Automatic merge of 'next' into merge (2025-05-12 10:01)

Author: maddy-kerneldev

Documentation/arch/powerpc/htm.rst

@@ -0,0 +1,104 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. _htm:
+
+===================================
+HTM (Hardware Trace Macro)
+===================================
+
+Athira Rajeev, 2 Mar 2025
+
+.. contents::
+    :depth: 3
+
+
+Basic overview
+==============
+
+H_HTM is used as an interface for executing Hardware Trace Macro (HTM)
+functions, including setup, configuration, control and dumping of the HTM data.
+For using HTM, it is required to setup HTM buffers and HTM operations can
+be controlled using the H_HTM hcall. The hcall can be invoked for any core/chip
+of the system from within a partition itself. To use this feature, a debugfs
+folder called "htmdump" is present under /sys/kernel/debug/powerpc.
+
+
+HTM debugfs example usage
+=========================
+
+.. code-block:: sh
+
+  #  ls /sys/kernel/debug/powerpc/htmdump/
+  coreindexonchip  htmcaps  htmconfigure  htmflags  htminfo  htmsetup
+  htmstart  htmstatus  htmtype  nodalchipindex  nodeindex  trace
+
+Details on each file:
+
+* nodeindex, nodalchipindex, coreindexonchip specifies which partition to configure the HTM for.
+* htmtype: specifies the type of HTM. Supported target is hardwareTarget.
+* trace: is to read the HTM data.
+* htmconfigure: Configure/Deconfigure the HTM. Writing 1 to the file will configure the trace, writing 0 to the file will do deconfigure.
+* htmstart: start/Stop the HTM. Writing 1 to the file will start the tracing, writing 0 to the file will stop the tracing.
+* htmstatus: get the status of HTM. This is needed to understand the HTM state after each operation.
+* htmsetup: set the HTM buffer size. Size of HTM buffer is in power of 2
+* htminfo: provides the system processor configuration details. This is needed to understand the appropriate values for nodeindex, nodalchipindex, coreindexonchip.
+* htmcaps : provides the HTM capabilities like minimum/maximum buffer size, what kind of tracing the HTM supports etc.
+* htmflags : allows to pass flags to hcall. Currently supports controlling the wrapping of HTM buffer.
+
+To see the system processor configuration details:
+
+.. code-block:: sh
+
+  # cat /sys/kernel/debug/powerpc/htmdump/htminfo > htminfo_file
+
+The result can be interpreted using hexdump.
+
+To collect HTM traces for a partition represented by nodeindex as
+zero, nodalchipindex as 1 and coreindexonchip as 12
+
+.. code-block:: sh
+
+  # cd /sys/kernel/debug/powerpc/htmdump/
+  # echo 2 > htmtype
+  # echo 33 > htmsetup ( sets 8GB memory for HTM buffer, number is size in power of 2 )
+
+This requires a CEC reboot to get the HTM buffers allocated.
+
+.. code-block:: sh
+
+  # cd /sys/kernel/debug/powerpc/htmdump/
+  # echo 2 > htmtype
+  # echo 0 > nodeindex
+  # echo 1 > nodalchipindex
+  # echo 12 > coreindexonchip
+  # echo 1 > htmflags     # to set noWrap for HTM buffers
+  # echo 1 > htmconfigure # Configure the HTM
+  # echo 1 > htmstart     # Start the HTM
+  # echo 0 > htmstart     # Stop the HTM
+  # echo 0 > htmconfigure # Deconfigure the HTM
+  # cat htmstatus         # Dump the status of HTM entries as data
+
+Above will set the htmtype and core details, followed by executing respective HTM operation.
+
+Read the HTM trace data
+========================
+
+After starting the trace collection, run the workload
+of interest. Stop the trace collection after required period
+of time, and read the trace file.
+
+.. code-block:: sh
+
+  # cat /sys/kernel/debug/powerpc/htmdump/trace > trace_file
+
+This trace file will contain the relevant instruction traces
+collected during the workload execution. And can be used as
+input file for trace decoders to understand data.
+
+Benefits of using HTM debugfs interface
+=======================================
+
+It is now possible to collect traces for a particular core/chip
+from within any partition of the system and decode it. Through
+this enablement, a small partition can be dedicated to collect the
+trace data and analyze to provide important information for Performance
+analysis, Software tuning, or Hardware debug.

arch/powerpc/boot/Makefile

@@ -70,6 +70,7 @@ BOOTCPPFLAGS	:= -nostdinc $(LINUXINCLUDE)
 BOOTCPPFLAGS	+= -isystem $(shell $(BOOTCC) -print-file-name=include)
 
 BOOTCFLAGS	:= $(BOOTTARGETFLAGS) \
+		   -std=gnu11 \
 		   -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -O2 \
 		   -msoft-float -mno-altivec -mno-vsx \

arch/powerpc/include/asm/plpar_wrappers.h

@@ -65,6 +65,14 @@ static inline long register_dtl(unsigned long cpu, unsigned long vpa)
 	return vpa_call(H_VPA_REG_DTL, cpu, vpa);
 }
 
+/*
+ * Invokes H_HTM hcall with parameters passed from htm_hcall_wrapper.
+ * flags: Set to hardwareTarget.
+ * target: Specifies target using node index, nodal chip index and core index.
+ * operation : action to perform ie configure, start, stop, deconfigure, trace
+ * based on the HTM type.
+ * param1, param2, param3: parameters for each action.
+ */
 static inline long htm_call(unsigned long flags, unsigned long target,
                unsigned long operation, unsigned long param1,
                unsigned long param2, unsigned long param3)
@@ -73,17 +81,17 @@ static inline long htm_call(unsigned long flags, unsigned long target,
                                  param1, param2, param3);
 }
 
-static inline long htm_get_dump_hardware(unsigned long nodeindex,
+static inline long htm_hcall_wrapper(unsigned long flags, unsigned long nodeindex,
                unsigned long nodalchipindex, unsigned long coreindexonchip,
-               unsigned long type, unsigned long addr, unsigned long size,
-               unsigned long offset)
+	       unsigned long type, unsigned long htm_op, unsigned long param1, unsigned long param2,
+	       unsigned long param3)
 {
-       return htm_call(H_HTM_FLAGS_HARDWARE_TARGET,
+	return htm_call(H_HTM_FLAGS_HARDWARE_TARGET | flags,
                        H_HTM_TARGET_NODE_INDEX(nodeindex) |
                        H_HTM_TARGET_NODAL_CHIP_INDEX(nodalchipindex) |
                        H_HTM_TARGET_CORE_INDEX_ON_CHIP(coreindexonchip),
-                       H_HTM_OP(H_HTM_OP_DUMP_DATA) | H_HTM_TYPE(type),
-                       addr, size, offset);
+		       H_HTM_OP(htm_op) | H_HTM_TYPE(type),
+		       param1, param2, param3);
 }
 
 extern void vpa_init(int cpu);

arch/powerpc/platforms/44x/gpio.c

@@ -75,8 +75,7 @@ __ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 		clrbits32(&regs->or, GPIO_MASK(gpio));
 }
 
-static void
-ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct ppc4xx_gpio_chip *chip = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -88,6 +87,8 @@ ppc4xx_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 	spin_unlock_irqrestore(&chip->lock, flags);
 
 	pr_debug("%s: gpio: %d val: %d\n", __func__, gpio, val);
+
+	return 0;
 }
 
 static int ppc4xx_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -179,7 +180,7 @@ static int __init ppc4xx_add_gpiochips(void)
 		gc->direction_input = ppc4xx_gpio_dir_in;
 		gc->direction_output = ppc4xx_gpio_dir_out;
 		gc->get = ppc4xx_gpio_get;
-		gc->set = ppc4xx_gpio_set;
+		gc->set_rv = ppc4xx_gpio_set;
 
 		ret = of_mm_gpiochip_add_data(np, mm_gc, ppc4xx_gc);
 		if (ret)

arch/powerpc/platforms/52xx/mpc52xx_gpt.c

@@ -280,7 +280,7 @@ static int mpc52xx_gpt_gpio_get(struct gpio_chip *gc, unsigned int gpio)
 	return (in_be32(&gpt->regs->status) >> 8) & 1;
 }
 
-static void
+static int
 mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 {
 	struct mpc52xx_gpt_priv *gpt = gpiochip_get_data(gc);
@@ -293,6 +293,8 @@ mpc52xx_gpt_gpio_set(struct gpio_chip *gc, unsigned int gpio, int v)
 	raw_spin_lock_irqsave(&gpt->lock, flags);
 	clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_GPIO_MASK, r);
 	raw_spin_unlock_irqrestore(&gpt->lock, flags);
+
+	return 0;
 }
 
 static int mpc52xx_gpt_gpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
@@ -334,7 +336,7 @@ static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt)
 	gpt->gc.direction_input  = mpc52xx_gpt_gpio_dir_in;
 	gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out;
 	gpt->gc.get = mpc52xx_gpt_gpio_get;
-	gpt->gc.set = mpc52xx_gpt_gpio_set;
+	gpt->gc.set_rv = mpc52xx_gpt_gpio_set;
 	gpt->gc.base = -1;
 	gpt->gc.parent = gpt->dev;
 

arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c

@@ -92,25 +92,28 @@ static void mcu_power_off(void)
 	mutex_unlock(&mcu->lock);
 }
 
-static void mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
+static int mcu_gpio_set(struct gpio_chip *gc, unsigned int gpio, int val)
 {
 	struct mcu *mcu = gpiochip_get_data(gc);
 	u8 bit = 1 << (4 + gpio);
+	int ret;
 
 	mutex_lock(&mcu->lock);
 	if (val)
 		mcu->reg_ctrl &= ~bit;
 	else
 		mcu->reg_ctrl |= bit;
 
-	i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL, mcu->reg_ctrl);
+	ret = i2c_smbus_write_byte_data(mcu->client, MCU_REG_CTRL,
+					mcu->reg_ctrl);
 	mutex_unlock(&mcu->lock);
+
+	return ret;
 }
 
 static int mcu_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 {
-	mcu_gpio_set(gc, gpio, val);
-	return 0;
+	return mcu_gpio_set(gc, gpio, val);
 }
 
 static int mcu_gpiochip_add(struct mcu *mcu)
@@ -123,7 +126,7 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 	gc->can_sleep = 1;
 	gc->ngpio = MCU_NUM_GPIO;
 	gc->base = -1;
-	gc->set = mcu_gpio_set;
+	gc->set_rv = mcu_gpio_set;
 	gc->direction_output = mcu_gpio_dir_out;
 	gc->parent = dev;
 

arch/powerpc/platforms/8xx/cpm1.c

@@ -417,7 +417,7 @@ static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, in
 	out_be16(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
 	struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -428,6 +428,8 @@ static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value)
 	__cpm1_gpio16_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio)
@@ -497,7 +499,7 @@ int cpm1_gpiochip_add16(struct device *dev)
 	gc->direction_input = cpm1_gpio16_dir_in;
 	gc->direction_output = cpm1_gpio16_dir_out;
 	gc->get = cpm1_gpio16_get;
-	gc->set = cpm1_gpio16_set;
+	gc->set_rv = cpm1_gpio16_set;
 	gc->to_irq = cpm1_gpio16_to_irq;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
@@ -554,7 +556,7 @@ static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, in
 	out_be32(&iop->dat, cpm1_gc->cpdata);
 }
 
-static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
+static int cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 {
 	struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc);
 	unsigned long flags;
@@ -565,6 +567,8 @@ static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value)
 	__cpm1_gpio32_set(cpm1_gc, pin_mask, value);
 
 	spin_unlock_irqrestore(&cpm1_gc->lock, flags);
+
+	return 0;
 }
 
 static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -618,7 +622,7 @@ int cpm1_gpiochip_add32(struct device *dev)
 	gc->direction_input = cpm1_gpio32_dir_in;
 	gc->direction_output = cpm1_gpio32_dir_out;
 	gc->get = cpm1_gpio32_get;
-	gc->set = cpm1_gpio32_set;
+	gc->set_rv = cpm1_gpio32_set;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;