent call from the verifier point of view. The verifier pretends to inline all function calls it sees are being called. It stores the callsite instruction index as part of the state to make sure that two calls to the same callee from two different places in the caller will be different from state pruning point of view 6. more safety checks are added to liveness analysis Implementation details: . struct bpf_verifier_state is now consists of all stack frames that led to this function . struct bpf_func_state represent one stack frame. It consists of registers in the given frame and its stack . propagate_liveness() logic had a premature optimization where mark_reg_read() and mark_stack_slot_read() were manually inlined with loop iterating over parents for each register or stack slot. Undo this optimization to reuse more complex mark_*_read() logic . skip_callee() logic is not necessary from safety point of view, but without it mark_*_read() markings become too conservative, since after returning from the funciton call a read of r6-r9 will incorrectly propagate the read marks into callee causing inefficient pruning later . mark_*_read() logic is now aware of control flow which makes it more complex. In the future the plan is to rewrite liveness to be hierarchical. So that liveness can be done within basic block only and control flow will be responsible for propagation of liveness information along cfg and between calls. . tail_calls and ld_abs insns are not allowed in the programs with bpf-to-bpf calls . returning stack pointers to the caller or storing them into stack frame of the caller is not allowed Testing: . no difference in cilium processed_insn numbers . large number of tests follows in next patches Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: John Fastabend <john.fastabend@gmail.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2017-12-15 09:55:06 +08:00
struct bpf_verifier_state *cur = env->cur_state;
return cur->frame[cur->curframe];
}
static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env)
{
return cur_func(env)->regs;
}
int bpf_prog_offload_verifier_prep(struct bpf_prog *prog);
int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int bpf_prog_offload_finalize(struct bpf_verifier_env *env);
void
bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
struct bpf_insn *insn);
void
bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
int check_ptr_off_reg(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno);
int check_func_arg_reg_off(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg, int regno,
enum bpf_arg_type arg_type);
bpf: Introduce mem, size argument pair support for kfunc BPF helpers can associate two adjacent arguments together to pass memory of certain size, using ARG_PTR_TO_MEM and ARG_CONST_SIZE arguments. Since we don't use bpf_func_proto for kfunc, we need to leverage BTF to implement similar support. The ARG_CONST_SIZE processing for helpers is refactored into a common check_mem_size_reg helper that is shared with kfunc as well. kfunc ptr_to_mem support follows logic similar to global functions, where verification is done as if pointer is not null, even when it may be null. This leads to a simple to follow rule for writing kfunc: always check the argument pointer for NULL, except when it is PTR_TO_CTX. Also, the PTR_TO_CTX case is also only safe when the helper expecting pointer to program ctx is not exposed to other programs where same struct is not ctx type. In that case, the type check will fall through to other cases and would permit passing other types of pointers, possibly NULL at runtime. Currently, we require the size argument to be suffixed with "__sz" in the parameter name. This information is then recorded in kernel BTF and verified during function argument checking. In the future we can use BTF tagging instead, and modify the kernel function definitions. This will be a purely kernel-side change. This allows us to have some form of backwards compatibility for structures that are passed in to the kernel function with their size, and allow variable length structures to be passed in if they are accompanied by a size parameter. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20220114163953.1455836-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-01-15 00:39:47 +08:00
int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno);
bpf: Support pointers in global func args Add an ability to pass a pointer to a type with known size in arguments of a global function. Such pointers may be used to overcome the limit on the maximum number of arguments, avoid expensive and tricky workarounds and to have multiple output arguments. A referenced type may contain pointers but indirect access through them isn't supported. The implementation consists of two parts. If a global function has an argument that is a pointer to a type with known size then: 1) In btf_check_func_arg_match(): check that the corresponding register points to NULL or to a valid memory region that is large enough to contain the expected argument's type. 2) In btf_prepare_func_args(): set the corresponding register type to PTR_TO_MEM_OR_NULL and its size to the size of the expected type. Only global functions are supported because allowance of pointers for static functions might break validation. Consider the following scenario. A static function has a pointer argument. A caller passes pointer to its stack memory. Because the callee can change referenced memory verifier cannot longer assume any particular slot type of the caller's stack memory hence the slot type is changed to SLOT_MISC. If there is an operation that relies on slot type other than SLOT_MISC then verifier won't be able to infer safety of the operation. When verifier sees a static function that has a pointer argument different from PTR_TO_CTX then it skips arguments check and continues with "inline" validation with more information available. The operation that relies on the particular slot type now succeeds. Because global functions were not allowed to have pointer arguments different from PTR_TO_CTX it's not possible to break existing and valid code. Signed-off-by: Dmitrii Banshchikov <me@ubique.spb.ru> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20210212205642.620788-4-me@ubique.spb.ru
2021-02-13 04:56:41 +08:00
int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
u32 regno, u32 mem_size);
bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env,
struct bpf_reg_state *reg);
bool is_dynptr_type_expected(struct bpf_verifier_env *env,
struct bpf_reg_state *reg,
enum bpf_arg_type arg_type);
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 14:41:20 +08:00
/* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
struct btf *btf, u32 btf_id)
{
if (tgt_prog)
return ((u64)tgt_prog->aux->id << 32) | btf_id;
else
return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id;
}
/* unpack the IDs from the key as constructed above */
static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id)
{
if (obj_id)
*obj_id = key >> 32;
if (btf_id)
*btf_id = key & 0x7FFFFFFF;
}
int bpf_check_attach_target(struct bpf_verifier_log *log,
const struct bpf_prog *prog,
const struct bpf_prog *tgt_prog,
u32 btf_id,
struct bpf_attach_target_info *tgt_info);
2021-10-02 09:17:49 +08:00
void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab);
int mark_chain_precision(struct bpf_verifier_env *env, int regno);
#define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0)
/* extract base type from bpf_{arg, return, reg}_type. */
static inline u32 base_type(u32 type)
{
return type & BPF_BASE_TYPE_MASK;
}
/* extract flags from an extended type. See bpf_type_flag in bpf.h. */
static inline u32 type_flag(u32 type)
{
return type & ~BPF_BASE_TYPE_MASK;
}
/* only use after check_attach_btf_id() */
bpf: Add reference tracking support to kfunc This patch adds verifier support for PTR_TO_BTF_ID return type of kfunc to be a reference, by reusing acquire_reference_state/release_reference support for existing in-kernel bpf helpers. We make use of the three kfunc types: - BTF_KFUNC_TYPE_ACQUIRE Return true if kfunc_btf_id is an acquire kfunc. This will acquire_reference_state for the returned PTR_TO_BTF_ID (this is the only allow return value). Note that acquire kfunc must always return a PTR_TO_BTF_ID{_OR_NULL}, otherwise the program is rejected. - BTF_KFUNC_TYPE_RELEASE Return true if kfunc_btf_id is a release kfunc. This will release the reference to the passed in PTR_TO_BTF_ID which has a reference state (from earlier acquire kfunc). The btf_check_func_arg_match returns the regno (of argument register, hence > 0) if the kfunc is a release kfunc, and a proper referenced PTR_TO_BTF_ID is being passed to it. This is similar to how helper call check uses bpf_call_arg_meta to store the ref_obj_id that is later used to release the reference. Similar to in-kernel helper, we only allow passing one referenced PTR_TO_BTF_ID as an argument. It can also be passed in to normal kfunc, but in case of release kfunc there must always be one PTR_TO_BTF_ID argument that is referenced. - BTF_KFUNC_TYPE_RET_NULL For kfunc returning PTR_TO_BTF_ID, tells if it can be NULL, hence force caller to mark the pointer not null (using check) before accessing it. Note that taking into account the case fixed by commit 93c230e3f5bd ("bpf: Enforce id generation for all may-be-null register type") we assign a non-zero id for mark_ptr_or_null_reg logic. Later, if more return types are supported by kfunc, which have a _OR_NULL variant, it might be better to move this id generation under a common reg_type_may_be_null check, similar to the case in the commit. Referenced PTR_TO_BTF_ID is currently only limited to kfunc, but can be extended in the future to other BPF helpers as well. For now, we can rely on the btf_struct_ids_match check to ensure we get the pointer to the expected struct type. In the future, care needs to be taken to avoid ambiguity for reference PTR_TO_BTF_ID passed to release function, in case multiple candidates can release same BTF ID. e.g. there might be two release kfuncs (or kfunc and helper): foo(struct abc *p); bar(struct abc *p); ... such that both release a PTR_TO_BTF_ID with btf_id of struct abc. In this case we would need to track the acquire function corresponding to the release function to avoid type confusion, and store this information in the register state so that an incorrect program can be rejected. This is not a problem right now, hence it is left as an exercise for the future patch introducing such a case in the kernel. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20220114163953.1455836-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-01-15 00:39:48 +08:00
static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
{
return prog->type == BPF_PROG_TYPE_EXT ?
prog->aux->dst_prog->type : prog->type;
bpf: Add reference tracking support to kfunc This patch adds verifier support for PTR_TO_BTF_ID return type of kfunc to be a reference, by reusing acquire_reference_state/release_reference support for existing in-kernel bpf helpers. We make use of the three kfunc types: - BTF_KFUNC_TYPE_ACQUIRE Return true if kfunc_btf_id is an acquire kfunc. This will acquire_reference_state for the returned PTR_TO_BTF_ID (this is the only allow return value). Note that acquire kfunc must always return a PTR_TO_BTF_ID{_OR_NULL}, otherwise the program is rejected. - BTF_KFUNC_TYPE_RELEASE Return true if kfunc_btf_id is a release kfunc. This will release the reference to the passed in PTR_TO_BTF_ID which has a reference state (from earlier acquire kfunc). The btf_check_func_arg_match returns the regno (of argument register, hence > 0) if the kfunc is a release kfunc, and a proper referenced PTR_TO_BTF_ID is being passed to it. This is similar to how helper call check uses bpf_call_arg_meta to store the ref_obj_id that is later used to release the reference. Similar to in-kernel helper, we only allow passing one referenced PTR_TO_BTF_ID as an argument. It can also be passed in to normal kfunc, but in case of release kfunc there must always be one PTR_TO_BTF_ID argument that is referenced. - BTF_KFUNC_TYPE_RET_NULL For kfunc returning PTR_TO_BTF_ID, tells if it can be NULL, hence force caller to mark the pointer not null (using check) before accessing it. Note that taking into account the case fixed by commit 93c230e3f5bd ("bpf: Enforce id generation for all may-be-null register type") we assign a non-zero id for mark_ptr_or_null_reg logic. Later, if more return types are supported by kfunc, which have a _OR_NULL variant, it might be better to move this id generation under a common reg_type_may_be_null check, similar to the case in the commit. Referenced PTR_TO_BTF_ID is currently only limited to kfunc, but can be extended in the future to other BPF helpers as well. For now, we can rely on the btf_struct_ids_match check to ensure we get the pointer to the expected struct type. In the future, care needs to be taken to avoid ambiguity for reference PTR_TO_BTF_ID passed to release function, in case multiple candidates can release same BTF ID. e.g. there might be two release kfuncs (or kfunc and helper): foo(struct abc *p); bar(struct abc *p); ... such that both release a PTR_TO_BTF_ID with btf_id of struct abc. In this case we would need to track the acquire function corresponding to the release function to avoid type confusion, and store this information in the register state so that an incorrect program can be rejected. This is not a problem right now, hence it is left as an exercise for the future patch introducing such a case in the kernel. Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20220114163953.1455836-6-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-01-15 00:39:48 +08:00
}
#endif /* _LINUX_BPF_VERIFIER_H */