* [PATCH 01/11] accel/ivpu: Update FW API
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
[not found] ` <c83b4b50-fb25-6888-deb3-0a1e6a27165d@quicinc.com>
2023-10-25 9:43 ` [PATCH 02/11] accel/ivpu: Remove unneeded drm_driver dectaration Stanislaw Gruszka
` (9 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Stanislaw Gruszka, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Krystian Pradzynski
From: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Bump boot API to 4.20
Bump JSM API to 3.15
Signed-off-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_jsm_msg.c | 17 ++
drivers/accel/ivpu/vpu_boot_api.h | 90 ++++++++-
drivers/accel/ivpu/vpu_jsm_api.h | 309 ++++++++++++++++++++++++++++--
3 files changed, 392 insertions(+), 24 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 0c2fe7142024..35a689475c68 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -36,6 +36,17 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
IVPU_CASE_TO_STR(VPU_JSM_MSG_DESTROY_CMD_QUEUE);
IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES);
IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_REGISTER_DB);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_ENGINE_RESUME);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_STATE_DUMP_RSP);
IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT);
IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL);
IVPU_CASE_TO_STR(VPU_JSM_MSG_JOB_DONE);
@@ -65,6 +76,12 @@ const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type)
IVPU_CASE_TO_STR(VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP);
IVPU_CASE_TO_STR(VPU_JSM_MSG_BLOB_DEINIT_DONE);
IVPU_CASE_TO_STR(VPU_JSM_MSG_DYNDBG_CONTROL_RSP);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_PWR_D0I3_ENTER_DONE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_ENABLE_DONE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE);
+ IVPU_CASE_TO_STR(VPU_JSM_MSG_DCT_DISABLE_DONE);
}
#undef IVPU_CASE_TO_STR
diff --git a/drivers/accel/ivpu/vpu_boot_api.h b/drivers/accel/ivpu/vpu_boot_api.h
index 6b71be92ba65..04c954258563 100644
--- a/drivers/accel/ivpu/vpu_boot_api.h
+++ b/drivers/accel/ivpu/vpu_boot_api.h
@@ -11,7 +11,10 @@
* The bellow values will be used to construct the version info this way:
* fw_bin_header->api_version[VPU_BOOT_API_VER_ID] = (VPU_BOOT_API_VER_MAJOR << 16) |
* VPU_BOOT_API_VER_MINOR;
- * VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes.
+ * VPU_BOOT_API_VER_PATCH will be ignored. KMD and compatibility is not affected if this changes
+ * This information is collected by using vpuip_2/application/vpuFirmware/make_std_fw_image.py
+ * If a header is missing this info we ignore the header, if a header is missing or contains
+ * partial info a build error will be generated.
*/
/*
@@ -24,12 +27,12 @@
* Minor version changes when API backward compatibility is preserved.
* Resets to 0 if Major version is incremented.
*/
-#define VPU_BOOT_API_VER_MINOR 12
+#define VPU_BOOT_API_VER_MINOR 20
/*
* API header changed (field names, documentation, formatting) but API itself has not been changed
*/
-#define VPU_BOOT_API_VER_PATCH 2
+#define VPU_BOOT_API_VER_PATCH 4
/*
* Index in the API version table
@@ -63,6 +66,12 @@ struct vpu_firmware_header {
/* Size of memory require for firmware execution */
u32 runtime_size;
u32 shave_nn_fw_size;
+ /* Size of primary preemption buffer. */
+ u32 preemption_buffer_1_size;
+ /* Size of secondary preemption buffer. */
+ u32 preemption_buffer_2_size;
+ /* Space reserved for future preemption-related fields. */
+ u32 preemption_reserved[6];
};
/*
@@ -89,6 +98,14 @@ enum VPU_BOOT_L2_CACHE_CFG_TYPE {
VPU_BOOT_L2_CACHE_CFG_NUM = 2
};
+/** VPU MCA ECC signalling mode. By default, no signalling is used */
+enum VPU_BOOT_MCA_ECC_SIGNAL_TYPE {
+ VPU_BOOT_MCA_ECC_NONE = 0,
+ VPU_BOOT_MCA_ECC_CORR = 1,
+ VPU_BOOT_MCA_ECC_FATAL = 2,
+ VPU_BOOT_MCA_ECC_BOTH = 3
+};
+
/**
* Logging destinations.
*
@@ -131,9 +148,11 @@ enum vpu_trace_destination {
#define VPU_TRACE_PROC_BIT_ACT_SHV_3 22
#define VPU_TRACE_PROC_NO_OF_HW_DEVS 23
-/* KMB HW component IDs are sequential, so define first and last IDs. */
-#define VPU_TRACE_PROC_BIT_KMB_FIRST VPU_TRACE_PROC_BIT_LRT
-#define VPU_TRACE_PROC_BIT_KMB_LAST VPU_TRACE_PROC_BIT_SHV_15
+/* VPU 30xx HW component IDs are sequential, so define first and last IDs. */
+#define VPU_TRACE_PROC_BIT_30XX_FIRST VPU_TRACE_PROC_BIT_LRT
+#define VPU_TRACE_PROC_BIT_30XX_LAST VPU_TRACE_PROC_BIT_SHV_15
+#define VPU_TRACE_PROC_BIT_KMB_FIRST VPU_TRACE_PROC_BIT_30XX_FIRST
+#define VPU_TRACE_PROC_BIT_KMB_LAST VPU_TRACE_PROC_BIT_30XX_LAST
struct vpu_boot_l2_cache_config {
u8 use;
@@ -148,6 +167,25 @@ struct vpu_warm_boot_section {
u32 is_clear_op;
};
+/*
+ * When HW scheduling mode is enabled, a present period is defined.
+ * It will be used by VPU to swap between normal and focus priorities
+ * to prevent starving of normal priority band (when implemented).
+ * Host must provide a valid value at boot time in
+ * `vpu_focus_present_timer_ms`. If the value provided by the host is not within the
+ * defined range a default value will be used. Here we define the min. and max.
+ * allowed values and the and default value of the present period. Units are milliseconds.
+ */
+#define VPU_PRESENT_CALL_PERIOD_MS_DEFAULT 50
+#define VPU_PRESENT_CALL_PERIOD_MS_MIN 16
+#define VPU_PRESENT_CALL_PERIOD_MS_MAX 10000
+
+/**
+ * Macros to enable various operation modes within the VPU.
+ * To be defined as part of 32 bit mask.
+ */
+#define VPU_OP_MODE_SURVIVABILITY 0x1
+
struct vpu_boot_params {
u32 magic;
u32 vpu_id;
@@ -218,6 +256,7 @@ struct vpu_boot_params {
* the threshold will not be logged); applies to every enabled logging
* destination and loggable HW component. See 'mvLog_t' enum for acceptable
* values.
+ * TODO: EISW-33556: Move log level definition (mvLog_t) to this file.
*/
u32 default_trace_level;
u32 boot_type;
@@ -249,7 +288,36 @@ struct vpu_boot_params {
u32 temp_sensor_period_ms;
/** PLL ratio for efficient clock frequency */
u32 pn_freq_pll_ratio;
- u32 pad4[28];
+ /** DVFS Mode: Default: 0, Max Performance: 1, On Demand: 2, Power Save: 3 */
+ u32 dvfs_mode;
+ /**
+ * Depending on DVFS Mode:
+ * On-demand: Default if 0.
+ * Bit 0-7 - uint8_t: Highest residency percent
+ * Bit 8-15 - uint8_t: High residency percent
+ * Bit 16-23 - uint8_t: Low residency percent
+ * Bit 24-31 - uint8_t: Lowest residency percent
+ * Bit 32-35 - unsigned 4b: PLL Ratio increase amount on highest residency
+ * Bit 36-39 - unsigned 4b: PLL Ratio increase amount on high residency
+ * Bit 40-43 - unsigned 4b: PLL Ratio decrease amount on low residency
+ * Bit 44-47 - unsigned 4b: PLL Ratio decrease amount on lowest frequency
+ * Bit 48-55 - uint8_t: Period (ms) for residency decisions
+ * Bit 56-63 - uint8_t: Averaging windows (as multiples of period. Max: 30 decimal)
+ * Power Save/Max Performance: Unused
+ */
+ u64 dvfs_param;
+ /**
+ * D0i3 delayed entry
+ * Bit0: Disable CPU state save on D0i2 entry flow.
+ * 0: Every D0i2 entry saves state. Save state IPC message ignored.
+ * 1: IPC message required to save state on D0i3 entry flow.
+ */
+ u32 d0i3_delayed_entry;
+ /* Time spent by VPU in D0i3 state */
+ u64 d0i3_residency_time_us;
+ /* Value of VPU perf counter at the time of entering D0i3 state . */
+ u64 d0i3_entry_vpu_ts;
+ u32 pad4[20];
/* Warm boot information: 0x400 - 0x43F */
u32 warm_boot_sections_count;
u32 warm_boot_start_address_reference;
@@ -274,8 +342,12 @@ struct vpu_boot_params {
u32 vpu_scheduling_mode;
/* Present call period in milliseconds. */
u32 vpu_focus_present_timer_ms;
- /* Unused/reserved: 0x478 - 0xFFF */
- u32 pad6[738];
+ /* VPU ECC Signaling */
+ u32 vpu_uses_ecc_mca_signal;
+ /* Values defined by VPU_OP_MODE* macros */
+ u32 vpu_operation_mode;
+ /* Unused/reserved: 0x480 - 0xFFF */
+ u32 pad6[736];
};
/*
diff --git a/drivers/accel/ivpu/vpu_jsm_api.h b/drivers/accel/ivpu/vpu_jsm_api.h
index 2949ec8365bd..7da7622742be 100644
--- a/drivers/accel/ivpu/vpu_jsm_api.h
+++ b/drivers/accel/ivpu/vpu_jsm_api.h
@@ -22,12 +22,12 @@
/*
* Minor version changes when API backward compatibility is preserved.
*/
-#define VPU_JSM_API_VER_MINOR 0
+#define VPU_JSM_API_VER_MINOR 15
/*
* API header changed (field names, documentation, formatting) but API itself has not been changed
*/
-#define VPU_JSM_API_VER_PATCH 1
+#define VPU_JSM_API_VER_PATCH 0
/*
* Index in the API version table
@@ -84,11 +84,13 @@
* Job flags bit masks.
*/
#define VPU_JOB_FLAGS_NULL_SUBMISSION_MASK 0x00000001
+#define VPU_JOB_FLAGS_PRIVATE_DATA_MASK 0xFF000000
/*
* Sizes of the reserved areas in jobs, in bytes.
*/
-#define VPU_JOB_RESERVED_BYTES 16
+#define VPU_JOB_RESERVED_BYTES 8
+
/*
* Sizes of the reserved areas in job queues, in bytes.
*/
@@ -108,6 +110,20 @@
*/
#define VPU_DYNDBG_CMD_MAX_LEN 96
+/*
+ * For HWS command queue scheduling, we can prioritise command queues inside the
+ * same process with a relative in-process priority. Valid values for relative
+ * priority are given below - max and min.
+ */
+#define VPU_HWS_COMMAND_QUEUE_MAX_IN_PROCESS_PRIORITY 7
+#define VPU_HWS_COMMAND_QUEUE_MIN_IN_PROCESS_PRIORITY -7
+
+/*
+ * For HWS priority scheduling, we can have multiple realtime priority bands.
+ * They are numbered 0 to a MAX.
+ */
+#define VPU_HWS_MAX_REALTIME_PRIORITY_LEVEL 31U
+
/*
* Job format.
*/
@@ -117,8 +133,14 @@ struct vpu_job_queue_entry {
u32 flags; /**< Flags bit field, see VPU_JOB_FLAGS_* above */
u64 root_page_table_addr; /**< Address of root page table to use for this job */
u64 root_page_table_update_counter; /**< Page tables update events counter */
- u64 preemption_buffer_address; /**< Address of the preemption buffer to use for this job */
- u64 preemption_buffer_size; /**< Size of the preemption buffer to use for this job */
+ u64 primary_preempt_buf_addr;
+ /**< Address of the primary preemption buffer to use for this job */
+ u32 primary_preempt_buf_size;
+ /**< Size of the primary preemption buffer to use for this job */
+ u32 secondary_preempt_buf_size;
+ /**< Size of secondary preemption buffer to use for this job */
+ u64 secondary_preempt_buf_addr;
+ /**< Address of secondary preemption buffer to use for this job */
u8 reserved_0[VPU_JOB_RESERVED_BYTES];
};
@@ -152,6 +174,46 @@ enum vpu_trace_entity_type {
VPU_TRACE_ENTITY_TYPE_HW_COMPONENT = 2,
};
+/*
+ * HWS specific log buffer header details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_header {
+ /* Written by VPU after adding a log entry. Initialised by host to 0. */
+ u32 first_free_entry_index;
+ /* Incremented by VPU every time the VPU overwrites the 0th entry;
+ * initialised by host to 0.
+ */
+ u32 wraparound_count;
+ /*
+ * This is the number of buffers that can be stored in the log buffer provided by the host.
+ * It is written by host before passing buffer to VPU. VPU should consider it read-only.
+ */
+ u64 num_of_entries;
+ u64 reserved[2];
+};
+
+/*
+ * HWS specific log buffer entry details.
+ * Total size is 32 bytes.
+ */
+struct vpu_hws_log_buffer_entry {
+ /* VPU timestamp must be an invariant timer tick (not impacted by DVFS) */
+ u64 vpu_timestamp;
+ /*
+ * Operation type:
+ * 0 - context state change
+ * 1 - queue new work
+ * 2 - queue unwait sync object
+ * 3 - queue no more work
+ * 4 - queue wait sync object
+ */
+ u32 operation_type;
+ u32 reserved;
+ /* Operation data depends on operation type */
+ u64 operation_data[2];
+};
+
/*
* Host <-> VPU IPC messages types.
*/
@@ -228,6 +290,23 @@ enum vpu_ipc_msg_type {
* deallocated or reassigned to another context.
*/
VPU_JSM_MSG_HWS_REGISTER_DB = 0x1117,
+ /** Control command: Log buffer setting */
+ VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG = 0x1118,
+ /* Control command: Suspend command queue. */
+ VPU_JSM_MSG_HWS_SUSPEND_CMDQ = 0x1119,
+ /* Control command: Resume command queue */
+ VPU_JSM_MSG_HWS_RESUME_CMDQ = 0x111a,
+ /* Control command: Resume engine after reset */
+ VPU_JSM_MSG_HWS_ENGINE_RESUME = 0x111b,
+ /* Control command: Enable survivability/DCT mode */
+ VPU_JSM_MSG_DCT_ENABLE = 0x111c,
+ /* Control command: Disable survivability/DCT mode */
+ VPU_JSM_MSG_DCT_DISABLE = 0x111d,
+ /**
+ * Dump VPU state. To be used for debug purposes only.
+ * NOTE: Please introduce new ASYNC commands before this one. *
+ */
+ VPU_JSM_MSG_STATE_DUMP = 0x11FF,
/* IPC Host -> Device, General commands */
VPU_JSM_MSG_GENERAL_CMD = 0x1200,
VPU_JSM_MSG_BLOB_DEINIT = VPU_JSM_MSG_GENERAL_CMD,
@@ -236,6 +315,10 @@ enum vpu_ipc_msg_type {
* Linux command: `echo '<dyndbg_cmd>' > <debugfs>/dynamic_debug/control`.
*/
VPU_JSM_MSG_DYNDBG_CONTROL = 0x1201,
+ /**
+ * Perform the save procedure for the D0i3 entry
+ */
+ VPU_JSM_MSG_PWR_D0I3_ENTER = 0x1202,
/* IPC Device -> Host, Job completion */
VPU_JSM_MSG_JOB_DONE = 0x2100,
/* IPC Device -> Host, Async command completion */
@@ -304,11 +387,35 @@ enum vpu_ipc_msg_type {
VPU_JSM_MSG_DESTROY_CMD_QUEUE_RSP = 0x2216,
/** Response to control command: Set context scheduling properties */
VPU_JSM_MSG_SET_CONTEXT_SCHED_PROPERTIES_RSP = 0x2217,
+ /** Response to control command: Log buffer setting */
+ VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP = 0x2218,
+ /* IPC Device -> Host, HWS notify index entry of log buffer written */
+ VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION = 0x2219,
+ /* IPC Device -> Host, HWS completion of a context suspend request */
+ VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE = 0x221a,
+ /* Response to control command: Resume command queue */
+ VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP = 0x221b,
+ /* Response to control command: Resume engine command response */
+ VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE = 0x221c,
+ /* Response to control command: Enable survivability/DCT mode */
+ VPU_JSM_MSG_DCT_ENABLE_DONE = 0x221d,
+ /* Response to control command: Disable survivability/DCT mode */
+ VPU_JSM_MSG_DCT_DISABLE_DONE = 0x221e,
+ /**
+ * Response to state dump control command.
+ * NOTE: Please introduce new ASYNC responses before this one. *
+ */
+ VPU_JSM_MSG_STATE_DUMP_RSP = 0x22FF,
/* IPC Device -> Host, General command completion */
VPU_JSM_MSG_GENERAL_CMD_DONE = 0x2300,
VPU_JSM_MSG_BLOB_DEINIT_DONE = VPU_JSM_MSG_GENERAL_CMD_DONE,
/** Response to VPU_JSM_MSG_DYNDBG_CONTROL. */
VPU_JSM_MSG_DYNDBG_CONTROL_RSP = 0x2301,
+ /**
+ * Acknowledgment of completion of the save procedure initiated by
+ * VPU_JSM_MSG_PWR_D0I3_ENTER
+ */
+ VPU_JSM_MSG_PWR_D0I3_ENTER_DONE = 0x2302,
};
enum vpu_ipc_msg_status { VPU_JSM_MSG_FREE, VPU_JSM_MSG_ALLOCATED };
@@ -593,12 +700,12 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
* Default quantum in 100ns units for scheduling across processes
* within a priority band
*/
- u64 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
+ u32 process_quantum[VPU_HWS_NUM_PRIORITY_BANDS];
/*
* Default grace period in 100ns units for processes that preempt each
* other within a priority band
*/
- u64 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
+ u32 process_grace_period[VPU_HWS_NUM_PRIORITY_BANDS];
/*
* For normal priority band, specifies the target VPU percentage
* in situations when it's starved by the focus band.
@@ -608,32 +715,51 @@ struct vpu_ipc_msg_payload_hws_priority_band_setup {
u32 reserved_0;
};
-/* HWS create command queue request */
+/*
+ * @brief HWS create command queue request.
+ * Host will create a command queue via this command.
+ * Note: Cmdq group is a handle of an object which
+ * may contain one or more command queues.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
struct vpu_ipc_msg_payload_hws_create_cmdq {
/* Process id */
u64 process_id;
/* Host SSID */
u32 host_ssid;
- /* Zero Padding */
- u32 reserved;
+ /* Engine for which queue is being created */
+ u32 engine_idx;
+ /*
+ * Cmdq group may be set to 0 or equal to
+ * cmdq_id while each priority band contains
+ * only single engine instances.
+ */
+ u64 cmdq_group;
/* Command queue id */
u64 cmdq_id;
/* Command queue base */
u64 cmdq_base;
/* Command queue size */
u32 cmdq_size;
- /* Reserved */
+ /* Zero padding */
u32 reserved_0;
};
-/* HWS create command queue response */
+/*
+ * @brief HWS create command queue response.
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE
+ * @see VPU_JSM_MSG_CREATE_CMD_QUEUE_RSP
+ */
struct vpu_ipc_msg_payload_hws_create_cmdq_rsp {
/* Process id */
u64 process_id;
/* Host SSID */
u32 host_ssid;
- /* Zero Padding */
- u32 reserved;
+ /* Engine for which queue is being created */
+ u32 engine_idx;
+ /* Command queue group */
+ u64 cmdq_group;
/* Command queue id */
u64 cmdq_id;
};
@@ -661,7 +787,7 @@ struct vpu_ipc_msg_payload_hws_set_context_sched_properties {
/* Inside realtime band assigns a further priority */
u32 realtime_priority_level;
/* Priority relative to other contexts in the same process */
- u32 in_process_priority;
+ s32 in_process_priority;
/* Zero padding / Reserved */
u32 reserved_1;
/* Context quantum relative to other contexts of same priority in the same process */
@@ -694,6 +820,123 @@ struct vpu_jsm_hws_register_db {
u64 cmdq_size;
};
+/*
+ * @brief Structure to set another buffer to be used for scheduling-related logging.
+ * The size of the logging buffer and the number of entries is defined as part of the
+ * buffer itself as described next.
+ * The log buffer received from the host is made up of;
+ * - header: 32 bytes in size, as shown in 'struct vpu_hws_log_buffer_header'.
+ * The header contains the number of log entries in the buffer.
+ * - log entry: 0 to n-1, each log entry is 32 bytes in size, as shown in
+ * 'struct vpu_hws_log_buffer_entry'.
+ * The entry contains the VPU timestamp, operation type and data.
+ * The host should provide the notify index value of log buffer to VPU. This is a
+ * value defined within the log buffer and when written to will generate the
+ * scheduling log notification.
+ * The host should set engine_idx and vpu_log_buffer_va to 0 to disable logging
+ * for a particular engine.
+ * VPU will handle one log buffer for each of supported engines.
+ * VPU should allow the logging to consume one host_ssid.
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG_RSP
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ */
+struct vpu_ipc_msg_payload_hws_set_scheduling_log {
+ /* Engine ordinal */
+ u32 engine_idx;
+ /* Host SSID */
+ u32 host_ssid;
+ /*
+ * VPU log buffer virtual address.
+ * Set to 0 to disable logging for this engine.
+ */
+ u64 vpu_log_buffer_va;
+ /*
+ * Notify index of log buffer. VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ * is generated when an event log is written to this index.
+ */
+ u64 notify_index;
+};
+
+/*
+ * @brief The scheduling log notification is generated by VPU when it writes
+ * an event into the log buffer at the notify_index. VPU notifies host with
+ * VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION. This is an asynchronous
+ * message from VPU to host.
+ * @see VPU_JSM_MSG_HWS_SCHEDULING_LOG_NOTIFICATION
+ * @see VPU_JSM_MSG_HWS_SET_SCHEDULING_LOG
+ */
+struct vpu_ipc_msg_payload_hws_scheduling_log_notification {
+ /* Engine ordinal */
+ u32 engine_idx;
+ /* Zero Padding */
+ u32 reserved_0;
+};
+
+/*
+ * @brief HWS suspend command queue request and done structure.
+ * Host will request the suspend of contexts and VPU will;
+ * - Suspend all work on this context
+ * - Preempt any running work
+ * - Asynchronously perform the above and return success immediately once
+ * all items above are started successfully
+ * - Notify the host of completion of these operations via
+ * VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ * - Reject any other context operations on a context with an in-flight
+ * suspend request running
+ * Same structure used when VPU notifies host of completion of a context suspend
+ * request. The ids and suspend fence value reported in this command will match
+ * the one in the request from the host to suspend the context. Once suspend is
+ * complete, VPU will not access any data relating to this command queue until
+ * it is resumed.
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ
+ * @see VPU_JSM_MSG_HWS_SUSPEND_CMDQ_DONE
+ */
+struct vpu_ipc_msg_payload_hws_suspend_cmdq {
+ /* Host SSID */
+ u32 host_ssid;
+ /* Zero Padding */
+ u32 reserved_0;
+ /* Command queue id */
+ u64 cmdq_id;
+ /*
+ * Suspend fence value - reported by the VPU suspend context
+ * completed once suspend is complete.
+ */
+ u64 suspend_fence_value;
+};
+
+/*
+ * @brief HWS Resume command queue request / response structure.
+ * Host will request the resume of a context;
+ * - VPU will resume all work on this context
+ * - Scheduler will allow this context to be scheduled
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ
+ * @see VPU_JSM_MSG_HWS_RESUME_CMDQ_RSP
+ */
+struct vpu_ipc_msg_payload_hws_resume_cmdq {
+ /* Host SSID */
+ u32 host_ssid;
+ /* Zero Padding */
+ u32 reserved_0;
+ /* Command queue id */
+ u64 cmdq_id;
+};
+
+/*
+ * @brief HWS Resume engine request / response structure.
+ * After a HWS engine reset, all scheduling is stopped on VPU until a engine resume.
+ * Host shall send this command to resume scheduling of any valid queue.
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE
+ * @see VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE
+ */
+struct vpu_ipc_msg_payload_hws_resume_engine {
+ /* Engine to be resumed */
+ u32 engine_idx;
+ /* Reserved */
+ u32 reserved_0;
+};
+
/**
* Payload for VPU_JSM_MSG_TRACE_SET_CONFIG[_RSP] and
* VPU_JSM_MSG_TRACE_GET_CONFIG_RSP messages.
@@ -938,6 +1181,35 @@ struct vpu_ipc_msg_payload_dyndbg_control {
char dyndbg_cmd[VPU_DYNDBG_CMD_MAX_LEN];
};
+/**
+ * Payload for VPU_JSM_MSG_PWR_D0I3_ENTER
+ *
+ * This is a bi-directional payload.
+ */
+struct vpu_ipc_msg_payload_pwr_d0i3_enter {
+ /**
+ * 0: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is not sent to the host driver
+ * The driver will poll for D0i2 Idle state transitions.
+ * 1: VPU_JSM_MSG_PWR_D0I3_ENTER_DONE is sent after VPU state save is complete
+ */
+ u32 send_response;
+ u32 reserved_0;
+};
+
+/**
+ * Payload for VPU_JSM_MSG_DCT_ENABLE message.
+ *
+ * Default values for DCT active/inactive times are 5.3ms and 30ms respectively,
+ * corresponding to a 85% duty cycle. This payload allows the host to tune these
+ * values according to application requirements.
+ */
+struct vpu_ipc_msg_payload_pwr_dct_control {
+ /** Duty cycle active time in microseconds */
+ u32 dct_active_us;
+ /** Duty cycle inactive time in microseconds */
+ u32 dct_inactive_us;
+};
+
/*
* Payloads union, used to define complete message format.
*/
@@ -974,6 +1246,13 @@ union vpu_ipc_msg_payload {
struct vpu_ipc_msg_payload_hws_destroy_cmdq hws_destroy_cmdq;
struct vpu_ipc_msg_payload_hws_set_context_sched_properties
hws_set_context_sched_properties;
+ struct vpu_ipc_msg_payload_hws_set_scheduling_log hws_set_scheduling_log;
+ struct vpu_ipc_msg_payload_hws_scheduling_log_notification hws_scheduling_log_notification;
+ struct vpu_ipc_msg_payload_hws_suspend_cmdq hws_suspend_cmdq;
+ struct vpu_ipc_msg_payload_hws_resume_cmdq hws_resume_cmdq;
+ struct vpu_ipc_msg_payload_hws_resume_engine hws_resume_engine;
+ struct vpu_ipc_msg_payload_pwr_d0i3_enter pwr_d0i3_enter;
+ struct vpu_ipc_msg_payload_pwr_dct_control pwr_dct_control;
};
/*
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 02/11] accel/ivpu: Remove unneeded drm_driver dectaration
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 01/11] accel/ivpu: Update FW API Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 03/11] accel/ivpu: Add dvfs_mode file to debugfs Stanislaw Gruszka
` (8 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Stanislaw Gruszka, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Krystian Pradzynski
Cleanup drm_driver declaration leftover.
Reviewed-by: Krystian Pradzynski <krystian.pradzynski@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 790603017653..346dd7fdcacb 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -31,8 +31,6 @@
__stringify(DRM_IVPU_DRIVER_MINOR) "."
#endif
-static const struct drm_driver driver;
-
static struct lock_class_key submitted_jobs_xa_lock_class_key;
int ivpu_dbg_mask;
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 03/11] accel/ivpu: Add dvfs_mode file to debugfs
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 01/11] accel/ivpu: Update FW API Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 02/11] accel/ivpu: Remove unneeded drm_driver dectaration Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 04/11] accel/ivpu: Remove reset from power up sequence Stanislaw Gruszka
` (7 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Stanislaw Gruszka, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Tomasz Rusinowicz
From: Tomasz Rusinowicz <tomasz.rusinowicz@intel.com>
Add new debugfs file to set dvfs_mode FW boot parameter and restart
the FW to allow experimenting with DVFS (dynamic voltage & frequency
scaling).
Signed-off-by: Tomasz Rusinowicz <tomasz.rusinowicz@intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_debugfs.c | 28 ++++++++++++++++++++++++++++
drivers/accel/ivpu/ivpu_fw.c | 5 +++++
drivers/accel/ivpu/ivpu_fw.h | 1 +
3 files changed, 34 insertions(+)
diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index ea453b985b49..6e0d56823024 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -115,6 +115,31 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = {
{"reset_pending", reset_pending_show, 0},
};
+static ssize_t
+dvfs_mode_fops_write(struct file *file, const char __user *user_buf, size_t size, loff_t *pos)
+{
+ struct ivpu_device *vdev = file->private_data;
+ struct ivpu_fw_info *fw = vdev->fw;
+ u32 dvfs_mode;
+ int ret;
+
+ ret = kstrtou32_from_user(user_buf, size, 0, &dvfs_mode);
+ if (ret < 0)
+ return ret;
+
+ fw->dvfs_mode = dvfs_mode;
+
+ ivpu_pm_schedule_recovery(vdev);
+
+ return size;
+}
+
+static const struct file_operations dvfs_mode_fops = {
+ .owner = THIS_MODULE,
+ .open = simple_open,
+ .write = dvfs_mode_fops_write,
+};
+
static int fw_log_show(struct seq_file *s, void *v)
{
struct ivpu_device *vdev = s->private;
@@ -280,6 +305,9 @@ void ivpu_debugfs_init(struct ivpu_device *vdev)
debugfs_create_file("force_recovery", 0200, debugfs_root, vdev,
&ivpu_force_recovery_fops);
+ debugfs_create_file("dvfs_mode", 0200, debugfs_root, vdev,
+ &dvfs_mode_fops);
+
debugfs_create_file("fw_log", 0644, debugfs_root, vdev,
&fw_log_fops);
debugfs_create_file("fw_trace_destination_mask", 0200, debugfs_root, vdev,
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 691da521dde5..a4149fc8a1d7 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -182,6 +182,8 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
fw->trace_destination_mask = VPU_TRACE_DESTINATION_VERBOSE_TRACING;
fw->trace_hw_component_mask = -1;
+ fw->dvfs_mode = 0;
+
ivpu_dbg(vdev, FW_BOOT, "Size: file %lu image %u runtime %u shavenn %u\n",
fw->file->size, fw->image_size, fw->runtime_size, fw->shave_nn_size);
ivpu_dbg(vdev, FW_BOOT, "Address: runtime 0x%llx, load 0x%llx, entry point 0x%llx\n",
@@ -422,6 +424,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
boot_params->punit_telemetry_sram_size);
ivpu_dbg(vdev, FW_BOOT, "boot_params.vpu_telemetry_enable = 0x%x\n",
boot_params->vpu_telemetry_enable);
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
+ boot_params->dvfs_mode);
}
void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params)
@@ -493,6 +497,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
boot_params->punit_telemetry_sram_base = ivpu_hw_reg_telemetry_offset_get(vdev);
boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
+ boot_params->dvfs_mode = vdev->fw->dvfs_mode;
wmb(); /* Flush WC buffers after writing bootparams */
diff --git a/drivers/accel/ivpu/ivpu_fw.h b/drivers/accel/ivpu/ivpu_fw.h
index 10ae2847f0ef..66b60fa161b5 100644
--- a/drivers/accel/ivpu/ivpu_fw.h
+++ b/drivers/accel/ivpu/ivpu_fw.h
@@ -27,6 +27,7 @@ struct ivpu_fw_info {
u32 trace_level;
u32 trace_destination_mask;
u64 trace_hw_component_mask;
+ u32 dvfs_mode;
};
int ivpu_fw_init(struct ivpu_device *vdev);
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 04/11] accel/ivpu: Remove reset from power up sequence
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (2 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 03/11] accel/ivpu: Add dvfs_mode file to debugfs Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 05/11] accel/ivpu: Add support for VPU_JOB_FLAGS_NULL_SUBMISSION_MASK Stanislaw Gruszka
` (6 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Karol Wachowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Setting a non-zero work point resets the IP hence IP_RESET
trigger is redundant.
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_hw_37xx.c | 4 ----
drivers/accel/ivpu/ivpu_hw_40xx.c | 6 ------
2 files changed, 10 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 56b53833ede2..0da4e6117d6b 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -668,10 +668,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev)
{
int ret;
- ret = ivpu_hw_37xx_ip_reset(vdev);
- if (ret)
- ivpu_warn(vdev, "Failed to reset HW: %d\n", ret);
-
ret = ivpu_hw_37xx_d0i3_disable(vdev);
if (ret)
ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index b25d02dc541b..5876cfd9dd40 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -841,12 +841,6 @@ static int ivpu_hw_40xx_power_up(struct ivpu_device *vdev)
{
int ret;
- ret = ivpu_hw_40xx_ip_reset(vdev);
- if (ret) {
- ivpu_err(vdev, "Failed to reset HW: %d\n", ret);
- return ret;
- }
-
ret = ivpu_hw_40xx_d0i3_disable(vdev);
if (ret)
ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret);
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 05/11] accel/ivpu: Add support for VPU_JOB_FLAGS_NULL_SUBMISSION_MASK
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (3 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 04/11] accel/ivpu: Remove reset from power up sequence Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 06/11] accel/ivpu: Change test_mode module param to bitmask Stanislaw Gruszka
` (5 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Andrzej Kacprowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Add test_mode = 3 that add VPU_JOB_FLAGS_NULL_SUBMISSION_MASK
flag to the job send to the VPU device. Then the VPU will process
the job but won't execute commands (except the command to signal
the fence).
This can b used to estimate job processing overhead in the host
software and VPU firmware.
Unlike the null hardware mode, the null submission mode will
still work even if UMD uses VPU fences to track job completion.
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.c | 2 +-
drivers/accel/ivpu/ivpu_drv.h | 7 ++++---
drivers/accel/ivpu/ivpu_job.c | 2 ++
3 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 346dd7fdcacb..2a58fb1e2fcc 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -39,7 +39,7 @@ MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
int ivpu_test_mode;
module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644);
-MODULE_PARM_DESC(test_mode, "Test mode: 0 - normal operation, 1 - fw unit test, 2 - null hw");
+MODULE_PARM_DESC(test_mode, "Test mode: 0 - disabled , 1 - fw unit test, 2 - null hw, 3 - null submission");
u8 ivpu_pll_min_ratio;
module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 417ddeca8517..267e03a5edf4 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -148,9 +148,10 @@ extern u8 ivpu_pll_min_ratio;
extern u8 ivpu_pll_max_ratio;
extern bool ivpu_disable_mmu_cont_pages;
-#define IVPU_TEST_MODE_DISABLED 0
-#define IVPU_TEST_MODE_FW_TEST 1
-#define IVPU_TEST_MODE_NULL_HW 2
+#define IVPU_TEST_MODE_DISABLED 0
+#define IVPU_TEST_MODE_FW_TEST 1
+#define IVPU_TEST_MODE_NULL_HW 2
+#define IVPU_TEST_MODE_NULL_SUBMISSION 3
extern int ivpu_test_mode;
struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 689dc0d13b8f..646b8f812901 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -196,6 +196,8 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
entry->batch_buf_addr = job->cmd_buf_vpu_addr;
entry->job_id = job->job_id;
entry->flags = 0;
+ if (unlikely(ivpu_test_mode == IVPU_TEST_MODE_NULL_SUBMISSION))
+ entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
wmb(); /* Ensure that tail is updated after filling entry */
header->tail = next_entry;
wmb(); /* Flush WC buffer for jobq header */
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 06/11] accel/ivpu: Change test_mode module param to bitmask
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (4 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 05/11] accel/ivpu: Add support for VPU_JOB_FLAGS_NULL_SUBMISSION_MASK Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
[not found] ` <e53dabb3-e8ec-b033-60f0-462f6e225e51@quicinc.com>
2023-10-25 9:43 ` [PATCH 07/11] accel/ivpu: Introduce ivpu_ipc_send_receive_active() Stanislaw Gruszka
` (4 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Karol Wachowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Change meaning of test_mode module parameter from integer value
to bitmask allowing setting different test features with corresponding
bits.
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.c | 4 ++--
drivers/accel/ivpu/ivpu_drv.h | 7 +++----
drivers/accel/ivpu/ivpu_job.c | 4 ++--
3 files changed, 7 insertions(+), 8 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c
index 2a58fb1e2fcc..4dbfd05680ce 100644
--- a/drivers/accel/ivpu/ivpu_drv.c
+++ b/drivers/accel/ivpu/ivpu_drv.c
@@ -39,7 +39,7 @@ MODULE_PARM_DESC(dbg_mask, "Driver debug mask. See IVPU_DBG_* macros.");
int ivpu_test_mode;
module_param_named_unsafe(test_mode, ivpu_test_mode, int, 0644);
-MODULE_PARM_DESC(test_mode, "Test mode: 0 - disabled , 1 - fw unit test, 2 - null hw, 3 - null submission");
+MODULE_PARM_DESC(test_mode, "Test mode mask. See IVPU_TEST_MODE_* macros.");
u8 ivpu_pll_min_ratio;
module_param_named(pll_min_ratio, ivpu_pll_min_ratio, byte, 0644);
@@ -315,7 +315,7 @@ static int ivpu_wait_for_ready(struct ivpu_device *vdev)
unsigned long timeout;
int ret;
- if (ivpu_test_mode == IVPU_TEST_MODE_FW_TEST)
+ if (ivpu_test_mode & IVPU_TEST_MODE_FW_TEST)
return 0;
ivpu_ipc_consumer_add(vdev, &cons, IVPU_IPC_CHAN_BOOT_MSG);
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 267e03a5edf4..5432b5ee90df 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -148,10 +148,9 @@ extern u8 ivpu_pll_min_ratio;
extern u8 ivpu_pll_max_ratio;
extern bool ivpu_disable_mmu_cont_pages;
-#define IVPU_TEST_MODE_DISABLED 0
-#define IVPU_TEST_MODE_FW_TEST 1
-#define IVPU_TEST_MODE_NULL_HW 2
-#define IVPU_TEST_MODE_NULL_SUBMISSION 3
+#define IVPU_TEST_MODE_FW_TEST BIT(0)
+#define IVPU_TEST_MODE_NULL_HW BIT(1)
+#define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2)
extern int ivpu_test_mode;
struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c
index 646b8f812901..6e96c921547d 100644
--- a/drivers/accel/ivpu/ivpu_job.c
+++ b/drivers/accel/ivpu/ivpu_job.c
@@ -196,7 +196,7 @@ static int ivpu_cmdq_push_job(struct ivpu_cmdq *cmdq, struct ivpu_job *job)
entry->batch_buf_addr = job->cmd_buf_vpu_addr;
entry->job_id = job->job_id;
entry->flags = 0;
- if (unlikely(ivpu_test_mode == IVPU_TEST_MODE_NULL_SUBMISSION))
+ if (unlikely(ivpu_test_mode & IVPU_TEST_MODE_NULL_SUBMISSION))
entry->flags = VPU_JOB_FLAGS_NULL_SUBMISSION_MASK;
wmb(); /* Ensure that tail is updated after filling entry */
header->tail = next_entry;
@@ -404,7 +404,7 @@ static int ivpu_direct_job_submission(struct ivpu_job *job)
job->job_id, job->cmd_buf_vpu_addr, file_priv->ctx.id,
job->engine_idx, cmdq->jobq->header.tail);
- if (ivpu_test_mode == IVPU_TEST_MODE_NULL_HW) {
+ if (ivpu_test_mode & IVPU_TEST_MODE_NULL_HW) {
ivpu_job_done(vdev, job->job_id, VPU_JSM_STATUS_SUCCESS);
cmdq->jobq->header.head = cmdq->jobq->header.tail;
wmb(); /* Flush WC buffer for jobq header */
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 07/11] accel/ivpu: Introduce ivpu_ipc_send_receive_active()
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (5 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 06/11] accel/ivpu: Change test_mode module param to bitmask Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
[not found] ` <bdd18dc1-fb4c-2058-b242-5e311266de5b@quicinc.com>
2023-10-25 9:43 ` [PATCH 08/11] accel/ivpu: Pass D0i3 residency time to the VPU firmware Stanislaw Gruszka
` (3 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Karol Wachowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Karol Wachowski <karol.wachowski@linux.intel.com>
Split ivpu_ipc_send_receive() implementation to have a version
that does not call pm_runtime_resume_and_get(). That implementation
can be invoked when device is up and runtime resume is prohibited
(for example at the end of boot sequence).
Signed-off-by: Karol Wachowski <karol.wachowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_ipc.c | 33 ++++++++++++++++++++++-----------
drivers/accel/ivpu/ivpu_ipc.h | 8 +++++---
2 files changed, 27 insertions(+), 14 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_ipc.c b/drivers/accel/ivpu/ivpu_ipc.c
index a4ca40b184d4..962b3bcca460 100644
--- a/drivers/accel/ivpu/ivpu_ipc.c
+++ b/drivers/accel/ivpu/ivpu_ipc.c
@@ -285,23 +285,20 @@ ivpu_ipc_send_receive_internal(struct ivpu_device *vdev, struct vpu_jsm_msg *req
return ret;
}
-int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
- enum vpu_ipc_msg_type expected_resp_type,
- struct vpu_jsm_msg *resp, u32 channel,
- unsigned long timeout_ms)
+int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+ enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+ u32 channel, unsigned long timeout_ms)
{
struct vpu_jsm_msg hb_req = { .type = VPU_JSM_MSG_QUERY_ENGINE_HB };
struct vpu_jsm_msg hb_resp;
int ret, hb_ret;
- ret = ivpu_rpm_get(vdev);
- if (ret < 0)
- return ret;
+ drm_WARN_ON(&vdev->drm,
+ vdev->drm.dev->power.runtime_status == RPM_SUSPENDED);
- ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp_type, resp,
- channel, timeout_ms);
+ ret = ivpu_ipc_send_receive_internal(vdev, req, expected_resp, resp, channel, timeout_ms);
if (ret != -ETIMEDOUT)
- goto rpm_put;
+ return ret;
hb_ret = ivpu_ipc_send_receive_internal(vdev, &hb_req, VPU_JSM_MSG_QUERY_ENGINE_HB_DONE,
&hb_resp, VPU_IPC_CHAN_ASYNC_CMD,
@@ -311,7 +308,21 @@ int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
ivpu_pm_schedule_recovery(vdev);
}
-rpm_put:
+ return ret;
+}
+
+int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+ enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+ u32 channel, unsigned long timeout_ms)
+{
+ int ret;
+
+ ret = ivpu_rpm_get(vdev);
+ if (ret < 0)
+ return ret;
+
+ ret = ivpu_ipc_send_receive_active(vdev, req, expected_resp, resp, channel, timeout_ms);
+
ivpu_rpm_put(vdev);
return ret;
}
diff --git a/drivers/accel/ivpu/ivpu_ipc.h b/drivers/accel/ivpu/ivpu_ipc.h
index 68f5b6668e00..6918db23daa4 100644
--- a/drivers/accel/ivpu/ivpu_ipc.h
+++ b/drivers/accel/ivpu/ivpu_ipc.h
@@ -85,9 +85,11 @@ int ivpu_ipc_receive(struct ivpu_device *vdev, struct ivpu_ipc_consumer *cons,
struct ivpu_ipc_hdr *ipc_buf, struct vpu_jsm_msg *ipc_payload,
unsigned long timeout_ms);
+int ivpu_ipc_send_receive_active(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
+ enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+ u32 channel, unsigned long timeout_ms);
int ivpu_ipc_send_receive(struct ivpu_device *vdev, struct vpu_jsm_msg *req,
- enum vpu_ipc_msg_type expected_resp_type,
- struct vpu_jsm_msg *resp, u32 channel,
- unsigned long timeout_ms);
+ enum vpu_ipc_msg_type expected_resp, struct vpu_jsm_msg *resp,
+ u32 channel, unsigned long timeout_ms);
#endif /* __IVPU_IPC_H__ */
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 08/11] accel/ivpu: Pass D0i3 residency time to the VPU firmware
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (6 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 07/11] accel/ivpu: Introduce ivpu_ipc_send_receive_active() Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 09/11] accel/ivpu/40xx: Capture D0i3 entry host and device timestamps Stanislaw Gruszka
` (2 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Andrzej Kacprowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
The firmware needs to know the time spend in D0i3/D3 to
calculate telemetry data. The D0i3/D3 residency time is
calculated by the driver and passed to the firmware
in the boot parameters.
The driver also passes VPU perf counter value captured
right before entering D0i3 - this allows the VPU firmware
to generate monotonic timestamps for the logs.
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_fw.c | 17 ++++++++++++++++-
drivers/accel/ivpu/ivpu_hw.h | 2 ++
drivers/accel/ivpu/ivpu_hw_37xx.c | 8 ++++++++
drivers/accel/ivpu/ivpu_hw_37xx_reg.h | 2 ++
4 files changed, 28 insertions(+), 1 deletion(-)
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index a4149fc8a1d7..51d976ba5276 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -426,14 +426,27 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
boot_params->vpu_telemetry_enable);
ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
boot_params->dvfs_mode);
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+ boot_params->d0i3_residency_time_us);
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+ boot_params->d0i3_entry_vpu_ts);
}
void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params *boot_params)
{
struct ivpu_bo *ipc_mem_rx = vdev->ipc->mem_rx;
- /* In case of warm boot we only have to reset the entrypoint addr */
+ /* In case of warm boot only update variable params */
if (!ivpu_fw_is_cold_boot(vdev)) {
+ boot_params->d0i3_residency_time_us =
+ ktime_us_delta(ktime_get_boottime(), vdev->hw->d0i3_entry_host_ts);
+ boot_params->d0i3_entry_vpu_ts = vdev->hw->d0i3_entry_vpu_ts;
+
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
+ boot_params->d0i3_residency_time_us);
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
+ boot_params->d0i3_entry_vpu_ts);
+
boot_params->save_restore_ret_address = 0;
vdev->pm->is_warmboot = true;
wmb(); /* Flush WC buffers after writing save_restore_ret_address */
@@ -498,6 +511,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
boot_params->dvfs_mode = vdev->fw->dvfs_mode;
+ boot_params->d0i3_residency_time_us = 0;
+ boot_params->d0i3_entry_vpu_ts = 0;
wmb(); /* Flush WC buffers after writing bootparams */
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index 1079e06255ba..bb4368168247 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -58,6 +58,8 @@ struct ivpu_hw_info {
u32 sku;
u16 config;
int dma_bits;
+ ktime_t d0i3_entry_host_ts;
+ u64 d0i3_entry_vpu_ts;
};
extern const struct ivpu_hw_ops ivpu_hw_37xx_ops;
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 0da4e6117d6b..06d7db28448a 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -731,10 +731,18 @@ static bool ivpu_hw_37xx_is_idle(struct ivpu_device *vdev)
REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, val);
}
+static void ivpu_hw_37xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
+{
+ vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
+ vdev->hw->d0i3_entry_vpu_ts = REGV_RD64(VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT);
+}
+
static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
{
int ret = 0;
+ ivpu_hw_37xx_save_d0i3_entry_timestamp(vdev);
+
if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_ip_reset(vdev))
ivpu_err(vdev, "Failed to reset the VPU\n");
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
index 4083beb5e9db..f6fec1919202 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
+++ b/drivers/accel/ivpu/ivpu_hw_37xx_reg.h
@@ -240,6 +240,8 @@
#define VPU_37XX_CPU_SS_TIM_GEN_CONFIG 0x06021008u
#define VPU_37XX_CPU_SS_TIM_GEN_CONFIG_WDOG_TO_INT_CLR_MASK BIT_MASK(9)
+#define VPU_37XX_CPU_SS_TIM_PERF_FREE_CNT 0x06029000u
+
#define VPU_37XX_CPU_SS_DOORBELL_0 0x06300000u
#define VPU_37XX_CPU_SS_DOORBELL_0_SET_MASK BIT_MASK(0)
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 09/11] accel/ivpu/40xx: Capture D0i3 entry host and device timestamps
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (7 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 08/11] accel/ivpu: Pass D0i3 residency time to the VPU firmware Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 10/11] accel/ivpu: Add support for delayed D0i3 entry message Stanislaw Gruszka
2023-10-25 9:43 ` [PATCH 11/11] accel/ivpu: Wait for VPU to enter idle state after " Stanislaw Gruszka
10 siblings, 0 replies; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Andrzej Kacprowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
The driver needs to capture the D0i3 entry timestamp to
calculate D0i3 residency time.
The D0i3 residency time and the VPU timestamp are passed
to the firmware at D0i3 exit (warm boot).
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_hw_40xx.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 5876cfd9dd40..d8df2addd18a 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -909,10 +909,18 @@ static bool ivpu_hw_40xx_is_idle(struct ivpu_device *vdev)
REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, val);
}
+static void ivpu_hw_40xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
+{
+ vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
+ vdev->hw->d0i3_entry_vpu_ts = REGV_RD64(VPU_40XX_CPU_SS_TIM_PERF_EXT_FREE_CNT);
+}
+
static int ivpu_hw_40xx_power_down(struct ivpu_device *vdev)
{
int ret = 0;
+ ivpu_hw_40xx_save_d0i3_entry_timestamp(vdev);
+
if (!ivpu_hw_40xx_is_idle(vdev) && ivpu_hw_40xx_ip_reset(vdev))
ivpu_warn(vdev, "Failed to reset the VPU\n");
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 10/11] accel/ivpu: Add support for delayed D0i3 entry message
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (8 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 09/11] accel/ivpu/40xx: Capture D0i3 entry host and device timestamps Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
[not found] ` <f45d777c-03eb-fb6b-fa3a-6c19f56e9d17@quicinc.com>
2023-10-25 9:43 ` [PATCH 11/11] accel/ivpu: Wait for VPU to enter idle state after " Stanislaw Gruszka
10 siblings, 1 reply; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Andrzej Kacprowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Currently the VPU firmware prepares for D0i3 every time the VPU
is entering D0i2 Idle state. This is not optimal as we might not
enter D0i3 every time we enter D0i2 Idle and this preparation
is quite costly.
This optimization moves D0i3 preparation to a dedicated
message sent from the host driver only when the driver is about
to enter D0i3 - this reduces power consumption and latency for
certain workloads, for example audio workloads that submit
inference every 10 ms.
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_drv.h | 10 +++++--
drivers/accel/ivpu/ivpu_fw.c | 48 +++++++++++++++++++++++++++++--
drivers/accel/ivpu/ivpu_hw_37xx.c | 8 ++++--
drivers/accel/ivpu/ivpu_hw_40xx.c | 3 ++
drivers/accel/ivpu/ivpu_jsm_msg.c | 15 ++++++++++
drivers/accel/ivpu/ivpu_jsm_msg.h | 1 +
drivers/accel/ivpu/ivpu_pm.c | 11 ++++++-
7 files changed, 87 insertions(+), 9 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h
index 5432b5ee90df..84b170a3c323 100644
--- a/drivers/accel/ivpu/ivpu_drv.h
+++ b/drivers/accel/ivpu/ivpu_drv.h
@@ -88,6 +88,7 @@ struct ivpu_wa_table {
bool d3hot_after_power_off;
bool interrupt_clear_with_0;
bool disable_clock_relinquish;
+ bool disable_d0i3_msg;
};
struct ivpu_hw_info;
@@ -126,6 +127,7 @@ struct ivpu_device {
int tdr;
int reschedule_suspend;
int autosuspend;
+ int d0i3_entry_msg;
} timeout;
};
@@ -148,9 +150,11 @@ extern u8 ivpu_pll_min_ratio;
extern u8 ivpu_pll_max_ratio;
extern bool ivpu_disable_mmu_cont_pages;
-#define IVPU_TEST_MODE_FW_TEST BIT(0)
-#define IVPU_TEST_MODE_NULL_HW BIT(1)
-#define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2)
+#define IVPU_TEST_MODE_FW_TEST BIT(0)
+#define IVPU_TEST_MODE_NULL_HW BIT(1)
+#define IVPU_TEST_MODE_NULL_SUBMISSION BIT(2)
+#define IVPU_TEST_MODE_D0I3_MSG_DISABLE BIT(4)
+#define IVPU_TEST_MODE_D0I3_MSG_ENABLE BIT(5)
extern int ivpu_test_mode;
struct ivpu_file_priv *ivpu_file_priv_get(struct ivpu_file_priv *file_priv);
diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c
index 51d976ba5276..3fd94c2d06c7 100644
--- a/drivers/accel/ivpu/ivpu_fw.c
+++ b/drivers/accel/ivpu/ivpu_fw.c
@@ -33,12 +33,17 @@
#define ADDR_TO_L2_CACHE_CFG(addr) ((addr) >> 31)
-#define IVPU_FW_CHECK_API(vdev, fw_hdr, name, min_major) \
+/* Check if FW API is compatible with the driver */
+#define IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, name, min_major) \
ivpu_fw_check_api(vdev, fw_hdr, #name, \
VPU_##name##_API_VER_INDEX, \
VPU_##name##_API_VER_MAJOR, \
VPU_##name##_API_VER_MINOR, min_major)
+/* Check if API version is lover that the given version */
+#define IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, name, major, minor) \
+ ivpu_fw_check_api_ver_lt(vdev, fw_hdr, #name, VPU_##name##_API_VER_INDEX, major, minor)
+
static char *ivpu_firmware;
module_param_named_unsafe(firmware, ivpu_firmware, charp, 0644);
MODULE_PARM_DESC(firmware, "VPU firmware binary in /lib/firmware/..");
@@ -105,6 +110,19 @@ ivpu_fw_check_api(struct ivpu_device *vdev, const struct vpu_firmware_header *fw
return 0;
}
+static bool
+ivpu_fw_check_api_ver_lt(struct ivpu_device *vdev, const struct vpu_firmware_header *fw_hdr,
+ const char *str, int index, u16 major, u16 minor)
+{
+ u16 fw_major = (u16)(fw_hdr->api_version[index] >> 16);
+ u16 fw_minor = (u16)(fw_hdr->api_version[index]);
+
+ if (fw_major < major || (fw_major == major && fw_minor < minor))
+ return true;
+
+ return false;
+}
+
static int ivpu_fw_parse(struct ivpu_device *vdev)
{
struct ivpu_fw_info *fw = vdev->fw;
@@ -164,9 +182,9 @@ static int ivpu_fw_parse(struct ivpu_device *vdev)
ivpu_info(vdev, "Firmware: %s, version: %s", fw->name,
(const char *)fw_hdr + VPU_FW_HEADER_SIZE);
- if (IVPU_FW_CHECK_API(vdev, fw_hdr, BOOT, 3))
+ if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, BOOT, 3))
return -EINVAL;
- if (IVPU_FW_CHECK_API(vdev, fw_hdr, JSM, 3))
+ if (IVPU_FW_CHECK_API_COMPAT(vdev, fw_hdr, JSM, 3))
return -EINVAL;
fw->runtime_addr = runtime_addr;
@@ -197,6 +215,24 @@ static void ivpu_fw_release(struct ivpu_device *vdev)
release_firmware(vdev->fw->file);
}
+/* Initialize workarounds that depend on FW version */
+static void
+ivpu_fw_init_wa(struct ivpu_device *vdev)
+{
+ const struct vpu_firmware_header *fw_hdr = (const void *)vdev->fw->file->data;
+
+ if (IVPU_FW_CHECK_API_VER_LT(vdev, fw_hdr, BOOT, 3, 17) ||
+ (ivpu_hw_gen(vdev) > IVPU_HW_37XX) ||
+ (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_DISABLE))
+ vdev->wa.disable_d0i3_msg = true;
+
+ /* Force enable the feature for testing purposes */
+ if (ivpu_test_mode & IVPU_TEST_MODE_D0I3_MSG_ENABLE)
+ vdev->wa.disable_d0i3_msg = false;
+
+ IVPU_PRINT_WA(disable_d0i3_msg);
+}
+
static int ivpu_fw_update_global_range(struct ivpu_device *vdev)
{
struct ivpu_fw_info *fw = vdev->fw;
@@ -299,6 +335,8 @@ int ivpu_fw_init(struct ivpu_device *vdev)
if (ret)
goto err_fw_release;
+ ivpu_fw_init_wa(vdev);
+
ret = ivpu_fw_mem_init(vdev);
if (ret)
goto err_fw_release;
@@ -426,6 +464,8 @@ static void ivpu_fw_boot_params_print(struct ivpu_device *vdev, struct vpu_boot_
boot_params->vpu_telemetry_enable);
ivpu_dbg(vdev, FW_BOOT, "boot_params.dvfs_mode = %u\n",
boot_params->dvfs_mode);
+ ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_delayed_entry = %d\n",
+ boot_params->d0i3_delayed_entry);
ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_residency_time_us = %lld\n",
boot_params->d0i3_residency_time_us);
ivpu_dbg(vdev, FW_BOOT, "boot_params.d0i3_entry_vpu_ts = %llu\n",
@@ -511,6 +551,8 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params
boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev);
boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev);
boot_params->dvfs_mode = vdev->fw->dvfs_mode;
+ if (!IVPU_WA(disable_d0i3_msg))
+ boot_params->d0i3_delayed_entry = 1;
boot_params->d0i3_residency_time_us = 0;
boot_params->d0i3_entry_vpu_ts = 0;
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index 06d7db28448a..edf4776acf29 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -90,6 +90,7 @@ static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
vdev->timeout.tdr = 2000;
vdev->timeout.reschedule_suspend = 10;
vdev->timeout.autosuspend = 10;
+ vdev->timeout.d0i3_entry_msg = 5;
}
static int ivpu_pll_wait_for_cmd_send(struct ivpu_device *vdev)
@@ -743,8 +744,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev)
ivpu_hw_37xx_save_d0i3_entry_timestamp(vdev);
- if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_ip_reset(vdev))
- ivpu_err(vdev, "Failed to reset the VPU\n");
+ if (!ivpu_hw_37xx_is_idle(vdev)) {
+ ivpu_warn(vdev, "VPU not idle during power down\n");
+ if (ivpu_hw_37xx_ip_reset(vdev))
+ ivpu_err(vdev, "Failed to reset the VPU\n");
+ }
if (ivpu_pll_disable(vdev)) {
ivpu_err(vdev, "Failed to disable PLL\n");
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index d8df2addd18a..971d8d4ecba1 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -139,18 +139,21 @@ static void ivpu_hw_timeouts_init(struct ivpu_device *vdev)
vdev->timeout.tdr = 2000000;
vdev->timeout.reschedule_suspend = 1000;
vdev->timeout.autosuspend = -1;
+ vdev->timeout.d0i3_entry_msg = 500;
} else if (ivpu_is_simics(vdev)) {
vdev->timeout.boot = 50;
vdev->timeout.jsm = 500;
vdev->timeout.tdr = 10000;
vdev->timeout.reschedule_suspend = 10;
vdev->timeout.autosuspend = -1;
+ vdev->timeout.d0i3_entry_msg = 100;
} else {
vdev->timeout.boot = 1000;
vdev->timeout.jsm = 500;
vdev->timeout.tdr = 2000;
vdev->timeout.reschedule_suspend = 10;
vdev->timeout.autosuspend = 10;
+ vdev->timeout.d0i3_entry_msg = 5;
}
}
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 35a689475c68..03cf6b35d73a 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -260,3 +260,18 @@ int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid)
return ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_SSID_RELEASE_DONE, &resp,
VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
}
+
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev)
+{
+ struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_PWR_D0I3_ENTER };
+ struct vpu_jsm_msg resp;
+
+ if (IVPU_WA(disable_d0i3_msg))
+ return 0;
+
+ req.payload.pwr_d0i3_enter.send_response = 1;
+
+ return ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE,
+ &resp, VPU_IPC_CHAN_GEN_CMD,
+ vdev->timeout.d0i3_entry_msg);
+}
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.h b/drivers/accel/ivpu/ivpu_jsm_msg.h
index 66979a948c7c..ae75e5dbcc41 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.h
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.h
@@ -22,4 +22,5 @@ int ivpu_jsm_trace_get_capability(struct ivpu_device *vdev, u32 *trace_destinati
int ivpu_jsm_trace_set_config(struct ivpu_device *vdev, u32 trace_level, u32 trace_destination_mask,
u64 trace_hw_component_mask);
int ivpu_jsm_context_release(struct ivpu_device *vdev, u32 host_ssid);
+int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev);
#endif
diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c
index 0ace218783c8..b5f613971be5 100644
--- a/drivers/accel/ivpu/ivpu_pm.c
+++ b/drivers/accel/ivpu/ivpu_pm.c
@@ -15,6 +15,7 @@
#include "ivpu_fw.h"
#include "ivpu_ipc.h"
#include "ivpu_job.h"
+#include "ivpu_jsm_msg.h"
#include "ivpu_mmu.h"
#include "ivpu_pm.h"
@@ -153,6 +154,8 @@ int ivpu_pm_suspend_cb(struct device *dev)
}
}
+ ivpu_jsm_pwr_d0i3_enter(vdev);
+
ivpu_suspend(vdev);
ivpu_pm_prepare_warm_boot(vdev);
@@ -188,6 +191,7 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
{
struct drm_device *drm = dev_get_drvdata(dev);
struct ivpu_device *vdev = to_ivpu_device(drm);
+ bool hw_is_idle = true;
int ret;
ivpu_dbg(vdev, PM, "Runtime suspend..\n");
@@ -200,11 +204,16 @@ int ivpu_pm_runtime_suspend_cb(struct device *dev)
return -EAGAIN;
}
+ if (!vdev->pm->suspend_reschedule_counter)
+ hw_is_idle = false;
+ else if (ivpu_jsm_pwr_d0i3_enter(vdev))
+ hw_is_idle = false;
+
ret = ivpu_suspend(vdev);
if (ret)
ivpu_err(vdev, "Failed to set suspend VPU: %d\n", ret);
- if (!vdev->pm->suspend_reschedule_counter) {
+ if (!hw_is_idle) {
ivpu_warn(vdev, "VPU failed to enter idle, force suspended.\n");
ivpu_pm_prepare_cold_boot(vdev);
} else {
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH 11/11] accel/ivpu: Wait for VPU to enter idle state after D0i3 entry message
2023-10-25 9:43 [PATCH 00/11] accel/ivpu: Update to -next 2023-10-25 Stanislaw Gruszka
` (9 preceding siblings ...)
2023-10-25 9:43 ` [PATCH 10/11] accel/ivpu: Add support for delayed D0i3 entry message Stanislaw Gruszka
@ 2023-10-25 9:43 ` Stanislaw Gruszka
[not found] ` <74227a8f-f89f-ed3d-1d39-ad771801c172@quicinc.com>
10 siblings, 1 reply; 20+ messages in thread
From: Stanislaw Gruszka @ 2023-10-25 9:43 UTC (permalink / raw)
To: dri-devel
Cc: Andrzej Kacprowski, Oded Gabbay, Jeffrey Hugo, Jacek Lawrynowicz,
Stanislaw Gruszka
From: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
The VPU needs non zero time to enter IDLE state after responding to
D0i3 entry message. If the driver does not wait for the VPU to enter
IDLE state it could cause warm boot failures.
Signed-off-by: Andrzej Kacprowski <andrzej.kacprowski@linux.intel.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Signed-off-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
---
drivers/accel/ivpu/ivpu_hw.h | 6 ++++++
drivers/accel/ivpu/ivpu_hw_37xx.c | 8 +++++++-
drivers/accel/ivpu/ivpu_hw_40xx.c | 7 +++++++
drivers/accel/ivpu/ivpu_jsm_msg.c | 12 +++++++++---
4 files changed, 29 insertions(+), 4 deletions(-)
diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h
index bb4368168247..329721f8f010 100644
--- a/drivers/accel/ivpu/ivpu_hw.h
+++ b/drivers/accel/ivpu/ivpu_hw.h
@@ -15,6 +15,7 @@ struct ivpu_hw_ops {
int (*power_down)(struct ivpu_device *vdev);
int (*reset)(struct ivpu_device *vdev);
bool (*is_idle)(struct ivpu_device *vdev);
+ int (*wait_for_idle)(struct ivpu_device *vdev);
void (*wdt_disable)(struct ivpu_device *vdev);
void (*diagnose_failure)(struct ivpu_device *vdev);
u32 (*reg_pll_freq_get)(struct ivpu_device *vdev);
@@ -87,6 +88,11 @@ static inline bool ivpu_hw_is_idle(struct ivpu_device *vdev)
return vdev->hw->ops->is_idle(vdev);
};
+static inline int ivpu_hw_wait_for_idle(struct ivpu_device *vdev)
+{
+ return vdev->hw->ops->wait_for_idle(vdev);
+};
+
static inline int ivpu_hw_power_down(struct ivpu_device *vdev)
{
ivpu_dbg(vdev, PM, "HW power down\n");
diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c
index edf4776acf29..9b04dcc90de1 100644
--- a/drivers/accel/ivpu/ivpu_hw_37xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_37xx.c
@@ -37,7 +37,7 @@
#define TIMEOUT_US (150 * USEC_PER_MSEC)
#define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
#define PLL_TIMEOUT_US (1500 * USEC_PER_MSEC)
-#define IDLE_TIMEOUT_US (500 * USEC_PER_MSEC)
+#define IDLE_TIMEOUT_US (5 * USEC_PER_MSEC)
#define ICB_0_IRQ_MASK ((REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, HOST_IPC_FIFO_INT)) | \
(REG_FLD(VPU_37XX_HOST_SS_ICB_STATUS_0, MMU_IRQ_0_INT)) | \
@@ -732,6 +732,11 @@ static bool ivpu_hw_37xx_is_idle(struct ivpu_device *vdev)
REG_TEST_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, val);
}
+static int ivpu_hw_37xx_wait_for_idle(struct ivpu_device *vdev)
+{
+ return REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+}
+
static void ivpu_hw_37xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
{
vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
@@ -1018,6 +1023,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = {
.info_init = ivpu_hw_37xx_info_init,
.power_up = ivpu_hw_37xx_power_up,
.is_idle = ivpu_hw_37xx_is_idle,
+ .wait_for_idle = ivpu_hw_37xx_wait_for_idle,
.power_down = ivpu_hw_37xx_power_down,
.reset = ivpu_hw_37xx_reset,
.boot_fw = ivpu_hw_37xx_boot_fw,
diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c
index 971d8d4ecba1..fb28e83a29a3 100644
--- a/drivers/accel/ivpu/ivpu_hw_40xx.c
+++ b/drivers/accel/ivpu/ivpu_hw_40xx.c
@@ -39,6 +39,7 @@
#define TIMEOUT_US (150 * USEC_PER_MSEC)
#define PWR_ISLAND_STATUS_TIMEOUT_US (5 * USEC_PER_MSEC)
#define PLL_TIMEOUT_US (1500 * USEC_PER_MSEC)
+#define IDLE_TIMEOUT_US (5 * USEC_PER_MSEC)
#define WEIGHTS_DEFAULT 0xf711f711u
#define WEIGHTS_ATS_DEFAULT 0x0000f711u
@@ -912,6 +913,11 @@ static bool ivpu_hw_40xx_is_idle(struct ivpu_device *vdev)
REG_TEST_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, val);
}
+static int ivpu_hw_40xx_wait_for_idle(struct ivpu_device *vdev)
+{
+ return REGB_POLL_FLD(VPU_40XX_BUTTRESS_VPU_STATUS, IDLE, 0x1, IDLE_TIMEOUT_US);
+}
+
static void ivpu_hw_40xx_save_d0i3_entry_timestamp(struct ivpu_device *vdev)
{
vdev->hw->d0i3_entry_host_ts = ktime_get_boottime();
@@ -1207,6 +1213,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = {
.info_init = ivpu_hw_40xx_info_init,
.power_up = ivpu_hw_40xx_power_up,
.is_idle = ivpu_hw_40xx_is_idle,
+ .wait_for_idle = ivpu_hw_40xx_wait_for_idle,
.power_down = ivpu_hw_40xx_power_down,
.reset = ivpu_hw_40xx_reset,
.boot_fw = ivpu_hw_40xx_boot_fw,
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 03cf6b35d73a..8cea0dd731b9 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -4,6 +4,7 @@
*/
#include "ivpu_drv.h"
+#include "ivpu_hw.h"
#include "ivpu_ipc.h"
#include "ivpu_jsm_msg.h"
@@ -265,13 +266,18 @@ int ivpu_jsm_pwr_d0i3_enter(struct ivpu_device *vdev)
{
struct vpu_jsm_msg req = { .type = VPU_JSM_MSG_PWR_D0I3_ENTER };
struct vpu_jsm_msg resp;
+ int ret;
if (IVPU_WA(disable_d0i3_msg))
return 0;
req.payload.pwr_d0i3_enter.send_response = 1;
- return ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE,
- &resp, VPU_IPC_CHAN_GEN_CMD,
- vdev->timeout.d0i3_entry_msg);
+ ret = ivpu_ipc_send_receive_active(vdev, &req, VPU_JSM_MSG_PWR_D0I3_ENTER_DONE,
+ &resp, VPU_IPC_CHAN_GEN_CMD,
+ vdev->timeout.d0i3_entry_msg);
+ if (ret)
+ return ret;
+
+ return ivpu_hw_wait_for_idle(vdev);
}
--
2.25.1
^ permalink raw reply related [flat|nested] 20+ messages in thread