diff mbox series

[1/6] accel/ivpu: Add support for hardware fault injection

Message ID 20250129125636.1047413-2-jacek.lawrynowicz@linux.intel.com (mailing list archive)
State New
Headers show
Series accel/ivpu: Changes for 6.15 | expand

Commit Message

Jacek Lawrynowicz Jan. 29, 2025, 12:56 p.m. UTC 
This commit introduces the capability to simulate hardware faults for
testing purposes. The new `fail_hw` fault can be injected in
`ivpu_hw_reg_poll_fld()`, which is used in various parts of the driver
to wait for the hardware to reach a specific state. This allows to test
failures during NPU boot and shutdown, IPC message handling and more.

Fault injection can be enabled using debugfs or a module parameter.

Reviewed-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>
---
 drivers/accel/ivpu/ivpu_debugfs.c   |  5 +++
 drivers/accel/ivpu/ivpu_hw.c        | 14 +++++++
 drivers/accel/ivpu/ivpu_hw_ip.c     |  4 +-
 drivers/accel/ivpu/ivpu_hw_reg_io.h | 64 +++++++++++++++++------------
 4 files changed, 58 insertions(+), 29 deletions(-)

Comments

Jeffrey Hugo Jan. 31, 2025, 6:41 p.m. UTC | #1 
On 1/29/2025 5:56 AM, Jacek Lawrynowicz wrote:
> This commit introduces the capability to simulate hardware faults for

Nit - "This commit" is redundant.

> testing purposes. The new `fail_hw` fault can be injected in
> `ivpu_hw_reg_poll_fld()`, which is used in various parts of the driver
> to wait for the hardware to reach a specific state. This allows to test
> failures during NPU boot and shutdown, IPC message handling and more.
> 
> Fault injection can be enabled using debugfs or a module parameter.
> 
> Reviewed-by: Maciej Falkowski <maciej.falkowski@linux.intel.com>
> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz@linux.intel.com>

Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Jacek Lawrynowicz Feb. 3, 2025, 9:41 a.m. UTC | #2 
On 1/31/2025 7:41 PM, Jeffrey Hugo wrote:
> On 1/29/2025 5:56 AM, Jacek Lawrynowicz wrote:
>> This commit introduces the capability to simulate hardware faults for
> 
> Nit - "This commit" is redundant.

Sure, removed.
diff mbox series

Patch

diff --git a/drivers/accel/ivpu/ivpu_debugfs.c b/drivers/accel/ivpu/ivpu_debugfs.c
index 8180b95ed69dc..e79715c53f2a0 100644
--- a/drivers/accel/ivpu/ivpu_debugfs.c
+++ b/drivers/accel/ivpu/ivpu_debugfs.c
@@ -4,6 +4,7 @@ 
  */
 
 #include <linux/debugfs.h>
+#include <linux/fault-inject.h>
 
 #include <drm/drm_debugfs.h>
 #include <drm/drm_file.h>
@@ -430,4 +431,8 @@  void ivpu_debugfs_init(struct ivpu_device *vdev)
 				    debugfs_root, vdev, &fw_profiling_freq_fops);
 		debugfs_create_file("dct", 0644, debugfs_root, vdev, &ivpu_dct_fops);
 	}
+
+#ifdef CONFIG_FAULT_INJECTION
+	fault_create_debugfs_attr("fail_hw", debugfs_root, &ivpu_hw_failure);
+#endif
 }
diff --git a/drivers/accel/ivpu/ivpu_hw.c b/drivers/accel/ivpu/ivpu_hw.c
index e332f19ab51de..8099ab047bfe6 100644
--- a/drivers/accel/ivpu/ivpu_hw.c
+++ b/drivers/accel/ivpu/ivpu_hw.c
@@ -9,6 +9,15 @@ 
 #include "ivpu_hw_ip.h"
 
 #include <linux/dmi.h>
+#include <linux/fault-inject.h>
+
+#ifdef CONFIG_FAULT_INJECTION
+DECLARE_FAULT_ATTR(ivpu_hw_failure);
+
+static char *ivpu_fail_hw;
+module_param_named_unsafe(fail_hw, ivpu_fail_hw, charp, 0444);
+MODULE_PARM_DESC(fail_hw, "<interval>,<probability>,<space>,<times>");
+#endif
 
 static char *platform_to_str(u32 platform)
 {
@@ -247,6 +256,11 @@  int ivpu_hw_init(struct ivpu_device *vdev)
 	timeouts_init(vdev);
 	atomic_set(&vdev->hw->firewall_irq_counter, 0);
 
+#ifdef CONFIG_FAULT_INJECTION
+	if (ivpu_fail_hw)
+		setup_fault_attr(&ivpu_hw_failure, ivpu_fail_hw);
+#endif
+
 	return 0;
 }
 
diff --git a/drivers/accel/ivpu/ivpu_hw_ip.c b/drivers/accel/ivpu/ivpu_hw_ip.c
index 029dd065614b2..823f6a57dc546 100644
--- a/drivers/accel/ivpu/ivpu_hw_ip.c
+++ b/drivers/accel/ivpu/ivpu_hw_ip.c
@@ -968,14 +968,14 @@  void ivpu_hw_ip_wdt_disable(struct ivpu_device *vdev)
 
 static u32 ipc_rx_count_get_37xx(struct ivpu_device *vdev)
 {
-	u32 count = REGV_RD32_SILENT(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT);
+	u32 count = readl(vdev->regv + VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT);
 
 	return REG_GET_FLD(VPU_37XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
 }
 
 static u32 ipc_rx_count_get_40xx(struct ivpu_device *vdev)
 {
-	u32 count = REGV_RD32_SILENT(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT);
+	u32 count = readl(vdev->regv + VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT);
 
 	return REG_GET_FLD(VPU_40XX_HOST_SS_TIM_IPC_FIFO_STAT, FILL_LEVEL, count);
 }
diff --git a/drivers/accel/ivpu/ivpu_hw_reg_io.h b/drivers/accel/ivpu/ivpu_hw_reg_io.h
index 79b3f441eac4d..66259b0ead026 100644
--- a/drivers/accel/ivpu/ivpu_hw_reg_io.h
+++ b/drivers/accel/ivpu/ivpu_hw_reg_io.h
@@ -7,6 +7,7 @@ 
 #define __IVPU_HW_REG_IO_H__
 
 #include <linux/bitfield.h>
+#include <linux/fault-inject.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
 
@@ -16,13 +17,11 @@ 
 #define REG_IO_ERROR      0xffffffff
 
 #define REGB_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regb, (reg), #reg, __func__)
-#define REGB_RD32_SILENT(reg)   readl(vdev->regb + (reg))
 #define REGB_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regb, (reg), #reg, __func__)
 #define REGB_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regb, (reg), (val), #reg, __func__)
 #define REGB_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regb, (reg), (val), #reg, __func__)
 
 #define REGV_RD32(reg)          ivpu_hw_reg_rd32(vdev, vdev->regv, (reg), #reg, __func__)
-#define REGV_RD32_SILENT(reg)   readl(vdev->regv + (reg))
 #define REGV_RD64(reg)          ivpu_hw_reg_rd64(vdev, vdev->regv, (reg), #reg, __func__)
 #define REGV_WR32(reg, val)     ivpu_hw_reg_wr32(vdev, vdev->regv, (reg), (val), #reg, __func__)
 #define REGV_WR64(reg, val)     ivpu_hw_reg_wr64(vdev, vdev->regv, (reg), (val), #reg, __func__)
@@ -47,31 +46,42 @@ 
 #define REG_TEST_FLD_NUM(REG, FLD, num, val) \
 	((num) == FIELD_GET(REG##_##FLD##_MASK, val))
 
-#define REGB_POLL_FLD(reg, fld, val, timeout_us) \
-({ \
-	u32 var; \
-	int r; \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \
-		 __func__, #reg, reg, #fld, val); \
-	r = read_poll_timeout(REGB_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\
-			      REG_POLL_SLEEP_US, timeout_us, false, (reg)); \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \
-		 __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \
-	r; \
-})
-
-#define REGV_POLL_FLD(reg, fld, val, timeout_us) \
-({ \
-	u32 var; \
-	int r; \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s started (expected 0x%x)\n", \
-		 __func__, #reg, reg, #fld, val); \
-	r = read_poll_timeout(REGV_RD32_SILENT, var, (FIELD_GET(reg##_##fld##_MASK, var) == (val)),\
-			      REG_POLL_SLEEP_US, timeout_us, false, (reg)); \
-	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) Polling field %s %s (reg val 0x%08x)\n", \
-		 __func__, #reg, reg, #fld, r ? "ETIMEDOUT" : "OK", var); \
-	r; \
-})
+#define REGB_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \
+	ivpu_hw_reg_poll_fld(vdev, vdev->regb, reg, reg##_##fld##_MASK, \
+			     FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \
+			     __func__, #reg, #fld)
+
+#define REGV_POLL_FLD(reg, fld, exp_fld_val, timeout_us) \
+	ivpu_hw_reg_poll_fld(vdev, vdev->regv, reg, reg##_##fld##_MASK, \
+			     FIELD_PREP(reg##_##fld##_MASK, exp_fld_val), timeout_us, \
+			     __func__, #reg, #fld)
+
+extern struct fault_attr ivpu_hw_failure;
+
+static inline int __must_check
+ivpu_hw_reg_poll_fld(struct ivpu_device *vdev, void __iomem *base,
+		     u32 reg_offset, u32 reg_mask, u32 exp_masked_val, u32 timeout_us,
+		     const char *func_name, const char *reg_name, const char *fld_name)
+{
+	u32 reg_val;
+	int ret;
+
+	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s started (exp_val 0x%x)\n",
+		 func_name, reg_name, reg_offset, fld_name, exp_masked_val);
+
+	ret = read_poll_timeout(readl, reg_val, (reg_val & reg_mask) == exp_masked_val,
+				REG_POLL_SLEEP_US, timeout_us, false, base + reg_offset);
+
+#ifdef CONFIG_FAULT_INJECTION
+	if (should_fail(&ivpu_hw_failure, 1))
+		ret = -ETIMEDOUT;
+#endif
+
+	ivpu_dbg(vdev, REG, "%s : %s (0x%08x) POLL %s %s (reg_val 0x%08x)\n",
+		 func_name, reg_name, reg_offset, fld_name, ret ? "ETIMEDOUT" : "OK", reg_val);
+
+	return ret;
+}
 
 static inline u32
 ivpu_hw_reg_rd32(struct ivpu_device *vdev, void __iomem *base, u32 reg,