From 69efc39d5c95f2917bf38b85109af15727043a30 Mon Sep 17 00:00:00 2001
From: Gilad S <giladgd@users.noreply.github.com>
Date: Wed, 8 May 2024 22:08:10 +0300
Subject: [PATCH] metal : use `vm_allocate` instead of `posix_memalign` on
 macOS (llama/7078)

* fix: use `malloc` instead of `posix_memalign` in `ggml-metal.m` to make it not crash Electron proccesses

* fix: typo

* fix: use `vm_allocate` instead of `posix_memalign`

* fix: don't call `newBufferWithBytesNoCopy` with `NULL` when `ggml_metal_host_malloc` returns `NULL`

* fix: use `vm_allocate` only on macOS
---
 ggml-metal.m | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/ggml-metal.m b/ggml-metal.m
index 4d4b9717..038a5061 100644
--- a/ggml-metal.m
+++ b/ggml-metal.m
@@ -266,11 +266,20 @@ static void ggml_metal_log(enum ggml_log_level level, const char * format, ...){
 
 static void * ggml_metal_host_malloc(size_t n) {
     void * data = NULL;
+
+#if TARGET_OS_OSX
+    kern_return_t err = vm_allocate((vm_map_t) mach_task_self(), (void *) &data, n, VM_FLAGS_ANYWHERE);
+    if (err != KERN_SUCCESS) {
+        GGML_METAL_LOG_ERROR("%s: error: vm_allocate failed\n", __func__);
+        return NULL;
+    }
+#else
     const int result = posix_memalign((void **) &data, sysconf(_SC_PAGESIZE), n);
     if (result != 0) {
         GGML_METAL_LOG_ERROR("%s: error: posix_memalign failed\n", __func__);
         return NULL;
     }
+#endif
 
     return data;
 }
@@ -2855,7 +2864,11 @@ GGML_CALL static void ggml_backend_metal_buffer_free_buffer(ggml_backend_buffer_
     ggml_backend_metal_free_device();
 
     if (ctx->owned) {
+#if TARGET_OS_OSX
+        vm_deallocate((vm_map_t)mach_task_self(), (vm_address_t)ctx->all_data, ctx->all_size);
+#else
         free(ctx->all_data);
+#endif
     }
 
     free(ctx);
@@ -2959,14 +2972,16 @@ GGML_CALL static ggml_backend_buffer_t ggml_backend_metal_buffer_type_alloc_buff
     ctx->owned = true;
     ctx->n_buffers = 1;
 
-    ctx->buffers[0].data = ctx->all_data;
-    ctx->buffers[0].size = size;
-    ctx->buffers[0].metal = [device newBufferWithBytesNoCopy:ctx->all_data
-                    length:size_aligned
-                    options:MTLResourceStorageModeShared
-                    deallocator:nil];
+    if (ctx->all_data != NULL) {
+        ctx->buffers[0].data = ctx->all_data;
+        ctx->buffers[0].size = size;
+        ctx->buffers[0].metal = [device newBufferWithBytesNoCopy:ctx->all_data
+                        length:size_aligned
+                        options:MTLResourceStorageModeShared
+                        deallocator:nil];
+    }
 
-    if (ctx->buffers[0].metal == nil) {
+    if (ctx->all_data == NULL || ctx->buffers[0].metal == nil) {
         GGML_METAL_LOG_ERROR("%s: error: failed to allocate buffer, size = %8.2f MiB\n", __func__, size_aligned / 1024.0 / 1024.0);
         free(ctx);
         ggml_backend_metal_free_device();