mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-16 09:39:58 -04:00
A mirror is made while a submission is recorded, and its first copy of the pool is in that submission's prologue. The table's pages moved to the mirror at once, and the table is memory the shaders read as they run: every part already handed to the queue read the mirror through it before the copy had run, memory nothing had written yet and, on a card over its budget, a block the driver had not made resident for those parts. A GTX 1650 4 GB lost its device that way at area loads in every session of 0.7.1 (#507): six reports of a GPU read fault at byte 0 of a mirror made in the faulting submission, each the first byte of a new 2 MiB-aligned block, with mirrors being made over the budget, and none with the table kept empty. The mirror code is the same in 0.9.2. Now the pages keep reading the imported buffer and take the mirror as their twin, so what shaders write through the table goes to both and what they read is guest memory, as before the mirror existed. Once the GPU has finished the submission that holds the copy, the pages move to the mirror with the imported buffer as the twin. gpa_late = 0 moves them at once, as before. tests/gpa_check.py covers the new table step; the mirror side was compiled and run through --probe-vkmem, not played. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
33 lines
2.3 KiB
C
33 lines
2.3 KiB
C
// The device address table (vk_gpa.c): GPU address pages to buffer device addresses for shaders' global memory accesses.
|
|
#pragma once
|
|
#include <stdint.h>
|
|
|
|
#include "vk.h"
|
|
|
|
#define VK_GPA_CB_SLOT 0x40 // res.json cb_slot of the table (translator ResourceManager.DeviceAddressTableCbSlot)
|
|
|
|
int vk_gpa_wanted(void); // the device has buffer device addresses and NX2NAVI_GPA is not 0
|
|
int vk_gpa_wanted_ctx(const VkCtx *c); // the same during device creation, before vk_ctx() returns it
|
|
int vk_gpa_on(void); // the table exists (created on first use)
|
|
uint64_t vk_gpa_device_address(VkBuffer b);
|
|
VkDescriptorBufferInfo vk_gpa_info(void); // the whole table, for a storage descriptor
|
|
// Maps the pages [lo, hi) holds whole to buf, whose byte 0 is GPU address buf_lo. Returns the record (0: not mapped).
|
|
uint32_t vk_gpa_map(uint64_t lo, uint64_t hi, VkBuffer buf, uint64_t buf_lo);
|
|
// Unmaps the pages of [lo, hi) that name rec; cover (may be NULL) gives the record of another live buffer that holds a
|
|
// page whole, or 0. rec is reused once the GPU finished the submissions issued until now.
|
|
void vk_gpa_unmap(uint64_t lo, uint64_t hi, uint32_t rec, uint32_t (*cover)(uint64_t page_addr));
|
|
// Unmaps every page of [lo, hi), whatever record it names (pages of a virtual pool whose physical memory goes away).
|
|
void vk_gpa_clear(uint64_t lo, uint64_t hi);
|
|
// Moves the pages of [lo, hi) that name old_rec (or none) to buf (a pool's VRAM mirror), with old_rec's buffer as their
|
|
// twin, which shaders write too; returns the new record.
|
|
uint32_t vk_gpa_remap(uint64_t lo, uint64_t hi, uint32_t old_rec, VkBuffer buf, uint64_t buf_lo);
|
|
// The same without the twin: the pages name buf alone (a pool whose VRAM mirror is evicted goes back to its imported
|
|
// buffer).
|
|
uint32_t vk_gpa_remap_plain(uint64_t lo, uint64_t hi, uint32_t old_rec, VkBuffer buf, uint64_t buf_lo);
|
|
// The pages of [lo, hi) that name old_rec keep reading old_rec's buffer and get buf as their twin: shaders read the
|
|
// pool where they did and write buf too (a VRAM mirror until its first copy has run, vk_memory.c mirror_create).
|
|
// Returns the new record, or 0 when there is none to give or twins are off (old_rec then stays as it is).
|
|
uint32_t vk_gpa_remap_writes(uint64_t lo, uint64_t hi, uint32_t old_rec, VkBuffer buf, uint64_t buf_lo);
|
|
void vk_gpa_report(void);
|
|
void vk_gpa_shutdown(void);
|