1641 Commits

Author	SHA1	Message	Date
YAMAMOTO Takashi	da9afc1d3a	wasi-nn: add a missing address validation for get_output ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4533	2025-08-04 15:54:28 +09:00
YAMAMOTO Takashi	29d465b44e	wasi_nn_tensorflowlite.cpp: make this compatible with wasmedge (#4517) ... for wasi_ephemeral_nn, * implement u8 input * stop dealing with quantization. * wasi-nn doesn't have a concept of quantization or pre/post-processing. i can't think of any ways to make the backend perform zero-point/scale processing without risking to break other applications. * there seems to be applications which just use u8 inputs/outputs for a quantized model. (see [1] for an example.) for certain kinds of inputs/outputs, it usually just works. this commit keeps the legacy wasi_nn logic intact for now. tested with [1] with [2] applied. WAMR with this patch: ``` Read graph weights, size in bytes: 3561598 [wasi_nn.c:297 WARNING] load_by_name_with_config() not found [wasi_nn_tensorflowlite.cpp:272 WARNING] Default encoding is CPU. Loaded graph into wasi-nn with ID: Graph#0 Read input tensor, size in bytes: 150528 1.) [166](198)Aix galericulata 2.) [34](1)Gallus gallus domesticus 3.) [158](1)Coccothraustes coccothraustes 4.) [778](1)Sitta europaea 5.) [819](1)Anas platyrhynchos ``` wasmedge: ``` Read graph weights, size in bytes: 3561598 Loaded graph into wasi-nn with ID: Graph#0 Read input tensor, size in bytes: 150528 1.) [166](198)Aix galericulata 2.) [34](1)Gallus gallus domesticus 3.) [158](1)Coccothraustes coccothraustes 4.) [778](1)Sitta europaea 5.) [819](1)Anas platyrhynchos ``` and "Aix galericulata" seems like a reasonable classification of the image to my eyes. [1] 67f174bab5/tflite-birds_v1-image [2] https://github.com/second-state/WasmEdge-WASINN-examples/pull/204 Related: https://github.com/bytecodealliance/wasm-micro-runtime/issues/3555 https://github.com/bytecodealliance/wasm-micro-runtime/issues/2611	2025-08-01 14:31:02 +08:00
Jaco Kroon	272a41dc80	Avoid executable stack by marking that it's not required. (#4418) ... Also refer to: https://github.com/fluent/fluent-bit/issues/10513 Signed-off-by: Jaco Kroon <jaco@uls.co.za>	2025-08-01 14:30:39 +08:00
Zhenwei Jin	378320b886	loader: add type index checking (#4521)	2025-08-01 08:58:26 +08:00
Zhenwei Jin	33eff933c0	add validation for rec indices in aot loader (#4520)	2025-08-01 08:45:57 +08:00
Zhenwei Jin	aad1866260	add validation for recursive type count in loader (#4522)	2025-07-31 16:19:08 +08:00
YAMAMOTO Takashi	a0de8c7b7d	wasi-nn: fix buffer overruns in load_by_name/load_by_name_with_config (#4491) ... also, ensure NUL terminations here to simplify backend implementations. (note that, although names with '\0' in the middle are usually valid in wasm, wamr doesn't support them in general. we might revisit this later.) also, add a missing address validation in load_by_name_with_config. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4487	2025-07-30 10:27:20 +08:00
ChenWen	c6afa131a4	feat(core): Support pthread using SPIRAM as stack (#4509) ... Signed-off-by: chenwen@espressif.com <chenwen@espressif.com>	2025-07-30 10:26:41 +08:00
TianlongLiang	b322e297c6	Add CLI option for iwasm to create and attach shared heap to wasm app (#4499)	2025-07-29 11:13:23 +08:00
YAMAMOTO Takashi	f34d28cfbc	lib-socket: implement gai_strerror (#4508) ... cf. https://pubs.opengroup.org/onlinepubs/9799919799/functions/gai_strerror.html	2025-07-29 11:12:27 +08:00
liang.he	b124f70345	Bump version to 2.4.1 (#4513)	2025-07-28 20:49:11 +08:00
YAMAMOTO Takashi	d298a66d38	bump AOT_CURRENT_VERSION for extended-const (#4511) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4504	2025-07-27 14:39:35 +08:00
liang.he	121232a995	Merge commit from fork ... If `--addr-pool=1.2.3.4`, the runtime will return an error. The value must be in the form of ADDRESS/MASK.	2025-07-27 14:38:56 +08:00
YAMAMOTO Takashi	a780ffdc43	lib-socket: make getaddrinfo return EAI_ values (#4498) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4464	2025-07-21 09:21:31 +08:00
YAMAMOTO Takashi	e4d2673a7c	wasi-nn: add a comment on load_by_name_with_config (#4492) ... this api has been introduced by https://github.com/bytecodealliance/wasm-micro-runtime/pull/3709 in which i couldn't find any explanations. this comment is my best guess.	2025-07-17 09:50:49 +08:00
Liu Jia	704aa3e7e5	modify macro related to simde when WASM_OP_SELECT_128 (#4461) ... * remove macro of fast interpreter when WASM_OP_SELECT_128 * Modified some macros related to SIMDE	2025-07-17 08:04:41 +08:00
YAMAMOTO Takashi	46d4e248bb	posix os_socket_accept: stop assuming socklen_t is unsigned int (#4488)	2025-07-17 08:04:13 +08:00
YAMAMOTO Takashi	db942f3aaf	wasi_socket_ext.c: fix error reporting ... do not return __WASI_ERRNO_xxx error code where 0/-1 is more appropriate. most of them were not harmful because the value of __WASI_ERRNO_SUCCESS is 0. the one with __WASI_ERRNO_NOPROTOOPT in socket() is a user-visible bug. tested with wamr-wasi-extensions/samples/socket-tcp-udp. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4474	2025-07-15 09:23:46 +02:00
YAMAMOTO Takashi	2a952b371a	wasi_socket_ext.c: fix the number of getaddrinfo results (#4466) ... the case of zero results was especially broken.	2025-07-14 13:12:32 +08:00
TianlongLiang	b3158e643c	Fix typos (#4472) ... * leave api name unchanged so don't break API	2025-07-14 13:12:08 +08:00
YAMAMOTO Takashi	2c4a660c4c	posix os_socket_addr_resolve: relax compatibility check (#4469) ... some getaddrinfo implementations sometimes return results with ai_protocol=0. cf. https://github.com/apache/nuttx/issues/16693 standard-wise, i couldn't find anything about ai_protocol in susv4-2018 except the following text: > The fields ai_family, ai_socktype, and ai_protocol shall be usable > as the arguments to the socket() function to create a socket suitable > for use with the returned address. because ai_protocol is usually merely used to feed socket() and socket() usually accepts 0, it's probably standard-wise ok for getaddrinfo to return ai_protocol=0. the major implementations of getaddrinfo (eg. kame) seem to return specific values like ai_protocol=IPPROTO_TCP though. anyway, for the purpose of this function, there is little point to be strict on the host getaddrinfo behavior. this commit just relaxes the check to be friendly to those getaddrinfo implementations.	2025-07-14 13:06:40 +08:00
YAMAMOTO Takashi	53feadc2b0	lib-socket: implement getsockopt(SOL_SOCKET,SO_TYPE) (#4458) ... cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4456	2025-07-14 13:06:33 +08:00
YAMAMOTO Takashi	5d48cfdbc0	introduce wasm_runtime_instantiate_ex2 (#4444) ... * introduce wasm_runtime_instantiate_ex2 at this point, just a slightly inefficiant functionality equivalent of wasm_runtime_instantiate_ex. however, unlike wasm_runtime_instantiate_ex, this one is designed to be extendable without breaking the user-visible ABI. because the definition of InstantiationArgs2 is not exposed to users, we can safely add new members to it. this commit also makes wasm_runtime_instantiate_ex a wrapper of wasm_runtime_instantiate_ex2. if this goes well, maybe it's a good idea to apply a similar pattern to RuntimeInitArgs, LoadArgs, SharedHeapInitArgs, etc. i started with InstantiationArgs just because i happen to have a need to extend it for wasi-nn. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4364 https://github.com/bytecodealliance/wasm-micro-runtime/issues/4331 * product-mini/platforms/posix: use wasm_runtime_instantiate_ex2	2025-07-14 13:06:23 +08:00
Zhenwei Jin	65d3ffa7a4	add validation for recursive type count in loader (#4440)	2025-07-14 13:06:08 +08:00
liang.he	47c7c85ac2	Bump version to 2.4.0 (#4483)	2025-07-14 11:06:03 +08:00
YAMAMOTO Takashi	17be90d8f0	posix os_socket_addr_resolve: return the consistent max_info_size (#4467) ... return the same value for max_info_size regardless of addr_info_size.	2025-07-10 13:42:57 +08:00
Zhenwei Jin	9e92f5ebe1	fix a wamrc debug mode compile issue (#4470)	2025-07-10 08:29:31 +08:00
YAMAMOTO Takashi	56f87b7ee9	wasi-nn: do not pretend to support legacy abi in openvino and llamacpp (#4468) ... as tested by core/iwasm/libraries/wasi-nn/test/test_tensorflow.c, the legacy "wasi_nn" abi uses the number of fp32 for get_output. because these backends don't implement the abi, bail out explicitly in build time. cf. https://github.com/bytecodealliance/wasm-micro-runtime/issues/4376	2025-07-10 08:28:08 +08:00
YAMAMOTO Takashi	933e49df18	appease a few compiler warnings (-Wstrict-prototypes) (#4465)	2025-07-10 08:28:00 +08:00
Liu Jia	903a5c1f8c	improve logic of heap_type validation when ref.null (#4372) ... * Follow-up to PR #4300: prevent potential overflow PR #4300 introduced the rationale for validating heap_type. This patch moves the validation before the computation of type1 to prevent potential overflow.	2025-07-10 08:27:11 +08:00
YAMAMOTO Takashi	fbd27e5e03	wasi_nn_llamacpp.c: explicitly reject unimplemented input index (#4446) ... note: wasmedge seems to accept index 1 for metadata. we don't implement it.	2025-07-09 10:35:46 +08:00
YAMAMOTO Takashi	0eceed2ba9	wasi: avoid user-triggerable 0-sized allocations (#4452) ... might fix https://github.com/bytecodealliance/wasm-micro-runtime/issues/4451	2025-07-08 09:25:50 +08:00
TianlongLiang	7d05dbc988	Support extended constant expressions (#4432) ... * implement extended const expr (#4318) * add a toggle to enable extended const on wamrc (#4412)	2025-07-07 13:34:02 +08:00
TianlongLiang	8a55a1e7a1	Shared heap enhancements for Interpreter and AOT (#4400) ... Propose two enhancements: - Shared heap created from preallocated memory buffer: The user can create a shared heap from a pre-allocated buffer and see that memory region as one large chunk; there's no need to dynamically manage it(malloc/free). The user needs to make sure the native address and size of that memory region are valid. - Introduce shared heap chain: The user can create a shared heap chain, from the wasm app point of view, it's still a continuous memory region in wasm app's point of view while in the native it can consist of multiple shared heaps (each of which is a continuous memory region). For example, one 500MB shared heap 1 and one 500 MB shared heap 2 form a chain, in Wasm's point of view, it's one 1GB shared heap. After these enhancements, the data sharing between wasm apps, and between hosts can be more efficient and flexible. Admittedly shared heap management can be more complex for users, but it's similar to the zero-overhead principle. No overhead will be imposed for the users who don't use the shared heap enhancement or don't use the shared heap at all.	2025-07-04 10:44:51 +08:00
YAMAMOTO Takashi	ee056d8076	wasi_nn_llamacpp.c: validate input tensor type/dimensions (#4442)	2025-07-03 10:17:19 +08:00
YAMAMOTO Takashi	da6019f749	wasi_nn_llamacpp.c: reject invalid graph and execution context (#4422) ... * return valid graph and execution context instead of using stack garbage. (always 0 for now because we don't implement multiple graph/context for this backend.) * validate user-given graph and execution context values. reject invalid ones.	2025-07-01 19:31:00 +08:00
YAMAMOTO Takashi	ebf1404ad1	wasi_nn_openvino.c: avoid self-assignment warning (#4434)	2025-07-01 19:19:36 +08:00
liang.he	c7148a6823	Fix potential integer overflow issues (#4429) ... It is reported as "Multiplication result converted to larger type". And "Multiplication result may overflow 'Type A' before it is converted to 'Type B'." Type A is a larger type than Type B. Since the conversion applies after the multiplication, arithmetic overflow may still occur. > The rule flags every multiplication of two non-constant integer expressions > that is (explicitly or implicitly) converted to a larger integer type. The > conversion is an indication that the expression would produce a result that > would be too large to fit in the smaller integer type.	2025-07-01 13:39:30 +08:00
YAMAMOTO Takashi	38fe056cc6	wasi-nn: reduce code duplication a bit (#4433)	2025-07-01 10:37:12 +08:00
liang.he	430cc5e5ef	Refactor AOTObjectData definition to use a forward declaration (#4428) ... > core/iwasm/compilation/aot_emit_aot_file.c:85:3: error: redefinition of typedef 'AOTObjectData' is a C11 feature	2025-07-01 10:10:11 +08:00
Zhenwei Jin	0127eafbe5	loader: fix a potential overflow issue (#4427)	2025-06-30 12:57:57 +08:00
YAMAMOTO Takashi	7a6a6a39e9	wasi_nn_openvino.c: fix a debug build (#4416) ... after "wasi_nn_openvino.c: implement multiple models per instance" change. (https://github.com/bytecodealliance/wasm-micro-runtime/pull/4380)	2025-06-30 12:57:44 +08:00
liang.he	0641dd1506	Fix few shadow warnings (#4409) ... - declaration of ‘memidx’ shadows a previous local - declaration of ‘count’ shadows a previous local	2025-06-27 11:55:32 +08:00
YAMAMOTO Takashi	8ed89e2ab2	wasi_nn_llamacpp.c: remove an unused variable (#4415)	2025-06-27 11:55:08 +08:00
YAMAMOTO Takashi	d6876f1e9f	wasi_nn_llamacpp.c: fix buffer overruns in set_input (#4420) ... note: for some reasons, wasmedge seems to ignore type/dimensions for the input of ggml. some user code relies on it. cf. https://github.com/second-state/WasmEdge-WASINN-examples/issues/196 note: despite the comment in our code, the input doesn't seem nul-terminated.	2025-06-27 11:51:03 +08:00
YAMAMOTO Takashi	2372a472aa	wasi-nn: make the host use the wasi_ephemeral_nn version of tensor_data (#4411) ... the motivations: * make the actual input size available to the backends. (currently the backends have to make a guess from shape/type.) * make the host logic look a bit similar to wasi_ephemeral_nn. this is a backend api/abi change.	2025-06-27 07:41:42 +08:00
TianlongLiang	23799a2cb6	Collective fix (#4413) ... * Fix vector growth check and typos in core (#9) * Fix resource cleanup in memory and running modes tests (#10) * Add end of file empty line in wasm_running_modes_test.cc	2025-06-26 10:20:40 +08:00
TianlongLiang	5b32130955	fix bug in bh_vector when extending (#4414)	2025-06-26 10:18:24 +08:00
YAMAMOTO Takashi	a7aae9d2cc	wasi_nn_llamacpp.c: make this compilable (#4403)	2025-06-26 07:05:45 +08:00
Liu Jia	535004dedc	Fix handling of non-nullable global_type during global import (#4408)	2025-06-26 06:59:57 +08:00