From 71eb4a6672872d2eff0190e50db42c0f70f7b39f Mon Sep 17 00:00:00 2001
From: oberdfr <alebennella@gmail.com>
Date: Sat, 23 May 2026 19:04:22 +0200
Subject: [PATCH] vega10: implement PSP mode1 reset

When the GPU gets released, the guest driver halts the GPU's SMU.
On subsequent reset events, this module attempts a BACO reset
which requires a responsive SMU to enter BACO state.
With the SMU halted, PPSMC_MSG_EnterBaco times out and the BACO reset fails,
leaving the GPU in an unusable state until the host is rebooted.

Add a PSP (Platform Security Processor) Mode 1 Reset path for
Vega10.
This work the same way as this amdgpu kernel driver patch:
https://lists.freedesktop.org/archives/amd-gfx/2017-September/013203.html
and its inspired from the already implemented mode1 reset for Vega20.

Mode 1 Reset sends a hardware reset command (GFX_CTRL_CMD_ID_MODE1_RST)
directly to the PSP via the MP0_SMN_C2PMSG_64 mailbox register,
bypassing the unresponsive SMU entirely.

The Mode 1 Reset is attempted first in the reset sequence.
The existing BACO path is used as a fallback.

Tested on
AMD Radeon RX Vega 56 (device 0x687f)
Proxmox VE 9.2.2
kernel 7.0.2-6-pve

Confirmed that VMs can be started, stopped, and restarted repeatedly without
requiring a host reboot.
---
 src/amd/vega10.c | 60 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 53 insertions(+), 7 deletions(-)

diff --git a/src/amd/vega10.c b/src/amd/vega10.c
index 21b733e..4df190a 100644
--- a/src/amd/vega10.c
+++ b/src/amd/vega10.c
@@ -30,6 +30,7 @@ Place, Suite 330, Boston, MA 02111-1307 USA
 #include "common.h"
 #include "compat.h"
 #include "common_baco.h"
+#include "psp_gfx_if.h"
 
 /* MP Apertures, from smu9_smumgr.c */
 #define MP0_Public 0x03800000
@@ -126,6 +127,41 @@ int vega10_baco_set_state(struct amd_fake_dev *adev, enum BACO_STATE state)
   return -EINVAL;
 }
 
+static int amd_vega10_mode1_reset(struct amd_fake_dev *adev)
+{
+  int ret, i;
+  uint32_t offset;
+  uint32_t pci_regs[128];
+  struct pci_dev *pdev = adev_to_amd_private(adev)->vdev->pdev;
+
+  offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64);
+  ret = psp_wait_for(adev, offset, 0x80000000, 0x8000FFFF, false);
+  if (ret) {
+    vr_warn(adev_to_amd_private(adev)->vdev,
+            "psp not working for mode1 reset\n");
+    return ret;
+  }
+
+  /* send mode 1 reset command to PSP */
+  WREG32(offset, GFX_CTRL_CMD_ID_MODE1_RST);
+  msleep(500);
+
+  /* check if PSP came back */
+  offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33);
+  ret = psp_wait_for(adev, offset, 0x80000000, 0x80000000, false);
+
+  if (ret) {
+    vr_warn(adev_to_amd_private(adev)->vdev,
+            "psp mode1 reset completed but PSP not responding\n");
+    return ret;
+  }
+
+  vr_info(adev_to_amd_private(adev)->vdev,
+          "psp mode1 reset succeeded\n");
+
+  return 0;
+}
+
 static int amd_vega10_reset(struct vendor_reset_dev *dev)
 {
   struct amd_vendor_private *priv = amd_private(dev);
@@ -150,13 +186,6 @@ static int amd_vega10_reset(struct vendor_reset_dev *dev)
     goto free_adev;
   }
 
-  ret = atom_bios_init(adev);
-  if (ret)
-  {
-    vr_err(dev, "atom_bios_init failed: %d\n", ret);
-    goto free_adev;
-  }
-
   /* it's important we wait for the SOC to be ready */
   for (timeout = 100000; timeout; --timeout)
   {
@@ -183,6 +212,23 @@ static int amd_vega10_reset(struct vendor_reset_dev *dev)
       psp_bl_ready ? "yes" : "no",
       baco_state == BACO_STATE_IN ? "on" : "off");
 
+  /* Try PSP Mode 1 Reset first. Preferred when the SMU is unresponsive */
+  ret = amd_vega10_mode1_reset(adev);
+  if (!ret)
+  {
+    vr_info(dev, "mode1 reset succeeded, skipping BACO\n");
+    goto free_adev;
+  }
+
+  vr_info(dev, "mode1 reset failed, falling back to BACO\n");
+
+  ret = atom_bios_init(adev);
+  if (ret)
+  {
+    vr_err(dev, "atom_bios_init failed: %d\n", ret);
+    goto free_adev;
+  }
+
   if (sol == ~1L && baco_state != BACO_STATE_IN)
   {
     vr_warn(dev, "timed out waiting for SOL to be valid\n");