ggml-virtgpu: improve the reliability of the code (#19846)
* ggml-virtgpu-backend: validate the consistency of the received objects This patch adds consistency checks in the ggml-virtgpu-backend (running on the host side) to ensure that the data received from the guest is consistent (valid pointers, valid sizes and offsets). * ggml-virtgpu-backend: add fallback/skips for optional ggml backend methods ``` 1. bck->iface.synchronize(bck) 2. buft->iface.get_alloc_size(buft, op) 3. buft->iface.get_max_size(buft) ``` these three methods are optional in the GGML interface. `get_max_size` was already properly defaulted, but `backend sychronize` and `butf get_max_size` would have segfaulted the backend if not implemented. * ggml-virtgpu-backend: fix log format missing argument * ggml-virtgpu-backend: improve the abort message * ggml-virtgpu-backend: more safety checks * ggml-virtgpu-backend: new error code * ggml-virtgpu-backend: initialize all the error codes * ggml-virtgpu: add a missing comment generated by the code generator * ggml-virtgpu: add the '[virtgpu]' prefix to the device/buffer names * ggml-virtgpu: apir_device_buffer_from_ptr: improve the error message * ggml-virtgpu: shared: make it match the latest api_remoting.h of Virglrenderer APIR (still unmerged) * ggml-virtgpu: update the code generator to have dispatch_command_name in a host/guest shared file * ggml-virtgpu: REMOTE_CALL: fail if the backend returns an error * docs/backend/VirtGPU.md: indicate that the RAM+VRAM size is limed to 64 GB with libkrun * ggml-virtgpu: turn off clang-format header ordering for some of the files Compilation breaks when ordered alphabetically. * ggml-virtgpu: clang-format * ggml-virtgpu/backend/shared/api_remoting: better comments for the APIR return codes
This commit is contained in:
@@ -1,6 +1,5 @@
|
||||
#include "backend-dispatched.h"
|
||||
#include "backend-virgl-apir.h"
|
||||
|
||||
#include "shared/api_remoting.h"
|
||||
#include "shared/apir_backend.h"
|
||||
#include "shared/apir_cs.h"
|
||||
@@ -17,10 +16,10 @@
|
||||
#define GGML_DEFAULT_BACKEND_REG "ggml_backend_init"
|
||||
|
||||
static void * backend_library_handle = NULL;
|
||||
static FILE * apir_logfile = NULL;
|
||||
static FILE * apir_logfile = NULL;
|
||||
|
||||
static void log_to_file_callback(enum ggml_log_level level, const char * text, void * user_data) {
|
||||
FILE * logfile = (FILE *)user_data;
|
||||
FILE * logfile = (FILE *) user_data;
|
||||
fprintf(logfile, "[%d] %s", level, text);
|
||||
fflush(logfile);
|
||||
}
|
||||
@@ -48,9 +47,9 @@ void apir_backend_deinit(uint32_t virgl_ctx_id) {
|
||||
}
|
||||
|
||||
#define APIR_GGML_LIBRARY_PATH_KEY "ggml.library.path"
|
||||
#define APIR_GGML_LIBRARY_REG_KEY "ggml.library.reg"
|
||||
#define APIR_GGML_LIBRARY_REG_KEY "ggml.library.reg"
|
||||
|
||||
ApirLoadLibraryReturnCode apir_backend_initialize(uint32_t virgl_ctx_id, struct virgl_apir_callbacks *virgl_cbs) {
|
||||
ApirLoadLibraryReturnCode apir_backend_initialize(uint32_t virgl_ctx_id, struct virgl_apir_callbacks * virgl_cbs) {
|
||||
const char * dlsym_error;
|
||||
|
||||
const char * apir_log_to_file = getenv(APIR_LLAMA_CPP_LOG_TO_FILE_ENV);
|
||||
@@ -63,15 +62,13 @@ ApirLoadLibraryReturnCode apir_backend_initialize(uint32_t virgl_ctx_id, struct
|
||||
}
|
||||
}
|
||||
|
||||
const char * library_name = virgl_cbs->get_config(virgl_ctx_id, APIR_GGML_LIBRARY_PATH_KEY);
|
||||
const char * library_name = virgl_cbs->get_config(virgl_ctx_id, APIR_GGML_LIBRARY_PATH_KEY);
|
||||
const char * virgl_library_reg = virgl_cbs->get_config(virgl_ctx_id, APIR_GGML_LIBRARY_REG_KEY);
|
||||
const char * library_reg = virgl_library_reg ? virgl_library_reg : GGML_DEFAULT_BACKEND_REG;
|
||||
const char * library_reg = virgl_library_reg ? virgl_library_reg : GGML_DEFAULT_BACKEND_REG;
|
||||
|
||||
if (!library_name) {
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK
|
||||
"%s: cannot open the GGML library: env var '%s' not defined\n",
|
||||
__func__, APIR_LLAMA_CPP_GGML_LIBRARY_PATH_ENV);
|
||||
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: cannot open the GGML library: env var '%s' not defined\n", __func__,
|
||||
APIR_LLAMA_CPP_GGML_LIBRARY_PATH_ENV);
|
||||
|
||||
return APIR_LOAD_LIBRARY_ENV_VAR_MISSING;
|
||||
}
|
||||
@@ -79,16 +76,14 @@ ApirLoadLibraryReturnCode apir_backend_initialize(uint32_t virgl_ctx_id, struct
|
||||
backend_library_handle = dlopen(library_name, RTLD_LAZY);
|
||||
|
||||
if (!backend_library_handle) {
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK
|
||||
"%s: cannot open the GGML library: %s\n", __func__, dlerror());
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: cannot open the GGML library: %s\n", __func__, dlerror());
|
||||
|
||||
return APIR_LOAD_LIBRARY_CANNOT_OPEN;
|
||||
}
|
||||
|
||||
if (!library_reg) {
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK
|
||||
"%s: cannot register the GGML library: env var '%s' not defined\n",
|
||||
__func__, APIR_LLAMA_CPP_GGML_LIBRARY_REG_ENV);
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: cannot register the GGML library: env var '%s' not defined\n", __func__,
|
||||
APIR_LLAMA_CPP_GGML_LIBRARY_REG_ENV);
|
||||
|
||||
return APIR_LOAD_LIBRARY_ENV_VAR_MISSING;
|
||||
}
|
||||
@@ -96,11 +91,9 @@ ApirLoadLibraryReturnCode apir_backend_initialize(uint32_t virgl_ctx_id, struct
|
||||
void * ggml_backend_reg_fct = dlsym(backend_library_handle, library_reg);
|
||||
dlsym_error = dlerror();
|
||||
if (dlsym_error) {
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK
|
||||
"%s: cannot find the GGML backend registration symbol '%s' (from %s): %s\n",
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: cannot find the GGML backend registration symbol '%s' (from %s): %s\n",
|
||||
__func__, library_reg, APIR_LLAMA_CPP_GGML_LIBRARY_REG_ENV, dlsym_error);
|
||||
|
||||
|
||||
return APIR_LOAD_LIBRARY_SYMBOL_MISSING;
|
||||
}
|
||||
|
||||
@@ -132,13 +125,12 @@ uint32_t apir_backend_dispatcher(uint32_t virgl_ctx_id,
|
||||
|
||||
virgl_apir_context ctx = {
|
||||
.ctx_id = virgl_ctx_id,
|
||||
.iface = virgl_cbs,
|
||||
.iface = virgl_cbs,
|
||||
};
|
||||
|
||||
if (cmd_type >= APIR_BACKEND_DISPATCH_TABLE_COUNT) {
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK
|
||||
"%s: Received an invalid dispatch index (%d >= %d)\n",
|
||||
__func__, cmd_type, APIR_BACKEND_DISPATCH_TABLE_COUNT);
|
||||
GGML_LOG_ERROR(GGML_VIRTGPU_BCK "%s: Received an invalid dispatch index (%d >= %d)\n", __func__, cmd_type,
|
||||
APIR_BACKEND_DISPATCH_TABLE_COUNT);
|
||||
return APIR_BACKEND_FORWARD_INDEX_INVALID;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user