[Patch v4 18/24] drm/amdkfd: CRIU checkpoint and restore xnack mode

[Rajneesh Bhardwaj]

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.

Signed-off-by: Rajneesh Bhardwaj <rajneesh.bhardwaj at amd.com>
---
 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 178b0ccfb286..446eb9310915 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1845,6 +1845,11 @@ 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));
@@ -2231,6 +2236,16 @@ 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 855c162b85ea..d72dda84c18c 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 {
-- 
2.17.1