From 043ceb0e64750ce29aec6551bd8ae94ac4fbbae6 Mon Sep 17 00:00:00 2001
From: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Date: Fri, 19 Nov 2021 10:23:05 -0500
Subject: drm/amdkfd: CRIU checkpoint and restore xnack mode
Git-commit: 4717fe3d8dec42bc951a44f41efc95d635d26325
Patch-mainline: v5.18-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

Recoverable page faults are represented by the xnack mode setting inside
a kfd process and are used to represent the device page faults. For CR,
we don't consider negative values which are typically used for querying
the current xnack mode without modifying it.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 15 +++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  1 +
 2 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index ab5107a3fe36..3ec44f71307d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1848,6 +1848,11 @@ static int criu_checkpoint_process(struct kfd_process *p,
 	memset(&process_priv, 0, sizeof(process_priv));
 
 	process_priv.version = KFD_CRIU_PRIV_VERSION;
+	/* For CR, we don't consider negative xnack mode which is used for
+	 * querying without changing it, here 0 simply means disabled and 1
+	 * means enabled so retry for finding a valid PTE.
+	 */
+	process_priv.xnack_mode = p->xnack_enabled ? 1 : 0;
 
 	ret = copy_to_user(user_priv_data + *priv_offset,
 				&process_priv, sizeof(process_priv));
@@ -2241,6 +2246,16 @@ static int criu_restore_process(struct kfd_process *p,
 		return -EINVAL;
 	}
 
+	pr_debug("Setting XNACK mode\n");
+	if (process_priv.xnack_mode && !kfd_process_xnack_mode(p, true)) {
+		pr_err("xnack mode cannot be set\n");
+		ret = -EPERM;
+		goto exit;
+	} else {
+		pr_debug("set xnack mode: %d\n", process_priv.xnack_mode);
+		p->xnack_enabled = process_priv.xnack_mode;
+	}
+
 exit:
 	return ret;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 18a8fdc574cd..cc024c05ee45 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -1057,6 +1057,7 @@ void kfd_process_set_trap_handler(struct qcm_process_device *qpd,
 
 struct kfd_criu_process_priv_data {
 	uint32_t version;
+	uint32_t xnack_mode;
 };
 
 struct kfd_criu_device_priv_data {
-- 
2.38.1