* [PATCH 2/6] habanalabs: use registers name defines for ETR block
2019-11-10 21:55 [PATCH 1/6] habanalabs: read F/W versions before failure Oded Gabbay
@ 2019-11-10 21:55 ` Oded Gabbay
2019-11-11 5:59 ` Omer Shpigelman
2019-11-10 21:55 ` [PATCH 3/6] habanalabs: set ETR as non-secured Oded Gabbay
` (4 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Oded Gabbay @ 2019-11-10 21:55 UTC (permalink / raw)
To: linux-kernel, oshpigelman, ttayar; +Cc: gregkh
We have a single ETR block in the SOC, so use explicit register
name defines for initializing this block. This makes it more readable and
maintainable.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
drivers/misc/habanalabs/goya/goya_coresight.c | 51 ++++----
.../include/goya/asic_reg/goya_regs.h | 1 +
.../include/goya/asic_reg/psoc_etr_regs.h | 114 ++++++++++++++++++
3 files changed, 140 insertions(+), 26 deletions(-)
create mode 100644 drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h
diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c
index b4d406af1bed..16bcd60b111f 100644
--- a/drivers/misc/habanalabs/goya/goya_coresight.c
+++ b/drivers/misc/habanalabs/goya/goya_coresight.c
@@ -377,33 +377,32 @@ static int goya_config_etr(struct hl_device *hdev,
struct hl_debug_params *params)
{
struct hl_debug_params_etr *input;
- u64 base_reg = mmPSOC_ETR_BASE - CFG_BASE;
u32 val;
int rc;
- WREG32(base_reg + 0xFB0, CORESIGHT_UNLOCK);
+ WREG32(mmPSOC_ETR_LAR, CORESIGHT_UNLOCK);
- val = RREG32(base_reg + 0x304);
+ val = RREG32(mmPSOC_ETR_FFCR);
val |= 0x1000;
- WREG32(base_reg + 0x304, val);
+ WREG32(mmPSOC_ETR_FFCR, val);
val |= 0x40;
- WREG32(base_reg + 0x304, val);
+ WREG32(mmPSOC_ETR_FFCR, val);
- rc = goya_coresight_timeout(hdev, base_reg + 0x304, 6, false);
+ rc = goya_coresight_timeout(hdev, mmPSOC_ETR_FFCR, 6, false);
if (rc) {
dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n",
params->enable ? "enable" : "disable", rc);
return rc;
}
- rc = goya_coresight_timeout(hdev, base_reg + 0xC, 2, true);
+ rc = goya_coresight_timeout(hdev, mmPSOC_ETR_STS, 2, true);
if (rc) {
dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n",
params->enable ? "enable" : "disable", rc);
return rc;
}
- WREG32(base_reg + 0x20, 0);
+ WREG32(mmPSOC_ETR_CTL, 0);
if (params->enable) {
input = params->input;
@@ -423,25 +422,25 @@ static int goya_config_etr(struct hl_device *hdev,
return -EINVAL;
}
- WREG32(base_reg + 0x34, 0x3FFC);
- WREG32(base_reg + 0x4, input->buffer_size);
- WREG32(base_reg + 0x28, input->sink_mode);
- WREG32(base_reg + 0x110, 0x700);
- WREG32(base_reg + 0x118,
+ WREG32(mmPSOC_ETR_BUFWM, 0x3FFC);
+ WREG32(mmPSOC_ETR_RSZ, input->buffer_size);
+ WREG32(mmPSOC_ETR_MODE, input->sink_mode);
+ WREG32(mmPSOC_ETR_AXICTL, 0x700);
+ WREG32(mmPSOC_ETR_DBALO,
lower_32_bits(input->buffer_address));
- WREG32(base_reg + 0x11C,
+ WREG32(mmPSOC_ETR_DBAHI,
upper_32_bits(input->buffer_address));
- WREG32(base_reg + 0x304, 3);
- WREG32(base_reg + 0x308, 0xA);
- WREG32(base_reg + 0x20, 1);
+ WREG32(mmPSOC_ETR_FFCR, 3);
+ WREG32(mmPSOC_ETR_PSCR, 0xA);
+ WREG32(mmPSOC_ETR_CTL, 1);
} else {
- WREG32(base_reg + 0x34, 0);
- WREG32(base_reg + 0x4, 0x400);
- WREG32(base_reg + 0x118, 0);
- WREG32(base_reg + 0x11C, 0);
- WREG32(base_reg + 0x308, 0);
- WREG32(base_reg + 0x28, 0);
- WREG32(base_reg + 0x304, 0);
+ WREG32(mmPSOC_ETR_BUFWM, 0);
+ WREG32(mmPSOC_ETR_RSZ, 0x400);
+ WREG32(mmPSOC_ETR_DBALO, 0);
+ WREG32(mmPSOC_ETR_DBAHI, 0);
+ WREG32(mmPSOC_ETR_PSCR, 0);
+ WREG32(mmPSOC_ETR_MODE, 0);
+ WREG32(mmPSOC_ETR_FFCR, 0);
if (params->output_size >= sizeof(u64)) {
u32 rwp, rwphi;
@@ -451,8 +450,8 @@ static int goya_config_etr(struct hl_device *hdev,
* the buffer is set in the RWP register (lower 32
* bits), and in the RWPHI register (upper 8 bits).
*/
- rwp = RREG32(base_reg + 0x18);
- rwphi = RREG32(base_reg + 0x3c) & 0xff;
+ rwp = RREG32(mmPSOC_ETR_RWP);
+ rwphi = RREG32(mmPSOC_ETR_RWPHI) & 0xff;
*(u64 *) params->output = ((u64) rwphi << 32) | rwp;
}
}
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
index 19b0f0ef1d0b..fce490e6a231 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h
@@ -84,6 +84,7 @@
#include "tpc6_rtr_regs.h"
#include "tpc7_nrtr_regs.h"
#include "tpc0_eml_cfg_regs.h"
+#include "psoc_etr_regs.h"
#include "psoc_global_conf_masks.h"
#include "dma_macro_masks.h"
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h
new file mode 100644
index 000000000000..b7c33e025db5
--- /dev/null
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_etr_regs.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2016-2018 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+/************************************
+ ** This is an auto-generated file **
+ ** DO NOT EDIT BELOW **
+ ************************************/
+
+#ifndef ASIC_REG_PSOC_ETR_REGS_H_
+#define ASIC_REG_PSOC_ETR_REGS_H_
+
+/*
+ *****************************************
+ * PSOC_ETR (Prototype: ETR)
+ *****************************************
+ */
+
+#define mmPSOC_ETR_RSZ 0x2C43004
+
+#define mmPSOC_ETR_STS 0x2C4300C
+
+#define mmPSOC_ETR_RRD 0x2C43010
+
+#define mmPSOC_ETR_RRP 0x2C43014
+
+#define mmPSOC_ETR_RWP 0x2C43018
+
+#define mmPSOC_ETR_TRG 0x2C4301C
+
+#define mmPSOC_ETR_CTL 0x2C43020
+
+#define mmPSOC_ETR_RWD 0x2C43024
+
+#define mmPSOC_ETR_MODE 0x2C43028
+
+#define mmPSOC_ETR_LBUFLEVEL 0x2C4302C
+
+#define mmPSOC_ETR_CBUFLEVEL 0x2C43030
+
+#define mmPSOC_ETR_BUFWM 0x2C43034
+
+#define mmPSOC_ETR_RRPHI 0x2C43038
+
+#define mmPSOC_ETR_RWPHI 0x2C4303C
+
+#define mmPSOC_ETR_AXICTL 0x2C43110
+
+#define mmPSOC_ETR_DBALO 0x2C43118
+
+#define mmPSOC_ETR_DBAHI 0x2C4311C
+
+#define mmPSOC_ETR_FFSR 0x2C43300
+
+#define mmPSOC_ETR_FFCR 0x2C43304
+
+#define mmPSOC_ETR_PSCR 0x2C43308
+
+#define mmPSOC_ETR_ITMISCOP0 0x2C43EE0
+
+#define mmPSOC_ETR_ITTRFLIN 0x2C43EE8
+
+#define mmPSOC_ETR_ITATBDATA0 0x2C43EEC
+
+#define mmPSOC_ETR_ITATBCTR2 0x2C43EF0
+
+#define mmPSOC_ETR_ITATBCTR1 0x2C43EF4
+
+#define mmPSOC_ETR_ITATBCTR0 0x2C43EF8
+
+#define mmPSOC_ETR_ITCTRL 0x2C43F00
+
+#define mmPSOC_ETR_CLAIMSET 0x2C43FA0
+
+#define mmPSOC_ETR_CLAIMCLR 0x2C43FA4
+
+#define mmPSOC_ETR_LAR 0x2C43FB0
+
+#define mmPSOC_ETR_LSR 0x2C43FB4
+
+#define mmPSOC_ETR_AUTHSTATUS 0x2C43FB8
+
+#define mmPSOC_ETR_DEVID 0x2C43FC8
+
+#define mmPSOC_ETR_DEVTYPE 0x2C43FCC
+
+#define mmPSOC_ETR_PERIPHID4 0x2C43FD0
+
+#define mmPSOC_ETR_PERIPHID5 0x2C43FD4
+
+#define mmPSOC_ETR_PERIPHID6 0x2C43FD8
+
+#define mmPSOC_ETR_PERIPHID7 0x2C43FDC
+
+#define mmPSOC_ETR_PERIPHID0 0x2C43FE0
+
+#define mmPSOC_ETR_PERIPHID1 0x2C43FE4
+
+#define mmPSOC_ETR_PERIPHID2 0x2C43FE8
+
+#define mmPSOC_ETR_PERIPHID3 0x2C43FEC
+
+#define mmPSOC_ETR_COMPID0 0x2C43FF0
+
+#define mmPSOC_ETR_COMPID1 0x2C43FF4
+
+#define mmPSOC_ETR_COMPID2 0x2C43FF8
+
+#define mmPSOC_ETR_COMPID3 0x2C43FFC
+
+#endif /* ASIC_REG_PSOC_ETR_REGS_H_ */
--
2.17.1
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 3/6] habanalabs: set ETR as non-secured
2019-11-10 21:55 [PATCH 1/6] habanalabs: read F/W versions before failure Oded Gabbay
2019-11-10 21:55 ` [PATCH 2/6] habanalabs: use registers name defines for ETR block Oded Gabbay
@ 2019-11-10 21:55 ` Oded Gabbay
2019-11-11 6:01 ` Omer Shpigelman
2019-11-10 21:55 ` [PATCH 4/6] habanalabs: increase max jobs number to 512 Oded Gabbay
` (3 subsequent siblings)
5 siblings, 1 reply; 12+ messages in thread
From: Oded Gabbay @ 2019-11-10 21:55 UTC (permalink / raw)
To: linux-kernel, oshpigelman, ttayar; +Cc: gregkh
ETR should always be non-secured as it is used by the users to record
profiling/trace data.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
drivers/misc/habanalabs/goya/goya_coresight.c | 4 +++-
drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h | 2 ++
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c
index 16bcd60b111f..c1ee6e2b5dff 100644
--- a/drivers/misc/habanalabs/goya/goya_coresight.c
+++ b/drivers/misc/habanalabs/goya/goya_coresight.c
@@ -8,6 +8,7 @@
#include "goyaP.h"
#include "include/goya/goya_coresight.h"
#include "include/goya/asic_reg/goya_regs.h"
+#include "include/goya/asic_reg/goya_masks.h"
#include <uapi/misc/habanalabs.h>
@@ -425,7 +426,8 @@ static int goya_config_etr(struct hl_device *hdev,
WREG32(mmPSOC_ETR_BUFWM, 0x3FFC);
WREG32(mmPSOC_ETR_RSZ, input->buffer_size);
WREG32(mmPSOC_ETR_MODE, input->sink_mode);
- WREG32(mmPSOC_ETR_AXICTL, 0x700);
+ WREG32(mmPSOC_ETR_AXICTL,
+ 0x700 | PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT);
WREG32(mmPSOC_ETR_DBALO,
lower_32_bits(input->buffer_address));
WREG32(mmPSOC_ETR_DBAHI,
diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
index 8618891d5afa..3c44ef3a23ed 100644
--- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
+++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h
@@ -260,4 +260,6 @@
#define DMA_QM_3_GLBL_CFG1_DMA_STOP_SHIFT DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT
#define DMA_QM_4_GLBL_CFG1_DMA_STOP_SHIFT DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT
+#define PSOC_ETR_AXICTL_PROTCTRLBIT1_SHIFT 1
+
#endif /* ASIC_REG_GOYA_MASKS_H_ */
--
2.17.1
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 5/6] habanalabs: don't print error when queues are full
2019-11-10 21:55 [PATCH 1/6] habanalabs: read F/W versions before failure Oded Gabbay
` (2 preceding siblings ...)
2019-11-10 21:55 ` [PATCH 4/6] habanalabs: increase max jobs number to 512 Oded Gabbay
@ 2019-11-10 21:55 ` Oded Gabbay
2019-11-11 6:04 ` Omer Shpigelman
2019-11-10 21:55 ` [PATCH 6/6] habanalabs: export uapi defines to user-space Oded Gabbay
2019-11-11 5:56 ` [PATCH 1/6] habanalabs: read F/W versions before failure Omer Shpigelman
5 siblings, 1 reply; 12+ messages in thread
From: Oded Gabbay @ 2019-11-10 21:55 UTC (permalink / raw)
To: linux-kernel, oshpigelman, ttayar; +Cc: gregkh
If the queues are full and we return -EAGAIN to the user, there is no need
to print an error, as that case isn't an error and the user is expected to
re-submit the work.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
drivers/misc/habanalabs/command_submission.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 776ddafc47fb..8850f475a413 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -626,9 +626,10 @@ static int _hl_cs_ioctl(struct hl_fpriv *hpriv, void __user *chunks,
rc = hl_hw_queue_schedule_cs(cs);
if (rc) {
- dev_err(hdev->dev,
- "Failed to submit CS %d.%llu to H/W queues, error %d\n",
- cs->ctx->asid, cs->sequence, rc);
+ if (rc != -EAGAIN)
+ dev_err(hdev->dev,
+ "Failed to submit CS %d.%llu to H/W queues, error %d\n",
+ cs->ctx->asid, cs->sequence, rc);
goto free_cs_object;
}
--
2.17.1
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 6/6] habanalabs: export uapi defines to user-space
2019-11-10 21:55 [PATCH 1/6] habanalabs: read F/W versions before failure Oded Gabbay
` (3 preceding siblings ...)
2019-11-10 21:55 ` [PATCH 5/6] habanalabs: don't print error when queues are full Oded Gabbay
@ 2019-11-10 21:55 ` Oded Gabbay
2019-11-11 6:08 ` Omer Shpigelman
2019-11-11 5:56 ` [PATCH 1/6] habanalabs: read F/W versions before failure Omer Shpigelman
5 siblings, 1 reply; 12+ messages in thread
From: Oded Gabbay @ 2019-11-10 21:55 UTC (permalink / raw)
To: linux-kernel, oshpigelman, ttayar; +Cc: gregkh
The two defines that control the maximum size of a command buffer and the
maximum number of JOBS per CS need to be exported to the user as they are
part of the API towards user-space.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
drivers/misc/habanalabs/habanalabs.h | 4 ----
include/uapi/misc/habanalabs.h | 16 ++++++++++++----
2 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index 0813041f669a..2a5344cc1a60 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -40,8 +40,6 @@
#define HL_MAX_QUEUES 128
-#define HL_MAX_JOBS_PER_CS 512
-
/* MUST BE POWER OF 2 and larger than 1 */
#define HL_MAX_PENDING_CS 64
@@ -242,8 +240,6 @@ struct hl_dma_fence {
* Command Buffers
*/
-#define HL_MAX_CB_SIZE 0x200000 /* 2MB */
-
/**
* struct hl_cb_mgr - describes a Command Buffer Manager.
* @cb_lock: protects cb_handles.
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index e387d9e560b3..716e70750f23 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -192,13 +192,15 @@ struct hl_info_args {
/* Opcode to destroy previously created command buffer */
#define HL_CB_OP_DESTROY 1
+#define HL_MAX_CB_SIZE 0x200000 /* 2MB */
+
struct hl_cb_in {
/* Handle of CB or 0 if we want to create one */
__u64 cb_handle;
/* HL_CB_OP_* */
__u32 op;
- /* Size of CB. Maximum size is 2MB. The minimum size that will be
- * allocated, regardless of this parameter's value, is PAGE_SIZE
+ /* Size of CB. Maximum size is HL_MAX_CB_SIZE. The minimum size that
+ * will be allocated, regardless of this parameter's value, is PAGE_SIZE
*/
__u32 cb_size;
/* Context ID - Currently not in use */
@@ -244,6 +246,8 @@ struct hl_cs_chunk {
#define HL_CS_STATUS_SUCCESS 0
+#define HL_MAX_JOBS_PER_CS 512
+
struct hl_cs_in {
/* this holds address of array of hl_cs_chunk for restore phase */
__u64 chunks_restore;
@@ -253,9 +257,13 @@ struct hl_cs_in {
* Currently not in use
*/
__u64 chunks_store;
- /* Number of chunks in restore phase array */
+ /* Number of chunks in restore phase array. Maximum number is
+ * HL_MAX_JOBS_PER_CS
+ */
__u32 num_chunks_restore;
- /* Number of chunks in execution array */
+ /* Number of chunks in execution array. Maximum number is
+ * HL_MAX_JOBS_PER_CS
+ */
__u32 num_chunks_execute;
/* Number of chunks in restore phase array - Currently not in use */
__u32 num_chunks_store;
--
2.17.1
^ permalink raw reply related [flat|nested] 12+ messages in thread