[PATCH V2 09/20] accel/amdxdna: Add context switch hysteresis with debugfs control

[David Zhang <yidong.zhang@amd.com>]

Add aie4_set_ctx_hysteresis() to configure the AIE4 context switch
hysteresis timeout via the SET_RUNTIME_CONFIG message, applied at hw
start (PF and classic paths) with a default of 1000 us.

Expose a debugfs node 'ctx_switch_hysteresis_us' to change the timeout
at runtime (0 disables hysteresis). The stored value is re-applied on
every hw start so it survives runtime suspend/resume.

Co-developed-by: Nishad Saraf <nishads@amd.com>
Signed-off-by: Nishad Saraf <nishads@amd.com>
Signed-off-by: David Zhang <yidong.zhang@amd.com>
---
 drivers/accel/amdxdna/aie4_message.c    | 43 +++++++++++++
 drivers/accel/amdxdna/aie4_msg_priv.h   | 24 +++++++
 drivers/accel/amdxdna/aie4_pci.c        | 83 ++++++++++++++++++++++++-
 drivers/accel/amdxdna/aie4_pci.h        |  9 +++
 drivers/accel/amdxdna/amdxdna_debugfs.c |  3 +
 drivers/accel/amdxdna/amdxdna_pci_drv.h |  1 +
 6 files changed, 161 insertions(+), 2 deletions(-)

diff --git a/drivers/accel/amdxdna/aie4_message.c b/drivers/accel/amdxdna/aie4_message.c
index 7112b0bc3725..5720aa88e6d6 100644
--- a/drivers/accel/amdxdna/aie4_message.c
+++ b/drivers/accel/amdxdna/aie4_message.c
@@ -262,3 +262,46 @@ int aie4_msg_set_power_mode(struct amdxdna_dev_hdl *ndev, u8 power_mode)
 
 	return ret;
 }
+
+int aie4_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type,
+			 const void *data, size_t size)
+{
+	DECLARE_AIE_MSG(aie4_msg_set_runtime_cfg, AIE4_MSG_OP_SET_RUNTIME_CONFIG);
+	u8 buf[sizeof(req.type) + AIE4_RUNTIME_CFG_MAX_DATA_SIZE] = { 0 };
+	int ret;
+
+	if (size > AIE4_RUNTIME_CFG_MAX_DATA_SIZE)
+		return -EINVAL;
+
+	/* Stage runtime config type and payload for firmware mailbox message. */
+	req.type = type;
+	memcpy(buf, &req.type, sizeof(req.type));
+	memcpy(buf + sizeof(req.type), data, size);
+
+	msg.send_data = buf;
+	msg.send_size = sizeof(req.type) + size;
+
+	ret = aie_send_mgmt_msg_wait(&ndev->aie, &msg);
+	if (ret)
+		XDNA_ERR(ndev->aie.xdna, "Failed to set runtime cfg %u: %d", type, ret);
+	return ret;
+}
+
+int aie4_set_ctx_hysteresis(struct amdxdna_dev_hdl *ndev, u32 timeout_us)
+{
+	struct aie4_msg_runtime_config_ctx_switch_hysteresis cfg = {
+		.timeout_us = timeout_us,
+	};
+	int ret;
+
+	ret = aie4_set_runtime_cfg(ndev, AIE4_RUNTIME_CONFIG_CTX_SWITCH_HYSTERESIS,
+				   &cfg, sizeof(cfg));
+	if (ret)
+		XDNA_WARN(ndev->aie.xdna,
+			  "Failed to set ctx switch hysteresis to %u us (%d), using fw default",
+			  timeout_us, ret);
+	else
+		XDNA_DBG(ndev->aie.xdna, "Context switch hysteresis set to %u us", timeout_us);
+
+	return ret;
+}
diff --git a/drivers/accel/amdxdna/aie4_msg_priv.h b/drivers/accel/amdxdna/aie4_msg_priv.h
index fe78df9e23c8..636bf8d04c76 100644
--- a/drivers/accel/amdxdna/aie4_msg_priv.h
+++ b/drivers/accel/amdxdna/aie4_msg_priv.h
@@ -12,6 +12,7 @@
 enum aie4_msg_opcode {
 	AIE4_MSG_OP_IDENTIFY                         = 0x10002,
 	AIE4_MSG_OP_SUSPEND                          = 0x10003,
+	AIE4_MSG_OP_SET_RUNTIME_CONFIG               = 0x10007,
 	AIE4_MSG_OP_QUERY_CERT_FIRMWARE_VERSION      = 0x1000F,
 
 	AIE4_MSG_OP_CREATE_VFS                       = 0x20001,
@@ -65,6 +66,29 @@ struct aie4_msg_suspend_resp {
 	enum aie4_msg_status status;
 } __packed;
 
+/* Type selector for AIE4_MSG_OP_SET_RUNTIME_CONFIG. */
+enum aie4_msg_runtime_config_type {
+	AIE4_RUNTIME_CONFIG_CTX_SWITCH_HYSTERESIS	= 0xD,
+	AIE4_MAX_RUNTIME_CONFIG
+};
+
+struct aie4_msg_set_runtime_cfg_req {
+	__u32 type;
+	__u8 data[4];
+} __packed;
+
+struct aie4_msg_set_runtime_cfg_resp {
+	enum aie4_msg_status status;
+} __packed;
+
+/* Maximum payload for runtime config firmware message. */
+#define AIE4_RUNTIME_CFG_MAX_DATA_SIZE 16
+
+/* Context switch hysteresis timeout in microseconds (0 disables). */
+struct aie4_msg_runtime_config_ctx_switch_hysteresis {
+	__u32 timeout_us;
+} __packed;
+
 struct aie4_msg_create_vfs_req {
 	__u32 vf_cnt;
 } __packed;
diff --git a/drivers/accel/amdxdna/aie4_pci.c b/drivers/accel/amdxdna/aie4_pci.c
index 3e02dabaf5fe..a315d2a5607e 100644
--- a/drivers/accel/amdxdna/aie4_pci.c
+++ b/drivers/accel/amdxdna/aie4_pci.c
@@ -5,8 +5,10 @@
 
 #include <drm/amdxdna_accel.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_file.h>
 #include <drm/drm_managed.h>
 #include <drm/drm_print.h>
+#include <linux/debugfs.h>
 #include <linux/firmware.h>
 #include <linux/sizes.h>
 
@@ -315,6 +317,22 @@ int aie4_restore_power_mode(struct amdxdna_dev_hdl *ndev)
 	return aie4_msg_set_power_mode(ndev, ndev->pw_mode);
 }
 
+static int aie4_config_fw(struct amdxdna_dev_hdl *ndev)
+{
+	int ret;
+
+	ret = aie4_attach_work_buffer(ndev);
+	if (ret)
+		return ret;
+
+	/* Best-effort tuning knob; failure is warned inside and does not fail hw start */
+	ret = aie4_set_ctx_hysteresis(ndev, ndev->ctx_switch_hysteresis_us);
+	if (ret == -ETIME)
+		return ret;
+
+	return 0;
+}
+
 static int aie4_pf_hw_start(struct amdxdna_dev_hdl *ndev)
 {
 	int ret;
@@ -327,7 +345,7 @@ static int aie4_pf_hw_start(struct amdxdna_dev_hdl *ndev)
 	if (ret)
 		goto stop_fw;
 
-	ret = aie4_attach_work_buffer(ndev);
+	ret = aie4_config_fw(ndev);
 	if (ret)
 		goto mbox_fini;
 
@@ -411,7 +429,7 @@ static int aie4_classic_hw_start(struct amdxdna_dev_hdl *ndev)
 	if (ret)
 		goto mailbox_fini;
 
-	ret = aie4_attach_work_buffer(ndev);
+	ret = aie4_config_fw(ndev);
 	if (ret)
 		goto mailbox_fini;
 
@@ -566,6 +584,7 @@ static int aie4m_pcidev_init(struct amdxdna_dev *xdna)
 
 	ndev->priv = xdna->dev_info->dev_priv;
 	ndev->aie.xdna = xdna;
+	ndev->ctx_switch_hysteresis_us = AIE4_CTX_HYSTERESIS_US;
 	ndev->pw_mode = POWER_MODE_DEFAULT;
 	xdna->dev_handle = ndev;
 
@@ -911,15 +930,74 @@ static void aie4_classic_fini(struct amdxdna_dev *xdna)
 	aie4_free_work_buffer(xdna->dev_handle);
 }
 
+static int aie4_ctx_hysteresis_get(void *data, u64 *val)
+{
+	struct amdxdna_dev_hdl *ndev = data;
+	struct amdxdna_dev *xdna = ndev->aie.xdna;
+
+	guard(mutex)(&xdna->dev_lock);
+	*val = ndev->ctx_switch_hysteresis_us;
+
+	return 0;
+}
+
+static int aie4_ctx_hysteresis_set(void *data, u64 val)
+{
+	struct amdxdna_dev_hdl *ndev = data;
+	struct amdxdna_dev *xdna = ndev->aie.xdna;
+	int ret, idx;
+
+	if (val > U32_MAX)
+		return -EINVAL;
+
+	if (!drm_dev_enter(&xdna->ddev, &idx))
+		return -ENODEV;
+
+	mutex_lock(&xdna->dev_lock);
+
+	ret = amdxdna_pm_resume_get_locked(xdna);
+	if (ret)
+		goto unlock;
+
+	ret = aie4_set_ctx_hysteresis(ndev, (u32)val);
+	if (!ret)
+		ndev->ctx_switch_hysteresis_us = (u32)val;
+
+	amdxdna_pm_suspend_put(xdna);
+
+unlock:
+	mutex_unlock(&xdna->dev_lock);
+	drm_dev_exit(idx);
+
+	return ret;
+}
+
+/* Context switch hysteresis timeout in microseconds; 0 disables hysteresis. */
+DEFINE_DEBUGFS_ATTRIBUTE(aie4_ctx_hysteresis_fops, aie4_ctx_hysteresis_get,
+			 aie4_ctx_hysteresis_set, "%llu\n");
+
+static void aie4_debugfs_init(struct amdxdna_dev *xdna)
+{
+	struct amdxdna_dev_hdl *ndev = xdna->dev_handle;
+
+	/* Context switch hysteresis is only supported on PF and classic devices. */
+	if (!to_pci_dev(xdna->ddev.dev)->is_virtfn)
+		debugfs_create_file_unsafe("ctx_switch_hysteresis_us", 0600,
+					   xdna->ddev.accel->debugfs_root, ndev,
+					   &aie4_ctx_hysteresis_fops);
+}
+
 const struct amdxdna_dev_ops aie4_pf_ops = {
 	.init			= aie4_pf_init,
 	.fini			= aie4_pf_fini,
+	.debugfs_init		= aie4_debugfs_init,
 	.sriov_configure        = aie4_sriov_configure,
 };
 
 const struct amdxdna_dev_ops aie4_vf_ops = {
 	.init			= aie4_vf_init,
 	.fini			= aie4_vf_fini,
+	.debugfs_init		= aie4_debugfs_init,
 	.hwctx_init		= aie4_hwctx_init,
 	.hwctx_fini		= aie4_hwctx_fini,
 	.cmd_wait		= aie4_cmd_wait,
@@ -930,6 +1008,7 @@ const struct amdxdna_dev_ops aie4_vf_ops = {
 const struct amdxdna_dev_ops aie4_classic_ops = {
 	.init			= aie4_classic_init,
 	.fini			= aie4_classic_fini,
+	.debugfs_init		= aie4_debugfs_init,
 	.hwctx_init		= aie4_hwctx_init,
 	.hwctx_fini		= aie4_hwctx_fini,
 	.cmd_wait		= aie4_cmd_wait,
diff --git a/drivers/accel/amdxdna/aie4_pci.h b/drivers/accel/amdxdna/aie4_pci.h
index 6e9e7f874a44..959ef3695813 100644
--- a/drivers/accel/amdxdna/aie4_pci.h
+++ b/drivers/accel/amdxdna/aie4_pci.h
@@ -14,6 +14,9 @@
 #include "aie4_msg_priv.h"
 #include "amdxdna_mailbox.h"
 
+/* Default context switch hysteresis timeout in microseconds. */
+#define AIE4_CTX_HYSTERESIS_US	1000
+
 struct cert_comp {
 	struct amdxdna_dev_hdl          *ndev;
 	u32                             msix_idx;
@@ -69,6 +72,9 @@ struct amdxdna_dev_hdl {
 
 	u8				pw_mode;
 
+	/* Context switch hysteresis timeout in microseconds. */
+	u32				ctx_switch_hysteresis_us;
+
 	struct amdxdna_drm_query_firmware_version cert_version;
 };
 
@@ -92,6 +98,9 @@ int aie4_init_dpm_freq_table(struct amdxdna_dev_hdl *ndev);
 int aie4_query_dpm_level(struct amdxdna_dev_hdl *ndev,
 			 u32 *aieclk_dpm_level, u32 *npuhclk_dpm_level);
 int aie4_msg_set_power_mode(struct amdxdna_dev_hdl *ndev, u8 power_mode);
+int aie4_set_runtime_cfg(struct amdxdna_dev_hdl *ndev, u32 type,
+			 const void *data, size_t size);
+int aie4_set_ctx_hysteresis(struct amdxdna_dev_hdl *ndev, u32 timeout_us);
 u32 aie4_msg_pasid(struct amdxdna_client *client);
 
 /* aie4_ctx.c */
diff --git a/drivers/accel/amdxdna/amdxdna_debugfs.c b/drivers/accel/amdxdna/amdxdna_debugfs.c
index a6ec17c63629..1f63cc91b168 100644
--- a/drivers/accel/amdxdna/amdxdna_debugfs.c
+++ b/drivers/accel/amdxdna/amdxdna_debugfs.c
@@ -126,4 +126,7 @@ void amdxdna_debugfs_init(struct amdxdna_dev *xdna)
 				    xdna,
 				    amdxdna_dbgfs_files[i].fops);
 	}
+
+	if (xdna->dev_info->ops->debugfs_init)
+		xdna->dev_info->ops->debugfs_init(xdna);
 }
diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.h b/drivers/accel/amdxdna/amdxdna_pci_drv.h
index 953bf783b3f7..11f46ec738d7 100644
--- a/drivers/accel/amdxdna/amdxdna_pci_drv.h
+++ b/drivers/accel/amdxdna/amdxdna_pci_drv.h
@@ -54,6 +54,7 @@ struct amdxdna_sched_job;
 struct amdxdna_dev_ops {
 	int (*init)(struct amdxdna_dev *xdna);
 	void (*fini)(struct amdxdna_dev *xdna);
+	void (*debugfs_init)(struct amdxdna_dev *xdna);
 	int (*resume)(struct amdxdna_dev *xdna);
 	int (*suspend)(struct amdxdna_dev *xdna);
 	int (*sriov_configure)(struct amdxdna_dev *xdna, int num_vfs);
-- 
2.34.1