anv: Advertise larger heap sizes

Instead of just advertising the aperture size, we do something more
intelligent.  On systems with a full 48-bit PPGTT, we can address 100%
of the available system RAM from the GPU.  In order to keep clients from
burning 100% of your available RAM for graphics resources, we have a
nice little heuristic (which has received exactly zero tuning) to keep
things under a reasonable level of control.

Reviewed-by: Kristian H. Kristensen <krh@bitplanet.net>

diff --git a/src/intel/vulkan/anv_device.c b/src/intel/vulkan/anv_device.c
index 22dd5d6bf3da145bf85fcf177aecb0caa7935acc..356b1b5f0d2873fa0c5ee48f7f52ead3c92bdfe5 100644 (file)
--- a/src/intel/vulkan/anv_device.c
+++ b/src/intel/vulkan/anv_device.c
@@ -25,6 +25,7 @@
 #include <stdbool.h>
 #include <string.h>
 #include <sys/mman.h>
+#include <sys/sysinfo.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <xf86drm.h>
@@ -53,6 +54,48 @@ compiler_perf_log(void *data, const char *fmt, ...)
    va_end(args);
 }
 
+static VkResult
+anv_compute_heap_size(int fd, uint64_t *heap_size)
+{
+   uint64_t gtt_size;
+   if (anv_gem_get_context_param(fd, 0, I915_CONTEXT_PARAM_GTT_SIZE,
+                                 &gtt_size) == -1) {
+      /* If, for whatever reason, we can't actually get the GTT size from the
+       * kernel (too old?) fall back to the aperture size.
+       */
+      anv_perf_warn("Failed to get I915_CONTEXT_PARAM_GTT_SIZE: %m");
+
+      if (anv_gem_get_aperture(fd, &gtt_size) == -1) {
+         return vk_errorf(VK_ERROR_INITIALIZATION_FAILED,
+                          "failed to get aperture size: %m");
+      }
+   }
+
+   /* Query the total ram from the system */
+   struct sysinfo info;
+   sysinfo(&info);
+
+   uint64_t total_ram = (uint64_t)info.totalram * (uint64_t)info.mem_unit;
+
+   /* We don't want to burn too much ram with the GPU.  If the user has 4GiB
+    * or less, we use at most half.  If they have more than 4GiB, we use 3/4.
+    */
+   uint64_t available_ram;
+   if (total_ram <= 4ull * 1024ull * 1024ull * 1024ull)
+      available_ram = total_ram / 2;
+   else
+      available_ram = total_ram * 3 / 4;
+
+   /* We also want to leave some padding for things we allocate in the driver,
+    * so don't go over 3/4 of the GTT either.
+    */
+   uint64_t available_gtt = gtt_size * 3 / 4;
+
+   *heap_size = MIN2(available_ram, available_gtt);
+
+   return VK_SUCCESS;
+}
+
 static bool
 anv_device_get_cache_uuid(void *uuid)
 {
@@ -124,12 +167,6 @@ anv_physical_device_init(struct anv_physical_device *device,
       }
    }
 
-   if (anv_gem_get_aperture(fd, &device->aperture_size) == -1) {
-      result = vk_errorf(VK_ERROR_INITIALIZATION_FAILED,
-                         "failed to get aperture size: %m");
-      goto fail;
-   }
-
    if (!anv_gem_get_param(fd, I915_PARAM_HAS_WAIT_TIMEOUT)) {
       result = vk_errorf(VK_ERROR_INITIALIZATION_FAILED,
                          "kernel missing gem wait");
@@ -151,6 +188,10 @@ anv_physical_device_init(struct anv_physical_device *device,
 
    device->supports_48bit_addresses = anv_gem_supports_48b_addresses(fd);
 
+   result = anv_compute_heap_size(fd, &device->heap_size);
+   if (result != VK_SUCCESS)
+      goto fail;
+
    if (!anv_device_get_cache_uuid(device->uuid)) {
       result = vk_errorf(VK_ERROR_INITIALIZATION_FAILED,
                          "cannot generate UUID");
@@ -735,12 +776,6 @@ void anv_GetPhysicalDeviceMemoryProperties(
     VkPhysicalDeviceMemoryProperties*           pMemoryProperties)
 {
    ANV_FROM_HANDLE(anv_physical_device, physical_device, physicalDevice);
-   VkDeviceSize heap_size;
-
-   /* Reserve some wiggle room for the driver by exposing only 75% of the
-    * aperture to the heap.
-    */
-   heap_size = 3 * physical_device->aperture_size / 4;
 
    if (physical_device->info.has_llc) {
       /* Big core GPUs share LLC with the CPU and thus one memory type can be
@@ -777,7 +812,7 @@ void anv_GetPhysicalDeviceMemoryProperties(
 
    pMemoryProperties->memoryHeapCount = 1;
    pMemoryProperties->memoryHeaps[0] = (VkMemoryHeap) {
-      .size = heap_size,
+      .size = physical_device->heap_size,
       .flags = VK_MEMORY_HEAP_DEVICE_LOCAL_BIT,
    };
 }

diff --git a/src/intel/vulkan/anv_gem.c b/src/intel/vulkan/anv_gem.c
index 6a996ea3db898b97e9ec99acb57b3d060a12f837..2d07a3dbb0ebefd0da963139b0fdfaa0d2191909 100644 (file)
--- a/src/intel/vulkan/anv_gem.c
+++ b/src/intel/vulkan/anv_gem.c
@@ -287,6 +287,22 @@ anv_gem_destroy_context(struct anv_device *device, int context)
    return anv_ioctl(device->fd, DRM_IOCTL_I915_GEM_CONTEXT_DESTROY, &destroy);
 }
 
+int
+anv_gem_get_context_param(int fd, int context, uint32_t param, uint64_t *value)
+{
+   struct drm_i915_gem_context_param gp = {
+      .ctx_id = context,
+      .param = param,
+   };
+
+   int ret = anv_ioctl(fd, DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM, &gp);
+   if (ret == -1)
+      return -1;
+
+   *value = gp.value;
+   return 0;
+}
+
 int
 anv_gem_get_aperture(int fd, uint64_t *size)
 {

diff --git a/src/intel/vulkan/anv_private.h b/src/intel/vulkan/anv_private.h
index 03381999152a09f6deb0c3065acc0e20adfe85b4..95666d8f4b6615d77451318986a8ceb06abfde77 100644 (file)
--- a/src/intel/vulkan/anv_private.h
+++ b/src/intel/vulkan/anv_private.h
@@ -516,7 +516,15 @@ struct anv_physical_device {
     char                                        path[20];
     const char *                                name;
     struct gen_device_info                      info;
-    uint64_t                                    aperture_size;
+    /** Amount of "GPU memory" we want to advertise
+     *
+     * Clearly, this value is bogus since Intel is a UMA architecture.  On
+     * gen7 platforms, we are limited by GTT size unless we want to implement
+     * fine-grained tracking and GTT splitting.  On Broadwell and above we are
+     * practically unlimited.  However, we will never report more than 3/4 of
+     * the total system ram to try and avoid running out of RAM.
+     */
+    uint64_t                                    heap_size;
     bool                                        supports_48bit_addresses;
     struct brw_compiler *                       compiler;
     struct isl_device                           isl_dev;
@@ -652,6 +660,8 @@ int anv_gem_set_tiling(struct anv_device *device, uint32_t gem_handle,
                        uint32_t stride, uint32_t tiling);
 int anv_gem_create_context(struct anv_device *device);
 int anv_gem_destroy_context(struct anv_device *device, int context);
+int anv_gem_get_context_param(int fd, int context, uint32_t param,
+                              uint64_t *value);
 int anv_gem_get_param(int fd, uint32_t param);
 bool anv_gem_get_bit6_swizzle(int fd, uint32_t tiling);
 int anv_gem_get_aperture(int fd, uint64_t *size);