diff options
Diffstat (limited to 'drivers/hwtracing')
91 files changed, 27983 insertions, 5397 deletions
diff --git a/drivers/hwtracing/Kconfig b/drivers/hwtracing/Kconfig index f68e025c5131..911ee977103c 100644 --- a/drivers/hwtracing/Kconfig +++ b/drivers/hwtracing/Kconfig @@ -1,7 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only menu "HW tracing support" source "drivers/hwtracing/stm/Kconfig" source "drivers/hwtracing/intel_th/Kconfig" +source "drivers/hwtracing/ptt/Kconfig" + endmenu diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index ad34380cac49..6a4239ebb582 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -1,10 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Coresight configuration # menuconfig CORESIGHT - bool "CoreSight Tracing Support" + tristate "CoreSight Tracing Support" + depends on ARM || ARM64 + depends on OF || ACPI select ARM_AMBA select PERF_EVENTS + select CONFIGFS_FS help This framework provides a kernel interface for the CoreSight debug and trace drivers to register themselves with. It's intended to build @@ -12,17 +16,24 @@ menuconfig CORESIGHT specification and configure the right series of components when a trace source gets enabled. + To compile this driver as a module, choose M here: the + module will be called coresight. + if CORESIGHT config CORESIGHT_LINKS_AND_SINKS - bool "CoreSight Link and Sink drivers" + tristate "CoreSight Link and Sink drivers" help This enables support for CoreSight link and sink drivers that are responsible for transporting and collecting the trace data respectively. Link and sinks are dynamically aggregated with a trace entity at run time to form a complete trace path. + To compile these drivers as modules, choose M here: the + modules will be called coresight-funnel and coresight-replicator. + config CORESIGHT_LINK_AND_SINK_TMC - bool "Coresight generic TMC driver" + tristate "Coresight generic TMC driver" + depends on CORESIGHT_LINKS_AND_SINKS help This enables support for the Trace Memory Controller driver. @@ -31,8 +42,11 @@ config CORESIGHT_LINK_AND_SINK_TMC complies with the generic implementation of the component without special enhancement or added features. + To compile this driver as a module, choose M here: the + module will be called coresight-tmc. + config CORESIGHT_CATU - bool "Coresight Address Translation Unit (CATU) driver" + tristate "Coresight Address Translation Unit (CATU) driver" depends on CORESIGHT_LINK_AND_SINK_TMC help Enable support for the Coresight Address Translation Unit (CATU). @@ -42,8 +56,11 @@ config CORESIGHT_CATU by looking up the provided table. CATU can also be used in pass-through mode where the address is not translated. + To compile this driver as a module, choose M here: the + module will be called coresight-catu. + config CORESIGHT_SINK_TPIU - bool "Coresight generic TPIU driver" + tristate "Coresight generic TPIU driver" depends on CORESIGHT_LINKS_AND_SINKS help This enables support for the Trace Port Interface Unit driver, @@ -53,16 +70,22 @@ config CORESIGHT_SINK_TPIU connected to an external host for use case capturing more traces than the on-board coresight memory can handle. + To compile this driver as a module, choose M here: the + module will be called coresight-tpiu. + config CORESIGHT_SINK_ETBV10 - bool "Coresight ETBv1.0 driver" + tristate "Coresight ETBv1.0 driver" depends on CORESIGHT_LINKS_AND_SINKS help This enables support for the Embedded Trace Buffer version 1.0 driver that complies with the generic implementation of the component without special enhancement or added features. + To compile this driver as a module, choose M here: the + module will be called coresight-etb10. + config CORESIGHT_SOURCE_ETM3X - bool "CoreSight Embedded Trace Macrocell 3.x driver" + tristate "CoreSight Embedded Trace Macrocell 3.x driver" depends on !ARM64 select CORESIGHT_LINKS_AND_SINKS help @@ -71,26 +94,33 @@ config CORESIGHT_SOURCE_ETM3X This is primarily useful for instruction level tracing. Depending the ETM version data tracing may also be available. + To compile this driver as a module, choose M here: the + module will be called coresight-etm3x. + config CORESIGHT_SOURCE_ETM4X - bool "CoreSight Embedded Trace Macrocell 4.x driver" + tristate "CoreSight ETMv4.x / ETE driver" depends on ARM64 select CORESIGHT_LINKS_AND_SINKS + select PID_IN_CONTEXTIDR help - This driver provides support for the ETM4.x tracer module, tracing the - instructions that a processor is executing. This is primarily useful - for instruction level tracing. Depending on the implemented version - data tracing may also be available. + This driver provides support for the CoreSight Embedded Trace Macrocell + version 4.x and the Embedded Trace Extensions (ETE). Both are CPU tracer + modules, tracing the instructions that a processor is executing. This is + primarily useful for instruction level tracing. -config CORESIGHT_DYNAMIC_REPLICATOR - bool "CoreSight Programmable Replicator driver" - depends on CORESIGHT_LINKS_AND_SINKS + To compile this driver as a module, choose M here: the + module will be called coresight-etm4x. + +config ETM4X_IMPDEF_FEATURE + bool "Control implementation defined overflow support in ETM 4.x driver" + depends on CORESIGHT_SOURCE_ETM4X help - This enables support for dynamic CoreSight replicator link driver. - The programmable ATB replicator allows independent filtering of the - trace data based on the traceid. + This control provides implementation define control for CoreSight + ETM 4.x tracer module that can't reduce commit rate automatically. + This avoids overflow between the ETM tracer module and the cpu core. config CORESIGHT_STM - bool "CoreSight System Trace Macrocell driver" + tristate "CoreSight System Trace Macrocell driver" depends on (ARM && !(CPU_32v3 || CPU_32v4 || CPU_32v4T)) || ARM64 select CORESIGHT_LINKS_AND_SINKS select STM @@ -100,6 +130,21 @@ config CORESIGHT_STM logging useful software events or data coming from various entities in the system, possibly running different OSs + To compile this driver as a module, choose M here: the + module will be called coresight-stm. + +config CORESIGHT_CTCU + tristate "CoreSight TMC Control Unit driver" + depends on CORESIGHT_LINK_AND_SINK_TMC + help + This driver provides support for CoreSight TMC Control Unit + that hosts miscellaneous configuration registers. This is + primarily used for controlling the behaviors of the TMC + ETR device. + + To compile this driver as a module, choose M here: the + module will be called coresight-ctcu. + config CORESIGHT_CPU_DEBUG tristate "CoreSight CPU Debug driver" depends on ARM || ARM64 @@ -111,7 +156,128 @@ config CORESIGHT_CPU_DEBUG can quickly get to know program counter (PC), secure state, exception level, etc. Before use debugging functionality, platform needs to ensure the clock domain and power domain are enabled - properly, please refer Documentation/trace/coresight-cpu-debug.txt + properly, please refer Documentation/trace/coresight/coresight-cpu-debug.rst for detailed description and the example for usage. + To compile this driver as a module, choose M here: the + module will be called coresight-cpu-debug. + +config CORESIGHT_CPU_DEBUG_DEFAULT_ON + bool "Enable CoreSight CPU Debug by default" + depends on CORESIGHT_CPU_DEBUG + help + Say Y here to enable the CoreSight Debug panic-debug by default. This + can also be enabled via debugfs, but this ensures the debug feature + is enabled as early as possible. + + Has the same effect as setting coresight_cpu_debug.enable=1 on the + kernel command line. + + Say N if unsure. + +config CORESIGHT_CTI + tristate "CoreSight Cross Trigger Interface (CTI) driver" + depends on ARM || ARM64 + help + This driver provides support for CoreSight CTI and CTM components. + These provide hardware triggering events between CoreSight trace + source and sink components. These can be used to halt trace or + inject events into the trace stream. CTI also provides a software + control to trigger the same halt events. This can provide fast trace + halt compared to disabling sources and sinks normally in driver + software. + + To compile this driver as a module, choose M here: the + module will be called coresight-cti. + +config CORESIGHT_CTI_INTEGRATION_REGS + bool "Access CTI CoreSight Integration Registers" + depends on CORESIGHT_CTI + help + This option adds support for the CoreSight integration registers on + this device. The integration registers allow the exploration of the + CTI trigger connections between this and other devices.These + registers are not used in normal operation and can leave devices in + an inconsistent state. + +config CORESIGHT_TRBE + tristate "Trace Buffer Extension (TRBE) driver" + depends on ARM64 && CORESIGHT_SOURCE_ETM4X + help + This driver provides support for percpu Trace Buffer Extension (TRBE). + TRBE always needs to be used along with its corresponding percpu ETE + component. ETE generates trace data which is then captured with TRBE. + Unlike traditional sink devices, TRBE is a CPU feature accessible via + system registers. But its explicit dependency with trace unit (ETE) + requires it to be plugged in as a coresight sink device. + + To compile this driver as a module, choose M here: the module will be + called coresight-trbe. + +config ULTRASOC_SMB + tristate "Ultrasoc system memory buffer drivers" + depends on ACPI || COMPILE_TEST + depends on ARM64 && CORESIGHT_LINKS_AND_SINKS + help + This driver provides support for the Ultrasoc system memory buffer (SMB). + SMB is responsible for receiving the trace data from Coresight ETM devices + and storing them to a system buffer. + + To compile this driver as a module, choose M here: the module will be + called ultrasoc-smb. + +config CORESIGHT_TPDM + tristate "CoreSight Trace, Profiling & Diagnostics Monitor driver" + select CORESIGHT_LINKS_AND_SINKS + select CORESIGHT_TPDA + help + This driver provides support for configuring monitor. Monitors are + primarily responsible for data set collection and support the + ability to collect any permutation of data set types. + + To compile this driver as a module, choose M here: the module will be + called coresight-tpdm. + +config CORESIGHT_TPDA + tristate "CoreSight Trace, Profiling & Diagnostics Aggregator driver" + help + This driver provides support for configuring aggregator. This is + primarily useful for pulling the data sets from one or more + attached monitors and pushing the resultant data out. Multiple + monitors are connected on different input ports of TPDA. + + To compile this driver as a module, choose M here: the module will be + called coresight-tpda. + +config CORESIGHT_DUMMY + tristate "Dummy driver support" + help + Enables support for dummy driver. Dummy driver can be used for + CoreSight sources/sinks that are owned and configured by some + other subsystem and use Linux drivers to configure rest of trace + path. + + To compile this driver as a module, choose M here: the module will be + called coresight-dummy. + +config CORESIGHT_KUNIT_TESTS + tristate "Enable Coresight unit tests" + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable Coresight unit tests. Only useful for development and not + intended for production. + +config CORESIGHT_TNOC + tristate "Coresight Trace Network On Chip driver" + help + This driver provides support for Trace Network On Chip (TNOC) component. + TNOC is an interconnect used to collect traces from various subsystems + and transport to a coresight trace sink. It sits in the different + tiles of SOC and aggregates the trace local to the tile and transports + it another tile or to coresight trace sink eventually. + + To compile this driver as a module, choose M here: the module will be + called coresight-tnoc. + endif diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index 41870ded51a3..ab16d06783a5 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -2,20 +2,58 @@ # # Makefile for CoreSight drivers. # -obj-$(CONFIG_CORESIGHT) += coresight.o coresight-etm-perf.o -obj-$(CONFIG_OF) += of_coresight.o -obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o \ - coresight-tmc-etf.o \ - coresight-tmc-etr.o + +# Current W=1 warnings +subdir-ccflags-y += -Wextra -Wunused -Wno-unused-parameter +subdir-ccflags-y += -Wmissing-declarations +subdir-ccflags-y += -Wmissing-format-attribute +subdir-ccflags-y += -Wmissing-prototypes +subdir-ccflags-y += -Wold-style-definition +subdir-ccflags-y += -Wmissing-include-dirs +subdir-ccflags-y += -Wno-sign-compare +condflags := \ + $(call cc-option, -Wrestrict) \ + $(call cc-option, -Wunused-but-set-variable) \ + $(call cc-option, -Wunused-const-variable) \ + $(call cc-option, -Wpacked-not-aligned) \ + $(call cc-option, -Wformat-overflow) \ + $(call cc-option, -Wformat-truncation) \ + $(call cc-option, -Wstringop-overflow) \ + $(call cc-option, -Wstringop-truncation) +subdir-ccflags-y += $(condflags) + +CFLAGS_coresight-stm.o := -D__DISABLE_TRACE_MMIO__ + +obj-$(CONFIG_CORESIGHT) += coresight.o +coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \ + coresight-sysfs.o coresight-syscfg.o coresight-config.o \ + coresight-cfg-preload.o coresight-cfg-afdo.o coresight-cfg-pstop.o \ + coresight-syscfg-configfs.o coresight-trace-id.o +obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o +coresight-tmc-y := coresight-tmc-core.o coresight-tmc-etf.o \ + coresight-tmc-etr.o obj-$(CONFIG_CORESIGHT_SINK_TPIU) += coresight-tpiu.o obj-$(CONFIG_CORESIGHT_SINK_ETBV10) += coresight-etb10.o obj-$(CONFIG_CORESIGHT_LINKS_AND_SINKS) += coresight-funnel.o \ coresight-replicator.o -obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o \ - coresight-etm3x-sysfs.o -obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o \ - coresight-etm4x-sysfs.o -obj-$(CONFIG_CORESIGHT_DYNAMIC_REPLICATOR) += coresight-dynamic-replicator.o +obj-$(CONFIG_CORESIGHT_TNOC) += coresight-tnoc.o +obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o +coresight-etm3x-y := coresight-etm3x-core.o coresight-etm-cp14.o \ + coresight-etm3x-sysfs.o +obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o +coresight-etm4x-y := coresight-etm4x-core.o coresight-etm4x-sysfs.o \ + coresight-etm4x-cfg.o obj-$(CONFIG_CORESIGHT_STM) += coresight-stm.o obj-$(CONFIG_CORESIGHT_CPU_DEBUG) += coresight-cpu-debug.o obj-$(CONFIG_CORESIGHT_CATU) += coresight-catu.o +obj-$(CONFIG_CORESIGHT_CTI) += coresight-cti.o +obj-$(CONFIG_CORESIGHT_TRBE) += coresight-trbe.o +obj-$(CONFIG_CORESIGHT_TPDM) += coresight-tpdm.o +obj-$(CONFIG_CORESIGHT_TPDA) += coresight-tpda.o +coresight-cti-y := coresight-cti-core.o coresight-cti-platform.o \ + coresight-cti-sysfs.o +obj-$(CONFIG_ULTRASOC_SMB) += ultrasoc-smb.o +obj-$(CONFIG_CORESIGHT_DUMMY) += coresight-dummy.o +obj-$(CONFIG_CORESIGHT_CTCU) += coresight-ctcu.o +coresight-ctcu-y := coresight-ctcu-core.o +obj-$(CONFIG_CORESIGHT_KUNIT_TESTS) += coresight-kunit-tests.o diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index 170fbb66bda2..69b36bae97ab 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -7,11 +7,13 @@ * Author: Suzuki K Poulose <suzuki.poulose@arm.com> */ +#include <linux/acpi.h> #include <linux/amba/bus.h> #include <linux/device.h> #include <linux/dma-mapping.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/platform_device.h> #include <linux/slab.h> #include "coresight-catu.h" @@ -28,6 +30,8 @@ #define catu_dbg(x, ...) do {} while (0) #endif +DEFINE_CORESIGHT_DEVLIST(catu_devs, "catu"); + struct catu_etr_buf { struct tmc_sg_table *catu_table; dma_addr_t sladdr; @@ -109,9 +113,8 @@ typedef u64 cate_t; * containing the data page pointer for @offset. If @daddrp is not NULL, * @daddrp points the DMA address of the beginning of the table. */ -static inline cate_t *catu_get_table(struct tmc_sg_table *catu_table, - unsigned long offset, - dma_addr_t *daddrp) +static cate_t *catu_get_table(struct tmc_sg_table *catu_table, unsigned long offset, + dma_addr_t *daddrp) { unsigned long buf_size = tmc_sg_table_buf_size(catu_table); unsigned int table_nr, pg_idx, pg_offset; @@ -161,12 +164,12 @@ static void catu_dump_table(struct tmc_sg_table *catu_table) } #else -static inline void catu_dump_table(struct tmc_sg_table *catu_table) +static void catu_dump_table(struct tmc_sg_table *catu_table) { } #endif -static inline cate_t catu_make_entry(dma_addr_t addr) +static cate_t catu_make_entry(dma_addr_t addr) { return addr ? CATU_VALID_ENTRY(addr) : 0; } @@ -265,7 +268,7 @@ catu_init_sg_table(struct device *catu_dev, int node, * Each table can address upto 1MB and we can have * CATU_PAGES_PER_SYSPAGE tables in a system page. */ - nr_tpages = DIV_ROUND_UP(size, SZ_1M) / CATU_PAGES_PER_SYSPAGE; + nr_tpages = DIV_ROUND_UP(size, CATU_PAGES_PER_SYSPAGE * SZ_1M); catu_table = tmc_alloc_sg_table(catu_dev, node, nr_tpages, size >> PAGE_SHIFT, pages); if (IS_ERR(catu_table)) @@ -328,19 +331,18 @@ static int catu_alloc_etr_buf(struct tmc_drvdata *tmc_drvdata, struct etr_buf *etr_buf, int node, void **pages) { struct coresight_device *csdev; - struct device *catu_dev; struct tmc_sg_table *catu_table; struct catu_etr_buf *catu_buf; csdev = tmc_etr_get_catu_device(tmc_drvdata); if (!csdev) return -ENODEV; - catu_dev = csdev->dev.parent; catu_buf = kzalloc(sizeof(*catu_buf), GFP_KERNEL); if (!catu_buf) return -ENOMEM; - catu_table = catu_init_sg_table(catu_dev, node, etr_buf->size, pages); + catu_table = catu_init_sg_table(&csdev->dev, node, + etr_buf->size, pages); if (IS_ERR(catu_table)) { kfree(catu_buf); return PTR_ERR(catu_table); @@ -357,33 +359,22 @@ static int catu_alloc_etr_buf(struct tmc_drvdata *tmc_drvdata, return 0; } -const struct etr_buf_operations etr_catu_buf_ops = { +static const struct etr_buf_operations etr_catu_buf_ops = { .alloc = catu_alloc_etr_buf, .free = catu_free_etr_buf, .sync = catu_sync_etr_buf, .get_data = catu_get_data_etr_buf, }; -coresight_simple_reg32(struct catu_drvdata, devid, CORESIGHT_DEVID); -coresight_simple_reg32(struct catu_drvdata, control, CATU_CONTROL); -coresight_simple_reg32(struct catu_drvdata, status, CATU_STATUS); -coresight_simple_reg32(struct catu_drvdata, mode, CATU_MODE); -coresight_simple_reg32(struct catu_drvdata, axictrl, CATU_AXICTRL); -coresight_simple_reg32(struct catu_drvdata, irqen, CATU_IRQEN); -coresight_simple_reg64(struct catu_drvdata, sladdr, - CATU_SLADDRLO, CATU_SLADDRHI); -coresight_simple_reg64(struct catu_drvdata, inaddr, - CATU_INADDRLO, CATU_INADDRHI); - static struct attribute *catu_mgmt_attrs[] = { - &dev_attr_devid.attr, - &dev_attr_control.attr, - &dev_attr_status.attr, - &dev_attr_mode.attr, - &dev_attr_axictrl.attr, - &dev_attr_irqen.attr, - &dev_attr_sladdr.attr, - &dev_attr_inaddr.attr, + coresight_simple_reg32(devid, CORESIGHT_DEVID), + coresight_simple_reg32(control, CATU_CONTROL), + coresight_simple_reg32(status, CATU_STATUS), + coresight_simple_reg32(mode, CATU_MODE), + coresight_simple_reg32(axictrl, CATU_AXICTRL), + coresight_simple_reg32(irqen, CATU_IRQEN), + coresight_simple_reg64(sladdr, CATU_SLADDRLO, CATU_SLADDRHI), + coresight_simple_reg64(inaddr, CATU_INADDRLO, CATU_INADDRHI), NULL, }; @@ -398,31 +389,46 @@ static const struct attribute_group *catu_groups[] = { }; -static inline int catu_wait_for_ready(struct catu_drvdata *drvdata) +static int catu_wait_for_ready(struct catu_drvdata *drvdata) { - return coresight_timeout(drvdata->base, - CATU_STATUS, CATU_STATUS_READY, 1); + struct csdev_access *csa = &drvdata->csdev->access; + + return coresight_timeout(csa, CATU_STATUS, CATU_STATUS_READY, 1); } -static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) +static int catu_enable_hw(struct catu_drvdata *drvdata, enum cs_mode cs_mode, + struct coresight_path *path) { int rc; u32 control, mode; - struct etr_buf *etr_buf = data; + struct etr_buf *etr_buf = NULL; + struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; + struct coresight_device *etrdev; + union coresight_dev_subtype etr_subtype = { + .sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM + }; if (catu_wait_for_ready(drvdata)) - dev_warn(drvdata->dev, "Timeout while waiting for READY\n"); + dev_warn(dev, "Timeout while waiting for READY\n"); control = catu_read_control(drvdata); if (control & BIT(CATU_CONTROL_ENABLE)) { - dev_warn(drvdata->dev, "CATU is already enabled\n"); + dev_warn(dev, "CATU is already enabled\n"); return -EBUSY; } - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) return rc; + etrdev = coresight_find_input_type( + csdev->pdata, CORESIGHT_DEV_TYPE_SINK, etr_subtype); + if (etrdev) { + etr_buf = tmc_etr_get_buffer(etrdev, cs_mode, path); + if (IS_ERR(etr_buf)) + return PTR_ERR(etr_buf); + } control |= BIT(CATU_CONTROL_ENABLE); if (etr_buf && etr_buf->mode == ETR_MODE_CATU) { @@ -441,88 +447,94 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) catu_write_irqen(drvdata, 0); catu_write_mode(drvdata, mode); catu_write_control(drvdata, control); - dev_dbg(drvdata->dev, "Enabled in %s mode\n", + dev_dbg(dev, "Enabled in %s mode\n", (mode == CATU_MODE_PASS_THROUGH) ? "Pass through" : "Translate"); return 0; } -static int catu_enable(struct coresight_device *csdev, void *data) +static int catu_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) { - int rc; + int rc = 0; struct catu_drvdata *catu_drvdata = csdev_to_catu_drvdata(csdev); - CS_UNLOCK(catu_drvdata->base); - rc = catu_enable_hw(catu_drvdata, data); - CS_LOCK(catu_drvdata->base); + guard(raw_spinlock_irqsave)(&catu_drvdata->spinlock); + if (csdev->refcnt == 0) { + CS_UNLOCK(catu_drvdata->base); + rc = catu_enable_hw(catu_drvdata, mode, path); + CS_LOCK(catu_drvdata->base); + } + if (!rc) + csdev->refcnt++; return rc; } static int catu_disable_hw(struct catu_drvdata *drvdata) { int rc = 0; + struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; catu_write_control(drvdata, 0); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); if (catu_wait_for_ready(drvdata)) { - dev_info(drvdata->dev, "Timeout while waiting for READY\n"); + dev_info(dev, "Timeout while waiting for READY\n"); rc = -EAGAIN; } - dev_dbg(drvdata->dev, "Disabled\n"); + dev_dbg(dev, "Disabled\n"); return rc; } -static int catu_disable(struct coresight_device *csdev, void *__unused) +static int catu_disable(struct coresight_device *csdev, struct coresight_path *path) { - int rc; + int rc = 0; struct catu_drvdata *catu_drvdata = csdev_to_catu_drvdata(csdev); - CS_UNLOCK(catu_drvdata->base); - rc = catu_disable_hw(catu_drvdata); - CS_LOCK(catu_drvdata->base); + guard(raw_spinlock_irqsave)(&catu_drvdata->spinlock); + if (--csdev->refcnt == 0) { + CS_UNLOCK(catu_drvdata->base); + rc = catu_disable_hw(catu_drvdata); + CS_LOCK(catu_drvdata->base); + } return rc; } -const struct coresight_ops_helper catu_helper_ops = { +static const struct coresight_ops_helper catu_helper_ops = { .enable = catu_enable, .disable = catu_disable, }; -const struct coresight_ops catu_ops = { +static const struct coresight_ops catu_ops = { .helper_ops = &catu_helper_ops, }; -static int catu_probe(struct amba_device *adev, const struct amba_id *id) +static int __catu_probe(struct device *dev, struct resource *res) { int ret = 0; u32 dma_mask; struct catu_drvdata *drvdata; struct coresight_desc catu_desc; struct coresight_platform_data *pdata = NULL; - struct device *dev = &adev->dev; - struct device_node *np = dev->of_node; void __iomem *base; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) { - ret = PTR_ERR(pdata); - goto out; - } - dev->platform_data = pdata; - } - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) { - ret = -ENOMEM; - goto out; - } + if (!drvdata) + return -ENOMEM; - drvdata->dev = dev; dev_set_drvdata(dev, drvdata); - base = devm_ioremap_resource(dev, &adev->res); + + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + + catu_desc.name = coresight_alloc_device_name(&catu_devs, dev); + if (!catu_desc.name) + return -ENOMEM; + + base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) { ret = PTR_ERR(base); goto out; @@ -547,37 +559,169 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id) if (ret) goto out; + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + goto out; + } + dev->platform_data = pdata; + drvdata->base = base; + raw_spin_lock_init(&drvdata->spinlock); + catu_desc.access = CSDEV_ACCESS_IOMEM(base); catu_desc.pdata = pdata; catu_desc.dev = dev; catu_desc.groups = catu_groups; catu_desc.type = CORESIGHT_DEV_TYPE_HELPER; catu_desc.subtype.helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_CATU; catu_desc.ops = &catu_ops; + + coresight_clear_self_claim_tag(&catu_desc.access); drvdata->csdev = coresight_register(&catu_desc); if (IS_ERR(drvdata->csdev)) ret = PTR_ERR(drvdata->csdev); out: - pm_runtime_put(&adev->dev); return ret; } -static struct amba_id catu_ids[] = { - { - .id = 0x000bb9ee, - .mask = 0x000fffff, - }, +static int catu_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + + ret = __catu_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void __catu_remove(struct device *dev) +{ + struct catu_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); +} + +static void catu_remove(struct amba_device *adev) +{ + __catu_remove(&adev->dev); +} + +static const struct amba_id catu_ids[] = { + CS_AMBA_ID(0x000bb9ee), {}, }; +MODULE_DEVICE_TABLE(amba, catu_ids); + static struct amba_driver catu_driver = { .drv = { .name = "coresight-catu", - .owner = THIS_MODULE, .suppress_bind_attrs = true, }, .probe = catu_probe, + .remove = catu_remove, .id_table = catu_ids, }; -builtin_amba_driver(catu_driver); +static int catu_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret = 0; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = __catu_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void catu_platform_remove(struct platform_device *pdev) +{ + struct catu_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + __catu_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_PM +static int catu_runtime_suspend(struct device *dev) +{ + struct catu_drvdata *drvdata = dev_get_drvdata(dev); + + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); + + return 0; +} + +static int catu_runtime_resume(struct device *dev) +{ + struct catu_drvdata *drvdata = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; + + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; +} +#endif + +static const struct dev_pm_ops catu_dev_pm_ops = { + SET_RUNTIME_PM_OPS(catu_runtime_suspend, catu_runtime_resume, NULL) +}; + +#ifdef CONFIG_ACPI +static const struct acpi_device_id catu_acpi_ids[] = { + {"ARMHC9CA", 0, 0, 0}, /* ARM CoreSight CATU */ + {}, +}; + +MODULE_DEVICE_TABLE(acpi, catu_acpi_ids); +#endif + +static struct platform_driver catu_platform_driver = { + .probe = catu_platform_probe, + .remove = catu_platform_remove, + .driver = { + .name = "coresight-catu-platform", + .acpi_match_table = ACPI_PTR(catu_acpi_ids), + .suppress_bind_attrs = true, + .pm = &catu_dev_pm_ops, + }, +}; + +static int __init catu_init(void) +{ + int ret; + + ret = coresight_init_driver("catu", &catu_driver, &catu_platform_driver, THIS_MODULE); + tmc_etr_set_catu_ops(&etr_catu_buf_ops); + return ret; +} + +static void __exit catu_exit(void) +{ + tmc_etr_remove_catu_ops(); + coresight_remove_driver(&catu_driver, &catu_platform_driver); +} + +module_init(catu_init); +module_exit(catu_exit); + +MODULE_AUTHOR("Suzuki K Poulose <suzuki.poulose@arm.com>"); +MODULE_DESCRIPTION("Arm CoreSight Address Translation Unit (CATU) Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-catu.h b/drivers/hwtracing/coresight/coresight-catu.h index 1b281f0dcccc..6e6b7aac206d 100644 --- a/drivers/hwtracing/coresight/coresight-catu.h +++ b/drivers/hwtracing/coresight/coresight-catu.h @@ -61,34 +61,36 @@ #define CATU_IRQEN_OFF 0x0 struct catu_drvdata { - struct device *dev; + struct clk *pclk; + struct clk *atclk; void __iomem *base; struct coresight_device *csdev; int irq; + raw_spinlock_t spinlock; }; #define CATU_REG32(name, offset) \ static inline u32 \ catu_read_##name(struct catu_drvdata *drvdata) \ { \ - return coresight_read_reg_pair(drvdata->base, offset, -1); \ + return csdev_access_relaxed_read32(&drvdata->csdev->access, offset); \ } \ static inline void \ catu_write_##name(struct catu_drvdata *drvdata, u32 val) \ { \ - coresight_write_reg_pair(drvdata->base, val, offset, -1); \ + csdev_access_relaxed_write32(&drvdata->csdev->access, val, offset); \ } #define CATU_REG_PAIR(name, lo_off, hi_off) \ static inline u64 \ catu_read_##name(struct catu_drvdata *drvdata) \ { \ - return coresight_read_reg_pair(drvdata->base, lo_off, hi_off); \ + return csdev_access_relaxed_read_pair(&drvdata->csdev->access, lo_off, hi_off); \ } \ static inline void \ catu_write_##name(struct catu_drvdata *drvdata, u64 val) \ { \ - coresight_write_reg_pair(drvdata->base, val, lo_off, hi_off); \ + csdev_access_relaxed_write_pair(&drvdata->csdev->access, val, lo_off, hi_off); \ } CATU_REG32(control, CATU_CONTROL); @@ -109,11 +111,4 @@ static inline bool coresight_is_catu_device(struct coresight_device *csdev) return true; } -#ifdef CONFIG_CORESIGHT_CATU -extern const struct etr_buf_operations etr_catu_buf_ops; -#else -/* Dummy declaration for the CATU ops */ -static const struct etr_buf_operations etr_catu_buf_ops; -#endif - #endif diff --git a/drivers/hwtracing/coresight/coresight-cfg-afdo.c b/drivers/hwtracing/coresight/coresight-cfg-afdo.c new file mode 100644 index 000000000000..e794f2e145fa --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-afdo.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2020 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include "coresight-config.h" + +/* ETMv4 includes and features */ +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) +#include "coresight-etm4x-cfg.h" +#include "coresight-cfg-preload.h" + +/* preload configurations and features */ + +/* preload in features for ETMv4 */ + +/* strobe feature */ +static struct cscfg_parameter_desc strobe_params[] = { + { + .name = "window", + .value = 5000, + }, + { + .name = "period", + .value = 10000, + }, +}; + +static struct cscfg_regval_desc strobe_regs[] = { + /* resource selectors */ + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCRSCTLRn(2), + .hw_info = ETM4_CFG_RES_SEL, + .val32 = 0x20001, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCRSCTLRn(3), + .hw_info = ETM4_CFG_RES_SEQ, + .val32 = 0x20002, + }, + /* strobe window counter 0 - reload from param 0 */ + { + .type = CS_CFG_REG_TYPE_RESOURCE | CS_CFG_REG_TYPE_VAL_SAVE, + .offset = TRCCNTVRn(0), + .hw_info = ETM4_CFG_RES_CTR, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE | CS_CFG_REG_TYPE_VAL_PARAM, + .offset = TRCCNTRLDVRn(0), + .hw_info = ETM4_CFG_RES_CTR, + .val32 = 0, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCCNTCTLRn(0), + .hw_info = ETM4_CFG_RES_CTR, + .val32 = 0x10001, + }, + /* strobe period counter 1 - reload from param 1 */ + { + .type = CS_CFG_REG_TYPE_RESOURCE | CS_CFG_REG_TYPE_VAL_SAVE, + .offset = TRCCNTVRn(1), + .hw_info = ETM4_CFG_RES_CTR, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE | CS_CFG_REG_TYPE_VAL_PARAM, + .offset = TRCCNTRLDVRn(1), + .hw_info = ETM4_CFG_RES_CTR, + .val32 = 1, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCCNTCTLRn(1), + .hw_info = ETM4_CFG_RES_CTR, + .val32 = 0x8102, + }, + /* sequencer */ + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCSEQEVRn(0), + .hw_info = ETM4_CFG_RES_SEQ, + .val32 = 0x0081, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCSEQEVRn(1), + .hw_info = ETM4_CFG_RES_SEQ, + .val32 = 0x0000, + }, + /* view-inst */ + { + .type = CS_CFG_REG_TYPE_STD | CS_CFG_REG_TYPE_VAL_MASK, + .offset = TRCVICTLR, + .val32 = 0x0003, + .mask32 = 0x0003, + }, + /* end of regs */ +}; + +struct cscfg_feature_desc strobe_etm4x = { + .name = "strobing", + .description = "Generate periodic trace capture windows.\n" + "parameter \'window\': a number of CPU cycles (W)\n" + "parameter \'period\': trace enabled for W cycles every period x W cycles\n", + .match_flags = CS_CFG_MATCH_CLASS_SRC_ETM4, + .nr_params = ARRAY_SIZE(strobe_params), + .params_desc = strobe_params, + .nr_regs = ARRAY_SIZE(strobe_regs), + .regs_desc = strobe_regs, +}; + +/* create an autofdo configuration */ + +/* we will provide 9 sets of preset parameter values */ +#define AFDO_NR_PRESETS 9 +/* the total number of parameters in used features */ +#define AFDO_NR_PARAMS ARRAY_SIZE(strobe_params) + +static const char *afdo_ref_names[] = { + "strobing", +}; + +/* + * set of presets leaves strobing window constant while varying period to allow + * experimentation with mark / space ratios for various workloads + */ +static u64 afdo_presets[AFDO_NR_PRESETS][AFDO_NR_PARAMS] = { + { 5000, 2 }, + { 5000, 4 }, + { 5000, 8 }, + { 5000, 16 }, + { 5000, 64 }, + { 5000, 128 }, + { 5000, 512 }, + { 5000, 1024 }, + { 5000, 4096 }, +}; + +struct cscfg_config_desc afdo_etm4x = { + .name = "autofdo", + .description = "Setup ETMs with strobing for autofdo\n" + "Supplied presets allow experimentation with mark-space ratio for various loads\n", + .nr_feat_refs = ARRAY_SIZE(afdo_ref_names), + .feat_ref_names = afdo_ref_names, + .nr_presets = AFDO_NR_PRESETS, + .nr_total_params = AFDO_NR_PARAMS, + .presets = &afdo_presets[0][0], +}; + +/* end of ETM4x configurations */ +#endif /* IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) */ diff --git a/drivers/hwtracing/coresight/coresight-cfg-preload.c b/drivers/hwtracing/coresight/coresight-cfg-preload.c new file mode 100644 index 000000000000..4980e68483c5 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-preload.c @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2020 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include "coresight-cfg-preload.h" +#include "coresight-config.h" +#include "coresight-syscfg.h" + +/* Basic features and configurations pre-loaded on initialisation */ + +static struct cscfg_feature_desc *preload_feats[] = { +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) + &strobe_etm4x, + &gen_etrig_etm4x, +#endif + NULL +}; + +static struct cscfg_config_desc *preload_cfgs[] = { +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) + &afdo_etm4x, + &pstop_etm4x, +#endif + NULL +}; + +static struct cscfg_load_owner_info preload_owner = { + .type = CSCFG_OWNER_PRELOAD, +}; + +/* preload called on initialisation */ +int cscfg_preload(void *owner_handle) +{ + preload_owner.owner_handle = owner_handle; + return cscfg_load_config_sets(preload_cfgs, preload_feats, &preload_owner); +} diff --git a/drivers/hwtracing/coresight/coresight-cfg-preload.h b/drivers/hwtracing/coresight/coresight-cfg-preload.h new file mode 100644 index 000000000000..291ba530a6a5 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-preload.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2020 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +/* declare preloaded configurations and features */ + +/* from coresight-cfg-afdo.c - etm 4x features */ +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) +extern struct cscfg_feature_desc strobe_etm4x; +extern struct cscfg_config_desc afdo_etm4x; +extern struct cscfg_feature_desc gen_etrig_etm4x; +extern struct cscfg_config_desc pstop_etm4x; +#endif diff --git a/drivers/hwtracing/coresight/coresight-cfg-pstop.c b/drivers/hwtracing/coresight/coresight-cfg-pstop.c new file mode 100644 index 000000000000..c2bfbd07bfaf --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-pstop.c @@ -0,0 +1,83 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2023 Marvell. + * Based on coresight-cfg-afdo.c + */ + +#include "coresight-config.h" + +/* ETMv4 includes and features */ +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) +#include "coresight-etm4x-cfg.h" + +/* preload configurations and features */ + +/* preload in features for ETMv4 */ + +/* panic_stop feature */ +static struct cscfg_parameter_desc gen_etrig_params[] = { + { + .name = "address", + .value = (u64)panic, + }, +}; + +static struct cscfg_regval_desc gen_etrig_regs[] = { + /* resource selector */ + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCRSCTLRn(2), + .hw_info = ETM4_CFG_RES_SEL, + .val32 = 0x40001, + }, + /* single address comparator */ + { + .type = CS_CFG_REG_TYPE_RESOURCE | CS_CFG_REG_TYPE_VAL_64BIT | + CS_CFG_REG_TYPE_VAL_PARAM, + .offset = TRCACVRn(0), + .val32 = 0x0, + }, + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCACATRn(0), + .val64 = 0xf00, + }, + /* Driver external output[0] with comparator out */ + { + .type = CS_CFG_REG_TYPE_RESOURCE, + .offset = TRCEVENTCTL0R, + .val32 = 0x2, + }, + /* end of regs */ +}; + +struct cscfg_feature_desc gen_etrig_etm4x = { + .name = "gen_etrig", + .description = "Generate external trigger on address match\n" + "parameter \'address\': address of kernel address\n", + .match_flags = CS_CFG_MATCH_CLASS_SRC_ETM4, + .nr_params = ARRAY_SIZE(gen_etrig_params), + .params_desc = gen_etrig_params, + .nr_regs = ARRAY_SIZE(gen_etrig_regs), + .regs_desc = gen_etrig_regs, +}; + +/* create a panic stop configuration */ + +/* the total number of parameters in used features */ +#define PSTOP_NR_PARAMS ARRAY_SIZE(gen_etrig_params) + +static const char *pstop_ref_names[] = { + "gen_etrig", +}; + +struct cscfg_config_desc pstop_etm4x = { + .name = "panicstop", + .description = "Stop ETM on kernel panic\n", + .nr_feat_refs = ARRAY_SIZE(pstop_ref_names), + .feat_ref_names = pstop_ref_names, + .nr_total_params = PSTOP_NR_PARAMS, +}; + +/* end of ETM4x configurations */ +#endif /* IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) */ diff --git a/drivers/hwtracing/coresight/coresight-config.c b/drivers/hwtracing/coresight/coresight-config.c new file mode 100644 index 000000000000..4f72ae71b696 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-config.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2020 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/sysfs.h> +#include "coresight-config.h" +#include "coresight-priv.h" + +/* + * This provides a set of generic functions that operate on configurations + * and features to manage the handling of parameters, the programming and + * saving of registers used by features on devices. + */ + +/* + * Write the value held in the register structure into the driver internal memory + * location. + */ +static void cscfg_set_reg(struct cscfg_regval_csdev *reg_csdev) +{ + u32 *p_val32 = (u32 *)reg_csdev->driver_regval; + u32 tmp32 = reg_csdev->reg_desc.val32; + + if (reg_csdev->reg_desc.type & CS_CFG_REG_TYPE_VAL_64BIT) { + *((u64 *)reg_csdev->driver_regval) = reg_csdev->reg_desc.val64; + return; + } + + if (reg_csdev->reg_desc.type & CS_CFG_REG_TYPE_VAL_MASK) { + tmp32 = *p_val32; + tmp32 &= ~reg_csdev->reg_desc.mask32; + tmp32 |= reg_csdev->reg_desc.val32 & reg_csdev->reg_desc.mask32; + } + *p_val32 = tmp32; +} + +/* + * Read the driver value into the reg if this is marked as one we want to save. + */ +static void cscfg_save_reg(struct cscfg_regval_csdev *reg_csdev) +{ + if (!(reg_csdev->reg_desc.type & CS_CFG_REG_TYPE_VAL_SAVE)) + return; + if (reg_csdev->reg_desc.type & CS_CFG_REG_TYPE_VAL_64BIT) + reg_csdev->reg_desc.val64 = *(u64 *)(reg_csdev->driver_regval); + else + reg_csdev->reg_desc.val32 = *(u32 *)(reg_csdev->driver_regval); +} + +/* + * Some register values are set from parameters. Initialise these registers + * from the current parameter values. + */ +static void cscfg_init_reg_param(struct cscfg_feature_csdev *feat_csdev, + struct cscfg_regval_desc *reg_desc, + struct cscfg_regval_csdev *reg_csdev) +{ + struct cscfg_parameter_csdev *param_csdev; + + /* for param, load routines have validated the index */ + param_csdev = &feat_csdev->params_csdev[reg_desc->param_idx]; + param_csdev->reg_csdev = reg_csdev; + param_csdev->val64 = reg_csdev->reg_desc.type & CS_CFG_REG_TYPE_VAL_64BIT; + + if (param_csdev->val64) + reg_csdev->reg_desc.val64 = param_csdev->current_value; + else + reg_csdev->reg_desc.val32 = (u32)param_csdev->current_value; +} + +/* set values into the driver locations referenced in cscfg_reg_csdev */ +static int cscfg_set_on_enable(struct cscfg_feature_csdev *feat_csdev) +{ + unsigned long flags; + int i; + + raw_spin_lock_irqsave(feat_csdev->drv_spinlock, flags); + for (i = 0; i < feat_csdev->nr_regs; i++) + cscfg_set_reg(&feat_csdev->regs_csdev[i]); + raw_spin_unlock_irqrestore(feat_csdev->drv_spinlock, flags); + dev_dbg(&feat_csdev->csdev->dev, "Feature %s: %s", + feat_csdev->feat_desc->name, "set on enable"); + return 0; +} + +/* copy back values from the driver locations referenced in cscfg_reg_csdev */ +static void cscfg_save_on_disable(struct cscfg_feature_csdev *feat_csdev) +{ + unsigned long flags; + int i; + + raw_spin_lock_irqsave(feat_csdev->drv_spinlock, flags); + for (i = 0; i < feat_csdev->nr_regs; i++) + cscfg_save_reg(&feat_csdev->regs_csdev[i]); + raw_spin_unlock_irqrestore(feat_csdev->drv_spinlock, flags); + dev_dbg(&feat_csdev->csdev->dev, "Feature %s: %s", + feat_csdev->feat_desc->name, "save on disable"); +} + +/* default reset - restore default values */ +void cscfg_reset_feat(struct cscfg_feature_csdev *feat_csdev) +{ + struct cscfg_regval_desc *reg_desc; + struct cscfg_regval_csdev *reg_csdev; + int i; + + /* + * set the default values for all parameters and regs from the + * relevant static descriptors. + */ + for (i = 0; i < feat_csdev->nr_params; i++) + feat_csdev->params_csdev[i].current_value = + feat_csdev->feat_desc->params_desc[i].value; + + for (i = 0; i < feat_csdev->nr_regs; i++) { + reg_desc = &feat_csdev->feat_desc->regs_desc[i]; + reg_csdev = &feat_csdev->regs_csdev[i]; + reg_csdev->reg_desc.type = reg_desc->type; + + /* check if reg set from a parameter otherwise desc default */ + if (reg_desc->type & CS_CFG_REG_TYPE_VAL_PARAM) + cscfg_init_reg_param(feat_csdev, reg_desc, reg_csdev); + else + /* + * for normal values the union between val64 & val32 + mask32 + * allows us to init using the 64 bit value + */ + reg_csdev->reg_desc.val64 = reg_desc->val64; + } +} + +/* + * For the selected presets, we set the register associated with the parameter, to + * the value of the preset index associated with the parameter. + */ +static int cscfg_update_presets(struct cscfg_config_csdev *config_csdev, int preset) +{ + int i, j, val_idx = 0, nr_cfg_params; + struct cscfg_parameter_csdev *param_csdev; + struct cscfg_feature_csdev *feat_csdev; + const struct cscfg_config_desc *config_desc = config_csdev->config_desc; + const char *name; + const u64 *preset_base; + u64 val; + + /* preset in range 1 to nr_presets */ + if (preset < 1 || preset > config_desc->nr_presets) + return -EINVAL; + /* + * Go through the array of features, assigning preset values to + * feature parameters in the order they appear. + * There should be precisely the same number of preset values as the + * sum of number of parameters over all the features - but we will + * ensure there is no overrun. + */ + nr_cfg_params = config_desc->nr_total_params; + preset_base = &config_desc->presets[(preset - 1) * nr_cfg_params]; + for (i = 0; i < config_csdev->nr_feat; i++) { + feat_csdev = config_csdev->feats_csdev[i]; + if (!feat_csdev->nr_params) + continue; + + for (j = 0; j < feat_csdev->nr_params; j++) { + param_csdev = &feat_csdev->params_csdev[j]; + name = feat_csdev->feat_desc->params_desc[j].name; + val = preset_base[val_idx++]; + if (param_csdev->val64) { + dev_dbg(&config_csdev->csdev->dev, + "set param %s (%lld)", name, val); + param_csdev->reg_csdev->reg_desc.val64 = val; + } else { + param_csdev->reg_csdev->reg_desc.val32 = (u32)val; + dev_dbg(&config_csdev->csdev->dev, + "set param %s (%d)", name, (u32)val); + } + } + + /* exit early if all params filled */ + if (val_idx >= nr_cfg_params) + break; + } + return 0; +} + +/* + * if we are not using a preset, then need to update the feature params + * with current values. This sets the register associated with the parameter + * with the current value of that parameter. + */ +static int cscfg_update_curr_params(struct cscfg_config_csdev *config_csdev) +{ + int i, j; + struct cscfg_feature_csdev *feat_csdev; + struct cscfg_parameter_csdev *param_csdev; + const char *name; + u64 val; + + for (i = 0; i < config_csdev->nr_feat; i++) { + feat_csdev = config_csdev->feats_csdev[i]; + if (!feat_csdev->nr_params) + continue; + for (j = 0; j < feat_csdev->nr_params; j++) { + param_csdev = &feat_csdev->params_csdev[j]; + name = feat_csdev->feat_desc->params_desc[j].name; + val = param_csdev->current_value; + if (param_csdev->val64) { + dev_dbg(&config_csdev->csdev->dev, + "set param %s (%lld)", name, val); + param_csdev->reg_csdev->reg_desc.val64 = val; + } else { + param_csdev->reg_csdev->reg_desc.val32 = (u32)val; + dev_dbg(&config_csdev->csdev->dev, + "set param %s (%d)", name, (u32)val); + } + } + } + return 0; +} + +/* + * Configuration values will be programmed into the driver locations if enabling, or read + * from relevant locations on disable. + */ +static int cscfg_prog_config(struct cscfg_config_csdev *config_csdev, bool enable) +{ + int i, err = 0; + struct cscfg_feature_csdev *feat_csdev; + struct coresight_device *csdev; + + for (i = 0; i < config_csdev->nr_feat; i++) { + feat_csdev = config_csdev->feats_csdev[i]; + csdev = feat_csdev->csdev; + dev_dbg(&csdev->dev, "cfg %s; %s feature:%s", config_csdev->config_desc->name, + enable ? "enable" : "disable", feat_csdev->feat_desc->name); + + if (enable) + err = cscfg_set_on_enable(feat_csdev); + else + cscfg_save_on_disable(feat_csdev); + + if (err) + break; + } + return err; +} + +/* + * Enable configuration for the device. Will result in the internal driver data + * being updated ready for programming into the device. + * + * @config_csdev: config_csdev to set. + * @preset: preset values to use - 0 for default. + */ +int cscfg_csdev_enable_config(struct cscfg_config_csdev *config_csdev, int preset) +{ + int err = 0; + + if (preset) + err = cscfg_update_presets(config_csdev, preset); + else + err = cscfg_update_curr_params(config_csdev); + if (!err) + err = cscfg_prog_config(config_csdev, true); + return err; +} + +void cscfg_csdev_disable_config(struct cscfg_config_csdev *config_csdev) +{ + cscfg_prog_config(config_csdev, false); +} diff --git a/drivers/hwtracing/coresight/coresight-config.h b/drivers/hwtracing/coresight/coresight-config.h new file mode 100644 index 000000000000..90fd937d3bd8 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-config.h @@ -0,0 +1,262 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2020 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#ifndef _CORESIGHT_CORESIGHT_CONFIG_H +#define _CORESIGHT_CORESIGHT_CONFIG_H + +#include <linux/coresight.h> +#include <linux/types.h> + +/* CoreSight Configuration Management - component and system wide configuration */ + +/* + * Register type flags for register value descriptor: + * describe how the value is interpreted, and handled. + */ +#define CS_CFG_REG_TYPE_STD 0x80 /* reg is standard reg */ +#define CS_CFG_REG_TYPE_RESOURCE 0x40 /* reg is a resource */ +#define CS_CFG_REG_TYPE_VAL_PARAM 0x08 /* reg value uses param */ +#define CS_CFG_REG_TYPE_VAL_MASK 0x04 /* reg value bit masked */ +#define CS_CFG_REG_TYPE_VAL_64BIT 0x02 /* reg value 64 bit */ +#define CS_CFG_REG_TYPE_VAL_SAVE 0x01 /* reg value save on disable */ + +/* + * flags defining what device class a feature will match to when processing a + * system configuration - used by config data and devices. + */ +#define CS_CFG_MATCH_CLASS_SRC_ALL 0x0001 /* match any source */ +#define CS_CFG_MATCH_CLASS_SRC_ETM4 0x0002 /* match any ETMv4 device */ + +/* flags defining device instance matching - used in config match desc data. */ +#define CS_CFG_MATCH_INST_ANY 0x80000000 /* any instance of a class */ + +/* + * Limit number of presets in a configuration + * This is related to the number of bits (4) we use to select the preset on + * the perf command line. Preset 0 is always none selected. + * See PMU_FORMAT_ATTR(preset, "config:0-3") in coresight-etm-perf.c + */ +#define CS_CFG_CONFIG_PRESET_MAX 15 + +/** + * Parameter descriptor for a device feature. + * + * @name: Name of parameter. + * @value: Initial or default value. + */ +struct cscfg_parameter_desc { + const char *name; + u64 value; +}; + +/** + * Representation of register value and a descriptor of register usage. + * + * Used as a descriptor in the feature descriptors. + * Used as a value in when in a feature loading into a csdev. + * + * Supports full 64 bit register value, or 32 bit value with optional mask + * value. + * + * @type: define register usage and interpretation. + * @offset: the address offset for register in the hardware device (per device specification). + * @hw_info: optional hardware device type specific information. (ETM / CTI specific etc) + * @val64: 64 bit value. + * @val32: 32 bit value. + * @mask32: 32 bit mask when using 32 bit value to access device register - if mask type. + * @param_idx: parameter index value into parameter array if param type. + */ +struct cscfg_regval_desc { + struct { + u32 type:8; + u32 offset:12; + u32 hw_info:12; + }; + union { + u64 val64; + struct { + u32 val32; + u32 mask32; + }; + u32 param_idx; + }; +}; + +/** + * Device feature descriptor - combination of registers and parameters to + * program a device to implement a specific complex function. + * + * @name: feature name. + * @description: brief description of the feature. + * @item: List entry. + * @match_flags: matching information if loading into a device + * @nr_params: number of parameters used. + * @params_desc: array of parameters used. + * @nr_regs: number of registers used. + * @regs_desc: array of registers used. + * @load_owner: handle to load owner for dynamic load and unload of features. + * @fs_group: reference to configfs group for dynamic unload. + */ +struct cscfg_feature_desc { + const char *name; + const char *description; + struct list_head item; + u32 match_flags; + int nr_params; + struct cscfg_parameter_desc *params_desc; + int nr_regs; + struct cscfg_regval_desc *regs_desc; + void *load_owner; + struct config_group *fs_group; +}; + +/** + * Configuration descriptor - describes selectable system configuration. + * + * A configuration describes device features in use, and may provide preset + * values for the parameters in those features. + * + * A single set of presets is the sum of the parameters declared by + * all the features in use - this value is @nr_total_params. + * + * @name: name of the configuration - used for selection. + * @description: description of the purpose of the configuration. + * @item: list entry. + * @nr_feat_refs: Number of features used in this configuration. + * @feat_ref_names: references to features used in this configuration. + * @nr_presets: Number of sets of presets supplied by this configuration. + * @nr_total_params: Sum of all parameters declared by used features + * @presets: Array of preset values. + * @event_ea: Extended attribute for perf event value + * @active_cnt: ref count for activate on this configuration. + * @load_owner: handle to load owner for dynamic load and unload of configs. + * @fs_group: reference to configfs group for dynamic unload. + * @available: config can be activated - multi-stage load sets true on completion. + */ +struct cscfg_config_desc { + const char *name; + const char *description; + struct list_head item; + int nr_feat_refs; + const char **feat_ref_names; + int nr_presets; + int nr_total_params; + const u64 *presets; /* nr_presets * nr_total_params */ + struct dev_ext_attribute *event_ea; + atomic_t active_cnt; + void *load_owner; + struct config_group *fs_group; + bool available; +}; + +/** + * config register instance - part of a loaded feature. + * maps register values to csdev driver structures + * + * @reg_desc: value to use when setting feature on device / store for + * readback of volatile values. + * @driver_regval: pointer to internal driver element used to set the value + * in hardware. + */ +struct cscfg_regval_csdev { + struct cscfg_regval_desc reg_desc; + void *driver_regval; +}; + +/** + * config parameter instance - part of a loaded feature. + * + * @feat_csdev: parent feature + * @reg_csdev: register value updated by this parameter. + * @current_value: current value of parameter - may be set by user via + * sysfs, or modified during device operation. + * @val64: true if 64 bit value + */ +struct cscfg_parameter_csdev { + struct cscfg_feature_csdev *feat_csdev; + struct cscfg_regval_csdev *reg_csdev; + u64 current_value; + bool val64; +}; + +/** + * Feature instance loaded into a CoreSight device. + * + * When a feature is loaded into a specific device, then this structure holds + * the connections between the register / parameter values used and the + * internal data structures that are written when the feature is enabled. + * + * Since applying a feature modifies internal data structures in the device, + * then we have a reference to the device spinlock to protect access to these + * structures (@drv_spinlock). + * + * @feat_desc: pointer to the static descriptor for this feature. + * @csdev: parent CoreSight device instance. + * @node: list entry into feature list for this device. + * @drv_spinlock: device spinlock for access to driver register data. + * @nr_params: number of parameters. + * @params_csdev: current parameter values on this device + * @nr_regs: number of registers to be programmed. + * @regs_csdev: Programming details for the registers + */ +struct cscfg_feature_csdev { + const struct cscfg_feature_desc *feat_desc; + struct coresight_device *csdev; + struct list_head node; + raw_spinlock_t *drv_spinlock; + int nr_params; + struct cscfg_parameter_csdev *params_csdev; + int nr_regs; + struct cscfg_regval_csdev *regs_csdev; +}; + +/** + * Configuration instance when loaded into a CoreSight device. + * + * The instance contains references to loaded features on this device that are + * used by the configuration. + * + * @config_desc:reference to the descriptor for this configuration + * @csdev: parent coresight device for this configuration instance. + * @enabled: true if configuration is enabled on this device. + * @node: list entry within the coresight device + * @nr_feat: Number of features on this device that are used in the + * configuration. + * @feats_csdev:references to the device features to enable. + */ +struct cscfg_config_csdev { + struct cscfg_config_desc *config_desc; + struct coresight_device *csdev; + bool enabled; + struct list_head node; + int nr_feat; + struct cscfg_feature_csdev *feats_csdev[]; +}; + +/** + * Coresight device operations. + * + * Registered coresight devices provide these operations to manage feature + * instances compatible with the device hardware and drivers + * + * @load_feat: Pass a feature descriptor into the device and create the + * loaded feature instance (struct cscfg_feature_csdev). + */ +struct cscfg_csdev_feat_ops { + int (*load_feat)(struct coresight_device *csdev, + struct cscfg_feature_csdev *feat_csdev); +}; + +/* coresight config helper functions*/ + +/* enable / disable config on a device - called with appropriate locks set.*/ +int cscfg_csdev_enable_config(struct cscfg_config_csdev *config_csdev, int preset); +void cscfg_csdev_disable_config(struct cscfg_config_csdev *config_csdev); + +/* reset a feature to default values */ +void cscfg_reset_feat(struct cscfg_feature_csdev *feat_csdev); + +#endif /* _CORESIGHT_CORESIGHT_CONFIG_H */ diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c new file mode 100644 index 000000000000..c660cf8adb1c --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -0,0 +1,1758 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2012, The Linux Foundation. All rights reserved. + */ + +#include <linux/acpi.h> +#include <linux/bitfield.h> +#include <linux/build_bug.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/stringhash.h> +#include <linux/mutex.h> +#include <linux/clk.h> +#include <linux/coresight.h> +#include <linux/property.h> +#include <linux/delay.h> +#include <linux/pm_runtime.h> +#include <linux/panic_notifier.h> + +#include "coresight-etm-perf.h" +#include "coresight-priv.h" +#include "coresight-syscfg.h" +#include "coresight-trace-id.h" + +/* + * Mutex used to lock all sysfs enable and disable actions and loading and + * unloading devices by the Coresight core. + */ +DEFINE_MUTEX(coresight_mutex); +static DEFINE_PER_CPU(struct coresight_device *, csdev_sink); + +/** + * struct coresight_node - elements of a path, from source to sink + * @csdev: Address of an element. + * @link: hook to the list. + */ +struct coresight_node { + struct coresight_device *csdev; + struct list_head link; +}; + +/* + * When losing synchronisation a new barrier packet needs to be inserted at the + * beginning of the data collected in a buffer. That way the decoder knows that + * it needs to look for another sync sequence. + */ +const u32 coresight_barrier_pkt[4] = {0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff}; +EXPORT_SYMBOL_GPL(coresight_barrier_pkt); + +static const struct cti_assoc_op *cti_assoc_ops; + +void coresight_set_cti_ops(const struct cti_assoc_op *cti_op) +{ + cti_assoc_ops = cti_op; +} +EXPORT_SYMBOL_GPL(coresight_set_cti_ops); + +void coresight_remove_cti_ops(void) +{ + cti_assoc_ops = NULL; +} +EXPORT_SYMBOL_GPL(coresight_remove_cti_ops); + +void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev) +{ + per_cpu(csdev_sink, cpu) = csdev; +} +EXPORT_SYMBOL_GPL(coresight_set_percpu_sink); + +struct coresight_device *coresight_get_percpu_sink(int cpu) +{ + return per_cpu(csdev_sink, cpu); +} +EXPORT_SYMBOL_GPL(coresight_get_percpu_sink); + +static struct coresight_device *coresight_get_source(struct coresight_path *path) +{ + struct coresight_device *csdev; + + if (!path) + return NULL; + + csdev = list_first_entry(&path->path_list, struct coresight_node, link)->csdev; + if (!coresight_is_device_source(csdev)) + return NULL; + + return csdev; +} + +/** + * coresight_blocks_source - checks whether the connection matches the source + * of path if connection is bound to specific source. + * @src: The source device of the trace path + * @conn: The connection of one outport + * + * Return false if the connection doesn't have a source binded or source of the + * path matches the source binds to connection. + */ +static bool coresight_blocks_source(struct coresight_device *src, + struct coresight_connection *conn) +{ + return conn->filter_src_fwnode && (conn->filter_src_dev != src); +} + +static struct coresight_connection * +coresight_find_out_connection(struct coresight_device *csdev, + struct coresight_device *out_dev, + struct coresight_device *trace_src) +{ + int i; + struct coresight_connection *conn; + + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + conn = csdev->pdata->out_conns[i]; + if (coresight_blocks_source(trace_src, conn)) + continue; + if (conn->dest_dev == out_dev) + return conn; + } + + dev_err(&csdev->dev, + "couldn't find output connection, csdev: %s, out_dev: %s\n", + dev_name(&csdev->dev), dev_name(&out_dev->dev)); + + return ERR_PTR(-ENODEV); +} + +static u32 coresight_read_claim_tags_unlocked(struct coresight_device *csdev) +{ + return FIELD_GET(CORESIGHT_CLAIM_MASK, + csdev_access_relaxed_read32(&csdev->access, CORESIGHT_CLAIMCLR)); +} + +static void coresight_set_self_claim_tag_unlocked(struct coresight_device *csdev) +{ + csdev_access_relaxed_write32(&csdev->access, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMSET); + isb(); +} + +void coresight_clear_self_claim_tag(struct csdev_access *csa) +{ + if (csa->io_mem) + CS_UNLOCK(csa->base); + coresight_clear_self_claim_tag_unlocked(csa); + if (csa->io_mem) + CS_LOCK(csa->base); +} +EXPORT_SYMBOL_GPL(coresight_clear_self_claim_tag); + +void coresight_clear_self_claim_tag_unlocked(struct csdev_access *csa) +{ + csdev_access_relaxed_write32(csa, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMCLR); + isb(); +} +EXPORT_SYMBOL_GPL(coresight_clear_self_claim_tag_unlocked); + +/* + * coresight_claim_device_unlocked : Claim the device for self-hosted usage + * to prevent an external tool from touching this device. As per PSCI + * standards, section "Preserving the execution context" => "Debug and Trace + * save and Restore", DBGCLAIM[1] is reserved for Self-hosted debug/trace and + * DBGCLAIM[0] is reserved for external tools. + * + * Called with CS_UNLOCKed for the component. + * Returns : 0 on success + */ +int coresight_claim_device_unlocked(struct coresight_device *csdev) +{ + int tag; + struct csdev_access *csa; + + if (WARN_ON(!csdev)) + return -EINVAL; + + csa = &csdev->access; + tag = coresight_read_claim_tags_unlocked(csdev); + + switch (tag) { + case CORESIGHT_CLAIM_FREE: + coresight_set_self_claim_tag_unlocked(csdev); + if (coresight_read_claim_tags_unlocked(csdev) == CORESIGHT_CLAIM_SELF_HOSTED) + return 0; + + /* There was a race setting the tag, clean up and fail */ + coresight_clear_self_claim_tag_unlocked(csa); + dev_dbg(&csdev->dev, "Busy: Couldn't set self claim tag"); + return -EBUSY; + + case CORESIGHT_CLAIM_EXTERNAL: + /* External debug is an expected state, so log and report BUSY */ + dev_dbg(&csdev->dev, "Busy: Claimed by external debugger"); + return -EBUSY; + + default: + case CORESIGHT_CLAIM_SELF_HOSTED: + case CORESIGHT_CLAIM_INVALID: + /* + * Warn here because we clear a lingering self hosted tag + * on probe, so other tag combinations are impossible. + */ + dev_err_once(&csdev->dev, "Invalid claim tag state: %x", tag); + return -EBUSY; + } +} +EXPORT_SYMBOL_GPL(coresight_claim_device_unlocked); + +int coresight_claim_device(struct coresight_device *csdev) +{ + int rc; + + if (WARN_ON(!csdev)) + return -EINVAL; + + CS_UNLOCK(csdev->access.base); + rc = coresight_claim_device_unlocked(csdev); + CS_LOCK(csdev->access.base); + + return rc; +} +EXPORT_SYMBOL_GPL(coresight_claim_device); + +/* + * coresight_disclaim_device_unlocked : Clear the claim tag for the device. + * Called with CS_UNLOCKed for the component. + */ +void coresight_disclaim_device_unlocked(struct coresight_device *csdev) +{ + + if (WARN_ON(!csdev)) + return; + + if (coresight_read_claim_tags_unlocked(csdev) == CORESIGHT_CLAIM_SELF_HOSTED) + coresight_clear_self_claim_tag_unlocked(&csdev->access); + else + /* + * The external agent may have not honoured our claim + * and has manipulated it. Or something else has seriously + * gone wrong in our driver. + */ + dev_WARN_ONCE(&csdev->dev, 1, "External agent took claim tag"); +} +EXPORT_SYMBOL_GPL(coresight_disclaim_device_unlocked); + +void coresight_disclaim_device(struct coresight_device *csdev) +{ + if (WARN_ON(!csdev)) + return; + + CS_UNLOCK(csdev->access.base); + coresight_disclaim_device_unlocked(csdev); + CS_LOCK(csdev->access.base); +} +EXPORT_SYMBOL_GPL(coresight_disclaim_device); + +/* + * Add a helper as an output device. This function takes the @coresight_mutex + * because it's assumed that it's called from the helper device, outside of the + * core code where the mutex would already be held. Don't add new calls to this + * from inside the core code, instead try to add the new helper to the DT and + * ACPI where it will be picked up and linked automatically. + */ +void coresight_add_helper(struct coresight_device *csdev, + struct coresight_device *helper) +{ + int i; + struct coresight_connection conn = {}; + struct coresight_connection *new_conn; + + mutex_lock(&coresight_mutex); + conn.dest_fwnode = fwnode_handle_get(dev_fwnode(&helper->dev)); + conn.dest_dev = helper; + conn.dest_port = conn.src_port = -1; + conn.src_dev = csdev; + + /* + * Check for duplicates because this is called every time a helper + * device is re-loaded. Existing connections will get re-linked + * automatically. + */ + for (i = 0; i < csdev->pdata->nr_outconns; ++i) + if (csdev->pdata->out_conns[i]->dest_fwnode == conn.dest_fwnode) + goto unlock; + + new_conn = coresight_add_out_conn(csdev->dev.parent, csdev->pdata, + &conn); + if (!IS_ERR(new_conn)) + coresight_add_in_conn(new_conn); + +unlock: + mutex_unlock(&coresight_mutex); +} +EXPORT_SYMBOL_GPL(coresight_add_helper); + +static int coresight_enable_sink(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path) +{ + return sink_ops(csdev)->enable(csdev, mode, path); +} + +static void coresight_disable_sink(struct coresight_device *csdev) +{ + sink_ops(csdev)->disable(csdev); +} + +static int coresight_enable_link(struct coresight_device *csdev, + struct coresight_device *parent, + struct coresight_device *child, + struct coresight_device *source) +{ + int link_subtype; + struct coresight_connection *inconn, *outconn; + + if (!parent || !child) + return -EINVAL; + + inconn = coresight_find_out_connection(parent, csdev, source); + outconn = coresight_find_out_connection(csdev, child, source); + link_subtype = csdev->subtype.link_subtype; + + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG && IS_ERR(inconn)) + return PTR_ERR(inconn); + if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT && IS_ERR(outconn)) + return PTR_ERR(outconn); + + return link_ops(csdev)->enable(csdev, inconn, outconn); +} + +static void coresight_disable_link(struct coresight_device *csdev, + struct coresight_device *parent, + struct coresight_device *child, + struct coresight_device *source) +{ + struct coresight_connection *inconn, *outconn; + + if (!parent || !child) + return; + + inconn = coresight_find_out_connection(parent, csdev, source); + outconn = coresight_find_out_connection(csdev, child, source); + + link_ops(csdev)->disable(csdev, inconn, outconn); +} + +static bool coresight_is_helper(struct coresight_device *csdev) +{ + return csdev->type == CORESIGHT_DEV_TYPE_HELPER; +} + +static int coresight_enable_helper(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path) +{ + return helper_ops(csdev)->enable(csdev, mode, path); +} + +static void coresight_disable_helper(struct coresight_device *csdev, + struct coresight_path *path) +{ + helper_ops(csdev)->disable(csdev, path); +} + +static void coresight_disable_helpers(struct coresight_device *csdev, + struct coresight_path *path) +{ + int i; + struct coresight_device *helper; + + for (i = 0; i < csdev->pdata->nr_outconns; ++i) { + helper = csdev->pdata->out_conns[i]->dest_dev; + if (helper && coresight_is_helper(helper)) + coresight_disable_helper(helper, path); + } +} + +/* + * Helper function to call source_ops(csdev)->disable and also disable the + * helpers. + * + * There is an imbalance between coresight_enable_path() and + * coresight_disable_path(). Enabling also enables the source's helpers as part + * of the path, but disabling always skips the first item in the path (which is + * the source), so sources and their helpers don't get disabled as part of that + * function and we need the extra step here. + */ +void coresight_disable_source(struct coresight_device *csdev, void *data) +{ + source_ops(csdev)->disable(csdev, data); + coresight_disable_helpers(csdev, NULL); +} +EXPORT_SYMBOL_GPL(coresight_disable_source); + +void coresight_pause_source(struct coresight_device *csdev) +{ + if (!coresight_is_percpu_source(csdev)) + return; + + if (source_ops(csdev)->pause_perf) + source_ops(csdev)->pause_perf(csdev); +} +EXPORT_SYMBOL_GPL(coresight_pause_source); + +int coresight_resume_source(struct coresight_device *csdev) +{ + if (!coresight_is_percpu_source(csdev)) + return -EOPNOTSUPP; + + if (!source_ops(csdev)->resume_perf) + return -EOPNOTSUPP; + + return source_ops(csdev)->resume_perf(csdev); +} +EXPORT_SYMBOL_GPL(coresight_resume_source); + +/* + * coresight_disable_path_from : Disable components in the given path beyond + * @nd in the list. If @nd is NULL, all the components, except the SOURCE are + * disabled. + */ +static void coresight_disable_path_from(struct coresight_path *path, + struct coresight_node *nd) +{ + u32 type; + struct coresight_device *csdev, *parent, *child; + + if (!nd) + nd = list_first_entry(&path->path_list, struct coresight_node, link); + + list_for_each_entry_continue(nd, &path->path_list, link) { + csdev = nd->csdev; + type = csdev->type; + + /* + * ETF devices are tricky... They can be a link or a sink, + * depending on how they are configured. If an ETF has been + * selected as a sink it will be configured as a sink, otherwise + * go ahead with the link configuration. + */ + if (type == CORESIGHT_DEV_TYPE_LINKSINK) + type = (csdev == coresight_get_sink(path)) ? + CORESIGHT_DEV_TYPE_SINK : + CORESIGHT_DEV_TYPE_LINK; + + switch (type) { + case CORESIGHT_DEV_TYPE_SINK: + coresight_disable_sink(csdev); + break; + case CORESIGHT_DEV_TYPE_SOURCE: + /* + * We skip the first node in the path assuming that it + * is the source. So we don't expect a source device in + * the middle of a path. + */ + WARN_ON(1); + break; + case CORESIGHT_DEV_TYPE_LINK: + parent = list_prev_entry(nd, link)->csdev; + child = list_next_entry(nd, link)->csdev; + coresight_disable_link(csdev, parent, child, + coresight_get_source(path)); + break; + default: + break; + } + + /* Disable all helpers adjacent along the path last */ + coresight_disable_helpers(csdev, path); + } +} + +void coresight_disable_path(struct coresight_path *path) +{ + coresight_disable_path_from(path, NULL); +} +EXPORT_SYMBOL_GPL(coresight_disable_path); + +static int coresight_enable_helpers(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path) +{ + int i, ret = 0; + struct coresight_device *helper; + + for (i = 0; i < csdev->pdata->nr_outconns; ++i) { + helper = csdev->pdata->out_conns[i]->dest_dev; + if (!helper || !coresight_is_helper(helper)) + continue; + + ret = coresight_enable_helper(helper, mode, path); + if (ret) + return ret; + } + + return 0; +} + +int coresight_enable_path(struct coresight_path *path, enum cs_mode mode) +{ + int ret = 0; + u32 type; + struct coresight_node *nd; + struct coresight_device *csdev, *parent, *child; + struct coresight_device *source; + + source = coresight_get_source(path); + list_for_each_entry_reverse(nd, &path->path_list, link) { + csdev = nd->csdev; + type = csdev->type; + + /* Enable all helpers adjacent to the path first */ + ret = coresight_enable_helpers(csdev, mode, path); + if (ret) + goto err_disable_path; + /* + * ETF devices are tricky... They can be a link or a sink, + * depending on how they are configured. If an ETF has been + * selected as a sink it will be configured as a sink, otherwise + * go ahead with the link configuration. + */ + if (type == CORESIGHT_DEV_TYPE_LINKSINK) + type = (csdev == coresight_get_sink(path)) ? + CORESIGHT_DEV_TYPE_SINK : + CORESIGHT_DEV_TYPE_LINK; + + switch (type) { + case CORESIGHT_DEV_TYPE_SINK: + ret = coresight_enable_sink(csdev, mode, path); + /* + * Sink is the first component turned on. If we + * failed to enable the sink, there are no components + * that need disabling. Disabling the path here + * would mean we could disrupt an existing session. + */ + if (ret) { + coresight_disable_helpers(csdev, path); + goto out; + } + break; + case CORESIGHT_DEV_TYPE_SOURCE: + /* sources are enabled from either sysFS or Perf */ + break; + case CORESIGHT_DEV_TYPE_LINK: + parent = list_prev_entry(nd, link)->csdev; + child = list_next_entry(nd, link)->csdev; + ret = coresight_enable_link(csdev, parent, child, source); + if (ret) + goto err_disable_helpers; + break; + default: + ret = -EINVAL; + goto err_disable_helpers; + } + } + +out: + return ret; +err_disable_helpers: + coresight_disable_helpers(csdev, path); +err_disable_path: + coresight_disable_path_from(path, nd); + goto out; +} + +struct coresight_device *coresight_get_sink(struct coresight_path *path) +{ + struct coresight_device *csdev; + + if (!path) + return NULL; + + csdev = list_last_entry(&path->path_list, struct coresight_node, link)->csdev; + if (csdev->type != CORESIGHT_DEV_TYPE_SINK && + csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) + return NULL; + + return csdev; +} +EXPORT_SYMBOL_GPL(coresight_get_sink); + +u32 coresight_get_sink_id(struct coresight_device *csdev) +{ + if (!csdev->ea) + return 0; + + /* + * See function etm_perf_add_symlink_sink() to know where + * this comes from. + */ + return (u32) (unsigned long) csdev->ea->var; +} + +static int coresight_sink_by_id(struct device *dev, const void *data) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + if (csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + if (coresight_get_sink_id(csdev) == *(u32 *)data) + return 1; + } + + return 0; +} + +/** + * coresight_get_sink_by_id - returns the sink that matches the id + * @id: Id of the sink to match + * + * The name of a sink is unique, whether it is found on the AMBA bus or + * otherwise. As such the hash of that name can easily be used to identify + * a sink. + */ +struct coresight_device *coresight_get_sink_by_id(u32 id) +{ + struct device *dev = NULL; + + dev = bus_find_device(&coresight_bustype, NULL, &id, + coresight_sink_by_id); + + return dev ? to_coresight_device(dev) : NULL; +} + +/** + * coresight_get_ref- Helper function to increase reference count to module + * and device. + * + * @csdev: The coresight device to get a reference on. + * + * Return true in successful case and power up the device. + * Return false when failed to get reference of module. + */ +static bool coresight_get_ref(struct coresight_device *csdev) +{ + struct device *dev = csdev->dev.parent; + + /* Make sure the driver can't be removed */ + if (!try_module_get(dev->driver->owner)) + return false; + /* Make sure the device can't go away */ + get_device(dev); + pm_runtime_get_sync(dev); + return true; +} + +/** + * coresight_put_ref- Helper function to decrease reference count to module + * and device. Power off the device. + * + * @csdev: The coresight device to decrement a reference from. + */ +static void coresight_put_ref(struct coresight_device *csdev) +{ + struct device *dev = csdev->dev.parent; + + pm_runtime_put(dev); + put_device(dev); + module_put(dev->driver->owner); +} + +/* + * coresight_grab_device - Power up this device and any of the helper + * devices connected to it for trace operation. Since the helper devices + * don't appear on the trace path, they should be handled along with the + * master device. + */ +static int coresight_grab_device(struct coresight_device *csdev) +{ + int i; + + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + struct coresight_device *child; + + child = csdev->pdata->out_conns[i]->dest_dev; + if (child && coresight_is_helper(child)) + if (!coresight_get_ref(child)) + goto err; + } + if (coresight_get_ref(csdev)) + return 0; +err: + for (i--; i >= 0; i--) { + struct coresight_device *child; + + child = csdev->pdata->out_conns[i]->dest_dev; + if (child && coresight_is_helper(child)) + coresight_put_ref(child); + } + return -ENODEV; +} + +/* + * coresight_drop_device - Release this device and any of the helper + * devices connected to it. + */ +static void coresight_drop_device(struct coresight_device *csdev) +{ + int i; + + coresight_put_ref(csdev); + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + struct coresight_device *child; + + child = csdev->pdata->out_conns[i]->dest_dev; + if (child && coresight_is_helper(child)) + coresight_put_ref(child); + } +} + +/* + * coresight device will read their existing or alloc a trace ID, if their trace_id + * callback is set. + * + * Return 0 if the trace_id callback is not set. + * Return the result of the trace_id callback if it is set. The return value + * will be the trace_id if successful, and an error number if it fails. + */ +static int coresight_get_trace_id(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_device *sink) +{ + if (coresight_ops(csdev)->trace_id) + return coresight_ops(csdev)->trace_id(csdev, mode, sink); + + return 0; +} + +/* + * Call this after creating the path and before enabling it. This leaves + * the trace ID set on the path, or it remains 0 if it couldn't be assigned. + */ +void coresight_path_assign_trace_id(struct coresight_path *path, + enum cs_mode mode) +{ + struct coresight_device *sink = coresight_get_sink(path); + struct coresight_node *nd; + int trace_id; + + list_for_each_entry(nd, &path->path_list, link) { + /* Assign a trace ID to the path for the first device that wants to do it */ + trace_id = coresight_get_trace_id(nd->csdev, mode, sink); + + /* + * 0 in this context is that it didn't want to assign so keep searching. + * Non 0 is either success or fail. + */ + if (trace_id != 0) { + path->trace_id = trace_id; + return; + } + } +} + +/** + * _coresight_build_path - recursively build a path from a @csdev to a sink. + * @csdev: The device to start from. + * @source: The trace source device of the path. + * @sink: The final sink we want in this path. + * @path: The list to add devices to. + * + * The tree of Coresight device is traversed until @sink is found. + * From there the sink is added to the list along with all the devices that led + * to that point - the end result is a list from source to sink. In that list + * the source is the first device and the sink the last one. + */ +static int _coresight_build_path(struct coresight_device *csdev, + struct coresight_device *source, + struct coresight_device *sink, + struct coresight_path *path) +{ + int i, ret; + bool found = false; + struct coresight_node *node; + + /* The sink has been found. Enqueue the element */ + if (csdev == sink) + goto out; + + if (coresight_is_percpu_source(csdev) && coresight_is_percpu_sink(sink) && + sink == per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev))) { + if (_coresight_build_path(sink, source, sink, path) == 0) { + found = true; + goto out; + } + } + + /* Not a sink - recursively explore each port found on this element */ + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + struct coresight_device *child_dev; + + child_dev = csdev->pdata->out_conns[i]->dest_dev; + + if (coresight_blocks_source(source, csdev->pdata->out_conns[i])) + continue; + + if (child_dev && + _coresight_build_path(child_dev, source, sink, path) == 0) { + found = true; + break; + } + } + + if (!found) + return -ENODEV; + +out: + /* + * A path from this element to a sink has been found. The elements + * leading to the sink are already enqueued, all that is left to do + * is tell the PM runtime core we need this element and add a node + * for it. + */ + ret = coresight_grab_device(csdev); + if (ret) + return ret; + + node = kzalloc(sizeof(struct coresight_node), GFP_KERNEL); + if (!node) + return -ENOMEM; + + node->csdev = csdev; + list_add(&node->link, &path->path_list); + + return 0; +} + +struct coresight_path *coresight_build_path(struct coresight_device *source, + struct coresight_device *sink) +{ + struct coresight_path *path; + int rc; + + if (!sink) + return ERR_PTR(-EINVAL); + + path = kzalloc(sizeof(struct coresight_path), GFP_KERNEL); + if (!path) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&path->path_list); + + rc = _coresight_build_path(source, source, sink, path); + if (rc) { + kfree(path); + return ERR_PTR(rc); + } + + return path; +} + +/** + * coresight_release_path - release a previously built path. + * @path: the path to release. + * + * Go through all the elements of a path and 1) removed it from the list and + * 2) free the memory allocated for each node. + */ +void coresight_release_path(struct coresight_path *path) +{ + struct coresight_device *csdev; + struct coresight_node *nd, *next; + + list_for_each_entry_safe(nd, next, &path->path_list, link) { + csdev = nd->csdev; + + coresight_drop_device(csdev); + list_del(&nd->link); + kfree(nd); + } + + kfree(path); +} + +/* return true if the device is a suitable type for a default sink */ +static bool coresight_is_def_sink_type(struct coresight_device *csdev) +{ + /* sink & correct subtype */ + if (((csdev->type == CORESIGHT_DEV_TYPE_SINK) || + (csdev->type == CORESIGHT_DEV_TYPE_LINKSINK)) && + (csdev->subtype.sink_subtype >= CORESIGHT_DEV_SUBTYPE_SINK_BUFFER)) + return true; + return false; +} + +/** + * coresight_select_best_sink - return the best sink for use as default from + * the two provided. + * + * @sink: current best sink. + * @depth: search depth where current sink was found. + * @new_sink: new sink for comparison with current sink. + * @new_depth: search depth where new sink was found. + * + * Sinks prioritised according to coresight_dev_subtype_sink, with only + * subtypes CORESIGHT_DEV_SUBTYPE_SINK_BUFFER or higher being used. + * + * Where two sinks of equal priority are found, the sink closest to the + * source is used (smallest search depth). + * + * return @new_sink & update @depth if better than @sink, else return @sink. + */ +static struct coresight_device * +coresight_select_best_sink(struct coresight_device *sink, int *depth, + struct coresight_device *new_sink, int new_depth) +{ + bool update = false; + + if (!sink) { + /* first found at this level */ + update = true; + } else if (new_sink->subtype.sink_subtype > + sink->subtype.sink_subtype) { + /* found better sink */ + update = true; + } else if ((new_sink->subtype.sink_subtype == + sink->subtype.sink_subtype) && + (*depth > new_depth)) { + /* found same but closer sink */ + update = true; + } + + if (update) + *depth = new_depth; + return update ? new_sink : sink; +} + +/** + * coresight_find_sink - recursive function to walk trace connections from + * source to find a suitable default sink. + * + * @csdev: source / current device to check. + * @depth: [in] search depth of calling dev, [out] depth of found sink. + * + * This will walk the connection path from a source (ETM) till a suitable + * sink is encountered and return that sink to the original caller. + * + * If current device is a plain sink return that & depth, otherwise recursively + * call child connections looking for a sink. Select best possible using + * coresight_select_best_sink. + * + * return best sink found, or NULL if not found at this node or child nodes. + */ +static struct coresight_device * +coresight_find_sink(struct coresight_device *csdev, int *depth) +{ + int i, curr_depth = *depth + 1, found_depth = 0; + struct coresight_device *found_sink = NULL; + + if (coresight_is_def_sink_type(csdev)) { + found_depth = curr_depth; + found_sink = csdev; + if (csdev->type == CORESIGHT_DEV_TYPE_SINK) + goto return_def_sink; + /* look past LINKSINK for something better */ + } + + /* + * Not a sink we want - or possible child sink may be better. + * recursively explore each port found on this element. + */ + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + struct coresight_device *child_dev, *sink = NULL; + int child_depth = curr_depth; + + child_dev = csdev->pdata->out_conns[i]->dest_dev; + if (child_dev) + sink = coresight_find_sink(child_dev, &child_depth); + + if (sink) + found_sink = coresight_select_best_sink(found_sink, + &found_depth, + sink, + child_depth); + } + +return_def_sink: + /* return found sink and depth */ + if (found_sink) + *depth = found_depth; + return found_sink; +} + +/** + * coresight_find_default_sink: Find a sink suitable for use as a + * default sink. + * + * @csdev: starting source to find a connected sink. + * + * Walks connections graph looking for a suitable sink to enable for the + * supplied source. Uses CoreSight device subtypes and distance from source + * to select the best sink. + * + * If a sink is found, then the default sink for this device is set and + * will be automatically used in future. + * + * Used in cases where the CoreSight user (perf / sysfs) has not selected a + * sink. + */ +struct coresight_device * +coresight_find_default_sink(struct coresight_device *csdev) +{ + int depth = 0; + + /* look for a default sink if we have not found for this device */ + if (!csdev->def_sink) { + if (coresight_is_percpu_source(csdev)) + csdev->def_sink = per_cpu(csdev_sink, source_ops(csdev)->cpu_id(csdev)); + if (!csdev->def_sink) + csdev->def_sink = coresight_find_sink(csdev, &depth); + } + return csdev->def_sink; +} +EXPORT_SYMBOL_GPL(coresight_find_default_sink); + +static int coresight_remove_sink_ref(struct device *dev, void *data) +{ + struct coresight_device *sink = data; + struct coresight_device *source = to_coresight_device(dev); + + if (source->def_sink == sink) + source->def_sink = NULL; + return 0; +} + +/** + * coresight_clear_default_sink: Remove all default sink references to the + * supplied sink. + * + * If supplied device is a sink, then check all the bus devices and clear + * out all the references to this sink from the coresight_device def_sink + * parameter. + * + * @csdev: coresight sink - remove references to this from all sources. + */ +static void coresight_clear_default_sink(struct coresight_device *csdev) +{ + if ((csdev->type == CORESIGHT_DEV_TYPE_SINK) || + (csdev->type == CORESIGHT_DEV_TYPE_LINKSINK)) { + bus_for_each_dev(&coresight_bustype, NULL, csdev, + coresight_remove_sink_ref); + } +} + +static void coresight_device_release(struct device *dev) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + fwnode_handle_put(csdev->dev.fwnode); + free_percpu(csdev->perf_sink_id_map.cpu_map); + kfree(csdev); +} + +static int coresight_orphan_match(struct device *dev, void *data) +{ + int i, ret = 0; + bool still_orphan = false; + struct coresight_device *dst_csdev = data; + struct coresight_device *src_csdev = to_coresight_device(dev); + struct coresight_connection *conn; + bool fixup_self = (src_csdev == dst_csdev); + + /* Move on to another component if no connection is orphan */ + if (!src_csdev->orphan) + return 0; + /* + * Circle through all the connections of that component. If we find + * an orphan connection whose name matches @dst_csdev, link it. + */ + for (i = 0; i < src_csdev->pdata->nr_outconns; i++) { + conn = src_csdev->pdata->out_conns[i]; + + /* Fix filter source device before skip the port */ + if (conn->filter_src_fwnode && !conn->filter_src_dev) { + if (dst_csdev && + (conn->filter_src_fwnode == dst_csdev->dev.fwnode) && + !WARN_ON_ONCE(!coresight_is_device_source(dst_csdev))) + conn->filter_src_dev = dst_csdev; + else + still_orphan = true; + } + + /* Skip the port if it's already connected. */ + if (conn->dest_dev) + continue; + + /* + * If we are at the "new" device, which triggered this search, + * we must find the remote device from the fwnode in the + * connection. + */ + if (fixup_self) + dst_csdev = coresight_find_csdev_by_fwnode( + conn->dest_fwnode); + + /* Does it match this newly added device? */ + if (dst_csdev && conn->dest_fwnode == dst_csdev->dev.fwnode) { + ret = coresight_make_links(src_csdev, conn, dst_csdev); + if (ret) + return ret; + + /* + * Install the device connection. This also indicates that + * the links are operational on both ends. + */ + conn->dest_dev = dst_csdev; + conn->src_dev = src_csdev; + + ret = coresight_add_in_conn(conn); + if (ret) + return ret; + } else { + /* This component still has an orphan */ + still_orphan = true; + } + } + + src_csdev->orphan = still_orphan; + + /* + * Returning '0' in case we didn't encounter any error, + * ensures that all known component on the bus will be checked. + */ + return 0; +} + +static int coresight_fixup_orphan_conns(struct coresight_device *csdev) +{ + return bus_for_each_dev(&coresight_bustype, NULL, + csdev, coresight_orphan_match); +} + +static int coresight_clear_filter_source(struct device *dev, void *data) +{ + int i; + struct coresight_device *source = data; + struct coresight_device *csdev = to_coresight_device(dev); + + for (i = 0; i < csdev->pdata->nr_outconns; ++i) { + if (csdev->pdata->out_conns[i]->filter_src_dev == source) + csdev->pdata->out_conns[i]->filter_src_dev = NULL; + } + return 0; +} + +/* coresight_remove_conns - Remove other device's references to this device */ +static void coresight_remove_conns(struct coresight_device *csdev) +{ + int i, j; + struct coresight_connection *conn; + + if (coresight_is_device_source(csdev)) + bus_for_each_dev(&coresight_bustype, NULL, csdev, + coresight_clear_filter_source); + + /* + * Remove the input connection references from the destination device + * for each output connection. + */ + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + conn = csdev->pdata->out_conns[i]; + if (conn->filter_src_fwnode) { + conn->filter_src_dev = NULL; + fwnode_handle_put(conn->filter_src_fwnode); + } + + if (!conn->dest_dev) + continue; + + for (j = 0; j < conn->dest_dev->pdata->nr_inconns; ++j) + if (conn->dest_dev->pdata->in_conns[j] == conn) { + conn->dest_dev->pdata->in_conns[j] = NULL; + break; + } + } + + /* + * For all input connections, remove references to this device. + * Connection objects are shared so modifying this device's input + * connections affects the other device's output connection. + */ + for (i = 0; i < csdev->pdata->nr_inconns; ++i) { + conn = csdev->pdata->in_conns[i]; + /* Input conns array is sparse */ + if (!conn) + continue; + + conn->src_dev->orphan = true; + coresight_remove_links(conn->src_dev, conn); + conn->dest_dev = NULL; + } +} + +/** + * coresight_timeout_action - loop until a bit has changed to a specific register + * state, with a callback after every trial. + * @csa: coresight device access for the device + * @offset: Offset of the register from the base of the device. + * @position: the position of the bit of interest. + * @value: the value the bit should have. + * @cb: Call back after each trial. + * + * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if + * TIMEOUT_US has elapsed, which ever happens first. + */ +int coresight_timeout_action(struct csdev_access *csa, u32 offset, + int position, int value, + coresight_timeout_cb_t cb) +{ + int i; + u32 val; + + for (i = TIMEOUT_US; i > 0; i--) { + val = csdev_access_read32(csa, offset); + /* waiting on the bit to go from 0 to 1 */ + if (value) { + if (val & BIT(position)) + return 0; + /* waiting on the bit to go from 1 to 0 */ + } else { + if (!(val & BIT(position))) + return 0; + } + if (cb) + cb(csa, offset, position, value); + /* + * Delay is arbitrary - the specification doesn't say how long + * we are expected to wait. Extra check required to make sure + * we don't wait needlessly on the last iteration. + */ + if (i - 1) + udelay(1); + } + + return -EAGAIN; +} +EXPORT_SYMBOL_GPL(coresight_timeout_action); + +int coresight_timeout(struct csdev_access *csa, u32 offset, + int position, int value) +{ + return coresight_timeout_action(csa, offset, position, value, NULL); +} +EXPORT_SYMBOL_GPL(coresight_timeout); + +u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_relaxed_read32(&csdev->access, offset); +} + +u32 coresight_read32(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_read32(&csdev->access, offset); +} + +void coresight_relaxed_write32(struct coresight_device *csdev, + u32 val, u32 offset) +{ + csdev_access_relaxed_write32(&csdev->access, val, offset); +} + +void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset) +{ + csdev_access_write32(&csdev->access, val, offset); +} + +u64 coresight_relaxed_read64(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_relaxed_read64(&csdev->access, offset); +} + +u64 coresight_read64(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_read64(&csdev->access, offset); +} + +void coresight_relaxed_write64(struct coresight_device *csdev, + u64 val, u32 offset) +{ + csdev_access_relaxed_write64(&csdev->access, val, offset); +} + +void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset) +{ + csdev_access_write64(&csdev->access, val, offset); +} + +/* + * coresight_release_platform_data: Release references to the devices connected + * to the output port of this device. + */ +void coresight_release_platform_data(struct coresight_device *csdev, + struct device *dev, + struct coresight_platform_data *pdata) +{ + int i; + struct coresight_connection **conns = pdata->out_conns; + + for (i = 0; i < pdata->nr_outconns; i++) { + /* If we have made the links, remove them now */ + if (csdev && conns[i]->dest_dev) + coresight_remove_links(csdev, conns[i]); + /* + * Drop the refcount and clear the handle as this device + * is going away + */ + fwnode_handle_put(conns[i]->dest_fwnode); + conns[i]->dest_fwnode = NULL; + devm_kfree(dev, conns[i]); + } + devm_kfree(dev, pdata->out_conns); + devm_kfree(dev, pdata->in_conns); + devm_kfree(dev, pdata); + if (csdev) + coresight_remove_conns_sysfs_group(csdev); +} + +struct coresight_device *coresight_register(struct coresight_desc *desc) +{ + int ret; + struct coresight_device *csdev; + bool registered = false; + + csdev = kzalloc(sizeof(*csdev), GFP_KERNEL); + if (!csdev) { + ret = -ENOMEM; + goto err_out; + } + + csdev->pdata = desc->pdata; + + csdev->type = desc->type; + csdev->subtype = desc->subtype; + csdev->ops = desc->ops; + csdev->access = desc->access; + csdev->orphan = true; + + csdev->dev.type = &coresight_dev_type[desc->type]; + csdev->dev.groups = desc->groups; + csdev->dev.parent = desc->dev; + csdev->dev.release = coresight_device_release; + csdev->dev.bus = &coresight_bustype; + /* + * Hold the reference to our parent device. This will be + * dropped only in coresight_device_release(). + */ + csdev->dev.fwnode = fwnode_handle_get(dev_fwnode(desc->dev)); + dev_set_name(&csdev->dev, "%s", desc->name); + + if (csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + raw_spin_lock_init(&csdev->perf_sink_id_map.lock); + csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); + if (!csdev->perf_sink_id_map.cpu_map) { + kfree(csdev); + ret = -ENOMEM; + goto err_out; + } + } + /* + * Make sure the device registration and the connection fixup + * are synchronised, so that we don't see uninitialised devices + * on the coresight bus while trying to resolve the connections. + */ + mutex_lock(&coresight_mutex); + + ret = device_register(&csdev->dev); + if (ret) { + put_device(&csdev->dev); + /* + * All resources are free'd explicitly via + * coresight_device_release(), triggered from put_device(). + */ + goto out_unlock; + } + + if ((csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && + sink_ops(csdev)->alloc_buffer) { + ret = etm_perf_add_symlink_sink(csdev); + + if (ret) { + device_unregister(&csdev->dev); + /* + * As with the above, all resources are free'd + * explicitly via coresight_device_release() triggered + * from put_device(), which is in turn called from + * function device_unregister(). + */ + goto out_unlock; + } + } + /* Device is now registered */ + registered = true; + + ret = coresight_create_conns_sysfs_group(csdev); + if (!ret) + ret = coresight_fixup_orphan_conns(csdev); + +out_unlock: + mutex_unlock(&coresight_mutex); + /* Success */ + if (!ret) { + if (cti_assoc_ops && cti_assoc_ops->add) + cti_assoc_ops->add(csdev); + return csdev; + } + + /* Unregister the device if needed */ + if (registered) { + coresight_unregister(csdev); + return ERR_PTR(ret); + } + +err_out: + /* Cleanup the connection information */ + coresight_release_platform_data(NULL, desc->dev, desc->pdata); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(coresight_register); + +void coresight_unregister(struct coresight_device *csdev) +{ + etm_perf_del_symlink_sink(csdev); + /* Remove references of that device in the topology */ + if (cti_assoc_ops && cti_assoc_ops->remove) + cti_assoc_ops->remove(csdev); + coresight_remove_conns(csdev); + coresight_clear_default_sink(csdev); + coresight_release_platform_data(csdev, csdev->dev.parent, csdev->pdata); + device_unregister(&csdev->dev); +} +EXPORT_SYMBOL_GPL(coresight_unregister); + + +/* + * coresight_search_device_idx - Search the fwnode handle of a device + * in the given dev_idx list. Must be called with the coresight_mutex held. + * + * Returns the index of the entry, when found. Otherwise, -ENOENT. + */ +static int coresight_search_device_idx(struct coresight_dev_list *dict, + struct fwnode_handle *fwnode) +{ + int i; + + for (i = 0; i < dict->nr_idx; i++) + if (dict->fwnode_list[i] == fwnode) + return i; + return -ENOENT; +} + +static bool coresight_compare_type(enum coresight_dev_type type_a, + union coresight_dev_subtype subtype_a, + enum coresight_dev_type type_b, + union coresight_dev_subtype subtype_b) +{ + if (type_a != type_b) + return false; + + switch (type_a) { + case CORESIGHT_DEV_TYPE_SINK: + return subtype_a.sink_subtype == subtype_b.sink_subtype; + case CORESIGHT_DEV_TYPE_LINK: + return subtype_a.link_subtype == subtype_b.link_subtype; + case CORESIGHT_DEV_TYPE_LINKSINK: + return subtype_a.link_subtype == subtype_b.link_subtype && + subtype_a.sink_subtype == subtype_b.sink_subtype; + case CORESIGHT_DEV_TYPE_SOURCE: + return subtype_a.source_subtype == subtype_b.source_subtype; + case CORESIGHT_DEV_TYPE_HELPER: + return subtype_a.helper_subtype == subtype_b.helper_subtype; + default: + return false; + } +} + +struct coresight_device * +coresight_find_input_type(struct coresight_platform_data *pdata, + enum coresight_dev_type type, + union coresight_dev_subtype subtype) +{ + int i; + struct coresight_connection *conn; + + for (i = 0; i < pdata->nr_inconns; ++i) { + conn = pdata->in_conns[i]; + if (conn && + coresight_compare_type(type, subtype, conn->src_dev->type, + conn->src_dev->subtype)) + return conn->src_dev; + } + return NULL; +} +EXPORT_SYMBOL_GPL(coresight_find_input_type); + +struct coresight_device * +coresight_find_output_type(struct coresight_platform_data *pdata, + enum coresight_dev_type type, + union coresight_dev_subtype subtype) +{ + int i; + struct coresight_connection *conn; + + for (i = 0; i < pdata->nr_outconns; ++i) { + conn = pdata->out_conns[i]; + if (conn->dest_dev && + coresight_compare_type(type, subtype, conn->dest_dev->type, + conn->dest_dev->subtype)) + return conn->dest_dev; + } + return NULL; +} +EXPORT_SYMBOL_GPL(coresight_find_output_type); + +bool coresight_loses_context_with_cpu(struct device *dev) +{ + return fwnode_property_present(dev_fwnode(dev), + "arm,coresight-loses-context-with-cpu"); +} +EXPORT_SYMBOL_GPL(coresight_loses_context_with_cpu); + +/* + * coresight_alloc_device_name - Get an index for a given device in the + * device index list specific to a driver. An index is allocated for a + * device and is tracked with the fwnode_handle to prevent allocating + * duplicate indices for the same device (e.g, if we defer probing of + * a device due to dependencies), in case the index is requested again. + */ +char *coresight_alloc_device_name(struct coresight_dev_list *dict, + struct device *dev) +{ + int idx; + char *name = NULL; + struct fwnode_handle **list; + + mutex_lock(&coresight_mutex); + + idx = coresight_search_device_idx(dict, dev_fwnode(dev)); + if (idx < 0) { + /* Make space for the new entry */ + idx = dict->nr_idx; + list = krealloc_array(dict->fwnode_list, + idx + 1, sizeof(*dict->fwnode_list), + GFP_KERNEL); + if (ZERO_OR_NULL_PTR(list)) { + idx = -ENOMEM; + goto done; + } + + list[idx] = dev_fwnode(dev); + dict->fwnode_list = list; + dict->nr_idx = idx + 1; + } + + name = devm_kasprintf(dev, GFP_KERNEL, "%s%d", dict->pfx, idx); +done: + mutex_unlock(&coresight_mutex); + return name; +} +EXPORT_SYMBOL_GPL(coresight_alloc_device_name); + +const struct bus_type coresight_bustype = { + .name = "coresight", +}; + +static int coresight_panic_sync(struct device *dev, void *data) +{ + int mode; + struct coresight_device *csdev; + + /* Run through panic sync handlers for all enabled devices */ + csdev = container_of(dev, struct coresight_device, dev); + mode = coresight_get_mode(csdev); + + if ((mode == CS_MODE_SYSFS) || (mode == CS_MODE_PERF)) { + if (panic_ops(csdev)) + panic_ops(csdev)->sync(csdev); + } + + return 0; +} + +static int coresight_panic_cb(struct notifier_block *self, + unsigned long v, void *p) +{ + bus_for_each_dev(&coresight_bustype, NULL, NULL, + coresight_panic_sync); + + return 0; +} + +static struct notifier_block coresight_notifier = { + .notifier_call = coresight_panic_cb, +}; + +static int __init coresight_init(void) +{ + int ret; + + ret = bus_register(&coresight_bustype); + if (ret) + return ret; + + ret = etm_perf_init(); + if (ret) + goto exit_bus_unregister; + + /* Register function to be called for panic */ + ret = atomic_notifier_chain_register(&panic_notifier_list, + &coresight_notifier); + if (ret) + goto exit_perf; + + /* initialise the coresight syscfg API */ + ret = cscfg_init(); + if (!ret) + return 0; + + atomic_notifier_chain_unregister(&panic_notifier_list, + &coresight_notifier); +exit_perf: + etm_perf_exit(); +exit_bus_unregister: + bus_unregister(&coresight_bustype); + return ret; +} + +static void __exit coresight_exit(void) +{ + cscfg_exit(); + atomic_notifier_chain_unregister(&panic_notifier_list, + &coresight_notifier); + etm_perf_exit(); + bus_unregister(&coresight_bustype); +} + +module_init(coresight_init); +module_exit(coresight_exit); + +int coresight_init_driver(const char *drv, struct amba_driver *amba_drv, + struct platform_driver *pdev_drv, struct module *owner) +{ + int ret; + + ret = __amba_driver_register(amba_drv, owner); + if (ret) { + pr_err("%s: error registering AMBA driver\n", drv); + return ret; + } + + ret = __platform_driver_register(pdev_drv, owner); + if (!ret) + return 0; + + pr_err("%s: error registering platform driver\n", drv); + amba_driver_unregister(amba_drv); + return ret; +} +EXPORT_SYMBOL_GPL(coresight_init_driver); + +void coresight_remove_driver(struct amba_driver *amba_drv, + struct platform_driver *pdev_drv) +{ + amba_driver_unregister(amba_drv); + platform_driver_unregister(pdev_drv); +} +EXPORT_SYMBOL_GPL(coresight_remove_driver); + +int coresight_etm_get_trace_id(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_device *sink) +{ + int cpu, trace_id; + + if (csdev->type != CORESIGHT_DEV_TYPE_SOURCE || !source_ops(csdev)->cpu_id) + return -EINVAL; + + cpu = source_ops(csdev)->cpu_id(csdev); + switch (mode) { + case CS_MODE_SYSFS: + trace_id = coresight_trace_id_get_cpu_id(cpu); + break; + case CS_MODE_PERF: + if (WARN_ON(!sink)) + return -EINVAL; + + trace_id = coresight_trace_id_get_cpu_id_map(cpu, &sink->perf_sink_id_map); + break; + default: + trace_id = -EINVAL; + break; + } + + if (!IS_VALID_CS_TRACE_ID(trace_id)) + dev_err(&csdev->dev, + "Failed to allocate trace ID on CPU%d\n", cpu); + + return trace_id; +} +EXPORT_SYMBOL_GPL(coresight_etm_get_trace_id); + +/* + * Attempt to find and enable programming clock (pclk) and trace clock (atclk) + * for the given device. + * + * For ACPI devices, clocks are controlled by firmware, so bail out early in + * this case. Also, skip enabling pclk if the clock is managed by the AMBA + * bus driver instead. + * + * atclk is an optional clock, it will be only enabled when it is existed. + * Otherwise, a NULL pointer will be returned to caller. + * + * Returns: '0' on Success; Error code otherwise. + */ +int coresight_get_enable_clocks(struct device *dev, struct clk **pclk, + struct clk **atclk) +{ + WARN_ON(!pclk); + + if (has_acpi_companion(dev)) + return 0; + + if (!dev_is_amba(dev)) { + /* + * "apb_pclk" is the default clock name for an Arm Primecell + * peripheral, while "apb" is used only by the CTCU driver. + * + * For easier maintenance, CoreSight drivers should use + * "apb_pclk" as the programming clock name. + */ + *pclk = devm_clk_get_optional_enabled(dev, "apb_pclk"); + if (!*pclk) + *pclk = devm_clk_get_optional_enabled(dev, "apb"); + if (IS_ERR(*pclk)) + return PTR_ERR(*pclk); + } + + /* Initialization of atclk is skipped if it is a NULL pointer. */ + if (atclk) { + *atclk = devm_clk_get_optional_enabled(dev, "atclk"); + if (IS_ERR(*atclk)) + return PTR_ERR(*atclk); + } + + return 0; +} +EXPORT_SYMBOL_GPL(coresight_get_enable_clocks); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight tracer driver"); diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 45b2460f3166..5f21366406aa 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -4,6 +4,7 @@ * * Author: Leo Yan <leo.yan@linaro.org> */ +#include <linux/acpi.h> #include <linux/amba/bus.h> #include <linux/coresight.h> #include <linux/cpu.h> @@ -17,6 +18,8 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/panic_notifier.h> +#include <linux/platform_device.h> #include <linux/pm_qos.h> #include <linux/slab.h> #include <linux/smp.h> @@ -83,6 +86,7 @@ #define DEBUG_WAIT_TIMEOUT 32000 struct debug_drvdata { + struct clk *pclk; void __iomem *base; struct device *dev; int cpu; @@ -104,7 +108,7 @@ static DEFINE_PER_CPU(struct debug_drvdata *, debug_drvdata); static int debug_count; static struct dentry *debug_debugfs_dir; -static bool debug_enable; +static bool debug_enable = IS_ENABLED(CONFIG_CORESIGHT_CPU_DEBUG_DEFAULT_ON); module_param_named(enable, debug_enable, bool, 0600); MODULE_PARM_DESC(enable, "Control to enable coresight CPU debug functionality"); @@ -346,10 +350,10 @@ static void debug_init_arch_data(void *info) switch (mode) { case EDDEVID_IMPL_FULL: drvdata->edvidsr_present = true; - /* Fall through */ + fallthrough; case EDDEVID_IMPL_EDPCSR_EDCIDSR: drvdata->edcidsr_present = true; - /* Fall through */ + fallthrough; case EDDEVID_IMPL_EDPCSR: /* * In ARM DDI 0487A.k, the EDDEVID1.PCSROffset is used to @@ -379,9 +383,10 @@ static int debug_notifier_call(struct notifier_block *self, int cpu; struct debug_drvdata *drvdata; - mutex_lock(&debug_lock); + /* Bail out if we can't acquire the mutex or the functionality is off */ + if (!mutex_trylock(&debug_lock)) + return NOTIFY_DONE; - /* Bail out if the functionality is disabled */ if (!debug_enable) goto skip_dump; @@ -400,7 +405,7 @@ static int debug_notifier_call(struct notifier_block *self, skip_dump: mutex_unlock(&debug_lock); - return 0; + return NOTIFY_DONE; } static struct notifier_block debug_notifier = { @@ -525,23 +530,12 @@ static const struct file_operations debug_func_knob_fops = { static int debug_func_init(void) { - struct dentry *file; int ret; /* Create debugfs node */ debug_debugfs_dir = debugfs_create_dir("coresight_cpu_debug", NULL); - if (!debug_debugfs_dir) { - pr_err("%s: unable to create debugfs directory\n", __func__); - return -ENOMEM; - } - - file = debugfs_create_file("enable", 0644, debug_debugfs_dir, NULL, - &debug_func_knob_fops); - if (!file) { - pr_err("%s: unable to create enable knob file\n", __func__); - ret = -ENOMEM; - goto err; - } + debugfs_create_file("enable", 0644, debug_debugfs_dir, NULL, + &debug_func_knob_fops); /* Register function to be called for panic */ ret = atomic_notifier_chain_register(&panic_notifier_list, @@ -566,41 +560,44 @@ static void debug_func_exit(void) debugfs_remove_recursive(debug_debugfs_dir); } -static int debug_probe(struct amba_device *adev, const struct amba_id *id) +static int __debug_probe(struct device *dev, struct resource *res) { - void __iomem *base; - struct device *dev = &adev->dev; struct debug_drvdata *drvdata; - struct resource *res = &adev->res; - struct device_node *np = adev->dev.of_node; + void __iomem *base; int ret; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->cpu = np ? of_coresight_get_cpu(np) : 0; + dev_set_drvdata(dev, drvdata); + + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, NULL); + if (ret) + return ret; + + drvdata->cpu = coresight_get_cpu(dev); + if (drvdata->cpu < 0) + return drvdata->cpu; + if (per_cpu(debug_drvdata, drvdata->cpu)) { dev_err(dev, "CPU%d drvdata has already been initialized\n", drvdata->cpu); return -EBUSY; } - drvdata->dev = &adev->dev; - amba_set_drvdata(adev, drvdata); - - /* Validity for the resource is already checked by the AMBA core */ + drvdata->dev = dev; base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) return PTR_ERR(base); drvdata->base = base; - get_online_cpus(); + cpus_read_lock(); per_cpu(debug_drvdata, drvdata->cpu) = drvdata; ret = smp_call_function_single(drvdata->cpu, debug_init_arch_data, drvdata, 1); - put_online_cpus(); + cpus_read_unlock(); if (ret) { dev_err(dev, "CPU%d debug arch init failed\n", drvdata->cpu); @@ -636,10 +633,14 @@ err: return ret; } -static int debug_remove(struct amba_device *adev) +static int debug_probe(struct amba_device *adev, const struct amba_id *id) +{ + return __debug_probe(&adev->dev, &adev->res); +} + +static void __debug_remove(struct device *dev) { - struct device *dev = &adev->dev; - struct debug_drvdata *drvdata = amba_get_drvdata(adev); + struct debug_drvdata *drvdata = dev_get_drvdata(dev); per_cpu(debug_drvdata, drvdata->cpu) = NULL; @@ -651,26 +652,34 @@ static int debug_remove(struct amba_device *adev) if (!--debug_count) debug_func_exit(); +} - return 0; +static void debug_remove(struct amba_device *adev) +{ + __debug_remove(&adev->dev); } +static const struct amba_cs_uci_id uci_id_debug[] = { + { + /* CPU Debug UCI data */ + .devarch = 0x47706a15, + .devarch_mask = 0xfff0ffff, + .devtype = 0x00000015, + } +}; + static const struct amba_id debug_ids[] = { - { /* Debug for Cortex-A53 */ - .id = 0x000bbd03, - .mask = 0x000fffff, - }, - { /* Debug for Cortex-A57 */ - .id = 0x000bbd07, - .mask = 0x000fffff, - }, - { /* Debug for Cortex-A72 */ - .id = 0x000bbd08, - .mask = 0x000fffff, - }, - { 0, 0 }, + CS_AMBA_ID(0x000bbd03), /* Cortex-A53 */ + CS_AMBA_ID(0x000bbd07), /* Cortex-A57 */ + CS_AMBA_ID(0x000bbd08), /* Cortex-A72 */ + CS_AMBA_ID(0x000bbd09), /* Cortex-A73 */ + CS_AMBA_UCI_ID(0x000f0205, uci_id_debug), /* Qualcomm Kryo */ + CS_AMBA_UCI_ID(0x000f0211, uci_id_debug), /* Qualcomm Kryo */ + {}, }; +MODULE_DEVICE_TABLE(amba, debug_ids); + static struct amba_driver debug_driver = { .drv = { .name = "coresight-cpu-debug", @@ -681,7 +690,87 @@ static struct amba_driver debug_driver = { .id_table = debug_ids, }; -module_amba_driver(debug_driver); +static int debug_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret = 0; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = __debug_probe(&pdev->dev, res); + if (ret) { + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + } + return ret; +} + +static void debug_platform_remove(struct platform_device *pdev) +{ + struct debug_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + __debug_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_ACPI +static const struct acpi_device_id debug_platform_ids[] = { + {"ARMHC503", 0, 0, 0}, /* ARM CoreSight Debug */ + {}, +}; +MODULE_DEVICE_TABLE(acpi, debug_platform_ids); +#endif + +#ifdef CONFIG_PM +static int debug_runtime_suspend(struct device *dev) +{ + struct debug_drvdata *drvdata = dev_get_drvdata(dev); + + clk_disable_unprepare(drvdata->pclk); + + return 0; +} + +static int debug_runtime_resume(struct device *dev) +{ + struct debug_drvdata *drvdata = dev_get_drvdata(dev); + + return clk_prepare_enable(drvdata->pclk); +} +#endif + +static const struct dev_pm_ops debug_dev_pm_ops = { + SET_RUNTIME_PM_OPS(debug_runtime_suspend, debug_runtime_resume, NULL) +}; + +static struct platform_driver debug_platform_driver = { + .probe = debug_platform_probe, + .remove = debug_platform_remove, + .driver = { + .name = "coresight-debug-platform", + .acpi_match_table = ACPI_PTR(debug_platform_ids), + .suppress_bind_attrs = true, + .pm = &debug_dev_pm_ops, + }, +}; + +static int __init debug_init(void) +{ + return coresight_init_driver("debug", &debug_driver, &debug_platform_driver, + THIS_MODULE); +} + +static void __exit debug_exit(void) +{ + coresight_remove_driver(&debug_driver, &debug_platform_driver); +} +module_init(debug_init); +module_exit(debug_exit); MODULE_AUTHOR("Leo Yan <leo.yan@linaro.org>"); MODULE_DESCRIPTION("ARM Coresight CPU Debug Driver"); diff --git a/drivers/hwtracing/coresight/coresight-ctcu-core.c b/drivers/hwtracing/coresight/coresight-ctcu-core.c new file mode 100644 index 000000000000..abed15eb72b4 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-ctcu-core.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/clk.h> +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/slab.h> + +#include "coresight-ctcu.h" +#include "coresight-priv.h" + +DEFINE_CORESIGHT_DEVLIST(ctcu_devs, "ctcu"); + +#define ctcu_writel(drvdata, val, offset) __raw_writel((val), drvdata->base + offset) +#define ctcu_readl(drvdata, offset) __raw_readl(drvdata->base + offset) + +/* + * The TMC Coresight Control Unit utilizes four ATID registers to control the data + * filter function based on the trace ID for each TMC ETR sink. The length of each + * ATID register is 32 bits. Therefore, an ETR device has a 128-bit long field + * in CTCU. Each trace ID is represented by one bit in that filed. + * e.g. ETR0ATID0 layout, set bit 5 for traceid 5 + * bit5 + * ------------------------------------------------------ + * | |28| |24| |20| |16| |12| |8| 1|4| |0| + * ------------------------------------------------------ + * + * e.g. ETR0: + * 127 0 from ATID_offset for ETR0ATID0 + * ------------------------- + * |ATID3|ATID2|ATID1|ATID0| + */ +#define CTCU_ATID_REG_OFFSET(traceid, atid_offset) \ + ((traceid / 32) * 4 + atid_offset) + +#define CTCU_ATID_REG_BIT(traceid) (traceid % 32) +#define CTCU_ATID_REG_SIZE 0x10 +#define CTCU_ETR0_ATID0 0xf8 +#define CTCU_ETR1_ATID0 0x108 + +static const struct ctcu_etr_config sa8775p_etr_cfgs[] = { + { + .atid_offset = CTCU_ETR0_ATID0, + .port_num = 0, + }, + { + .atid_offset = CTCU_ETR1_ATID0, + .port_num = 1, + }, +}; + +static const struct ctcu_config sa8775p_cfgs = { + .etr_cfgs = sa8775p_etr_cfgs, + .num_etr_config = ARRAY_SIZE(sa8775p_etr_cfgs), +}; + +static void ctcu_program_atid_register(struct ctcu_drvdata *drvdata, u32 reg_offset, + u8 bit, bool enable) +{ + u32 val; + + CS_UNLOCK(drvdata->base); + val = ctcu_readl(drvdata, reg_offset); + if (enable) + val |= BIT(bit); + else + val &= ~BIT(bit); + + ctcu_writel(drvdata, val, reg_offset); + CS_LOCK(drvdata->base); +} + +/* + * __ctcu_set_etr_traceid: Set bit in the ATID register based on trace ID when enable is true. + * Reset the bit of the ATID register based on trace ID when enable is false. + * + * @csdev: coresight_device of CTCU. + * @traceid: trace ID of the source tracer. + * @port_num: port number connected to TMC ETR sink. + * @enable: True for set bit and false for reset bit. + * + * Returns 0 indicates success. Non-zero result means failure. + */ +static int __ctcu_set_etr_traceid(struct coresight_device *csdev, u8 traceid, int port_num, + bool enable) +{ + struct ctcu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + u32 atid_offset, reg_offset; + u8 refcnt, bit; + + atid_offset = drvdata->atid_offset[port_num]; + if (atid_offset == 0) + return -EINVAL; + + bit = CTCU_ATID_REG_BIT(traceid); + reg_offset = CTCU_ATID_REG_OFFSET(traceid, atid_offset); + if (reg_offset - atid_offset > CTCU_ATID_REG_SIZE) + return -EINVAL; + + guard(raw_spinlock_irqsave)(&drvdata->spin_lock); + refcnt = drvdata->traceid_refcnt[port_num][traceid]; + /* Only program the atid register when the refcnt value is 1 or 0 */ + if ((enable && !refcnt++) || (!enable && !--refcnt)) + ctcu_program_atid_register(drvdata, reg_offset, bit, enable); + + drvdata->traceid_refcnt[port_num][traceid] = refcnt; + + return 0; +} + +/* + * Searching the sink device from helper's view in case there are multiple helper devices + * connected to the sink device. + */ +static int ctcu_get_active_port(struct coresight_device *sink, struct coresight_device *helper) +{ + struct coresight_platform_data *pdata = helper->pdata; + int i; + + for (i = 0; i < pdata->nr_inconns; ++i) { + if (pdata->in_conns[i]->src_dev == sink) + return pdata->in_conns[i]->dest_port; + } + + return -EINVAL; +} + +static int ctcu_set_etr_traceid(struct coresight_device *csdev, struct coresight_path *path, + bool enable) +{ + struct coresight_device *sink = coresight_get_sink(path); + u8 traceid = path->trace_id; + int port_num; + + if ((sink == NULL) || !IS_VALID_CS_TRACE_ID(traceid)) { + dev_err(&csdev->dev, "Invalid sink device or trace ID\n"); + return -EINVAL; + } + + port_num = ctcu_get_active_port(sink, csdev); + if (port_num < 0) + return -EINVAL; + + dev_dbg(&csdev->dev, "traceid is %d\n", traceid); + + return __ctcu_set_etr_traceid(csdev, traceid, port_num, enable); +} + +static int ctcu_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) +{ + return ctcu_set_etr_traceid(csdev, path, true); +} + +static int ctcu_disable(struct coresight_device *csdev, struct coresight_path *path) +{ + return ctcu_set_etr_traceid(csdev, path, false); +} + +static const struct coresight_ops_helper ctcu_helper_ops = { + .enable = ctcu_enable, + .disable = ctcu_disable, +}; + +static const struct coresight_ops ctcu_ops = { + .helper_ops = &ctcu_helper_ops, +}; + +static int ctcu_probe(struct platform_device *pdev) +{ + const struct ctcu_etr_config *etr_cfg; + struct coresight_platform_data *pdata; + struct coresight_desc desc = { 0 }; + struct device *dev = &pdev->dev; + const struct ctcu_config *cfgs; + struct ctcu_drvdata *drvdata; + void __iomem *base; + int i, ret; + + desc.name = coresight_alloc_device_name(&ctcu_devs, dev); + if (!desc.name) + return -ENOMEM; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + dev->platform_data = pdata; + + base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(base)) + return PTR_ERR(base); + + ret = coresight_get_enable_clocks(dev, &drvdata->apb_clk, NULL); + if (ret) + return ret; + + cfgs = of_device_get_match_data(dev); + if (cfgs) { + if (cfgs->num_etr_config <= ETR_MAX_NUM) { + for (i = 0; i < cfgs->num_etr_config; i++) { + etr_cfg = &cfgs->etr_cfgs[i]; + drvdata->atid_offset[i] = etr_cfg->atid_offset; + } + } + } + + drvdata->base = base; + drvdata->dev = dev; + platform_set_drvdata(pdev, drvdata); + + desc.type = CORESIGHT_DEV_TYPE_HELPER; + desc.subtype.helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_CTCU; + desc.pdata = pdata; + desc.dev = dev; + desc.ops = &ctcu_ops; + desc.access = CSDEV_ACCESS_IOMEM(base); + + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + return 0; +} + +static void ctcu_remove(struct platform_device *pdev) +{ + struct ctcu_drvdata *drvdata = platform_get_drvdata(pdev); + + coresight_unregister(drvdata->csdev); +} + +static int ctcu_platform_probe(struct platform_device *pdev) +{ + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = ctcu_probe(pdev); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void ctcu_platform_remove(struct platform_device *pdev) +{ + struct ctcu_drvdata *drvdata = platform_get_drvdata(pdev); + + if (WARN_ON(!drvdata)) + return; + + ctcu_remove(pdev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_PM +static int ctcu_runtime_suspend(struct device *dev) +{ + struct ctcu_drvdata *drvdata = dev_get_drvdata(dev); + + clk_disable_unprepare(drvdata->apb_clk); + + return 0; +} + +static int ctcu_runtime_resume(struct device *dev) +{ + struct ctcu_drvdata *drvdata = dev_get_drvdata(dev); + + return clk_prepare_enable(drvdata->apb_clk); +} +#endif + +static const struct dev_pm_ops ctcu_dev_pm_ops = { + SET_RUNTIME_PM_OPS(ctcu_runtime_suspend, ctcu_runtime_resume, NULL) +}; + +static const struct of_device_id ctcu_match[] = { + {.compatible = "qcom,sa8775p-ctcu", .data = &sa8775p_cfgs}, + {} +}; + +static struct platform_driver ctcu_driver = { + .probe = ctcu_platform_probe, + .remove = ctcu_platform_remove, + .driver = { + .name = "coresight-ctcu", + .of_match_table = ctcu_match, + .pm = &ctcu_dev_pm_ops, + .suppress_bind_attrs = true, + }, +}; +module_platform_driver(ctcu_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("CoreSight TMC Control Unit driver"); diff --git a/drivers/hwtracing/coresight/coresight-ctcu.h b/drivers/hwtracing/coresight/coresight-ctcu.h new file mode 100644 index 000000000000..e9594c38dd91 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-ctcu.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _CORESIGHT_CTCU_H +#define _CORESIGHT_CTCU_H +#include "coresight-trace-id.h" + +/* Maximum number of supported ETR devices for a single CTCU. */ +#define ETR_MAX_NUM 2 + +/** + * struct ctcu_etr_config + * @atid_offset: offset to the ATID0 Register. + * @port_num: in-port number of CTCU device that connected to ETR. + */ +struct ctcu_etr_config { + const u32 atid_offset; + const u32 port_num; +}; + +struct ctcu_config { + const struct ctcu_etr_config *etr_cfgs; + int num_etr_config; +}; + +struct ctcu_drvdata { + void __iomem *base; + struct clk *apb_clk; + struct device *dev; + struct coresight_device *csdev; + raw_spinlock_t spin_lock; + u32 atid_offset[ETR_MAX_NUM]; + /* refcnt for each traceid of each sink */ + u8 traceid_refcnt[ETR_MAX_NUM][CORESIGHT_TRACE_ID_RES_TOP]; +}; + +#endif diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c new file mode 100644 index 000000000000..bfbc365bb2ef --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -0,0 +1,1017 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/amba/bus.h> +#include <linux/atomic.h> +#include <linux/bits.h> +#include <linux/coresight.h> +#include <linux/cpu_pm.h> +#include <linux/cpuhotplug.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/pm_runtime.h> +#include <linux/property.h> +#include <linux/spinlock.h> + +#include "coresight-priv.h" +#include "coresight-cti.h" + +/* + * CTI devices can be associated with a PE, or be connected to CoreSight + * hardware. We have a list of all CTIs irrespective of CPU bound or + * otherwise. + * + * We assume that the non-CPU CTIs are always powered as we do with sinks etc. + * + * We leave the client to figure out if all the CTIs are interconnected with + * the same CTM, in general this is the case but does not always have to be. + */ + +/* net of CTI devices connected via CTM */ +static LIST_HEAD(ect_net); + +/* protect the list */ +static DEFINE_MUTEX(ect_mutex); + +#define csdev_to_cti_drvdata(csdev) \ + dev_get_drvdata(csdev->dev.parent) + +/* power management handling */ +static int nr_cti_cpu; + +/* quick lookup list for CPU bound CTIs when power handling */ +static struct cti_drvdata *cti_cpu_drvdata[NR_CPUS]; + +/* + * CTI naming. CTI bound to cores will have the name cti_cpu<N> where + * N is the CPU ID. System CTIs will have the name cti_sys<I> where I + * is an index allocated by order of discovery. + * + * CTI device name list - for CTI not bound to cores. + */ +DEFINE_CORESIGHT_DEVLIST(cti_sys_devs, "cti_sys"); + +/* write set of regs to hardware - call with spinlock claimed */ +void cti_write_all_hw_regs(struct cti_drvdata *drvdata) +{ + struct cti_config *config = &drvdata->config; + int i; + + CS_UNLOCK(drvdata->base); + + /* disable CTI before writing registers */ + writel_relaxed(0, drvdata->base + CTICONTROL); + + /* write the CTI trigger registers */ + for (i = 0; i < config->nr_trig_max; i++) { + writel_relaxed(config->ctiinen[i], drvdata->base + CTIINEN(i)); + writel_relaxed(config->ctiouten[i], + drvdata->base + CTIOUTEN(i)); + } + + /* other regs */ + writel_relaxed(config->ctigate, drvdata->base + CTIGATE); + writel_relaxed(config->asicctl, drvdata->base + ASICCTL); + writel_relaxed(config->ctiappset, drvdata->base + CTIAPPSET); + + /* re-enable CTI */ + writel_relaxed(1, drvdata->base + CTICONTROL); + + CS_LOCK(drvdata->base); +} + +/* write regs to hardware and enable */ +static int cti_enable_hw(struct cti_drvdata *drvdata) +{ + struct cti_config *config = &drvdata->config; + unsigned long flags; + int rc = 0; + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* no need to do anything if enabled or unpowered*/ + if (config->hw_enabled || !config->hw_powered) + goto cti_state_unchanged; + + /* claim the device */ + rc = coresight_claim_device(drvdata->csdev); + if (rc) + goto cti_err_not_enabled; + + cti_write_all_hw_regs(drvdata); + + config->hw_enabled = true; + drvdata->config.enable_req_count++; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return rc; + +cti_state_unchanged: + drvdata->config.enable_req_count++; + + /* cannot enable due to error */ +cti_err_not_enabled: + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return rc; +} + +/* re-enable CTI on CPU when using CPU hotplug */ +static void cti_cpuhp_enable_hw(struct cti_drvdata *drvdata) +{ + struct cti_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + config->hw_powered = true; + + /* no need to do anything if no enable request */ + if (!drvdata->config.enable_req_count) + goto cti_hp_not_enabled; + + /* try to claim the device */ + if (coresight_claim_device(drvdata->csdev)) + goto cti_hp_not_enabled; + + cti_write_all_hw_regs(drvdata); + config->hw_enabled = true; + raw_spin_unlock(&drvdata->spinlock); + return; + + /* did not re-enable due to no claim / no request */ +cti_hp_not_enabled: + raw_spin_unlock(&drvdata->spinlock); +} + +/* disable hardware */ +static int cti_disable_hw(struct cti_drvdata *drvdata) +{ + struct cti_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; + int ret = 0; + + raw_spin_lock(&drvdata->spinlock); + + /* don't allow negative refcounts, return an error */ + if (!drvdata->config.enable_req_count) { + ret = -EINVAL; + goto cti_not_disabled; + } + + /* check refcount - disable on 0 */ + if (--drvdata->config.enable_req_count > 0) + goto cti_not_disabled; + + /* no need to do anything if disabled or cpu unpowered */ + if (!config->hw_enabled || !config->hw_powered) + goto cti_not_disabled; + + CS_UNLOCK(drvdata->base); + + /* disable CTI */ + writel_relaxed(0, drvdata->base + CTICONTROL); + config->hw_enabled = false; + + coresight_disclaim_device_unlocked(csdev); + CS_LOCK(drvdata->base); + raw_spin_unlock(&drvdata->spinlock); + return ret; + + /* not disabled this call */ +cti_not_disabled: + raw_spin_unlock(&drvdata->spinlock); + return ret; +} + +void cti_write_single_reg(struct cti_drvdata *drvdata, int offset, u32 value) +{ + CS_UNLOCK(drvdata->base); + writel_relaxed(value, drvdata->base + offset); + CS_LOCK(drvdata->base); +} + +void cti_write_intack(struct device *dev, u32 ackval) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + /* write if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIINTACK, ackval); + raw_spin_unlock(&drvdata->spinlock); +} + +/* + * Look at the HW DEVID register for some of the HW settings. + * DEVID[15:8] - max number of in / out triggers. + */ +#define CTI_DEVID_MAXTRIGS(devid_val) ((int) BMVAL(devid_val, 8, 15)) + +/* DEVID[19:16] - number of CTM channels */ +#define CTI_DEVID_CTMCHANNELS(devid_val) ((int) BMVAL(devid_val, 16, 19)) + +static void cti_set_default_config(struct device *dev, + struct cti_drvdata *drvdata) +{ + struct cti_config *config = &drvdata->config; + u32 devid; + + devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID); + config->nr_trig_max = CTI_DEVID_MAXTRIGS(devid); + + /* + * no current hardware should exceed this, but protect the driver + * in case of fault / out of spec hw + */ + if (config->nr_trig_max > CTIINOUTEN_MAX) { + dev_warn_once(dev, + "Limiting HW MaxTrig value(%d) to driver max(%d)\n", + config->nr_trig_max, CTIINOUTEN_MAX); + config->nr_trig_max = CTIINOUTEN_MAX; + } + + config->nr_ctm_channels = CTI_DEVID_CTMCHANNELS(devid); + + /* Most regs default to 0 as zalloc'ed except...*/ + config->trig_filter_enable = true; + config->ctigate = GENMASK(config->nr_ctm_channels - 1, 0); + config->enable_req_count = 0; +} + +/* + * Add a connection entry to the list of connections for this + * CTI device. + */ +int cti_add_connection_entry(struct device *dev, struct cti_drvdata *drvdata, + struct cti_trig_con *tc, + struct coresight_device *csdev, + const char *assoc_dev_name) +{ + struct cti_device *cti_dev = &drvdata->ctidev; + + tc->con_dev = csdev; + /* + * Prefer actual associated CS device dev name to supplied value - + * which is likely to be node name / other conn name. + */ + if (csdev) + tc->con_dev_name = dev_name(&csdev->dev); + else if (assoc_dev_name != NULL) { + tc->con_dev_name = devm_kstrdup(dev, + assoc_dev_name, GFP_KERNEL); + if (!tc->con_dev_name) + return -ENOMEM; + } + list_add_tail(&tc->node, &cti_dev->trig_cons); + cti_dev->nr_trig_con++; + + /* add connection usage bit info to overall info */ + drvdata->config.trig_in_use |= tc->con_in->used_mask; + drvdata->config.trig_out_use |= tc->con_out->used_mask; + + return 0; +} + +/* create a trigger connection with appropriately sized signal groups */ +struct cti_trig_con *cti_allocate_trig_con(struct device *dev, int in_sigs, + int out_sigs) +{ + struct cti_trig_con *tc = NULL; + struct cti_trig_grp *in = NULL, *out = NULL; + + tc = devm_kzalloc(dev, sizeof(struct cti_trig_con), GFP_KERNEL); + if (!tc) + return tc; + + in = devm_kzalloc(dev, + offsetof(struct cti_trig_grp, sig_types[in_sigs]), + GFP_KERNEL); + if (!in) + return NULL; + + out = devm_kzalloc(dev, + offsetof(struct cti_trig_grp, sig_types[out_sigs]), + GFP_KERNEL); + if (!out) + return NULL; + + tc->con_in = in; + tc->con_out = out; + tc->con_in->nr_sigs = in_sigs; + tc->con_out->nr_sigs = out_sigs; + return tc; +} + +/* + * Add a default connection if nothing else is specified. + * single connection based on max in/out info, no assoc device + */ +int cti_add_default_connection(struct device *dev, struct cti_drvdata *drvdata) +{ + int ret = 0; + int n_trigs = drvdata->config.nr_trig_max; + u32 n_trig_mask = GENMASK(n_trigs - 1, 0); + struct cti_trig_con *tc = NULL; + + /* + * Assume max trigs for in and out, + * all used, default sig types allocated + */ + tc = cti_allocate_trig_con(dev, n_trigs, n_trigs); + if (!tc) + return -ENOMEM; + + tc->con_in->used_mask = n_trig_mask; + tc->con_out->used_mask = n_trig_mask; + ret = cti_add_connection_entry(dev, drvdata, tc, NULL, "default"); + return ret; +} + +/** cti channel api **/ +/* attach/detach channel from trigger - write through if enabled. */ +int cti_channel_trig_op(struct device *dev, enum cti_chan_op op, + enum cti_trig_dir direction, u32 channel_idx, + u32 trigger_idx) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + u32 trig_bitmask; + u32 chan_bitmask; + u32 reg_value; + int reg_offset; + + /* ensure indexes in range */ + if ((channel_idx >= config->nr_ctm_channels) || + (trigger_idx >= config->nr_trig_max)) + return -EINVAL; + + trig_bitmask = BIT(trigger_idx); + + /* ensure registered triggers and not out filtered */ + if (direction == CTI_TRIG_IN) { + if (!(trig_bitmask & config->trig_in_use)) + return -EINVAL; + } else { + if (!(trig_bitmask & config->trig_out_use)) + return -EINVAL; + + if ((config->trig_filter_enable) && + (config->trig_out_filter & trig_bitmask)) + return -EINVAL; + } + + /* update the local register values */ + chan_bitmask = BIT(channel_idx); + reg_offset = (direction == CTI_TRIG_IN ? CTIINEN(trigger_idx) : + CTIOUTEN(trigger_idx)); + + raw_spin_lock(&drvdata->spinlock); + + /* read - modify write - the trigger / channel enable value */ + reg_value = direction == CTI_TRIG_IN ? config->ctiinen[trigger_idx] : + config->ctiouten[trigger_idx]; + if (op == CTI_CHAN_ATTACH) + reg_value |= chan_bitmask; + else + reg_value &= ~chan_bitmask; + + /* write local copy */ + if (direction == CTI_TRIG_IN) + config->ctiinen[trigger_idx] = reg_value; + else + config->ctiouten[trigger_idx] = reg_value; + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, reg_offset, reg_value); + raw_spin_unlock(&drvdata->spinlock); + return 0; +} + +int cti_channel_gate_op(struct device *dev, enum cti_chan_gate_op op, + u32 channel_idx) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + u32 chan_bitmask; + u32 reg_value; + int err = 0; + + if (channel_idx >= config->nr_ctm_channels) + return -EINVAL; + + chan_bitmask = BIT(channel_idx); + + raw_spin_lock(&drvdata->spinlock); + reg_value = config->ctigate; + switch (op) { + case CTI_GATE_CHAN_ENABLE: + reg_value |= chan_bitmask; + break; + + case CTI_GATE_CHAN_DISABLE: + reg_value &= ~chan_bitmask; + break; + + default: + err = -EINVAL; + break; + } + if (err == 0) { + config->ctigate = reg_value; + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIGATE, reg_value); + } + raw_spin_unlock(&drvdata->spinlock); + return err; +} + +int cti_channel_setop(struct device *dev, enum cti_chan_set_op op, + u32 channel_idx) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + u32 chan_bitmask; + u32 reg_value; + u32 reg_offset; + int err = 0; + + if (channel_idx >= config->nr_ctm_channels) + return -EINVAL; + + chan_bitmask = BIT(channel_idx); + + raw_spin_lock(&drvdata->spinlock); + reg_value = config->ctiappset; + switch (op) { + case CTI_CHAN_SET: + config->ctiappset |= chan_bitmask; + reg_value = config->ctiappset; + reg_offset = CTIAPPSET; + break; + + case CTI_CHAN_CLR: + config->ctiappset &= ~chan_bitmask; + reg_value = chan_bitmask; + reg_offset = CTIAPPCLEAR; + break; + + case CTI_CHAN_PULSE: + config->ctiappset &= ~chan_bitmask; + reg_value = chan_bitmask; + reg_offset = CTIAPPPULSE; + break; + + default: + err = -EINVAL; + break; + } + + if ((err == 0) && cti_active(config)) + cti_write_single_reg(drvdata, reg_offset, reg_value); + raw_spin_unlock(&drvdata->spinlock); + + return err; +} + +static bool cti_add_sysfs_link(struct cti_drvdata *drvdata, + struct cti_trig_con *tc) +{ + struct coresight_sysfs_link link_info; + int link_err = 0; + + link_info.orig = drvdata->csdev; + link_info.orig_name = tc->con_dev_name; + link_info.target = tc->con_dev; + link_info.target_name = dev_name(&drvdata->csdev->dev); + + link_err = coresight_add_sysfs_link(&link_info); + if (link_err) + dev_warn(&drvdata->csdev->dev, + "Failed to set CTI sysfs link %s<=>%s\n", + link_info.orig_name, link_info.target_name); + return !link_err; +} + +static void cti_remove_sysfs_link(struct cti_drvdata *drvdata, + struct cti_trig_con *tc) +{ + struct coresight_sysfs_link link_info; + + link_info.orig = drvdata->csdev; + link_info.orig_name = tc->con_dev_name; + link_info.target = tc->con_dev; + link_info.target_name = dev_name(&drvdata->csdev->dev); + coresight_remove_sysfs_link(&link_info); +} + +/* + * Look for a matching connection device name in the list of connections. + * If found then swap in the csdev name, set trig con association pointer + * and return found. + */ +static bool +cti_match_fixup_csdev(struct cti_device *ctidev, const char *node_name, + struct coresight_device *csdev) +{ + struct cti_trig_con *tc; + struct cti_drvdata *drvdata = container_of(ctidev, struct cti_drvdata, + ctidev); + + list_for_each_entry(tc, &ctidev->trig_cons, node) { + if (tc->con_dev_name) { + if (!strcmp(node_name, tc->con_dev_name)) { + /* match: so swap in csdev name & dev */ + tc->con_dev_name = dev_name(&csdev->dev); + tc->con_dev = csdev; + /* try to set sysfs link */ + if (cti_add_sysfs_link(drvdata, tc)) + return true; + /* link failed - remove CTI reference */ + tc->con_dev = NULL; + break; + } + } + } + return false; +} + +/* + * Search the cti list to add an associated CTI into the supplied CS device + * This will set the association if CTI declared before the CS device. + * (called from coresight_register() without coresight_mutex locked). + */ +static void cti_add_assoc_to_csdev(struct coresight_device *csdev) +{ + struct cti_drvdata *ect_item; + struct cti_device *ctidev; + const char *node_name = NULL; + + /* protect the list */ + mutex_lock(&ect_mutex); + + /* exit if current is an ECT device.*/ + if ((csdev->type == CORESIGHT_DEV_TYPE_HELPER && + csdev->subtype.helper_subtype == + CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI) || + list_empty(&ect_net)) + goto cti_add_done; + + /* if we didn't find the csdev previously we used the fwnode name */ + node_name = cti_plat_get_node_name(dev_fwnode(csdev->dev.parent)); + if (!node_name) + goto cti_add_done; + + /* for each CTI in list... */ + list_for_each_entry(ect_item, &ect_net, node) { + ctidev = &ect_item->ctidev; + if (cti_match_fixup_csdev(ctidev, node_name, csdev)) { + /* + * if we found a matching csdev then update the ECT + * association pointer for the device with this CTI. + */ + coresight_add_helper(csdev, ect_item->csdev); + break; + } + } +cti_add_done: + mutex_unlock(&ect_mutex); +} + +/* + * Removing the associated devices is easier. + */ +static void cti_remove_assoc_from_csdev(struct coresight_device *csdev) +{ + struct cti_drvdata *ctidrv; + struct cti_trig_con *tc; + struct cti_device *ctidev; + union coresight_dev_subtype cti_subtype = { + .helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI + }; + struct coresight_device *cti_csdev = coresight_find_output_type( + csdev->pdata, CORESIGHT_DEV_TYPE_HELPER, cti_subtype); + + if (!cti_csdev) + return; + + mutex_lock(&ect_mutex); + ctidrv = csdev_to_cti_drvdata(cti_csdev); + ctidev = &ctidrv->ctidev; + list_for_each_entry(tc, &ctidev->trig_cons, node) { + if (tc->con_dev == csdev) { + cti_remove_sysfs_link(ctidrv, tc); + tc->con_dev = NULL; + break; + } + } + mutex_unlock(&ect_mutex); +} + +/* + * Operations to add and remove associated CTI. + * Register to coresight core driver as call back function. + */ +static struct cti_assoc_op cti_assoc_ops = { + .add = cti_add_assoc_to_csdev, + .remove = cti_remove_assoc_from_csdev +}; + +/* + * Update the cross references where the associated device was found + * while we were building the connection info. This will occur if the + * assoc device was registered before the CTI. + */ +static void cti_update_conn_xrefs(struct cti_drvdata *drvdata) +{ + struct cti_trig_con *tc; + struct cti_device *ctidev = &drvdata->ctidev; + + list_for_each_entry(tc, &ctidev->trig_cons, node) { + if (tc->con_dev) { + /* if we can set the sysfs link */ + if (cti_add_sysfs_link(drvdata, tc)) + /* set the CTI/csdev association */ + coresight_add_helper(tc->con_dev, + drvdata->csdev); + else + /* otherwise remove reference from CTI */ + tc->con_dev = NULL; + } + } +} + +static void cti_remove_conn_xrefs(struct cti_drvdata *drvdata) +{ + struct cti_trig_con *tc; + struct cti_device *ctidev = &drvdata->ctidev; + + list_for_each_entry(tc, &ctidev->trig_cons, node) { + if (tc->con_dev) { + cti_remove_sysfs_link(drvdata, tc); + tc->con_dev = NULL; + } + } +} + +/** cti PM callbacks **/ +static int cti_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, + void *v) +{ + struct cti_drvdata *drvdata; + struct coresight_device *csdev; + unsigned int cpu = smp_processor_id(); + int notify_res = NOTIFY_OK; + + if (!cti_cpu_drvdata[cpu]) + return NOTIFY_OK; + + drvdata = cti_cpu_drvdata[cpu]; + csdev = drvdata->csdev; + + if (WARN_ON_ONCE(drvdata->ctidev.cpu != cpu)) + return NOTIFY_BAD; + + raw_spin_lock(&drvdata->spinlock); + + switch (cmd) { + case CPU_PM_ENTER: + /* CTI regs all static - we have a copy & nothing to save */ + drvdata->config.hw_powered = false; + if (drvdata->config.hw_enabled) + coresight_disclaim_device(csdev); + break; + + case CPU_PM_ENTER_FAILED: + drvdata->config.hw_powered = true; + if (drvdata->config.hw_enabled) { + if (coresight_claim_device(csdev)) + drvdata->config.hw_enabled = false; + } + break; + + case CPU_PM_EXIT: + /* write hardware registers to re-enable. */ + drvdata->config.hw_powered = true; + drvdata->config.hw_enabled = false; + + /* check enable reference count to enable HW */ + if (drvdata->config.enable_req_count) { + /* check we can claim the device as we re-power */ + if (coresight_claim_device(csdev)) + goto cti_notify_exit; + + drvdata->config.hw_enabled = true; + cti_write_all_hw_regs(drvdata); + } + break; + + default: + notify_res = NOTIFY_DONE; + break; + } + +cti_notify_exit: + raw_spin_unlock(&drvdata->spinlock); + return notify_res; +} + +static struct notifier_block cti_cpu_pm_nb = { + .notifier_call = cti_cpu_pm_notify, +}; + +/* CPU HP handlers */ +static int cti_starting_cpu(unsigned int cpu) +{ + struct cti_drvdata *drvdata = cti_cpu_drvdata[cpu]; + + if (!drvdata) + return 0; + + cti_cpuhp_enable_hw(drvdata); + return 0; +} + +static int cti_dying_cpu(unsigned int cpu) +{ + struct cti_drvdata *drvdata = cti_cpu_drvdata[cpu]; + + if (!drvdata) + return 0; + + raw_spin_lock(&drvdata->spinlock); + drvdata->config.hw_powered = false; + if (drvdata->config.hw_enabled) + coresight_disclaim_device(drvdata->csdev); + raw_spin_unlock(&drvdata->spinlock); + return 0; +} + +static int cti_pm_setup(struct cti_drvdata *drvdata) +{ + int ret; + + if (drvdata->ctidev.cpu == -1) + return 0; + + if (nr_cti_cpu) + goto done; + + cpus_read_lock(); + ret = cpuhp_setup_state_nocalls_cpuslocked( + CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, + "arm/coresight_cti:starting", + cti_starting_cpu, cti_dying_cpu); + if (ret) { + cpus_read_unlock(); + return ret; + } + + ret = cpu_pm_register_notifier(&cti_cpu_pm_nb); + cpus_read_unlock(); + if (ret) { + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_CTI_STARTING); + return ret; + } + +done: + nr_cti_cpu++; + cti_cpu_drvdata[drvdata->ctidev.cpu] = drvdata; + + return 0; +} + +/* release PM registrations */ +static void cti_pm_release(struct cti_drvdata *drvdata) +{ + if (drvdata->ctidev.cpu == -1) + return; + + cti_cpu_drvdata[drvdata->ctidev.cpu] = NULL; + if (--nr_cti_cpu == 0) { + cpu_pm_unregister_notifier(&cti_cpu_pm_nb); + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_CTI_STARTING); + } +} + +/** cti ect operations **/ +int cti_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) +{ + struct cti_drvdata *drvdata = csdev_to_cti_drvdata(csdev); + + return cti_enable_hw(drvdata); +} + +int cti_disable(struct coresight_device *csdev, struct coresight_path *path) +{ + struct cti_drvdata *drvdata = csdev_to_cti_drvdata(csdev); + + return cti_disable_hw(drvdata); +} + +static const struct coresight_ops_helper cti_ops_ect = { + .enable = cti_enable, + .disable = cti_disable, +}; + +static const struct coresight_ops cti_ops = { + .helper_ops = &cti_ops_ect, +}; + +/* + * Free up CTI specific resources + * called by dev->release, need to call down to underlying csdev release. + */ +static void cti_device_release(struct device *dev) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_drvdata *ect_item, *ect_tmp; + + mutex_lock(&ect_mutex); + cti_pm_release(drvdata); + + /* remove from the list */ + list_for_each_entry_safe(ect_item, ect_tmp, &ect_net, node) { + if (ect_item == drvdata) { + list_del(&ect_item->node); + break; + } + } + mutex_unlock(&ect_mutex); + + if (drvdata->csdev_release) + drvdata->csdev_release(dev); +} +static void cti_remove(struct amba_device *adev) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + mutex_lock(&ect_mutex); + cti_remove_conn_xrefs(drvdata); + mutex_unlock(&ect_mutex); + + coresight_unregister(drvdata->csdev); +} + +static int cti_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret = 0; + void __iomem *base; + struct device *dev = &adev->dev; + struct cti_drvdata *drvdata = NULL; + struct coresight_desc cti_desc; + struct coresight_platform_data *pdata = NULL; + struct resource *res = &adev->res; + + /* driver data*/ + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + cti_desc.access = CSDEV_ACCESS_IOMEM(base); + + dev_set_drvdata(dev, drvdata); + + /* default CTI device info */ + drvdata->ctidev.cpu = -1; + drvdata->ctidev.nr_trig_con = 0; + drvdata->ctidev.ctm_id = 0; + INIT_LIST_HEAD(&drvdata->ctidev.trig_cons); + + raw_spin_lock_init(&drvdata->spinlock); + + /* initialise CTI driver config values */ + cti_set_default_config(dev, drvdata); + + pdata = coresight_cti_get_platform_data(dev); + if (IS_ERR(pdata)) { + dev_err(dev, "coresight_cti_get_platform_data err\n"); + return PTR_ERR(pdata); + } + + /* default to powered - could change on PM notifications */ + drvdata->config.hw_powered = true; + + /* set up device name - will depend if cpu bound or otherwise */ + if (drvdata->ctidev.cpu >= 0) + cti_desc.name = devm_kasprintf(dev, GFP_KERNEL, "cti_cpu%d", + drvdata->ctidev.cpu); + else + cti_desc.name = coresight_alloc_device_name(&cti_sys_devs, dev); + if (!cti_desc.name) + return -ENOMEM; + + /* setup CPU power management handling for CPU bound CTI devices. */ + ret = cti_pm_setup(drvdata); + if (ret) + return ret; + + /* create dynamic attributes for connections */ + ret = cti_create_cons_sysfs(dev, drvdata); + if (ret) { + dev_err(dev, "%s: create dynamic sysfs entries failed\n", + cti_desc.name); + goto pm_release; + } + + /* set up coresight component description */ + cti_desc.pdata = pdata; + cti_desc.type = CORESIGHT_DEV_TYPE_HELPER; + cti_desc.subtype.helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI; + cti_desc.ops = &cti_ops; + cti_desc.groups = drvdata->ctidev.con_groups; + cti_desc.dev = dev; + + coresight_clear_self_claim_tag(&cti_desc.access); + drvdata->csdev = coresight_register(&cti_desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto pm_release; + } + + /* add to list of CTI devices */ + mutex_lock(&ect_mutex); + list_add(&drvdata->node, &ect_net); + /* set any cross references */ + cti_update_conn_xrefs(drvdata); + mutex_unlock(&ect_mutex); + + /* set up release chain */ + drvdata->csdev_release = drvdata->csdev->dev.release; + drvdata->csdev->dev.release = cti_device_release; + + /* all done - dec pm refcount */ + pm_runtime_put(&adev->dev); + dev_info(&drvdata->csdev->dev, "CTI initialized\n"); + return 0; + +pm_release: + cti_pm_release(drvdata); + return ret; +} + +static struct amba_cs_uci_id uci_id_cti[] = { + { + /* CTI UCI data */ + .devarch = 0x47701a14, /* CTI v2 */ + .devarch_mask = 0xfff0ffff, + .devtype = 0x00000014, /* maj(0x4-debug) min(0x1-ECT) */ + } +}; + +static const struct amba_id cti_ids[] = { + CS_AMBA_ID(0x000bb906), /* Coresight CTI (SoC 400), C-A72, C-A57 */ + CS_AMBA_ID(0x000bb922), /* CTI - C-A8 */ + CS_AMBA_ID(0x000bb9a8), /* CTI - C-A53 */ + CS_AMBA_ID(0x000bb9aa), /* CTI - C-A73 */ + CS_AMBA_UCI_ID(0x000bb9da, uci_id_cti), /* CTI - C-A35 */ + CS_AMBA_UCI_ID(0x000bb9ed, uci_id_cti), /* Coresight CTI (SoC 600) */ + { 0, 0, NULL }, +}; + +MODULE_DEVICE_TABLE(amba, cti_ids); + +static struct amba_driver cti_driver = { + .drv = { + .name = "coresight-cti", + .suppress_bind_attrs = true, + }, + .probe = cti_probe, + .remove = cti_remove, + .id_table = cti_ids, +}; + +static int __init cti_init(void) +{ + int ret; + + ret = amba_driver_register(&cti_driver); + if (ret) + pr_info("Error registering cti driver\n"); + coresight_set_cti_ops(&cti_assoc_ops); + return ret; +} + +static void __exit cti_exit(void) +{ + coresight_remove_cti_ops(); + amba_driver_unregister(&cti_driver); +} + +module_init(cti_init); +module_exit(cti_exit); + +MODULE_AUTHOR("Mike Leach <mike.leach@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight CTI Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-cti-platform.c b/drivers/hwtracing/coresight/coresight-cti-platform.c new file mode 100644 index 000000000000..d0ae10bf6128 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-platform.c @@ -0,0 +1,486 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019, The Linaro Limited. All rights reserved. + */ +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/of.h> +#include <linux/property.h> +#include <linux/slab.h> + +#include <dt-bindings/arm/coresight-cti-dt.h> + +#include "coresight-cti.h" +#include "coresight-priv.h" + +/* Number of CTI signals in the v8 architecturally defined connection */ +#define NR_V8PE_IN_SIGS 2 +#define NR_V8PE_OUT_SIGS 3 +#define NR_V8ETM_INOUT_SIGS 4 + +/* CTI device tree trigger connection node keyword */ +#define CTI_DT_CONNS "trig-conns" + +/* CTI device tree connection property keywords */ +#define CTI_DT_V8ARCH_COMPAT "arm,coresight-cti-v8-arch" +#define CTI_DT_CSDEV_ASSOC "arm,cs-dev-assoc" +#define CTI_DT_TRIGIN_SIGS "arm,trig-in-sigs" +#define CTI_DT_TRIGOUT_SIGS "arm,trig-out-sigs" +#define CTI_DT_TRIGIN_TYPES "arm,trig-in-types" +#define CTI_DT_TRIGOUT_TYPES "arm,trig-out-types" +#define CTI_DT_FILTER_OUT_SIGS "arm,trig-filters" +#define CTI_DT_CONN_NAME "arm,trig-conn-name" +#define CTI_DT_CTM_ID "arm,cti-ctm-id" + +#ifdef CONFIG_OF +/* + * CTI can be bound to a CPU, or a system device. + * CPU can be declared at the device top level or in a connections node + * so need to check relative to node not device. + */ +static int of_cti_get_cpu_at_node(const struct device_node *node) +{ + int cpu; + struct device_node *dn; + + if (node == NULL) + return -1; + + dn = of_parse_phandle(node, "cpu", 0); + /* CTI affinity defaults to no cpu */ + if (!dn) + return -1; + cpu = of_cpu_node_to_id(dn); + of_node_put(dn); + + /* No Affinity if no cpu nodes are found */ + return (cpu < 0) ? -1 : cpu; +} + +#else +static int of_cti_get_cpu_at_node(const struct device_node *node) +{ + return -1; +} + +#endif + +/* + * CTI can be bound to a CPU, or a system device. + * CPU can be declared at the device top level or in a connections node + * so need to check relative to node not device. + */ +static int cti_plat_get_cpu_at_node(struct fwnode_handle *fwnode) +{ + if (is_of_node(fwnode)) + return of_cti_get_cpu_at_node(to_of_node(fwnode)); + return -1; +} + +const char *cti_plat_get_node_name(struct fwnode_handle *fwnode) +{ + if (is_of_node(fwnode)) + return of_node_full_name(to_of_node(fwnode)); + return "unknown"; +} + +/* + * Extract a name from the fwnode. + * If the device associated with the node is a coresight_device, then return + * that name and the coresight_device pointer, otherwise return the node name. + */ +static const char * +cti_plat_get_csdev_or_node_name(struct fwnode_handle *fwnode, + struct coresight_device **csdev) +{ + const char *name = NULL; + *csdev = coresight_find_csdev_by_fwnode(fwnode); + if (*csdev) + name = dev_name(&(*csdev)->dev); + else + name = cti_plat_get_node_name(fwnode); + return name; +} + +static bool cti_plat_node_name_eq(struct fwnode_handle *fwnode, + const char *name) +{ + if (is_of_node(fwnode)) + return of_node_name_eq(to_of_node(fwnode), name); + return false; +} + +static int cti_plat_create_v8_etm_connection(struct device *dev, + struct cti_drvdata *drvdata) +{ + int ret = -ENOMEM, i; + struct fwnode_handle *root_fwnode, *cs_fwnode; + const char *assoc_name = NULL; + struct coresight_device *csdev; + struct cti_trig_con *tc = NULL; + + root_fwnode = dev_fwnode(dev); + if (IS_ERR_OR_NULL(root_fwnode)) + return -EINVAL; + + /* Can optionally have an etm node - return if not */ + cs_fwnode = fwnode_find_reference(root_fwnode, CTI_DT_CSDEV_ASSOC, 0); + if (IS_ERR(cs_fwnode)) + return 0; + + /* allocate memory */ + tc = cti_allocate_trig_con(dev, NR_V8ETM_INOUT_SIGS, + NR_V8ETM_INOUT_SIGS); + if (!tc) + goto create_v8_etm_out; + + /* build connection data */ + tc->con_in->used_mask = 0xF0; /* sigs <4,5,6,7> */ + tc->con_out->used_mask = 0xF0; /* sigs <4,5,6,7> */ + + /* + * The EXTOUT type signals from the ETM are connected to a set of input + * triggers on the CTI, the EXTIN being connected to output triggers. + */ + for (i = 0; i < NR_V8ETM_INOUT_SIGS; i++) { + tc->con_in->sig_types[i] = ETM_EXTOUT; + tc->con_out->sig_types[i] = ETM_EXTIN; + } + + /* + * We look to see if the ETM coresight device associated with this + * handle has been registered with the system - i.e. probed before + * this CTI. If so csdev will be non NULL and we can use the device + * name and pass the csdev to the connection entry function where + * the association will be recorded. + * If not, then simply record the name in the connection data, the + * probing of the ETM will call into the CTI driver API to update the + * association then. + */ + assoc_name = cti_plat_get_csdev_or_node_name(cs_fwnode, &csdev); + ret = cti_add_connection_entry(dev, drvdata, tc, csdev, assoc_name); + +create_v8_etm_out: + fwnode_handle_put(cs_fwnode); + return ret; +} + +/* + * Create an architecturally defined v8 connection + * must have a cpu, can have an ETM. + */ +static int cti_plat_create_v8_connections(struct device *dev, + struct cti_drvdata *drvdata) +{ + struct cti_device *cti_dev = &drvdata->ctidev; + struct cti_trig_con *tc = NULL; + int cpuid = 0; + char cpu_name_str[16]; + int ret = -ENOMEM; + + /* Must have a cpu node */ + cpuid = cti_plat_get_cpu_at_node(dev_fwnode(dev)); + if (cpuid < 0) { + dev_warn(dev, + "ARM v8 architectural CTI connection: missing cpu\n"); + return -EINVAL; + } + cti_dev->cpu = cpuid; + + /* Allocate the v8 cpu connection memory */ + tc = cti_allocate_trig_con(dev, NR_V8PE_IN_SIGS, NR_V8PE_OUT_SIGS); + if (!tc) + goto of_create_v8_out; + + /* Set the v8 PE CTI connection data */ + tc->con_in->used_mask = 0x3; /* sigs <0 1> */ + tc->con_in->sig_types[0] = PE_DBGTRIGGER; + tc->con_in->sig_types[1] = PE_PMUIRQ; + tc->con_out->used_mask = 0x7; /* sigs <0 1 2 > */ + tc->con_out->sig_types[0] = PE_EDBGREQ; + tc->con_out->sig_types[1] = PE_DBGRESTART; + tc->con_out->sig_types[2] = PE_CTIIRQ; + scnprintf(cpu_name_str, sizeof(cpu_name_str), "cpu%d", cpuid); + + ret = cti_add_connection_entry(dev, drvdata, tc, NULL, cpu_name_str); + if (ret) + goto of_create_v8_out; + + /* Create the v8 ETM associated connection */ + ret = cti_plat_create_v8_etm_connection(dev, drvdata); + if (ret) + goto of_create_v8_out; + + /* filter pe_edbgreq - PE trigout sig <0> */ + drvdata->config.trig_out_filter |= 0x1; + +of_create_v8_out: + return ret; +} + +static int cti_plat_check_v8_arch_compatible(struct device *dev) +{ + struct fwnode_handle *fwnode = dev_fwnode(dev); + + if (is_of_node(fwnode)) + return of_device_is_compatible(to_of_node(fwnode), + CTI_DT_V8ARCH_COMPAT); + return 0; +} + +static int cti_plat_count_sig_elements(const struct fwnode_handle *fwnode, + const char *name) +{ + int nr_elem = fwnode_property_count_u32(fwnode, name); + + return (nr_elem < 0 ? 0 : nr_elem); +} + +static int cti_plat_read_trig_group(struct cti_trig_grp *tgrp, + const struct fwnode_handle *fwnode, + const char *grp_name) +{ + int idx, err = 0; + u32 *values; + + if (!tgrp->nr_sigs) + return 0; + + values = kcalloc(tgrp->nr_sigs, sizeof(u32), GFP_KERNEL); + if (!values) + return -ENOMEM; + + err = fwnode_property_read_u32_array(fwnode, grp_name, + values, tgrp->nr_sigs); + + if (!err) { + /* set the signal usage mask */ + for (idx = 0; idx < tgrp->nr_sigs; idx++) + tgrp->used_mask |= BIT(values[idx]); + } + + kfree(values); + return err; +} + +static int cti_plat_read_trig_types(struct cti_trig_grp *tgrp, + const struct fwnode_handle *fwnode, + const char *type_name) +{ + int items, err = 0, nr_sigs; + u32 *values = NULL, i; + + /* allocate an array according to number of signals in connection */ + nr_sigs = tgrp->nr_sigs; + if (!nr_sigs) + return 0; + + /* see if any types have been included in the device description */ + items = cti_plat_count_sig_elements(fwnode, type_name); + if (items > nr_sigs) + return -EINVAL; + + /* need an array to store the values iff there are any */ + if (items) { + values = kcalloc(items, sizeof(u32), GFP_KERNEL); + if (!values) + return -ENOMEM; + + err = fwnode_property_read_u32_array(fwnode, type_name, + values, items); + if (err) + goto read_trig_types_out; + } + + /* + * Match type id to signal index, 1st type to 1st index etc. + * If fewer types than signals default remainder to GEN_IO. + */ + for (i = 0; i < nr_sigs; i++) { + if (i < items) { + tgrp->sig_types[i] = + values[i] < CTI_TRIG_MAX ? values[i] : GEN_IO; + } else { + tgrp->sig_types[i] = GEN_IO; + } + } + +read_trig_types_out: + kfree(values); + return err; +} + +static int cti_plat_process_filter_sigs(struct cti_drvdata *drvdata, + const struct fwnode_handle *fwnode) +{ + struct cti_trig_grp *tg = NULL; + int err = 0, nr_filter_sigs; + + nr_filter_sigs = cti_plat_count_sig_elements(fwnode, + CTI_DT_FILTER_OUT_SIGS); + if (nr_filter_sigs == 0) + return 0; + + if (nr_filter_sigs > drvdata->config.nr_trig_max) + return -EINVAL; + + tg = kzalloc(sizeof(*tg), GFP_KERNEL); + if (!tg) + return -ENOMEM; + + err = cti_plat_read_trig_group(tg, fwnode, CTI_DT_FILTER_OUT_SIGS); + if (!err) + drvdata->config.trig_out_filter |= tg->used_mask; + + kfree(tg); + return err; +} + +static int cti_plat_create_connection(struct device *dev, + struct cti_drvdata *drvdata, + struct fwnode_handle *fwnode) +{ + struct cti_trig_con *tc = NULL; + int cpuid = -1, err = 0; + struct coresight_device *csdev = NULL; + const char *assoc_name = "unknown"; + char cpu_name_str[16]; + int nr_sigs_in, nr_sigs_out; + + /* look to see how many in and out signals we have */ + nr_sigs_in = cti_plat_count_sig_elements(fwnode, CTI_DT_TRIGIN_SIGS); + nr_sigs_out = cti_plat_count_sig_elements(fwnode, CTI_DT_TRIGOUT_SIGS); + + if ((nr_sigs_in > drvdata->config.nr_trig_max) || + (nr_sigs_out > drvdata->config.nr_trig_max)) + return -EINVAL; + + tc = cti_allocate_trig_con(dev, nr_sigs_in, nr_sigs_out); + if (!tc) + return -ENOMEM; + + /* look for the signals properties. */ + err = cti_plat_read_trig_group(tc->con_in, fwnode, + CTI_DT_TRIGIN_SIGS); + if (err) + goto create_con_err; + + err = cti_plat_read_trig_types(tc->con_in, fwnode, + CTI_DT_TRIGIN_TYPES); + if (err) + goto create_con_err; + + err = cti_plat_read_trig_group(tc->con_out, fwnode, + CTI_DT_TRIGOUT_SIGS); + if (err) + goto create_con_err; + + err = cti_plat_read_trig_types(tc->con_out, fwnode, + CTI_DT_TRIGOUT_TYPES); + if (err) + goto create_con_err; + + err = cti_plat_process_filter_sigs(drvdata, fwnode); + if (err) + goto create_con_err; + + /* read the connection name if set - may be overridden by later */ + fwnode_property_read_string(fwnode, CTI_DT_CONN_NAME, &assoc_name); + + /* associated cpu ? */ + cpuid = cti_plat_get_cpu_at_node(fwnode); + if (cpuid >= 0) { + drvdata->ctidev.cpu = cpuid; + scnprintf(cpu_name_str, sizeof(cpu_name_str), "cpu%d", cpuid); + assoc_name = cpu_name_str; + } else { + /* associated device ? */ + struct fwnode_handle *cs_fwnode = fwnode_find_reference(fwnode, + CTI_DT_CSDEV_ASSOC, + 0); + if (!IS_ERR(cs_fwnode)) { + assoc_name = cti_plat_get_csdev_or_node_name(cs_fwnode, + &csdev); + fwnode_handle_put(cs_fwnode); + } + } + /* set up a connection */ + err = cti_add_connection_entry(dev, drvdata, tc, csdev, assoc_name); + +create_con_err: + return err; +} + +static int cti_plat_create_impdef_connections(struct device *dev, + struct cti_drvdata *drvdata) +{ + int rc = 0; + + if (IS_ERR_OR_NULL(dev_fwnode(dev))) + return -EINVAL; + + device_for_each_child_node_scoped(dev, child) { + if (cti_plat_node_name_eq(child, CTI_DT_CONNS)) + rc = cti_plat_create_connection(dev, drvdata, child); + if (rc != 0) + break; + } + + return rc; +} + +/* get the hardware configuration & connection data. */ +static int cti_plat_get_hw_data(struct device *dev, struct cti_drvdata *drvdata) +{ + int rc = 0; + struct cti_device *cti_dev = &drvdata->ctidev; + + /* get any CTM ID - defaults to 0 */ + device_property_read_u32(dev, CTI_DT_CTM_ID, &cti_dev->ctm_id); + + /* check for a v8 architectural CTI device */ + if (cti_plat_check_v8_arch_compatible(dev)) + rc = cti_plat_create_v8_connections(dev, drvdata); + else + rc = cti_plat_create_impdef_connections(dev, drvdata); + if (rc) + return rc; + + /* if no connections, just add a single default based on max IN-OUT */ + if (cti_dev->nr_trig_con == 0) + rc = cti_add_default_connection(dev, drvdata); + return rc; +} + +struct coresight_platform_data * +coresight_cti_get_platform_data(struct device *dev) +{ + int ret = -ENOENT; + struct coresight_platform_data *pdata = NULL; + struct fwnode_handle *fwnode = dev_fwnode(dev); + struct cti_drvdata *drvdata = dev_get_drvdata(dev); + + if (IS_ERR_OR_NULL(fwnode)) + goto error; + + /* + * Alloc platform data but leave it zero init. CTI does not use the + * same connection infrastructuree as trace path components but an + * empty struct enables us to use the standard coresight component + * registration code. + */ + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) { + ret = -ENOMEM; + goto error; + } + + /* get some CTI specifics */ + ret = cti_plat_get_hw_data(dev, drvdata); + + if (!ret) + return pdata; +error: + return ERR_PTR(ret); +} diff --git a/drivers/hwtracing/coresight/coresight-cti-sysfs.c b/drivers/hwtracing/coresight/coresight-cti-sysfs.c new file mode 100644 index 000000000000..572b80ee96fb --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-sysfs.c @@ -0,0 +1,1187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/atomic.h> +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/sysfs.h> + +#include "coresight-cti.h" + +/* + * Declare the number of static declared attribute groups + * Value includes groups + NULL value at end of table. + */ +#define CORESIGHT_CTI_STATIC_GROUPS_MAX 5 + +/* + * List of trigger signal type names. Match the constants declared in + * include\dt-bindings\arm\coresight-cti-dt.h + */ +static const char * const sig_type_names[] = { + "genio", /* GEN_IO */ + "intreq", /* GEN_INTREQ */ + "intack", /* GEN_INTACK */ + "haltreq", /* GEN_HALTREQ */ + "restartreq", /* GEN_RESTARTREQ */ + "pe_edbgreq", /* PE_EDBGREQ */ + "pe_dbgrestart",/* PE_DBGRESTART */ + "pe_ctiirq", /* PE_CTIIRQ */ + "pe_pmuirq", /* PE_PMUIRQ */ + "pe_dbgtrigger",/* PE_DBGTRIGGER */ + "etm_extout", /* ETM_EXTOUT */ + "etm_extin", /* ETM_EXTIN */ + "snk_full", /* SNK_FULL */ + "snk_acqcomp", /* SNK_ACQCOMP */ + "snk_flushcomp",/* SNK_FLUSHCOMP */ + "snk_flushin", /* SNK_FLUSHIN */ + "snk_trigin", /* SNK_TRIGIN */ + "stm_asyncout", /* STM_ASYNCOUT */ + "stm_tout_spte",/* STM_TOUT_SPTE */ + "stm_tout_sw", /* STM_TOUT_SW */ + "stm_tout_hete",/* STM_TOUT_HETE */ + "stm_hwevent", /* STM_HWEVENT */ + "ela_tstart", /* ELA_TSTART */ + "ela_tstop", /* ELA_TSTOP */ + "ela_dbgreq", /* ELA_DBGREQ */ +}; + +/* Show function pointer used in the connections dynamic declared attributes*/ +typedef ssize_t (*p_show_fn)(struct device *dev, struct device_attribute *attr, + char *buf); + +/* Connection attribute types */ +enum cti_conn_attr_type { + CTI_CON_ATTR_NAME, + CTI_CON_ATTR_TRIGIN_SIG, + CTI_CON_ATTR_TRIGOUT_SIG, + CTI_CON_ATTR_TRIGIN_TYPES, + CTI_CON_ATTR_TRIGOUT_TYPES, + CTI_CON_ATTR_MAX, +}; + +/* Names for the connection attributes */ +static const char * const con_attr_names[CTI_CON_ATTR_MAX] = { + "name", + "in_signals", + "out_signals", + "in_types", + "out_types", +}; + +/* basic attributes */ +static ssize_t enable_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int enable_req; + bool enabled, powered; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + enable_req = drvdata->config.enable_req_count; + powered = drvdata->config.hw_powered; + enabled = drvdata->config.hw_enabled; + raw_spin_unlock(&drvdata->spinlock); + + if (powered) + return sprintf(buf, "%d\n", enabled); + else + return sprintf(buf, "%d\n", !!enable_req); +} + +static ssize_t enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret = 0; + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val) { + ret = pm_runtime_resume_and_get(dev->parent); + if (ret) + return ret; + ret = cti_enable(drvdata->csdev, CS_MODE_SYSFS, NULL); + if (ret) + pm_runtime_put(dev->parent); + } else { + ret = cti_disable(drvdata->csdev, NULL); + if (!ret) + pm_runtime_put(dev->parent); + } + + if (ret) + return ret; + return size; +} +static DEVICE_ATTR_RW(enable); + +static ssize_t powered_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + bool powered; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + powered = drvdata->config.hw_powered; + raw_spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%d\n", powered); +} +static DEVICE_ATTR_RO(powered); + +static ssize_t ctmid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sprintf(buf, "%d\n", drvdata->ctidev.ctm_id); +} +static DEVICE_ATTR_RO(ctmid); + +static ssize_t nr_trigger_cons_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sprintf(buf, "%d\n", drvdata->ctidev.nr_trig_con); +} +static DEVICE_ATTR_RO(nr_trigger_cons); + +/* attribute and group sysfs tables. */ +static struct attribute *coresight_cti_attrs[] = { + &dev_attr_enable.attr, + &dev_attr_powered.attr, + &dev_attr_ctmid.attr, + &dev_attr_nr_trigger_cons.attr, + NULL, +}; + +/* register based attributes */ + +/* Read registers with power check only (no enable check). */ +static ssize_t coresight_cti_reg_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cs_off_attribute *cti_attr = container_of(attr, struct cs_off_attribute, attr); + u32 val = 0; + + pm_runtime_get_sync(dev->parent); + raw_spin_lock(&drvdata->spinlock); + if (drvdata->config.hw_powered) + val = readl_relaxed(drvdata->base + cti_attr->off); + raw_spin_unlock(&drvdata->spinlock); + pm_runtime_put_sync(dev->parent); + return sysfs_emit(buf, "0x%x\n", val); +} + +/* Write registers with power check only (no enable check). */ +static __maybe_unused ssize_t coresight_cti_reg_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cs_off_attribute *cti_attr = container_of(attr, struct cs_off_attribute, attr); + unsigned long val = 0; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + pm_runtime_get_sync(dev->parent); + raw_spin_lock(&drvdata->spinlock); + if (drvdata->config.hw_powered) + cti_write_single_reg(drvdata, cti_attr->off, val); + raw_spin_unlock(&drvdata->spinlock); + pm_runtime_put_sync(dev->parent); + return size; +} + +#define coresight_cti_reg(name, offset) \ + (&((struct cs_off_attribute[]) { \ + { \ + __ATTR(name, 0444, coresight_cti_reg_show, NULL), \ + offset \ + } \ + })[0].attr.attr) + +#define coresight_cti_reg_rw(name, offset) \ + (&((struct cs_off_attribute[]) { \ + { \ + __ATTR(name, 0644, coresight_cti_reg_show, \ + coresight_cti_reg_store), \ + offset \ + } \ + })[0].attr.attr) + +#define coresight_cti_reg_wo(name, offset) \ + (&((struct cs_off_attribute[]) { \ + { \ + __ATTR(name, 0200, NULL, coresight_cti_reg_store), \ + offset \ + } \ + })[0].attr.attr) + +/* coresight management registers */ +static struct attribute *coresight_cti_mgmt_attrs[] = { + coresight_cti_reg(devaff0, CTIDEVAFF0), + coresight_cti_reg(devaff1, CTIDEVAFF1), + coresight_cti_reg(authstatus, CORESIGHT_AUTHSTATUS), + coresight_cti_reg(devarch, CORESIGHT_DEVARCH), + coresight_cti_reg(devid, CORESIGHT_DEVID), + coresight_cti_reg(devtype, CORESIGHT_DEVTYPE), + coresight_cti_reg(pidr0, CORESIGHT_PERIPHIDR0), + coresight_cti_reg(pidr1, CORESIGHT_PERIPHIDR1), + coresight_cti_reg(pidr2, CORESIGHT_PERIPHIDR2), + coresight_cti_reg(pidr3, CORESIGHT_PERIPHIDR3), + coresight_cti_reg(pidr4, CORESIGHT_PERIPHIDR4), + NULL, +}; + +/* CTI low level programming registers */ + +/* + * Show a simple 32 bit value if enabled and powered. + * If inaccessible & pcached_val not NULL then show cached value. + */ +static ssize_t cti_reg32_show(struct device *dev, char *buf, + u32 *pcached_val, int reg_offset) +{ + u32 val = 0; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + if ((reg_offset >= 0) && cti_active(config)) { + CS_UNLOCK(drvdata->base); + val = readl_relaxed(drvdata->base + reg_offset); + if (pcached_val) + *pcached_val = val; + CS_LOCK(drvdata->base); + } else if (pcached_val) { + val = *pcached_val; + } + raw_spin_unlock(&drvdata->spinlock); + return sprintf(buf, "%#x\n", val); +} + +/* + * Store a simple 32 bit value. + * If pcached_val not NULL, then copy to here too, + * if reg_offset >= 0 then write through if enabled. + */ +static ssize_t cti_reg32_store(struct device *dev, const char *buf, + size_t size, u32 *pcached_val, int reg_offset) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + /* local store */ + if (pcached_val) + *pcached_val = (u32)val; + + /* write through if offset and enabled */ + if ((reg_offset >= 0) && cti_active(config)) + cti_write_single_reg(drvdata, reg_offset, val); + raw_spin_unlock(&drvdata->spinlock); + return size; +} + +/* Standard macro for simple rw cti config registers */ +#define cti_config_reg32_rw(name, cfgname, offset) \ +static ssize_t name##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *buf) \ +{ \ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); \ + return cti_reg32_show(dev, buf, \ + &drvdata->config.cfgname, offset); \ +} \ + \ +static ssize_t name##_store(struct device *dev, \ + struct device_attribute *attr, \ + const char *buf, size_t size) \ +{ \ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); \ + return cti_reg32_store(dev, buf, size, \ + &drvdata->config.cfgname, offset); \ +} \ +static DEVICE_ATTR_RW(name) + +static ssize_t inout_sel_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u32 val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = (u32)drvdata->config.ctiinout_sel; + return sprintf(buf, "%d\n", val); +} + +static ssize_t inout_sel_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + if (val > (CTIINOUTEN_MAX - 1)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + drvdata->config.ctiinout_sel = val; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(inout_sel); + +static ssize_t inen_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + int index; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + index = drvdata->config.ctiinout_sel; + val = drvdata->config.ctiinen[index]; + raw_spin_unlock(&drvdata->spinlock); + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t inen_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + int index; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + index = config->ctiinout_sel; + config->ctiinen[index] = val; + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIINEN(index), val); + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(inen); + +static ssize_t outen_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + int index; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + index = drvdata->config.ctiinout_sel; + val = drvdata->config.ctiouten[index]; + raw_spin_unlock(&drvdata->spinlock); + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t outen_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + int index; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + index = config->ctiinout_sel; + config->ctiouten[index] = val; + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIOUTEN(index), val); + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(outen); + +static ssize_t intack_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + cti_write_intack(dev, val); + return size; +} +static DEVICE_ATTR_WO(intack); + +cti_config_reg32_rw(gate, ctigate, CTIGATE); +cti_config_reg32_rw(asicctl, asicctl, ASICCTL); +cti_config_reg32_rw(appset, ctiappset, CTIAPPSET); + +static ssize_t appclear_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + + /* a 1'b1 in appclr clears down the same bit in appset*/ + config->ctiappset &= ~val; + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIAPPCLEAR, val); + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_WO(appclear); + +static ssize_t apppulse_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIAPPPULSE, val); + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_WO(apppulse); + +/* + * Define CONFIG_CORESIGHT_CTI_INTEGRATION_REGS to enable the access to the + * integration control registers. Normally only used to investigate connection + * data. + */ +static struct attribute *coresight_cti_regs_attrs[] = { + &dev_attr_inout_sel.attr, + &dev_attr_inen.attr, + &dev_attr_outen.attr, + &dev_attr_gate.attr, + &dev_attr_asicctl.attr, + &dev_attr_intack.attr, + &dev_attr_appset.attr, + &dev_attr_appclear.attr, + &dev_attr_apppulse.attr, + coresight_cti_reg(triginstatus, CTITRIGINSTATUS), + coresight_cti_reg(trigoutstatus, CTITRIGOUTSTATUS), + coresight_cti_reg(chinstatus, CTICHINSTATUS), + coresight_cti_reg(choutstatus, CTICHOUTSTATUS), +#ifdef CONFIG_CORESIGHT_CTI_INTEGRATION_REGS + coresight_cti_reg_rw(itctrl, CORESIGHT_ITCTRL), + coresight_cti_reg(ittrigin, ITTRIGIN), + coresight_cti_reg(itchin, ITCHIN), + coresight_cti_reg_rw(ittrigout, ITTRIGOUT), + coresight_cti_reg_rw(itchout, ITCHOUT), + coresight_cti_reg(itchoutack, ITCHOUTACK), + coresight_cti_reg(ittrigoutack, ITTRIGOUTACK), + coresight_cti_reg_wo(ittriginack, ITTRIGINACK), + coresight_cti_reg_wo(itchinack, ITCHINACK), +#endif + NULL, +}; + +/* CTI channel x-trigger programming */ +static int +cti_trig_op_parse(struct device *dev, enum cti_chan_op op, + enum cti_trig_dir dir, const char *buf, size_t size) +{ + u32 chan_idx; + u32 trig_idx; + int items, err = -EINVAL; + + /* extract chan idx and trigger idx */ + items = sscanf(buf, "%d %d", &chan_idx, &trig_idx); + if (items == 2) { + err = cti_channel_trig_op(dev, op, dir, chan_idx, trig_idx); + if (!err) + err = size; + } + return err; +} + +static ssize_t trigin_attach_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + return cti_trig_op_parse(dev, CTI_CHAN_ATTACH, CTI_TRIG_IN, + buf, size); +} +static DEVICE_ATTR_WO(trigin_attach); + +static ssize_t trigin_detach_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + return cti_trig_op_parse(dev, CTI_CHAN_DETACH, CTI_TRIG_IN, + buf, size); +} +static DEVICE_ATTR_WO(trigin_detach); + +static ssize_t trigout_attach_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + return cti_trig_op_parse(dev, CTI_CHAN_ATTACH, CTI_TRIG_OUT, + buf, size); +} +static DEVICE_ATTR_WO(trigout_attach); + +static ssize_t trigout_detach_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + return cti_trig_op_parse(dev, CTI_CHAN_DETACH, CTI_TRIG_OUT, + buf, size); +} +static DEVICE_ATTR_WO(trigout_detach); + + +static ssize_t chan_gate_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int err = 0, channel = 0; + + if (kstrtoint(buf, 0, &channel)) + return -EINVAL; + + err = cti_channel_gate_op(dev, CTI_GATE_CHAN_ENABLE, channel); + return err ? err : size; +} + +static ssize_t chan_gate_enable_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + unsigned long ctigate_bitmask = cfg->ctigate; + int size = 0; + + if (cfg->ctigate == 0) + size = sprintf(buf, "\n"); + else + size = bitmap_print_to_pagebuf(true, buf, &ctigate_bitmask, + cfg->nr_ctm_channels); + return size; +} +static DEVICE_ATTR_RW(chan_gate_enable); + +static ssize_t chan_gate_disable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int err = 0, channel = 0; + + if (kstrtoint(buf, 0, &channel)) + return -EINVAL; + + err = cti_channel_gate_op(dev, CTI_GATE_CHAN_DISABLE, channel); + return err ? err : size; +} +static DEVICE_ATTR_WO(chan_gate_disable); + +static int +chan_op_parse(struct device *dev, enum cti_chan_set_op op, const char *buf) +{ + int err = 0, channel = 0; + + if (kstrtoint(buf, 0, &channel)) + return -EINVAL; + + err = cti_channel_setop(dev, op, channel); + return err; + +} + +static ssize_t chan_set_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int err = chan_op_parse(dev, CTI_CHAN_SET, buf); + + return err ? err : size; +} +static DEVICE_ATTR_WO(chan_set); + +static ssize_t chan_clear_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int err = chan_op_parse(dev, CTI_CHAN_CLR, buf); + + return err ? err : size; +} +static DEVICE_ATTR_WO(chan_clear); + +static ssize_t chan_pulse_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int err = chan_op_parse(dev, CTI_CHAN_PULSE, buf); + + return err ? err : size; +} +static DEVICE_ATTR_WO(chan_pulse); + +static ssize_t trig_filter_enable_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u32 val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + val = drvdata->config.trig_filter_enable; + raw_spin_unlock(&drvdata->spinlock); + return sprintf(buf, "%d\n", val); +} + +static ssize_t trig_filter_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + drvdata->config.trig_filter_enable = !!val; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(trig_filter_enable); + +static ssize_t trigout_filtered_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + int size = 0, nr_trig_max = cfg->nr_trig_max; + unsigned long mask = cfg->trig_out_filter; + + if (mask) + size = bitmap_print_to_pagebuf(true, buf, &mask, nr_trig_max); + return size; +} +static DEVICE_ATTR_RO(trigout_filtered); + +/* clear all xtrigger / channel programming */ +static ssize_t chan_xtrigs_reset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int i; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + + /* clear the CTI trigger / channel programming registers */ + for (i = 0; i < config->nr_trig_max; i++) { + config->ctiinen[i] = 0; + config->ctiouten[i] = 0; + } + + /* clear the other regs */ + config->ctigate = GENMASK(config->nr_ctm_channels - 1, 0); + config->asicctl = 0; + config->ctiappset = 0; + config->ctiinout_sel = 0; + config->xtrig_rchan_sel = 0; + + /* if enabled then write through */ + if (cti_active(config)) + cti_write_all_hw_regs(drvdata); + + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_WO(chan_xtrigs_reset); + +/* + * Write to select a channel to view, read to display the + * cross triggers for the selected channel. + */ +static ssize_t chan_xtrigs_sel_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + if (val > (drvdata->config.nr_ctm_channels - 1)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + drvdata->config.xtrig_rchan_sel = val; + raw_spin_unlock(&drvdata->spinlock); + return size; +} + +static ssize_t chan_xtrigs_sel_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + + raw_spin_lock(&drvdata->spinlock); + val = drvdata->config.xtrig_rchan_sel; + raw_spin_unlock(&drvdata->spinlock); + + return sprintf(buf, "%ld\n", val); +} +static DEVICE_ATTR_RW(chan_xtrigs_sel); + +static ssize_t chan_xtrigs_in_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + int used = 0, reg_idx; + int nr_trig_max = drvdata->config.nr_trig_max; + u32 chan_mask = BIT(cfg->xtrig_rchan_sel); + + for (reg_idx = 0; reg_idx < nr_trig_max; reg_idx++) { + if (chan_mask & cfg->ctiinen[reg_idx]) + used += sprintf(buf + used, "%d ", reg_idx); + } + + used += sprintf(buf + used, "\n"); + return used; +} +static DEVICE_ATTR_RO(chan_xtrigs_in); + +static ssize_t chan_xtrigs_out_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + int used = 0, reg_idx; + int nr_trig_max = drvdata->config.nr_trig_max; + u32 chan_mask = BIT(cfg->xtrig_rchan_sel); + + for (reg_idx = 0; reg_idx < nr_trig_max; reg_idx++) { + if (chan_mask & cfg->ctiouten[reg_idx]) + used += sprintf(buf + used, "%d ", reg_idx); + } + + used += sprintf(buf + used, "\n"); + return used; +} +static DEVICE_ATTR_RO(chan_xtrigs_out); + +static ssize_t print_chan_list(struct device *dev, + char *buf, bool inuse) +{ + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *config = &drvdata->config; + int size, i; + unsigned long inuse_bits = 0, chan_mask; + + /* scan regs to get bitmap of channels in use. */ + raw_spin_lock(&drvdata->spinlock); + for (i = 0; i < config->nr_trig_max; i++) { + inuse_bits |= config->ctiinen[i]; + inuse_bits |= config->ctiouten[i]; + } + raw_spin_unlock(&drvdata->spinlock); + + /* inverse bits if printing free channels */ + if (!inuse) + inuse_bits = ~inuse_bits; + + /* list of channels, or 'none' */ + chan_mask = GENMASK(config->nr_ctm_channels - 1, 0); + if (inuse_bits & chan_mask) + size = bitmap_print_to_pagebuf(true, buf, &inuse_bits, + config->nr_ctm_channels); + else + size = sprintf(buf, "\n"); + return size; +} + +static ssize_t chan_inuse_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return print_chan_list(dev, buf, true); +} +static DEVICE_ATTR_RO(chan_inuse); + +static ssize_t chan_free_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return print_chan_list(dev, buf, false); +} +static DEVICE_ATTR_RO(chan_free); + +static struct attribute *coresight_cti_channel_attrs[] = { + &dev_attr_trigin_attach.attr, + &dev_attr_trigin_detach.attr, + &dev_attr_trigout_attach.attr, + &dev_attr_trigout_detach.attr, + &dev_attr_trig_filter_enable.attr, + &dev_attr_trigout_filtered.attr, + &dev_attr_chan_gate_enable.attr, + &dev_attr_chan_gate_disable.attr, + &dev_attr_chan_set.attr, + &dev_attr_chan_clear.attr, + &dev_attr_chan_pulse.attr, + &dev_attr_chan_inuse.attr, + &dev_attr_chan_free.attr, + &dev_attr_chan_xtrigs_sel.attr, + &dev_attr_chan_xtrigs_in.attr, + &dev_attr_chan_xtrigs_out.attr, + &dev_attr_chan_xtrigs_reset.attr, + NULL, +}; + +/* Create the connections trigger groups and attrs dynamically */ +/* + * Each connection has dynamic group triggers<N> + name, trigin/out sigs/types + * attributes, + each device has static nr_trigger_cons giving the number + * of groups. e.g. in sysfs:- + * /cti_<name>/triggers0 + * /cti_<name>/triggers1 + * /cti_<name>/nr_trigger_cons + * where nr_trigger_cons = 2 + */ +static ssize_t con_name_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr = + container_of(attr, struct dev_ext_attribute, attr); + struct cti_trig_con *con = (struct cti_trig_con *)ext_attr->var; + + return sprintf(buf, "%s\n", con->con_dev_name); +} + +static ssize_t trigin_sig_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr = + container_of(attr, struct dev_ext_attribute, attr); + struct cti_trig_con *con = (struct cti_trig_con *)ext_attr->var; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + unsigned long mask = con->con_in->used_mask; + + return bitmap_print_to_pagebuf(true, buf, &mask, cfg->nr_trig_max); +} + +static ssize_t trigout_sig_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr = + container_of(attr, struct dev_ext_attribute, attr); + struct cti_trig_con *con = (struct cti_trig_con *)ext_attr->var; + struct cti_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct cti_config *cfg = &drvdata->config; + unsigned long mask = con->con_out->used_mask; + + return bitmap_print_to_pagebuf(true, buf, &mask, cfg->nr_trig_max); +} + +/* convert a sig type id to a name */ +static const char * +cti_sig_type_name(struct cti_trig_con *con, int used_count, bool in) +{ + int idx = 0; + struct cti_trig_grp *grp = in ? con->con_in : con->con_out; + + if (used_count < grp->nr_sigs) + idx = grp->sig_types[used_count]; + return sig_type_names[idx]; +} + +static ssize_t trigin_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr = + container_of(attr, struct dev_ext_attribute, attr); + struct cti_trig_con *con = (struct cti_trig_con *)ext_attr->var; + int sig_idx, used = 0; + const char *name; + + for (sig_idx = 0; sig_idx < con->con_in->nr_sigs; sig_idx++) { + name = cti_sig_type_name(con, sig_idx, true); + used += sprintf(buf + used, "%s ", name); + } + used += sprintf(buf + used, "\n"); + return used; +} + +static ssize_t trigout_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr = + container_of(attr, struct dev_ext_attribute, attr); + struct cti_trig_con *con = (struct cti_trig_con *)ext_attr->var; + int sig_idx, used = 0; + const char *name; + + for (sig_idx = 0; sig_idx < con->con_out->nr_sigs; sig_idx++) { + name = cti_sig_type_name(con, sig_idx, false); + used += sprintf(buf + used, "%s ", name); + } + used += sprintf(buf + used, "\n"); + return used; +} + +/* + * Array of show function names declared above to allow selection + * for the connection attributes + */ +static p_show_fn show_fns[CTI_CON_ATTR_MAX] = { + con_name_show, + trigin_sig_show, + trigout_sig_show, + trigin_type_show, + trigout_type_show, +}; + +static int cti_create_con_sysfs_attr(struct device *dev, + struct cti_trig_con *con, + enum cti_conn_attr_type attr_type, + int attr_idx) +{ + struct dev_ext_attribute *eattr; + char *name; + + eattr = devm_kzalloc(dev, sizeof(struct dev_ext_attribute), + GFP_KERNEL); + if (eattr) { + name = devm_kstrdup(dev, con_attr_names[attr_type], + GFP_KERNEL); + if (name) { + /* fill out the underlying attribute struct */ + eattr->attr.attr.name = name; + eattr->attr.attr.mode = 0444; + + /* now the device_attribute struct */ + eattr->attr.show = show_fns[attr_type]; + } else { + return -ENOMEM; + } + } else { + return -ENOMEM; + } + eattr->var = con; + con->con_attrs[attr_idx] = &eattr->attr.attr; + /* + * Initialize the dynamically allocated attribute + * to avoid LOCKDEP splat. See include/linux/sysfs.h + * for more details. + */ + sysfs_attr_init(con->con_attrs[attr_idx]); + + return 0; +} + +static struct attribute_group * +cti_create_con_sysfs_group(struct device *dev, struct cti_device *ctidev, + int con_idx, struct cti_trig_con *tc) +{ + struct attribute_group *group = NULL; + int grp_idx; + + group = devm_kzalloc(dev, sizeof(struct attribute_group), GFP_KERNEL); + if (!group) + return NULL; + + group->name = devm_kasprintf(dev, GFP_KERNEL, "triggers%d", con_idx); + if (!group->name) + return NULL; + + grp_idx = con_idx + CORESIGHT_CTI_STATIC_GROUPS_MAX - 1; + ctidev->con_groups[grp_idx] = group; + tc->attr_group = group; + return group; +} + +/* create a triggers connection group and the attributes for that group */ +static int cti_create_con_attr_set(struct device *dev, int con_idx, + struct cti_device *ctidev, + struct cti_trig_con *tc) +{ + struct attribute_group *attr_group = NULL; + int attr_idx = 0; + int err = -ENOMEM; + + attr_group = cti_create_con_sysfs_group(dev, ctidev, con_idx, tc); + if (!attr_group) + return -ENOMEM; + + /* allocate NULL terminated array of attributes */ + tc->con_attrs = devm_kcalloc(dev, CTI_CON_ATTR_MAX + 1, + sizeof(struct attribute *), GFP_KERNEL); + if (!tc->con_attrs) + return -ENOMEM; + + err = cti_create_con_sysfs_attr(dev, tc, CTI_CON_ATTR_NAME, + attr_idx++); + if (err) + return err; + + if (tc->con_in->nr_sigs > 0) { + err = cti_create_con_sysfs_attr(dev, tc, + CTI_CON_ATTR_TRIGIN_SIG, + attr_idx++); + if (err) + return err; + + err = cti_create_con_sysfs_attr(dev, tc, + CTI_CON_ATTR_TRIGIN_TYPES, + attr_idx++); + if (err) + return err; + } + + if (tc->con_out->nr_sigs > 0) { + err = cti_create_con_sysfs_attr(dev, tc, + CTI_CON_ATTR_TRIGOUT_SIG, + attr_idx++); + if (err) + return err; + + err = cti_create_con_sysfs_attr(dev, tc, + CTI_CON_ATTR_TRIGOUT_TYPES, + attr_idx++); + if (err) + return err; + } + attr_group->attrs = tc->con_attrs; + return 0; +} + +/* create the array of group pointers for the CTI sysfs groups */ +static int cti_create_cons_groups(struct device *dev, struct cti_device *ctidev) +{ + int nr_groups; + + /* nr groups = dynamic + static + NULL terminator */ + nr_groups = ctidev->nr_trig_con + CORESIGHT_CTI_STATIC_GROUPS_MAX; + ctidev->con_groups = devm_kcalloc(dev, nr_groups, + sizeof(struct attribute_group *), + GFP_KERNEL); + if (!ctidev->con_groups) + return -ENOMEM; + return 0; +} + +int cti_create_cons_sysfs(struct device *dev, struct cti_drvdata *drvdata) +{ + struct cti_device *ctidev = &drvdata->ctidev; + int err, con_idx = 0, i; + struct cti_trig_con *tc; + + err = cti_create_cons_groups(dev, ctidev); + if (err) + return err; + + /* populate first locations with the static set of groups */ + for (i = 0; i < (CORESIGHT_CTI_STATIC_GROUPS_MAX - 1); i++) + ctidev->con_groups[i] = coresight_cti_groups[i]; + + /* add dynamic set for each connection */ + list_for_each_entry(tc, &ctidev->trig_cons, node) { + err = cti_create_con_attr_set(dev, con_idx++, ctidev, tc); + if (err) + break; + } + return err; +} + +/* attribute and group sysfs tables. */ +static const struct attribute_group coresight_cti_group = { + .attrs = coresight_cti_attrs, +}; + +static const struct attribute_group coresight_cti_mgmt_group = { + .attrs = coresight_cti_mgmt_attrs, + .name = "mgmt", +}; + +static const struct attribute_group coresight_cti_regs_group = { + .attrs = coresight_cti_regs_attrs, + .name = "regs", +}; + +static const struct attribute_group coresight_cti_channels_group = { + .attrs = coresight_cti_channel_attrs, + .name = "channels", +}; + +const struct attribute_group * +coresight_cti_groups[CORESIGHT_CTI_STATIC_GROUPS_MAX] = { + &coresight_cti_group, + &coresight_cti_mgmt_group, + &coresight_cti_regs_group, + &coresight_cti_channels_group, + NULL, +}; diff --git a/drivers/hwtracing/coresight/coresight-cti.h b/drivers/hwtracing/coresight/coresight-cti.h new file mode 100644 index 000000000000..4f89091ee93f --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti.h @@ -0,0 +1,243 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2018 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#ifndef _CORESIGHT_CORESIGHT_CTI_H +#define _CORESIGHT_CORESIGHT_CTI_H + +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/sysfs.h> +#include <linux/types.h> + +#include "coresight-priv.h" + +struct fwnode_handle; + +/* + * Device registers + * 0x000 - 0x144: CTI programming and status + * 0xEDC - 0xEF8: CTI integration test. + * 0xF00 - 0xFFC: Coresight management registers. + */ +/* CTI programming registers */ +#define CTICONTROL 0x000 +#define CTIINTACK 0x010 +#define CTIAPPSET 0x014 +#define CTIAPPCLEAR 0x018 +#define CTIAPPPULSE 0x01C +#define CTIINEN(n) (0x020 + (4 * n)) +#define CTIOUTEN(n) (0x0A0 + (4 * n)) +#define CTITRIGINSTATUS 0x130 +#define CTITRIGOUTSTATUS 0x134 +#define CTICHINSTATUS 0x138 +#define CTICHOUTSTATUS 0x13C +#define CTIGATE 0x140 +#define ASICCTL 0x144 +/* Integration test registers */ +#define ITCHINACK 0xEDC /* WO CTI CSSoc 400 only*/ +#define ITTRIGINACK 0xEE0 /* WO CTI CSSoc 400 only*/ +#define ITCHOUT 0xEE4 /* WO RW-600 */ +#define ITTRIGOUT 0xEE8 /* WO RW-600 */ +#define ITCHOUTACK 0xEEC /* RO CTI CSSoc 400 only*/ +#define ITTRIGOUTACK 0xEF0 /* RO CTI CSSoc 400 only*/ +#define ITCHIN 0xEF4 /* RO */ +#define ITTRIGIN 0xEF8 /* RO */ +/* management registers */ +#define CTIDEVAFF0 0xFA8 +#define CTIDEVAFF1 0xFAC + +/* + * CTI CSSoc 600 has a max of 32 trigger signals per direction. + * CTI CSSoc 400 has 8 IO triggers - other CTIs can be impl def. + * Max of in and out defined in the DEVID register. + * - pick up actual number used from .dts parameters if present. + */ +#define CTIINOUTEN_MAX 32 + +/** + * Group of related trigger signals + * + * @nr_sigs: number of signals in the group. + * @used_mask: bitmask representing the signal indexes in the group. + * @sig_types: array of types for the signals, length nr_sigs. + */ +struct cti_trig_grp { + int nr_sigs; + u32 used_mask; + int sig_types[]; +}; + +/** + * Trigger connection - connection between a CTI and other (coresight) device + * lists input and output trigger signals for the device + * + * @con_in: connected CTIIN signals for the device. + * @con_out: connected CTIOUT signals for the device. + * @con_dev: coresight device connected to the CTI, NULL if not CS device + * @con_dev_name: name of connected device (CS or CPU) + * @node: entry node in list of connections. + * @con_attrs: Dynamic sysfs attributes specific to this connection. + * @attr_group: Dynamic attribute group created for this connection. + */ +struct cti_trig_con { + struct cti_trig_grp *con_in; + struct cti_trig_grp *con_out; + struct coresight_device *con_dev; + const char *con_dev_name; + struct list_head node; + struct attribute **con_attrs; + struct attribute_group *attr_group; +}; + +/** + * struct cti_device - description of CTI device properties. + * + * @nt_trig_con: Number of external devices connected to this device. + * @ctm_id: which CTM this device is connected to (by default it is + * assumed there is a single CTM per SoC, ID 0). + * @trig_cons: list of connections to this device. + * @cpu: CPU ID if associated with CPU, -1 otherwise. + * @con_groups: combined static and dynamic sysfs groups for trigger + * connections. + */ +struct cti_device { + int nr_trig_con; + u32 ctm_id; + struct list_head trig_cons; + int cpu; + const struct attribute_group **con_groups; +}; + +/** + * struct cti_config - configuration of the CTI device hardware + * + * @nr_trig_max: Max number of trigger signals implemented on device. + * (max of trig_in or trig_out) - from ID register. + * @nr_ctm_channels: number of available CTM channels - from ID register. + * @enable_req_count: CTI is enabled alongside >=1 associated devices. + * @hw_enabled: true if hw is currently enabled. + * @hw_powered: true if associated cpu powered on, or no cpu. + * @trig_in_use: bitfield of in triggers registered as in use. + * @trig_out_use: bitfield of out triggers registered as in use. + * @trig_out_filter: bitfield of out triggers that are blocked if filter + * enabled. Typically this would be dbgreq / restart on + * a core CTI. + * @trig_filter_enable: 1 if filtering enabled. + * @xtrig_rchan_sel: channel selection for xtrigger connection show. + * @ctiappset: CTI Software application channel set. + * @ctiinout_sel: register selector for INEN and OUTEN regs. + * @ctiinen: enable input trigger to a channel. + * @ctiouten: enable output trigger from a channel. + * @ctigate: gate channel output from CTI to CTM. + * @asicctl: asic control register. + */ +struct cti_config { + /* hardware description */ + int nr_ctm_channels; + int nr_trig_max; + + /* cti enable control */ + int enable_req_count; + bool hw_enabled; + bool hw_powered; + + /* registered triggers and filtering */ + u32 trig_in_use; + u32 trig_out_use; + u32 trig_out_filter; + bool trig_filter_enable; + u8 xtrig_rchan_sel; + + /* cti cross trig programmable regs */ + u32 ctiappset; + u8 ctiinout_sel; + u32 ctiinen[CTIINOUTEN_MAX]; + u32 ctiouten[CTIINOUTEN_MAX]; + u32 ctigate; + u32 asicctl; +}; + +/** + * struct cti_drvdata - specifics for the CTI device + * @base: Memory mapped base address for this component.. + * @csdev: Standard CoreSight device information. + * @ctidev: Extra information needed by the CTI/CTM framework. + * @spinlock: Control data access to one at a time. + * @config: Configuration data for this CTI device. + * @node: List entry of this device in the list of CTI devices. + * @csdev_release: release function for underlying coresight_device. + */ +struct cti_drvdata { + void __iomem *base; + struct coresight_device *csdev; + struct cti_device ctidev; + raw_spinlock_t spinlock; + struct cti_config config; + struct list_head node; + void (*csdev_release)(struct device *dev); +}; + +/* + * Channel operation types. + */ +enum cti_chan_op { + CTI_CHAN_ATTACH, + CTI_CHAN_DETACH, +}; + +enum cti_trig_dir { + CTI_TRIG_IN, + CTI_TRIG_OUT, +}; + +enum cti_chan_gate_op { + CTI_GATE_CHAN_ENABLE, + CTI_GATE_CHAN_DISABLE, +}; + +enum cti_chan_set_op { + CTI_CHAN_SET, + CTI_CHAN_CLR, + CTI_CHAN_PULSE, +}; + +/* private cti driver fns & vars */ +extern const struct attribute_group *coresight_cti_groups[]; +int cti_add_default_connection(struct device *dev, + struct cti_drvdata *drvdata); +int cti_add_connection_entry(struct device *dev, struct cti_drvdata *drvdata, + struct cti_trig_con *tc, + struct coresight_device *csdev, + const char *assoc_dev_name); +struct cti_trig_con *cti_allocate_trig_con(struct device *dev, int in_sigs, + int out_sigs); +int cti_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path); +int cti_disable(struct coresight_device *csdev, struct coresight_path *path); +void cti_write_all_hw_regs(struct cti_drvdata *drvdata); +void cti_write_intack(struct device *dev, u32 ackval); +void cti_write_single_reg(struct cti_drvdata *drvdata, int offset, u32 value); +int cti_channel_trig_op(struct device *dev, enum cti_chan_op op, + enum cti_trig_dir direction, u32 channel_idx, + u32 trigger_idx); +int cti_channel_gate_op(struct device *dev, enum cti_chan_gate_op op, + u32 channel_idx); +int cti_channel_setop(struct device *dev, enum cti_chan_set_op op, + u32 channel_idx); +int cti_create_cons_sysfs(struct device *dev, struct cti_drvdata *drvdata); +struct coresight_platform_data * +coresight_cti_get_platform_data(struct device *dev); +const char *cti_plat_get_node_name(struct fwnode_handle *fwnode); + +/* cti powered and enabled */ +static inline bool cti_active(struct cti_config *cfg) +{ + return cfg->hw_powered && cfg->hw_enabled; +} + +#endif /* _CORESIGHT_CORESIGHT_CTI_H */ diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c new file mode 100644 index 000000000000..14322c99e29d --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-dummy.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/coresight.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "coresight-priv.h" +#include "coresight-trace-id.h" + +struct dummy_drvdata { + struct device *dev; + struct coresight_device *csdev; + u8 traceid; +}; + +DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source"); +DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink"); + +static int dummy_source_enable(struct coresight_device *csdev, + struct perf_event *event, enum cs_mode mode, + __maybe_unused struct coresight_path *path) +{ + if (!coresight_take_mode(csdev, mode)) + return -EBUSY; + + dev_dbg(csdev->dev.parent, "Dummy source enabled\n"); + + return 0; +} + +static void dummy_source_disable(struct coresight_device *csdev, + struct perf_event *event) +{ + coresight_set_mode(csdev, CS_MODE_DISABLED); + dev_dbg(csdev->dev.parent, "Dummy source disabled\n"); +} + +static int dummy_source_trace_id(struct coresight_device *csdev, __maybe_unused enum cs_mode mode, + __maybe_unused struct coresight_device *sink) +{ + struct dummy_drvdata *drvdata; + + drvdata = dev_get_drvdata(csdev->dev.parent); + + return drvdata->traceid; +} + +static int dummy_sink_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) +{ + dev_dbg(csdev->dev.parent, "Dummy sink enabled\n"); + + return 0; +} + +static int dummy_sink_disable(struct coresight_device *csdev) +{ + dev_dbg(csdev->dev.parent, "Dummy sink disabled\n"); + + return 0; +} + +static const struct coresight_ops_source dummy_source_ops = { + .enable = dummy_source_enable, + .disable = dummy_source_disable, +}; + +static const struct coresight_ops dummy_source_cs_ops = { + .trace_id = dummy_source_trace_id, + .source_ops = &dummy_source_ops, +}; + +static const struct coresight_ops_sink dummy_sink_ops = { + .enable = dummy_sink_enable, + .disable = dummy_sink_disable, +}; + +static const struct coresight_ops dummy_sink_cs_ops = { + .sink_ops = &dummy_sink_ops, +}; + +/* User can get the trace id of dummy source from this node. */ +static ssize_t traceid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct dummy_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->traceid; + return sysfs_emit(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(traceid); + +static struct attribute *coresight_dummy_attrs[] = { + &dev_attr_traceid.attr, + NULL, +}; + +static const struct attribute_group coresight_dummy_group = { + .attrs = coresight_dummy_attrs, +}; + +static const struct attribute_group *coresight_dummy_groups[] = { + &coresight_dummy_group, + NULL, +}; + +static int dummy_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct coresight_platform_data *pdata; + struct dummy_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + int ret = 0, trace_id = 0; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + if (of_device_is_compatible(node, "arm,coresight-dummy-source")) { + + desc.name = coresight_alloc_device_name(&source_devs, dev); + if (!desc.name) + return -ENOMEM; + + desc.type = CORESIGHT_DEV_TYPE_SOURCE; + desc.subtype.source_subtype = + CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS; + desc.ops = &dummy_source_cs_ops; + desc.groups = coresight_dummy_groups; + + ret = coresight_get_static_trace_id(dev, &trace_id); + if (!ret) { + /* Get the static id if id is set in device tree. */ + ret = coresight_trace_id_get_static_system_id(trace_id); + if (ret < 0) { + dev_err(dev, "Fail to get static id.\n"); + return ret; + } + } else { + /* Get next available id if id is not set in device tree. */ + trace_id = coresight_trace_id_get_system_id(); + if (trace_id < 0) { + ret = trace_id; + return ret; + } + } + drvdata->traceid = (u8)trace_id; + + } else if (of_device_is_compatible(node, "arm,coresight-dummy-sink")) { + desc.name = coresight_alloc_device_name(&sink_devs, dev); + if (!desc.name) + return -ENOMEM; + + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_DUMMY; + desc.ops = &dummy_sink_cs_ops; + } else { + dev_err(dev, "Device type not set\n"); + return -EINVAL; + } + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + goto free_id; + } + pdev->dev.platform_data = pdata; + + drvdata->dev = &pdev->dev; + platform_set_drvdata(pdev, drvdata); + + desc.pdata = pdev->dev.platform_data; + desc.dev = &pdev->dev; + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto free_id; + } + + pm_runtime_enable(dev); + dev_dbg(dev, "Dummy device initialized\n"); + + ret = 0; + goto out; + +free_id: + if (IS_VALID_CS_TRACE_ID(drvdata->traceid)) + coresight_trace_id_put_system_id(drvdata->traceid); + +out: + return ret; +} + +static void dummy_remove(struct platform_device *pdev) +{ + struct dummy_drvdata *drvdata = platform_get_drvdata(pdev); + struct device *dev = &pdev->dev; + + if (IS_VALID_CS_TRACE_ID(drvdata->traceid)) + coresight_trace_id_put_system_id(drvdata->traceid); + pm_runtime_disable(dev); + coresight_unregister(drvdata->csdev); +} + +static const struct of_device_id dummy_match[] = { + {.compatible = "arm,coresight-dummy-source"}, + {.compatible = "arm,coresight-dummy-sink"}, + {}, +}; + +static struct platform_driver dummy_driver = { + .probe = dummy_probe, + .remove = dummy_remove, + .driver = { + .name = "coresight-dummy", + .of_match_table = dummy_match, + }, +}; + +module_platform_driver(dummy_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("CoreSight dummy driver"); diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c deleted file mode 100644 index 299667b887fc..000000000000 --- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c +++ /dev/null @@ -1,255 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved. - */ - -#include <linux/amba/bus.h> -#include <linux/clk.h> -#include <linux/coresight.h> -#include <linux/device.h> -#include <linux/err.h> -#include <linux/init.h> -#include <linux/io.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/pm_runtime.h> -#include <linux/slab.h> - -#include "coresight-priv.h" - -#define REPLICATOR_IDFILTER0 0x000 -#define REPLICATOR_IDFILTER1 0x004 - -/** - * struct replicator_state - specifics associated to a replicator component - * @base: memory mapped base address for this component. - * @dev: the device entity associated with this component - * @atclk: optional clock for the core parts of the replicator. - * @csdev: component vitals needed by the framework - */ -struct replicator_state { - void __iomem *base; - struct device *dev; - struct clk *atclk; - struct coresight_device *csdev; -}; - -/* - * replicator_reset : Reset the replicator configuration to sane values. - */ -static void replicator_reset(struct replicator_state *drvdata) -{ - CS_UNLOCK(drvdata->base); - - if (!coresight_claim_device_unlocked(drvdata->base)) { - writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0); - writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1); - coresight_disclaim_device_unlocked(drvdata->base); - } - - CS_LOCK(drvdata->base); -} - -static int replicator_enable(struct coresight_device *csdev, int inport, - int outport) -{ - int rc = 0; - u32 reg; - struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent); - - switch (outport) { - case 0: - reg = REPLICATOR_IDFILTER0; - break; - case 1: - reg = REPLICATOR_IDFILTER1; - break; - default: - WARN_ON(1); - return -EINVAL; - } - - CS_UNLOCK(drvdata->base); - - if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && - (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - rc = coresight_claim_device_unlocked(drvdata->base); - - /* Ensure that the outport is enabled. */ - if (!rc) { - writel_relaxed(0x00, drvdata->base + reg); - dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); - } - - CS_LOCK(drvdata->base); - - return rc; -} - -static void replicator_disable(struct coresight_device *csdev, int inport, - int outport) -{ - u32 reg; - struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent); - - switch (outport) { - case 0: - reg = REPLICATOR_IDFILTER0; - break; - case 1: - reg = REPLICATOR_IDFILTER1; - break; - default: - WARN_ON(1); - return; - } - - CS_UNLOCK(drvdata->base); - - /* disable the flow of ATB data through port */ - writel_relaxed(0xff, drvdata->base + reg); - - if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && - (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - coresight_disclaim_device_unlocked(drvdata->base); - CS_LOCK(drvdata->base); - - dev_dbg(drvdata->dev, "REPLICATOR disabled\n"); -} - -static const struct coresight_ops_link replicator_link_ops = { - .enable = replicator_enable, - .disable = replicator_disable, -}; - -static const struct coresight_ops replicator_cs_ops = { - .link_ops = &replicator_link_ops, -}; - -#define coresight_replicator_reg(name, offset) \ - coresight_simple_reg32(struct replicator_state, name, offset) - -coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0); -coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1); - -static struct attribute *replicator_mgmt_attrs[] = { - &dev_attr_idfilter0.attr, - &dev_attr_idfilter1.attr, - NULL, -}; - -static const struct attribute_group replicator_mgmt_group = { - .attrs = replicator_mgmt_attrs, - .name = "mgmt", -}; - -static const struct attribute_group *replicator_groups[] = { - &replicator_mgmt_group, - NULL, -}; - -static int replicator_probe(struct amba_device *adev, const struct amba_id *id) -{ - int ret; - struct device *dev = &adev->dev; - struct resource *res = &adev->res; - struct coresight_platform_data *pdata = NULL; - struct replicator_state *drvdata; - struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; - void __iomem *base; - - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } - - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } - - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); - - drvdata->base = base; - dev_set_drvdata(dev, drvdata); - pm_runtime_put(&adev->dev); - - desc.type = CORESIGHT_DEV_TYPE_LINK; - desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; - desc.ops = &replicator_cs_ops; - desc.pdata = adev->dev.platform_data; - desc.dev = &adev->dev; - desc.groups = replicator_groups; - drvdata->csdev = coresight_register(&desc); - - if (!IS_ERR(drvdata->csdev)) { - replicator_reset(drvdata); - return 0; - } - return PTR_ERR(drvdata->csdev); -} - -#ifdef CONFIG_PM -static int replicator_runtime_suspend(struct device *dev) -{ - struct replicator_state *drvdata = dev_get_drvdata(dev); - - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); - - return 0; -} - -static int replicator_runtime_resume(struct device *dev) -{ - struct replicator_state *drvdata = dev_get_drvdata(dev); - - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); - - return 0; -} -#endif - -static const struct dev_pm_ops replicator_dev_pm_ops = { - SET_RUNTIME_PM_OPS(replicator_runtime_suspend, - replicator_runtime_resume, - NULL) -}; - -static const struct amba_id replicator_ids[] = { - { - .id = 0x000bb909, - .mask = 0x000fffff, - }, - { - /* Coresight SoC-600 */ - .id = 0x000bb9ec, - .mask = 0x000fffff, - }, - { 0, 0 }, -}; - -static struct amba_driver replicator_driver = { - .drv = { - .name = "coresight-dynamic-replicator", - .pm = &replicator_dev_pm_ops, - .suppress_bind_attrs = true, - }, - .probe = replicator_probe, - .id_table = replicator_ids, -}; -builtin_amba_driver(replicator_driver); diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 105782ea64c7..6657602d8f2e 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -5,6 +5,7 @@ * Description: CoreSight Embedded Trace Buffer driver */ +#include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -62,30 +63,31 @@ #define ETB_FFSR_BIT 1 #define ETB_FRAME_SIZE_WORDS 4 +DEFINE_CORESIGHT_DEVLIST(etb_devs, "etb"); + /** * struct etb_drvdata - specifics associated to an ETB component * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @atclk: optional clock for the core parts of the ETB. * @csdev: component vitals needed by the framework. * @miscdev: specifics to handle "/dev/xyz.etb" entry. * @spinlock: only one at a time pls. * @reading: synchronise user space access to etb buffer. + * @pid: Process ID of the process being monitored by the session + * that is using this component. * @buf: area of memory where ETB buffer content gets sent. - * @mode: this ETB is being used. * @buffer_depth: size of @buf. * @trigger_cntr: amount of words to store after a trigger. */ struct etb_drvdata { void __iomem *base; - struct device *dev; struct clk *atclk; struct coresight_device *csdev; struct miscdevice miscdev; - spinlock_t spinlock; + raw_spinlock_t spinlock; local_t reading; + pid_t pid; u8 *buf; - u32 mode; u32 buffer_depth; u32 trigger_cntr; }; @@ -95,15 +97,7 @@ static int etb_set_buffer(struct coresight_device *csdev, static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata) { - u32 depth = 0; - - pm_runtime_get_sync(drvdata->dev); - - /* RO registers don't need locking */ - depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); - - pm_runtime_put(drvdata->dev); - return depth; + return readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); } static void __etb_enable_hw(struct etb_drvdata *drvdata) @@ -136,7 +130,7 @@ static void __etb_enable_hw(struct etb_drvdata *drvdata) static int etb_enable_hw(struct etb_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; @@ -151,70 +145,95 @@ static int etb_enable_sysfs(struct coresight_device *csdev) unsigned long flags; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); /* Don't messup with perf sessions. */ - if (drvdata->mode == CS_MODE_PERF) { + if (coresight_get_mode(csdev) == CS_MODE_PERF) { ret = -EBUSY; goto out; } - /* Nothing to do, the tracer is already enabled. */ - if (drvdata->mode == CS_MODE_SYSFS) - goto out; + if (coresight_get_mode(csdev) == CS_MODE_DISABLED) { + ret = etb_enable_hw(drvdata); + if (ret) + goto out; - ret = etb_enable_hw(drvdata); - if (!ret) - drvdata->mode = CS_MODE_SYSFS; + coresight_set_mode(csdev, CS_MODE_SYSFS); + } + csdev->refcnt++; out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } -static int etb_enable_perf(struct coresight_device *csdev, void *data) +static int etb_enable_perf(struct coresight_device *csdev, struct coresight_path *path) { int ret = 0; + pid_t pid; unsigned long flags; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_output_handle *handle = path->handle; + struct cs_buffers *buf = etm_perf_sink_config(handle); - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); - /* No need to continue if the component is already in use. */ - if (drvdata->mode != CS_MODE_DISABLED) { + /* No need to continue if the component is already in used by sysFS. */ + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) { + ret = -EBUSY; + goto out; + } + + /* Get a handle on the pid of the process to monitor */ + pid = buf->pid; + + if (drvdata->pid != -1 && drvdata->pid != pid) { ret = -EBUSY; goto out; } /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + csdev->refcnt++; + goto out; + } + + /* * We don't have an internal state to clean up if we fail to setup * the perf buffer. So we can perform the step before we turn the * ETB on and leave without cleaning up. */ - ret = etb_set_buffer(csdev, (struct perf_output_handle *)data); + ret = etb_set_buffer(csdev, handle); if (ret) goto out; ret = etb_enable_hw(drvdata); - if (!ret) - drvdata->mode = CS_MODE_PERF; + if (!ret) { + /* Associate with monitored process. */ + drvdata->pid = pid; + coresight_set_mode(drvdata->csdev, CS_MODE_PERF); + csdev->refcnt++; + } out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } -static int etb_enable(struct coresight_device *csdev, u32 mode, void *data) +static int etb_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) { int ret; - struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); switch (mode) { case CS_MODE_SYSFS: ret = etb_enable_sysfs(csdev); break; case CS_MODE_PERF: - ret = etb_enable_perf(csdev, data); + ret = etb_enable_perf(csdev, path); break; default: ret = -EINVAL; @@ -224,13 +243,15 @@ static int etb_enable(struct coresight_device *csdev, u32 mode, void *data) if (ret) return ret; - dev_dbg(drvdata->dev, "ETB enabled\n"); + dev_dbg(&csdev->dev, "ETB enabled\n"); return 0; } static void __etb_disable_hw(struct etb_drvdata *drvdata) { u32 ffcr; + struct device *dev = &drvdata->csdev->dev; + struct csdev_access *csa = &drvdata->csdev->access; CS_UNLOCK(drvdata->base); @@ -242,16 +263,16 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata) ffcr |= ETB_FFCR_FON_MAN; writel_relaxed(ffcr, drvdata->base + ETB_FFCR); - if (coresight_timeout(drvdata->base, ETB_FFCR, ETB_FFCR_BIT, 0)) { - dev_err(drvdata->dev, + if (coresight_timeout(csa, ETB_FFCR, ETB_FFCR_BIT, 0)) { + dev_err(dev, "timeout while waiting for completion of Manual Flush\n"); } /* disable trace capture */ writel_relaxed(0x0, drvdata->base + ETB_CTL_REG); - if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) { - dev_err(drvdata->dev, + if (coresight_timeout(csa, ETB_FFSR, ETB_FFSR_BIT, 1)) { + dev_err(dev, "timeout while waiting for Formatter to Stop\n"); } @@ -266,6 +287,7 @@ static void etb_dump_hw(struct etb_drvdata *drvdata) u32 read_data, depth; u32 read_ptr, write_ptr; u32 frame_off, frame_endoff; + struct device *dev = &drvdata->csdev->dev; CS_UNLOCK(drvdata->base); @@ -275,10 +297,10 @@ static void etb_dump_hw(struct etb_drvdata *drvdata) frame_off = write_ptr % ETB_FRAME_SIZE_WORDS; frame_endoff = ETB_FRAME_SIZE_WORDS - frame_off; if (frame_off) { - dev_err(drvdata->dev, + dev_err(dev, "write_ptr: %lu not aligned to formatter frame size\n", (unsigned long)write_ptr); - dev_err(drvdata->dev, "frameoff: %lu, frame_endoff: %lu\n", + dev_err(dev, "frameoff: %lu, frame_endoff: %lu\n", (unsigned long)frame_off, (unsigned long)frame_endoff); write_ptr += frame_endoff; } @@ -322,40 +344,48 @@ static void etb_disable_hw(struct etb_drvdata *drvdata) { __etb_disable_hw(drvdata); etb_dump_hw(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); } -static void etb_disable(struct coresight_device *csdev) +static int etb_disable(struct coresight_device *csdev) { struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); unsigned long flags; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); - /* Disable the ETB only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - etb_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; + csdev->refcnt--; + if (csdev->refcnt) { + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; } - spin_unlock_irqrestore(&drvdata->spinlock, flags); - dev_dbg(drvdata->dev, "ETB disabled\n"); + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(coresight_get_mode(csdev) == CS_MODE_DISABLED); + etb_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; + coresight_set_mode(csdev, CS_MODE_DISABLED); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_dbg(&csdev->dev, "ETB disabled\n"); + return 0; } -static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu, - void **pages, int nr_pages, bool overwrite) +static void *etb_alloc_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite) { int node; struct cs_buffers *buf; - if (cpu == -1) - cpu = smp_processor_id(); - node = cpu_to_node(cpu); + node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu); buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node); if (!buf) return NULL; + buf->pid = task_pid_nr(event->owner); buf->snapshot = overwrite; buf->nr_pages = nr_pages; buf->data_pages = pages; @@ -404,7 +434,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, const u32 *barrier; u32 read_ptr, write_ptr, capacity; u32 status, read_data; - unsigned long offset, to_read; + unsigned long offset, to_read = 0, flags; struct cs_buffers *buf = sink_config; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -413,6 +443,12 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS; + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* Don't do anything if another tracer is using this sink */ + if (csdev->refcnt != 1) + goto out; + __etb_disable_hw(drvdata); CS_UNLOCK(drvdata->base); @@ -426,7 +462,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, * chance to fix things. */ if (write_ptr % ETB_FRAME_SIZE_WORDS) { - dev_err(drvdata->dev, + dev_err(&csdev->dev, "write_ptr: %lu not aligned to formatter frame size\n", (unsigned long)write_ptr); @@ -478,7 +514,13 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, lost = true; } - if (lost) + /* + * Don't set the TRUNCATED flag in snapshot mode because 1) the + * captured buffer is expected to be truncated and 2) a full buffer + * prevents the event from being re-enabled by the perf core, + * resulting in stale data being send to user space. + */ + if (!buf->snapshot && lost) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); /* finally tell HW where we want to start reading from */ @@ -486,7 +528,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, cur = buf->cur; offset = buf->offset; - barrier = barrier_pkt; + barrier = coresight_barrier_pkt; for (i = 0; i < to_read; i += 4) { buf_ptr = buf->data_pages[cur] + offset; @@ -514,15 +556,17 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, writel_relaxed(0x0, drvdata->base + ETB_RAM_WRITE_POINTER); /* - * In snapshot mode we have to update the handle->head to point - * to the new location. + * In snapshot mode we simply increment the head by the number of byte + * that were written. User space will figure out how many bytes to get + * from the AUX buffer based on the position of the head. */ - if (buf->snapshot) { - handle->head = (cur * PAGE_SIZE) + offset; - to_read = buf->nr_pages << PAGE_SHIFT; - } + if (buf->snapshot) + handle->head += to_read; + __etb_enable_hw(drvdata); CS_LOCK(drvdata->base); +out: + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return to_read; } @@ -543,15 +587,15 @@ static void etb_dump(struct etb_drvdata *drvdata) { unsigned long flags; - spin_lock_irqsave(&drvdata->spinlock, flags); - if (drvdata->mode == CS_MODE_SYSFS) { + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) { __etb_disable_hw(drvdata); etb_dump_hw(drvdata); __etb_enable_hw(drvdata); } - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); - dev_dbg(drvdata->dev, "ETB dumped\n"); + dev_dbg(&drvdata->csdev->dev, "ETB dumped\n"); } static int etb_open(struct inode *inode, struct file *file) @@ -562,7 +606,7 @@ static int etb_open(struct inode *inode, struct file *file) if (local_cmpxchg(&drvdata->reading, 0, 1)) return -EBUSY; - dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__); + dev_dbg(&drvdata->csdev->dev, "%s: successfully opened\n", __func__); return 0; } @@ -572,6 +616,7 @@ static ssize_t etb_read(struct file *file, char __user *data, u32 depth; struct etb_drvdata *drvdata = container_of(file->private_data, struct etb_drvdata, miscdev); + struct device *dev = &drvdata->csdev->dev; etb_dump(drvdata); @@ -580,13 +625,14 @@ static ssize_t etb_read(struct file *file, char __user *data, len = depth * 4 - *ppos; if (copy_to_user(data, drvdata->buf + *ppos, len)) { - dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__); + dev_dbg(dev, + "%s: copy_to_user failed\n", __func__); return -EFAULT; } *ppos += len; - dev_dbg(drvdata->dev, "%s: %zu bytes copied, %d bytes left\n", + dev_dbg(dev, "%s: %zu bytes copied, %d bytes left\n", __func__, len, (int)(depth * 4 - *ppos)); return len; } @@ -597,7 +643,7 @@ static int etb_release(struct inode *inode, struct file *file) struct etb_drvdata, miscdev); local_set(&drvdata->reading, 0); - dev_dbg(drvdata->dev, "%s: released\n", __func__); + dev_dbg(&drvdata->csdev->dev, "%s: released\n", __func__); return 0; } @@ -606,30 +652,17 @@ static const struct file_operations etb_fops = { .open = etb_open, .read = etb_read, .release = etb_release, - .llseek = no_llseek, }; -#define coresight_etb10_reg(name, offset) \ - coresight_simple_reg32(struct etb_drvdata, name, offset) - -coresight_etb10_reg(rdp, ETB_RAM_DEPTH_REG); -coresight_etb10_reg(sts, ETB_STATUS_REG); -coresight_etb10_reg(rrp, ETB_RAM_READ_POINTER); -coresight_etb10_reg(rwp, ETB_RAM_WRITE_POINTER); -coresight_etb10_reg(trg, ETB_TRG); -coresight_etb10_reg(ctl, ETB_CTL_REG); -coresight_etb10_reg(ffsr, ETB_FFSR); -coresight_etb10_reg(ffcr, ETB_FFCR); - static struct attribute *coresight_etb_mgmt_attrs[] = { - &dev_attr_rdp.attr, - &dev_attr_sts.attr, - &dev_attr_rrp.attr, - &dev_attr_rwp.attr, - &dev_attr_trg.attr, - &dev_attr_ctl.attr, - &dev_attr_ffsr.attr, - &dev_attr_ffcr.attr, + coresight_simple_reg32(rdp, ETB_RAM_DEPTH_REG), + coresight_simple_reg32(sts, ETB_STATUS_REG), + coresight_simple_reg32(rrp, ETB_RAM_READ_POINTER), + coresight_simple_reg32(rwp, ETB_RAM_WRITE_POINTER), + coresight_simple_reg32(trg, ETB_TRG), + coresight_simple_reg32(ctl, ETB_CTL_REG), + coresight_simple_reg32(ffsr, ETB_FFSR), + coresight_simple_reg32(ffcr, ETB_FFCR), NULL, }; @@ -673,7 +706,7 @@ static const struct attribute_group coresight_etb_mgmt_group = { .name = "mgmt", }; -const struct attribute_group *coresight_etb_groups[] = { +static const struct attribute_group *coresight_etb_groups[] = { &coresight_etb_group, &coresight_etb_mgmt_group, NULL, @@ -688,26 +721,19 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) struct etb_drvdata *drvdata; struct resource *res = &adev->res; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } + desc.name = coresight_alloc_device_name(&etb_devs, dev); + if (!desc.name) + return -ENOMEM; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } + drvdata->atclk = devm_clk_get_optional_enabled(dev, "atclk"); + if (IS_ERR(drvdata->atclk)) + return PTR_ERR(drvdata->atclk); + dev_set_drvdata(dev, drvdata); /* validity for the resource is already checked by the AMBA core */ @@ -716,11 +742,11 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); - spin_lock_init(&drvdata->spinlock); + raw_spin_lock_init(&drvdata->spinlock); drvdata->buffer_depth = etb_get_buffer_depth(drvdata); - pm_runtime_put(&adev->dev); if (drvdata->buffer_depth & 0x80000000) return -EINVAL; @@ -730,23 +756,34 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) if (!drvdata->buf) return -ENOMEM; + /* This device is not associated with a session */ + drvdata->pid = -1; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + desc.type = CORESIGHT_DEV_TYPE_SINK; desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; desc.ops = &etb_cs_ops; desc.pdata = pdata; desc.dev = dev; desc.groups = coresight_etb_groups; + + coresight_clear_self_claim_tag(&desc.access); drvdata->csdev = coresight_register(&desc); if (IS_ERR(drvdata->csdev)) return PTR_ERR(drvdata->csdev); - drvdata->miscdev.name = pdata->name; + drvdata->miscdev.name = desc.name; drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; drvdata->miscdev.fops = &etb_fops; ret = misc_register(&drvdata->miscdev); if (ret) goto err_misc_register; + pm_runtime_put(&adev->dev); return 0; err_misc_register: @@ -754,13 +791,25 @@ err_misc_register: return ret; } +static void etb_remove(struct amba_device *adev) +{ + struct etb_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + /* + * Since misc_open() holds a refcount on the f_ops, which is + * etb fops in this case, device is there until last file + * handler to this device is closed. + */ + misc_deregister(&drvdata->miscdev); + coresight_unregister(drvdata->csdev); +} + #ifdef CONFIG_PM static int etb_runtime_suspend(struct device *dev) { struct etb_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); return 0; } @@ -769,10 +818,7 @@ static int etb_runtime_resume(struct device *dev) { struct etb_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); - - return 0; + return clk_prepare_enable(drvdata->atclk); } #endif @@ -785,18 +831,26 @@ static const struct amba_id etb_ids[] = { .id = 0x000bb907, .mask = 0x000fffff, }, - { 0, 0}, + { 0, 0, NULL }, }; +MODULE_DEVICE_TABLE(amba, etb_ids); + static struct amba_driver etb_driver = { .drv = { .name = "coresight-etb10", - .owner = THIS_MODULE, .pm = &etb_dev_pm_ops, .suppress_bind_attrs = true, }, .probe = etb_probe, + .remove = etb_remove, .id_table = etb_ids, }; -builtin_amba_driver(etb_driver); + +module_amba_driver(etb_driver); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight Embedded Trace Buffer driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index abe8249b893b..17afa0f4cdee 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/bitfield.h> #include <linux/coresight.h> #include <linux/coresight-pmu.h> #include <linux/cpumask.h> @@ -14,27 +15,94 @@ #include <linux/perf_event.h> #include <linux/percpu-defs.h> #include <linux/slab.h> +#include <linux/stringhash.h> #include <linux/types.h> #include <linux/workqueue.h> +#include "coresight-config.h" #include "coresight-etm-perf.h" #include "coresight-priv.h" +#include "coresight-syscfg.h" +#include "coresight-trace-id.h" static struct pmu etm_pmu; static bool etm_perf_up; -static DEFINE_PER_CPU(struct perf_output_handle, ctx_handle); +/* + * An ETM context for a running event includes the perf aux handle + * and aux_data. For ETM, the aux_data (etm_event_data), consists of + * the trace path and the sink configuration. The event data is accessible + * via perf_get_aux(handle). However, a sink could "end" a perf output + * handle via the IRQ handler. And if the "sink" encounters a failure + * to "begin" another session (e.g due to lack of space in the buffer), + * the handle will be cleared. Thus, the event_data may not be accessible + * from the handle when we get to the etm_event_stop(), which is required + * for stopping the trace path. The event_data is guaranteed to stay alive + * until "free_aux()", which cannot happen as long as the event is active on + * the ETM. Thus the event_data for the session must be part of the ETM context + * to make sure we can disable the trace path. + */ +struct etm_ctxt { + struct perf_output_handle handle; + struct etm_event_data *event_data; +}; + +static DEFINE_PER_CPU(struct etm_ctxt, etm_ctxt); static DEFINE_PER_CPU(struct coresight_device *, csdev_src); -/* ETMv3.5/PTM's ETMCR is 'config' */ +/* + * The PMU formats were orignally for ETMv3.5/PTM's ETMCR 'config'; + * now take them as general formats and apply on all ETMs. + */ +PMU_FORMAT_ATTR(branch_broadcast, "config:"__stringify(ETM_OPT_BRANCH_BROADCAST)); PMU_FORMAT_ATTR(cycacc, "config:" __stringify(ETM_OPT_CYCACC)); +/* contextid1 enables tracing CONTEXTIDR_EL1 for ETMv4 */ +PMU_FORMAT_ATTR(contextid1, "config:" __stringify(ETM_OPT_CTXTID)); +/* contextid2 enables tracing CONTEXTIDR_EL2 for ETMv4 */ +PMU_FORMAT_ATTR(contextid2, "config:" __stringify(ETM_OPT_CTXTID2)); PMU_FORMAT_ATTR(timestamp, "config:" __stringify(ETM_OPT_TS)); PMU_FORMAT_ATTR(retstack, "config:" __stringify(ETM_OPT_RETSTK)); +/* preset - if sink ID is used as a configuration selector */ +PMU_FORMAT_ATTR(preset, "config:0-3"); +/* Sink ID - same for all ETMs */ +PMU_FORMAT_ATTR(sinkid, "config2:0-31"); +/* config ID - set if a system configuration is selected */ +PMU_FORMAT_ATTR(configid, "config2:32-63"); +PMU_FORMAT_ATTR(cc_threshold, "config3:0-11"); + + +/* + * contextid always traces the "PID". The PID is in CONTEXTIDR_EL1 + * when the kernel is running at EL1; when the kernel is at EL2, + * the PID is in CONTEXTIDR_EL2. + */ +static ssize_t format_attr_contextid_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + int pid_fmt = ETM_OPT_CTXTID; + +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) + pid_fmt = is_kernel_in_hyp_mode() ? ETM_OPT_CTXTID2 : ETM_OPT_CTXTID; +#endif + return sprintf(page, "config:%d\n", pid_fmt); +} + +static struct device_attribute format_attr_contextid = + __ATTR(contextid, 0444, format_attr_contextid_show, NULL); static struct attribute *etm_config_formats_attr[] = { &format_attr_cycacc.attr, + &format_attr_contextid.attr, + &format_attr_contextid1.attr, + &format_attr_contextid2.attr, &format_attr_timestamp.attr, &format_attr_retstack.attr, + &format_attr_sinkid.attr, + &format_attr_preset.attr, + &format_attr_configid.attr, + &format_attr_branch_broadcast.attr, + &format_attr_cc_threshold.attr, NULL, }; @@ -43,18 +111,38 @@ static const struct attribute_group etm_pmu_format_group = { .attrs = etm_config_formats_attr, }; +static struct attribute *etm_config_sinks_attr[] = { + NULL, +}; + +static const struct attribute_group etm_pmu_sinks_group = { + .name = "sinks", + .attrs = etm_config_sinks_attr, +}; + +static struct attribute *etm_config_events_attr[] = { + NULL, +}; + +static const struct attribute_group etm_pmu_events_group = { + .name = "events", + .attrs = etm_config_events_attr, +}; + static const struct attribute_group *etm_pmu_attr_groups[] = { &etm_pmu_format_group, + &etm_pmu_sinks_group, + &etm_pmu_events_group, NULL, }; -static inline struct list_head ** +static inline struct coresight_path ** etm_event_cpu_path_ptr(struct etm_event_data *data, int cpu) { return per_cpu_ptr(data->path, cpu); } -static inline struct list_head * +static inline struct coresight_path * etm_event_cpu_path(struct etm_event_data *data, int cpu) { return *etm_event_cpu_path_ptr(data, cpu); @@ -104,30 +192,58 @@ out: return ret; } +static void free_sink_buffer(struct etm_event_data *event_data) +{ + int cpu; + cpumask_t *mask = &event_data->mask; + struct coresight_device *sink; + + if (!event_data->snk_config) + return; + + if (WARN_ON(cpumask_empty(mask))) + return; + + cpu = cpumask_first(mask); + sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu)); + sink_ops(sink)->free_buffer(event_data->snk_config); +} + static void free_event_data(struct work_struct *work) { int cpu; cpumask_t *mask; struct etm_event_data *event_data; - struct coresight_device *sink; event_data = container_of(work, struct etm_event_data, work); mask = &event_data->mask; /* Free the sink buffers, if there are any */ - if (event_data->snk_config && !WARN_ON(cpumask_empty(mask))) { - cpu = cpumask_first(mask); - sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu)); - if (sink_ops(sink)->free_buffer) - sink_ops(sink)->free_buffer(event_data->snk_config); - } + free_sink_buffer(event_data); + + /* clear any configuration we were using */ + if (event_data->cfg_hash) + cscfg_deactivate_config(event_data->cfg_hash); for_each_cpu(cpu, mask) { - struct list_head **ppath; + struct coresight_path **ppath; ppath = etm_event_cpu_path_ptr(event_data, cpu); - if (!(IS_ERR_OR_NULL(*ppath))) + if (!(IS_ERR_OR_NULL(*ppath))) { + struct coresight_device *sink = coresight_get_sink(*ppath); + + /* + * Mark perf event as done for trace id allocator, but don't call + * coresight_trace_id_put_cpu_id_map() on individual IDs. Perf sessions + * never free trace IDs to ensure that the ID associated with a CPU + * cannot change during their and other's concurrent sessions. Instead, + * a refcount is used so that the last event to call + * coresight_trace_id_perf_stop() frees all IDs. + */ + coresight_trace_id_perf_stop(&sink->perf_sink_id_map); + coresight_release_path(*ppath); + } *ppath = NULL; } @@ -160,7 +276,7 @@ static void *alloc_event_data(int cpu) * unused memory when dealing with single CPU trace scenarios is small * compared to the cost of searching through an optimized array. */ - event_data->path = alloc_percpu(struct list_head *); + event_data->path = alloc_percpu(struct coresight_path *); if (!event_data->path) { kfree(event_data); @@ -177,33 +293,53 @@ static void etm_free_aux(void *data) schedule_work(&event_data->work); } -static void *etm_setup_aux(int event_cpu, void **pages, +/* + * Check if two given sinks are compatible with each other, + * so that they can use the same sink buffers, when an event + * moves around. + */ +static bool sinks_compatible(struct coresight_device *a, + struct coresight_device *b) +{ + if (!a || !b) + return false; + /* + * If the sinks are of the same subtype and driven + * by the same driver, we can use the same buffer + * on these sinks. + */ + return (a->subtype.sink_subtype == b->subtype.sink_subtype) && + (sink_ops(a) == sink_ops(b)); +} + +static void *etm_setup_aux(struct perf_event *event, void **pages, int nr_pages, bool overwrite) { - int cpu; + u32 id, cfg_hash; + int cpu = event->cpu; cpumask_t *mask; - struct coresight_device *sink; + struct coresight_device *sink = NULL; + struct coresight_device *user_sink = NULL, *last_sink = NULL; struct etm_event_data *event_data = NULL; - event_data = alloc_event_data(event_cpu); + event_data = alloc_event_data(cpu); if (!event_data) return NULL; INIT_WORK(&event_data->work, free_event_data); - /* - * In theory nothing prevent tracers in a trace session from being - * associated with different sinks, nor having a sink per tracer. But - * until we have HW with this kind of topology we need to assume tracers - * in a trace session are using the same sink. Therefore go through - * the coresight bus and pick the first enabled sink. - * - * When operated from sysFS users are responsible to enable the sink - * while from perf, the perf tools will do it based on the choice made - * on the cmd line. As such the "enable_sink" flag in sysFS is reset. - */ - sink = coresight_get_enabled_sink(true); - if (!sink || !sink_ops(sink)->alloc_buffer) - goto err; + /* First get the selected sink from user space. */ + if (event->attr.config2 & GENMASK_ULL(31, 0)) { + id = (u32)event->attr.config2; + sink = user_sink = coresight_get_sink_by_id(id); + } + + /* check if user wants a coresight configuration selected */ + cfg_hash = (u32)((event->attr.config2 & GENMASK_ULL(63, 32)) >> 32); + if (cfg_hash) { + if (cscfg_activate_config(cfg_hash)) + goto err; + event_data->cfg_hash = cfg_hash; + } mask = &event_data->mask; @@ -215,7 +351,7 @@ static void *etm_setup_aux(int event_cpu, void **pages, * CPUs, we can handle it and fail the session. */ for_each_cpu(cpu, mask) { - struct list_head *path; + struct coresight_path *path; struct coresight_device *csdev; csdev = per_cpu(csdev_src, cpu); @@ -230,6 +366,47 @@ static void *etm_setup_aux(int event_cpu, void **pages, } /* + * If AUX pause feature is enabled but the ETM driver does not + * support the operations, clear this CPU from the mask and + * continue to next one. + */ + if (event->attr.aux_start_paused && + (!source_ops(csdev)->pause_perf || !source_ops(csdev)->resume_perf)) { + dev_err_once(&csdev->dev, "AUX pause is not supported.\n"); + cpumask_clear_cpu(cpu, mask); + continue; + } + + /* + * No sink provided - look for a default sink for all the ETMs, + * where this event can be scheduled. + * We allocate the sink specific buffers only once for this + * event. If the ETMs have different default sink devices, we + * can only use a single "type" of sink as the event can carry + * only one sink specific buffer. Thus we have to make sure + * that the sinks are of the same type and driven by the same + * driver, as the one we allocate the buffer for. As such + * we choose the first sink and check if the remaining ETMs + * have a compatible default sink. We don't trace on a CPU + * if the sink is not compatible. + */ + if (!user_sink) { + /* Find the default sink for this ETM */ + sink = coresight_find_default_sink(csdev); + if (!sink) { + cpumask_clear_cpu(cpu, mask); + continue; + } + + /* Check if this sink compatible with the last sink */ + if (last_sink && !sinks_compatible(last_sink, sink)) { + cpumask_clear_cpu(cpu, mask); + continue; + } + last_sink = sink; + } + + /* * Building a path doesn't enable it, it simply builds a * list of devices from source to sink that can be * referenced later when the path is actually needed. @@ -240,17 +417,38 @@ static void *etm_setup_aux(int event_cpu, void **pages, continue; } + /* ensure we can allocate a trace ID for this CPU */ + coresight_path_assign_trace_id(path, CS_MODE_PERF); + if (!IS_VALID_CS_TRACE_ID(path->trace_id)) { + cpumask_clear_cpu(cpu, mask); + coresight_release_path(path); + continue; + } + + coresight_trace_id_perf_start(&sink->perf_sink_id_map); *etm_event_cpu_path_ptr(event_data, cpu) = path; } + /* no sink found for any CPU - cannot trace */ + if (!sink) + goto err; + /* If we don't have any CPUs ready for tracing, abort */ cpu = cpumask_first(mask); if (cpu >= nr_cpu_ids) goto err; - /* Allocate the sink buffer for this session */ + if (!sink_ops(sink)->alloc_buffer || !sink_ops(sink)->free_buffer) + goto err; + + /* + * Allocate the sink buffer for this session. All the sinks + * where this event can be scheduled are ensured to be of the + * same type. Thus the same sink configuration is used by the + * sinks. + */ event_data->snk_config = - sink_ops(sink)->alloc_buffer(sink, cpu, pages, + sink_ops(sink)->alloc_buffer(sink, event, pages, nr_pages, overwrite); if (!event_data->snk_config) goto err; @@ -264,17 +462,40 @@ err: goto out; } +static int etm_event_resume(struct coresight_device *csdev, + struct etm_ctxt *ctxt) +{ + if (!ctxt->event_data) + return 0; + + return coresight_resume_source(csdev); +} + static void etm_event_start(struct perf_event *event, int flags) { int cpu = smp_processor_id(); struct etm_event_data *event_data; - struct perf_output_handle *handle = this_cpu_ptr(&ctx_handle); + struct etm_ctxt *ctxt = this_cpu_ptr(&etm_ctxt); + struct perf_output_handle *handle = &ctxt->handle; struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); - struct list_head *path; + struct coresight_path *path; + u64 hw_id; if (!csdev) goto fail; + if (flags & PERF_EF_RESUME) { + if (etm_event_resume(csdev, ctxt) < 0) { + dev_err(&csdev->dev, "Failed to resume ETM event.\n"); + goto fail; + } + return; + } + + /* Have we messed up our tracking ? */ + if (WARN_ON(ctxt->event_data)) + goto fail; + /* * Deal with the ring buffer API and get a handle on the * session's information. @@ -283,34 +504,124 @@ static void etm_event_start(struct perf_event *event, int flags) if (!event_data) goto fail; + /* + * Check if this ETM is allowed to trace, as decided + * at etm_setup_aux(). This could be due to an unreachable + * sink from this ETM. We can't do much in this case if + * the sink was specified or hinted to the driver. For + * now, simply don't record anything on this ETM. + * + * As such we pretend that everything is fine, and let + * it continue without actually tracing. The event could + * continue tracing when it moves to a CPU where it is + * reachable to a sink. + */ + if (!cpumask_test_cpu(cpu, &event_data->mask)) + goto out; + path = etm_event_cpu_path(event_data, cpu); + path->handle = handle; /* We need a sink, no need to continue without one */ sink = coresight_get_sink(path); if (WARN_ON_ONCE(!sink)) goto fail_end_stop; /* Nothing will happen without a path */ - if (coresight_enable_path(path, CS_MODE_PERF, handle)) + if (coresight_enable_path(path, CS_MODE_PERF)) goto fail_end_stop; - /* Tell the perf core the event is alive */ - event->hw.state = 0; - /* Finally enable the tracer */ - if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) + if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF, path)) goto fail_disable_path; + /* + * output cpu / trace ID in perf record, once for the lifetime + * of the event. + */ + if (!cpumask_test_cpu(cpu, &event_data->aux_hwid_done)) { + cpumask_set_cpu(cpu, &event_data->aux_hwid_done); + + hw_id = FIELD_PREP(CS_AUX_HW_ID_MAJOR_VERSION_MASK, + CS_AUX_HW_ID_MAJOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_MINOR_VERSION_MASK, + CS_AUX_HW_ID_MINOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, path->trace_id); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_SINK_ID_MASK, coresight_get_sink_id(sink)); + + perf_report_aux_output_id(event, hw_id); + } + out: + /* Tell the perf core the event is alive */ + event->hw.state = 0; + /* Save the event_data for this ETM */ + ctxt->event_data = event_data; return; fail_disable_path: coresight_disable_path(path); fail_end_stop: - perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); - perf_aux_output_end(handle, 0); + /* + * Check if the handle is still associated with the event, + * to handle cases where if the sink failed to start the + * trace and TRUNCATED the handle already. + */ + if (READ_ONCE(handle->event)) { + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); + perf_aux_output_end(handle, 0); + } fail: event->hw.state = PERF_HES_STOPPED; - goto out; + return; +} + +static void etm_event_pause(struct perf_event *event, + struct coresight_device *csdev, + struct etm_ctxt *ctxt) +{ + int cpu = smp_processor_id(); + struct coresight_device *sink; + struct perf_output_handle *handle = &ctxt->handle; + struct coresight_path *path; + unsigned long size; + + if (!ctxt->event_data) + return; + + /* Stop tracer */ + coresight_pause_source(csdev); + + path = etm_event_cpu_path(ctxt->event_data, cpu); + sink = coresight_get_sink(path); + if (WARN_ON_ONCE(!sink)) + return; + + /* + * The per CPU sink has own interrupt handling, it might have + * race condition with updating buffer on AUX trace pause if + * it is invoked from NMI. To avoid the race condition, + * disallows updating buffer for the per CPU sink case. + */ + if (coresight_is_percpu_sink(sink)) + return; + + if (WARN_ON_ONCE(handle->event != event)) + return; + + if (!sink_ops(sink)->update_buffer) + return; + + size = sink_ops(sink)->update_buffer(sink, handle, + ctxt->event_data->snk_config); + if (READ_ONCE(handle->event)) { + if (!size) + return; + + perf_aux_output_end(handle, size); + perf_aux_output_begin(handle, event); + } else { + WARN_ON_ONCE(size); + } } static void etm_event_stop(struct perf_event *event, int mode) @@ -318,13 +629,46 @@ static void etm_event_stop(struct perf_event *event, int mode) int cpu = smp_processor_id(); unsigned long size; struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); - struct perf_output_handle *handle = this_cpu_ptr(&ctx_handle); - struct etm_event_data *event_data = perf_get_aux(handle); - struct list_head *path; + struct etm_ctxt *ctxt = this_cpu_ptr(&etm_ctxt); + struct perf_output_handle *handle = &ctxt->handle; + struct etm_event_data *event_data; + struct coresight_path *path; + + if (mode & PERF_EF_PAUSE) + return etm_event_pause(event, csdev, ctxt); + + /* + * If we still have access to the event_data via handle, + * confirm that we haven't messed up the tracking. + */ + if (handle->event && + WARN_ON(perf_get_aux(handle) != ctxt->event_data)) + return; + + event_data = ctxt->event_data; + /* Clear the event_data as this ETM is stopping the trace. */ + ctxt->event_data = NULL; if (event->hw.state == PERF_HES_STOPPED) return; + /* We must have a valid event_data for a running event */ + if (WARN_ON(!event_data)) + return; + + /* + * Check if this ETM was allowed to trace, as decided at + * etm_setup_aux(). If it wasn't allowed to trace, then + * nothing needs to be torn down other than outputting a + * zero sized record. + */ + if (handle->event && (mode & PERF_EF_UPDATE) && + !cpumask_test_cpu(cpu, &event_data->mask)) { + event->hw.state = PERF_HES_STOPPED; + perf_aux_output_end(handle, 0); + return; + } + if (!csdev) return; @@ -337,12 +681,18 @@ static void etm_event_stop(struct perf_event *event, int mode) return; /* stop tracer */ - source_ops(csdev)->disable(csdev, event); + coresight_disable_source(csdev, event); /* tell the core */ event->hw.state = PERF_HES_STOPPED; - if (mode & PERF_EF_UPDATE) { + /* + * If the handle is not bound to an event anymore + * (e.g, the sink driver was unable to restart the + * handle due to lack of buffer space), we don't + * have to do anything here. + */ + if (handle->event && (mode & PERF_EF_UPDATE)) { if (WARN_ON_ONCE(handle->event != event)) return; @@ -352,7 +702,21 @@ static void etm_event_stop(struct perf_event *event, int mode) size = sink_ops(sink)->update_buffer(sink, handle, event_data->snk_config); - perf_aux_output_end(handle, size); + /* + * Make sure the handle is still valid as the + * sink could have closed it from an IRQ. + * The sink driver must handle the race with + * update_buffer() and IRQ. Thus either we + * should get a valid handle and valid size + * (which may be 0). + * + * But we should never get a non-zero size with + * an invalid handle. + */ + if (READ_ONCE(handle->event)) + perf_aux_output_end(handle, size); + else + WARN_ON(size); } /* Disabling the path make its elements available to other sessions */ @@ -422,15 +786,16 @@ static int etm_addr_filters_validate(struct list_head *filters) static void etm_addr_filters_sync(struct perf_event *event) { struct perf_addr_filters_head *head = perf_event_addr_filters(event); - unsigned long start, stop, *offs = event->addr_filters_offs; + unsigned long start, stop; + struct perf_addr_filter_range *fr = event->addr_filter_ranges; struct etm_filters *filters = event->hw.addr_filters; struct etm_filter *etm_filter; struct perf_addr_filter *filter; int i = 0; list_for_each_entry(filter, &head->list, entry) { - start = filter->offset + offs[i]; - stop = start + filter->size; + start = fr[i].start; + stop = start + fr[i].size; etm_filter = &filters->etm_filter[i]; switch (filter->action) { @@ -478,12 +843,146 @@ int etm_perf_symlink(struct coresight_device *csdev, bool link) return 0; } +EXPORT_SYMBOL_GPL(etm_perf_symlink); + +static ssize_t etm_perf_sink_name_show(struct device *dev, + struct device_attribute *dattr, + char *buf) +{ + struct dev_ext_attribute *ea; + + ea = container_of(dattr, struct dev_ext_attribute, attr); + return scnprintf(buf, PAGE_SIZE, "0x%px\n", ea->var); +} -static int __init etm_perf_init(void) +static struct dev_ext_attribute * +etm_perf_add_symlink_group(struct device *dev, const char *name, const char *group_name) { + struct dev_ext_attribute *ea; + unsigned long hash; int ret; + struct device *pmu_dev = etm_pmu.dev; + + if (!etm_perf_up) + return ERR_PTR(-EPROBE_DEFER); + + ea = devm_kzalloc(dev, sizeof(*ea), GFP_KERNEL); + if (!ea) + return ERR_PTR(-ENOMEM); - etm_pmu.capabilities = PERF_PMU_CAP_EXCLUSIVE; + /* + * If this function is called adding a sink then the hash is used for + * sink selection - see function coresight_get_sink_by_id(). + * If adding a configuration then the hash is used for selection in + * cscfg_activate_config() + */ + hash = hashlen_hash(hashlen_string(NULL, name)); + + sysfs_attr_init(&ea->attr.attr); + ea->attr.attr.name = devm_kstrdup(dev, name, GFP_KERNEL); + if (!ea->attr.attr.name) + return ERR_PTR(-ENOMEM); + + ea->attr.attr.mode = 0444; + ea->var = (unsigned long *)hash; + + ret = sysfs_add_file_to_group(&pmu_dev->kobj, + &ea->attr.attr, group_name); + + return ret ? ERR_PTR(ret) : ea; +} + +int etm_perf_add_symlink_sink(struct coresight_device *csdev) +{ + const char *name; + struct device *dev = &csdev->dev; + int err = 0; + + if (csdev->type != CORESIGHT_DEV_TYPE_SINK && + csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) + return -EINVAL; + + if (csdev->ea != NULL) + return -EINVAL; + + name = dev_name(dev); + csdev->ea = etm_perf_add_symlink_group(dev, name, "sinks"); + if (IS_ERR(csdev->ea)) { + err = PTR_ERR(csdev->ea); + csdev->ea = NULL; + } else + csdev->ea->attr.show = etm_perf_sink_name_show; + + return err; +} + +static void etm_perf_del_symlink_group(struct dev_ext_attribute *ea, const char *group_name) +{ + struct device *pmu_dev = etm_pmu.dev; + + sysfs_remove_file_from_group(&pmu_dev->kobj, + &ea->attr.attr, group_name); +} + +void etm_perf_del_symlink_sink(struct coresight_device *csdev) +{ + if (csdev->type != CORESIGHT_DEV_TYPE_SINK && + csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) + return; + + if (!csdev->ea) + return; + + etm_perf_del_symlink_group(csdev->ea, "sinks"); + csdev->ea = NULL; +} + +static ssize_t etm_perf_cscfg_event_show(struct device *dev, + struct device_attribute *dattr, + char *buf) +{ + struct dev_ext_attribute *ea; + + ea = container_of(dattr, struct dev_ext_attribute, attr); + return scnprintf(buf, PAGE_SIZE, "configid=0x%px\n", ea->var); +} + +int etm_perf_add_symlink_cscfg(struct device *dev, struct cscfg_config_desc *config_desc) +{ + int err = 0; + + if (config_desc->event_ea != NULL) + return 0; + + config_desc->event_ea = etm_perf_add_symlink_group(dev, config_desc->name, "events"); + + /* set the show function to the custom cscfg event */ + if (!IS_ERR(config_desc->event_ea)) + config_desc->event_ea->attr.show = etm_perf_cscfg_event_show; + else { + err = PTR_ERR(config_desc->event_ea); + config_desc->event_ea = NULL; + } + + return err; +} + +void etm_perf_del_symlink_cscfg(struct cscfg_config_desc *config_desc) +{ + if (!config_desc->event_ea) + return; + + etm_perf_del_symlink_group(config_desc->event_ea, "events"); + config_desc->event_ea = NULL; +} + +int __init etm_perf_init(void) +{ + int ret; + + etm_pmu.capabilities = (PERF_PMU_CAP_EXCLUSIVE | + PERF_PMU_CAP_ITRACE | + PERF_PMU_CAP_AUX_PAUSE); etm_pmu.attr_groups = etm_pmu_attr_groups; etm_pmu.task_ctx_nr = perf_sw_context; @@ -498,6 +997,7 @@ static int __init etm_perf_init(void) etm_pmu.addr_filters_sync = etm_addr_filters_sync; etm_pmu.addr_filters_validate = etm_addr_filters_validate; etm_pmu.nr_addr_filters = ETM_ADDR_CMP_MAX; + etm_pmu.module = THIS_MODULE; ret = perf_pmu_register(&etm_pmu, CORESIGHT_ETM_PMU_NAME, -1); if (ret == 0) @@ -505,4 +1005,8 @@ static int __init etm_perf_init(void) return ret; } -device_initcall(etm_perf_init); + +void etm_perf_exit(void) +{ + perf_pmu_unregister(&etm_pmu); +} diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h index da7d9336a15c..5febbcdb8696 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.h +++ b/drivers/hwtracing/coresight/coresight-etm-perf.h @@ -11,6 +11,7 @@ #include "coresight-priv.h" struct coresight_device; +struct cscfg_config_desc; /* * In both ETMv3 and v4 the maximum number of address comparator implentable @@ -47,18 +48,23 @@ struct etm_filters { * struct etm_event_data - Coresight specifics associated to an event * @work: Handle to free allocated memory outside IRQ context. * @mask: Hold the CPU(s) this event was set for. + * @aux_hwid_done: Whether a CPU has emitted the TraceID packet or not. * @snk_config: The sink configuration. + * @cfg_hash: The hash id of any coresight config selected. * @path: An array of path, each slot for one CPU. */ struct etm_event_data { struct work_struct work; cpumask_t mask; + cpumask_t aux_hwid_done; void *snk_config; - struct list_head * __percpu *path; + u32 cfg_hash; + struct coresight_path * __percpu *path; }; -#ifdef CONFIG_CORESIGHT int etm_perf_symlink(struct coresight_device *csdev, bool link); +int etm_perf_add_symlink_sink(struct coresight_device *csdev); +void etm_perf_del_symlink_sink(struct coresight_device *csdev); static inline void *etm_perf_sink_config(struct perf_output_handle *handle) { struct etm_event_data *data = perf_get_aux(handle); @@ -67,15 +73,10 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle) return data->snk_config; return NULL; } -#else -static inline int etm_perf_symlink(struct coresight_device *csdev, bool link) -{ return -EINVAL; } - -static inline void *etm_perf_sink_config(struct perf_output_handle *handle) -{ - return NULL; -} - -#endif /* CONFIG_CORESIGHT */ +int etm_perf_add_symlink_cscfg(struct device *dev, + struct cscfg_config_desc *config_desc); +void etm_perf_del_symlink_cscfg(struct cscfg_config_desc *config_desc); +int __init etm_perf_init(void); +void etm_perf_exit(void); #endif diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h index 79e1ad860d8a..1d753cca2943 100644 --- a/drivers/hwtracing/coresight/coresight-etm.h +++ b/drivers/hwtracing/coresight/coresight-etm.h @@ -208,7 +208,6 @@ struct etm_config { /** * struct etm_drvdata - specifics associated to an ETM component * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @atclk: optional clock for the core parts of the ETM. * @csdev: component vitals needed by the framework. * @spinlock: only one at a time pls. @@ -216,7 +215,6 @@ struct etm_config { * @port_size: port size as reported by ETMCR bit 4-6 and 21. * @arch: ETM/PTM version number. * @use_cpu14: true if management registers need to be accessed via CP14. - * @mode: this tracer's mode, i.e sysFS, Perf or disabled. * @sticky_enable: true if ETM base configuration has been done. * @boot_enable:true if we should start tracing at boot time. * @os_unlock: true if access to management registers is allowed. @@ -231,8 +229,7 @@ struct etm_config { * @config: structure holding configuration parameters. */ struct etm_drvdata { - void __iomem *base; - struct device *dev; + struct csdev_access csa; struct clk *atclk; struct coresight_device *csdev; spinlock_t spinlock; @@ -240,7 +237,6 @@ struct etm_drvdata { int port_size; u8 arch; bool use_cp14; - local_t mode; bool sticky_enable; bool boot_enable; bool os_unlock; @@ -260,11 +256,11 @@ static inline void etm_writel(struct etm_drvdata *drvdata, { if (drvdata->use_cp14) { if (etm_writel_cp14(off, val)) { - dev_err(drvdata->dev, + dev_err(&drvdata->csdev->dev, "invalid CP14 access to ETM reg: %#x", off); } } else { - writel_relaxed(val, drvdata->base + off); + writel_relaxed(val, drvdata->csa.base + off); } } @@ -274,19 +270,19 @@ static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off) if (drvdata->use_cp14) { if (etm_readl_cp14(off, &val)) { - dev_err(drvdata->dev, + dev_err(&drvdata->csdev->dev, "invalid CP14 access to ETM reg: %#x", off); } } else { - val = readl_relaxed(drvdata->base + off); + val = readl_relaxed(drvdata->csa.base + off); } return val; } extern const struct attribute_group *coresight_etm_groups[]; -int etm_get_trace_id(struct etm_drvdata *drvdata); void etm_set_default(struct etm_config *config); void etm_config_trace_mode(struct etm_config *config); struct etm_config *get_etm_config(struct etm_drvdata *drvdata); +void etm_release_trace_id(struct etm_drvdata *drvdata); #endif diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 9a63e87ea5f3..a5e809589d3e 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -32,6 +32,7 @@ #include "coresight-etm.h" #include "coresight-etm-perf.h" +#include "coresight-trace-id.h" /* * Not really modular but using module_param is the easiest way to @@ -40,8 +41,6 @@ static int boot_enable; module_param_named(boot_enable, boot_enable, int, S_IRUGO); -/* The number of ETM/PTM currently registered */ -static int etm_count; static struct etm_drvdata *etmdrvdata[NR_CPUS]; static enum cpuhp_state hp_online; @@ -87,9 +86,9 @@ static void etm_set_pwrup(struct etm_drvdata *drvdata) { u32 etmpdcr; - etmpdcr = readl_relaxed(drvdata->base + ETMPDCR); + etmpdcr = readl_relaxed(drvdata->csa.base + ETMPDCR); etmpdcr |= ETMPDCR_PWD_UP; - writel_relaxed(etmpdcr, drvdata->base + ETMPDCR); + writel_relaxed(etmpdcr, drvdata->csa.base + ETMPDCR); /* Ensure pwrup completes before subsequent cp14 accesses */ mb(); isb(); @@ -102,9 +101,9 @@ static void etm_clr_pwrup(struct etm_drvdata *drvdata) /* Ensure pending cp14 accesses complete before clearing pwrup */ mb(); isb(); - etmpdcr = readl_relaxed(drvdata->base + ETMPDCR); + etmpdcr = readl_relaxed(drvdata->csa.base + ETMPDCR); etmpdcr &= ~ETMPDCR_PWD_UP; - writel_relaxed(etmpdcr, drvdata->base + ETMPDCR); + writel_relaxed(etmpdcr, drvdata->csa.base + ETMPDCR); } /** @@ -116,7 +115,7 @@ static void etm_clr_pwrup(struct etm_drvdata *drvdata) * * Basically the same as @coresight_timeout except for the register access * method where we have to account for CP14 configurations. - + * * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if * TIMEOUT_US has elapsed, which ever happens first. */ @@ -165,7 +164,7 @@ static void etm_set_prog(struct etm_drvdata *drvdata) */ isb(); if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 1)) { - dev_err(drvdata->dev, + dev_err(&drvdata->csdev->dev, "%s: timeout observed when probing at offset %#x\n", __func__, ETMSR); } @@ -184,7 +183,7 @@ static void etm_clr_prog(struct etm_drvdata *drvdata) */ isb(); if (coresight_timeout_etm(drvdata, ETMSR, ETMSR_PROG_BIT, 0)) { - dev_err(drvdata->dev, + dev_err(&drvdata->csdev->dev, "%s: timeout observed when probing at offset %#x\n", __func__, ETMSR); } @@ -206,7 +205,7 @@ void etm_set_default(struct etm_config *config) * set all bits in register 0x007, the ETMTECR2, to 0 * set register 0x008, the ETMTEEVR, to 0x6F (TRUE). */ - config->enable_ctrl1 = BIT(24); + config->enable_ctrl1 = ETMTECR1_INC_EXC; config->enable_ctrl2 = 0x0; config->enable_event = ETM_HARD_WIRE_RES_A; @@ -342,6 +341,10 @@ static int etm_parse_event_config(struct etm_drvdata *drvdata, config->ctrl = attr->config; + /* Don't trace contextID when runs in non-root PID namespace */ + if (!task_is_in_init_pid_ns(current)) + config->ctrl &= ~ETMCR_CTXID_SIZE; + /* * Possible to have cores with PTM (supports ret stack) and ETM * (never has ret stack) on the same SoC. So if we have a request @@ -360,10 +363,11 @@ static int etm_enable_hw(struct etm_drvdata *drvdata) int i, rc; u32 etmcr; struct etm_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; @@ -423,9 +427,9 @@ static int etm_enable_hw(struct etm_drvdata *drvdata) etm_clr_prog(drvdata); done: - CS_LOCK(drvdata->base); + CS_LOCK(drvdata->csa.base); - dev_dbg(drvdata->dev, "cpu: %d enable smp call done: %d\n", + dev_dbg(&drvdata->csdev->dev, "cpu: %d enable smp call done: %d\n", drvdata->cpu, rc); return rc; } @@ -435,13 +439,26 @@ struct etm_enable_arg { int rc; }; -static void etm_enable_hw_smp_call(void *info) +static void etm_enable_sysfs_smp_call(void *info) { struct etm_enable_arg *arg = info; + struct coresight_device *csdev; if (WARN_ON(!arg)) return; + + csdev = arg->drvdata->csdev; + if (!coresight_take_mode(csdev, CS_MODE_SYSFS)) { + /* Someone is already using the tracer */ + arg->rc = -EBUSY; + return; + } + arg->rc = etm_enable_hw(arg->drvdata); + + /* The tracer didn't start */ + if (arg->rc) + coresight_set_mode(csdev, CS_MODE_DISABLED); } static int etm_cpu_id(struct coresight_device *csdev) @@ -451,62 +468,48 @@ static int etm_cpu_id(struct coresight_device *csdev) return drvdata->cpu; } -int etm_get_trace_id(struct etm_drvdata *drvdata) +void etm_release_trace_id(struct etm_drvdata *drvdata) { - unsigned long flags; - int trace_id = -1; - - if (!drvdata) - goto out; - - if (!local_read(&drvdata->mode)) - return drvdata->traceid; - - pm_runtime_get_sync(drvdata->dev); - - spin_lock_irqsave(&drvdata->spinlock, flags); - - CS_UNLOCK(drvdata->base); - trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); - CS_LOCK(drvdata->base); - - spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(drvdata->dev); - -out: - return trace_id; - -} - -static int etm_trace_id(struct coresight_device *csdev) -{ - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return etm_get_trace_id(drvdata); + coresight_trace_id_put_cpu_id(drvdata->cpu); } static int etm_enable_perf(struct coresight_device *csdev, - struct perf_event *event) + struct perf_event *event, + struct coresight_path *path) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) return -EINVAL; + if (!coresight_take_mode(csdev, CS_MODE_PERF)) + return -EBUSY; + /* Configure the tracer based on the session's specifics */ etm_parse_event_config(drvdata, event); + drvdata->traceid = path->trace_id; + /* And enable it */ - return etm_enable_hw(drvdata); + ret = etm_enable_hw(drvdata); + + /* Failed to start tracer; roll back to DISABLED mode */ + if (ret) + coresight_set_mode(csdev, CS_MODE_DISABLED); + + return ret; } -static int etm_enable_sysfs(struct coresight_device *csdev) +static int etm_enable_sysfs(struct coresight_device *csdev, struct coresight_path *path) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - struct etm_enable_arg arg = { 0 }; + struct etm_enable_arg arg = { }; int ret; spin_lock(&drvdata->spinlock); + drvdata->traceid = path->trace_id; + /* * Configure the ETM only if the CPU is online. If it isn't online * hw configuration will take place on the local CPU during bring up. @@ -514,7 +517,7 @@ static int etm_enable_sysfs(struct coresight_device *csdev) if (cpu_online(drvdata->cpu)) { arg.drvdata = drvdata; ret = smp_call_function_single(drvdata->cpu, - etm_enable_hw_smp_call, &arg, 1); + etm_enable_sysfs_smp_call, &arg, 1); if (!ret) ret = arg.rc; if (!ret) @@ -523,51 +526,42 @@ static int etm_enable_sysfs(struct coresight_device *csdev) ret = -ENODEV; } + if (ret) + etm_release_trace_id(drvdata); + spin_unlock(&drvdata->spinlock); if (!ret) - dev_dbg(drvdata->dev, "ETM tracing enabled\n"); + dev_dbg(&csdev->dev, "ETM tracing enabled\n"); return ret; } -static int etm_enable(struct coresight_device *csdev, - struct perf_event *event, u32 mode) +static int etm_enable(struct coresight_device *csdev, struct perf_event *event, + enum cs_mode mode, struct coresight_path *path) { int ret; - u32 val; - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - val = local_cmpxchg(&drvdata->mode, CS_MODE_DISABLED, mode); - - /* Someone is already using the tracer */ - if (val) - return -EBUSY; switch (mode) { case CS_MODE_SYSFS: - ret = etm_enable_sysfs(csdev); + ret = etm_enable_sysfs(csdev, path); break; case CS_MODE_PERF: - ret = etm_enable_perf(csdev, event); + ret = etm_enable_perf(csdev, event, path); break; default: ret = -EINVAL; } - /* The tracer didn't start */ - if (ret) - local_set(&drvdata->mode, CS_MODE_DISABLED); - return ret; } -static void etm_disable_hw(void *info) +static void etm_disable_hw(struct etm_drvdata *drvdata) { int i; - struct etm_drvdata *drvdata = info; struct etm_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); etm_set_prog(drvdata); /* Read back sequencer and counters for post trace analysis */ @@ -577,11 +571,21 @@ static void etm_disable_hw(void *info) config->cntr_val[i] = etm_readl(drvdata, ETMCNTVRn(i)); etm_set_pwrdwn(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); - CS_LOCK(drvdata->base); + CS_LOCK(drvdata->csa.base); - dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu); + dev_dbg(&drvdata->csdev->dev, + "cpu: %d disable smp call done\n", drvdata->cpu); +} + +static void etm_disable_sysfs_smp_call(void *info) +{ + struct etm_drvdata *drvdata = info; + + etm_disable_hw(drvdata); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); } static void etm_disable_perf(struct coresight_device *csdev) @@ -591,7 +595,7 @@ static void etm_disable_perf(struct coresight_device *csdev) if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) return; - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); /* Setting the prog bit disables tracing immediately */ etm_set_prog(drvdata); @@ -601,9 +605,17 @@ static void etm_disable_perf(struct coresight_device *csdev) * power down the tracer. */ etm_set_pwrdwn(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); + + CS_LOCK(drvdata->csa.base); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); + + /* + * perf will release trace ids when _free_aux() + * is called at the end of the session + */ - CS_LOCK(drvdata->base); } static void etm_disable_sysfs(struct coresight_device *csdev) @@ -623,26 +635,33 @@ static void etm_disable_sysfs(struct coresight_device *csdev) * Executing etm_disable_hw on the cpu whose ETM is being disabled * ensures that register writes occur when cpu is powered. */ - smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1); + smp_call_function_single(drvdata->cpu, etm_disable_sysfs_smp_call, + drvdata, 1); spin_unlock(&drvdata->spinlock); cpus_read_unlock(); - dev_dbg(drvdata->dev, "ETM tracing disabled\n"); + /* + * we only release trace IDs when resetting sysfs. + * This permits sysfs users to read the trace ID after the trace + * session has completed. This maintains operational behaviour with + * prior trace id allocation method + */ + + dev_dbg(&csdev->dev, "ETM tracing disabled\n"); } static void etm_disable(struct coresight_device *csdev, struct perf_event *event) { - u32 mode; - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + enum cs_mode mode; /* * For as long as the tracer isn't disabled another entity can't * change its status. As such we can read the status here without * fearing it will change under us. */ - mode = local_read(&drvdata->mode); + mode = coresight_get_mode(csdev); switch (mode) { case CS_MODE_DISABLED: @@ -657,19 +676,16 @@ static void etm_disable(struct coresight_device *csdev, WARN_ON_ONCE(mode); return; } - - if (mode) - local_set(&drvdata->mode, CS_MODE_DISABLED); } static const struct coresight_ops_source etm_source_ops = { .cpu_id = etm_cpu_id, - .trace_id = etm_trace_id, .enable = etm_enable, .disable = etm_disable, }; static const struct coresight_ops etm_cs_ops = { + .trace_id = coresight_etm_get_trace_id, .source_ops = &etm_source_ops, }; @@ -679,7 +695,7 @@ static int etm_online_cpu(unsigned int cpu) return 0; if (etmdrvdata[cpu]->boot_enable && !etmdrvdata[cpu]->sticky_enable) - coresight_enable(etmdrvdata[cpu]->csdev); + coresight_enable_sysfs(etmdrvdata[cpu]->csdev); return 0; } @@ -694,7 +710,7 @@ static int etm_starting_cpu(unsigned int cpu) etmdrvdata[cpu]->os_unlock = true; } - if (local_read(&etmdrvdata[cpu]->mode)) + if (coresight_get_mode(etmdrvdata[cpu]->csdev)) etm_enable_hw(etmdrvdata[cpu]); spin_unlock(&etmdrvdata[cpu]->spinlock); return 0; @@ -706,7 +722,7 @@ static int etm_dying_cpu(unsigned int cpu) return 0; spin_lock(&etmdrvdata[cpu]->spinlock); - if (local_read(&etmdrvdata[cpu]->mode)) + if (coresight_get_mode(etmdrvdata[cpu]->csdev)) etm_disable_hw(etmdrvdata[cpu]); spin_unlock(&etmdrvdata[cpu]->spinlock); return 0; @@ -738,7 +754,7 @@ static void etm_init_arch_data(void *info) /* Make sure all registers are accessible */ etm_os_unlock(drvdata); - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); /* First dummy read */ (void)etm_readl(drvdata, ETMPDSR); @@ -769,14 +785,46 @@ static void etm_init_arch_data(void *info) drvdata->nr_ext_out = BMVAL(etmccr, 20, 22); drvdata->nr_ctxid_cmp = BMVAL(etmccr, 24, 25); + coresight_clear_self_claim_tag_unlocked(&drvdata->csa); etm_set_pwrdwn(drvdata); etm_clr_pwrup(drvdata); - CS_LOCK(drvdata->base); + CS_LOCK(drvdata->csa.base); +} + +static int __init etm_hp_setup(void) +{ + int ret; + + ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING, + "arm/coresight:starting", + etm_starting_cpu, etm_dying_cpu); + + if (ret) + return ret; + + ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, + "arm/coresight:online", + etm_online_cpu, NULL); + + /* HP dyn state ID returned in ret on success */ + if (ret > 0) { + hp_online = ret; + return 0; + } + + /* failed dyn state - remove others */ + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); + + return ret; } -static void etm_init_trace_id(struct etm_drvdata *drvdata) +static void etm_hp_clear(void) { - drvdata->traceid = coresight_get_trace_id(drvdata->cpu); + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); + if (hp_online) { + cpuhp_remove_state_nocalls(hp_online); + hp_online = 0; + } } static int etm_probe(struct amba_device *adev, const struct amba_id *id) @@ -788,22 +836,12 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) struct etm_drvdata *drvdata; struct resource *res = &adev->res; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - - adev->dev.platform_data = pdata; - drvdata->use_cp14 = of_property_read_bool(np, "arm,cp14"); - } - - drvdata->dev = &adev->dev; + drvdata->use_cp14 = fwnode_property_read_bool(dev->fwnode, "arm,cp14"); dev_set_drvdata(dev, drvdata); /* Validity for the resource is already checked by the AMBA core */ @@ -811,47 +849,37 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) if (IS_ERR(base)) return PTR_ERR(base); - drvdata->base = base; + desc.access = drvdata->csa = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } + drvdata->atclk = devm_clk_get_optional_enabled(dev, "atclk"); + if (IS_ERR(drvdata->atclk)) + return PTR_ERR(drvdata->atclk); - drvdata->cpu = pdata ? pdata->cpu : 0; + drvdata->cpu = coresight_get_cpu(dev); + if (drvdata->cpu < 0) + return drvdata->cpu; - cpus_read_lock(); - etmdrvdata[drvdata->cpu] = drvdata; + desc.name = devm_kasprintf(dev, GFP_KERNEL, "etm%d", drvdata->cpu); + if (!desc.name) + return -ENOMEM; if (smp_call_function_single(drvdata->cpu, etm_init_arch_data, drvdata, 1)) dev_err(dev, "ETM arch init failed\n"); - if (!etm_count++) { - cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING, - "arm/coresight:starting", - etm_starting_cpu, etm_dying_cpu); - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, - "arm/coresight:online", - etm_online_cpu, NULL); - if (ret < 0) - goto err_arch_supported; - hp_online = ret; - } - cpus_read_unlock(); - - if (etm_arch_supported(drvdata->arch) == false) { - ret = -EINVAL; - goto err_arch_supported; - } + if (etm_arch_supported(drvdata->arch) == false) + return -EINVAL; - etm_init_trace_id(drvdata); etm_set_default(&drvdata->config); + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + + adev->dev.platform_data = pdata; + desc.type = CORESIGHT_DEV_TYPE_SOURCE; desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC; desc.ops = &etm_cs_ops; @@ -859,33 +887,58 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) desc.dev = dev; desc.groups = coresight_etm_groups; drvdata->csdev = coresight_register(&desc); - if (IS_ERR(drvdata->csdev)) { - ret = PTR_ERR(drvdata->csdev); - goto err_arch_supported; - } + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); ret = etm_perf_symlink(drvdata->csdev, true); if (ret) { coresight_unregister(drvdata->csdev); - goto err_arch_supported; + return ret; } + etmdrvdata[drvdata->cpu] = drvdata; + pm_runtime_put(&adev->dev); - dev_info(dev, "%s initialized\n", (char *)id->data); + dev_info(&drvdata->csdev->dev, + "%s initialized\n", (char *)coresight_get_uci_data(id)); if (boot_enable) { - coresight_enable(drvdata->csdev); + coresight_enable_sysfs(drvdata->csdev); drvdata->boot_enable = true; } return 0; +} -err_arch_supported: - if (--etm_count == 0) { - cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); - if (hp_online) - cpuhp_remove_state_nocalls(hp_online); - } - return ret; +static void clear_etmdrvdata(void *info) +{ + int cpu = *(int *)info; + + etmdrvdata[cpu] = NULL; +} + +static void etm_remove(struct amba_device *adev) +{ + struct etm_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + etm_perf_symlink(drvdata->csdev, false); + + /* + * Taking hotplug lock here to avoid racing between etm_remove and + * CPU hotplug call backs. + */ + cpus_read_lock(); + /* + * The readers for etmdrvdata[] are CPU hotplug call backs + * and PM notification call backs. Change etmdrvdata[i] on + * CPU i ensures these call backs has consistent view + * inside one call back function. + */ + if (smp_call_function_single(drvdata->cpu, clear_etmdrvdata, &drvdata->cpu, 1)) + etmdrvdata[drvdata->cpu] = NULL; + + cpus_read_unlock(); + + coresight_unregister(drvdata->csdev); } #ifdef CONFIG_PM @@ -893,8 +946,7 @@ static int etm_runtime_suspend(struct device *dev) { struct etm_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); return 0; } @@ -903,10 +955,7 @@ static int etm_runtime_resume(struct device *dev) { struct etm_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); - - return 0; + return clk_prepare_enable(drvdata->atclk); } #endif @@ -915,47 +964,63 @@ static const struct dev_pm_ops etm_dev_pm_ops = { }; static const struct amba_id etm_ids[] = { - { /* ETM 3.3 */ - .id = 0x000bb921, - .mask = 0x000fffff, - .data = "ETM 3.3", - }, - { /* ETM 3.5 - Cortex-A5 */ - .id = 0x000bb955, - .mask = 0x000fffff, - .data = "ETM 3.5", - }, - { /* ETM 3.5 */ - .id = 0x000bb956, - .mask = 0x000fffff, - .data = "ETM 3.5", - }, - { /* PTM 1.0 */ - .id = 0x000bb950, - .mask = 0x000fffff, - .data = "PTM 1.0", - }, - { /* PTM 1.1 */ - .id = 0x000bb95f, - .mask = 0x000fffff, - .data = "PTM 1.1", - }, - { /* PTM 1.1 Qualcomm */ - .id = 0x000b006f, - .mask = 0x000fffff, - .data = "PTM 1.1", - }, - { 0, 0}, + /* ETM 3.3 */ + CS_AMBA_ID_DATA(0x000bb921, "ETM 3.3"), + /* ETM 3.5 - Cortex-A5 */ + CS_AMBA_ID_DATA(0x000bb955, "ETM 3.5"), + /* ETM 3.5 */ + CS_AMBA_ID_DATA(0x000bb956, "ETM 3.5"), + /* PTM 1.0 */ + CS_AMBA_ID_DATA(0x000bb950, "PTM 1.0"), + /* PTM 1.1 */ + CS_AMBA_ID_DATA(0x000bb95f, "PTM 1.1"), + /* PTM 1.1 Qualcomm */ + CS_AMBA_ID_DATA(0x000b006f, "PTM 1.1"), + { 0, 0, NULL}, }; +MODULE_DEVICE_TABLE(amba, etm_ids); + static struct amba_driver etm_driver = { .drv = { .name = "coresight-etm3x", - .owner = THIS_MODULE, .pm = &etm_dev_pm_ops, .suppress_bind_attrs = true, }, .probe = etm_probe, + .remove = etm_remove, .id_table = etm_ids, }; -builtin_amba_driver(etm_driver); + +static int __init etm_init(void) +{ + int ret; + + ret = etm_hp_setup(); + + /* etm_hp_setup() does its own cleanup - exit on error */ + if (ret) + return ret; + + ret = amba_driver_register(&etm_driver); + if (ret) { + pr_err("Error registering etm3x driver\n"); + etm_hp_clear(); + } + + return ret; +} + +static void __exit etm_exit(void) +{ + amba_driver_unregister(&etm_driver); + etm_hp_clear(); +} + +module_init(etm_init); +module_exit(etm_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight Program Flow Trace driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c index 75487b3fad86..762109307b86 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c @@ -48,15 +48,15 @@ static ssize_t etmsr_show(struct device *dev, unsigned long flags, val; struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); - pm_runtime_get_sync(drvdata->dev); + pm_runtime_get_sync(dev->parent); spin_lock_irqsave(&drvdata->spinlock, flags); - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); val = etm_readl(drvdata, ETMSR); - CS_LOCK(drvdata->base); + CS_LOCK(drvdata->csa.base); spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(drvdata->dev); + pm_runtime_put(dev->parent); return sprintf(buf, "%#lx\n", val); } @@ -85,6 +85,7 @@ static ssize_t reset_store(struct device *dev, } etm_set_default(config); + etm_release_trace_id(drvdata); spin_unlock(&drvdata->spinlock); } @@ -131,7 +132,7 @@ static ssize_t mode_store(struct device *dev, if (config->mode & ETM_MODE_STALL) { if (!(drvdata->etmccr & ETMCCR_FIFOFULL)) { - dev_warn(drvdata->dev, "stall mode not supported\n"); + dev_warn(dev, "stall mode not supported\n"); ret = -EINVAL; goto err_unlock; } @@ -141,7 +142,7 @@ static ssize_t mode_store(struct device *dev, if (config->mode & ETM_MODE_TIMESTAMP) { if (!(drvdata->etmccer & ETMCCER_TIMESTAMP)) { - dev_warn(drvdata->dev, "timestamp not supported\n"); + dev_warn(dev, "timestamp not supported\n"); ret = -EINVAL; goto err_unlock; } @@ -474,7 +475,7 @@ static ssize_t addr_start_store(struct device *dev, config->addr_val[idx] = val; config->addr_type[idx] = ETM_ADDR_TYPE_START; config->startstop_ctrl |= (1 << idx); - config->enable_ctrl1 |= BIT(25); + config->enable_ctrl1 |= ETMTECR1_START_STOP; spin_unlock(&drvdata->spinlock); return size; @@ -721,7 +722,7 @@ static ssize_t cntr_val_show(struct device *dev, struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etm_config *config = &drvdata->config; - if (!local_read(&drvdata->mode)) { + if (!coresight_get_mode(drvdata->csdev)) { spin_lock(&drvdata->spinlock); for (i = 0; i < drvdata->nr_cntr; i++) ret += sprintf(buf, "counter %d: %x\n", @@ -940,20 +941,20 @@ static ssize_t seq_curr_state_show(struct device *dev, struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etm_config *config = &drvdata->config; - if (!local_read(&drvdata->mode)) { + if (!coresight_get_mode(drvdata->csdev)) { val = config->seq_curr_state; goto out; } - pm_runtime_get_sync(drvdata->dev); + pm_runtime_get_sync(dev->parent); spin_lock_irqsave(&drvdata->spinlock, flags); - CS_UNLOCK(drvdata->base); + CS_UNLOCK(drvdata->csa.base); val = (etm_readl(drvdata, ETMSQR) & ETM_SQR_MASK); - CS_LOCK(drvdata->base); + CS_LOCK(drvdata->csa.base); spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(drvdata->dev); + pm_runtime_put(dev->parent); out: return sprintf(buf, "%#lx\n", val); } @@ -1189,30 +1190,15 @@ static DEVICE_ATTR_RO(cpu); static ssize_t traceid_show(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned long val; struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); + int trace_id = coresight_etm_get_trace_id(drvdata->csdev, CS_MODE_SYSFS, NULL); - val = etm_get_trace_id(drvdata); + if (trace_id < 0) + return trace_id; - return sprintf(buf, "%#lx\n", val); + return sysfs_emit(buf, "%#x\n", trace_id); } - -static ssize_t traceid_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret; - unsigned long val; - struct etm_drvdata *drvdata = dev_get_drvdata(dev->parent); - - ret = kstrtoul(buf, 16, &val); - if (ret) - return ret; - - drvdata->traceid = val & ETM_TRACEID_MASK; - return size; -} -static DEVICE_ATTR_RW(traceid); +static DEVICE_ATTR_RO(traceid); static struct attribute *coresight_etm_attrs[] = { &dev_attr_nr_addr_cmp.attr, @@ -1252,31 +1238,17 @@ static struct attribute *coresight_etm_attrs[] = { NULL, }; -#define coresight_etm3x_reg(name, offset) \ - coresight_simple_reg32(struct etm_drvdata, name, offset) - -coresight_etm3x_reg(etmccr, ETMCCR); -coresight_etm3x_reg(etmccer, ETMCCER); -coresight_etm3x_reg(etmscr, ETMSCR); -coresight_etm3x_reg(etmidr, ETMIDR); -coresight_etm3x_reg(etmcr, ETMCR); -coresight_etm3x_reg(etmtraceidr, ETMTRACEIDR); -coresight_etm3x_reg(etmteevr, ETMTEEVR); -coresight_etm3x_reg(etmtssvr, ETMTSSCR); -coresight_etm3x_reg(etmtecr1, ETMTECR1); -coresight_etm3x_reg(etmtecr2, ETMTECR2); - static struct attribute *coresight_etm_mgmt_attrs[] = { - &dev_attr_etmccr.attr, - &dev_attr_etmccer.attr, - &dev_attr_etmscr.attr, - &dev_attr_etmidr.attr, - &dev_attr_etmcr.attr, - &dev_attr_etmtraceidr.attr, - &dev_attr_etmteevr.attr, - &dev_attr_etmtssvr.attr, - &dev_attr_etmtecr1.attr, - &dev_attr_etmtecr2.attr, + coresight_simple_reg32(etmccr, ETMCCR), + coresight_simple_reg32(etmccer, ETMCCER), + coresight_simple_reg32(etmscr, ETMSCR), + coresight_simple_reg32(etmidr, ETMIDR), + coresight_simple_reg32(etmcr, ETMCR), + coresight_simple_reg32(etmtraceidr, ETMTRACEIDR), + coresight_simple_reg32(etmteevr, ETMTEEVR), + coresight_simple_reg32(etmtssvr, ETMTSSCR), + coresight_simple_reg32(etmtecr1, ETMTECR1), + coresight_simple_reg32(etmtecr2, ETMTECR2), NULL, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-cfg.c b/drivers/hwtracing/coresight/coresight-etm4x-cfg.c new file mode 100644 index 000000000000..c302072b293a --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-etm4x-cfg.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(C) 2020 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include "coresight-etm4x.h" +#include "coresight-etm4x-cfg.h" +#include "coresight-priv.h" +#include "coresight-syscfg.h" + +/* defines to associate register IDs with driver data locations */ +#define CHECKREG(cval, elem) \ + { \ + if (offset == cval) { \ + reg_csdev->driver_regval = &drvcfg->elem; \ + err = 0; \ + break; \ + } \ + } + +#define CHECKREGIDX(cval, elem, off_idx, mask) \ + { \ + if (mask == cval) { \ + reg_csdev->driver_regval = &drvcfg->elem[off_idx]; \ + err = 0; \ + break; \ + } \ + } + +/** + * etm4_cfg_map_reg_offset - validate and map the register offset into a + * location in the driver config struct. + * + * Limits the number of registers that can be accessed and programmed in + * features, to those which are used to control the trace capture parameters. + * + * Omits or limits access to those which the driver must use exclusively. + * + * Invalid offsets will result in fail code return and feature load failure. + * + * @drvdata: driver data to map into. + * @reg_csdev: register to map. + * @offset: device offset for the register + */ +static int etm4_cfg_map_reg_offset(struct etmv4_drvdata *drvdata, + struct cscfg_regval_csdev *reg_csdev, u32 offset) +{ + int err = -EINVAL, idx; + struct etmv4_config *drvcfg = &drvdata->config; + u32 off_mask; + + if (((offset >= TRCEVENTCTL0R) && (offset <= TRCVIPCSSCTLR)) || + ((offset >= TRCSEQRSTEVR) && (offset <= TRCEXTINSELR)) || + ((offset >= TRCCIDCCTLR0) && (offset <= TRCVMIDCCTLR1))) { + do { + CHECKREG(TRCEVENTCTL0R, eventctrl0); + CHECKREG(TRCEVENTCTL1R, eventctrl1); + CHECKREG(TRCSTALLCTLR, stall_ctrl); + CHECKREG(TRCTSCTLR, ts_ctrl); + CHECKREG(TRCSYNCPR, syncfreq); + CHECKREG(TRCCCCTLR, ccctlr); + CHECKREG(TRCBBCTLR, bb_ctrl); + CHECKREG(TRCVICTLR, vinst_ctrl); + CHECKREG(TRCVIIECTLR, viiectlr); + CHECKREG(TRCVISSCTLR, vissctlr); + CHECKREG(TRCVIPCSSCTLR, vipcssctlr); + CHECKREG(TRCSEQRSTEVR, seq_rst); + CHECKREG(TRCSEQSTR, seq_state); + CHECKREG(TRCEXTINSELR, ext_inp); + CHECKREG(TRCCIDCCTLR0, ctxid_mask0); + CHECKREG(TRCCIDCCTLR1, ctxid_mask1); + CHECKREG(TRCVMIDCCTLR0, vmid_mask0); + CHECKREG(TRCVMIDCCTLR1, vmid_mask1); + } while (0); + } else if ((offset & GENMASK(11, 4)) == TRCSEQEVRn(0)) { + /* sequencer state control registers */ + idx = (offset & GENMASK(3, 0)) / 4; + if (idx < ETM_MAX_SEQ_STATES) { + reg_csdev->driver_regval = &drvcfg->seq_ctrl[idx]; + err = 0; + } + } else if ((offset >= TRCSSCCRn(0)) && (offset <= TRCSSPCICRn(7))) { + /* 32 bit, 8 off indexed register sets */ + idx = (offset & GENMASK(4, 0)) / 4; + off_mask = (offset & GENMASK(11, 5)); + do { + CHECKREGIDX(TRCSSCCRn(0), ss_ctrl, idx, off_mask); + CHECKREGIDX(TRCSSCSRn(0), ss_status, idx, off_mask); + CHECKREGIDX(TRCSSPCICRn(0), ss_pe_cmp, idx, off_mask); + } while (0); + } else if ((offset >= TRCCIDCVRn(0)) && (offset <= TRCVMIDCVRn(7))) { + /* 64 bit, 8 off indexed register sets */ + idx = (offset & GENMASK(5, 0)) / 8; + off_mask = (offset & GENMASK(11, 6)); + do { + CHECKREGIDX(TRCCIDCVRn(0), ctxid_pid, idx, off_mask); + CHECKREGIDX(TRCVMIDCVRn(0), vmid_val, idx, off_mask); + } while (0); + } else if ((offset >= TRCRSCTLRn(2)) && + (offset <= TRCRSCTLRn((ETM_MAX_RES_SEL - 1)))) { + /* 32 bit resource selection regs, 32 off, skip fixed 0,1 */ + idx = (offset & GENMASK(6, 0)) / 4; + if (idx < ETM_MAX_RES_SEL) { + reg_csdev->driver_regval = &drvcfg->res_ctrl[idx]; + err = 0; + } + } else if ((offset >= TRCACVRn(0)) && + (offset <= TRCACATRn((ETM_MAX_SINGLE_ADDR_CMP - 1)))) { + /* 64 bit addr cmp regs, 16 off */ + idx = (offset & GENMASK(6, 0)) / 8; + off_mask = offset & GENMASK(11, 7); + do { + CHECKREGIDX(TRCACVRn(0), addr_val, idx, off_mask); + CHECKREGIDX(TRCACATRn(0), addr_acc, idx, off_mask); + } while (0); + } else if ((offset >= TRCCNTRLDVRn(0)) && + (offset <= TRCCNTVRn((ETMv4_MAX_CNTR - 1)))) { + /* 32 bit counter regs, 4 off (ETMv4_MAX_CNTR - 1) */ + idx = (offset & GENMASK(3, 0)) / 4; + off_mask = offset & GENMASK(11, 4); + do { + CHECKREGIDX(TRCCNTRLDVRn(0), cntrldvr, idx, off_mask); + CHECKREGIDX(TRCCNTCTLRn(0), cntr_ctrl, idx, off_mask); + CHECKREGIDX(TRCCNTVRn(0), cntr_val, idx, off_mask); + } while (0); + } + return err; +} + +/** + * etm4_cfg_load_feature - load a feature into a device instance. + * + * @csdev: An ETMv4 CoreSight device. + * @feat_csdev: The feature to be loaded. + * + * The function will load a feature instance into the device, checking that + * the register definitions are valid for the device. + * + * Parameter and register definitions will be converted into internal + * structures that are used to set the values in the driver when the + * feature is enabled for the device. + * + * The feature spinlock pointer is initialised to the same spinlock + * that the driver uses to protect the internal register values. + */ +static int etm4_cfg_load_feature(struct coresight_device *csdev, + struct cscfg_feature_csdev *feat_csdev) +{ + struct device *dev = csdev->dev.parent; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); + const struct cscfg_feature_desc *feat_desc = feat_csdev->feat_desc; + u32 offset; + int i = 0, err = 0; + + /* + * essential we set the device spinlock - this is used in the generic + * programming routines when copying values into the drvdata structures + * via the pointers setup in etm4_cfg_map_reg_offset(). + */ + feat_csdev->drv_spinlock = &drvdata->spinlock; + + /* process the register descriptions */ + for (i = 0; i < feat_csdev->nr_regs && !err; i++) { + offset = feat_desc->regs_desc[i].offset; + err = etm4_cfg_map_reg_offset(drvdata, &feat_csdev->regs_csdev[i], offset); + } + return err; +} + +/* match information when loading configurations */ +#define CS_CFG_ETM4_MATCH_FLAGS (CS_CFG_MATCH_CLASS_SRC_ALL | \ + CS_CFG_MATCH_CLASS_SRC_ETM4) + +int etm4_cscfg_register(struct coresight_device *csdev) +{ + struct cscfg_csdev_feat_ops ops; + + ops.load_feat = &etm4_cfg_load_feature; + + return cscfg_register_csdev(csdev, CS_CFG_ETM4_MATCH_FLAGS, &ops); +} diff --git a/drivers/hwtracing/coresight/coresight-etm4x-cfg.h b/drivers/hwtracing/coresight/coresight-etm4x-cfg.h new file mode 100644 index 000000000000..32dab34c1dac --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-etm4x-cfg.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2014-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef _CORESIGHT_ETM4X_CFG_H +#define _CORESIGHT_ETM4X_CFG_H + +#include "coresight-config.h" +#include "coresight-etm4x.h" + +/* ETMv4 specific config defines */ + +/* resource IDs */ + +#define ETM4_CFG_RES_CTR 0x001 +#define ETM4_CFG_RES_CMP 0x002 +#define ETM4_CFG_RES_CMP_PAIR0 0x003 +#define ETM4_CFG_RES_CMP_PAIR1 0x004 +#define ETM4_CFG_RES_SEL 0x005 +#define ETM4_CFG_RES_SEL_PAIR0 0x006 +#define ETM4_CFG_RES_SEL_PAIR1 0x007 +#define ETM4_CFG_RES_SEQ 0x008 +#define ETM4_CFG_RES_TS 0x009 +#define ETM4_CFG_RES_MASK 0x00F + +/* ETMv4 specific config functions */ +int etm4_cscfg_register(struct coresight_device *csdev); + +#endif /* CORESIGHT_ETM4X_CFG_H */ diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c new file mode 100644 index 000000000000..560975b70474 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -0,0 +1,2612 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014, The Linux Foundation. All rights reserved. + */ + +#include <linux/acpi.h> +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/kvm_host.h> +#include <linux/moduleparam.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/io.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/sysfs.h> +#include <linux/stat.h> +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/cpu_pm.h> +#include <linux/coresight.h> +#include <linux/coresight-pmu.h> +#include <linux/amba/bus.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> +#include <linux/perf_event.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/property.h> +#include <linux/clk/clk-conf.h> + +#include <asm/barrier.h> +#include <asm/sections.h> +#include <asm/sysreg.h> +#include <asm/local.h> +#include <asm/virt.h> + +#include "coresight-etm4x.h" +#include "coresight-etm-perf.h" +#include "coresight-etm4x-cfg.h" +#include "coresight-self-hosted-trace.h" +#include "coresight-syscfg.h" +#include "coresight-trace-id.h" + +static int boot_enable; +module_param(boot_enable, int, 0444); +MODULE_PARM_DESC(boot_enable, "Enable tracing on boot"); + +#define PARAM_PM_SAVE_FIRMWARE 0 /* save self-hosted state as per firmware */ +#define PARAM_PM_SAVE_NEVER 1 /* never save any state */ +#define PARAM_PM_SAVE_SELF_HOSTED 2 /* save self-hosted state only */ + +static int pm_save_enable = PARAM_PM_SAVE_FIRMWARE; +module_param(pm_save_enable, int, 0444); +MODULE_PARM_DESC(pm_save_enable, + "Save/restore state on power down: 1 = never, 2 = self-hosted"); + +static struct etmv4_drvdata *etmdrvdata[NR_CPUS]; +static void etm4_set_default_config(struct etmv4_config *config); +static int etm4_set_event_filters(struct etmv4_drvdata *drvdata, + struct perf_event *event); +static u64 etm4_get_access_type(struct etmv4_config *config); + +static enum cpuhp_state hp_online; + +struct etm4_init_arg { + struct device *dev; + struct csdev_access *csa; +}; + +static DEFINE_PER_CPU(struct etm4_init_arg *, delayed_probe); +static int etm4_probe_cpu(unsigned int cpu); + +/* + * Check if TRCSSPCICRn(i) is implemented for a given instance. + * + * TRCSSPCICRn is implemented only if : + * TRCSSPCICR<n> is present only if all of the following are true: + * TRCIDR4.NUMSSCC > n. + * TRCIDR4.NUMPC > 0b0000 . + * TRCSSCSR<n>.PC == 0b1 + */ +static bool etm4x_sspcicrn_present(struct etmv4_drvdata *drvdata, int n) +{ + return (n < drvdata->nr_ss_cmp) && + drvdata->nr_pe && + (drvdata->config.ss_status[n] & TRCSSCSRn_PC); +} + +u64 etm4x_sysreg_read(u32 offset, bool _relaxed, bool _64bit) +{ + u64 res = 0; + + switch (offset) { + ETM4x_READ_SYSREG_CASES(res) + default : + pr_warn_ratelimited("etm4x: trying to read unsupported register @%x\n", + offset); + } + + if (!_relaxed) + __io_ar(res); /* Imitate the !relaxed I/O helpers */ + + return res; +} + +void etm4x_sysreg_write(u64 val, u32 offset, bool _relaxed, bool _64bit) +{ + if (!_relaxed) + __io_bw(); /* Imitate the !relaxed I/O helpers */ + if (!_64bit) + val &= GENMASK(31, 0); + + switch (offset) { + ETM4x_WRITE_SYSREG_CASES(val) + default : + pr_warn_ratelimited("etm4x: trying to write to unsupported register @%x\n", + offset); + } +} + +static u64 ete_sysreg_read(u32 offset, bool _relaxed, bool _64bit) +{ + u64 res = 0; + + switch (offset) { + ETE_READ_CASES(res) + default : + pr_warn_ratelimited("ete: trying to read unsupported register @%x\n", + offset); + } + + if (!_relaxed) + __io_ar(res); /* Imitate the !relaxed I/O helpers */ + + return res; +} + +static void ete_sysreg_write(u64 val, u32 offset, bool _relaxed, bool _64bit) +{ + if (!_relaxed) + __io_bw(); /* Imitate the !relaxed I/O helpers */ + if (!_64bit) + val &= GENMASK(31, 0); + + switch (offset) { + ETE_WRITE_CASES(val) + default : + pr_warn_ratelimited("ete: trying to write to unsupported register @%x\n", + offset); + } +} + +static void etm_detect_os_lock(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + u32 oslsr = etm4x_relaxed_read32(csa, TRCOSLSR); + + drvdata->os_lock_model = ETM_OSLSR_OSLM(oslsr); +} + +static void etm_write_os_lock(struct etmv4_drvdata *drvdata, + struct csdev_access *csa, u32 val) +{ + val = !!val; + + switch (drvdata->os_lock_model) { + case ETM_OSLOCK_PRESENT: + etm4x_relaxed_write32(csa, val, TRCOSLAR); + break; + case ETM_OSLOCK_PE: + write_sysreg_s(val, SYS_OSLAR_EL1); + break; + default: + pr_warn_once("CPU%d: Unsupported Trace OSLock model: %x\n", + smp_processor_id(), drvdata->os_lock_model); + fallthrough; + case ETM_OSLOCK_NI: + return; + } + isb(); +} + +static void etm4_os_unlock_csa(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + WARN_ON(drvdata->cpu != smp_processor_id()); + + /* Writing 0 to OS Lock unlocks the trace unit registers */ + etm_write_os_lock(drvdata, csa, 0x0); + drvdata->os_unlock = true; +} + +static void etm4_os_unlock(struct etmv4_drvdata *drvdata) +{ + if (!WARN_ON(!drvdata->csdev)) + etm4_os_unlock_csa(drvdata, &drvdata->csdev->access); +} + +static void etm4_os_lock(struct etmv4_drvdata *drvdata) +{ + if (WARN_ON(!drvdata->csdev)) + return; + /* Writing 0x1 to OS Lock locks the trace registers */ + etm_write_os_lock(drvdata, &drvdata->csdev->access, 0x1); + drvdata->os_unlock = false; +} + +static void etm4_cs_lock(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + /* Software Lock is only accessible via memory mapped interface */ + if (csa->io_mem) + CS_LOCK(csa->base); +} + +static void etm4_cs_unlock(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + if (csa->io_mem) + CS_UNLOCK(csa->base); +} + +static int etm4_cpu_id(struct coresight_device *csdev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + return drvdata->cpu; +} + +void etm4_release_trace_id(struct etmv4_drvdata *drvdata) +{ + coresight_trace_id_put_cpu_id(drvdata->cpu); +} + +struct etm4_enable_arg { + struct etmv4_drvdata *drvdata; + int rc; +}; + +/* + * etm4x_prohibit_trace - Prohibit the CPU from tracing at all ELs. + * When the CPU supports FEAT_TRF, we could move the ETM to a trace + * prohibited state by filtering the Exception levels via TRFCR_EL1. + */ +static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) +{ + u64 trfcr; + + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!drvdata->trfcr) + return; + + trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + + write_trfcr(trfcr); + kvm_tracing_set_el1_configuration(trfcr); +} + +static u64 etm4x_get_kern_user_filter(struct etmv4_drvdata *drvdata) +{ + u64 trfcr = drvdata->trfcr; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_EL1_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_EL1_E0TRE; + + return trfcr; +} + +/* + * etm4x_allow_trace - Allow CPU tracing in the respective ELs, + * as configured by the drvdata->config.mode for the current + * session. Even though we have TRCVICTLR bits to filter the + * trace in the ELs, it doesn't prevent the ETM from generating + * a packet (e.g, TraceInfo) that might contain the addresses from + * the excluded levels. Thus we use the additional controls provided + * via the Trace Filtering controls (FEAT_TRF) to make sure no trace + * is generated for the excluded ELs. + */ +static void etm4x_allow_trace(struct etmv4_drvdata *drvdata) +{ + u64 trfcr, guest_trfcr; + + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!drvdata->trfcr) + return; + + if (drvdata->config.mode & ETM_MODE_EXCL_HOST) + trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + else + trfcr = etm4x_get_kern_user_filter(drvdata); + + write_trfcr(trfcr); + + /* Set filters for guests and pass to KVM */ + if (drvdata->config.mode & ETM_MODE_EXCL_GUEST) + guest_trfcr = drvdata->trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE); + else + guest_trfcr = etm4x_get_kern_user_filter(drvdata); + + /* TRFCR_EL1 doesn't have CX so mask it out. */ + guest_trfcr &= ~TRFCR_EL2_CX; + kvm_tracing_set_el1_configuration(guest_trfcr); +} + +#ifdef CONFIG_ETM4X_IMPDEF_FEATURE + +#define HISI_HIP08_AMBA_ID 0x000b6d01 +#define ETM4_AMBA_MASK 0xfffff +#define HISI_HIP08_CORE_COMMIT_MASK 0x3000 +#define HISI_HIP08_CORE_COMMIT_SHIFT 12 +#define HISI_HIP08_CORE_COMMIT_FULL 0b00 +#define HISI_HIP08_CORE_COMMIT_LVL_1 0b01 +#define HISI_HIP08_CORE_COMMIT_REG sys_reg(3, 1, 15, 2, 5) + +struct etm4_arch_features { + void (*arch_callback)(bool enable); +}; + +static bool etm4_hisi_match_pid(unsigned int id) +{ + return (id & ETM4_AMBA_MASK) == HISI_HIP08_AMBA_ID; +} + +static void etm4_hisi_config_core_commit(bool enable) +{ + u8 commit = enable ? HISI_HIP08_CORE_COMMIT_LVL_1 : + HISI_HIP08_CORE_COMMIT_FULL; + u64 val; + + /* + * bit 12 and 13 of HISI_HIP08_CORE_COMMIT_REG are used together + * to set core-commit, 2'b00 means cpu is at full speed, 2'b01, + * 2'b10, 2'b11 mean reduce pipeline speed, and 2'b01 means level-1 + * speed(minimun value). So bit 12 and 13 should be cleared together. + */ + val = read_sysreg_s(HISI_HIP08_CORE_COMMIT_REG); + val &= ~HISI_HIP08_CORE_COMMIT_MASK; + val |= commit << HISI_HIP08_CORE_COMMIT_SHIFT; + write_sysreg_s(val, HISI_HIP08_CORE_COMMIT_REG); +} + +static struct etm4_arch_features etm4_features[] = { + [ETM4_IMPDEF_HISI_CORE_COMMIT] = { + .arch_callback = etm4_hisi_config_core_commit, + }, + {}, +}; + +static void etm4_enable_arch_specific(struct etmv4_drvdata *drvdata) +{ + struct etm4_arch_features *ftr; + int bit; + + for_each_set_bit(bit, drvdata->arch_features, ETM4_IMPDEF_FEATURE_MAX) { + ftr = &etm4_features[bit]; + + if (ftr->arch_callback) + ftr->arch_callback(true); + } +} + +static void etm4_disable_arch_specific(struct etmv4_drvdata *drvdata) +{ + struct etm4_arch_features *ftr; + int bit; + + for_each_set_bit(bit, drvdata->arch_features, ETM4_IMPDEF_FEATURE_MAX) { + ftr = &etm4_features[bit]; + + if (ftr->arch_callback) + ftr->arch_callback(false); + } +} + +static void etm4_check_arch_features(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + /* + * TRCPIDR* registers are not required for ETMs with system + * instructions. They must be identified by the MIDR+REVIDRs. + * Skip the TRCPID checks for now. + */ + if (!csa->io_mem) + return; + + if (etm4_hisi_match_pid(coresight_get_pid(csa))) + set_bit(ETM4_IMPDEF_HISI_CORE_COMMIT, drvdata->arch_features); +} +#else +static void etm4_enable_arch_specific(struct etmv4_drvdata *drvdata) +{ +} + +static void etm4_disable_arch_specific(struct etmv4_drvdata *drvdata) +{ +} + +static void etm4_check_arch_features(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ +} +#endif /* CONFIG_ETM4X_IMPDEF_FEATURE */ + +static void etm4x_sys_ins_barrier(struct csdev_access *csa, u32 offset, int pos, int val) +{ + if (!csa->io_mem) + isb(); +} + +/* + * etm4x_wait_status: Poll for TRCSTATR.<pos> == <val>. While using system + * instruction to access the trace unit, each access must be separated by a + * synchronization barrier. See ARM IHI0064H.b section "4.3.7 Synchronization of + * register updates", for system instructions section, in "Notes": + * + * "In particular, whenever disabling or enabling the trace unit, a poll of + * TRCSTATR needs explicit synchronization between each read of TRCSTATR" + */ +static int etm4x_wait_status(struct csdev_access *csa, int pos, int val) +{ + if (!csa->io_mem) + return coresight_timeout_action(csa, TRCSTATR, pos, val, + etm4x_sys_ins_barrier); + return coresight_timeout(csa, TRCSTATR, pos, val); +} + +static int etm4_enable_trace_unit(struct etmv4_drvdata *drvdata) +{ + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + struct csdev_access *csa = &csdev->access; + + /* + * ETE mandates that the TRCRSR is written to before + * enabling it. + */ + if (etm4x_is_ete(drvdata)) + etm4x_relaxed_write32(csa, TRCRSR_TA, TRCRSR); + + etm4x_allow_trace(drvdata); + + /* + * According to software usage PKLXF in Arm ARM (ARM DDI 0487 L.a), + * execute a Context synchronization event to guarantee the trace unit + * will observe the new values of the System registers. + */ + if (!csa->io_mem) + isb(); + + /* Enable the trace unit */ + etm4x_relaxed_write32(csa, 1, TRCPRGCTLR); + + /* + * As recommended by section 4.3.7 ("Synchronization when using system + * instructions to progrom the trace unit") of ARM IHI 0064H.b, the + * self-hosted trace analyzer must perform a Context synchronization + * event between writing to the TRCPRGCTLR and reading the TRCSTATR. + */ + if (!csa->io_mem) + isb(); + + /* wait for TRCSTATR.IDLE to go back down to '0' */ + if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 0)) { + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + return -ETIME; + } + + /* + * As recommended in section 4.3.7 (Synchronization of register updates) + * of ARM IHI 0064H.b, the self-hosted trace analyzer always executes an + * ISB instruction after programming the trace unit registers. + * + * For the memory-mapped interface, the registers are mapped as Device + * type (Device-nGnRE). Reading back the value of any register in the + * trace unit ensures that all writes have completed. Therefore, polling + * on TRCSTATR guarantees that the writing TRCPRGCTLR is complete, and + * no explicit dsb() is required at here. + */ + isb(); + + return 0; +} + +static int etm4_enable_hw(struct etmv4_drvdata *drvdata) +{ + int i, rc; + struct etmv4_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + struct csdev_access *csa = &csdev->access; + + + etm4_cs_unlock(drvdata, csa); + etm4_enable_arch_specific(drvdata); + + etm4_os_unlock(drvdata); + + rc = coresight_claim_device_unlocked(csdev); + if (rc) + goto done; + + /* Disable the trace unit before programming trace registers */ + etm4x_relaxed_write32(csa, 0, TRCPRGCTLR); + + /* + * If we use system instructions, we need to synchronize the + * write to the TRCPRGCTLR, before accessing the TRCSTATR. + * See ARM IHI0064F, section + * "4.3.7 Synchronization of register updates" + */ + if (!csa->io_mem) + isb(); + + /* wait for TRCSTATR.IDLE to go up */ + if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 1)) + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + if (drvdata->nr_pe) + etm4x_relaxed_write32(csa, config->pe_sel, TRCPROCSELR); + etm4x_relaxed_write32(csa, config->cfg, TRCCONFIGR); + /* nothing specific implemented */ + etm4x_relaxed_write32(csa, 0x0, TRCAUXCTLR); + etm4x_relaxed_write32(csa, config->eventctrl0, TRCEVENTCTL0R); + etm4x_relaxed_write32(csa, config->eventctrl1, TRCEVENTCTL1R); + if (drvdata->stallctl) + etm4x_relaxed_write32(csa, config->stall_ctrl, TRCSTALLCTLR); + etm4x_relaxed_write32(csa, config->ts_ctrl, TRCTSCTLR); + etm4x_relaxed_write32(csa, config->syncfreq, TRCSYNCPR); + etm4x_relaxed_write32(csa, config->ccctlr, TRCCCCTLR); + etm4x_relaxed_write32(csa, config->bb_ctrl, TRCBBCTLR); + etm4x_relaxed_write32(csa, drvdata->trcid, TRCTRACEIDR); + etm4x_relaxed_write32(csa, config->vinst_ctrl, TRCVICTLR); + etm4x_relaxed_write32(csa, config->viiectlr, TRCVIIECTLR); + etm4x_relaxed_write32(csa, config->vissctlr, TRCVISSCTLR); + if (drvdata->nr_pe_cmp) + etm4x_relaxed_write32(csa, config->vipcssctlr, TRCVIPCSSCTLR); + for (i = 0; i < drvdata->nrseqstate - 1; i++) + etm4x_relaxed_write32(csa, config->seq_ctrl[i], TRCSEQEVRn(i)); + if (drvdata->nrseqstate) { + etm4x_relaxed_write32(csa, config->seq_rst, TRCSEQRSTEVR); + etm4x_relaxed_write32(csa, config->seq_state, TRCSEQSTR); + } + if (drvdata->numextinsel) + etm4x_relaxed_write32(csa, config->ext_inp, TRCEXTINSELR); + for (i = 0; i < drvdata->nr_cntr; i++) { + etm4x_relaxed_write32(csa, config->cntrldvr[i], TRCCNTRLDVRn(i)); + etm4x_relaxed_write32(csa, config->cntr_ctrl[i], TRCCNTCTLRn(i)); + etm4x_relaxed_write32(csa, config->cntr_val[i], TRCCNTVRn(i)); + } + + /* + * Resource selector pair 0 is always implemented and reserved. As + * such start at 2. + */ + for (i = 2; i < drvdata->nr_resource * 2; i++) + etm4x_relaxed_write32(csa, config->res_ctrl[i], TRCRSCTLRn(i)); + + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + /* always clear status bit on restart if using single-shot */ + if (config->ss_ctrl[i] || config->ss_pe_cmp[i]) + config->ss_status[i] &= ~TRCSSCSRn_STATUS; + etm4x_relaxed_write32(csa, config->ss_ctrl[i], TRCSSCCRn(i)); + etm4x_relaxed_write32(csa, config->ss_status[i], TRCSSCSRn(i)); + if (etm4x_sspcicrn_present(drvdata, i)) + etm4x_relaxed_write32(csa, config->ss_pe_cmp[i], TRCSSPCICRn(i)); + } + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { + etm4x_relaxed_write64(csa, config->addr_val[i], TRCACVRn(i)); + etm4x_relaxed_write64(csa, config->addr_acc[i], TRCACATRn(i)); + } + for (i = 0; i < drvdata->numcidc; i++) + etm4x_relaxed_write64(csa, config->ctxid_pid[i], TRCCIDCVRn(i)); + etm4x_relaxed_write32(csa, config->ctxid_mask0, TRCCIDCCTLR0); + if (drvdata->numcidc > 4) + etm4x_relaxed_write32(csa, config->ctxid_mask1, TRCCIDCCTLR1); + + for (i = 0; i < drvdata->numvmidc; i++) + etm4x_relaxed_write64(csa, config->vmid_val[i], TRCVMIDCVRn(i)); + etm4x_relaxed_write32(csa, config->vmid_mask0, TRCVMIDCCTLR0); + if (drvdata->numvmidc > 4) + etm4x_relaxed_write32(csa, config->vmid_mask1, TRCVMIDCCTLR1); + + if (!drvdata->skip_power_up) { + u32 trcpdcr = etm4x_relaxed_read32(csa, TRCPDCR); + + /* + * Request to keep the trace unit powered and also + * emulation of powerdown + */ + etm4x_relaxed_write32(csa, trcpdcr | TRCPDCR_PU, TRCPDCR); + } + + if (!drvdata->paused) + rc = etm4_enable_trace_unit(drvdata); +done: + etm4_cs_lock(drvdata, csa); + + dev_dbg(etm_dev, "cpu: %d enable smp call done: %d\n", + drvdata->cpu, rc); + return rc; +} + +static void etm4_enable_sysfs_smp_call(void *info) +{ + struct etm4_enable_arg *arg = info; + struct coresight_device *csdev; + + if (WARN_ON(!arg)) + return; + + csdev = arg->drvdata->csdev; + if (!coresight_take_mode(csdev, CS_MODE_SYSFS)) { + /* Someone is already using the tracer */ + arg->rc = -EBUSY; + return; + } + + arg->rc = etm4_enable_hw(arg->drvdata); + + /* The tracer didn't start */ + if (arg->rc) + coresight_set_mode(csdev, CS_MODE_DISABLED); +} + +/* + * The goal of function etm4_config_timestamp_event() is to configure a + * counter that will tell the tracer to emit a timestamp packet when it + * reaches zero. This is done in order to get a more fine grained idea + * of when instructions are executed so that they can be correlated + * with execution on other CPUs. + * + * To do this the counter itself is configured to self reload and + * TRCRSCTLR1 (always true) used to get the counter to decrement. From + * there a resource selector is configured with the counter and the + * timestamp control register to use the resource selector to trigger the + * event that will insert a timestamp packet in the stream. + */ +static int etm4_config_timestamp_event(struct etmv4_drvdata *drvdata) +{ + int ctridx, ret = -EINVAL; + int counter, rselector; + u32 val = 0; + struct etmv4_config *config = &drvdata->config; + + /* No point in trying if we don't have at least one counter */ + if (!drvdata->nr_cntr) + goto out; + + /* Find a counter that hasn't been initialised */ + for (ctridx = 0; ctridx < drvdata->nr_cntr; ctridx++) + if (config->cntr_val[ctridx] == 0) + break; + + /* All the counters have been configured already, bail out */ + if (ctridx == drvdata->nr_cntr) { + pr_debug("%s: no available counter found\n", __func__); + ret = -ENOSPC; + goto out; + } + + /* + * Searching for an available resource selector to use, starting at + * '2' since every implementation has at least 2 resource selector. + * ETMIDR4 gives the number of resource selector _pairs_, + * hence multiply by 2. + */ + for (rselector = 2; rselector < drvdata->nr_resource * 2; rselector++) + if (!config->res_ctrl[rselector]) + break; + + if (rselector == drvdata->nr_resource * 2) { + pr_debug("%s: no available resource selector found\n", + __func__); + ret = -ENOSPC; + goto out; + } + + /* Remember what counter we used */ + counter = 1 << ctridx; + + /* + * Initialise original and reload counter value to the smallest + * possible value in order to get as much precision as we can. + */ + config->cntr_val[ctridx] = 1; + config->cntrldvr[ctridx] = 1; + + /* Set the trace counter control register */ + val = 0x1 << 16 | /* Bit 16, reload counter automatically */ + 0x0 << 7 | /* Select single resource selector */ + 0x1; /* Resource selector 1, i.e always true */ + + config->cntr_ctrl[ctridx] = val; + + val = 0x2 << 16 | /* Group 0b0010 - Counter and sequencers */ + counter << 0; /* Counter to use */ + + config->res_ctrl[rselector] = val; + + val = 0x0 << 7 | /* Select single resource selector */ + rselector; /* Resource selector */ + + config->ts_ctrl = val; + + ret = 0; +out: + return ret; +} + +static int etm4_parse_event_config(struct coresight_device *csdev, + struct perf_event *event) +{ + int ret = 0; + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct etmv4_config *config = &drvdata->config; + struct perf_event_attr *attr = &event->attr; + unsigned long cfg_hash; + int preset, cc_threshold; + + /* Clear configuration from previous run */ + memset(config, 0, sizeof(struct etmv4_config)); + + if (attr->exclude_kernel) + config->mode = ETM_MODE_EXCL_KERN; + + if (attr->exclude_user) + config->mode = ETM_MODE_EXCL_USER; + + if (attr->exclude_host) + config->mode |= ETM_MODE_EXCL_HOST; + + if (attr->exclude_guest) + config->mode |= ETM_MODE_EXCL_GUEST; + + /* Always start from the default config */ + etm4_set_default_config(config); + + /* Configure filters specified on the perf cmd line, if any. */ + ret = etm4_set_event_filters(drvdata, event); + if (ret) + goto out; + + /* Go from generic option to ETMv4 specifics */ + if (attr->config & BIT(ETM_OPT_CYCACC)) { + config->cfg |= TRCCONFIGR_CCI; + /* TRM: Must program this for cycacc to work */ + cc_threshold = attr->config3 & ETM_CYC_THRESHOLD_MASK; + if (!cc_threshold) + cc_threshold = ETM_CYC_THRESHOLD_DEFAULT; + if (cc_threshold < drvdata->ccitmin) + cc_threshold = drvdata->ccitmin; + config->ccctlr = cc_threshold; + } + if (attr->config & BIT(ETM_OPT_TS)) { + /* + * Configure timestamps to be emitted at regular intervals in + * order to correlate instructions executed on different CPUs + * (CPU-wide trace scenarios). + */ + ret = etm4_config_timestamp_event(drvdata); + + /* + * No need to go further if timestamp intervals can't + * be configured. + */ + if (ret) + goto out; + + /* bit[11], Global timestamp tracing bit */ + config->cfg |= TRCCONFIGR_TS; + } + + /* Only trace contextID when runs in root PID namespace */ + if ((attr->config & BIT(ETM_OPT_CTXTID)) && + task_is_in_init_pid_ns(current)) + /* bit[6], Context ID tracing bit */ + config->cfg |= TRCCONFIGR_CID; + + /* + * If set bit ETM_OPT_CTXTID2 in perf config, this asks to trace VMID + * for recording CONTEXTIDR_EL2. Do not enable VMID tracing if the + * kernel is not running in EL2. + */ + if (attr->config & BIT(ETM_OPT_CTXTID2)) { + if (!is_kernel_in_hyp_mode()) { + ret = -EINVAL; + goto out; + } + /* Only trace virtual contextID when runs in root PID namespace */ + if (task_is_in_init_pid_ns(current)) + config->cfg |= TRCCONFIGR_VMID | TRCCONFIGR_VMIDOPT; + } + + /* return stack - enable if selected and supported */ + if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack) + /* bit[12], Return stack enable bit */ + config->cfg |= TRCCONFIGR_RS; + + /* + * Set any selected configuration and preset. + * + * This extracts the values of PMU_FORMAT_ATTR(configid) and PMU_FORMAT_ATTR(preset) + * in the perf attributes defined in coresight-etm-perf.c. + * configid uses bits 63:32 of attr->config2, preset uses bits 3:0 of attr->config. + * A zero configid means no configuration active, preset = 0 means no preset selected. + */ + if (attr->config2 & GENMASK_ULL(63, 32)) { + cfg_hash = (u32)(attr->config2 >> 32); + preset = attr->config & 0xF; + ret = cscfg_csdev_enable_active_config(csdev, cfg_hash, preset); + } + + /* branch broadcast - enable if selected and supported */ + if (attr->config & BIT(ETM_OPT_BRANCH_BROADCAST)) { + if (!drvdata->trcbb) { + /* + * Missing BB support could cause silent decode errors + * so fail to open if it's not supported. + */ + ret = -EINVAL; + goto out; + } else { + config->cfg |= BIT(ETM4_CFG_BIT_BB); + } + } + +out: + return ret; +} + +static int etm4_enable_perf(struct coresight_device *csdev, + struct perf_event *event, + struct coresight_path *path) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret; + + if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) + return -EINVAL; + + if (!coresight_take_mode(csdev, CS_MODE_PERF)) + return -EBUSY; + + /* Configure the tracer based on the session's specifics */ + ret = etm4_parse_event_config(csdev, event); + if (ret) + goto out; + + drvdata->trcid = path->trace_id; + + /* Populate pause state */ + drvdata->paused = !!READ_ONCE(event->hw.aux_paused); + + /* And enable it */ + ret = etm4_enable_hw(drvdata); + +out: + /* Failed to start tracer; roll back to DISABLED mode */ + if (ret) + coresight_set_mode(csdev, CS_MODE_DISABLED); + return ret; +} + +static int etm4_enable_sysfs(struct coresight_device *csdev, struct coresight_path *path) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct etm4_enable_arg arg = { }; + unsigned long cfg_hash; + int ret, preset; + + /* enable any config activated by configfs */ + cscfg_config_sysfs_get_active_cfg(&cfg_hash, &preset); + if (cfg_hash) { + ret = cscfg_csdev_enable_active_config(csdev, cfg_hash, preset); + if (ret) + return ret; + } + + raw_spin_lock(&drvdata->spinlock); + + drvdata->trcid = path->trace_id; + + /* Tracer will never be paused in sysfs mode */ + drvdata->paused = false; + + /* + * Executing etm4_enable_hw on the cpu whose ETM is being enabled + * ensures that register writes occur when cpu is powered. + */ + arg.drvdata = drvdata; + ret = smp_call_function_single(drvdata->cpu, + etm4_enable_sysfs_smp_call, &arg, 1); + if (!ret) + ret = arg.rc; + if (!ret) + drvdata->sticky_enable = true; + + if (ret) + etm4_release_trace_id(drvdata); + + raw_spin_unlock(&drvdata->spinlock); + + if (!ret) + dev_dbg(&csdev->dev, "ETM tracing enabled\n"); + return ret; +} + +static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, + enum cs_mode mode, struct coresight_path *path) +{ + int ret; + + switch (mode) { + case CS_MODE_SYSFS: + ret = etm4_enable_sysfs(csdev, path); + break; + case CS_MODE_PERF: + ret = etm4_enable_perf(csdev, event, path); + break; + default: + ret = -EINVAL; + } + + return ret; +} + +static void etm4_disable_trace_unit(struct etmv4_drvdata *drvdata) +{ + u32 control; + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + struct csdev_access *csa = &csdev->access; + + control = etm4x_relaxed_read32(csa, TRCPRGCTLR); + + /* EN, bit[0] Trace unit enable bit */ + control &= ~0x1; + + /* + * If the CPU supports v8.4 Trace filter Control, + * set the ETM to trace prohibited region. + */ + etm4x_prohibit_trace(drvdata); + /* + * Prevent being speculative at the point of disabling the trace unit, + * as recommended by section 7.3.77 ("TRCVICTLR, ViewInst Main Control + * Register, SSTATUS") of ARM IHI 0064D + */ + dsb(sy); + /* + * According to software usage VKHHY in Arm ARM (ARM DDI 0487 L.a), + * execute a Context synchronization event to guarantee no new + * program-flow trace is generated. + */ + isb(); + /* Trace synchronization barrier, is a nop if not supported */ + tsb_csync(); + etm4x_relaxed_write32(csa, control, TRCPRGCTLR); + + /* + * As recommended by section 4.3.7 ("Synchronization when using system + * instructions to progrom the trace unit") of ARM IHI 0064H.b, the + * self-hosted trace analyzer must perform a Context synchronization + * event between writing to the TRCPRGCTLR and reading the TRCSTATR. + */ + if (!csa->io_mem) + isb(); + + /* wait for TRCSTATR.PMSTABLE to go to '1' */ + if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1)) + dev_err(etm_dev, + "timeout while waiting for PM stable Trace Status\n"); + /* + * As recommended in section 4.3.7 (Synchronization of register updates) + * of ARM IHI 0064H.b, the self-hosted trace analyzer always executes an + * ISB instruction after programming the trace unit registers. + * + * For the memory-mapped interface, the registers are mapped as Device + * type (Device-nGnRE). Reading back the value of any register in the + * trace unit ensures that all writes have completed. Therefore, polling + * on TRCSTATR guarantees that the writing TRCPRGCTLR is complete, and + * no explicit dsb() is required at here. + */ + isb(); +} + +static void etm4_disable_hw(struct etmv4_drvdata *drvdata) +{ + u32 control; + struct etmv4_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa = &csdev->access; + int i; + + etm4_cs_unlock(drvdata, csa); + etm4_disable_arch_specific(drvdata); + + if (!drvdata->skip_power_up) { + /* power can be removed from the trace unit now */ + control = etm4x_relaxed_read32(csa, TRCPDCR); + control &= ~TRCPDCR_PU; + etm4x_relaxed_write32(csa, control, TRCPDCR); + } + + etm4_disable_trace_unit(drvdata); + + /* read the status of the single shot comparators */ + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + config->ss_status[i] = + etm4x_relaxed_read32(csa, TRCSSCSRn(i)); + } + + /* read back the current counter values */ + for (i = 0; i < drvdata->nr_cntr; i++) { + config->cntr_val[i] = + etm4x_relaxed_read32(csa, TRCCNTVRn(i)); + } + + coresight_disclaim_device_unlocked(csdev); + etm4_cs_lock(drvdata, csa); + + dev_dbg(&drvdata->csdev->dev, + "cpu: %d disable smp call done\n", drvdata->cpu); +} + +static void etm4_disable_sysfs_smp_call(void *info) +{ + struct etmv4_drvdata *drvdata = info; + + etm4_disable_hw(drvdata); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); +} + +static int etm4_disable_perf(struct coresight_device *csdev, + struct perf_event *event) +{ + u32 control; + struct etm_filters *filters = event->hw.addr_filters; + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_event_attr *attr = &event->attr; + + if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) + return -EINVAL; + + etm4_disable_hw(drvdata); + /* + * The config_id occupies bits 63:32 of the config2 perf event attr + * field. If this is non-zero then we will have enabled a config. + */ + if (attr->config2 & GENMASK_ULL(63, 32)) + cscfg_csdev_disable_active_config(csdev); + + /* + * Check if the start/stop logic was active when the unit was stopped. + * That way we can re-enable the start/stop logic when the process is + * scheduled again. Configuration of the start/stop logic happens in + * function etm4_set_event_filters(). + */ + control = etm4x_relaxed_read32(&csdev->access, TRCVICTLR); + /* TRCVICTLR::SSSTATUS, bit[9] */ + filters->ssstatus = (control & BIT(9)); + + coresight_set_mode(drvdata->csdev, CS_MODE_DISABLED); + + /* + * perf will release trace ids when _free_aux() is + * called at the end of the session. + */ + + return 0; +} + +static void etm4_disable_sysfs(struct coresight_device *csdev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + /* + * Taking hotplug lock here protects from clocks getting disabled + * with tracing being left on (crash scenario) if user disable occurs + * after cpu online mask indicates the cpu is offline but before the + * DYING hotplug callback is serviced by the ETM driver. + */ + cpus_read_lock(); + raw_spin_lock(&drvdata->spinlock); + + /* + * Executing etm4_disable_hw on the cpu whose ETM is being disabled + * ensures that register writes occur when cpu is powered. + */ + smp_call_function_single(drvdata->cpu, etm4_disable_sysfs_smp_call, + drvdata, 1); + + raw_spin_unlock(&drvdata->spinlock); + + cscfg_csdev_disable_active_config(csdev); + + cpus_read_unlock(); + + /* + * we only release trace IDs when resetting sysfs. + * This permits sysfs users to read the trace ID after the trace + * session has completed. This maintains operational behaviour with + * prior trace id allocation method + */ + + dev_dbg(&csdev->dev, "ETM tracing disabled\n"); +} + +static void etm4_disable(struct coresight_device *csdev, + struct perf_event *event) +{ + enum cs_mode mode; + + /* + * For as long as the tracer isn't disabled another entity can't + * change its status. As such we can read the status here without + * fearing it will change under us. + */ + mode = coresight_get_mode(csdev); + + switch (mode) { + case CS_MODE_DISABLED: + break; + case CS_MODE_SYSFS: + etm4_disable_sysfs(csdev); + break; + case CS_MODE_PERF: + etm4_disable_perf(csdev, event); + break; + } +} + +static int etm4_resume_perf(struct coresight_device *csdev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct csdev_access *csa = &csdev->access; + + if (coresight_get_mode(csdev) != CS_MODE_PERF) + return -EINVAL; + + etm4_cs_unlock(drvdata, csa); + etm4_enable_trace_unit(drvdata); + etm4_cs_lock(drvdata, csa); + + drvdata->paused = false; + return 0; +} + +static void etm4_pause_perf(struct coresight_device *csdev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct csdev_access *csa = &csdev->access; + + if (coresight_get_mode(csdev) != CS_MODE_PERF) + return; + + etm4_cs_unlock(drvdata, csa); + etm4_disable_trace_unit(drvdata); + etm4_cs_lock(drvdata, csa); + + drvdata->paused = true; +} + +static const struct coresight_ops_source etm4_source_ops = { + .cpu_id = etm4_cpu_id, + .enable = etm4_enable, + .disable = etm4_disable, + .resume_perf = etm4_resume_perf, + .pause_perf = etm4_pause_perf, +}; + +static const struct coresight_ops etm4_cs_ops = { + .trace_id = coresight_etm_get_trace_id, + .source_ops = &etm4_source_ops, +}; + +static bool cpu_supports_sysreg_trace(void) +{ + u64 dfr0 = read_sysreg_s(SYS_ID_AA64DFR0_EL1); + + return ((dfr0 >> ID_AA64DFR0_EL1_TraceVer_SHIFT) & 0xfUL) > 0; +} + +static bool etm4_init_sysreg_access(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + u32 devarch; + + if (!cpu_supports_sysreg_trace()) + return false; + + /* + * ETMs implementing sysreg access must implement TRCDEVARCH. + */ + devarch = read_etm4x_sysreg_const_offset(TRCDEVARCH); + switch (devarch & ETM_DEVARCH_ID_MASK) { + case ETM_DEVARCH_ETMv4x_ARCH: + *csa = (struct csdev_access) { + .io_mem = false, + .read = etm4x_sysreg_read, + .write = etm4x_sysreg_write, + }; + break; + case ETM_DEVARCH_ETE_ARCH: + *csa = (struct csdev_access) { + .io_mem = false, + .read = ete_sysreg_read, + .write = ete_sysreg_write, + }; + break; + default: + return false; + } + + drvdata->arch = etm_devarch_to_arch(devarch); + return true; +} + +static bool is_devtype_cpu_trace(void __iomem *base) +{ + u32 devtype = readl(base + TRCDEVTYPE); + + return (devtype == CS_DEVTYPE_PE_TRACE); +} + +static bool etm4_init_iomem_access(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + u32 devarch = readl_relaxed(drvdata->base + TRCDEVARCH); + + if (!is_coresight_device(drvdata->base) || !is_devtype_cpu_trace(drvdata->base)) + return false; + + /* + * All ETMs must implement TRCDEVARCH to indicate that + * the component is an ETMv4. Even though TRCIDR1 also + * contains the information, it is part of the "Trace" + * register and must be accessed with the OSLK cleared, + * with MMIO. But we cannot touch the OSLK until we are + * sure this is an ETM. So rely only on the TRCDEVARCH. + */ + if ((devarch & ETM_DEVARCH_ID_MASK) != ETM_DEVARCH_ETMv4x_ARCH) { + pr_warn_once("TRCDEVARCH doesn't match ETMv4 architecture\n"); + return false; + } + + drvdata->arch = etm_devarch_to_arch(devarch); + *csa = CSDEV_ACCESS_IOMEM(drvdata->base); + return true; +} + +static bool etm4_init_csdev_access(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + /* + * Always choose the memory mapped io, if there is + * a memory map to prevent sysreg access on broken + * systems. + */ + if (drvdata->base) + return etm4_init_iomem_access(drvdata, csa); + + if (etm4_init_sysreg_access(drvdata, csa)) + return true; + + return false; +} + +static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata) +{ + u64 dfr0 = read_sysreg(id_aa64dfr0_el1); + u64 trfcr; + + drvdata->trfcr = 0; + if (!cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_TraceFilt_SHIFT)) + return; + + /* + * If the CPU supports v8.4 SelfHosted Tracing, enable + * tracing at the kernel EL and EL0, forcing to use the + * virtual time as the timestamp. + */ + trfcr = (FIELD_PREP(TRFCR_EL1_TS_MASK, TRFCR_EL1_TS_VIRTUAL) | + TRFCR_EL1_ExTRE | + TRFCR_EL1_E0TRE); + + /* If we are running at EL2, allow tracing the CONTEXTIDR_EL2. */ + if (is_kernel_in_hyp_mode()) + trfcr |= TRFCR_EL2_CX; + + drvdata->trfcr = trfcr; +} + +/* + * The following errata on applicable cpu ranges, affect the CCITMIN filed + * in TCRIDR3 register. Software read for the field returns 0x100 limiting + * the cycle threshold granularity, whereas the right value should have + * been 0x4, which is well supported in the hardware. + */ +static struct midr_range etm_wrong_ccitmin_cpus[] = { + /* Erratum #1490853 - Cortex-A76 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 4, 0), + /* Erratum #1490853 - Neoverse-N1 */ + MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 4, 0), + /* Erratum #1491015 - Cortex-A77 */ + MIDR_RANGE(MIDR_CORTEX_A77, 0, 0, 1, 0), + /* Erratum #1502854 - Cortex-X1 */ + MIDR_REV(MIDR_CORTEX_X1, 0, 0), + /* Erratum #1619801 - Neoverse-V1 */ + MIDR_REV(MIDR_NEOVERSE_V1, 0, 0), + {}, +}; + +static void etm4_fixup_wrong_ccitmin(struct etmv4_drvdata *drvdata) +{ + /* + * Erratum affected cpus will read 256 as the minimum + * instruction trace cycle counting threshold whereas + * the correct value should be 4 instead. Override the + * recorded value for 'drvdata->ccitmin' to workaround + * this problem. + */ + if (is_midr_in_range_list(etm_wrong_ccitmin_cpus)) { + if (drvdata->ccitmin == 256) + drvdata->ccitmin = 4; + } +} + +static void etm4_init_arch_data(void *info) +{ + u32 etmidr0; + u32 etmidr2; + u32 etmidr3; + u32 etmidr4; + u32 etmidr5; + struct etm4_init_arg *init_arg = info; + struct etmv4_drvdata *drvdata; + struct csdev_access *csa; + struct device *dev = init_arg->dev; + int i; + + drvdata = dev_get_drvdata(init_arg->dev); + csa = init_arg->csa; + + /* + * If we are unable to detect the access mechanism, + * or unable to detect the trace unit type, fail + * early. + */ + if (!etm4_init_csdev_access(drvdata, csa)) + return; + + if (!csa->io_mem || + fwnode_property_present(dev_fwnode(dev), "qcom,skip-power-up")) + drvdata->skip_power_up = true; + + /* Detect the support for OS Lock before we actually use it */ + etm_detect_os_lock(drvdata, csa); + + /* Make sure all registers are accessible */ + etm4_os_unlock_csa(drvdata, csa); + etm4_cs_unlock(drvdata, csa); + + etm4_check_arch_features(drvdata, csa); + + /* find all capabilities of the tracing unit */ + etmidr0 = etm4x_relaxed_read32(csa, TRCIDR0); + + /* INSTP0, bits[2:1] P0 tracing support field */ + drvdata->instrp0 = !!(FIELD_GET(TRCIDR0_INSTP0_MASK, etmidr0) == 0b11); + /* TRCBB, bit[5] Branch broadcast tracing support bit */ + drvdata->trcbb = !!(etmidr0 & TRCIDR0_TRCBB); + /* TRCCOND, bit[6] Conditional instruction tracing support bit */ + drvdata->trccond = !!(etmidr0 & TRCIDR0_TRCCOND); + /* TRCCCI, bit[7] Cycle counting instruction bit */ + drvdata->trccci = !!(etmidr0 & TRCIDR0_TRCCCI); + /* RETSTACK, bit[9] Return stack bit */ + drvdata->retstack = !!(etmidr0 & TRCIDR0_RETSTACK); + /* NUMEVENT, bits[11:10] Number of events field */ + drvdata->nr_event = FIELD_GET(TRCIDR0_NUMEVENT_MASK, etmidr0); + /* QSUPP, bits[16:15] Q element support field */ + drvdata->q_support = FIELD_GET(TRCIDR0_QSUPP_MASK, etmidr0); + if (drvdata->q_support) + drvdata->q_filt = !!(etmidr0 & TRCIDR0_QFILT); + /* TSSIZE, bits[28:24] Global timestamp size field */ + drvdata->ts_size = FIELD_GET(TRCIDR0_TSSIZE_MASK, etmidr0); + + /* maximum size of resources */ + etmidr2 = etm4x_relaxed_read32(csa, TRCIDR2); + /* CIDSIZE, bits[9:5] Indicates the Context ID size */ + drvdata->ctxid_size = FIELD_GET(TRCIDR2_CIDSIZE_MASK, etmidr2); + /* VMIDSIZE, bits[14:10] Indicates the VMID size */ + drvdata->vmid_size = FIELD_GET(TRCIDR2_VMIDSIZE_MASK, etmidr2); + /* CCSIZE, bits[28:25] size of the cycle counter in bits minus 12 */ + drvdata->ccsize = FIELD_GET(TRCIDR2_CCSIZE_MASK, etmidr2); + + etmidr3 = etm4x_relaxed_read32(csa, TRCIDR3); + /* CCITMIN, bits[11:0] minimum threshold value that can be programmed */ + drvdata->ccitmin = FIELD_GET(TRCIDR3_CCITMIN_MASK, etmidr3); + etm4_fixup_wrong_ccitmin(drvdata); + + /* EXLEVEL_S, bits[19:16] Secure state instruction tracing */ + drvdata->s_ex_level = FIELD_GET(TRCIDR3_EXLEVEL_S_MASK, etmidr3); + drvdata->config.s_ex_level = drvdata->s_ex_level; + /* EXLEVEL_NS, bits[23:20] Non-secure state instruction tracing */ + drvdata->ns_ex_level = FIELD_GET(TRCIDR3_EXLEVEL_NS_MASK, etmidr3); + /* + * TRCERR, bit[24] whether a trace unit can trace a + * system error exception. + */ + drvdata->trc_error = !!(etmidr3 & TRCIDR3_TRCERR); + /* SYNCPR, bit[25] implementation has a fixed synchronization period? */ + drvdata->syncpr = !!(etmidr3 & TRCIDR3_SYNCPR); + /* STALLCTL, bit[26] is stall control implemented? */ + drvdata->stallctl = !!(etmidr3 & TRCIDR3_STALLCTL); + /* SYSSTALL, bit[27] implementation can support stall control? */ + drvdata->sysstall = !!(etmidr3 & TRCIDR3_SYSSTALL); + /* + * NUMPROC - the number of PEs available for tracing, 5bits + * = TRCIDR3.bits[13:12]bits[30:28] + * bits[4:3] = TRCIDR3.bits[13:12] (since etm-v4.2, otherwise RES0) + * bits[3:0] = TRCIDR3.bits[30:28] + */ + drvdata->nr_pe = (FIELD_GET(TRCIDR3_NUMPROC_HI_MASK, etmidr3) << 3) | + FIELD_GET(TRCIDR3_NUMPROC_LO_MASK, etmidr3); + /* NOOVERFLOW, bit[31] is trace overflow prevention supported */ + drvdata->nooverflow = !!(etmidr3 & TRCIDR3_NOOVERFLOW); + + /* number of resources trace unit supports */ + etmidr4 = etm4x_relaxed_read32(csa, TRCIDR4); + /* NUMACPAIRS, bits[0:3] number of addr comparator pairs for tracing */ + drvdata->nr_addr_cmp = FIELD_GET(TRCIDR4_NUMACPAIRS_MASK, etmidr4); + /* NUMPC, bits[15:12] number of PE comparator inputs for tracing */ + drvdata->nr_pe_cmp = FIELD_GET(TRCIDR4_NUMPC_MASK, etmidr4); + /* + * NUMRSPAIR, bits[19:16] + * The number of resource pairs conveyed by the HW starts at 0, i.e a + * value of 0x0 indicate 1 resource pair, 0x1 indicate two and so on. + * As such add 1 to the value of NUMRSPAIR for a better representation. + * + * For ETM v4.3 and later, 0x0 means 0, and no pairs are available - + * the default TRUE and FALSE resource selectors are omitted. + * Otherwise for values 0x1 and above the number is N + 1 as per v4.2. + */ + drvdata->nr_resource = FIELD_GET(TRCIDR4_NUMRSPAIR_MASK, etmidr4); + if ((drvdata->arch < ETM_ARCH_V4_3) || (drvdata->nr_resource > 0)) + drvdata->nr_resource += 1; + /* + * NUMSSCC, bits[23:20] the number of single-shot + * comparator control for tracing. Read any status regs as these + * also contain RO capability data. + */ + drvdata->nr_ss_cmp = FIELD_GET(TRCIDR4_NUMSSCC_MASK, etmidr4); + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + drvdata->config.ss_status[i] = + etm4x_relaxed_read32(csa, TRCSSCSRn(i)); + } + /* NUMCIDC, bits[27:24] number of Context ID comparators for tracing */ + drvdata->numcidc = FIELD_GET(TRCIDR4_NUMCIDC_MASK, etmidr4); + /* NUMVMIDC, bits[31:28] number of VMID comparators for tracing */ + drvdata->numvmidc = FIELD_GET(TRCIDR4_NUMVMIDC_MASK, etmidr4); + + etmidr5 = etm4x_relaxed_read32(csa, TRCIDR5); + /* NUMEXTIN, bits[8:0] number of external inputs implemented */ + drvdata->nr_ext_inp = FIELD_GET(TRCIDR5_NUMEXTIN_MASK, etmidr5); + drvdata->numextinsel = FIELD_GET(TRCIDR5_NUMEXTINSEL_MASK, etmidr5); + /* TRACEIDSIZE, bits[21:16] indicates the trace ID width */ + drvdata->trcid_size = FIELD_GET(TRCIDR5_TRACEIDSIZE_MASK, etmidr5); + /* ATBTRIG, bit[22] implementation can support ATB triggers? */ + drvdata->atbtrig = !!(etmidr5 & TRCIDR5_ATBTRIG); + /* + * LPOVERRIDE, bit[23] implementation supports + * low-power state override + */ + drvdata->lpoverride = (etmidr5 & TRCIDR5_LPOVERRIDE) && (!drvdata->skip_power_up); + /* NUMSEQSTATE, bits[27:25] number of sequencer states implemented */ + drvdata->nrseqstate = FIELD_GET(TRCIDR5_NUMSEQSTATE_MASK, etmidr5); + /* NUMCNTR, bits[30:28] number of counters available for tracing */ + drvdata->nr_cntr = FIELD_GET(TRCIDR5_NUMCNTR_MASK, etmidr5); + + coresight_clear_self_claim_tag_unlocked(csa); + etm4_cs_lock(drvdata, csa); + cpu_detect_trace_filtering(drvdata); +} + +static u32 etm4_get_victlr_access_type(struct etmv4_config *config) +{ + return etm4_get_access_type(config) << __bf_shf(TRCVICTLR_EXLEVEL_MASK); +} + +/* Set ELx trace filter access in the TRCVICTLR register */ +static void etm4_set_victlr_access(struct etmv4_config *config) +{ + config->vinst_ctrl &= ~TRCVICTLR_EXLEVEL_MASK; + config->vinst_ctrl |= etm4_get_victlr_access_type(config); +} + +static void etm4_set_default_config(struct etmv4_config *config) +{ + /* disable all events tracing */ + config->eventctrl0 = 0x0; + config->eventctrl1 = 0x0; + + /* disable stalling */ + config->stall_ctrl = 0x0; + + /* enable trace synchronization every 4096 bytes, if available */ + config->syncfreq = 0xC; + + /* disable timestamp event */ + config->ts_ctrl = 0x0; + + /* TRCVICTLR::EVENT = 0x01, select the always on logic */ + config->vinst_ctrl = FIELD_PREP(TRCVICTLR_EVENT_MASK, 0x01); + + /* TRCVICTLR::EXLEVEL_NS:EXLEVELS: Set kernel / user filtering */ + etm4_set_victlr_access(config); +} + +static u64 etm4_get_ns_access_type(struct etmv4_config *config) +{ + u64 access_type = 0; + + /* + * EXLEVEL_NS, for NonSecure Exception levels. + * The mask here is a generic value and must be + * shifted to the corresponding field for the registers + */ + if (!is_kernel_in_hyp_mode()) { + /* Stay away from hypervisor mode for non-VHE */ + access_type = ETM_EXLEVEL_NS_HYP; + if (config->mode & ETM_MODE_EXCL_KERN) + access_type |= ETM_EXLEVEL_NS_OS; + } else if (config->mode & ETM_MODE_EXCL_KERN) { + access_type = ETM_EXLEVEL_NS_HYP; + } + + if (config->mode & ETM_MODE_EXCL_USER) + access_type |= ETM_EXLEVEL_NS_APP; + + return access_type; +} + +/* + * Construct the exception level masks for a given config. + * This must be shifted to the corresponding register field + * for usage. + */ +static u64 etm4_get_access_type(struct etmv4_config *config) +{ + /* All Secure exception levels are excluded from the trace */ + return etm4_get_ns_access_type(config) | (u64)config->s_ex_level; +} + +static u64 etm4_get_comparator_access_type(struct etmv4_config *config) +{ + return etm4_get_access_type(config) << TRCACATR_EXLEVEL_SHIFT; +} + +static void etm4_set_comparator_filter(struct etmv4_config *config, + u64 start, u64 stop, int comparator) +{ + u64 access_type = etm4_get_comparator_access_type(config); + + /* First half of default address comparator */ + config->addr_val[comparator] = start; + config->addr_acc[comparator] = access_type; + config->addr_type[comparator] = ETM_ADDR_TYPE_RANGE; + + /* Second half of default address comparator */ + config->addr_val[comparator + 1] = stop; + config->addr_acc[comparator + 1] = access_type; + config->addr_type[comparator + 1] = ETM_ADDR_TYPE_RANGE; + + /* + * Configure the ViewInst function to include this address range + * comparator. + * + * @comparator is divided by two since it is the index in the + * etmv4_config::addr_val array but register TRCVIIECTLR deals with + * address range comparator _pairs_. + * + * Therefore: + * index 0 -> compatator pair 0 + * index 2 -> comparator pair 1 + * index 4 -> comparator pair 2 + * ... + * index 14 -> comparator pair 7 + */ + config->viiectlr |= BIT(comparator / 2); +} + +static void etm4_set_start_stop_filter(struct etmv4_config *config, + u64 address, int comparator, + enum etm_addr_type type) +{ + int shift; + u64 access_type = etm4_get_comparator_access_type(config); + + /* Configure the comparator */ + config->addr_val[comparator] = address; + config->addr_acc[comparator] = access_type; + config->addr_type[comparator] = type; + + /* + * Configure ViewInst Start-Stop control register. + * Addresses configured to start tracing go from bit 0 to n-1, + * while those configured to stop tracing from 16 to 16 + n-1. + */ + shift = (type == ETM_ADDR_TYPE_START ? 0 : 16); + config->vissctlr |= BIT(shift + comparator); +} + +static void etm4_set_default_filter(struct etmv4_config *config) +{ + /* Trace everything 'default' filter achieved by no filtering */ + config->viiectlr = 0x0; + + /* + * TRCVICTLR::SSSTATUS == 1, the start-stop logic is + * in the started state + */ + config->vinst_ctrl |= TRCVICTLR_SSSTATUS; + config->mode |= ETM_MODE_VIEWINST_STARTSTOP; + + /* No start-stop filtering for ViewInst */ + config->vissctlr = 0x0; +} + +static void etm4_set_default(struct etmv4_config *config) +{ + if (WARN_ON_ONCE(!config)) + return; + + /* + * Make default initialisation trace everything + * + * This is done by a minimum default config sufficient to enable + * full instruction trace - with a default filter for trace all + * achieved by having no filtering. + */ + etm4_set_default_config(config); + etm4_set_default_filter(config); +} + +static int etm4_get_next_comparator(struct etmv4_drvdata *drvdata, u32 type) +{ + int nr_comparator, index = 0; + struct etmv4_config *config = &drvdata->config; + + /* + * nr_addr_cmp holds the number of comparator _pair_, so time 2 + * for the total number of comparators. + */ + nr_comparator = drvdata->nr_addr_cmp * 2; + + /* Go through the tally of comparators looking for a free one. */ + while (index < nr_comparator) { + switch (type) { + case ETM_ADDR_TYPE_RANGE: + if (config->addr_type[index] == ETM_ADDR_TYPE_NONE && + config->addr_type[index + 1] == ETM_ADDR_TYPE_NONE) + return index; + + /* Address range comparators go in pairs */ + index += 2; + break; + case ETM_ADDR_TYPE_START: + case ETM_ADDR_TYPE_STOP: + if (config->addr_type[index] == ETM_ADDR_TYPE_NONE) + return index; + + /* Start/stop address can have odd indexes */ + index += 1; + break; + default: + return -EINVAL; + } + } + + /* If we are here all the comparators have been used. */ + return -ENOSPC; +} + +static int etm4_set_event_filters(struct etmv4_drvdata *drvdata, + struct perf_event *event) +{ + int i, comparator, ret = 0; + u64 address; + struct etmv4_config *config = &drvdata->config; + struct etm_filters *filters = event->hw.addr_filters; + + if (!filters) + goto default_filter; + + /* Sync events with what Perf got */ + perf_event_addr_filters_sync(event); + + /* + * If there are no filters to deal with simply go ahead with + * the default filter, i.e the entire address range. + */ + if (!filters->nr_filters) + goto default_filter; + + for (i = 0; i < filters->nr_filters; i++) { + struct etm_filter *filter = &filters->etm_filter[i]; + enum etm_addr_type type = filter->type; + + /* See if a comparator is free. */ + comparator = etm4_get_next_comparator(drvdata, type); + if (comparator < 0) { + ret = comparator; + goto out; + } + + switch (type) { + case ETM_ADDR_TYPE_RANGE: + etm4_set_comparator_filter(config, + filter->start_addr, + filter->stop_addr, + comparator); + /* + * TRCVICTLR::SSSTATUS == 1, the start-stop logic is + * in the started state + */ + config->vinst_ctrl |= TRCVICTLR_SSSTATUS; + + /* No start-stop filtering for ViewInst */ + config->vissctlr = 0x0; + break; + case ETM_ADDR_TYPE_START: + case ETM_ADDR_TYPE_STOP: + /* Get the right start or stop address */ + address = (type == ETM_ADDR_TYPE_START ? + filter->start_addr : + filter->stop_addr); + + /* Configure comparator */ + etm4_set_start_stop_filter(config, address, + comparator, type); + + /* + * If filters::ssstatus == 1, trace acquisition was + * started but the process was yanked away before the + * stop address was hit. As such the start/stop + * logic needs to be re-started so that tracing can + * resume where it left. + * + * The start/stop logic status when a process is + * scheduled out is checked in function + * etm4_disable_perf(). + */ + if (filters->ssstatus) + config->vinst_ctrl |= TRCVICTLR_SSSTATUS; + + /* No include/exclude filtering for ViewInst */ + config->viiectlr = 0x0; + break; + default: + ret = -EINVAL; + goto out; + } + } + + goto out; + + +default_filter: + etm4_set_default_filter(config); + +out: + return ret; +} + +void etm4_config_trace_mode(struct etmv4_config *config) +{ + u32 mode; + + mode = config->mode; + mode &= (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER); + + /* excluding kernel AND user space doesn't make sense */ + WARN_ON_ONCE(mode == (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER)); + + /* nothing to do if neither flags are set */ + if (!(mode & ETM_MODE_EXCL_KERN) && !(mode & ETM_MODE_EXCL_USER)) + return; + + etm4_set_victlr_access(config); +} + +static int etm4_online_cpu(unsigned int cpu) +{ + if (!etmdrvdata[cpu]) + return etm4_probe_cpu(cpu); + + if (etmdrvdata[cpu]->boot_enable && !etmdrvdata[cpu]->sticky_enable) + coresight_enable_sysfs(etmdrvdata[cpu]->csdev); + return 0; +} + +static int etm4_starting_cpu(unsigned int cpu) +{ + if (!etmdrvdata[cpu]) + return 0; + + raw_spin_lock(&etmdrvdata[cpu]->spinlock); + if (!etmdrvdata[cpu]->os_unlock) + etm4_os_unlock(etmdrvdata[cpu]); + + if (coresight_get_mode(etmdrvdata[cpu]->csdev)) + etm4_enable_hw(etmdrvdata[cpu]); + raw_spin_unlock(&etmdrvdata[cpu]->spinlock); + return 0; +} + +static int etm4_dying_cpu(unsigned int cpu) +{ + if (!etmdrvdata[cpu]) + return 0; + + raw_spin_lock(&etmdrvdata[cpu]->spinlock); + if (coresight_get_mode(etmdrvdata[cpu]->csdev)) + etm4_disable_hw(etmdrvdata[cpu]); + raw_spin_unlock(&etmdrvdata[cpu]->spinlock); + return 0; +} + +static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) +{ + int i, ret = 0; + struct etmv4_save_state *state; + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa; + struct device *etm_dev; + + if (WARN_ON(!csdev)) + return -ENODEV; + + etm_dev = &csdev->dev; + csa = &csdev->access; + + /* + * As recommended by 3.4.1 ("The procedure when powering down the PE") + * of ARM IHI 0064D + */ + dsb(sy); + isb(); + + etm4_cs_unlock(drvdata, csa); + /* Lock the OS lock to disable trace and external debugger access */ + etm4_os_lock(drvdata); + + /* wait for TRCSTATR.PMSTABLE to go up */ + if (etm4x_wait_status(csa, TRCSTATR_PMSTABLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for PM Stable Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + if (!drvdata->paused) + etm4_disable_trace_unit(drvdata); + + state = drvdata->save_state; + + if (drvdata->nr_pe) + state->trcprocselr = etm4x_read32(csa, TRCPROCSELR); + state->trcconfigr = etm4x_read32(csa, TRCCONFIGR); + state->trcauxctlr = etm4x_read32(csa, TRCAUXCTLR); + state->trceventctl0r = etm4x_read32(csa, TRCEVENTCTL0R); + state->trceventctl1r = etm4x_read32(csa, TRCEVENTCTL1R); + if (drvdata->stallctl) + state->trcstallctlr = etm4x_read32(csa, TRCSTALLCTLR); + state->trctsctlr = etm4x_read32(csa, TRCTSCTLR); + state->trcsyncpr = etm4x_read32(csa, TRCSYNCPR); + state->trcccctlr = etm4x_read32(csa, TRCCCCTLR); + state->trcbbctlr = etm4x_read32(csa, TRCBBCTLR); + state->trctraceidr = etm4x_read32(csa, TRCTRACEIDR); + if (drvdata->q_filt) + state->trcqctlr = etm4x_read32(csa, TRCQCTLR); + + state->trcvictlr = etm4x_read32(csa, TRCVICTLR); + state->trcviiectlr = etm4x_read32(csa, TRCVIIECTLR); + state->trcvissctlr = etm4x_read32(csa, TRCVISSCTLR); + if (drvdata->nr_pe_cmp) + state->trcvipcssctlr = etm4x_read32(csa, TRCVIPCSSCTLR); + + for (i = 0; i < drvdata->nrseqstate - 1; i++) + state->trcseqevr[i] = etm4x_read32(csa, TRCSEQEVRn(i)); + + if (drvdata->nrseqstate) { + state->trcseqrstevr = etm4x_read32(csa, TRCSEQRSTEVR); + state->trcseqstr = etm4x_read32(csa, TRCSEQSTR); + } + + if (drvdata->numextinsel) + state->trcextinselr = etm4x_read32(csa, TRCEXTINSELR); + + for (i = 0; i < drvdata->nr_cntr; i++) { + state->trccntrldvr[i] = etm4x_read32(csa, TRCCNTRLDVRn(i)); + state->trccntctlr[i] = etm4x_read32(csa, TRCCNTCTLRn(i)); + state->trccntvr[i] = etm4x_read32(csa, TRCCNTVRn(i)); + } + + /* Resource selector pair 0 is reserved */ + for (i = 2; i < drvdata->nr_resource * 2; i++) + state->trcrsctlr[i] = etm4x_read32(csa, TRCRSCTLRn(i)); + + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + state->trcssccr[i] = etm4x_read32(csa, TRCSSCCRn(i)); + state->trcsscsr[i] = etm4x_read32(csa, TRCSSCSRn(i)); + if (etm4x_sspcicrn_present(drvdata, i)) + state->trcsspcicr[i] = etm4x_read32(csa, TRCSSPCICRn(i)); + } + + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { + state->trcacvr[i] = etm4x_read64(csa, TRCACVRn(i)); + state->trcacatr[i] = etm4x_read64(csa, TRCACATRn(i)); + } + + /* + * Data trace stream is architecturally prohibited for A profile cores + * so we don't save (or later restore) trcdvcvr and trcdvcmr - As per + * section 1.3.4 ("Possible functional configurations of an ETMv4 trace + * unit") of ARM IHI 0064D. + */ + + for (i = 0; i < drvdata->numcidc; i++) + state->trccidcvr[i] = etm4x_read64(csa, TRCCIDCVRn(i)); + + for (i = 0; i < drvdata->numvmidc; i++) + state->trcvmidcvr[i] = etm4x_read64(csa, TRCVMIDCVRn(i)); + + state->trccidcctlr0 = etm4x_read32(csa, TRCCIDCCTLR0); + if (drvdata->numcidc > 4) + state->trccidcctlr1 = etm4x_read32(csa, TRCCIDCCTLR1); + + state->trcvmidcctlr0 = etm4x_read32(csa, TRCVMIDCCTLR0); + if (drvdata->numvmidc > 4) + state->trcvmidcctlr0 = etm4x_read32(csa, TRCVMIDCCTLR1); + + state->trcclaimset = etm4x_read32(csa, TRCCLAIMCLR); + + if (!drvdata->skip_power_up) + state->trcpdcr = etm4x_read32(csa, TRCPDCR); + + /* wait for TRCSTATR.IDLE to go up */ + if (etm4x_wait_status(csa, TRCSTATR_IDLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + /* + * Power can be removed from the trace unit now. We do this to + * potentially save power on systems that respect the TRCPDCR_PU + * despite requesting software to save/restore state. + */ + if (!drvdata->skip_power_up) + etm4x_relaxed_write32(csa, (state->trcpdcr & ~TRCPDCR_PU), + TRCPDCR); +out: + etm4_cs_lock(drvdata, csa); + return ret; +} + +static int etm4_cpu_save(struct etmv4_drvdata *drvdata) +{ + int ret = 0; + + if (pm_save_enable != PARAM_PM_SAVE_SELF_HOSTED) + return 0; + + /* + * Save and restore the ETM Trace registers only if + * the ETM is active. + */ + if (coresight_get_mode(drvdata->csdev)) + ret = __etm4_cpu_save(drvdata); + return ret; +} + +static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) +{ + int i; + struct etmv4_save_state *state = drvdata->save_state; + struct csdev_access *csa = &drvdata->csdev->access; + + if (WARN_ON(!drvdata->csdev)) + return; + + etm4_cs_unlock(drvdata, csa); + etm4x_relaxed_write32(csa, state->trcclaimset, TRCCLAIMSET); + + if (drvdata->nr_pe) + etm4x_relaxed_write32(csa, state->trcprocselr, TRCPROCSELR); + etm4x_relaxed_write32(csa, state->trcconfigr, TRCCONFIGR); + etm4x_relaxed_write32(csa, state->trcauxctlr, TRCAUXCTLR); + etm4x_relaxed_write32(csa, state->trceventctl0r, TRCEVENTCTL0R); + etm4x_relaxed_write32(csa, state->trceventctl1r, TRCEVENTCTL1R); + if (drvdata->stallctl) + etm4x_relaxed_write32(csa, state->trcstallctlr, TRCSTALLCTLR); + etm4x_relaxed_write32(csa, state->trctsctlr, TRCTSCTLR); + etm4x_relaxed_write32(csa, state->trcsyncpr, TRCSYNCPR); + etm4x_relaxed_write32(csa, state->trcccctlr, TRCCCCTLR); + etm4x_relaxed_write32(csa, state->trcbbctlr, TRCBBCTLR); + etm4x_relaxed_write32(csa, state->trctraceidr, TRCTRACEIDR); + if (drvdata->q_filt) + etm4x_relaxed_write32(csa, state->trcqctlr, TRCQCTLR); + + etm4x_relaxed_write32(csa, state->trcvictlr, TRCVICTLR); + etm4x_relaxed_write32(csa, state->trcviiectlr, TRCVIIECTLR); + etm4x_relaxed_write32(csa, state->trcvissctlr, TRCVISSCTLR); + if (drvdata->nr_pe_cmp) + etm4x_relaxed_write32(csa, state->trcvipcssctlr, TRCVIPCSSCTLR); + + for (i = 0; i < drvdata->nrseqstate - 1; i++) + etm4x_relaxed_write32(csa, state->trcseqevr[i], TRCSEQEVRn(i)); + + if (drvdata->nrseqstate) { + etm4x_relaxed_write32(csa, state->trcseqrstevr, TRCSEQRSTEVR); + etm4x_relaxed_write32(csa, state->trcseqstr, TRCSEQSTR); + } + if (drvdata->numextinsel) + etm4x_relaxed_write32(csa, state->trcextinselr, TRCEXTINSELR); + + for (i = 0; i < drvdata->nr_cntr; i++) { + etm4x_relaxed_write32(csa, state->trccntrldvr[i], TRCCNTRLDVRn(i)); + etm4x_relaxed_write32(csa, state->trccntctlr[i], TRCCNTCTLRn(i)); + etm4x_relaxed_write32(csa, state->trccntvr[i], TRCCNTVRn(i)); + } + + /* Resource selector pair 0 is reserved */ + for (i = 2; i < drvdata->nr_resource * 2; i++) + etm4x_relaxed_write32(csa, state->trcrsctlr[i], TRCRSCTLRn(i)); + + for (i = 0; i < drvdata->nr_ss_cmp; i++) { + etm4x_relaxed_write32(csa, state->trcssccr[i], TRCSSCCRn(i)); + etm4x_relaxed_write32(csa, state->trcsscsr[i], TRCSSCSRn(i)); + if (etm4x_sspcicrn_present(drvdata, i)) + etm4x_relaxed_write32(csa, state->trcsspcicr[i], TRCSSPCICRn(i)); + } + + for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { + etm4x_relaxed_write64(csa, state->trcacvr[i], TRCACVRn(i)); + etm4x_relaxed_write64(csa, state->trcacatr[i], TRCACATRn(i)); + } + + for (i = 0; i < drvdata->numcidc; i++) + etm4x_relaxed_write64(csa, state->trccidcvr[i], TRCCIDCVRn(i)); + + for (i = 0; i < drvdata->numvmidc; i++) + etm4x_relaxed_write64(csa, state->trcvmidcvr[i], TRCVMIDCVRn(i)); + + etm4x_relaxed_write32(csa, state->trccidcctlr0, TRCCIDCCTLR0); + if (drvdata->numcidc > 4) + etm4x_relaxed_write32(csa, state->trccidcctlr1, TRCCIDCCTLR1); + + etm4x_relaxed_write32(csa, state->trcvmidcctlr0, TRCVMIDCCTLR0); + if (drvdata->numvmidc > 4) + etm4x_relaxed_write32(csa, state->trcvmidcctlr0, TRCVMIDCCTLR1); + + etm4x_relaxed_write32(csa, state->trcclaimset, TRCCLAIMSET); + + if (!drvdata->skip_power_up) + etm4x_relaxed_write32(csa, state->trcpdcr, TRCPDCR); + + /* + * As recommended by section 4.3.7 ("Synchronization when using the + * memory-mapped interface") of ARM IHI 0064D + */ + dsb(sy); + isb(); + + /* Unlock the OS lock to re-enable trace and external debug access */ + etm4_os_unlock(drvdata); + + if (!drvdata->paused) + etm4_enable_trace_unit(drvdata); + + etm4_cs_lock(drvdata, csa); +} + +static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) +{ + if (pm_save_enable != PARAM_PM_SAVE_SELF_HOSTED) + return; + + if (coresight_get_mode(drvdata->csdev)) + __etm4_cpu_restore(drvdata); +} + +static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, + void *v) +{ + struct etmv4_drvdata *drvdata; + unsigned int cpu = smp_processor_id(); + + if (!etmdrvdata[cpu]) + return NOTIFY_OK; + + drvdata = etmdrvdata[cpu]; + + if (WARN_ON_ONCE(drvdata->cpu != cpu)) + return NOTIFY_BAD; + + switch (cmd) { + case CPU_PM_ENTER: + if (etm4_cpu_save(drvdata)) + return NOTIFY_BAD; + break; + case CPU_PM_EXIT: + case CPU_PM_ENTER_FAILED: + etm4_cpu_restore(drvdata); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block etm4_cpu_pm_nb = { + .notifier_call = etm4_cpu_pm_notify, +}; + +/* Setup PM. Deals with error conditions and counts */ +static int __init etm4_pm_setup(void) +{ + int ret; + + ret = cpu_pm_register_notifier(&etm4_cpu_pm_nb); + if (ret) + return ret; + + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING, + "arm/coresight4:starting", + etm4_starting_cpu, etm4_dying_cpu); + + if (ret) + goto unregister_notifier; + + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "arm/coresight4:online", + etm4_online_cpu, NULL); + + /* HP dyn state ID returned in ret on success */ + if (ret > 0) { + hp_online = ret; + return 0; + } + + /* failed dyn state - remove others */ + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); + +unregister_notifier: + cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); + return ret; +} + +static void etm4_pm_clear(void) +{ + cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); + cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); + if (hp_online) { + cpuhp_remove_state_nocalls(hp_online); + hp_online = 0; + } +} + +static int etm4_add_coresight_dev(struct etm4_init_arg *init_arg) +{ + int ret; + struct coresight_platform_data *pdata = NULL; + struct device *dev = init_arg->dev; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); + struct coresight_desc desc = { 0 }; + u8 major, minor; + char *type_name; + + if (!drvdata) + return -EINVAL; + + desc.access = *init_arg->csa; + + if (!drvdata->arch) + return -EINVAL; + + major = ETM_ARCH_MAJOR_VERSION(drvdata->arch); + minor = ETM_ARCH_MINOR_VERSION(drvdata->arch); + + if (etm4x_is_ete(drvdata)) { + type_name = "ete"; + /* ETE v1 has major version == 0b101. Adjust this for logging.*/ + major -= 4; + } else { + type_name = "etm"; + } + + desc.name = devm_kasprintf(dev, GFP_KERNEL, + "%s%d", type_name, drvdata->cpu); + if (!desc.name) + return -ENOMEM; + + etm4_set_default(&drvdata->config); + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + + dev->platform_data = pdata; + + desc.type = CORESIGHT_DEV_TYPE_SOURCE; + desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC; + desc.ops = &etm4_cs_ops; + desc.pdata = pdata; + desc.dev = dev; + desc.groups = coresight_etmv4_groups; + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + ret = etm_perf_symlink(drvdata->csdev, true); + if (ret) { + coresight_unregister(drvdata->csdev); + return ret; + } + + /* register with config infrastructure & load any current features */ + ret = etm4_cscfg_register(drvdata->csdev); + if (ret) { + coresight_unregister(drvdata->csdev); + return ret; + } + + etmdrvdata[drvdata->cpu] = drvdata; + + dev_info(&drvdata->csdev->dev, "CPU%d: %s v%d.%d initialized\n", + drvdata->cpu, type_name, major, minor); + + if (boot_enable) { + coresight_enable_sysfs(drvdata->csdev); + drvdata->boot_enable = true; + } + + return 0; +} + +static int etm4_probe(struct device *dev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); + struct csdev_access access = { 0 }; + struct etm4_init_arg init_arg = { 0 }; + struct etm4_init_arg *delayed; + int ret; + + if (WARN_ON(!drvdata)) + return -ENOMEM; + + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + + if (pm_save_enable == PARAM_PM_SAVE_FIRMWARE) + pm_save_enable = coresight_loses_context_with_cpu(dev) ? + PARAM_PM_SAVE_SELF_HOSTED : PARAM_PM_SAVE_NEVER; + + if (pm_save_enable != PARAM_PM_SAVE_NEVER) { + drvdata->save_state = devm_kmalloc(dev, + sizeof(struct etmv4_save_state), GFP_KERNEL); + if (!drvdata->save_state) + return -ENOMEM; + } + + raw_spin_lock_init(&drvdata->spinlock); + + drvdata->cpu = coresight_get_cpu(dev); + if (drvdata->cpu < 0) + return drvdata->cpu; + + init_arg.dev = dev; + init_arg.csa = &access; + + /* + * Serialize against CPUHP callbacks to avoid race condition + * between the smp call and saving the delayed probe. + */ + cpus_read_lock(); + if (smp_call_function_single(drvdata->cpu, + etm4_init_arch_data, &init_arg, 1)) { + /* The CPU was offline, try again once it comes online. */ + delayed = devm_kmalloc(dev, sizeof(*delayed), GFP_KERNEL); + if (!delayed) { + cpus_read_unlock(); + return -ENOMEM; + } + + *delayed = init_arg; + + per_cpu(delayed_probe, drvdata->cpu) = delayed; + + cpus_read_unlock(); + return 0; + } + cpus_read_unlock(); + + return etm4_add_coresight_dev(&init_arg); +} + +static int etm4_probe_amba(struct amba_device *adev, const struct amba_id *id) +{ + struct etmv4_drvdata *drvdata; + void __iomem *base; + struct device *dev = &adev->dev; + struct resource *res = &adev->res; + int ret; + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->base = base; + dev_set_drvdata(dev, drvdata); + ret = etm4_probe(dev); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static int etm4_probe_platform_dev(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + struct etmv4_drvdata *drvdata; + int ret; + + drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + if (res) { + drvdata->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(drvdata->base)) + return PTR_ERR(drvdata->base); + } + + dev_set_drvdata(&pdev->dev, drvdata); + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = etm4_probe(&pdev->dev); + + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static int etm4_probe_cpu(unsigned int cpu) +{ + int ret; + struct etm4_init_arg init_arg; + struct csdev_access access = { 0 }; + struct etm4_init_arg *iap = *this_cpu_ptr(&delayed_probe); + + if (!iap) + return 0; + + init_arg = *iap; + devm_kfree(init_arg.dev, iap); + *this_cpu_ptr(&delayed_probe) = NULL; + + ret = pm_runtime_resume_and_get(init_arg.dev); + if (ret < 0) { + dev_err(init_arg.dev, "Failed to get PM runtime!\n"); + return 0; + } + + init_arg.csa = &access; + etm4_init_arch_data(&init_arg); + + etm4_add_coresight_dev(&init_arg); + + pm_runtime_put(init_arg.dev); + return 0; +} + +static struct amba_cs_uci_id uci_id_etm4[] = { + { + /* ETMv4 UCI data */ + .devarch = ETM_DEVARCH_ETMv4x_ARCH, + .devarch_mask = ETM_DEVARCH_ID_MASK, + .devtype = CS_DEVTYPE_PE_TRACE, + } +}; + +static void clear_etmdrvdata(void *info) +{ + int cpu = *(int *)info; + + etmdrvdata[cpu] = NULL; + per_cpu(delayed_probe, cpu) = NULL; +} + +static void etm4_remove_dev(struct etmv4_drvdata *drvdata) +{ + bool had_delayed_probe; + /* + * Taking hotplug lock here to avoid racing between etm4_remove_dev() + * and CPU hotplug call backs. + */ + cpus_read_lock(); + + had_delayed_probe = per_cpu(delayed_probe, drvdata->cpu); + + /* + * The readers for etmdrvdata[] are CPU hotplug call backs + * and PM notification call backs. Change etmdrvdata[i] on + * CPU i ensures these call backs has consistent view + * inside one call back function. + */ + if (smp_call_function_single(drvdata->cpu, clear_etmdrvdata, &drvdata->cpu, 1)) + clear_etmdrvdata(&drvdata->cpu); + + cpus_read_unlock(); + + if (!had_delayed_probe) { + etm_perf_symlink(drvdata->csdev, false); + cscfg_unregister_csdev(drvdata->csdev); + coresight_unregister(drvdata->csdev); + } +} + +static void etm4_remove_amba(struct amba_device *adev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + if (drvdata) + etm4_remove_dev(drvdata); +} + +static void etm4_remove_platform_dev(struct platform_device *pdev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (drvdata) + etm4_remove_dev(drvdata); + pm_runtime_disable(&pdev->dev); +} + +static const struct amba_id etm4_ids[] = { + CS_AMBA_ID(0x000bb95d), /* Cortex-A53 */ + CS_AMBA_ID(0x000bb95e), /* Cortex-A57 */ + CS_AMBA_ID(0x000bb95a), /* Cortex-A72 */ + CS_AMBA_ID(0x000bb959), /* Cortex-A73 */ + CS_AMBA_UCI_ID(0x000bb9da, uci_id_etm4),/* Cortex-A35 */ + CS_AMBA_UCI_ID(0x000bbd05, uci_id_etm4),/* Cortex-A55 */ + CS_AMBA_UCI_ID(0x000bbd0a, uci_id_etm4),/* Cortex-A75 */ + CS_AMBA_UCI_ID(0x000bbd0c, uci_id_etm4),/* Neoverse N1 */ + CS_AMBA_UCI_ID(0x000bbd41, uci_id_etm4),/* Cortex-A78 */ + CS_AMBA_UCI_ID(0x000f0205, uci_id_etm4),/* Qualcomm Kryo */ + CS_AMBA_UCI_ID(0x000f0211, uci_id_etm4),/* Qualcomm Kryo */ + CS_AMBA_UCI_ID(0x000bb802, uci_id_etm4),/* Qualcomm Kryo 385 Cortex-A55 */ + CS_AMBA_UCI_ID(0x000bb803, uci_id_etm4),/* Qualcomm Kryo 385 Cortex-A75 */ + CS_AMBA_UCI_ID(0x000bb805, uci_id_etm4),/* Qualcomm Kryo 4XX Cortex-A55 */ + CS_AMBA_UCI_ID(0x000bb804, uci_id_etm4),/* Qualcomm Kryo 4XX Cortex-A76 */ + CS_AMBA_UCI_ID(0x000bbd0d, uci_id_etm4),/* Qualcomm Kryo 5XX Cortex-A77 */ + CS_AMBA_UCI_ID(0x000cc0af, uci_id_etm4),/* Marvell ThunderX2 */ + CS_AMBA_UCI_ID(0x000b6d01, uci_id_etm4),/* HiSilicon-Hip08 */ + CS_AMBA_UCI_ID(0x000b6d02, uci_id_etm4),/* HiSilicon-Hip09 */ + /* + * Match all PIDs with ETM4 DEVARCH. No need for adding any of the new + * CPUs to the list here. + */ + CS_AMBA_MATCH_ALL_UCI(uci_id_etm4), + {}, +}; + +MODULE_DEVICE_TABLE(amba, etm4_ids); + +static struct amba_driver etm4x_amba_driver = { + .drv = { + .name = "coresight-etm4x", + .suppress_bind_attrs = true, + }, + .probe = etm4_probe_amba, + .remove = etm4_remove_amba, + .id_table = etm4_ids, +}; + +#ifdef CONFIG_PM +static int etm4_runtime_suspend(struct device *dev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); + + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); + + return 0; +} + +static int etm4_runtime_resume(struct device *dev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; + + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; +} +#endif + +static const struct dev_pm_ops etm4_dev_pm_ops = { + SET_RUNTIME_PM_OPS(etm4_runtime_suspend, etm4_runtime_resume, NULL) +}; + +static const struct of_device_id etm4_sysreg_match[] = { + { .compatible = "arm,coresight-etm4x-sysreg" }, + { .compatible = "arm,embedded-trace-extension" }, + {} +}; + +#ifdef CONFIG_ACPI +static const struct acpi_device_id etm4x_acpi_ids[] = { + {"ARMHC500", 0, 0, 0}, /* ARM CoreSight ETM4x */ + {} +}; +MODULE_DEVICE_TABLE(acpi, etm4x_acpi_ids); +#endif + +static struct platform_driver etm4_platform_driver = { + .probe = etm4_probe_platform_dev, + .remove = etm4_remove_platform_dev, + .driver = { + .name = "coresight-etm4x", + .of_match_table = etm4_sysreg_match, + .acpi_match_table = ACPI_PTR(etm4x_acpi_ids), + .suppress_bind_attrs = true, + .pm = &etm4_dev_pm_ops, + }, +}; + +static int __init etm4x_init(void) +{ + int ret; + + ret = etm4_pm_setup(); + + /* etm4_pm_setup() does its own cleanup - exit on error */ + if (ret) + return ret; + + ret = amba_driver_register(&etm4x_amba_driver); + if (ret) { + pr_err("Error registering etm4x AMBA driver\n"); + goto clear_pm; + } + + ret = platform_driver_register(&etm4_platform_driver); + if (!ret) + return 0; + + pr_err("Error registering etm4x platform driver\n"); + amba_driver_unregister(&etm4x_amba_driver); + +clear_pm: + etm4_pm_clear(); + return ret; +} + +static void __exit etm4x_exit(void) +{ + amba_driver_unregister(&etm4x_amba_driver); + platform_driver_unregister(&etm4_platform_driver); + etm4_pm_clear(); +} + +module_init(etm4x_init); +module_exit(etm4x_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight Program Flow Trace v4.x driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index a0365e23678e..e9eeea6240d5 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -4,11 +4,14 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/bitfield.h> +#include <linux/coresight.h> #include <linux/pid_namespace.h> #include <linux/pm_runtime.h> #include <linux/sysfs.h> #include "coresight-etm4x.h" #include "coresight-priv.h" +#include "coresight-syscfg.h" static int etm4_set_mode_exclude(struct etmv4_drvdata *drvdata, bool exclude) { @@ -21,7 +24,7 @@ static int etm4_set_mode_exclude(struct etmv4_drvdata *drvdata, bool exclude) * TRCACATRn.TYPE bit[1:0]: type of comparison * the trace unit performs */ - if (BMVAL(config->addr_acc[idx], 0, 1) == ETM_INSTR_ADDR) { + if (FIELD_GET(TRCACATRn_TYPE_MASK, config->addr_acc[idx]) == TRCACATRn_TYPE_ADDR) { if (idx % 2 != 0) return -EINVAL; @@ -173,18 +176,18 @@ static ssize_t reset_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); if (val) config->mode = 0x0; /* Disable data tracing: do not trace load and store data transfers */ config->mode &= ~(ETM_MODE_LOAD | ETM_MODE_STORE); - config->cfg &= ~(BIT(1) | BIT(2)); + config->cfg &= ~(TRCCONFIGR_INSTP0_LOAD | TRCCONFIGR_INSTP0_STORE); /* Disable data value and data address tracing */ config->mode &= ~(ETM_MODE_DATA_TRACE_ADDR | ETM_MODE_DATA_TRACE_VAL); - config->cfg &= ~(BIT(16) | BIT(17)); + config->cfg &= ~(TRCCONFIGR_DA | TRCCONFIGR_DV); /* Disable all events tracing */ config->eventctrl0 = 0x0; @@ -205,11 +208,11 @@ static ssize_t reset_store(struct device *dev, * started state. ARM recommends start-stop logic is set before * each trace run. */ - config->vinst_ctrl |= BIT(0); - if (drvdata->nr_addr_cmp == true) { + config->vinst_ctrl = FIELD_PREP(TRCVICTLR_EVENT_MASK, 0x01); + if (drvdata->nr_addr_cmp > 0) { config->mode |= ETM_MODE_VIEWINST_STARTSTOP; /* SSSTATUS, bit[9] */ - config->vinst_ctrl |= BIT(9); + config->vinst_ctrl |= TRCVICTLR_SSSTATUS; } /* No address range filtering for ViewInst */ @@ -217,6 +220,7 @@ static ssize_t reset_store(struct device *dev, /* No start-stop filtering for ViewInst */ config->vissctlr = 0x0; + config->vipcssctlr = 0x0; /* Disable seq events */ for (i = 0; i < drvdata->nrseqstate-1; i++) @@ -235,9 +239,10 @@ static ssize_t reset_store(struct device *dev, } config->res_idx = 0x0; - for (i = 0; i < drvdata->nr_resource; i++) + for (i = 2; i < 2 * drvdata->nr_resource; i++) config->res_ctrl[i] = 0x0; + config->ss_idx = 0x0; for (i = 0; i < drvdata->nr_ss_cmp; i++) { config->ss_ctrl[i] = 0x0; config->ss_pe_cmp[i] = 0x0; @@ -263,9 +268,12 @@ static ssize_t reset_store(struct device *dev, config->vmid_mask0 = 0x0; config->vmid_mask1 = 0x0; - drvdata->trcid = drvdata->cpu + 1; + raw_spin_unlock(&drvdata->spinlock); - spin_unlock(&drvdata->spinlock); + /* for sysfs - only release trace id when resetting */ + etm4_release_trace_id(drvdata); + + cscfg_csdev_reset_feats(to_coresight_device(dev)); return size; } @@ -294,145 +302,144 @@ static ssize_t mode_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->mode = val & ETMv4_MODE_ALL; - if (config->mode & ETM_MODE_EXCLUDE) - etm4_set_mode_exclude(drvdata, true); - else - etm4_set_mode_exclude(drvdata, false); - if (drvdata->instrp0 == true) { /* start by clearing instruction P0 field */ - config->cfg &= ~(BIT(1) | BIT(2)); + config->cfg &= ~TRCCONFIGR_INSTP0_LOAD_STORE; if (config->mode & ETM_MODE_LOAD) /* 0b01 Trace load instructions as P0 instructions */ - config->cfg |= BIT(1); + config->cfg |= TRCCONFIGR_INSTP0_LOAD; if (config->mode & ETM_MODE_STORE) /* 0b10 Trace store instructions as P0 instructions */ - config->cfg |= BIT(2); + config->cfg |= TRCCONFIGR_INSTP0_STORE; if (config->mode & ETM_MODE_LOAD_STORE) /* * 0b11 Trace load and store instructions * as P0 instructions */ - config->cfg |= BIT(1) | BIT(2); + config->cfg |= TRCCONFIGR_INSTP0_LOAD_STORE; } /* bit[3], Branch broadcast mode */ if ((config->mode & ETM_MODE_BB) && (drvdata->trcbb == true)) - config->cfg |= BIT(3); + config->cfg |= TRCCONFIGR_BB; else - config->cfg &= ~BIT(3); + config->cfg &= ~TRCCONFIGR_BB; /* bit[4], Cycle counting instruction trace bit */ if ((config->mode & ETMv4_MODE_CYCACC) && (drvdata->trccci == true)) - config->cfg |= BIT(4); + config->cfg |= TRCCONFIGR_CCI; else - config->cfg &= ~BIT(4); + config->cfg &= ~TRCCONFIGR_CCI; /* bit[6], Context ID tracing bit */ if ((config->mode & ETMv4_MODE_CTXID) && (drvdata->ctxid_size)) - config->cfg |= BIT(6); + config->cfg |= TRCCONFIGR_CID; else - config->cfg &= ~BIT(6); + config->cfg &= ~TRCCONFIGR_CID; if ((config->mode & ETM_MODE_VMID) && (drvdata->vmid_size)) - config->cfg |= BIT(7); + config->cfg |= TRCCONFIGR_VMID; else - config->cfg &= ~BIT(7); + config->cfg &= ~TRCCONFIGR_VMID; /* bits[10:8], Conditional instruction tracing bit */ mode = ETM_MODE_COND(config->mode); if (drvdata->trccond == true) { - config->cfg &= ~(BIT(8) | BIT(9) | BIT(10)); - config->cfg |= mode << 8; + config->cfg &= ~TRCCONFIGR_COND_MASK; + config->cfg |= mode << __bf_shf(TRCCONFIGR_COND_MASK); } /* bit[11], Global timestamp tracing bit */ if ((config->mode & ETMv4_MODE_TIMESTAMP) && (drvdata->ts_size)) - config->cfg |= BIT(11); + config->cfg |= TRCCONFIGR_TS; else - config->cfg &= ~BIT(11); + config->cfg &= ~TRCCONFIGR_TS; /* bit[12], Return stack enable bit */ if ((config->mode & ETM_MODE_RETURNSTACK) && (drvdata->retstack == true)) - config->cfg |= BIT(12); + config->cfg |= TRCCONFIGR_RS; else - config->cfg &= ~BIT(12); + config->cfg &= ~TRCCONFIGR_RS; /* bits[14:13], Q element enable field */ mode = ETM_MODE_QELEM(config->mode); /* start by clearing QE bits */ - config->cfg &= ~(BIT(13) | BIT(14)); - /* if supported, Q elements with instruction counts are enabled */ - if ((mode & BIT(0)) && (drvdata->q_support & BIT(0))) - config->cfg |= BIT(13); + config->cfg &= ~(TRCCONFIGR_QE_W_COUNTS | TRCCONFIGR_QE_WO_COUNTS); + /* + * if supported, Q elements with instruction counts are enabled. + * Always set the low bit for any requested mode. Valid combos are + * 0b00, 0b01 and 0b11. + */ + if (mode && drvdata->q_support) + config->cfg |= TRCCONFIGR_QE_W_COUNTS; /* * if supported, Q elements with and without instruction * counts are enabled */ if ((mode & BIT(1)) && (drvdata->q_support & BIT(1))) - config->cfg |= BIT(14); + config->cfg |= TRCCONFIGR_QE_WO_COUNTS; /* bit[11], AMBA Trace Bus (ATB) trigger enable bit */ if ((config->mode & ETM_MODE_ATB_TRIGGER) && (drvdata->atbtrig == true)) - config->eventctrl1 |= BIT(11); + config->eventctrl1 |= TRCEVENTCTL1R_ATB; else - config->eventctrl1 &= ~BIT(11); + config->eventctrl1 &= ~TRCEVENTCTL1R_ATB; /* bit[12], Low-power state behavior override bit */ if ((config->mode & ETM_MODE_LPOVERRIDE) && (drvdata->lpoverride == true)) - config->eventctrl1 |= BIT(12); + config->eventctrl1 |= TRCEVENTCTL1R_LPOVERRIDE; else - config->eventctrl1 &= ~BIT(12); + config->eventctrl1 &= ~TRCEVENTCTL1R_LPOVERRIDE; /* bit[8], Instruction stall bit */ - if (config->mode & ETM_MODE_ISTALL_EN) - config->stall_ctrl |= BIT(8); + if ((config->mode & ETM_MODE_ISTALL_EN) && (drvdata->stallctl == true)) + config->stall_ctrl |= TRCSTALLCTLR_ISTALL; else - config->stall_ctrl &= ~BIT(8); + config->stall_ctrl &= ~TRCSTALLCTLR_ISTALL; /* bit[10], Prioritize instruction trace bit */ if (config->mode & ETM_MODE_INSTPRIO) - config->stall_ctrl |= BIT(10); + config->stall_ctrl |= TRCSTALLCTLR_INSTPRIORITY; else - config->stall_ctrl &= ~BIT(10); + config->stall_ctrl &= ~TRCSTALLCTLR_INSTPRIORITY; /* bit[13], Trace overflow prevention bit */ if ((config->mode & ETM_MODE_NOOVERFLOW) && (drvdata->nooverflow == true)) - config->stall_ctrl |= BIT(13); + config->stall_ctrl |= TRCSTALLCTLR_NOOVERFLOW; else - config->stall_ctrl &= ~BIT(13); + config->stall_ctrl &= ~TRCSTALLCTLR_NOOVERFLOW; /* bit[9] Start/stop logic control bit */ if (config->mode & ETM_MODE_VIEWINST_STARTSTOP) - config->vinst_ctrl |= BIT(9); + config->vinst_ctrl |= TRCVICTLR_SSSTATUS; else - config->vinst_ctrl &= ~BIT(9); + config->vinst_ctrl &= ~TRCVICTLR_SSSTATUS; /* bit[10], Whether a trace unit must trace a Reset exception */ if (config->mode & ETM_MODE_TRACE_RESET) - config->vinst_ctrl |= BIT(10); + config->vinst_ctrl |= TRCVICTLR_TRCRESET; else - config->vinst_ctrl &= ~BIT(10); + config->vinst_ctrl &= ~TRCVICTLR_TRCRESET; /* bit[11], Whether a trace unit must trace a system error exception */ if ((config->mode & ETM_MODE_TRACE_ERR) && (drvdata->trc_error == true)) - config->vinst_ctrl |= BIT(11); + config->vinst_ctrl |= TRCVICTLR_TRCERR; else - config->vinst_ctrl &= ~BIT(11); + config->vinst_ctrl &= ~TRCVICTLR_TRCERR; if (config->mode & (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER)) etm4_config_trace_mode(config); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } @@ -461,14 +468,14 @@ static ssize_t pe_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); if (val > drvdata->nr_pe) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EINVAL; } config->pe_sel = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(pe); @@ -496,7 +503,7 @@ static ssize_t event_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); switch (drvdata->nr_event) { case 0x0: /* EVENT0, bits[7:0] */ @@ -517,7 +524,7 @@ static ssize_t event_store(struct device *dev, default: break; } - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(event); @@ -530,7 +537,7 @@ static ssize_t event_instren_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - val = BMVAL(config->eventctrl1, 0, 3); + val = FIELD_GET(TRCEVENTCTL1R_INSTEN_MASK, config->eventctrl1); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -545,30 +552,35 @@ static ssize_t event_instren_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); /* start by clearing all instruction event enable bits */ - config->eventctrl1 &= ~(BIT(0) | BIT(1) | BIT(2) | BIT(3)); + config->eventctrl1 &= ~TRCEVENTCTL1R_INSTEN_MASK; switch (drvdata->nr_event) { case 0x0: /* generate Event element for event 1 */ - config->eventctrl1 |= val & BIT(1); + config->eventctrl1 |= val & TRCEVENTCTL1R_INSTEN_1; break; case 0x1: /* generate Event element for event 1 and 2 */ - config->eventctrl1 |= val & (BIT(0) | BIT(1)); + config->eventctrl1 |= val & (TRCEVENTCTL1R_INSTEN_0 | TRCEVENTCTL1R_INSTEN_1); break; case 0x2: /* generate Event element for event 1, 2 and 3 */ - config->eventctrl1 |= val & (BIT(0) | BIT(1) | BIT(2)); + config->eventctrl1 |= val & (TRCEVENTCTL1R_INSTEN_0 | + TRCEVENTCTL1R_INSTEN_1 | + TRCEVENTCTL1R_INSTEN_2); break; case 0x3: /* generate Event element for all 4 events */ - config->eventctrl1 |= val & 0xF; + config->eventctrl1 |= val & (TRCEVENTCTL1R_INSTEN_0 | + TRCEVENTCTL1R_INSTEN_1 | + TRCEVENTCTL1R_INSTEN_2 | + TRCEVENTCTL1R_INSTEN_3); break; default: break; } - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(event_instren); @@ -655,10 +667,13 @@ static ssize_t cyc_threshold_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; + + /* mask off max threshold before checking min value */ + val &= ETM_CYC_THRESHOLD_MASK; if (val < drvdata->ccitmin) return -EINVAL; - config->ccctlr = val & ETM_CYC_THRESHOLD_MASK; + config->ccctlr = val; return size; } static DEVICE_ATTR_RW(cyc_threshold); @@ -689,14 +704,16 @@ static ssize_t bb_ctrl_store(struct device *dev, return -EINVAL; if (!drvdata->nr_addr_cmp) return -EINVAL; + /* - * Bit[7:0] selects which address range comparator is used for - * branch broadcast control. + * Bit[8] controls include(1) / exclude(0), bits[0-7] select + * individual range comparators. If include then at least 1 + * range must be selected. */ - if (BMVAL(val, 0, 7) > drvdata->nr_addr_cmp) + if ((val & TRCBBCTLR_MODE) && (FIELD_GET(TRCBBCTLR_RANGE_MASK, val) == 0)) return -EINVAL; - config->bb_ctrl = val; + config->bb_ctrl = val & (TRCBBCTLR_MODE | TRCBBCTLR_RANGE_MASK); return size; } static DEVICE_ATTR_RW(bb_ctrl); @@ -709,7 +726,7 @@ static ssize_t event_vinst_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - val = config->vinst_ctrl & ETMv4_EVENT_MASK; + val = FIELD_GET(TRCVICTLR_EVENT_MASK, config->vinst_ctrl); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -724,11 +741,11 @@ static ssize_t event_vinst_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); - val &= ETMv4_EVENT_MASK; - config->vinst_ctrl &= ~ETMv4_EVENT_MASK; - config->vinst_ctrl |= val; - spin_unlock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); + val &= TRCVICTLR_EVENT_MASK >> __bf_shf(TRCVICTLR_EVENT_MASK); + config->vinst_ctrl &= ~TRCVICTLR_EVENT_MASK; + config->vinst_ctrl |= FIELD_PREP(TRCVICTLR_EVENT_MASK, val); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(event_vinst); @@ -741,7 +758,7 @@ static ssize_t s_exlevel_vinst_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - val = BMVAL(config->vinst_ctrl, 16, 19); + val = FIELD_GET(TRCVICTLR_EXLEVEL_S_MASK, config->vinst_ctrl); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -756,13 +773,13 @@ static ssize_t s_exlevel_vinst_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); - /* clear all EXLEVEL_S bits (bit[18] is never implemented) */ - config->vinst_ctrl &= ~(BIT(16) | BIT(17) | BIT(19)); + raw_spin_lock(&drvdata->spinlock); + /* clear all EXLEVEL_S bits */ + config->vinst_ctrl &= ~TRCVICTLR_EXLEVEL_S_MASK; /* enable instruction tracing for corresponding exception level */ val &= drvdata->s_ex_level; - config->vinst_ctrl |= (val << 16); - spin_unlock(&drvdata->spinlock); + config->vinst_ctrl |= val << __bf_shf(TRCVICTLR_EXLEVEL_S_MASK); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(s_exlevel_vinst); @@ -776,7 +793,7 @@ static ssize_t ns_exlevel_vinst_show(struct device *dev, struct etmv4_config *config = &drvdata->config; /* EXLEVEL_NS, bits[23:20] */ - val = BMVAL(config->vinst_ctrl, 20, 23); + val = FIELD_GET(TRCVICTLR_EXLEVEL_NS_MASK, config->vinst_ctrl); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -791,13 +808,13 @@ static ssize_t ns_exlevel_vinst_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); - /* clear EXLEVEL_NS bits (bit[23] is never implemented */ - config->vinst_ctrl &= ~(BIT(20) | BIT(21) | BIT(22)); + raw_spin_lock(&drvdata->spinlock); + /* clear EXLEVEL_NS bits */ + config->vinst_ctrl &= ~TRCVICTLR_EXLEVEL_NS_MASK; /* enable instruction tracing for corresponding exception level */ val &= drvdata->ns_ex_level; - config->vinst_ctrl |= (val << 20); - spin_unlock(&drvdata->spinlock); + config->vinst_ctrl |= val << __bf_shf(TRCVICTLR_EXLEVEL_NS_MASK); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(ns_exlevel_vinst); @@ -831,9 +848,9 @@ static ssize_t addr_idx_store(struct device *dev, * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->addr_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_idx); @@ -847,15 +864,15 @@ static ssize_t addr_instdatatype_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; - val = BMVAL(config->addr_acc[idx], 0, 1); + val = FIELD_GET(TRCACATRn_TYPE_MASK, config->addr_acc[idx]); len = scnprintf(buf, PAGE_SIZE, "%s\n", - val == ETM_INSTR_ADDR ? "instr" : - (val == ETM_DATA_LOAD_ADDR ? "data_load" : - (val == ETM_DATA_STORE_ADDR ? "data_store" : + val == TRCACATRn_TYPE_ADDR ? "instr" : + (val == TRCACATRn_TYPE_DATA_LOAD_ADDR ? "data_load" : + (val == TRCACATRn_TYPE_DATA_STORE_ADDR ? "data_store" : "data_load_store"))); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return len; } @@ -873,13 +890,13 @@ static ssize_t addr_instdatatype_store(struct device *dev, if (sscanf(buf, "%s", str) != 1) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!strcmp(str, "instr")) /* TYPE, bits[1:0] */ - config->addr_acc[idx] &= ~(BIT(0) | BIT(1)); + config->addr_acc[idx] &= ~TRCACATRn_TYPE_MASK; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_instdatatype); @@ -894,14 +911,14 @@ static ssize_t addr_single_show(struct device *dev, struct etmv4_config *config = &drvdata->config; idx = config->addr_idx; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } val = (unsigned long)config->addr_val[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -917,17 +934,17 @@ static ssize_t addr_single_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_SINGLE)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } config->addr_val[idx] = (u64)val; config->addr_type[idx] = ETM_ADDR_TYPE_SINGLE; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_single); @@ -941,23 +958,23 @@ static ssize_t addr_range_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (idx % 2 != 0) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } if (!((config->addr_type[idx] == ETM_ADDR_TYPE_NONE && config->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) || (config->addr_type[idx] == ETM_ADDR_TYPE_RANGE && config->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } val1 = (unsigned long)config->addr_val[idx]; val2 = (unsigned long)config->addr_val[idx + 1]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx %#lx\n", val1, val2); } @@ -969,17 +986,21 @@ static ssize_t addr_range_store(struct device *dev, unsigned long val1, val2; struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; + int elements, exclude; + + elements = sscanf(buf, "%lx %lx %x", &val1, &val2, &exclude); - if (sscanf(buf, "%lx %lx", &val1, &val2) != 2) + /* exclude is optional, but need at least two parameter */ + if (elements < 2) return -EINVAL; /* lower address comparator cannot have a higher address value */ if (val1 > val2) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (idx % 2 != 0) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } @@ -987,7 +1008,7 @@ static ssize_t addr_range_store(struct device *dev, config->addr_type[idx + 1] == ETM_ADDR_TYPE_NONE) || (config->addr_type[idx] == ETM_ADDR_TYPE_RANGE && config->addr_type[idx + 1] == ETM_ADDR_TYPE_RANGE))) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } @@ -998,13 +1019,13 @@ static ssize_t addr_range_store(struct device *dev, /* * Program include or exclude control bits for vinst or vdata * whenever we change addr comparators to ETM_ADDR_TYPE_RANGE + * use supplied value, or default to bit set in 'mode' */ - if (config->mode & ETM_MODE_EXCLUDE) - etm4_set_mode_exclude(drvdata, true); - else - etm4_set_mode_exclude(drvdata, false); + if (elements != 3) + exclude = config->mode & ETM_MODE_EXCLUDE; + etm4_set_mode_exclude(drvdata, exclude ? true : false); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_range); @@ -1018,17 +1039,17 @@ static ssize_t addr_start_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_START)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } val = (unsigned long)config->addr_val[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1044,24 +1065,22 @@ static ssize_t addr_start_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!drvdata->nr_addr_cmp) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EINVAL; } if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_START)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } config->addr_val[idx] = (u64)val; config->addr_type[idx] = ETM_ADDR_TYPE_START; config->vissctlr |= BIT(idx); - /* SSSTATUS, bit[9] - turn on start/stop logic */ - config->vinst_ctrl |= BIT(9); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_start); @@ -1075,17 +1094,17 @@ static ssize_t addr_stop_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_STOP)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } val = (unsigned long)config->addr_val[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1101,24 +1120,22 @@ static ssize_t addr_stop_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!drvdata->nr_addr_cmp) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EINVAL; } if (!(config->addr_type[idx] == ETM_ADDR_TYPE_NONE || config->addr_type[idx] == ETM_ADDR_TYPE_STOP)) { - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return -EPERM; } config->addr_val[idx] = (u64)val; config->addr_type[idx] = ETM_ADDR_TYPE_STOP; config->vissctlr |= BIT(idx + 16); - /* SSSTATUS, bit[9] - turn on start/stop logic */ - config->vinst_ctrl |= BIT(9); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_stop); @@ -1132,14 +1149,14 @@ static ssize_t addr_ctxtype_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; /* CONTEXTTYPE, bits[3:2] */ - val = BMVAL(config->addr_acc[idx], 2, 3); + val = FIELD_GET(TRCACATRn_CONTEXTTYPE_MASK, config->addr_acc[idx]); len = scnprintf(buf, PAGE_SIZE, "%s\n", val == ETM_CTX_NONE ? "none" : (val == ETM_CTX_CTXID ? "ctxid" : (val == ETM_CTX_VMID ? "vmid" : "all"))); - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return len; } @@ -1157,22 +1174,22 @@ static ssize_t addr_ctxtype_store(struct device *dev, if (sscanf(buf, "%s", str) != 1) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; if (!strcmp(str, "none")) /* start by clearing context type bits */ - config->addr_acc[idx] &= ~(BIT(2) | BIT(3)); + config->addr_acc[idx] &= ~TRCACATRn_CONTEXTTYPE_MASK; else if (!strcmp(str, "ctxid")) { /* 0b01 The trace unit performs a Context ID */ if (drvdata->numcidc) { - config->addr_acc[idx] |= BIT(2); - config->addr_acc[idx] &= ~BIT(3); + config->addr_acc[idx] |= TRCACATRn_CONTEXTTYPE_CTXID; + config->addr_acc[idx] &= ~TRCACATRn_CONTEXTTYPE_VMID; } } else if (!strcmp(str, "vmid")) { /* 0b10 The trace unit performs a VMID */ if (drvdata->numvmidc) { - config->addr_acc[idx] &= ~BIT(2); - config->addr_acc[idx] |= BIT(3); + config->addr_acc[idx] &= ~TRCACATRn_CONTEXTTYPE_CTXID; + config->addr_acc[idx] |= TRCACATRn_CONTEXTTYPE_VMID; } } else if (!strcmp(str, "all")) { /* @@ -1180,11 +1197,11 @@ static ssize_t addr_ctxtype_store(struct device *dev, * comparison and a VMID */ if (drvdata->numcidc) - config->addr_acc[idx] |= BIT(2); + config->addr_acc[idx] |= TRCACATRn_CONTEXTTYPE_CTXID; if (drvdata->numvmidc) - config->addr_acc[idx] |= BIT(3); + config->addr_acc[idx] |= TRCACATRn_CONTEXTTYPE_VMID; } - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_ctxtype); @@ -1198,11 +1215,11 @@ static ssize_t addr_context_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; /* context ID comparator bits[6:4] */ - val = BMVAL(config->addr_acc[idx], 4, 6); - spin_unlock(&drvdata->spinlock); + val = FIELD_GET(TRCACATRn_CONTEXT_MASK, config->addr_acc[idx]); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1223,16 +1240,141 @@ static ssize_t addr_context_store(struct device *dev, drvdata->numcidc : drvdata->numvmidc)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->addr_idx; /* clear context ID comparator bits[6:4] */ - config->addr_acc[idx] &= ~(BIT(4) | BIT(5) | BIT(6)); - config->addr_acc[idx] |= (val << 4); - spin_unlock(&drvdata->spinlock); + config->addr_acc[idx] &= ~TRCACATRn_CONTEXT_MASK; + config->addr_acc[idx] |= val << __bf_shf(TRCACATRn_CONTEXT_MASK); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(addr_context); +static ssize_t addr_exlevel_s_ns_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u8 idx; + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + idx = config->addr_idx; + val = FIELD_GET(TRCACATRn_EXLEVEL_MASK, config->addr_acc[idx]); + raw_spin_unlock(&drvdata->spinlock); + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} + +static ssize_t addr_exlevel_s_ns_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (kstrtoul(buf, 0, &val)) + return -EINVAL; + + if (val & ~(TRCACATRn_EXLEVEL_MASK >> __bf_shf(TRCACATRn_EXLEVEL_MASK))) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + idx = config->addr_idx; + /* clear Exlevel_ns & Exlevel_s bits[14:12, 11:8], bit[15] is res0 */ + config->addr_acc[idx] &= ~TRCACATRn_EXLEVEL_MASK; + config->addr_acc[idx] |= val << __bf_shf(TRCACATRn_EXLEVEL_MASK); + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(addr_exlevel_s_ns); + +static const char * const addr_type_names[] = { + "unused", + "single", + "range", + "start", + "stop" +}; + +static ssize_t addr_cmp_view_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u8 idx, addr_type; + unsigned long addr_v, addr_v2, addr_ctrl; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + int size = 0; + bool exclude = false; + + raw_spin_lock(&drvdata->spinlock); + idx = config->addr_idx; + addr_v = config->addr_val[idx]; + addr_ctrl = config->addr_acc[idx]; + addr_type = config->addr_type[idx]; + if (addr_type == ETM_ADDR_TYPE_RANGE) { + if (idx & 0x1) { + idx -= 1; + addr_v2 = addr_v; + addr_v = config->addr_val[idx]; + } else { + addr_v2 = config->addr_val[idx + 1]; + } + exclude = config->viiectlr & BIT(idx / 2 + 16); + } + raw_spin_unlock(&drvdata->spinlock); + if (addr_type) { + size = scnprintf(buf, PAGE_SIZE, "addr_cmp[%i] %s %#lx", idx, + addr_type_names[addr_type], addr_v); + if (addr_type == ETM_ADDR_TYPE_RANGE) { + size += scnprintf(buf + size, PAGE_SIZE - size, + " %#lx %s", addr_v2, + exclude ? "exclude" : "include"); + } + size += scnprintf(buf + size, PAGE_SIZE - size, + " ctrl(%#lx)\n", addr_ctrl); + } else { + size = scnprintf(buf, PAGE_SIZE, "addr_cmp[%i] unused\n", idx); + } + return size; +} +static DEVICE_ATTR_RO(addr_cmp_view); + +static ssize_t vinst_pe_cmp_start_stop_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (!drvdata->nr_pe_cmp) + return -EINVAL; + val = config->vipcssctlr; + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} +static ssize_t vinst_pe_cmp_start_stop_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (kstrtoul(buf, 16, &val)) + return -EINVAL; + if (!drvdata->nr_pe_cmp) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + config->vipcssctlr = val; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(vinst_pe_cmp_start_stop); + static ssize_t seq_idx_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1262,9 +1404,9 @@ static ssize_t seq_idx_store(struct device *dev, * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->seq_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(seq_idx); @@ -1308,10 +1450,10 @@ static ssize_t seq_event_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->seq_idx; val = config->seq_ctrl[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1327,11 +1469,11 @@ static ssize_t seq_event_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->seq_idx; - /* RST, bits[7:0] */ - config->seq_ctrl[idx] = val & 0xFF; - spin_unlock(&drvdata->spinlock); + /* Seq control has two masks B[15:8] F[7:0] */ + config->seq_ctrl[idx] = val & 0xFFFF; + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(seq_event); @@ -1395,9 +1537,9 @@ static ssize_t cntr_idx_store(struct device *dev, * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->cntr_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(cntr_idx); @@ -1411,10 +1553,10 @@ static ssize_t cntrldvr_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; val = config->cntrldvr[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1432,10 +1574,10 @@ static ssize_t cntrldvr_store(struct device *dev, if (val > ETM_CNTR_MAX_VAL) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; config->cntrldvr[idx] = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(cntrldvr); @@ -1449,10 +1591,10 @@ static ssize_t cntr_val_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; val = config->cntr_val[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1470,10 +1612,10 @@ static ssize_t cntr_val_store(struct device *dev, if (val > ETM_CNTR_MAX_VAL) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; config->cntr_val[idx] = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(cntr_val); @@ -1487,10 +1629,10 @@ static ssize_t cntr_ctrl_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; val = config->cntr_ctrl[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1506,10 +1648,10 @@ static ssize_t cntr_ctrl_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->cntr_idx; config->cntr_ctrl[idx] = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(cntr_ctrl); @@ -1536,17 +1678,20 @@ static ssize_t res_idx_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - /* Resource selector pair 0 is always implemented and reserved */ - if ((val == 0) || (val >= drvdata->nr_resource)) + /* + * Resource selector pair 0 is always implemented and reserved, + * namely an idx with 0 and 1 is illegal. + */ + if ((val < 2) || (val >= 2 * drvdata->nr_resource)) return -EINVAL; /* * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->res_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(res_idx); @@ -1560,10 +1705,10 @@ static ssize_t res_ctrl_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->res_idx; val = config->res_ctrl[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1579,18 +1724,138 @@ static ssize_t res_ctrl_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->res_idx; /* For odd idx pair inversal bit is RES0 */ if (idx % 2 != 0) /* PAIRINV, bit[21] */ - val &= ~BIT(21); - config->res_ctrl[idx] = val; - spin_unlock(&drvdata->spinlock); + val &= ~TRCRSCTLRn_PAIRINV; + config->res_ctrl[idx] = val & (TRCRSCTLRn_PAIRINV | + TRCRSCTLRn_INV | + TRCRSCTLRn_GROUP_MASK | + TRCRSCTLRn_SELECT_MASK); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(res_ctrl); +static ssize_t sshot_idx_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + val = config->ss_idx; + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} + +static ssize_t sshot_idx_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (kstrtoul(buf, 16, &val)) + return -EINVAL; + if (val >= drvdata->nr_ss_cmp) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + config->ss_idx = val; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(sshot_idx); + +static ssize_t sshot_ctrl_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + val = config->ss_ctrl[config->ss_idx]; + raw_spin_unlock(&drvdata->spinlock); + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} + +static ssize_t sshot_ctrl_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (kstrtoul(buf, 16, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + idx = config->ss_idx; + config->ss_ctrl[idx] = FIELD_PREP(TRCSSCCRn_SAC_ARC_RST_MASK, val); + /* must clear bit 31 in related status register on programming */ + config->ss_status[idx] &= ~TRCSSCSRn_STATUS; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(sshot_ctrl); + +static ssize_t sshot_status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + val = config->ss_status[config->ss_idx]; + raw_spin_unlock(&drvdata->spinlock); + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} +static DEVICE_ATTR_RO(sshot_status); + +static ssize_t sshot_pe_ctrl_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + raw_spin_lock(&drvdata->spinlock); + val = config->ss_pe_cmp[config->ss_idx]; + raw_spin_unlock(&drvdata->spinlock); + return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); +} + +static ssize_t sshot_pe_ctrl_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 idx; + unsigned long val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etmv4_config *config = &drvdata->config; + + if (kstrtoul(buf, 16, &val)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); + idx = config->ss_idx; + config->ss_pe_cmp[idx] = FIELD_PREP(TRCSSPCICRn_PC_MASK, val); + /* must clear bit 31 in related status register on programming */ + config->ss_status[idx] &= ~TRCSSCSRn_STATUS; + raw_spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(sshot_pe_ctrl); + static ssize_t ctxid_idx_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -1620,9 +1885,9 @@ static ssize_t ctxid_idx_store(struct device *dev, * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->ctxid_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(ctxid_idx); @@ -1643,10 +1908,10 @@ static ssize_t ctxid_pid_show(struct device *dev, if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->ctxid_idx; val = (unsigned long)config->ctxid_pid[idx]; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1681,10 +1946,10 @@ static ssize_t ctxid_pid_store(struct device *dev, if (kstrtoul(buf, 16, &pid)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); idx = config->ctxid_idx; config->ctxid_pid[idx] = (u64)pid; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(ctxid_pid); @@ -1704,10 +1969,10 @@ static ssize_t ctxid_masks_show(struct device *dev, if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); val1 = config->ctxid_mask0; val2 = config->ctxid_mask1; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx %#lx\n", val1, val2); } @@ -1719,6 +1984,7 @@ static ssize_t ctxid_masks_store(struct device *dev, unsigned long val1, val2, mask; struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; + int nr_inputs; /* * Don't use contextID tracing if coming from a PID namespace. See @@ -1734,10 +2000,12 @@ static ssize_t ctxid_masks_store(struct device *dev, */ if (!drvdata->ctxid_size || !drvdata->numcidc) return -EINVAL; - if (sscanf(buf, "%lx %lx", &val1, &val2) != 2) + /* one mask if <= 4 comparators, two for up to 8 */ + nr_inputs = sscanf(buf, "%lx %lx", &val1, &val2); + if ((drvdata->numcidc > 4) && (nr_inputs != 2)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); /* * each byte[0..3] controls mask value applied to ctxid * comparator[0..3] @@ -1809,7 +2077,7 @@ static ssize_t ctxid_masks_store(struct device *dev, mask >>= 0x8; } - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(ctxid_masks); @@ -1843,9 +2111,9 @@ static ssize_t vmid_idx_store(struct device *dev, * Use spinlock to ensure index doesn't change while it gets * dereferenced multiple times within a spinlock block elsewhere. */ - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->vmid_idx = val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(vmid_idx); @@ -1858,7 +2126,16 @@ static ssize_t vmid_val_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; + /* + * Don't use virtual contextID tracing if coming from a PID namespace. + * See comment in ctxid_pid_store(). + */ + if (!task_is_in_init_pid_ns(current)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); val = (unsigned long)config->vmid_val[config->vmid_idx]; + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1871,6 +2148,13 @@ static ssize_t vmid_val_store(struct device *dev, struct etmv4_config *config = &drvdata->config; /* + * Don't use virtual contextID tracing if coming from a PID namespace. + * See comment in ctxid_pid_store(). + */ + if (!task_is_in_init_pid_ns(current)) + return -EINVAL; + + /* * only implemented when vmid tracing is enabled, i.e. at least one * vmid comparator is implemented and at least 8 bit vmid size */ @@ -1879,9 +2163,9 @@ static ssize_t vmid_val_store(struct device *dev, if (kstrtoul(buf, 16, &val)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); config->vmid_val[config->vmid_idx] = (u64)val; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(vmid_val); @@ -1893,10 +2177,17 @@ static ssize_t vmid_masks_show(struct device *dev, struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; - spin_lock(&drvdata->spinlock); + /* + * Don't use virtual contextID tracing if coming from a PID namespace. + * See comment in ctxid_pid_store(). + */ + if (!task_is_in_init_pid_ns(current)) + return -EINVAL; + + raw_spin_lock(&drvdata->spinlock); val1 = config->vmid_mask0; val2 = config->vmid_mask1; - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx %#lx\n", val1, val2); } @@ -1908,6 +2199,14 @@ static ssize_t vmid_masks_store(struct device *dev, unsigned long val1, val2, mask; struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); struct etmv4_config *config = &drvdata->config; + int nr_inputs; + + /* + * Don't use virtual contextID tracing if coming from a PID namespace. + * See comment in ctxid_pid_store(). + */ + if (!task_is_in_init_pid_ns(current)) + return -EINVAL; /* * only implemented when vmid tracing is enabled, i.e. at least one @@ -1915,10 +2214,12 @@ static ssize_t vmid_masks_store(struct device *dev, */ if (!drvdata->vmid_size || !drvdata->numvmidc) return -EINVAL; - if (sscanf(buf, "%lx %lx", &val1, &val2) != 2) + /* one mask if <= 4 comparators, two for up to 8 */ + nr_inputs = sscanf(buf, "%lx %lx", &val1, &val2); + if ((drvdata->numvmidc > 4) && (nr_inputs != 2)) return -EINVAL; - spin_lock(&drvdata->spinlock); + raw_spin_lock(&drvdata->spinlock); /* * each byte[0..3] controls mask value applied to vmid @@ -1991,7 +2292,7 @@ static ssize_t vmid_masks_store(struct device *dev, else mask >>= 0x8; } - spin_unlock(&drvdata->spinlock); + raw_spin_unlock(&drvdata->spinlock); return size; } static DEVICE_ATTR_RW(vmid_masks); @@ -2008,6 +2309,34 @@ static ssize_t cpu_show(struct device *dev, } static DEVICE_ATTR_RO(cpu); +static ssize_t ts_source_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int val; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (!drvdata->trfcr) { + val = -1; + goto out; + } + + val = FIELD_GET(TRFCR_EL1_TS_MASK, drvdata->trfcr); + switch (val) { + case TRFCR_EL1_TS_VIRTUAL: + case TRFCR_EL1_TS_GUEST_PHYSICAL: + case TRFCR_EL1_TS_PHYSICAL: + break; + default: + val = -1; + break; + } + +out: + return sysfs_emit(buf, "%d\n", val); +} +static DEVICE_ATTR_RO(ts_source); + static struct attribute *coresight_etmv4_attrs[] = { &dev_attr_nr_pe_cmp.attr, &dev_attr_nr_addr_cmp.attr, @@ -2038,6 +2367,13 @@ static struct attribute *coresight_etmv4_attrs[] = { &dev_attr_addr_stop.attr, &dev_attr_addr_ctxtype.attr, &dev_attr_addr_context.attr, + &dev_attr_addr_exlevel_s_ns.attr, + &dev_attr_addr_cmp_view.attr, + &dev_attr_vinst_pe_cmp_start_stop.attr, + &dev_attr_sshot_idx.attr, + &dev_attr_sshot_ctrl.attr, + &dev_attr_sshot_pe_ctrl.attr, + &dev_attr_sshot_status.attr, &dev_attr_seq_idx.attr, &dev_attr_seq_state.attr, &dev_attr_seq_event.attr, @@ -2055,11 +2391,31 @@ static struct attribute *coresight_etmv4_attrs[] = { &dev_attr_vmid_val.attr, &dev_attr_vmid_masks.attr, &dev_attr_cpu.attr, + &dev_attr_ts_source.attr, NULL, }; +/* + * Trace ID allocated dynamically on enable - but also allocate on read + * in case sysfs or perf read before enable to ensure consistent metadata + * information for trace decode + */ +static ssize_t trctraceid_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + int trace_id = coresight_etm_get_trace_id(drvdata->csdev, CS_MODE_SYSFS, NULL); + + if (trace_id < 0) + return trace_id; + + return sysfs_emit(buf, "0x%x\n", trace_id); +} + struct etmv4_reg { - void __iomem *addr; + struct coresight_device *csdev; + u32 offset; u32 data; }; @@ -2067,15 +2423,16 @@ static void do_smp_cross_read(void *data) { struct etmv4_reg *reg = data; - reg->data = readl_relaxed(reg->addr); + reg->data = etm4x_relaxed_read32(®->csdev->access, reg->offset); } -static u32 etmv4_cross_read(const struct device *dev, u32 offset) +static u32 etmv4_cross_read(const struct etmv4_drvdata *drvdata, u32 offset) { - struct etmv4_drvdata *drvdata = dev_get_drvdata(dev); struct etmv4_reg reg; - reg.addr = drvdata->base + offset; + reg.offset = offset; + reg.csdev = drvdata->csdev; + /* * smp cross call ensures the CPU will be powered up before * accessing the ETMv4 trace core registers @@ -2084,72 +2441,143 @@ static u32 etmv4_cross_read(const struct device *dev, u32 offset) return reg.data; } -#define coresight_etm4x_reg(name, offset) \ - coresight_simple_reg32(struct etmv4_drvdata, name, offset) +static u32 coresight_etm4x_attr_to_offset(struct device_attribute *attr) +{ + struct dev_ext_attribute *eattr; -#define coresight_etm4x_cross_read(name, offset) \ - coresight_simple_func(struct etmv4_drvdata, etmv4_cross_read, \ - name, offset) + eattr = container_of(attr, struct dev_ext_attribute, attr); + return (u32)(unsigned long)eattr->var; +} -coresight_etm4x_reg(trcpdcr, TRCPDCR); -coresight_etm4x_reg(trcpdsr, TRCPDSR); -coresight_etm4x_reg(trclsr, TRCLSR); -coresight_etm4x_reg(trcauthstatus, TRCAUTHSTATUS); -coresight_etm4x_reg(trcdevid, TRCDEVID); -coresight_etm4x_reg(trcdevtype, TRCDEVTYPE); -coresight_etm4x_reg(trcpidr0, TRCPIDR0); -coresight_etm4x_reg(trcpidr1, TRCPIDR1); -coresight_etm4x_reg(trcpidr2, TRCPIDR2); -coresight_etm4x_reg(trcpidr3, TRCPIDR3); -coresight_etm4x_cross_read(trcoslsr, TRCOSLSR); -coresight_etm4x_cross_read(trcconfig, TRCCONFIGR); -coresight_etm4x_cross_read(trctraceid, TRCTRACEIDR); +static ssize_t coresight_etm4x_reg_show(struct device *dev, + struct device_attribute *d_attr, + char *buf) +{ + u32 val, offset; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + + offset = coresight_etm4x_attr_to_offset(d_attr); + + pm_runtime_get_sync(dev->parent); + val = etmv4_cross_read(drvdata, offset); + pm_runtime_put_sync(dev->parent); + + return scnprintf(buf, PAGE_SIZE, "0x%x\n", val); +} + +static bool +etm4x_register_implemented(struct etmv4_drvdata *drvdata, u32 offset) +{ + switch (offset) { + ETM_COMMON_SYSREG_LIST_CASES + /* + * Common registers to ETE & ETM4x accessible via system + * instructions are always implemented. + */ + return true; + + ETM4x_ONLY_SYSREG_LIST_CASES + /* + * We only support etm4x and ete. So if the device is not + * ETE, it must be ETMv4x. + */ + return !etm4x_is_ete(drvdata); + + ETM4x_MMAP_LIST_CASES + /* + * Registers accessible only via memory-mapped registers + * must not be accessed via system instructions. + * We cannot access the drvdata->csdev here, as this + * function is called during the device creation, via + * coresight_register() and the csdev is not initialized + * until that is done. So rely on the drvdata->base to + * detect if we have a memory mapped access. + * Also ETE doesn't implement memory mapped access, thus + * it is sufficient to check that we are using mmio. + */ + return !!drvdata->base; + + ETE_ONLY_SYSREG_LIST_CASES + return etm4x_is_ete(drvdata); + } + + return false; +} + +/* + * Hide the ETM4x registers that may not be available on the + * hardware. + * There are certain management registers unavailable via system + * instructions. Make those sysfs attributes hidden on such + * systems. + */ +static umode_t +coresight_etm4x_attr_reg_implemented(struct kobject *kobj, + struct attribute *attr, int unused) +{ + struct device *dev = kobj_to_dev(kobj); + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct device_attribute *d_attr; + u32 offset; + + d_attr = container_of(attr, struct device_attribute, attr); + offset = coresight_etm4x_attr_to_offset(d_attr); + + if (etm4x_register_implemented(drvdata, offset)) + return attr->mode; + return 0; +} + +/* + * Macro to set an RO ext attribute with offset and show function. + * Offset is used in mgmt group to ensure only correct registers for + * the ETM / ETE variant are visible. + */ +#define coresight_etm4x_reg_showfn(name, offset, showfn) ( \ + &((struct dev_ext_attribute[]) { \ + { \ + __ATTR(name, 0444, showfn, NULL), \ + (void *)(unsigned long)offset \ + } \ + })[0].attr.attr \ + ) + +/* macro using the default coresight_etm4x_reg_show function */ +#define coresight_etm4x_reg(name, offset) \ + coresight_etm4x_reg_showfn(name, offset, coresight_etm4x_reg_show) static struct attribute *coresight_etmv4_mgmt_attrs[] = { - &dev_attr_trcoslsr.attr, - &dev_attr_trcpdcr.attr, - &dev_attr_trcpdsr.attr, - &dev_attr_trclsr.attr, - &dev_attr_trcconfig.attr, - &dev_attr_trctraceid.attr, - &dev_attr_trcauthstatus.attr, - &dev_attr_trcdevid.attr, - &dev_attr_trcdevtype.attr, - &dev_attr_trcpidr0.attr, - &dev_attr_trcpidr1.attr, - &dev_attr_trcpidr2.attr, - &dev_attr_trcpidr3.attr, + coresight_etm4x_reg(trcpdcr, TRCPDCR), + coresight_etm4x_reg(trcpdsr, TRCPDSR), + coresight_etm4x_reg(trclsr, TRCLSR), + coresight_etm4x_reg(trcauthstatus, TRCAUTHSTATUS), + coresight_etm4x_reg(trcdevid, TRCDEVID), + coresight_etm4x_reg(trcdevtype, TRCDEVTYPE), + coresight_etm4x_reg(trcpidr0, TRCPIDR0), + coresight_etm4x_reg(trcpidr1, TRCPIDR1), + coresight_etm4x_reg(trcpidr2, TRCPIDR2), + coresight_etm4x_reg(trcpidr3, TRCPIDR3), + coresight_etm4x_reg(trcoslsr, TRCOSLSR), + coresight_etm4x_reg(trcconfig, TRCCONFIGR), + coresight_etm4x_reg_showfn(trctraceid, TRCTRACEIDR, trctraceid_show), + coresight_etm4x_reg(trcdevarch, TRCDEVARCH), NULL, }; -coresight_etm4x_cross_read(trcidr0, TRCIDR0); -coresight_etm4x_cross_read(trcidr1, TRCIDR1); -coresight_etm4x_cross_read(trcidr2, TRCIDR2); -coresight_etm4x_cross_read(trcidr3, TRCIDR3); -coresight_etm4x_cross_read(trcidr4, TRCIDR4); -coresight_etm4x_cross_read(trcidr5, TRCIDR5); -/* trcidr[6,7] are reserved */ -coresight_etm4x_cross_read(trcidr8, TRCIDR8); -coresight_etm4x_cross_read(trcidr9, TRCIDR9); -coresight_etm4x_cross_read(trcidr10, TRCIDR10); -coresight_etm4x_cross_read(trcidr11, TRCIDR11); -coresight_etm4x_cross_read(trcidr12, TRCIDR12); -coresight_etm4x_cross_read(trcidr13, TRCIDR13); - static struct attribute *coresight_etmv4_trcidr_attrs[] = { - &dev_attr_trcidr0.attr, - &dev_attr_trcidr1.attr, - &dev_attr_trcidr2.attr, - &dev_attr_trcidr3.attr, - &dev_attr_trcidr4.attr, - &dev_attr_trcidr5.attr, + coresight_etm4x_reg(trcidr0, TRCIDR0), + coresight_etm4x_reg(trcidr1, TRCIDR1), + coresight_etm4x_reg(trcidr2, TRCIDR2), + coresight_etm4x_reg(trcidr3, TRCIDR3), + coresight_etm4x_reg(trcidr4, TRCIDR4), + coresight_etm4x_reg(trcidr5, TRCIDR5), /* trcidr[6,7] are reserved */ - &dev_attr_trcidr8.attr, - &dev_attr_trcidr9.attr, - &dev_attr_trcidr10.attr, - &dev_attr_trcidr11.attr, - &dev_attr_trcidr12.attr, - &dev_attr_trcidr13.attr, + coresight_etm4x_reg(trcidr8, TRCIDR8), + coresight_etm4x_reg(trcidr9, TRCIDR9), + coresight_etm4x_reg(trcidr10, TRCIDR10), + coresight_etm4x_reg(trcidr11, TRCIDR11), + coresight_etm4x_reg(trcidr12, TRCIDR12), + coresight_etm4x_reg(trcidr13, TRCIDR13), NULL, }; @@ -2158,6 +2586,7 @@ static const struct attribute_group coresight_etmv4_group = { }; static const struct attribute_group coresight_etmv4_mgmt_group = { + .is_visible = coresight_etm4x_attr_reg_implemented, .attrs = coresight_etmv4_mgmt_attrs, .name = "mgmt", }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c deleted file mode 100644 index 53e2fb6e86f6..000000000000 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ /dev/null @@ -1,1093 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2014, The Linux Foundation. All rights reserved. - */ - -#include <linux/kernel.h> -#include <linux/moduleparam.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/device.h> -#include <linux/io.h> -#include <linux/err.h> -#include <linux/fs.h> -#include <linux/slab.h> -#include <linux/delay.h> -#include <linux/smp.h> -#include <linux/sysfs.h> -#include <linux/stat.h> -#include <linux/clk.h> -#include <linux/cpu.h> -#include <linux/coresight.h> -#include <linux/coresight-pmu.h> -#include <linux/pm_wakeup.h> -#include <linux/amba/bus.h> -#include <linux/seq_file.h> -#include <linux/uaccess.h> -#include <linux/perf_event.h> -#include <linux/pm_runtime.h> -#include <asm/sections.h> -#include <asm/local.h> -#include <asm/virt.h> - -#include "coresight-etm4x.h" -#include "coresight-etm-perf.h" - -static int boot_enable; -module_param_named(boot_enable, boot_enable, int, S_IRUGO); - -/* The number of ETMv4 currently registered */ -static int etm4_count; -static struct etmv4_drvdata *etmdrvdata[NR_CPUS]; -static void etm4_set_default_config(struct etmv4_config *config); -static int etm4_set_event_filters(struct etmv4_drvdata *drvdata, - struct perf_event *event); - -static enum cpuhp_state hp_online; - -static void etm4_os_unlock(struct etmv4_drvdata *drvdata) -{ - /* Writing any value to ETMOSLAR unlocks the trace registers */ - writel_relaxed(0x0, drvdata->base + TRCOSLAR); - drvdata->os_unlock = true; - isb(); -} - -static bool etm4_arch_supported(u8 arch) -{ - switch (arch) { - case ETM_ARCH_V4: - break; - default: - return false; - } - return true; -} - -static int etm4_cpu_id(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->cpu; -} - -static int etm4_trace_id(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->trcid; -} - -struct etm4_enable_arg { - struct etmv4_drvdata *drvdata; - int rc; -}; - -static int etm4_enable_hw(struct etmv4_drvdata *drvdata) -{ - int i, rc; - struct etmv4_config *config = &drvdata->config; - - CS_UNLOCK(drvdata->base); - - etm4_os_unlock(drvdata); - - rc = coresight_claim_device_unlocked(drvdata->base); - if (rc) - goto done; - - /* Disable the trace unit before programming trace registers */ - writel_relaxed(0, drvdata->base + TRCPRGCTLR); - - /* wait for TRCSTATR.IDLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) - dev_err(drvdata->dev, - "timeout while waiting for Idle Trace Status\n"); - - writel_relaxed(config->pe_sel, drvdata->base + TRCPROCSELR); - writel_relaxed(config->cfg, drvdata->base + TRCCONFIGR); - /* nothing specific implemented */ - writel_relaxed(0x0, drvdata->base + TRCAUXCTLR); - writel_relaxed(config->eventctrl0, drvdata->base + TRCEVENTCTL0R); - writel_relaxed(config->eventctrl1, drvdata->base + TRCEVENTCTL1R); - writel_relaxed(config->stall_ctrl, drvdata->base + TRCSTALLCTLR); - writel_relaxed(config->ts_ctrl, drvdata->base + TRCTSCTLR); - writel_relaxed(config->syncfreq, drvdata->base + TRCSYNCPR); - writel_relaxed(config->ccctlr, drvdata->base + TRCCCCTLR); - writel_relaxed(config->bb_ctrl, drvdata->base + TRCBBCTLR); - writel_relaxed(drvdata->trcid, drvdata->base + TRCTRACEIDR); - writel_relaxed(config->vinst_ctrl, drvdata->base + TRCVICTLR); - writel_relaxed(config->viiectlr, drvdata->base + TRCVIIECTLR); - writel_relaxed(config->vissctlr, - drvdata->base + TRCVISSCTLR); - writel_relaxed(config->vipcssctlr, - drvdata->base + TRCVIPCSSCTLR); - for (i = 0; i < drvdata->nrseqstate - 1; i++) - writel_relaxed(config->seq_ctrl[i], - drvdata->base + TRCSEQEVRn(i)); - writel_relaxed(config->seq_rst, drvdata->base + TRCSEQRSTEVR); - writel_relaxed(config->seq_state, drvdata->base + TRCSEQSTR); - writel_relaxed(config->ext_inp, drvdata->base + TRCEXTINSELR); - for (i = 0; i < drvdata->nr_cntr; i++) { - writel_relaxed(config->cntrldvr[i], - drvdata->base + TRCCNTRLDVRn(i)); - writel_relaxed(config->cntr_ctrl[i], - drvdata->base + TRCCNTCTLRn(i)); - writel_relaxed(config->cntr_val[i], - drvdata->base + TRCCNTVRn(i)); - } - - /* Resource selector pair 0 is always implemented and reserved */ - for (i = 0; i < drvdata->nr_resource * 2; i++) - writel_relaxed(config->res_ctrl[i], - drvdata->base + TRCRSCTLRn(i)); - - for (i = 0; i < drvdata->nr_ss_cmp; i++) { - writel_relaxed(config->ss_ctrl[i], - drvdata->base + TRCSSCCRn(i)); - writel_relaxed(config->ss_status[i], - drvdata->base + TRCSSCSRn(i)); - writel_relaxed(config->ss_pe_cmp[i], - drvdata->base + TRCSSPCICRn(i)); - } - for (i = 0; i < drvdata->nr_addr_cmp; i++) { - writeq_relaxed(config->addr_val[i], - drvdata->base + TRCACVRn(i)); - writeq_relaxed(config->addr_acc[i], - drvdata->base + TRCACATRn(i)); - } - for (i = 0; i < drvdata->numcidc; i++) - writeq_relaxed(config->ctxid_pid[i], - drvdata->base + TRCCIDCVRn(i)); - writel_relaxed(config->ctxid_mask0, drvdata->base + TRCCIDCCTLR0); - writel_relaxed(config->ctxid_mask1, drvdata->base + TRCCIDCCTLR1); - - for (i = 0; i < drvdata->numvmidc; i++) - writeq_relaxed(config->vmid_val[i], - drvdata->base + TRCVMIDCVRn(i)); - writel_relaxed(config->vmid_mask0, drvdata->base + TRCVMIDCCTLR0); - writel_relaxed(config->vmid_mask1, drvdata->base + TRCVMIDCCTLR1); - - /* - * Request to keep the trace unit powered and also - * emulation of powerdown - */ - writel_relaxed(readl_relaxed(drvdata->base + TRCPDCR) | TRCPDCR_PU, - drvdata->base + TRCPDCR); - - /* Enable the trace unit */ - writel_relaxed(1, drvdata->base + TRCPRGCTLR); - - /* wait for TRCSTATR.IDLE to go back down to '0' */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 0)) - dev_err(drvdata->dev, - "timeout while waiting for Idle Trace Status\n"); - -done: - CS_LOCK(drvdata->base); - - dev_dbg(drvdata->dev, "cpu: %d enable smp call done: %d\n", - drvdata->cpu, rc); - return rc; -} - -static void etm4_enable_hw_smp_call(void *info) -{ - struct etm4_enable_arg *arg = info; - - if (WARN_ON(!arg)) - return; - arg->rc = etm4_enable_hw(arg->drvdata); -} - -static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, - struct perf_event *event) -{ - int ret = 0; - struct etmv4_config *config = &drvdata->config; - struct perf_event_attr *attr = &event->attr; - - if (!attr) { - ret = -EINVAL; - goto out; - } - - /* Clear configuration from previous run */ - memset(config, 0, sizeof(struct etmv4_config)); - - if (attr->exclude_kernel) - config->mode = ETM_MODE_EXCL_KERN; - - if (attr->exclude_user) - config->mode = ETM_MODE_EXCL_USER; - - /* Always start from the default config */ - etm4_set_default_config(config); - - /* Configure filters specified on the perf cmd line, if any. */ - ret = etm4_set_event_filters(drvdata, event); - if (ret) - goto out; - - /* Go from generic option to ETMv4 specifics */ - if (attr->config & BIT(ETM_OPT_CYCACC)) { - config->cfg |= BIT(4); - /* TRM: Must program this for cycacc to work */ - config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT; - } - if (attr->config & BIT(ETM_OPT_TS)) - /* bit[11], Global timestamp tracing bit */ - config->cfg |= BIT(11); - /* return stack - enable if selected and supported */ - if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack) - /* bit[12], Return stack enable bit */ - config->cfg |= BIT(12); - -out: - return ret; -} - -static int etm4_enable_perf(struct coresight_device *csdev, - struct perf_event *event) -{ - int ret = 0; - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) { - ret = -EINVAL; - goto out; - } - - /* Configure the tracer based on the session's specifics */ - ret = etm4_parse_event_config(drvdata, event); - if (ret) - goto out; - /* And enable it */ - ret = etm4_enable_hw(drvdata); - -out: - return ret; -} - -static int etm4_enable_sysfs(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - struct etm4_enable_arg arg = { 0 }; - int ret; - - spin_lock(&drvdata->spinlock); - - /* - * Executing etm4_enable_hw on the cpu whose ETM is being enabled - * ensures that register writes occur when cpu is powered. - */ - arg.drvdata = drvdata; - ret = smp_call_function_single(drvdata->cpu, - etm4_enable_hw_smp_call, &arg, 1); - if (!ret) - ret = arg.rc; - if (!ret) - drvdata->sticky_enable = true; - spin_unlock(&drvdata->spinlock); - - if (!ret) - dev_dbg(drvdata->dev, "ETM tracing enabled\n"); - return ret; -} - -static int etm4_enable(struct coresight_device *csdev, - struct perf_event *event, u32 mode) -{ - int ret; - u32 val; - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - val = local_cmpxchg(&drvdata->mode, CS_MODE_DISABLED, mode); - - /* Someone is already using the tracer */ - if (val) - return -EBUSY; - - switch (mode) { - case CS_MODE_SYSFS: - ret = etm4_enable_sysfs(csdev); - break; - case CS_MODE_PERF: - ret = etm4_enable_perf(csdev, event); - break; - default: - ret = -EINVAL; - } - - /* The tracer didn't start */ - if (ret) - local_set(&drvdata->mode, CS_MODE_DISABLED); - - return ret; -} - -static void etm4_disable_hw(void *info) -{ - u32 control; - struct etmv4_drvdata *drvdata = info; - - CS_UNLOCK(drvdata->base); - - /* power can be removed from the trace unit now */ - control = readl_relaxed(drvdata->base + TRCPDCR); - control &= ~TRCPDCR_PU; - writel_relaxed(control, drvdata->base + TRCPDCR); - - control = readl_relaxed(drvdata->base + TRCPRGCTLR); - - /* EN, bit[0] Trace unit enable bit */ - control &= ~0x1; - - /* make sure everything completes before disabling */ - mb(); - isb(); - writel_relaxed(control, drvdata->base + TRCPRGCTLR); - - coresight_disclaim_device_unlocked(drvdata->base); - - CS_LOCK(drvdata->base); - - dev_dbg(drvdata->dev, "cpu: %d disable smp call done\n", drvdata->cpu); -} - -static int etm4_disable_perf(struct coresight_device *csdev, - struct perf_event *event) -{ - u32 control; - struct etm_filters *filters = event->hw.addr_filters; - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) - return -EINVAL; - - etm4_disable_hw(drvdata); - - /* - * Check if the start/stop logic was active when the unit was stopped. - * That way we can re-enable the start/stop logic when the process is - * scheduled again. Configuration of the start/stop logic happens in - * function etm4_set_event_filters(). - */ - control = readl_relaxed(drvdata->base + TRCVICTLR); - /* TRCVICTLR::SSSTATUS, bit[9] */ - filters->ssstatus = (control & BIT(9)); - - return 0; -} - -static void etm4_disable_sysfs(struct coresight_device *csdev) -{ - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - /* - * Taking hotplug lock here protects from clocks getting disabled - * with tracing being left on (crash scenario) if user disable occurs - * after cpu online mask indicates the cpu is offline but before the - * DYING hotplug callback is serviced by the ETM driver. - */ - cpus_read_lock(); - spin_lock(&drvdata->spinlock); - - /* - * Executing etm4_disable_hw on the cpu whose ETM is being disabled - * ensures that register writes occur when cpu is powered. - */ - smp_call_function_single(drvdata->cpu, etm4_disable_hw, drvdata, 1); - - spin_unlock(&drvdata->spinlock); - cpus_read_unlock(); - - dev_dbg(drvdata->dev, "ETM tracing disabled\n"); -} - -static void etm4_disable(struct coresight_device *csdev, - struct perf_event *event) -{ - u32 mode; - struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - /* - * For as long as the tracer isn't disabled another entity can't - * change its status. As such we can read the status here without - * fearing it will change under us. - */ - mode = local_read(&drvdata->mode); - - switch (mode) { - case CS_MODE_DISABLED: - break; - case CS_MODE_SYSFS: - etm4_disable_sysfs(csdev); - break; - case CS_MODE_PERF: - etm4_disable_perf(csdev, event); - break; - } - - if (mode) - local_set(&drvdata->mode, CS_MODE_DISABLED); -} - -static const struct coresight_ops_source etm4_source_ops = { - .cpu_id = etm4_cpu_id, - .trace_id = etm4_trace_id, - .enable = etm4_enable, - .disable = etm4_disable, -}; - -static const struct coresight_ops etm4_cs_ops = { - .source_ops = &etm4_source_ops, -}; - -static void etm4_init_arch_data(void *info) -{ - u32 etmidr0; - u32 etmidr1; - u32 etmidr2; - u32 etmidr3; - u32 etmidr4; - u32 etmidr5; - struct etmv4_drvdata *drvdata = info; - - /* Make sure all registers are accessible */ - etm4_os_unlock(drvdata); - - CS_UNLOCK(drvdata->base); - - /* find all capabilities of the tracing unit */ - etmidr0 = readl_relaxed(drvdata->base + TRCIDR0); - - /* INSTP0, bits[2:1] P0 tracing support field */ - if (BMVAL(etmidr0, 1, 1) && BMVAL(etmidr0, 2, 2)) - drvdata->instrp0 = true; - else - drvdata->instrp0 = false; - - /* TRCBB, bit[5] Branch broadcast tracing support bit */ - if (BMVAL(etmidr0, 5, 5)) - drvdata->trcbb = true; - else - drvdata->trcbb = false; - - /* TRCCOND, bit[6] Conditional instruction tracing support bit */ - if (BMVAL(etmidr0, 6, 6)) - drvdata->trccond = true; - else - drvdata->trccond = false; - - /* TRCCCI, bit[7] Cycle counting instruction bit */ - if (BMVAL(etmidr0, 7, 7)) - drvdata->trccci = true; - else - drvdata->trccci = false; - - /* RETSTACK, bit[9] Return stack bit */ - if (BMVAL(etmidr0, 9, 9)) - drvdata->retstack = true; - else - drvdata->retstack = false; - - /* NUMEVENT, bits[11:10] Number of events field */ - drvdata->nr_event = BMVAL(etmidr0, 10, 11); - /* QSUPP, bits[16:15] Q element support field */ - drvdata->q_support = BMVAL(etmidr0, 15, 16); - /* TSSIZE, bits[28:24] Global timestamp size field */ - drvdata->ts_size = BMVAL(etmidr0, 24, 28); - - /* base architecture of trace unit */ - etmidr1 = readl_relaxed(drvdata->base + TRCIDR1); - /* - * TRCARCHMIN, bits[7:4] architecture the minor version number - * TRCARCHMAJ, bits[11:8] architecture major versin number - */ - drvdata->arch = BMVAL(etmidr1, 4, 11); - - /* maximum size of resources */ - etmidr2 = readl_relaxed(drvdata->base + TRCIDR2); - /* CIDSIZE, bits[9:5] Indicates the Context ID size */ - drvdata->ctxid_size = BMVAL(etmidr2, 5, 9); - /* VMIDSIZE, bits[14:10] Indicates the VMID size */ - drvdata->vmid_size = BMVAL(etmidr2, 10, 14); - /* CCSIZE, bits[28:25] size of the cycle counter in bits minus 12 */ - drvdata->ccsize = BMVAL(etmidr2, 25, 28); - - etmidr3 = readl_relaxed(drvdata->base + TRCIDR3); - /* CCITMIN, bits[11:0] minimum threshold value that can be programmed */ - drvdata->ccitmin = BMVAL(etmidr3, 0, 11); - /* EXLEVEL_S, bits[19:16] Secure state instruction tracing */ - drvdata->s_ex_level = BMVAL(etmidr3, 16, 19); - /* EXLEVEL_NS, bits[23:20] Non-secure state instruction tracing */ - drvdata->ns_ex_level = BMVAL(etmidr3, 20, 23); - - /* - * TRCERR, bit[24] whether a trace unit can trace a - * system error exception. - */ - if (BMVAL(etmidr3, 24, 24)) - drvdata->trc_error = true; - else - drvdata->trc_error = false; - - /* SYNCPR, bit[25] implementation has a fixed synchronization period? */ - if (BMVAL(etmidr3, 25, 25)) - drvdata->syncpr = true; - else - drvdata->syncpr = false; - - /* STALLCTL, bit[26] is stall control implemented? */ - if (BMVAL(etmidr3, 26, 26)) - drvdata->stallctl = true; - else - drvdata->stallctl = false; - - /* SYSSTALL, bit[27] implementation can support stall control? */ - if (BMVAL(etmidr3, 27, 27)) - drvdata->sysstall = true; - else - drvdata->sysstall = false; - - /* NUMPROC, bits[30:28] the number of PEs available for tracing */ - drvdata->nr_pe = BMVAL(etmidr3, 28, 30); - - /* NOOVERFLOW, bit[31] is trace overflow prevention supported */ - if (BMVAL(etmidr3, 31, 31)) - drvdata->nooverflow = true; - else - drvdata->nooverflow = false; - - /* number of resources trace unit supports */ - etmidr4 = readl_relaxed(drvdata->base + TRCIDR4); - /* NUMACPAIRS, bits[0:3] number of addr comparator pairs for tracing */ - drvdata->nr_addr_cmp = BMVAL(etmidr4, 0, 3); - /* NUMPC, bits[15:12] number of PE comparator inputs for tracing */ - drvdata->nr_pe_cmp = BMVAL(etmidr4, 12, 15); - /* - * NUMRSPAIR, bits[19:16] - * The number of resource pairs conveyed by the HW starts at 0, i.e a - * value of 0x0 indicate 1 resource pair, 0x1 indicate two and so on. - * As such add 1 to the value of NUMRSPAIR for a better representation. - */ - drvdata->nr_resource = BMVAL(etmidr4, 16, 19) + 1; - /* - * NUMSSCC, bits[23:20] the number of single-shot - * comparator control for tracing - */ - drvdata->nr_ss_cmp = BMVAL(etmidr4, 20, 23); - /* NUMCIDC, bits[27:24] number of Context ID comparators for tracing */ - drvdata->numcidc = BMVAL(etmidr4, 24, 27); - /* NUMVMIDC, bits[31:28] number of VMID comparators for tracing */ - drvdata->numvmidc = BMVAL(etmidr4, 28, 31); - - etmidr5 = readl_relaxed(drvdata->base + TRCIDR5); - /* NUMEXTIN, bits[8:0] number of external inputs implemented */ - drvdata->nr_ext_inp = BMVAL(etmidr5, 0, 8); - /* TRACEIDSIZE, bits[21:16] indicates the trace ID width */ - drvdata->trcid_size = BMVAL(etmidr5, 16, 21); - /* ATBTRIG, bit[22] implementation can support ATB triggers? */ - if (BMVAL(etmidr5, 22, 22)) - drvdata->atbtrig = true; - else - drvdata->atbtrig = false; - /* - * LPOVERRIDE, bit[23] implementation supports - * low-power state override - */ - if (BMVAL(etmidr5, 23, 23)) - drvdata->lpoverride = true; - else - drvdata->lpoverride = false; - /* NUMSEQSTATE, bits[27:25] number of sequencer states implemented */ - drvdata->nrseqstate = BMVAL(etmidr5, 25, 27); - /* NUMCNTR, bits[30:28] number of counters available for tracing */ - drvdata->nr_cntr = BMVAL(etmidr5, 28, 30); - CS_LOCK(drvdata->base); -} - -static void etm4_set_default_config(struct etmv4_config *config) -{ - /* disable all events tracing */ - config->eventctrl0 = 0x0; - config->eventctrl1 = 0x0; - - /* disable stalling */ - config->stall_ctrl = 0x0; - - /* enable trace synchronization every 4096 bytes, if available */ - config->syncfreq = 0xC; - - /* disable timestamp event */ - config->ts_ctrl = 0x0; - - /* TRCVICTLR::EVENT = 0x01, select the always on logic */ - config->vinst_ctrl |= BIT(0); -} - -static u64 etm4_get_ns_access_type(struct etmv4_config *config) -{ - u64 access_type = 0; - - /* - * EXLEVEL_NS, bits[15:12] - * The Exception levels are: - * Bit[12] Exception level 0 - Application - * Bit[13] Exception level 1 - OS - * Bit[14] Exception level 2 - Hypervisor - * Bit[15] Never implemented - */ - if (!is_kernel_in_hyp_mode()) { - /* Stay away from hypervisor mode for non-VHE */ - access_type = ETM_EXLEVEL_NS_HYP; - if (config->mode & ETM_MODE_EXCL_KERN) - access_type |= ETM_EXLEVEL_NS_OS; - } else if (config->mode & ETM_MODE_EXCL_KERN) { - access_type = ETM_EXLEVEL_NS_HYP; - } - - if (config->mode & ETM_MODE_EXCL_USER) - access_type |= ETM_EXLEVEL_NS_APP; - - return access_type; -} - -static u64 etm4_get_access_type(struct etmv4_config *config) -{ - u64 access_type = etm4_get_ns_access_type(config); - - /* - * EXLEVEL_S, bits[11:8], don't trace anything happening - * in secure state. - */ - access_type |= (ETM_EXLEVEL_S_APP | - ETM_EXLEVEL_S_OS | - ETM_EXLEVEL_S_HYP); - - return access_type; -} - -static void etm4_set_comparator_filter(struct etmv4_config *config, - u64 start, u64 stop, int comparator) -{ - u64 access_type = etm4_get_access_type(config); - - /* First half of default address comparator */ - config->addr_val[comparator] = start; - config->addr_acc[comparator] = access_type; - config->addr_type[comparator] = ETM_ADDR_TYPE_RANGE; - - /* Second half of default address comparator */ - config->addr_val[comparator + 1] = stop; - config->addr_acc[comparator + 1] = access_type; - config->addr_type[comparator + 1] = ETM_ADDR_TYPE_RANGE; - - /* - * Configure the ViewInst function to include this address range - * comparator. - * - * @comparator is divided by two since it is the index in the - * etmv4_config::addr_val array but register TRCVIIECTLR deals with - * address range comparator _pairs_. - * - * Therefore: - * index 0 -> compatator pair 0 - * index 2 -> comparator pair 1 - * index 4 -> comparator pair 2 - * ... - * index 14 -> comparator pair 7 - */ - config->viiectlr |= BIT(comparator / 2); -} - -static void etm4_set_start_stop_filter(struct etmv4_config *config, - u64 address, int comparator, - enum etm_addr_type type) -{ - int shift; - u64 access_type = etm4_get_access_type(config); - - /* Configure the comparator */ - config->addr_val[comparator] = address; - config->addr_acc[comparator] = access_type; - config->addr_type[comparator] = type; - - /* - * Configure ViewInst Start-Stop control register. - * Addresses configured to start tracing go from bit 0 to n-1, - * while those configured to stop tracing from 16 to 16 + n-1. - */ - shift = (type == ETM_ADDR_TYPE_START ? 0 : 16); - config->vissctlr |= BIT(shift + comparator); -} - -static void etm4_set_default_filter(struct etmv4_config *config) -{ - u64 start, stop; - - /* - * Configure address range comparator '0' to encompass all - * possible addresses. - */ - start = 0x0; - stop = ~0x0; - - etm4_set_comparator_filter(config, start, stop, - ETM_DEFAULT_ADDR_COMP); - - /* - * TRCVICTLR::SSSTATUS == 1, the start-stop logic is - * in the started state - */ - config->vinst_ctrl |= BIT(9); - - /* No start-stop filtering for ViewInst */ - config->vissctlr = 0x0; -} - -static void etm4_set_default(struct etmv4_config *config) -{ - if (WARN_ON_ONCE(!config)) - return; - - /* - * Make default initialisation trace everything - * - * Select the "always true" resource selector on the - * "Enablign Event" line and configure address range comparator - * '0' to trace all the possible address range. From there - * configure the "include/exclude" engine to include address - * range comparator '0'. - */ - etm4_set_default_config(config); - etm4_set_default_filter(config); -} - -static int etm4_get_next_comparator(struct etmv4_drvdata *drvdata, u32 type) -{ - int nr_comparator, index = 0; - struct etmv4_config *config = &drvdata->config; - - /* - * nr_addr_cmp holds the number of comparator _pair_, so time 2 - * for the total number of comparators. - */ - nr_comparator = drvdata->nr_addr_cmp * 2; - - /* Go through the tally of comparators looking for a free one. */ - while (index < nr_comparator) { - switch (type) { - case ETM_ADDR_TYPE_RANGE: - if (config->addr_type[index] == ETM_ADDR_TYPE_NONE && - config->addr_type[index + 1] == ETM_ADDR_TYPE_NONE) - return index; - - /* Address range comparators go in pairs */ - index += 2; - break; - case ETM_ADDR_TYPE_START: - case ETM_ADDR_TYPE_STOP: - if (config->addr_type[index] == ETM_ADDR_TYPE_NONE) - return index; - - /* Start/stop address can have odd indexes */ - index += 1; - break; - default: - return -EINVAL; - } - } - - /* If we are here all the comparators have been used. */ - return -ENOSPC; -} - -static int etm4_set_event_filters(struct etmv4_drvdata *drvdata, - struct perf_event *event) -{ - int i, comparator, ret = 0; - u64 address; - struct etmv4_config *config = &drvdata->config; - struct etm_filters *filters = event->hw.addr_filters; - - if (!filters) - goto default_filter; - - /* Sync events with what Perf got */ - perf_event_addr_filters_sync(event); - - /* - * If there are no filters to deal with simply go ahead with - * the default filter, i.e the entire address range. - */ - if (!filters->nr_filters) - goto default_filter; - - for (i = 0; i < filters->nr_filters; i++) { - struct etm_filter *filter = &filters->etm_filter[i]; - enum etm_addr_type type = filter->type; - - /* See if a comparator is free. */ - comparator = etm4_get_next_comparator(drvdata, type); - if (comparator < 0) { - ret = comparator; - goto out; - } - - switch (type) { - case ETM_ADDR_TYPE_RANGE: - etm4_set_comparator_filter(config, - filter->start_addr, - filter->stop_addr, - comparator); - /* - * TRCVICTLR::SSSTATUS == 1, the start-stop logic is - * in the started state - */ - config->vinst_ctrl |= BIT(9); - - /* No start-stop filtering for ViewInst */ - config->vissctlr = 0x0; - break; - case ETM_ADDR_TYPE_START: - case ETM_ADDR_TYPE_STOP: - /* Get the right start or stop address */ - address = (type == ETM_ADDR_TYPE_START ? - filter->start_addr : - filter->stop_addr); - - /* Configure comparator */ - etm4_set_start_stop_filter(config, address, - comparator, type); - - /* - * If filters::ssstatus == 1, trace acquisition was - * started but the process was yanked away before the - * the stop address was hit. As such the start/stop - * logic needs to be re-started so that tracing can - * resume where it left. - * - * The start/stop logic status when a process is - * scheduled out is checked in function - * etm4_disable_perf(). - */ - if (filters->ssstatus) - config->vinst_ctrl |= BIT(9); - - /* No include/exclude filtering for ViewInst */ - config->viiectlr = 0x0; - break; - default: - ret = -EINVAL; - goto out; - } - } - - goto out; - - -default_filter: - etm4_set_default_filter(config); - -out: - return ret; -} - -void etm4_config_trace_mode(struct etmv4_config *config) -{ - u32 addr_acc, mode; - - mode = config->mode; - mode &= (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER); - - /* excluding kernel AND user space doesn't make sense */ - WARN_ON_ONCE(mode == (ETM_MODE_EXCL_KERN | ETM_MODE_EXCL_USER)); - - /* nothing to do if neither flags are set */ - if (!(mode & ETM_MODE_EXCL_KERN) && !(mode & ETM_MODE_EXCL_USER)) - return; - - addr_acc = config->addr_acc[ETM_DEFAULT_ADDR_COMP]; - /* clear default config */ - addr_acc &= ~(ETM_EXLEVEL_NS_APP | ETM_EXLEVEL_NS_OS | - ETM_EXLEVEL_NS_HYP); - - addr_acc |= etm4_get_ns_access_type(config); - - config->addr_acc[ETM_DEFAULT_ADDR_COMP] = addr_acc; - config->addr_acc[ETM_DEFAULT_ADDR_COMP + 1] = addr_acc; -} - -static int etm4_online_cpu(unsigned int cpu) -{ - if (!etmdrvdata[cpu]) - return 0; - - if (etmdrvdata[cpu]->boot_enable && !etmdrvdata[cpu]->sticky_enable) - coresight_enable(etmdrvdata[cpu]->csdev); - return 0; -} - -static int etm4_starting_cpu(unsigned int cpu) -{ - if (!etmdrvdata[cpu]) - return 0; - - spin_lock(&etmdrvdata[cpu]->spinlock); - if (!etmdrvdata[cpu]->os_unlock) { - etm4_os_unlock(etmdrvdata[cpu]); - etmdrvdata[cpu]->os_unlock = true; - } - - if (local_read(&etmdrvdata[cpu]->mode)) - etm4_enable_hw(etmdrvdata[cpu]); - spin_unlock(&etmdrvdata[cpu]->spinlock); - return 0; -} - -static int etm4_dying_cpu(unsigned int cpu) -{ - if (!etmdrvdata[cpu]) - return 0; - - spin_lock(&etmdrvdata[cpu]->spinlock); - if (local_read(&etmdrvdata[cpu]->mode)) - etm4_disable_hw(etmdrvdata[cpu]); - spin_unlock(&etmdrvdata[cpu]->spinlock); - return 0; -} - -static void etm4_init_trace_id(struct etmv4_drvdata *drvdata) -{ - drvdata->trcid = coresight_get_trace_id(drvdata->cpu); -} - -static int etm4_probe(struct amba_device *adev, const struct amba_id *id) -{ - int ret; - void __iomem *base; - struct device *dev = &adev->dev; - struct coresight_platform_data *pdata = NULL; - struct etmv4_drvdata *drvdata; - struct resource *res = &adev->res; - struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; - - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } - - drvdata->dev = &adev->dev; - dev_set_drvdata(dev, drvdata); - - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); - - drvdata->base = base; - - spin_lock_init(&drvdata->spinlock); - - drvdata->cpu = pdata ? pdata->cpu : 0; - - cpus_read_lock(); - etmdrvdata[drvdata->cpu] = drvdata; - - if (smp_call_function_single(drvdata->cpu, - etm4_init_arch_data, drvdata, 1)) - dev_err(dev, "ETM arch init failed\n"); - - if (!etm4_count++) { - cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING, - "arm/coresight4:starting", - etm4_starting_cpu, etm4_dying_cpu); - ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN, - "arm/coresight4:online", - etm4_online_cpu, NULL); - if (ret < 0) - goto err_arch_supported; - hp_online = ret; - } - - cpus_read_unlock(); - - if (etm4_arch_supported(drvdata->arch) == false) { - ret = -EINVAL; - goto err_arch_supported; - } - - etm4_init_trace_id(drvdata); - etm4_set_default(&drvdata->config); - - desc.type = CORESIGHT_DEV_TYPE_SOURCE; - desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_PROC; - desc.ops = &etm4_cs_ops; - desc.pdata = pdata; - desc.dev = dev; - desc.groups = coresight_etmv4_groups; - drvdata->csdev = coresight_register(&desc); - if (IS_ERR(drvdata->csdev)) { - ret = PTR_ERR(drvdata->csdev); - goto err_arch_supported; - } - - ret = etm_perf_symlink(drvdata->csdev, true); - if (ret) { - coresight_unregister(drvdata->csdev); - goto err_arch_supported; - } - - pm_runtime_put(&adev->dev); - dev_info(dev, "CPU%d: ETM v%d.%d initialized\n", - drvdata->cpu, drvdata->arch >> 4, drvdata->arch & 0xf); - - if (boot_enable) { - coresight_enable(drvdata->csdev); - drvdata->boot_enable = true; - } - - return 0; - -err_arch_supported: - if (--etm4_count == 0) { - cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); - if (hp_online) - cpuhp_remove_state_nocalls(hp_online); - } - return ret; -} - -#define ETM4x_AMBA_ID(pid) \ - { \ - .id = pid, \ - .mask = 0x000fffff, \ - } - -static const struct amba_id etm4_ids[] = { - ETM4x_AMBA_ID(0x000bb95d), /* Cortex-A53 */ - ETM4x_AMBA_ID(0x000bb95e), /* Cortex-A57 */ - ETM4x_AMBA_ID(0x000bb95a), /* Cortex-A72 */ - ETM4x_AMBA_ID(0x000bb959), /* Cortex-A73 */ - ETM4x_AMBA_ID(0x000bb9da), /* Cortex-A35 */ - {}, -}; - -static struct amba_driver etm4x_driver = { - .drv = { - .name = "coresight-etm4x", - .suppress_bind_attrs = true, - }, - .probe = etm4_probe, - .id_table = etm4_ids, -}; -builtin_amba_driver(etm4x_driver); diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 52786e9d8926..012c52fd1933 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -7,7 +7,9 @@ #define _CORESIGHT_CORESIGHT_ETM_H #include <asm/local.h> +#include <linux/const.h> #include <linux/spinlock.h> +#include <linux/types.h> #include "coresight-priv.h" /* @@ -28,6 +30,7 @@ #define TRCAUXCTLR 0x018 #define TRCEVENTCTL0R 0x020 #define TRCEVENTCTL1R 0x024 +#define TRCRSR 0x028 #define TRCSTALLCTLR 0x02C #define TRCTSCTLR 0x030 #define TRCSYNCPR 0x034 @@ -40,17 +43,15 @@ #define TRCVIIECTLR 0x084 #define TRCVISSCTLR 0x088 #define TRCVIPCSSCTLR 0x08C -#define TRCVDCTLR 0x0A0 -#define TRCVDSACCTLR 0x0A4 -#define TRCVDARCCTLR 0x0A8 /* Derived resources registers */ -#define TRCSEQEVRn(n) (0x100 + (n * 4)) +#define TRCSEQEVRn(n) (0x100 + (n * 4)) /* n = 0-2 */ #define TRCSEQRSTEVR 0x118 #define TRCSEQSTR 0x11C #define TRCEXTINSELR 0x120 -#define TRCCNTRLDVRn(n) (0x140 + (n * 4)) -#define TRCCNTCTLRn(n) (0x150 + (n * 4)) -#define TRCCNTVRn(n) (0x160 + (n * 4)) +#define TRCEXTINSELRn(n) (0x120 + (n * 4)) /* n = 0-3 */ +#define TRCCNTRLDVRn(n) (0x140 + (n * 4)) /* n = 0-3 */ +#define TRCCNTCTLRn(n) (0x150 + (n * 4)) /* n = 0-3 */ +#define TRCCNTVRn(n) (0x160 + (n * 4)) /* n = 0-3 */ /* ID registers */ #define TRCIDR8 0x180 #define TRCIDR9 0x184 @@ -59,7 +60,7 @@ #define TRCIDR12 0x190 #define TRCIDR13 0x194 #define TRCIMSPEC0 0x1C0 -#define TRCIMSPECn(n) (0x1C0 + (n * 4)) +#define TRCIMSPECn(n) (0x1C0 + (n * 4)) /* n = 1-7 */ #define TRCIDR0 0x1E0 #define TRCIDR1 0x1E4 #define TRCIDR2 0x1E8 @@ -68,9 +69,12 @@ #define TRCIDR5 0x1F4 #define TRCIDR6 0x1F8 #define TRCIDR7 0x1FC -/* Resource selection registers */ +/* + * Resource selection registers, n = 2-31. + * First pair (regs 0, 1) is always present and is reserved. + */ #define TRCRSCTLRn(n) (0x200 + (n * 4)) -/* Single-shot comparator registers */ +/* Single-shot comparator registers, n = 0-7 */ #define TRCSSCCRn(n) (0x280 + (n * 4)) #define TRCSSCSRn(n) (0x2A0 + (n * 4)) #define TRCSSPCICRn(n) (0x2C0 + (n * 4)) @@ -80,11 +84,10 @@ #define TRCPDCR 0x310 #define TRCPDSR 0x314 /* Trace registers (0x318-0xEFC) */ -/* Comparator registers */ +/* Address Comparator registers n = 0-15 */ #define TRCACVRn(n) (0x400 + (n * 8)) #define TRCACATRn(n) (0x480 + (n * 8)) -#define TRCDVCVRn(n) (0x500 + (n * 16)) -#define TRCDVCMRn(n) (0x580 + (n * 16)) +/* ContextID/Virtual ContextID comparators, n = 0-7 */ #define TRCCIDCVRn(n) (0x600 + (n * 8)) #define TRCVMIDCVRn(n) (0x640 + (n * 8)) #define TRCCIDCCTLR0 0x680 @@ -120,6 +123,449 @@ #define TRCCIDR2 0xFF8 #define TRCCIDR3 0xFFC +#define TRCRSR_TA BIT(12) + +/* + * Bit positions of registers that are defined above, in the sysreg.h style + * of _MASK for multi bit fields and BIT() for single bits. + */ +#define TRCIDR0_INSTP0_MASK GENMASK(2, 1) +#define TRCIDR0_TRCBB BIT(5) +#define TRCIDR0_TRCCOND BIT(6) +#define TRCIDR0_TRCCCI BIT(7) +#define TRCIDR0_RETSTACK BIT(9) +#define TRCIDR0_NUMEVENT_MASK GENMASK(11, 10) +#define TRCIDR0_QFILT BIT(14) +#define TRCIDR0_QSUPP_MASK GENMASK(16, 15) +#define TRCIDR0_TSSIZE_MASK GENMASK(28, 24) + +#define TRCIDR2_CIDSIZE_MASK GENMASK(9, 5) +#define TRCIDR2_VMIDSIZE_MASK GENMASK(14, 10) +#define TRCIDR2_CCSIZE_MASK GENMASK(28, 25) + +#define TRCIDR3_CCITMIN_MASK GENMASK(11, 0) +#define TRCIDR3_EXLEVEL_S_MASK GENMASK(19, 16) +#define TRCIDR3_EXLEVEL_NS_MASK GENMASK(23, 20) +#define TRCIDR3_TRCERR BIT(24) +#define TRCIDR3_SYNCPR BIT(25) +#define TRCIDR3_STALLCTL BIT(26) +#define TRCIDR3_SYSSTALL BIT(27) +#define TRCIDR3_NUMPROC_LO_MASK GENMASK(30, 28) +#define TRCIDR3_NUMPROC_HI_MASK GENMASK(13, 12) +#define TRCIDR3_NOOVERFLOW BIT(31) + +#define TRCIDR4_NUMACPAIRS_MASK GENMASK(3, 0) +#define TRCIDR4_NUMPC_MASK GENMASK(15, 12) +#define TRCIDR4_NUMRSPAIR_MASK GENMASK(19, 16) +#define TRCIDR4_NUMSSCC_MASK GENMASK(23, 20) +#define TRCIDR4_NUMCIDC_MASK GENMASK(27, 24) +#define TRCIDR4_NUMVMIDC_MASK GENMASK(31, 28) + +#define TRCIDR5_NUMEXTIN_MASK GENMASK(8, 0) +#define TRCIDR5_NUMEXTINSEL_MASK GENMASK(11, 9) +#define TRCIDR5_TRACEIDSIZE_MASK GENMASK(21, 16) +#define TRCIDR5_ATBTRIG BIT(22) +#define TRCIDR5_LPOVERRIDE BIT(23) +#define TRCIDR5_NUMSEQSTATE_MASK GENMASK(27, 25) +#define TRCIDR5_NUMCNTR_MASK GENMASK(30, 28) + +#define TRCCONFIGR_INSTP0_LOAD BIT(1) +#define TRCCONFIGR_INSTP0_STORE BIT(2) +#define TRCCONFIGR_INSTP0_LOAD_STORE (TRCCONFIGR_INSTP0_LOAD | TRCCONFIGR_INSTP0_STORE) +#define TRCCONFIGR_BB BIT(3) +#define TRCCONFIGR_CCI BIT(4) +#define TRCCONFIGR_CID BIT(6) +#define TRCCONFIGR_VMID BIT(7) +#define TRCCONFIGR_COND_MASK GENMASK(10, 8) +#define TRCCONFIGR_TS BIT(11) +#define TRCCONFIGR_RS BIT(12) +#define TRCCONFIGR_QE_W_COUNTS BIT(13) +#define TRCCONFIGR_QE_WO_COUNTS BIT(14) +#define TRCCONFIGR_VMIDOPT BIT(15) +#define TRCCONFIGR_DA BIT(16) +#define TRCCONFIGR_DV BIT(17) + +#define TRCEVENTCTL1R_INSTEN_MASK GENMASK(3, 0) +#define TRCEVENTCTL1R_INSTEN_0 BIT(0) +#define TRCEVENTCTL1R_INSTEN_1 BIT(1) +#define TRCEVENTCTL1R_INSTEN_2 BIT(2) +#define TRCEVENTCTL1R_INSTEN_3 BIT(3) +#define TRCEVENTCTL1R_ATB BIT(11) +#define TRCEVENTCTL1R_LPOVERRIDE BIT(12) + +#define TRCSTALLCTLR_ISTALL BIT(8) +#define TRCSTALLCTLR_INSTPRIORITY BIT(10) +#define TRCSTALLCTLR_NOOVERFLOW BIT(13) + +#define TRCVICTLR_EVENT_MASK GENMASK(7, 0) +#define TRCVICTLR_SSSTATUS BIT(9) +#define TRCVICTLR_TRCRESET BIT(10) +#define TRCVICTLR_TRCERR BIT(11) +#define TRCVICTLR_EXLEVEL_MASK GENMASK(22, 16) +#define TRCVICTLR_EXLEVEL_S_MASK GENMASK(19, 16) +#define TRCVICTLR_EXLEVEL_NS_MASK GENMASK(22, 20) + +#define TRCACATRn_TYPE_MASK GENMASK(1, 0) +#define TRCACATRn_CONTEXTTYPE_MASK GENMASK(3, 2) +#define TRCACATRn_CONTEXTTYPE_CTXID BIT(2) +#define TRCACATRn_CONTEXTTYPE_VMID BIT(3) +#define TRCACATRn_CONTEXT_MASK GENMASK(6, 4) +#define TRCACATRn_EXLEVEL_MASK GENMASK(14, 8) + +#define TRCSSCSRn_STATUS BIT(31) +#define TRCSSCCRn_SAC_ARC_RST_MASK GENMASK(24, 0) + +#define TRCSSPCICRn_PC_MASK GENMASK(7, 0) + +#define TRCBBCTLR_MODE BIT(8) +#define TRCBBCTLR_RANGE_MASK GENMASK(7, 0) + +#define TRCRSCTLRn_PAIRINV BIT(21) +#define TRCRSCTLRn_INV BIT(20) +#define TRCRSCTLRn_GROUP_MASK GENMASK(19, 16) +#define TRCRSCTLRn_SELECT_MASK GENMASK(15, 0) + +/* + * System instructions to access ETM registers. + * See ETMv4.4 spec ARM IHI0064F section 4.3.6 System instructions + */ +#define ETM4x_OFFSET_TO_REG(x) ((x) >> 2) + +#define ETM4x_CRn(n) (((n) >> 7) & 0x7) +#define ETM4x_Op2(n) (((n) >> 4) & 0x7) +#define ETM4x_CRm(n) ((n) & 0xf) + +#include <asm/sysreg.h> +#define ETM4x_REG_NUM_TO_SYSREG(n) \ + sys_reg(2, 1, ETM4x_CRn(n), ETM4x_CRm(n), ETM4x_Op2(n)) + +#define READ_ETM4x_REG(reg) \ + read_sysreg_s(ETM4x_REG_NUM_TO_SYSREG((reg))) +#define WRITE_ETM4x_REG(val, reg) \ + write_sysreg_s(val, ETM4x_REG_NUM_TO_SYSREG((reg))) + +#define read_etm4x_sysreg_const_offset(offset) \ + READ_ETM4x_REG(ETM4x_OFFSET_TO_REG(offset)) + +#define write_etm4x_sysreg_const_offset(val, offset) \ + WRITE_ETM4x_REG(val, ETM4x_OFFSET_TO_REG(offset)) + +#define CASE_READ(res, x) \ + case (x): { (res) = read_etm4x_sysreg_const_offset((x)); break; } + +#define CASE_WRITE(val, x) \ + case (x): { write_etm4x_sysreg_const_offset((val), (x)); break; } + +#define CASE_NOP(__unused, x) \ + case (x): /* fall through */ + +#define ETE_ONLY_SYSREG_LIST(op, val) \ + CASE_##op((val), TRCRSR) \ + CASE_##op((val), TRCEXTINSELRn(1)) \ + CASE_##op((val), TRCEXTINSELRn(2)) \ + CASE_##op((val), TRCEXTINSELRn(3)) + +/* List of registers accessible via System instructions */ +#define ETM4x_ONLY_SYSREG_LIST(op, val) \ + CASE_##op((val), TRCPROCSELR) \ + CASE_##op((val), TRCOSLAR) + +#define ETM_COMMON_SYSREG_LIST(op, val) \ + CASE_##op((val), TRCPRGCTLR) \ + CASE_##op((val), TRCSTATR) \ + CASE_##op((val), TRCCONFIGR) \ + CASE_##op((val), TRCAUXCTLR) \ + CASE_##op((val), TRCEVENTCTL0R) \ + CASE_##op((val), TRCEVENTCTL1R) \ + CASE_##op((val), TRCSTALLCTLR) \ + CASE_##op((val), TRCTSCTLR) \ + CASE_##op((val), TRCSYNCPR) \ + CASE_##op((val), TRCCCCTLR) \ + CASE_##op((val), TRCBBCTLR) \ + CASE_##op((val), TRCTRACEIDR) \ + CASE_##op((val), TRCQCTLR) \ + CASE_##op((val), TRCVICTLR) \ + CASE_##op((val), TRCVIIECTLR) \ + CASE_##op((val), TRCVISSCTLR) \ + CASE_##op((val), TRCVIPCSSCTLR) \ + CASE_##op((val), TRCSEQEVRn(0)) \ + CASE_##op((val), TRCSEQEVRn(1)) \ + CASE_##op((val), TRCSEQEVRn(2)) \ + CASE_##op((val), TRCSEQRSTEVR) \ + CASE_##op((val), TRCSEQSTR) \ + CASE_##op((val), TRCEXTINSELR) \ + CASE_##op((val), TRCCNTRLDVRn(0)) \ + CASE_##op((val), TRCCNTRLDVRn(1)) \ + CASE_##op((val), TRCCNTRLDVRn(2)) \ + CASE_##op((val), TRCCNTRLDVRn(3)) \ + CASE_##op((val), TRCCNTCTLRn(0)) \ + CASE_##op((val), TRCCNTCTLRn(1)) \ + CASE_##op((val), TRCCNTCTLRn(2)) \ + CASE_##op((val), TRCCNTCTLRn(3)) \ + CASE_##op((val), TRCCNTVRn(0)) \ + CASE_##op((val), TRCCNTVRn(1)) \ + CASE_##op((val), TRCCNTVRn(2)) \ + CASE_##op((val), TRCCNTVRn(3)) \ + CASE_##op((val), TRCIDR8) \ + CASE_##op((val), TRCIDR9) \ + CASE_##op((val), TRCIDR10) \ + CASE_##op((val), TRCIDR11) \ + CASE_##op((val), TRCIDR12) \ + CASE_##op((val), TRCIDR13) \ + CASE_##op((val), TRCIMSPECn(0)) \ + CASE_##op((val), TRCIMSPECn(1)) \ + CASE_##op((val), TRCIMSPECn(2)) \ + CASE_##op((val), TRCIMSPECn(3)) \ + CASE_##op((val), TRCIMSPECn(4)) \ + CASE_##op((val), TRCIMSPECn(5)) \ + CASE_##op((val), TRCIMSPECn(6)) \ + CASE_##op((val), TRCIMSPECn(7)) \ + CASE_##op((val), TRCIDR0) \ + CASE_##op((val), TRCIDR1) \ + CASE_##op((val), TRCIDR2) \ + CASE_##op((val), TRCIDR3) \ + CASE_##op((val), TRCIDR4) \ + CASE_##op((val), TRCIDR5) \ + CASE_##op((val), TRCIDR6) \ + CASE_##op((val), TRCIDR7) \ + CASE_##op((val), TRCRSCTLRn(2)) \ + CASE_##op((val), TRCRSCTLRn(3)) \ + CASE_##op((val), TRCRSCTLRn(4)) \ + CASE_##op((val), TRCRSCTLRn(5)) \ + CASE_##op((val), TRCRSCTLRn(6)) \ + CASE_##op((val), TRCRSCTLRn(7)) \ + CASE_##op((val), TRCRSCTLRn(8)) \ + CASE_##op((val), TRCRSCTLRn(9)) \ + CASE_##op((val), TRCRSCTLRn(10)) \ + CASE_##op((val), TRCRSCTLRn(11)) \ + CASE_##op((val), TRCRSCTLRn(12)) \ + CASE_##op((val), TRCRSCTLRn(13)) \ + CASE_##op((val), TRCRSCTLRn(14)) \ + CASE_##op((val), TRCRSCTLRn(15)) \ + CASE_##op((val), TRCRSCTLRn(16)) \ + CASE_##op((val), TRCRSCTLRn(17)) \ + CASE_##op((val), TRCRSCTLRn(18)) \ + CASE_##op((val), TRCRSCTLRn(19)) \ + CASE_##op((val), TRCRSCTLRn(20)) \ + CASE_##op((val), TRCRSCTLRn(21)) \ + CASE_##op((val), TRCRSCTLRn(22)) \ + CASE_##op((val), TRCRSCTLRn(23)) \ + CASE_##op((val), TRCRSCTLRn(24)) \ + CASE_##op((val), TRCRSCTLRn(25)) \ + CASE_##op((val), TRCRSCTLRn(26)) \ + CASE_##op((val), TRCRSCTLRn(27)) \ + CASE_##op((val), TRCRSCTLRn(28)) \ + CASE_##op((val), TRCRSCTLRn(29)) \ + CASE_##op((val), TRCRSCTLRn(30)) \ + CASE_##op((val), TRCRSCTLRn(31)) \ + CASE_##op((val), TRCSSCCRn(0)) \ + CASE_##op((val), TRCSSCCRn(1)) \ + CASE_##op((val), TRCSSCCRn(2)) \ + CASE_##op((val), TRCSSCCRn(3)) \ + CASE_##op((val), TRCSSCCRn(4)) \ + CASE_##op((val), TRCSSCCRn(5)) \ + CASE_##op((val), TRCSSCCRn(6)) \ + CASE_##op((val), TRCSSCCRn(7)) \ + CASE_##op((val), TRCSSCSRn(0)) \ + CASE_##op((val), TRCSSCSRn(1)) \ + CASE_##op((val), TRCSSCSRn(2)) \ + CASE_##op((val), TRCSSCSRn(3)) \ + CASE_##op((val), TRCSSCSRn(4)) \ + CASE_##op((val), TRCSSCSRn(5)) \ + CASE_##op((val), TRCSSCSRn(6)) \ + CASE_##op((val), TRCSSCSRn(7)) \ + CASE_##op((val), TRCSSPCICRn(0)) \ + CASE_##op((val), TRCSSPCICRn(1)) \ + CASE_##op((val), TRCSSPCICRn(2)) \ + CASE_##op((val), TRCSSPCICRn(3)) \ + CASE_##op((val), TRCSSPCICRn(4)) \ + CASE_##op((val), TRCSSPCICRn(5)) \ + CASE_##op((val), TRCSSPCICRn(6)) \ + CASE_##op((val), TRCSSPCICRn(7)) \ + CASE_##op((val), TRCOSLSR) \ + CASE_##op((val), TRCACVRn(0)) \ + CASE_##op((val), TRCACVRn(1)) \ + CASE_##op((val), TRCACVRn(2)) \ + CASE_##op((val), TRCACVRn(3)) \ + CASE_##op((val), TRCACVRn(4)) \ + CASE_##op((val), TRCACVRn(5)) \ + CASE_##op((val), TRCACVRn(6)) \ + CASE_##op((val), TRCACVRn(7)) \ + CASE_##op((val), TRCACVRn(8)) \ + CASE_##op((val), TRCACVRn(9)) \ + CASE_##op((val), TRCACVRn(10)) \ + CASE_##op((val), TRCACVRn(11)) \ + CASE_##op((val), TRCACVRn(12)) \ + CASE_##op((val), TRCACVRn(13)) \ + CASE_##op((val), TRCACVRn(14)) \ + CASE_##op((val), TRCACVRn(15)) \ + CASE_##op((val), TRCACATRn(0)) \ + CASE_##op((val), TRCACATRn(1)) \ + CASE_##op((val), TRCACATRn(2)) \ + CASE_##op((val), TRCACATRn(3)) \ + CASE_##op((val), TRCACATRn(4)) \ + CASE_##op((val), TRCACATRn(5)) \ + CASE_##op((val), TRCACATRn(6)) \ + CASE_##op((val), TRCACATRn(7)) \ + CASE_##op((val), TRCACATRn(8)) \ + CASE_##op((val), TRCACATRn(9)) \ + CASE_##op((val), TRCACATRn(10)) \ + CASE_##op((val), TRCACATRn(11)) \ + CASE_##op((val), TRCACATRn(12)) \ + CASE_##op((val), TRCACATRn(13)) \ + CASE_##op((val), TRCACATRn(14)) \ + CASE_##op((val), TRCACATRn(15)) \ + CASE_##op((val), TRCCIDCVRn(0)) \ + CASE_##op((val), TRCCIDCVRn(1)) \ + CASE_##op((val), TRCCIDCVRn(2)) \ + CASE_##op((val), TRCCIDCVRn(3)) \ + CASE_##op((val), TRCCIDCVRn(4)) \ + CASE_##op((val), TRCCIDCVRn(5)) \ + CASE_##op((val), TRCCIDCVRn(6)) \ + CASE_##op((val), TRCCIDCVRn(7)) \ + CASE_##op((val), TRCVMIDCVRn(0)) \ + CASE_##op((val), TRCVMIDCVRn(1)) \ + CASE_##op((val), TRCVMIDCVRn(2)) \ + CASE_##op((val), TRCVMIDCVRn(3)) \ + CASE_##op((val), TRCVMIDCVRn(4)) \ + CASE_##op((val), TRCVMIDCVRn(5)) \ + CASE_##op((val), TRCVMIDCVRn(6)) \ + CASE_##op((val), TRCVMIDCVRn(7)) \ + CASE_##op((val), TRCCIDCCTLR0) \ + CASE_##op((val), TRCCIDCCTLR1) \ + CASE_##op((val), TRCVMIDCCTLR0) \ + CASE_##op((val), TRCVMIDCCTLR1) \ + CASE_##op((val), TRCCLAIMSET) \ + CASE_##op((val), TRCCLAIMCLR) \ + CASE_##op((val), TRCAUTHSTATUS) \ + CASE_##op((val), TRCDEVARCH) \ + CASE_##op((val), TRCDEVID) + +/* List of registers only accessible via memory-mapped interface */ +#define ETM_MMAP_LIST(op, val) \ + CASE_##op((val), TRCDEVTYPE) \ + CASE_##op((val), TRCPDCR) \ + CASE_##op((val), TRCPDSR) \ + CASE_##op((val), TRCDEVAFF0) \ + CASE_##op((val), TRCDEVAFF1) \ + CASE_##op((val), TRCLAR) \ + CASE_##op((val), TRCLSR) \ + CASE_##op((val), TRCITCTRL) \ + CASE_##op((val), TRCPIDR4) \ + CASE_##op((val), TRCPIDR0) \ + CASE_##op((val), TRCPIDR1) \ + CASE_##op((val), TRCPIDR2) \ + CASE_##op((val), TRCPIDR3) + +#define ETM4x_READ_SYSREG_CASES(res) \ + ETM_COMMON_SYSREG_LIST(READ, (res)) \ + ETM4x_ONLY_SYSREG_LIST(READ, (res)) + +#define ETM4x_WRITE_SYSREG_CASES(val) \ + ETM_COMMON_SYSREG_LIST(WRITE, (val)) \ + ETM4x_ONLY_SYSREG_LIST(WRITE, (val)) + +#define ETM_COMMON_SYSREG_LIST_CASES \ + ETM_COMMON_SYSREG_LIST(NOP, __unused) + +#define ETM4x_ONLY_SYSREG_LIST_CASES \ + ETM4x_ONLY_SYSREG_LIST(NOP, __unused) + +#define ETM4x_SYSREG_LIST_CASES \ + ETM_COMMON_SYSREG_LIST_CASES \ + ETM4x_ONLY_SYSREG_LIST(NOP, __unused) + +#define ETM4x_MMAP_LIST_CASES ETM_MMAP_LIST(NOP, __unused) + +/* ETE only supports system register access */ +#define ETE_READ_CASES(res) \ + ETM_COMMON_SYSREG_LIST(READ, (res)) \ + ETE_ONLY_SYSREG_LIST(READ, (res)) + +#define ETE_WRITE_CASES(val) \ + ETM_COMMON_SYSREG_LIST(WRITE, (val)) \ + ETE_ONLY_SYSREG_LIST(WRITE, (val)) + +#define ETE_ONLY_SYSREG_LIST_CASES \ + ETE_ONLY_SYSREG_LIST(NOP, __unused) + +#define read_etm4x_sysreg_offset(offset, _64bit) \ + ({ \ + u64 __val; \ + \ + if (__is_constexpr((offset))) \ + __val = read_etm4x_sysreg_const_offset((offset)); \ + else \ + __val = etm4x_sysreg_read((offset), true, (_64bit)); \ + __val; \ + }) + +#define write_etm4x_sysreg_offset(val, offset, _64bit) \ + do { \ + if (__builtin_constant_p((offset))) \ + write_etm4x_sysreg_const_offset((val), \ + (offset)); \ + else \ + etm4x_sysreg_write((val), (offset), true, \ + (_64bit)); \ + } while (0) + + +#define etm4x_relaxed_read32(csa, offset) \ + ((u32)((csa)->io_mem ? \ + readl_relaxed((csa)->base + (offset)) : \ + read_etm4x_sysreg_offset((offset), false))) + +#define etm4x_relaxed_read64(csa, offset) \ + ((u64)((csa)->io_mem ? \ + readq_relaxed((csa)->base + (offset)) : \ + read_etm4x_sysreg_offset((offset), true))) + +#define etm4x_read32(csa, offset) \ + ({ \ + u32 __val = etm4x_relaxed_read32((csa), (offset)); \ + __io_ar(__val); \ + __val; \ + }) + +#define etm4x_read64(csa, offset) \ + ({ \ + u64 __val = etm4x_relaxed_read64((csa), (offset)); \ + __io_ar(__val); \ + __val; \ + }) + +#define etm4x_relaxed_write32(csa, val, offset) \ + do { \ + if ((csa)->io_mem) \ + writel_relaxed((val), (csa)->base + (offset)); \ + else \ + write_etm4x_sysreg_offset((val), (offset), \ + false); \ + } while (0) + +#define etm4x_relaxed_write64(csa, val, offset) \ + do { \ + if ((csa)->io_mem) \ + writeq_relaxed((val), (csa)->base + (offset)); \ + else \ + write_etm4x_sysreg_offset((val), (offset), \ + true); \ + } while (0) + +#define etm4x_write32(csa, val, offset) \ + do { \ + __io_bw(); \ + etm4x_relaxed_write32((csa), (val), (offset)); \ + } while (0) + +#define etm4x_write64(csa, val, offset) \ + do { \ + __io_bw(); \ + etm4x_relaxed_write64((csa), (val), (offset)); \ + } while (0) + + /* ETMv4 resources */ #define ETM_MAX_NR_PE 8 #define ETMv4_MAX_CNTR 4 @@ -133,10 +579,9 @@ #define ETMv4_MAX_CTXID_CMP 8 #define ETM_MAX_VMID_CMP 8 #define ETM_MAX_PE_CMP 8 -#define ETM_MAX_RES_SEL 16 +#define ETM_MAX_RES_SEL 32 #define ETM_MAX_SS_CMP 8 -#define ETM_ARCH_V4 0x40 #define ETMv4_SYNC_MASK 0x1F #define ETM_CYC_THRESHOLD_MASK 0xFFF #define ETM_CYC_THRESHOLD_DEFAULT 0x100 @@ -174,22 +619,154 @@ ETM_MODE_EXCL_KERN | \ ETM_MODE_EXCL_USER) +/* + * TRCOSLSR.OSLM advertises the OS Lock model. + * OSLM[2:0] = TRCOSLSR[4:3,0] + * + * 0b000 - Trace OS Lock is not implemented. + * 0b010 - Trace OS Lock is implemented. + * 0b100 - Trace OS Lock is not implemented, unit is controlled by PE OS Lock. + */ +#define ETM_OSLOCK_NI 0b000 +#define ETM_OSLOCK_PRESENT 0b010 +#define ETM_OSLOCK_PE 0b100 + +#define ETM_OSLSR_OSLM(oslsr) ((((oslsr) & GENMASK(4, 3)) >> 2) | (oslsr & 0x1)) + +/* + * TRCDEVARCH Bit field definitions + * Bits[31:21] - ARCHITECT = Always Arm Ltd. + * * Bits[31:28] = 0x4 + * * Bits[27:21] = 0b0111011 + * Bit[20] - PRESENT, Indicates the presence of this register. + * + * Bit[19:16] - REVISION, Revision of the architecture. + * + * Bit[15:0] - ARCHID, Identifies this component as an ETM + * * Bits[15:12] - architecture version of ETM + * * = 4 for ETMv4 + * * Bits[11:0] = 0xA13, architecture part number for ETM. + */ +#define ETM_DEVARCH_ARCHITECT_MASK GENMASK(31, 21) +#define ETM_DEVARCH_ARCHITECT_ARM ((0x4 << 28) | (0b0111011 << 21)) +#define ETM_DEVARCH_PRESENT BIT(20) +#define ETM_DEVARCH_REVISION_SHIFT 16 +#define ETM_DEVARCH_REVISION_MASK GENMASK(19, 16) +#define ETM_DEVARCH_REVISION(x) \ + (((x) & ETM_DEVARCH_REVISION_MASK) >> ETM_DEVARCH_REVISION_SHIFT) +#define ETM_DEVARCH_ARCHID_MASK GENMASK(15, 0) +#define ETM_DEVARCH_ARCHID_ARCH_VER_SHIFT 12 +#define ETM_DEVARCH_ARCHID_ARCH_VER_MASK GENMASK(15, 12) +#define ETM_DEVARCH_ARCHID_ARCH_VER(x) \ + (((x) & ETM_DEVARCH_ARCHID_ARCH_VER_MASK) >> ETM_DEVARCH_ARCHID_ARCH_VER_SHIFT) + +#define ETM_DEVARCH_MAKE_ARCHID_ARCH_VER(ver) \ + (((ver) << ETM_DEVARCH_ARCHID_ARCH_VER_SHIFT) & ETM_DEVARCH_ARCHID_ARCH_VER_MASK) + +#define ETM_DEVARCH_ARCHID_ARCH_PART(x) ((x) & 0xfffUL) + +#define ETM_DEVARCH_MAKE_ARCHID(major) \ + ((ETM_DEVARCH_MAKE_ARCHID_ARCH_VER(major)) | ETM_DEVARCH_ARCHID_ARCH_PART(0xA13)) + +#define ETM_DEVARCH_ARCHID_ETMv4x ETM_DEVARCH_MAKE_ARCHID(0x4) +#define ETM_DEVARCH_ARCHID_ETE ETM_DEVARCH_MAKE_ARCHID(0x5) + +#define ETM_DEVARCH_ID_MASK \ + (ETM_DEVARCH_ARCHITECT_MASK | ETM_DEVARCH_ARCHID_MASK | ETM_DEVARCH_PRESENT) +#define ETM_DEVARCH_ETMv4x_ARCH \ + (ETM_DEVARCH_ARCHITECT_ARM | ETM_DEVARCH_ARCHID_ETMv4x | ETM_DEVARCH_PRESENT) +#define ETM_DEVARCH_ETE_ARCH \ + (ETM_DEVARCH_ARCHITECT_ARM | ETM_DEVARCH_ARCHID_ETE | ETM_DEVARCH_PRESENT) + +#define CS_DEVTYPE_PE_TRACE 0x00000013 + #define TRCSTATR_IDLE_BIT 0 +#define TRCSTATR_PMSTABLE_BIT 1 #define ETM_DEFAULT_ADDR_COMP 0 +#define TRCSSCSRn_PC BIT(3) + /* PowerDown Control Register bits */ #define TRCPDCR_PU BIT(3) -/* secure state access levels */ -#define ETM_EXLEVEL_S_APP BIT(8) -#define ETM_EXLEVEL_S_OS BIT(9) -#define ETM_EXLEVEL_S_NA BIT(10) -#define ETM_EXLEVEL_S_HYP BIT(11) -/* non-secure state access levels */ -#define ETM_EXLEVEL_NS_APP BIT(12) -#define ETM_EXLEVEL_NS_OS BIT(13) -#define ETM_EXLEVEL_NS_HYP BIT(14) -#define ETM_EXLEVEL_NS_NA BIT(15) +#define TRCACATR_EXLEVEL_SHIFT 8 + +/* + * Exception level mask for Secure and Non-Secure ELs. + * ETM defines the bits for EL control (e.g, TRVICTLR, TRCACTRn). + * The Secure and Non-Secure ELs are always to gether. + * Non-secure EL3 is never implemented. + * We use the following generic mask as they appear in different + * registers and this can be shifted for the appropriate + * fields. + */ +#define ETM_EXLEVEL_S_APP BIT(0) /* Secure EL0 */ +#define ETM_EXLEVEL_S_OS BIT(1) /* Secure EL1 */ +#define ETM_EXLEVEL_S_HYP BIT(2) /* Secure EL2 */ +#define ETM_EXLEVEL_S_MON BIT(3) /* Secure EL3/Monitor */ +#define ETM_EXLEVEL_NS_APP BIT(4) /* NonSecure EL0 */ +#define ETM_EXLEVEL_NS_OS BIT(5) /* NonSecure EL1 */ +#define ETM_EXLEVEL_NS_HYP BIT(6) /* NonSecure EL2 */ + +/* access level controls in TRCACATRn */ +#define TRCACATR_EXLEVEL_SHIFT 8 + +#define ETM_TRCIDR1_ARCH_MAJOR_SHIFT 8 +#define ETM_TRCIDR1_ARCH_MAJOR_MASK (0xfU << ETM_TRCIDR1_ARCH_MAJOR_SHIFT) +#define ETM_TRCIDR1_ARCH_MAJOR(x) \ + (((x) & ETM_TRCIDR1_ARCH_MAJOR_MASK) >> ETM_TRCIDR1_ARCH_MAJOR_SHIFT) +#define ETM_TRCIDR1_ARCH_MINOR_SHIFT 4 +#define ETM_TRCIDR1_ARCH_MINOR_MASK (0xfU << ETM_TRCIDR1_ARCH_MINOR_SHIFT) +#define ETM_TRCIDR1_ARCH_MINOR(x) \ + (((x) & ETM_TRCIDR1_ARCH_MINOR_MASK) >> ETM_TRCIDR1_ARCH_MINOR_SHIFT) +#define ETM_TRCIDR1_ARCH_SHIFT ETM_TRCIDR1_ARCH_MINOR_SHIFT +#define ETM_TRCIDR1_ARCH_MASK \ + (ETM_TRCIDR1_ARCH_MAJOR_MASK | ETM_TRCIDR1_ARCH_MINOR_MASK) + +#define ETM_TRCIDR1_ARCH_ETMv4 0x4 + +/* + * Driver representation of the ETM architecture. + * The version of an ETM component can be detected from + * + * TRCDEVARCH - CoreSight architected register + * - Bits[15:12] - Major version + * - Bits[19:16] - Minor version + * + * We must rely only on TRCDEVARCH for the version information. Even though, + * TRCIDR1 also provides the architecture version, it is a "Trace" register + * and as such must be accessed only with Trace power domain ON. This may + * not be available at probe time. + * + * Now to make certain decisions easier based on the version + * we use an internal representation of the version in the + * driver, as follows : + * + * ETM_ARCH_VERSION[7:0], where : + * Bits[7:4] - Major version + * Bits[3:0] - Minro version + */ +#define ETM_ARCH_VERSION(major, minor) \ + ((((major) & 0xfU) << 4) | (((minor) & 0xfU))) +#define ETM_ARCH_MAJOR_VERSION(arch) (((arch) >> 4) & 0xfU) +#define ETM_ARCH_MINOR_VERSION(arch) ((arch) & 0xfU) + +#define ETM_ARCH_V4 ETM_ARCH_VERSION(4, 0) +#define ETM_ARCH_ETE ETM_ARCH_VERSION(5, 0) + +/* Interpretation of resource numbers change at ETM v4.3 architecture */ +#define ETM_ARCH_V4_3 ETM_ARCH_VERSION(4, 3) + +static inline u8 etm_devarch_to_arch(u32 devarch) +{ + return ETM_ARCH_VERSION(ETM_DEVARCH_ARCHID_ARCH_VER(devarch), + ETM_DEVARCH_REVISION(devarch)); +} + +enum etm_impdef_type { + ETM4_IMPDEF_HISI_CORE_COMMIT, + ETM4_IMPDEF_FEATURE_MAX, +}; /** * struct etmv4_config - configuration information related to an ETMv4 @@ -221,6 +798,7 @@ * @cntr_val: Sets or returns the value for a counter. * @res_idx: Resource index selector. * @res_ctrl: Controls the selection of the resources in the trace unit. + * @ss_idx: Single-shot index selector. * @ss_ctrl: Controls the corresponding single-shot comparator resource. * @ss_status: The status of the corresponding single-shot comparator. * @ss_pe_cmp: Selects the PE comparator inputs for Single-shot control. @@ -237,9 +815,10 @@ * @vmid_mask0: VM ID comparator mask for comparator 0-3. * @vmid_mask1: VM ID comparator mask for comparator 4-7. * @ext_inp: External input selection. + * @s_ex_level: Secure ELs where tracing is supported. */ struct etmv4_config { - u32 mode; + u64 mode; u32 pe_sel; u32 cfg; u32 eventctrl0; @@ -263,6 +842,7 @@ struct etmv4_config { u32 cntr_val[ETMv4_MAX_CNTR]; u8 res_idx; u32 res_ctrl[ETM_MAX_RES_SEL]; + u8 ss_idx; u32 ss_ctrl[ETM_MAX_SS_CMP]; u32 ss_status[ETM_MAX_SS_CMP]; u32 ss_pe_cmp[ETM_MAX_SS_CMP]; @@ -279,17 +859,74 @@ struct etmv4_config { u32 vmid_mask0; u32 vmid_mask1; u32 ext_inp; + u8 s_ex_level; +}; + +/** + * struct etm4_save_state - state to be preserved when ETM is without power + */ +struct etmv4_save_state { + u32 trcprocselr; + u32 trcconfigr; + u32 trcauxctlr; + u32 trceventctl0r; + u32 trceventctl1r; + u32 trcstallctlr; + u32 trctsctlr; + u32 trcsyncpr; + u32 trcccctlr; + u32 trcbbctlr; + u32 trctraceidr; + u32 trcqctlr; + + u32 trcvictlr; + u32 trcviiectlr; + u32 trcvissctlr; + u32 trcvipcssctlr; + + u32 trcseqevr[ETM_MAX_SEQ_STATES]; + u32 trcseqrstevr; + u32 trcseqstr; + u32 trcextinselr; + u32 trccntrldvr[ETMv4_MAX_CNTR]; + u32 trccntctlr[ETMv4_MAX_CNTR]; + u32 trccntvr[ETMv4_MAX_CNTR]; + + u32 trcrsctlr[ETM_MAX_RES_SEL]; + + u32 trcssccr[ETM_MAX_SS_CMP]; + u32 trcsscsr[ETM_MAX_SS_CMP]; + u32 trcsspcicr[ETM_MAX_SS_CMP]; + + u64 trcacvr[ETM_MAX_SINGLE_ADDR_CMP]; + u64 trcacatr[ETM_MAX_SINGLE_ADDR_CMP]; + u64 trccidcvr[ETMv4_MAX_CTXID_CMP]; + u64 trcvmidcvr[ETM_MAX_VMID_CMP]; + u32 trccidcctlr0; + u32 trccidcctlr1; + u32 trcvmidcctlr0; + u32 trcvmidcctlr1; + + u32 trcclaimset; + + u32 cntr_val[ETMv4_MAX_CNTR]; + u32 seq_state; + u32 vinst_ctrl; + u32 ss_status[ETM_MAX_SS_CMP]; + + u32 trcpdcr; }; /** * struct etm4_drvdata - specifics associated to an ETM component + * @pclk: APB clock if present, otherwise NULL + * @atclk: Optional clock for the core parts of the ETMv4. * @base: Memory mapped base address for this component. - * @dev: The device entity associated to this component. * @csdev: Component vitals needed by the framework. * @spinlock: Only one at a time pls. * @mode: This tracer's mode, i.e sysFS, Perf or disabled. * @cpu: The cpu this component is affined to. - * @arch: ETM version number. + * @arch: ETM architecture version. * @nr_pe: The number of processing entity available for tracing. * @nr_pe_cmp: The number of processing entity comparator inputs that are * available for tracing. @@ -319,6 +956,7 @@ struct etmv4_config { * @os_unlock: True if access to management registers is allowed. * @instrp0: Tracing of load and store instructions * as P0 elements is supported. + * @q_filt: Q element filtering support, if Q elements are supported. * @trcbb: Indicates if the trace unit supports branch broadcast tracing. * @trccond: If the trace unit supports conditional * instruction tracing. @@ -336,14 +974,23 @@ struct etmv4_config { * @nooverflow: Indicate if overflow prevention is supported. * @atbtrig: If the implementation can support ATB triggers * @lpoverride: If the implementation can support low-power state over. + * @trfcr: If the CPU supports FEAT_TRF, value of the TRFCR_ELx that + * allows tracing at all ELs. We don't want to compute this + * at runtime, due to the additional setting of TRFCR_CX when + * in EL2. Otherwise, 0. * @config: structure holding configuration parameters. + * @save_state: State to be preserved across power loss + * @skip_power_up: Indicates if an implementation can skip powering up + * the trace unit. + * @paused: Indicates if the trace unit is paused. + * @arch_features: Bitmap of arch features of etmv4 devices. */ struct etmv4_drvdata { + struct clk *pclk; + struct clk *atclk; void __iomem *base; - struct device *dev; struct coresight_device *csdev; - spinlock_t spinlock; - local_t mode; + raw_spinlock_t spinlock; int cpu; u8 arch; u8 nr_pe; @@ -352,6 +999,7 @@ struct etmv4_drvdata { u8 nr_cntr; u8 nr_ext_inp; u8 numcidc; + u8 numextinsel; u8 numvmidc; u8 nrseqstate; u8 nr_event; @@ -363,14 +1011,16 @@ struct etmv4_drvdata { u8 ctxid_size; u8 vmid_size; u8 ccsize; - u8 ccitmin; + u16 ccitmin; u8 s_ex_level; u8 ns_ex_level; u8 q_support; + u8 os_lock_model; bool sticky_enable; bool boot_enable; bool os_unlock; bool instrp0; + bool q_filt; bool trcbb; bool trccond; bool retstack; @@ -382,15 +1032,20 @@ struct etmv4_drvdata { bool nooverflow; bool atbtrig; bool lpoverride; + u64 trfcr; struct etmv4_config config; + struct etmv4_save_state *save_state; + bool skip_power_up; + bool paused; + DECLARE_BITMAP(arch_features, ETM4_IMPDEF_FEATURE_MAX); }; /* Address comparator access types */ enum etm_addr_acctype { - ETM_INSTR_ADDR, - ETM_DATA_LOAD_ADDR, - ETM_DATA_STORE_ADDR, - ETM_DATA_LOAD_STORE_ADDR, + TRCACATRn_TYPE_ADDR, + TRCACATRn_TYPE_DATA_LOAD_ADDR, + TRCACATRn_TYPE_DATA_STORE_ADDR, + TRCACATRn_TYPE_DATA_LOAD_STORE_ADDR, }; /* Address comparator context types */ @@ -403,4 +1058,14 @@ enum etm_addr_ctxtype { extern const struct attribute_group *coresight_etmv4_groups[]; void etm4_config_trace_mode(struct etmv4_config *config); + +u64 etm4x_sysreg_read(u32 offset, bool _relaxed, bool _64bit); +void etm4x_sysreg_write(u64 val, u32 offset, bool _relaxed, bool _64bit); + +static inline bool etm4x_is_ete(struct etmv4_drvdata *drvdata) +{ + return drvdata->arch >= ETM_ARCH_ETE; +} + +void etm4_release_trace_id(struct etmv4_drvdata *drvdata); #endif diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 927925151509..3b248e54471a 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -5,6 +5,7 @@ * Description: CoreSight Funnel driver */ +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -12,6 +13,8 @@ #include <linux/err.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/of.h> +#include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/coresight.h> #include <linux/amba/bus.h> @@ -27,33 +30,38 @@ #define FUNNEL_HOLDTIME (0x7 << FUNNEL_HOLDTIME_SHFT) #define FUNNEL_ENSx_MASK 0xff +DEFINE_CORESIGHT_DEVLIST(funnel_devs, "funnel"); + /** * struct funnel_drvdata - specifics associated to a funnel component * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @atclk: optional clock for the core parts of the funnel. + * @pclk: APB clock if present, otherwise NULL * @csdev: component vitals needed by the framework. * @priority: port selection order. + * @spinlock: serialize enable/disable operations. */ struct funnel_drvdata { void __iomem *base; - struct device *dev; struct clk *atclk; + struct clk *pclk; struct coresight_device *csdev; unsigned long priority; + raw_spinlock_t spinlock; }; -static int funnel_enable_hw(struct funnel_drvdata *drvdata, int port) +static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port) { u32 functl; int rc = 0; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); functl = readl_relaxed(drvdata->base + FUNNEL_FUNCTL); /* Claim the device only when we enable the first slave */ if (!(functl & FUNNEL_ENSx_MASK)) { - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; } @@ -68,22 +76,37 @@ done: return rc; } -static int funnel_enable(struct coresight_device *csdev, int inport, - int outport) +static int funnel_enable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) { - int rc; + int rc = 0; struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - rc = funnel_enable_hw(drvdata, inport); - + unsigned long flags; + bool first_enable = false; + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (in->dest_refcnt == 0) { + if (drvdata->base) + rc = dynamic_funnel_enable_hw(drvdata, in->dest_port); + if (!rc) + first_enable = true; + } if (!rc) - dev_dbg(drvdata->dev, "FUNNEL inport %d enabled\n", inport); + in->dest_refcnt++; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + if (first_enable) + dev_dbg(&csdev->dev, "FUNNEL inport %d enabled\n", + in->dest_port); return rc; } -static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) +static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, + int inport) { u32 functl; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); @@ -93,19 +116,30 @@ static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) /* Disclaim the device if none of the slaves are now active */ if (!(functl & FUNNEL_ENSx_MASK)) - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } -static void funnel_disable(struct coresight_device *csdev, int inport, - int outport) +static void funnel_disable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) { struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + bool last_disable = false; + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (--in->dest_refcnt == 0) { + if (drvdata->base) + dynamic_funnel_disable_hw(drvdata, in->dest_port); + last_disable = true; + } + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); - funnel_disable_hw(drvdata, inport); - - dev_dbg(drvdata->dev, "FUNNEL inport %d disabled\n", inport); + if (last_disable) + dev_dbg(&csdev->dev, "FUNNEL inport %d disabled\n", + in->dest_port); } static const struct coresight_ops_link funnel_link_ops = { @@ -160,11 +194,11 @@ static ssize_t funnel_ctrl_show(struct device *dev, u32 val; struct funnel_drvdata *drvdata = dev_get_drvdata(dev->parent); - pm_runtime_get_sync(drvdata->dev); + pm_runtime_get_sync(dev->parent); val = get_funnel_ctrl_hw(drvdata); - pm_runtime_put(drvdata->dev); + pm_runtime_put(dev->parent); return sprintf(buf, "%#x\n", val); } @@ -177,54 +211,72 @@ static struct attribute *coresight_funnel_attrs[] = { }; ATTRIBUTE_GROUPS(coresight_funnel); -static int funnel_probe(struct amba_device *adev, const struct amba_id *id) +static int funnel_probe(struct device *dev, struct resource *res) { - int ret; void __iomem *base; - struct device *dev = &adev->dev; struct coresight_platform_data *pdata = NULL; struct funnel_drvdata *drvdata; - struct resource *res = &adev->res; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; + int ret; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } + if (is_of_node(dev_fwnode(dev)) && + of_device_is_compatible(dev->of_node, "arm,coresight-funnel")) + dev_warn_once(dev, "Uses OBSOLETE CoreSight funnel binding\n"); + + desc.name = coresight_alloc_device_name(&funnel_devs, dev); + if (!desc.name) + return -ENOMEM; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + + /* + * Map the device base for dynamic-funnel, which has been + * validated by AMBA core. + */ + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + drvdata->base = base; + desc.groups = coresight_funnel_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); + coresight_clear_self_claim_tag(&desc.access); } + dev_set_drvdata(dev, drvdata); - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); - drvdata->base = base; - pm_runtime_put(&adev->dev); + dev->platform_data = pdata; + raw_spin_lock_init(&drvdata->spinlock); desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG; desc.ops = &funnel_cs_ops; desc.pdata = pdata; desc.dev = dev; - desc.groups = coresight_funnel_groups; drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); - return PTR_ERR_OR_ZERO(drvdata->csdev); + return 0; +} + +static int funnel_remove(struct device *dev) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); + + return 0; } #ifdef CONFIG_PM @@ -232,8 +284,8 @@ static int funnel_runtime_suspend(struct device *dev) { struct funnel_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); return 0; } @@ -241,11 +293,17 @@ static int funnel_runtime_suspend(struct device *dev) static int funnel_runtime_resume(struct device *dev) { struct funnel_drvdata *drvdata = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); - return 0; + return ret; } #endif @@ -253,7 +311,82 @@ static const struct dev_pm_ops funnel_dev_pm_ops = { SET_RUNTIME_PM_OPS(funnel_runtime_suspend, funnel_runtime_resume, NULL) }; -static const struct amba_id funnel_ids[] = { +static int funnel_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = funnel_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void funnel_platform_remove(struct platform_device *pdev) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + funnel_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +static const struct of_device_id funnel_match[] = { + {.compatible = "arm,coresight-static-funnel"}, + {} +}; + +MODULE_DEVICE_TABLE(of, funnel_match); + +#ifdef CONFIG_ACPI +static const struct acpi_device_id funnel_acpi_ids[] = { + {"ARMHC9FE", 0, 0, 0}, /* ARM Coresight Static Funnel */ + {"ARMHC9FF", 0, 0, 0}, /* ARM CoreSight Dynamic Funnel */ + {}, +}; + +MODULE_DEVICE_TABLE(acpi, funnel_acpi_ids); +#endif + +static struct platform_driver funnel_driver = { + .probe = funnel_platform_probe, + .remove = funnel_platform_remove, + .driver = { + .name = "coresight-funnel", + /* THIS_MODULE is taken care of by platform_driver_register() */ + .of_match_table = funnel_match, + .acpi_match_table = ACPI_PTR(funnel_acpi_ids), + .pm = &funnel_dev_pm_ops, + .suppress_bind_attrs = true, + }, +}; + +static int dynamic_funnel_probe(struct amba_device *adev, + const struct amba_id *id) +{ + int ret; + + ret = funnel_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void dynamic_funnel_remove(struct amba_device *adev) +{ + funnel_remove(&adev->dev); +} + +static const struct amba_id dynamic_funnel_ids[] = { { .id = 0x000bb908, .mask = 0x000fffff, @@ -263,17 +396,37 @@ static const struct amba_id funnel_ids[] = { .id = 0x000bb9eb, .mask = 0x000fffff, }, - { 0, 0}, + { 0, 0, NULL }, }; -static struct amba_driver funnel_driver = { +MODULE_DEVICE_TABLE(amba, dynamic_funnel_ids); + +static struct amba_driver dynamic_funnel_driver = { .drv = { - .name = "coresight-funnel", - .owner = THIS_MODULE, + .name = "coresight-dynamic-funnel", .pm = &funnel_dev_pm_ops, .suppress_bind_attrs = true, }, - .probe = funnel_probe, - .id_table = funnel_ids, + .probe = dynamic_funnel_probe, + .remove = dynamic_funnel_remove, + .id_table = dynamic_funnel_ids, }; -builtin_amba_driver(funnel_driver); + +static int __init funnel_init(void) +{ + return coresight_init_driver("funnel", &dynamic_funnel_driver, &funnel_driver, + THIS_MODULE); +} + +static void __exit funnel_exit(void) +{ + coresight_remove_driver(&dynamic_funnel_driver, &funnel_driver); +} + +module_init(funnel_init); +module_exit(funnel_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight Funnel Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-kunit-tests.c b/drivers/hwtracing/coresight/coresight-kunit-tests.c new file mode 100644 index 000000000000..c8f361767c45 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-kunit-tests.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <kunit/test.h> +#include <kunit/device.h> +#include <linux/coresight.h> + +#include "coresight-priv.h" + +static struct coresight_device *coresight_test_device(struct device *dev) +{ + struct coresight_device *csdev = devm_kcalloc(dev, 1, + sizeof(struct coresight_device), + GFP_KERNEL); + csdev->pdata = devm_kcalloc(dev, 1, + sizeof(struct coresight_platform_data), + GFP_KERNEL); + return csdev; +} + +static void test_default_sink(struct kunit *test) +{ + /* + * Source -> ETF -> ETR -> CATU + * ^ + * | default + */ + struct device *dev = kunit_device_register(test, "coresight_kunit"); + struct coresight_device *src = coresight_test_device(dev), + *etf = coresight_test_device(dev), + *etr = coresight_test_device(dev), + *catu = coresight_test_device(dev); + struct coresight_connection conn = {}; + + src->type = CORESIGHT_DEV_TYPE_SOURCE; + /* + * Don't use CORESIGHT_DEV_SUBTYPE_SOURCE_PROC, that would always return + * a TRBE sink if one is registered. + */ + src->subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_BUS; + etf->type = CORESIGHT_DEV_TYPE_LINKSINK; + etf->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + etr->type = CORESIGHT_DEV_TYPE_SINK; + etr->subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM; + catu->type = CORESIGHT_DEV_TYPE_HELPER; + + conn.src_dev = src; + conn.dest_dev = etf; + coresight_add_out_conn(dev, src->pdata, &conn); + + conn.src_dev = etf; + conn.dest_dev = etr; + coresight_add_out_conn(dev, etf->pdata, &conn); + + conn.src_dev = etr; + conn.dest_dev = catu; + coresight_add_out_conn(dev, etr->pdata, &conn); + + KUNIT_ASSERT_PTR_EQ(test, coresight_find_default_sink(src), etr); +} + +static struct kunit_case coresight_testcases[] = { + KUNIT_CASE(test_default_sink), + {} +}; + +static struct kunit_suite coresight_test_suite = { + .name = "coresight_test_suite", + .test_cases = coresight_testcases, +}; + +kunit_test_suites(&coresight_test_suite); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("James Clark <james.clark@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight KUnit tests"); diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c new file mode 100644 index 000000000000..0db64c5f4995 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -0,0 +1,855 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2012, The Linux Foundation. All rights reserved. + */ + +#include <linux/acpi.h> +#include <linux/types.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/clk.h> +#include <linux/of.h> +#include <linux/of_graph.h> +#include <linux/platform_device.h> +#include <linux/amba/bus.h> +#include <linux/coresight.h> +#include <linux/cpumask.h> +#include <asm/smp_plat.h> + +#include "coresight-priv.h" + +/* + * Add an entry to the connection list and assign @conn's contents to it. + * + * If the output port is already assigned on this device, return -EINVAL + */ +struct coresight_connection * +coresight_add_out_conn(struct device *dev, + struct coresight_platform_data *pdata, + const struct coresight_connection *new_conn) +{ + int i; + struct coresight_connection *conn; + + /* + * Warn on any existing duplicate output port. + */ + for (i = 0; i < pdata->nr_outconns; ++i) { + conn = pdata->out_conns[i]; + /* Output == -1 means ignore the port for example for helpers */ + if (conn->src_port != -1 && + conn->src_port == new_conn->src_port) { + dev_warn(dev, "Duplicate output port %d\n", + conn->src_port); + return ERR_PTR(-EINVAL); + } + } + + pdata->nr_outconns++; + pdata->out_conns = + devm_krealloc_array(dev, pdata->out_conns, pdata->nr_outconns, + sizeof(*pdata->out_conns), GFP_KERNEL); + if (!pdata->out_conns) + return ERR_PTR(-ENOMEM); + + conn = devm_kmalloc(dev, sizeof(struct coresight_connection), + GFP_KERNEL); + if (!conn) + return ERR_PTR(-ENOMEM); + + /* + * Copy the new connection into the allocation, save the pointer to the + * end of the connection array and also return it in case it needs to be + * used right away. + */ + *conn = *new_conn; + pdata->out_conns[pdata->nr_outconns - 1] = conn; + return conn; +} +EXPORT_SYMBOL_GPL(coresight_add_out_conn); + +/* + * Add an input connection reference to @out_conn in the target's in_conns array + * + * @out_conn: Existing output connection to store as an input on the + * connection's remote device. + */ +int coresight_add_in_conn(struct coresight_connection *out_conn) +{ + int i; + struct device *dev = out_conn->dest_dev->dev.parent; + struct coresight_platform_data *pdata = out_conn->dest_dev->pdata; + + for (i = 0; i < pdata->nr_inconns; ++i) + if (!pdata->in_conns[i]) { + pdata->in_conns[i] = out_conn; + return 0; + } + + pdata->nr_inconns++; + pdata->in_conns = + devm_krealloc_array(dev, pdata->in_conns, pdata->nr_inconns, + sizeof(*pdata->in_conns), GFP_KERNEL); + if (!pdata->in_conns) + return -ENOMEM; + pdata->in_conns[pdata->nr_inconns - 1] = out_conn; + return 0; +} +EXPORT_SYMBOL_GPL(coresight_add_in_conn); + +static struct device * +coresight_find_device_by_fwnode(struct fwnode_handle *fwnode) +{ + struct device *dev = NULL; + + /* + * If we have a non-configurable replicator, it will be found on the + * platform bus. + */ + dev = bus_find_device_by_fwnode(&platform_bus_type, fwnode); + if (dev) + return dev; + + /* + * We have a configurable component - circle through the AMBA bus + * looking for the device that matches the endpoint node. + */ + return bus_find_device_by_fwnode(&amba_bustype, fwnode); +} + +/* + * Find a registered coresight device from a device fwnode. + * The node info is associated with the AMBA parent, but the + * csdev keeps a copy so iterate round the coresight bus to + * find the device. + */ +struct coresight_device * +coresight_find_csdev_by_fwnode(struct fwnode_handle *r_fwnode) +{ + struct device *dev; + struct coresight_device *csdev = NULL; + + dev = bus_find_device_by_fwnode(&coresight_bustype, r_fwnode); + if (dev) { + csdev = to_coresight_device(dev); + put_device(dev); + } + return csdev; +} +EXPORT_SYMBOL_GPL(coresight_find_csdev_by_fwnode); + +#ifdef CONFIG_OF +static bool of_coresight_legacy_ep_is_input(struct device_node *ep) +{ + return of_property_read_bool(ep, "slave-mode"); +} + +static struct device_node *of_coresight_get_port_parent(struct device_node *ep) +{ + struct device_node *parent = of_graph_get_port_parent(ep); + + /* + * Skip one-level up to the real device node, if we + * are using the new bindings. + */ + if (of_node_name_eq(parent, "in-ports") || + of_node_name_eq(parent, "out-ports")) + parent = of_get_next_parent(parent); + + return parent; +} + +static struct device_node * +of_coresight_get_output_ports_node(const struct device_node *node) +{ + return of_get_child_by_name(node, "out-ports"); +} + +static int of_coresight_get_cpu(struct device *dev) +{ + int cpu; + struct device_node *dn; + + if (!dev->of_node) + return -ENODEV; + + dn = of_parse_phandle(dev->of_node, "cpu", 0); + if (!dn) + return -ENODEV; + + cpu = of_cpu_node_to_id(dn); + of_node_put(dn); + + return cpu; +} + +/* + * of_coresight_parse_endpoint : Parse the given output endpoint @ep + * and fill the connection information in @pdata->out_conns + * + * Parses the local port, remote device name and the remote port. + * + * Returns : + * 0 - If the parsing completed without any fatal errors. + * -Errno - Fatal error, abort the scanning. + */ +static int of_coresight_parse_endpoint(struct device *dev, + struct device_node *ep, + struct coresight_platform_data *pdata) +{ + int ret = 0; + struct of_endpoint endpoint, rendpoint; + struct device_node *rparent = NULL; + struct device_node *rep = NULL; + struct device *rdev = NULL; + struct fwnode_handle *rdev_fwnode; + struct coresight_connection conn = {}; + struct coresight_connection *new_conn; + + do { + /* Parse the local port details */ + if (of_graph_parse_endpoint(ep, &endpoint)) + break; + /* + * Get a handle on the remote endpoint and the device it is + * attached to. + */ + rep = of_graph_get_remote_endpoint(ep); + if (!rep) + break; + rparent = of_coresight_get_port_parent(rep); + if (!rparent) + break; + if (of_graph_parse_endpoint(rep, &rendpoint)) + break; + + rdev_fwnode = of_fwnode_handle(rparent); + /* If the remote device is not available, defer probing */ + rdev = coresight_find_device_by_fwnode(rdev_fwnode); + if (!rdev) { + ret = -EPROBE_DEFER; + break; + } + + conn.src_port = endpoint.port; + /* + * Hold the refcount to the target device. This could be + * released via: + * 1) coresight_release_platform_data() if the probe fails or + * this device is unregistered. + * 2) While removing the target device via + * coresight_remove_match() + */ + conn.dest_fwnode = fwnode_handle_get(rdev_fwnode); + conn.dest_port = rendpoint.port; + + /* + * Get the firmware node of the filter source through the + * reference. This could be used to filter the source in + * building path. + */ + conn.filter_src_fwnode = + fwnode_find_reference(&ep->fwnode, "filter-source", 0); + if (IS_ERR(conn.filter_src_fwnode)) { + conn.filter_src_fwnode = NULL; + } else { + conn.filter_src_dev = + coresight_find_csdev_by_fwnode(conn.filter_src_fwnode); + if (conn.filter_src_dev && + !coresight_is_device_source(conn.filter_src_dev)) { + dev_warn(dev, "port %d: Filter handle is not a trace source : %s\n", + conn.src_port, dev_name(&conn.filter_src_dev->dev)); + conn.filter_src_dev = NULL; + conn.filter_src_fwnode = NULL; + } + } + + new_conn = coresight_add_out_conn(dev, pdata, &conn); + if (IS_ERR_VALUE(new_conn)) { + fwnode_handle_put(conn.dest_fwnode); + return PTR_ERR(new_conn); + } + /* Connection record updated */ + } while (0); + + of_node_put(rparent); + of_node_put(rep); + put_device(rdev); + + return ret; +} + +static int of_get_coresight_platform_data(struct device *dev, + struct coresight_platform_data *pdata) +{ + int ret = 0; + struct device_node *ep = NULL; + const struct device_node *parent = NULL; + bool legacy_binding = false; + struct device_node *node = dev->of_node; + + parent = of_coresight_get_output_ports_node(node); + /* + * If the DT uses obsoleted bindings, the ports are listed + * under the device and we need to filter out the input + * ports. + */ + if (!parent) { + /* + * Avoid warnings in for_each_endpoint_of_node() + * if the device doesn't have any graph connections + */ + if (!of_graph_is_present(node)) + return 0; + legacy_binding = true; + parent = node; + dev_warn_once(dev, "Uses obsolete Coresight DT bindings\n"); + } + + /* Iterate through each output port to discover topology */ + for_each_endpoint_of_node(parent, ep) { + /* + * Legacy binding mixes input/output ports under the + * same parent. So, skip the input ports if we are dealing + * with legacy binding, as they processed with their + * connected output ports. + */ + if (legacy_binding && of_coresight_legacy_ep_is_input(ep)) + continue; + + ret = of_coresight_parse_endpoint(dev, ep, pdata); + if (ret) { + of_node_put(ep); + return ret; + } + } + + return 0; +} +#else +static int +of_get_coresight_platform_data(struct device *dev, + struct coresight_platform_data *pdata) +{ + return -ENOENT; +} + +static int of_coresight_get_cpu(struct device *dev) +{ + return -ENODEV; +} +#endif + +#ifdef CONFIG_ACPI + +#include <acpi/actypes.h> +#include <acpi/processor.h> + +/* ACPI Graph _DSD UUID : "ab02a46b-74c7-45a2-bd68-f7d344ef2153" */ +static const guid_t acpi_graph_uuid = GUID_INIT(0xab02a46b, 0x74c7, 0x45a2, + 0xbd, 0x68, 0xf7, 0xd3, + 0x44, 0xef, 0x21, 0x53); +/* Coresight ACPI Graph UUID : "3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd" */ +static const guid_t coresight_graph_uuid = GUID_INIT(0x3ecbc8b6, 0x1d0e, 0x4fb3, + 0x81, 0x07, 0xe6, 0x27, + 0xf8, 0x05, 0xc6, 0xcd); +#define ACPI_CORESIGHT_LINK_SLAVE 0 +#define ACPI_CORESIGHT_LINK_MASTER 1 + +static bool is_acpi_guid(const union acpi_object *obj) +{ + return (obj->type == ACPI_TYPE_BUFFER) && (obj->buffer.length == 16); +} + +/* + * acpi_guid_matches - Checks if the given object is a GUID object and + * that it matches the supplied the GUID. + */ +static bool acpi_guid_matches(const union acpi_object *obj, + const guid_t *guid) +{ + return is_acpi_guid(obj) && + guid_equal((guid_t *)obj->buffer.pointer, guid); +} + +static bool is_acpi_dsd_graph_guid(const union acpi_object *obj) +{ + return acpi_guid_matches(obj, &acpi_graph_uuid); +} + +static bool is_acpi_coresight_graph_guid(const union acpi_object *obj) +{ + return acpi_guid_matches(obj, &coresight_graph_uuid); +} + +static bool is_acpi_coresight_graph(const union acpi_object *obj) +{ + const union acpi_object *graphid, *guid, *links; + + if (obj->type != ACPI_TYPE_PACKAGE || + obj->package.count < 3) + return false; + + graphid = &obj->package.elements[0]; + guid = &obj->package.elements[1]; + links = &obj->package.elements[2]; + + if (graphid->type != ACPI_TYPE_INTEGER || + links->type != ACPI_TYPE_INTEGER) + return false; + + return is_acpi_coresight_graph_guid(guid); +} + +/* + * acpi_validate_dsd_graph - Make sure the given _DSD graph conforms + * to the ACPI _DSD Graph specification. + * + * ACPI Devices Graph property has the following format: + * { + * Revision - Integer, must be 0 + * NumberOfGraphs - Integer, N indicating the following list. + * Graph[1], + * ... + * Graph[N] + * } + * + * And each Graph entry has the following format: + * { + * GraphID - Integer, identifying a graph the device belongs to. + * UUID - UUID identifying the specification that governs + * this graph. (e.g, see is_acpi_coresight_graph()) + * NumberOfLinks - Number "N" of connections on this node of the graph. + * Links[1] + * ... + * Links[N] + * } + * + * Where each "Links" entry has the following format: + * + * { + * SourcePortAddress - Integer + * DestinationPortAddress - Integer + * DestinationDeviceName - Reference to another device + * ( --- CoreSight specific extensions below ---) + * DirectionOfFlow - Integer 1 for output(master) + * 0 for input(slave) + * } + * + * e.g: + * For a Funnel device + * + * Device(MFUN) { + * ... + * + * Name (_DSD, Package() { + * // DSD Package contains tuples of { Proeprty_Type_UUID, Package() } + * ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), //Std. Property UUID + * Package() { + * Package(2) { "property-name", <property-value> } + * }, + * + * ToUUID("ab02a46b-74c7-45a2-bd68-f7d344ef2153"), // ACPI Graph UUID + * Package() { + * 0, // Revision + * 1, // NumberOfGraphs. + * Package() { // Graph[0] Package + * 1, // GraphID + * // Coresight Graph UUID + * ToUUID("3ecbc8b6-1d0e-4fb3-8107-e627f805c6cd"), + * 3, // NumberOfLinks aka ports + * // Link[0]: Output_0 -> Replicator:Input_0 + * Package () { 0, 0, \_SB_.RPL0, 1 }, + * // Link[1]: Input_0 <- Cluster0_Funnel0:Output_0 + * Package () { 0, 0, \_SB_.CLU0.FUN0, 0 }, + * // Link[2]: Input_1 <- Cluster1_Funnel0:Output_0 + * Package () { 1, 0, \_SB_.CLU1.FUN0, 0 }, + * } // End of Graph[0] Package + * + * }, // End of ACPI Graph Property + * }) + */ +static bool acpi_validate_dsd_graph(const union acpi_object *graph) +{ + int i, n; + const union acpi_object *rev, *nr_graphs; + + /* The graph must contain at least the Revision and Number of Graphs */ + if (graph->package.count < 2) + return false; + + rev = &graph->package.elements[0]; + nr_graphs = &graph->package.elements[1]; + + if (rev->type != ACPI_TYPE_INTEGER || + nr_graphs->type != ACPI_TYPE_INTEGER) + return false; + + /* We only support revision 0 */ + if (rev->integer.value != 0) + return false; + + n = nr_graphs->integer.value; + /* CoreSight devices are only part of a single Graph */ + if (n != 1) + return false; + + /* Make sure the ACPI graph package has right number of elements */ + if (graph->package.count != (n + 2)) + return false; + + /* + * Each entry must be a graph package with at least 3 members : + * { GraphID, UUID, NumberOfLinks(n), Links[.],... } + */ + for (i = 2; i < n + 2; i++) { + const union acpi_object *obj = &graph->package.elements[i]; + + if (obj->type != ACPI_TYPE_PACKAGE || + obj->package.count < 3) + return false; + } + + return true; +} + +/* acpi_get_dsd_graph - Find the _DSD Graph property for the given device. */ +static const union acpi_object * +acpi_get_dsd_graph(struct acpi_device *adev, struct acpi_buffer *buf) +{ + int i; + acpi_status status; + const union acpi_object *dsd; + + status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, + buf, ACPI_TYPE_PACKAGE); + if (ACPI_FAILURE(status)) + return NULL; + + dsd = buf->pointer; + + /* + * _DSD property consists tuples { Prop_UUID, Package() } + * Iterate through all the packages and find the Graph. + */ + for (i = 0; i + 1 < dsd->package.count; i += 2) { + const union acpi_object *guid, *package; + + guid = &dsd->package.elements[i]; + package = &dsd->package.elements[i + 1]; + + /* All _DSD elements must have a UUID and a Package */ + if (!is_acpi_guid(guid) || package->type != ACPI_TYPE_PACKAGE) + break; + /* Skip the non-Graph _DSD packages */ + if (!is_acpi_dsd_graph_guid(guid)) + continue; + if (acpi_validate_dsd_graph(package)) + return package; + /* Invalid graph format, continue */ + dev_warn(&adev->dev, "Invalid Graph _DSD property\n"); + } + + return NULL; +} + +static bool +acpi_validate_coresight_graph(const union acpi_object *cs_graph) +{ + int nlinks; + + nlinks = cs_graph->package.elements[2].integer.value; + /* + * Graph must have the following fields : + * { GraphID, GraphUUID, NumberOfLinks, Links... } + */ + if (cs_graph->package.count != (nlinks + 3)) + return false; + /* The links are validated in acpi_coresight_parse_link() */ + return true; +} + +/* + * acpi_get_coresight_graph - Parse the device _DSD tables and find + * the Graph property matching the CoreSight Graphs. + * + * Returns the pointer to the CoreSight Graph Package when found. Otherwise + * returns NULL. + */ +static const union acpi_object * +acpi_get_coresight_graph(struct acpi_device *adev, struct acpi_buffer *buf) +{ + const union acpi_object *graph_list, *graph; + int i, nr_graphs; + + graph_list = acpi_get_dsd_graph(adev, buf); + if (!graph_list) + return graph_list; + + nr_graphs = graph_list->package.elements[1].integer.value; + + for (i = 2; i < nr_graphs + 2; i++) { + graph = &graph_list->package.elements[i]; + if (!is_acpi_coresight_graph(graph)) + continue; + if (acpi_validate_coresight_graph(graph)) + return graph; + /* Invalid graph format */ + break; + } + + return NULL; +} + +/* + * acpi_coresight_parse_link - Parse the given Graph connection + * of the device and populate the coresight_connection for an output + * connection. + * + * CoreSight Graph specification mandates that the direction of the data + * flow must be specified in the link. i.e, + * + * SourcePortAddress, // Integer + * DestinationPortAddress, // Integer + * DestinationDeviceName, // Reference to another device + * DirectionOfFlow, // 1 for output(master), 0 for input(slave) + * + * Returns the direction of the data flow [ Input(slave) or Output(master) ] + * upon success. + * Returns an negative error number otherwise. + */ +static int acpi_coresight_parse_link(struct acpi_device *adev, + const union acpi_object *link, + struct coresight_connection *conn) +{ + int dir; + const union acpi_object *fields; + struct acpi_device *r_adev; + struct device *rdev; + + if (link->type != ACPI_TYPE_PACKAGE || + link->package.count != 4) + return -EINVAL; + + fields = link->package.elements; + + if (fields[0].type != ACPI_TYPE_INTEGER || + fields[1].type != ACPI_TYPE_INTEGER || + fields[2].type != ACPI_TYPE_LOCAL_REFERENCE || + fields[3].type != ACPI_TYPE_INTEGER) + return -EINVAL; + + r_adev = acpi_fetch_acpi_dev(fields[2].reference.handle); + if (!r_adev) + return -ENODEV; + + dir = fields[3].integer.value; + if (dir == ACPI_CORESIGHT_LINK_MASTER) { + conn->src_port = fields[0].integer.value; + conn->dest_port = fields[1].integer.value; + rdev = coresight_find_device_by_fwnode(&r_adev->fwnode); + if (!rdev) + return -EPROBE_DEFER; + /* + * Hold the refcount to the target device. This could be + * released via: + * 1) coresight_release_platform_data() if the probe fails or + * this device is unregistered. + * 2) While removing the target device via + * coresight_remove_match(). + */ + conn->dest_fwnode = fwnode_handle_get(&r_adev->fwnode); + } else if (dir == ACPI_CORESIGHT_LINK_SLAVE) { + /* + * We are only interested in the port number + * for the input ports at this component. + * Store the port number in child_port. + */ + conn->dest_port = fields[0].integer.value; + } else { + /* Invalid direction */ + return -EINVAL; + } + + return dir; +} + +/* + * acpi_coresight_parse_graph - Parse the _DSD CoreSight graph + * connection information and populate the supplied coresight_platform_data + * instance. + */ +static int acpi_coresight_parse_graph(struct device *dev, + struct acpi_device *adev, + struct coresight_platform_data *pdata) +{ + int ret = 0; + int i, nlinks; + const union acpi_object *graph; + struct coresight_connection conn, zero_conn = {}; + struct coresight_connection *new_conn; + struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL }; + + graph = acpi_get_coresight_graph(adev, &buf); + /* + * There are no graph connections, which is fine for some components. + * e.g., ETE + */ + if (!graph) + goto free; + + nlinks = graph->package.elements[2].integer.value; + if (!nlinks) + goto free; + + for (i = 0; i < nlinks; i++) { + const union acpi_object *link = &graph->package.elements[3 + i]; + int dir; + + conn = zero_conn; + dir = acpi_coresight_parse_link(adev, link, &conn); + if (dir < 0) { + ret = dir; + goto free; + } + + if (dir == ACPI_CORESIGHT_LINK_MASTER) { + new_conn = coresight_add_out_conn(dev, pdata, &conn); + if (IS_ERR(new_conn)) { + ret = PTR_ERR(new_conn); + goto free; + } + } + } + +free: + /* + * When ACPI fails to alloc a buffer, it will free the buffer + * created via ACPI_ALLOCATE_BUFFER and set to NULL. + * ACPI_FREE can handle NULL pointers, so free it directly. + */ + ACPI_FREE(buf.pointer); + return ret; +} + +/* + * acpi_handle_to_logical_cpuid - Map a given acpi_handle to the + * logical CPU id of the corresponding CPU device. + * + * Returns the logical CPU id when found. Otherwise returns >= nr_cpus_id. + */ +static int +acpi_handle_to_logical_cpuid(acpi_handle handle) +{ + int i; + struct acpi_processor *pr; + + for_each_possible_cpu(i) { + pr = per_cpu(processors, i); + if (pr && pr->handle == handle) + break; + } + + return i; +} + +/* + * acpi_coresigh_get_cpu - Find the logical CPU id of the CPU associated + * with this coresight device. With ACPI bindings, the CoreSight components + * are listed as child device of the associated CPU. + * + * Returns the logical CPU id when found. Otherwise returns 0. + */ +static int acpi_coresight_get_cpu(struct device *dev) +{ + int cpu; + acpi_handle cpu_handle; + acpi_status status; + struct acpi_device *adev = ACPI_COMPANION(dev); + + if (!adev) + return -ENODEV; + status = acpi_get_parent(adev->handle, &cpu_handle); + if (ACPI_FAILURE(status)) + return -ENODEV; + + cpu = acpi_handle_to_logical_cpuid(cpu_handle); + if (cpu >= nr_cpu_ids) + return -ENODEV; + return cpu; +} + +static int +acpi_get_coresight_platform_data(struct device *dev, + struct coresight_platform_data *pdata) +{ + struct acpi_device *adev; + + adev = ACPI_COMPANION(dev); + if (!adev) + return -EINVAL; + + return acpi_coresight_parse_graph(dev, adev, pdata); +} + +#else + +static int +acpi_get_coresight_platform_data(struct device *dev, + struct coresight_platform_data *pdata) +{ + return -ENOENT; +} + +static int acpi_coresight_get_cpu(struct device *dev) +{ + return -ENODEV; +} +#endif + +int coresight_get_cpu(struct device *dev) +{ + if (is_of_node(dev->fwnode)) + return of_coresight_get_cpu(dev); + else if (is_acpi_device_node(dev->fwnode)) + return acpi_coresight_get_cpu(dev); + return 0; +} +EXPORT_SYMBOL_GPL(coresight_get_cpu); + +int coresight_get_static_trace_id(struct device *dev, u32 *id) +{ + return fwnode_property_read_u32(dev_fwnode(dev), "arm,static-trace-id", id); +} +EXPORT_SYMBOL_GPL(coresight_get_static_trace_id); + +struct coresight_platform_data * +coresight_get_platform_data(struct device *dev) +{ + int ret = -ENOENT; + struct coresight_platform_data *pdata = NULL; + struct fwnode_handle *fwnode = dev_fwnode(dev); + + if (IS_ERR_OR_NULL(fwnode)) + goto error; + + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); + if (!pdata) { + ret = -ENOMEM; + goto error; + } + + if (is_of_node(fwnode)) + ret = of_get_coresight_platform_data(dev, pdata); + else if (is_acpi_device_node(fwnode)) + ret = acpi_get_coresight_platform_data(dev, pdata); + + if (!ret) + return pdata; +error: + if (!IS_ERR_OR_NULL(pdata)) + /* Cleanup the connection information */ + coresight_release_platform_data(NULL, dev, pdata); + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(coresight_get_platform_data); diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 579f34943bf1..fd896ac07942 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -6,11 +6,15 @@ #ifndef _CORESIGHT_PRIV_H #define _CORESIGHT_PRIV_H +#include <linux/amba/bus.h> #include <linux/bitops.h> #include <linux/io.h> #include <linux/coresight.h> #include <linux/pm_runtime.h> +extern struct mutex coresight_mutex; +extern const struct device_type coresight_dev_type[]; + /* * Coresight management registers (0xf00-0xfcc) * 0xfa0 - 0xfa4: Management registers in PFTv1.0 @@ -21,6 +25,7 @@ #define CORESIGHT_CLAIMCLR 0xfa4 #define CORESIGHT_LAR 0xfb0 #define CORESIGHT_LSR 0xfb4 +#define CORESIGHT_DEVARCH 0xfbc #define CORESIGHT_AUTHSTATUS 0xfb8 #define CORESIGHT_DEVID 0xfc8 #define CORESIGHT_DEVTYPE 0xfcc @@ -30,42 +35,52 @@ * Coresight device CLAIM protocol. * See PSCI - ARM DEN 0022D, Section: 6.8.1 Debug and Trace save and restore. */ -#define CORESIGHT_CLAIM_SELF_HOSTED BIT(1) +#define CORESIGHT_CLAIM_MASK GENMASK(1, 0) +#define CORESIGHT_CLAIM_FREE 0 +#define CORESIGHT_CLAIM_EXTERNAL 1 +#define CORESIGHT_CLAIM_SELF_HOSTED 2 +#define CORESIGHT_CLAIM_INVALID 3 #define TIMEOUT_US 100 #define BMVAL(val, lsb, msb) ((val & GENMASK(msb, lsb)) >> lsb) #define ETM_MODE_EXCL_KERN BIT(30) #define ETM_MODE_EXCL_USER BIT(31) +#define ETM_MODE_EXCL_HOST BIT(32) +#define ETM_MODE_EXCL_GUEST BIT(33) + +struct cs_pair_attribute { + struct device_attribute attr; + u32 lo_off; + u32 hi_off; +}; + +struct cs_off_attribute { + struct device_attribute attr; + u32 off; +}; -typedef u32 (*coresight_read_fn)(const struct device *, u32 offset); -#define __coresight_simple_func(type, func, name, lo_off, hi_off) \ -static ssize_t name##_show(struct device *_dev, \ - struct device_attribute *attr, char *buf) \ -{ \ - type *drvdata = dev_get_drvdata(_dev->parent); \ - coresight_read_fn fn = func; \ - u64 val; \ - pm_runtime_get_sync(_dev->parent); \ - if (fn) \ - val = (u64)fn(_dev->parent, lo_off); \ - else \ - val = coresight_read_reg_pair(drvdata->base, \ - lo_off, hi_off); \ - pm_runtime_put_sync(_dev->parent); \ - return scnprintf(buf, PAGE_SIZE, "0x%llx\n", val); \ -} \ -static DEVICE_ATTR_RO(name) - -#define coresight_simple_func(type, func, name, offset) \ - __coresight_simple_func(type, func, name, offset, -1) -#define coresight_simple_reg32(type, name, offset) \ - __coresight_simple_func(type, NULL, name, offset, -1) -#define coresight_simple_reg64(type, name, lo_off, hi_off) \ - __coresight_simple_func(type, NULL, name, lo_off, hi_off) - -extern const u32 barrier_pkt[4]; -#define CORESIGHT_BARRIER_PKT_SIZE (sizeof(barrier_pkt)) +ssize_t coresight_simple_show32(struct device *_dev, struct device_attribute *attr, char *buf); +ssize_t coresight_simple_show_pair(struct device *_dev, struct device_attribute *attr, char *buf); + +#define coresight_simple_reg32(name, offset) \ + (&((struct cs_off_attribute[]) { \ + { \ + __ATTR(name, 0444, coresight_simple_show32, NULL), \ + offset \ + } \ + })[0].attr.attr) + +#define coresight_simple_reg64(name, lo_off, hi_off) \ + (&((struct cs_pair_attribute[]) { \ + { \ + __ATTR(name, 0444, coresight_simple_show_pair, NULL), \ + lo_off, hi_off \ + } \ + })[0].attr.attr) + +extern const u32 coresight_barrier_pkt[4]; +#define CORESIGHT_BARRIER_PKT_SIZE (sizeof(coresight_barrier_pkt)) enum etm_addr_type { ETM_ADDR_TYPE_NONE, @@ -75,16 +90,11 @@ enum etm_addr_type { ETM_ADDR_TYPE_STOP, }; -enum cs_mode { - CS_MODE_DISABLED, - CS_MODE_SYSFS, - CS_MODE_PERF, -}; - /** * struct cs_buffer - keep track of a recording session' specifics * @cur: index of the current buffer * @nr_pages: max number of pages granted to us + * @pid: PID this cs_buffer belongs to * @offset: offset within the current buffer * @data_size: how much we collected in this run * @snapshot: is this run in snapshot mode @@ -93,6 +103,7 @@ enum cs_mode { struct cs_buffers { unsigned int cur; unsigned int nr_pages; + pid_t pid; unsigned long offset; local_t data_size; bool snapshot; @@ -102,10 +113,9 @@ struct cs_buffers { static inline void coresight_insert_barrier_packet(void *buf) { if (buf) - memcpy(buf, barrier_pkt, CORESIGHT_BARRIER_PKT_SIZE); + memcpy(buf, coresight_barrier_pkt, CORESIGHT_BARRIER_PKT_SIZE); } - static inline void CS_LOCK(void __iomem *addr) { do { @@ -124,39 +134,123 @@ static inline void CS_UNLOCK(void __iomem *addr) } while (0); } -static inline u64 -coresight_read_reg_pair(void __iomem *addr, s32 lo_offset, s32 hi_offset) +void coresight_disable_path(struct coresight_path *path); +int coresight_enable_path(struct coresight_path *path, enum cs_mode mode); +struct coresight_device *coresight_get_sink(struct coresight_path *path); +struct coresight_device *coresight_get_sink_by_id(u32 id); +struct coresight_device * +coresight_find_default_sink(struct coresight_device *csdev); +struct coresight_path *coresight_build_path(struct coresight_device *csdev, + struct coresight_device *sink); +void coresight_release_path(struct coresight_path *path); +int coresight_add_sysfs_link(struct coresight_sysfs_link *info); +void coresight_remove_sysfs_link(struct coresight_sysfs_link *info); +int coresight_create_conns_sysfs_group(struct coresight_device *csdev); +void coresight_remove_conns_sysfs_group(struct coresight_device *csdev); +int coresight_make_links(struct coresight_device *orig, + struct coresight_connection *conn, + struct coresight_device *target); +void coresight_remove_links(struct coresight_device *orig, + struct coresight_connection *conn); +u32 coresight_get_sink_id(struct coresight_device *csdev); +void coresight_path_assign_trace_id(struct coresight_path *path, + enum cs_mode mode); + +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X) +int etm_readl_cp14(u32 off, unsigned int *val); +int etm_writel_cp14(u32 off, u32 val); +#else +static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; } +static inline int etm_writel_cp14(u32 off, u32 val) { return 0; } +#endif + +struct cti_assoc_op { + void (*add)(struct coresight_device *csdev); + void (*remove)(struct coresight_device *csdev); +}; + +void coresight_set_cti_ops(const struct cti_assoc_op *cti_op); +void coresight_remove_cti_ops(void); + +/* + * Macros and inline functions to handle CoreSight UCI data and driver + * private data in AMBA ID table entries, and extract data values. + */ + +/* coresight AMBA ID, no UCI, no driver data: id table entry */ +#define CS_AMBA_ID(pid) \ + { \ + .id = pid, \ + .mask = 0x000fffff, \ + } + +/* coresight AMBA ID, UCI with driver data only: id table entry. */ +#define CS_AMBA_ID_DATA(pid, dval) \ + { \ + .id = pid, \ + .mask = 0x000fffff, \ + .data = (void *)&(struct amba_cs_uci_id) \ + { \ + .data = (void *)dval, \ + } \ + } + +/* coresight AMBA ID, full UCI structure: id table entry. */ +#define __CS_AMBA_UCI_ID(pid, m, uci_ptr) \ + { \ + .id = pid, \ + .mask = m, \ + .data = (void *)uci_ptr \ + } +#define CS_AMBA_UCI_ID(pid, uci) __CS_AMBA_UCI_ID(pid, 0x000fffff, uci) +/* + * PIDR2[JEDEC], BIT(3) must be 1 (Read As One) to indicate that rest of the + * PIDR1, PIDR2 DES_* fields follow JEDEC encoding for the designer. Use that + * as a match value for blanket matching all devices in the given CoreSight + * device type and architecture. + */ +#define PIDR2_JEDEC BIT(3) +#define PID_PIDR2_JEDEC (PIDR2_JEDEC << 16) +/* + * Match all PIDs in a given CoreSight device type and architecture, defined + * by the uci. + */ +#define CS_AMBA_MATCH_ALL_UCI(uci) \ + __CS_AMBA_UCI_ID(PID_PIDR2_JEDEC, PID_PIDR2_JEDEC, uci) + +/* extract the data value from a UCI structure given amba_id pointer. */ +static inline void *coresight_get_uci_data(const struct amba_id *id) { - u64 val; + struct amba_cs_uci_id *uci_id = id->data; - val = readl_relaxed(addr + lo_offset); - val |= (hi_offset < 0) ? 0 : - (u64)readl_relaxed(addr + hi_offset) << 32; - return val; + if (!uci_id) + return NULL; + + return uci_id->data; } -static inline void coresight_write_reg_pair(void __iomem *addr, u64 val, - s32 lo_offset, s32 hi_offset) +static inline void *coresight_get_uci_data_from_amba(const struct amba_id *table, u32 pid) { - writel_relaxed((u32)val, addr + lo_offset); - if (hi_offset >= 0) - writel_relaxed((u32)(val >> 32), addr + hi_offset); + while (table->mask) { + if ((pid & table->mask) == table->id) + return coresight_get_uci_data(table); + table++; + }; + return NULL; } -void coresight_disable_path(struct list_head *path); -int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data); -struct coresight_device *coresight_get_sink(struct list_head *path); -struct coresight_device *coresight_get_enabled_sink(bool reset); -struct list_head *coresight_build_path(struct coresight_device *csdev, - struct coresight_device *sink); -void coresight_release_path(struct list_head *path); - -#ifdef CONFIG_CORESIGHT_SOURCE_ETM3X -extern int etm_readl_cp14(u32 off, unsigned int *val); -extern int etm_writel_cp14(u32 off, u32 val); -#else -static inline int etm_readl_cp14(u32 off, unsigned int *val) { return 0; } -static inline int etm_writel_cp14(u32 off, u32 val) { return 0; } -#endif +void coresight_release_platform_data(struct coresight_device *csdev, + struct device *dev, + struct coresight_platform_data *pdata); +struct coresight_device * +coresight_find_csdev_by_fwnode(struct fwnode_handle *r_fwnode); +void coresight_add_helper(struct coresight_device *csdev, + struct coresight_device *helper); + +void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev); +struct coresight_device *coresight_get_percpu_sink(int cpu); +void coresight_disable_source(struct coresight_device *csdev, void *data); +void coresight_pause_source(struct coresight_device *csdev); +int coresight_resume_source(struct coresight_device *csdev); #endif diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index feac98315471..e6472658235d 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -1,10 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved. * * Description: CoreSight Replicator driver */ +#include <linux/acpi.h> +#include <linux/amba/bus.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/platform_device.h> @@ -12,39 +14,182 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/pm_runtime.h> +#include <linux/property.h> #include <linux/clk.h> #include <linux/of.h> #include <linux/coresight.h> #include "coresight-priv.h" +#define REPLICATOR_IDFILTER0 0x000 +#define REPLICATOR_IDFILTER1 0x004 + +DEFINE_CORESIGHT_DEVLIST(replicator_devs, "replicator"); + /** * struct replicator_drvdata - specifics associated to a replicator component - * @dev: the device entity associated with this component + * @base: memory mapped base address for this component. Also indicates + * whether this one is programmable or not. * @atclk: optional clock for the core parts of the replicator. + * @pclk: APB clock if present, otherwise NULL * @csdev: component vitals needed by the framework + * @spinlock: serialize enable/disable operations. + * @check_idfilter_val: check if the context is lost upon clock removal. */ struct replicator_drvdata { - struct device *dev; + void __iomem *base; struct clk *atclk; + struct clk *pclk; struct coresight_device *csdev; + raw_spinlock_t spinlock; + bool check_idfilter_val; }; -static int replicator_enable(struct coresight_device *csdev, int inport, - int outport) +static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) +{ + struct coresight_device *csdev = drvdata->csdev; + + CS_UNLOCK(drvdata->base); + + if (!coresight_claim_device_unlocked(csdev)) { + writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0); + writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1); + coresight_disclaim_device_unlocked(csdev); + } + + CS_LOCK(drvdata->base); +} + +/* + * replicator_reset : Reset the replicator configuration to sane values. + */ +static void replicator_reset(struct replicator_drvdata *drvdata) +{ + if (drvdata->base) + dynamic_replicator_reset(drvdata); +} + +static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, + int inport, int outport) +{ + int rc = 0; + u32 id0val, id1val; + struct coresight_device *csdev = drvdata->csdev; + + CS_UNLOCK(drvdata->base); + + id0val = readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0); + id1val = readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1); + + /* + * Some replicator designs lose context when AMBA clocks are removed, + * so have a check for this. + */ + if (drvdata->check_idfilter_val && id0val == 0x0 && id1val == 0x0) + id0val = id1val = 0xff; + + if (id0val == 0xff && id1val == 0xff) + rc = coresight_claim_device_unlocked(csdev); + + if (!rc) { + switch (outport) { + case 0: + id0val = 0x0; + break; + case 1: + id1val = 0x0; + break; + default: + WARN_ON(1); + rc = -EINVAL; + } + } + + /* Ensure that the outport is enabled. */ + if (!rc) { + writel_relaxed(id0val, drvdata->base + REPLICATOR_IDFILTER0); + writel_relaxed(id1val, drvdata->base + REPLICATOR_IDFILTER1); + } + + CS_LOCK(drvdata->base); + + return rc; +} + +static int replicator_enable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) { + int rc = 0; struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + bool first_enable = false; - dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); - return 0; + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (out->src_refcnt == 0) { + if (drvdata->base) + rc = dynamic_replicator_enable(drvdata, in->dest_port, + out->src_port); + if (!rc) + first_enable = true; + } + if (!rc) + out->src_refcnt++; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + if (first_enable) + dev_dbg(&csdev->dev, "REPLICATOR enabled\n"); + return rc; } -static void replicator_disable(struct coresight_device *csdev, int inport, - int outport) +static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, + int inport, int outport) +{ + u32 reg; + struct coresight_device *csdev = drvdata->csdev; + + switch (outport) { + case 0: + reg = REPLICATOR_IDFILTER0; + break; + case 1: + reg = REPLICATOR_IDFILTER1; + break; + default: + WARN_ON(1); + return; + } + + CS_UNLOCK(drvdata->base); + + /* disable the flow of ATB data through port */ + writel_relaxed(0xff, drvdata->base + reg); + + if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && + (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) + coresight_disclaim_device_unlocked(csdev); + CS_LOCK(drvdata->base); +} + +static void replicator_disable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) { struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + unsigned long flags; + bool last_disable = false; - dev_dbg(drvdata->dev, "REPLICATOR disabled\n"); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (--out->src_refcnt == 0) { + if (drvdata->base) + dynamic_replicator_disable(drvdata, in->dest_port, + out->src_port); + last_disable = true; + } + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + if (last_disable) + dev_dbg(&csdev->dev, "REPLICATOR disabled\n"); } static const struct coresight_ops_link replicator_link_ops = { @@ -56,69 +201,130 @@ static const struct coresight_ops replicator_cs_ops = { .link_ops = &replicator_link_ops, }; -static int replicator_probe(struct platform_device *pdev) +static struct attribute *replicator_mgmt_attrs[] = { + coresight_simple_reg32(idfilter0, REPLICATOR_IDFILTER0), + coresight_simple_reg32(idfilter1, REPLICATOR_IDFILTER1), + NULL, +}; + +static const struct attribute_group replicator_mgmt_group = { + .attrs = replicator_mgmt_attrs, + .name = "mgmt", +}; + +static const struct attribute_group *replicator_groups[] = { + &replicator_mgmt_group, + NULL, +}; + +static int replicator_probe(struct device *dev, struct resource *res) { - int ret; - struct device *dev = &pdev->dev; struct coresight_platform_data *pdata = NULL; struct replicator_drvdata *drvdata; struct coresight_desc desc = { 0 }; - struct device_node *np = pdev->dev.of_node; + void __iomem *base; + int ret; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - pdev->dev.platform_data = pdata; - } + if (is_of_node(dev_fwnode(dev)) && + of_device_is_compatible(dev->of_node, "arm,coresight-replicator")) + dev_warn_once(dev, + "Uses OBSOLETE CoreSight replicator binding\n"); + + desc.name = coresight_alloc_device_name(&replicator_devs, dev); + if (!desc.name) + return -ENOMEM; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &pdev->dev; - drvdata->atclk = devm_clk_get(&pdev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + + /* + * Map the device base for dynamic-replicator, which has been + * validated by AMBA core + */ + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + drvdata->base = base; + desc.groups = replicator_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); + coresight_clear_self_claim_tag(&desc.access); } - pm_runtime_get_noresume(&pdev->dev); - pm_runtime_set_active(&pdev->dev); - pm_runtime_enable(&pdev->dev); - platform_set_drvdata(pdev, drvdata); + if (fwnode_property_present(dev_fwnode(dev), + "qcom,replicator-loses-context")) + drvdata->check_idfilter_val = true; + + dev_set_drvdata(dev, drvdata); + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + dev->platform_data = pdata; + + raw_spin_lock_init(&drvdata->spinlock); desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; desc.ops = &replicator_cs_ops; - desc.pdata = pdev->dev.platform_data; - desc.dev = &pdev->dev; + desc.pdata = dev->platform_data; + desc.dev = dev; + drvdata->csdev = coresight_register(&desc); - if (IS_ERR(drvdata->csdev)) { - ret = PTR_ERR(drvdata->csdev); - goto out_disable_pm; - } + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); - pm_runtime_put(&pdev->dev); + replicator_reset(drvdata); + return 0; +} +static int replicator_remove(struct device *dev) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); return 0; +} -out_disable_pm: - if (!IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); - pm_runtime_put_noidle(&pdev->dev); - pm_runtime_disable(&pdev->dev); +static int replicator_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = replicator_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); return ret; } +static void replicator_platform_remove(struct platform_device *pdev) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + replicator_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + #ifdef CONFIG_PM static int replicator_runtime_suspend(struct device *dev) { struct replicator_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); return 0; } @@ -126,11 +332,17 @@ static int replicator_runtime_suspend(struct device *dev) static int replicator_runtime_resume(struct device *dev) { struct replicator_drvdata *drvdata = dev_get_drvdata(dev); + int ret; - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; - return 0; + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; } #endif @@ -141,16 +353,86 @@ static const struct dev_pm_ops replicator_dev_pm_ops = { static const struct of_device_id replicator_match[] = { {.compatible = "arm,coresight-replicator"}, + {.compatible = "arm,coresight-static-replicator"}, {} }; +MODULE_DEVICE_TABLE(of, replicator_match); + +#ifdef CONFIG_ACPI +static const struct acpi_device_id replicator_acpi_ids[] = { + {"ARMHC985", 0, 0, 0}, /* ARM CoreSight Static Replicator */ + {"ARMHC98D", 0, 0, 0}, /* ARM CoreSight Dynamic Replicator */ + {} +}; + +MODULE_DEVICE_TABLE(acpi, replicator_acpi_ids); +#endif + static struct platform_driver replicator_driver = { - .probe = replicator_probe, + .probe = replicator_platform_probe, + .remove = replicator_platform_remove, .driver = { .name = "coresight-replicator", - .of_match_table = replicator_match, + /* THIS_MODULE is taken care of by platform_driver_register() */ + .of_match_table = of_match_ptr(replicator_match), + .acpi_match_table = ACPI_PTR(replicator_acpi_ids), .pm = &replicator_dev_pm_ops, .suppress_bind_attrs = true, }, }; -builtin_platform_driver(replicator_driver); + +static int dynamic_replicator_probe(struct amba_device *adev, + const struct amba_id *id) +{ + int ret; + + ret = replicator_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void dynamic_replicator_remove(struct amba_device *adev) +{ + replicator_remove(&adev->dev); +} + +static const struct amba_id dynamic_replicator_ids[] = { + CS_AMBA_ID(0x000bb909), + CS_AMBA_ID(0x000bb9ec), /* Coresight SoC-600 */ + {}, +}; + +MODULE_DEVICE_TABLE(amba, dynamic_replicator_ids); + +static struct amba_driver dynamic_replicator_driver = { + .drv = { + .name = "coresight-dynamic-replicator", + .pm = &replicator_dev_pm_ops, + .suppress_bind_attrs = true, + }, + .probe = dynamic_replicator_probe, + .remove = dynamic_replicator_remove, + .id_table = dynamic_replicator_ids, +}; + +static int __init replicator_init(void) +{ + return coresight_init_driver("replicator", &dynamic_replicator_driver, &replicator_driver, + THIS_MODULE); +} + +static void __exit replicator_exit(void) +{ + coresight_remove_driver(&dynamic_replicator_driver, &replicator_driver); +} + +module_init(replicator_init); +module_exit(replicator_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight Replicator Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h new file mode 100644 index 000000000000..303d71911870 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Arm v8 Self-Hosted trace support. + * + * Copyright (C) 2021 ARM Ltd. + */ + +#ifndef __CORESIGHT_SELF_HOSTED_TRACE_H +#define __CORESIGHT_SELF_HOSTED_TRACE_H + +#include <asm/sysreg.h> + +static inline u64 read_trfcr(void) +{ + return read_sysreg_s(SYS_TRFCR_EL1); +} + +static inline void write_trfcr(u64 val) +{ + write_sysreg_s(val, SYS_TRFCR_EL1); + isb(); +} + +#endif /* __CORESIGHT_SELF_HOSTED_TRACE_H */ diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index ef339ff22090..e68529bf89c9 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -16,6 +16,7 @@ * (C) 2015-2016 Chunyan Zhang <zhang.chunyan@linaro.org> */ #include <asm/local.h> +#include <linux/acpi.h> #include <linux/amba/bus.h> #include <linux/bitmap.h> #include <linux/clk.h> @@ -28,8 +29,10 @@ #include <linux/perf_event.h> #include <linux/pm_runtime.h> #include <linux/stm.h> +#include <linux/platform_device.h> #include "coresight-priv.h" +#include "coresight-trace-id.h" #define STMDMASTARTR 0xc04 #define STMDMASTOPR 0xc08 @@ -95,7 +98,7 @@ module_param_named( boot_nr_channel, boot_nr_channel, int, S_IRUGO ); -/** +/* * struct channel_space - central management entity for extended ports * @base: memory mapped base address where channels start. * @phys: physical base address of channel region. @@ -107,16 +110,17 @@ struct channel_space { unsigned long *guaranteed; }; +DEFINE_CORESIGHT_DEVLIST(stm_devs, "stm"); + /** * struct stm_drvdata - specifics associated to an STM component * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @atclk: optional clock for the core parts of the STM. + * @pclk: APB clock if present, otherwise NULL * @csdev: component vitals needed by the framework. * @spinlock: only one at a time pls. * @chs: the channels accociated to this STM. * @stm: structure associated to the generic STM interface. - * @mode: this tracer's mode, i.e sysFS, or disabled. * @traceid: value of the current ID for this component. * @write_bytes: Maximus bytes this STM can write at a time. * @stmsper: settings for register STMSPER. @@ -128,13 +132,12 @@ struct channel_space { */ struct stm_drvdata { void __iomem *base; - struct device *dev; struct clk *atclk; + struct clk *pclk; struct coresight_device *csdev; spinlock_t spinlock; struct channel_space chs; struct stm_data stm; - local_t mode; u8 traceid; u32 write_bytes; u32 stmsper; @@ -190,28 +193,27 @@ static void stm_enable_hw(struct stm_drvdata *drvdata) CS_LOCK(drvdata->base); } -static int stm_enable(struct coresight_device *csdev, - struct perf_event *event, u32 mode) +static int stm_enable(struct coresight_device *csdev, struct perf_event *event, + enum cs_mode mode, + __maybe_unused struct coresight_path *path) { - u32 val; struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); if (mode != CS_MODE_SYSFS) return -EINVAL; - val = local_cmpxchg(&drvdata->mode, CS_MODE_DISABLED, mode); - - /* Someone is already using the tracer */ - if (val) + if (!coresight_take_mode(csdev, mode)) { + /* Someone is already using the tracer */ return -EBUSY; + } - pm_runtime_get_sync(drvdata->dev); + pm_runtime_get_sync(csdev->dev.parent); spin_lock(&drvdata->spinlock); stm_enable_hw(drvdata); spin_unlock(&drvdata->spinlock); - dev_dbg(drvdata->dev, "STM tracing enabled\n"); + dev_dbg(&csdev->dev, "STM tracing enabled\n"); return 0; } @@ -257,45 +259,49 @@ static void stm_disable(struct coresight_device *csdev, struct perf_event *event) { struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct csdev_access *csa = &csdev->access; /* * For as long as the tracer isn't disabled another entity can't * change its status. As such we can read the status here without * fearing it will change under us. */ - if (local_read(&drvdata->mode) == CS_MODE_SYSFS) { + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { spin_lock(&drvdata->spinlock); stm_disable_hw(drvdata); spin_unlock(&drvdata->spinlock); /* Wait until the engine has completely stopped */ - coresight_timeout(drvdata->base, STMTCSR, STMTCSR_BUSY_BIT, 0); + coresight_timeout(csa, STMTCSR, STMTCSR_BUSY_BIT, 0); - pm_runtime_put(drvdata->dev); + pm_runtime_put(csdev->dev.parent); - local_set(&drvdata->mode, CS_MODE_DISABLED); - dev_dbg(drvdata->dev, "STM tracing disabled\n"); + coresight_set_mode(csdev, CS_MODE_DISABLED); + dev_dbg(&csdev->dev, "STM tracing disabled\n"); } } -static int stm_trace_id(struct coresight_device *csdev) +static int stm_trace_id(struct coresight_device *csdev, __maybe_unused enum cs_mode mode, + __maybe_unused struct coresight_device *sink) { - struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct stm_drvdata *drvdata; + + drvdata = dev_get_drvdata(csdev->dev.parent); return drvdata->traceid; } static const struct coresight_ops_source stm_source_ops = { - .trace_id = stm_trace_id, .enable = stm_enable, .disable = stm_disable, }; static const struct coresight_ops stm_cs_ops = { + .trace_id = stm_trace_id, .source_ops = &stm_source_ops, }; -static inline bool stm_addr_unaligned(const void *addr, u8 write_bytes) +static bool stm_addr_unaligned(const void *addr, u8 write_bytes) { return ((unsigned long)addr & (write_bytes - 1)); } @@ -336,10 +342,10 @@ static int stm_generic_link(struct stm_data *stm_data, { struct stm_drvdata *drvdata = container_of(stm_data, struct stm_drvdata, stm); - if (!drvdata || !drvdata->csdev) + if (!drvdata->csdev) return -EINVAL; - return coresight_enable(drvdata->csdev); + return coresight_enable_sysfs(drvdata->csdev); } static void stm_generic_unlink(struct stm_data *stm_data, @@ -347,10 +353,10 @@ static void stm_generic_unlink(struct stm_data *stm_data, { struct stm_drvdata *drvdata = container_of(stm_data, struct stm_drvdata, stm); - if (!drvdata || !drvdata->csdev) + if (!drvdata->csdev) return; - coresight_disable(drvdata->csdev); + coresight_disable_sysfs(drvdata->csdev); } static phys_addr_t @@ -378,7 +384,7 @@ static long stm_generic_set_options(struct stm_data *stm_data, { struct stm_drvdata *drvdata = container_of(stm_data, struct stm_drvdata, stm); - if (!(drvdata && local_read(&drvdata->mode))) + if (!coresight_get_mode(drvdata->csdev)) return -EINVAL; if (channel >= drvdata->numsp) @@ -411,8 +417,9 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data, void __iomem *ch_addr; struct stm_drvdata *drvdata = container_of(stm_data, struct stm_drvdata, stm); + unsigned int stm_flags; - if (!(drvdata && local_read(&drvdata->mode))) + if (!coresight_get_mode(drvdata->csdev)) return -EACCES; if (channel >= drvdata->numsp) @@ -420,8 +427,9 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data, ch_addr = stm_channel_addr(drvdata, channel); - flags = (flags == STP_PACKET_TIMESTAMPED) ? STM_FLAG_TIMESTAMPED : 0; - flags |= test_bit(channel, drvdata->chs.guaranteed) ? + stm_flags = (flags & STP_PACKET_TIMESTAMPED) ? + STM_FLAG_TIMESTAMPED : 0; + stm_flags |= test_bit(channel, drvdata->chs.guaranteed) ? STM_FLAG_GUARANTEED : 0; if (size > drvdata->write_bytes) @@ -431,7 +439,7 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data, switch (packet) { case STP_PACKET_FLAG: - ch_addr += stm_channel_off(STM_PKT_TYPE_FLAG, flags); + ch_addr += stm_channel_off(STM_PKT_TYPE_FLAG, stm_flags); /* * The generic STM core sets a size of '0' on flag packets. @@ -443,7 +451,8 @@ static ssize_t notrace stm_generic_packet(struct stm_data *stm_data, break; case STP_PACKET_DATA: - ch_addr += stm_channel_off(STM_PKT_TYPE_DATA, flags); + stm_flags |= (flags & STP_PACKET_MARKED) ? STM_FLAG_MARKED : 0; + ch_addr += stm_channel_off(STM_PKT_TYPE_DATA, stm_flags); stm_send(ch_addr, payload, size, drvdata->write_bytes); break; @@ -517,7 +526,7 @@ static ssize_t port_select_show(struct device *dev, struct stm_drvdata *drvdata = dev_get_drvdata(dev->parent); unsigned long val; - if (!local_read(&drvdata->mode)) { + if (!coresight_get_mode(drvdata->csdev)) { val = drvdata->stmspscr; } else { spin_lock(&drvdata->spinlock); @@ -543,7 +552,7 @@ static ssize_t port_select_store(struct device *dev, spin_lock(&drvdata->spinlock); drvdata->stmspscr = val; - if (local_read(&drvdata->mode)) { + if (coresight_get_mode(drvdata->csdev)) { CS_UNLOCK(drvdata->base); /* Process as per ARM's TRM recommendation */ stmsper = readl_relaxed(drvdata->base + STMSPER); @@ -564,7 +573,7 @@ static ssize_t port_enable_show(struct device *dev, struct stm_drvdata *drvdata = dev_get_drvdata(dev->parent); unsigned long val; - if (!local_read(&drvdata->mode)) { + if (!coresight_get_mode(drvdata->csdev)) { val = drvdata->stmsper; } else { spin_lock(&drvdata->spinlock); @@ -590,7 +599,7 @@ static ssize_t port_enable_store(struct device *dev, spin_lock(&drvdata->spinlock); drvdata->stmsper = val; - if (local_read(&drvdata->mode)) { + if (coresight_get_mode(drvdata->csdev)) { CS_UNLOCK(drvdata->base); writel_relaxed(drvdata->stmsper, drvdata->base + STMSPER); CS_LOCK(drvdata->base); @@ -610,40 +619,7 @@ static ssize_t traceid_show(struct device *dev, val = drvdata->traceid; return sprintf(buf, "%#lx\n", val); } - -static ssize_t traceid_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret; - unsigned long val; - struct stm_drvdata *drvdata = dev_get_drvdata(dev->parent); - - ret = kstrtoul(buf, 16, &val); - if (ret) - return ret; - - /* traceid field is 7bit wide on STM32 */ - drvdata->traceid = val & 0x7f; - return size; -} -static DEVICE_ATTR_RW(traceid); - -#define coresight_stm_reg(name, offset) \ - coresight_simple_reg32(struct stm_drvdata, name, offset) - -coresight_stm_reg(tcsr, STMTCSR); -coresight_stm_reg(tsfreqr, STMTSFREQR); -coresight_stm_reg(syncr, STMSYNCR); -coresight_stm_reg(sper, STMSPER); -coresight_stm_reg(spter, STMSPTER); -coresight_stm_reg(privmaskr, STMPRIVMASKR); -coresight_stm_reg(spscr, STMSPSCR); -coresight_stm_reg(spmscr, STMSPMSCR); -coresight_stm_reg(spfeat1r, STMSPFEAT1R); -coresight_stm_reg(spfeat2r, STMSPFEAT2R); -coresight_stm_reg(spfeat3r, STMSPFEAT3R); -coresight_stm_reg(devid, CORESIGHT_DEVID); +static DEVICE_ATTR_RO(traceid); static struct attribute *coresight_stm_attrs[] = { &dev_attr_hwevent_enable.attr, @@ -655,18 +631,18 @@ static struct attribute *coresight_stm_attrs[] = { }; static struct attribute *coresight_stm_mgmt_attrs[] = { - &dev_attr_tcsr.attr, - &dev_attr_tsfreqr.attr, - &dev_attr_syncr.attr, - &dev_attr_sper.attr, - &dev_attr_spter.attr, - &dev_attr_privmaskr.attr, - &dev_attr_spscr.attr, - &dev_attr_spmscr.attr, - &dev_attr_spfeat1r.attr, - &dev_attr_spfeat2r.attr, - &dev_attr_spfeat3r.attr, - &dev_attr_devid.attr, + coresight_simple_reg32(tcsr, STMTCSR), + coresight_simple_reg32(tsfreqr, STMTSFREQR), + coresight_simple_reg32(syncr, STMSYNCR), + coresight_simple_reg32(sper, STMSPER), + coresight_simple_reg32(spter, STMSPTER), + coresight_simple_reg32(privmaskr, STMPRIVMASKR), + coresight_simple_reg32(spscr, STMSPSCR), + coresight_simple_reg32(spmscr, STMSPMSCR), + coresight_simple_reg32(spfeat1r, STMSPFEAT1R), + coresight_simple_reg32(spfeat2r, STMSPFEAT2R), + coresight_simple_reg32(spfeat3r, STMSPFEAT3R), + coresight_simple_reg32(devid, CORESIGHT_DEVID), NULL, }; @@ -685,14 +661,15 @@ static const struct attribute_group *coresight_stm_groups[] = { NULL, }; -static int stm_get_resource_byname(struct device_node *np, - char *ch_base, struct resource *res) +#ifdef CONFIG_OF +static int of_stm_get_stimulus_area(struct device *dev, struct resource *res) { const char *name = NULL; int index = 0, found = 0; + struct device_node *np = dev->of_node; while (!of_property_read_string_index(np, "reg-names", index, &name)) { - if (strcmp(ch_base, name)) { + if (strcmp("stm-stimulus-base", name)) { index++; continue; } @@ -707,6 +684,68 @@ static int stm_get_resource_byname(struct device_node *np, return of_address_to_resource(np, index, res); } +#else +static int of_stm_get_stimulus_area(struct device *dev, + struct resource *res) +{ + return -ENOENT; +} +#endif + +#ifdef CONFIG_ACPI +static int acpi_stm_get_stimulus_area(struct device *dev, struct resource *res) +{ + int rc; + bool found_base = false; + struct resource_entry *rent; + LIST_HEAD(res_list); + + struct acpi_device *adev = ACPI_COMPANION(dev); + + rc = acpi_dev_get_resources(adev, &res_list, NULL, NULL); + if (rc < 0) + return rc; + + /* + * The stimulus base for STM device must be listed as the second memory + * resource, followed by the programming base address as described in + * "Section 2.3 Resources" in ACPI for CoreSightTM 1.0 Platform Design + * document (DEN0067). + */ + rc = -ENOENT; + list_for_each_entry(rent, &res_list, node) { + if (resource_type(rent->res) != IORESOURCE_MEM) + continue; + if (found_base) { + *res = *rent->res; + rc = 0; + break; + } + + found_base = true; + } + + acpi_dev_free_resource_list(&res_list); + return rc; +} +#else +static int acpi_stm_get_stimulus_area(struct device *dev, + struct resource *res) +{ + return -ENOENT; +} +#endif + +static int stm_get_stimulus_area(struct device *dev, struct resource *res) +{ + struct fwnode_handle *fwnode = dev_fwnode(dev); + + if (is_of_node(fwnode)) + return of_stm_get_stimulus_area(dev, res); + else if (is_acpi_node(fwnode)) + return acpi_stm_get_stimulus_area(dev, res); + return -ENOENT; +} static u32 stm_fundamental_data_size(struct stm_drvdata *drvdata) { @@ -751,21 +790,14 @@ static void stm_init_default_data(struct stm_drvdata *drvdata) */ drvdata->stmsper = ~0x0; - /* - * The trace ID value for *ETM* tracers start at CPU_ID * 2 + 0x10 and - * anything equal to or higher than 0x70 is reserved. Since 0x00 is - * also reserved the STM trace ID needs to be higher than 0x00 and - * lowner than 0x10. - */ - drvdata->traceid = 0x1; - /* Set invariant transaction timing on all channels */ bitmap_clear(drvdata->chs.guaranteed, 0, drvdata->numsp); } -static void stm_init_generic_data(struct stm_drvdata *drvdata) +static void stm_init_generic_data(struct stm_drvdata *drvdata, + const char *name) { - drvdata->stm.name = dev_name(drvdata->dev); + drvdata->stm.name = name; /* * MasterIDs are assigned at HW design phase. As such the core is @@ -783,45 +815,46 @@ static void stm_init_generic_data(struct stm_drvdata *drvdata) drvdata->stm.set_options = stm_generic_set_options; } -static int stm_probe(struct amba_device *adev, const struct amba_id *id) +static const struct amba_id stm_ids[]; + +static char *stm_csdev_name(struct coresight_device *csdev) { - int ret; + u32 stm_pid = coresight_get_pid(&csdev->access); + void *uci_data = coresight_get_uci_data_from_amba(stm_ids, stm_pid); + + return uci_data ? (char *)uci_data : "STM"; +} + +static int __stm_probe(struct device *dev, struct resource *res) +{ + int ret, trace_id; void __iomem *base; - unsigned long *guaranteed; - struct device *dev = &adev->dev; struct coresight_platform_data *pdata = NULL; struct stm_drvdata *drvdata; - struct resource *res = &adev->res; struct resource ch_res; - size_t res_size, bitmap_size; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } + desc.name = coresight_alloc_device_name(&stm_devs, dev); + if (!desc.name) + return -ENOMEM; + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + dev_set_drvdata(dev, drvdata); base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); - ret = stm_get_resource_byname(np, "stm-stimulus-base", &ch_res); + ret = stm_get_stimulus_area(dev, &ch_res); if (ret) return ret; drvdata->chs.phys = ch_res.start; @@ -833,33 +866,35 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) drvdata->write_bytes = stm_fundamental_data_size(drvdata); - if (boot_nr_channel) { + if (boot_nr_channel) drvdata->numsp = boot_nr_channel; - res_size = min((resource_size_t)(boot_nr_channel * - BYTES_PER_CHANNEL), resource_size(res)); - } else { + else drvdata->numsp = stm_num_stimulus_port(drvdata); - res_size = min((resource_size_t)(drvdata->numsp * - BYTES_PER_CHANNEL), resource_size(res)); - } - bitmap_size = BITS_TO_LONGS(drvdata->numsp) * sizeof(long); - guaranteed = devm_kzalloc(dev, bitmap_size, GFP_KERNEL); - if (!guaranteed) + drvdata->chs.guaranteed = devm_bitmap_zalloc(dev, drvdata->numsp, + GFP_KERNEL); + if (!drvdata->chs.guaranteed) return -ENOMEM; - drvdata->chs.guaranteed = guaranteed; spin_lock_init(&drvdata->spinlock); stm_init_default_data(drvdata); - stm_init_generic_data(drvdata); + stm_init_generic_data(drvdata, desc.name); if (stm_register_device(dev, &drvdata->stm, THIS_MODULE)) { dev_info(dev, - "stm_register_device failed, probing deferred\n"); + "%s : stm_register_device failed, probing deferred\n", + desc.name); return -EPROBE_DEFER; } + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + goto stm_unregister; + } + dev->platform_data = pdata; + desc.type = CORESIGHT_DEV_TYPE_SOURCE; desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE; desc.ops = &stm_cs_ops; @@ -872,23 +907,58 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) goto stm_unregister; } - pm_runtime_put(&adev->dev); + trace_id = coresight_trace_id_get_system_id(); + if (trace_id < 0) { + ret = trace_id; + goto cs_unregister; + } + drvdata->traceid = (u8)trace_id; - dev_info(dev, "%s initialized\n", (char *)id->data); + dev_info(&drvdata->csdev->dev, "%s initialized\n", + stm_csdev_name(drvdata->csdev)); return 0; +cs_unregister: + coresight_unregister(drvdata->csdev); + stm_unregister: stm_unregister_device(&drvdata->stm); return ret; } +static int stm_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + + ret = __stm_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void __stm_remove(struct device *dev) +{ + struct stm_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_trace_id_put_system_id(drvdata->traceid); + coresight_unregister(drvdata->csdev); + + stm_unregister_device(&drvdata->stm); +} + +static void stm_remove(struct amba_device *adev) +{ + __stm_remove(&adev->dev); +} + #ifdef CONFIG_PM static int stm_runtime_suspend(struct device *dev) { struct stm_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); return 0; } @@ -896,11 +966,17 @@ static int stm_runtime_suspend(struct device *dev) static int stm_runtime_resume(struct device *dev) { struct stm_drvdata *drvdata = dev_get_drvdata(dev); + int ret; - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; - return 0; + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; } #endif @@ -909,28 +985,83 @@ static const struct dev_pm_ops stm_dev_pm_ops = { }; static const struct amba_id stm_ids[] = { - { - .id = 0x000bb962, - .mask = 0x000fffff, - .data = "STM32", - }, - { - .id = 0x000bb963, - .mask = 0x000fffff, - .data = "STM500", - }, - { 0, 0}, + CS_AMBA_ID_DATA(0x000bb962, "STM32"), + CS_AMBA_ID_DATA(0x000bb963, "STM500"), + { 0, 0, NULL }, }; +MODULE_DEVICE_TABLE(amba, stm_ids); + static struct amba_driver stm_driver = { .drv = { .name = "coresight-stm", - .owner = THIS_MODULE, .pm = &stm_dev_pm_ops, .suppress_bind_attrs = true, }, .probe = stm_probe, + .remove = stm_remove, .id_table = stm_ids, }; -builtin_amba_driver(stm_driver); +static int stm_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret = 0; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = __stm_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void stm_platform_remove(struct platform_device *pdev) +{ + struct stm_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + __stm_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_ACPI +static const struct acpi_device_id stm_acpi_ids[] = { + {"ARMHC502", 0, 0, 0}, /* ARM CoreSight STM */ + {}, +}; +MODULE_DEVICE_TABLE(acpi, stm_acpi_ids); +#endif + +static struct platform_driver stm_platform_driver = { + .probe = stm_platform_probe, + .remove = stm_platform_remove, + .driver = { + .name = "coresight-stm-platform", + .acpi_match_table = ACPI_PTR(stm_acpi_ids), + .suppress_bind_attrs = true, + .pm = &stm_dev_pm_ops, + }, +}; + +static int __init stm_init(void) +{ + return coresight_init_driver("stm", &stm_driver, &stm_platform_driver, THIS_MODULE); +} + +static void __exit stm_exit(void) +{ + coresight_remove_driver(&stm_driver, &stm_platform_driver); +} +module_init(stm_init); +module_exit(stm_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_DESCRIPTION("Arm CoreSight System Trace Macrocell driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-syscfg-configfs.c b/drivers/hwtracing/coresight/coresight-syscfg-configfs.c new file mode 100644 index 000000000000..2b40e556be87 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-syscfg-configfs.c @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/configfs.h> + +#include "coresight-config.h" +#include "coresight-syscfg-configfs.h" + +/* create a default ci_type. */ +static struct config_item_type *cscfg_create_ci_type(void) +{ + struct config_item_type *ci_type; + + ci_type = devm_kzalloc(cscfg_device(), sizeof(*ci_type), GFP_KERNEL); + if (ci_type) + ci_type->ct_owner = THIS_MODULE; + + return ci_type; +} + +/* configurations sub-group */ + +/* attributes for the config view group */ +static ssize_t cscfg_cfg_description_show(struct config_item *item, char *page) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + + return scnprintf(page, PAGE_SIZE, "%s", fs_config->config_desc->description); +} +CONFIGFS_ATTR_RO(cscfg_cfg_, description); + +static ssize_t cscfg_cfg_feature_refs_show(struct config_item *item, char *page) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + const struct cscfg_config_desc *config_desc = fs_config->config_desc; + ssize_t ch_used = 0; + int i; + + for (i = 0; i < config_desc->nr_feat_refs; i++) + ch_used += scnprintf(page + ch_used, PAGE_SIZE - ch_used, + "%s\n", config_desc->feat_ref_names[i]); + return ch_used; +} +CONFIGFS_ATTR_RO(cscfg_cfg_, feature_refs); + +/* list preset values in order of features and params */ +static ssize_t cscfg_cfg_values_show(struct config_item *item, char *page) +{ + const struct cscfg_feature_desc *feat_desc; + const struct cscfg_config_desc *config_desc; + struct cscfg_fs_preset *fs_preset; + int i, j, val_idx, preset_idx; + ssize_t used = 0; + + fs_preset = container_of(to_config_group(item), struct cscfg_fs_preset, group); + config_desc = fs_preset->config_desc; + + if (!config_desc->nr_presets) + return 0; + + preset_idx = fs_preset->preset_num - 1; + + /* start index on the correct array line */ + val_idx = config_desc->nr_total_params * preset_idx; + + /* + * A set of presets is the sum of all params in used features, + * in order of declaration of features and params in the features + */ + for (i = 0; i < config_desc->nr_feat_refs; i++) { + feat_desc = cscfg_get_named_feat_desc(config_desc->feat_ref_names[i]); + for (j = 0; j < feat_desc->nr_params; j++) { + used += scnprintf(page + used, PAGE_SIZE - used, + "%s.%s = 0x%llx ", + feat_desc->name, + feat_desc->params_desc[j].name, + config_desc->presets[val_idx++]); + } + } + used += scnprintf(page + used, PAGE_SIZE - used, "\n"); + + return used; +} +CONFIGFS_ATTR_RO(cscfg_cfg_, values); + +static ssize_t cscfg_cfg_enable_show(struct config_item *item, char *page) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + + return scnprintf(page, PAGE_SIZE, "%d\n", fs_config->active); +} + +static ssize_t cscfg_cfg_enable_store(struct config_item *item, + const char *page, size_t count) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + int err; + bool val; + + err = kstrtobool(page, &val); + if (!err) + err = cscfg_config_sysfs_activate(fs_config->config_desc, val); + if (!err) { + fs_config->active = val; + if (val) + cscfg_config_sysfs_set_preset(fs_config->preset); + } + return err ? err : count; +} +CONFIGFS_ATTR(cscfg_cfg_, enable); + +static ssize_t cscfg_cfg_preset_show(struct config_item *item, char *page) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + + return scnprintf(page, PAGE_SIZE, "%d\n", fs_config->preset); +} + +static ssize_t cscfg_cfg_preset_store(struct config_item *item, + const char *page, size_t count) +{ + struct cscfg_fs_config *fs_config = container_of(to_config_group(item), + struct cscfg_fs_config, group); + int preset, err; + + err = kstrtoint(page, 0, &preset); + if (!err) { + /* + * presets start at 1, and go up to max (15), + * but the config may provide fewer. + */ + if ((preset < 1) || (preset > fs_config->config_desc->nr_presets)) + err = -EINVAL; + } + + if (!err) { + /* set new value */ + fs_config->preset = preset; + /* set on system if active */ + if (fs_config->active) + cscfg_config_sysfs_set_preset(fs_config->preset); + } + return err ? err : count; +} +CONFIGFS_ATTR(cscfg_cfg_, preset); + +static struct configfs_attribute *cscfg_config_view_attrs[] = { + &cscfg_cfg_attr_description, + &cscfg_cfg_attr_feature_refs, + &cscfg_cfg_attr_enable, + &cscfg_cfg_attr_preset, + NULL, +}; + +static const struct config_item_type cscfg_config_view_type = { + .ct_owner = THIS_MODULE, + .ct_attrs = cscfg_config_view_attrs, +}; + +static struct configfs_attribute *cscfg_config_preset_attrs[] = { + &cscfg_cfg_attr_values, + NULL, +}; + +static const struct config_item_type cscfg_config_preset_type = { + .ct_owner = THIS_MODULE, + .ct_attrs = cscfg_config_preset_attrs, +}; + +static int cscfg_add_preset_groups(struct cscfg_fs_config *cfg_view) +{ + int preset_num; + struct cscfg_fs_preset *cfg_fs_preset; + struct cscfg_config_desc *config_desc = cfg_view->config_desc; + char name[CONFIGFS_ITEM_NAME_LEN]; + + if (!config_desc->nr_presets) + return 0; + + for (preset_num = 1; preset_num <= config_desc->nr_presets; preset_num++) { + cfg_fs_preset = devm_kzalloc(cscfg_device(), + sizeof(struct cscfg_fs_preset), GFP_KERNEL); + + if (!cfg_fs_preset) + return -ENOMEM; + + snprintf(name, CONFIGFS_ITEM_NAME_LEN, "preset%d", preset_num); + cfg_fs_preset->preset_num = preset_num; + cfg_fs_preset->config_desc = cfg_view->config_desc; + config_group_init_type_name(&cfg_fs_preset->group, name, + &cscfg_config_preset_type); + configfs_add_default_group(&cfg_fs_preset->group, &cfg_view->group); + } + return 0; +} + +static struct config_group *cscfg_create_config_group(struct cscfg_config_desc *config_desc) +{ + struct cscfg_fs_config *cfg_view; + struct device *dev = cscfg_device(); + int err; + + if (!dev) + return ERR_PTR(-EINVAL); + + cfg_view = devm_kzalloc(dev, sizeof(struct cscfg_fs_config), GFP_KERNEL); + if (!cfg_view) + return ERR_PTR(-ENOMEM); + + cfg_view->config_desc = config_desc; + config_group_init_type_name(&cfg_view->group, config_desc->name, &cscfg_config_view_type); + + /* add in a preset<n> dir for each preset */ + err = cscfg_add_preset_groups(cfg_view); + if (err) + return ERR_PTR(err); + + return &cfg_view->group; +} + +/* attributes for features view */ + +static ssize_t cscfg_feat_description_show(struct config_item *item, char *page) +{ + struct cscfg_fs_feature *fs_feat = container_of(to_config_group(item), + struct cscfg_fs_feature, group); + + return scnprintf(page, PAGE_SIZE, "%s", fs_feat->feat_desc->description); +} +CONFIGFS_ATTR_RO(cscfg_feat_, description); + +static ssize_t cscfg_feat_matches_show(struct config_item *item, char *page) +{ + struct cscfg_fs_feature *fs_feat = container_of(to_config_group(item), + struct cscfg_fs_feature, group); + u32 match_flags = fs_feat->feat_desc->match_flags; + int used = 0; + + if (match_flags & CS_CFG_MATCH_CLASS_SRC_ALL) + used = scnprintf(page, PAGE_SIZE, "SRC_ALL "); + + if (match_flags & CS_CFG_MATCH_CLASS_SRC_ETM4) + used += scnprintf(page + used, PAGE_SIZE - used, "SRC_ETMV4 "); + + used += scnprintf(page + used, PAGE_SIZE - used, "\n"); + return used; +} +CONFIGFS_ATTR_RO(cscfg_feat_, matches); + +static ssize_t cscfg_feat_nr_params_show(struct config_item *item, char *page) +{ + struct cscfg_fs_feature *fs_feat = container_of(to_config_group(item), + struct cscfg_fs_feature, group); + + return scnprintf(page, PAGE_SIZE, "%d\n", fs_feat->feat_desc->nr_params); +} +CONFIGFS_ATTR_RO(cscfg_feat_, nr_params); + +/* base feature desc attrib structures */ +static struct configfs_attribute *cscfg_feature_view_attrs[] = { + &cscfg_feat_attr_description, + &cscfg_feat_attr_matches, + &cscfg_feat_attr_nr_params, + NULL, +}; + +static const struct config_item_type cscfg_feature_view_type = { + .ct_owner = THIS_MODULE, + .ct_attrs = cscfg_feature_view_attrs, +}; + +static ssize_t cscfg_param_value_show(struct config_item *item, char *page) +{ + struct cscfg_fs_param *param_item = container_of(to_config_group(item), + struct cscfg_fs_param, group); + u64 value = param_item->feat_desc->params_desc[param_item->param_idx].value; + + return scnprintf(page, PAGE_SIZE, "0x%llx\n", value); +} + +static ssize_t cscfg_param_value_store(struct config_item *item, + const char *page, size_t size) +{ + struct cscfg_fs_param *param_item = container_of(to_config_group(item), + struct cscfg_fs_param, group); + struct cscfg_feature_desc *feat_desc = param_item->feat_desc; + int param_idx = param_item->param_idx; + u64 value; + int err; + + err = kstrtoull(page, 0, &value); + if (!err) + err = cscfg_update_feat_param_val(feat_desc, param_idx, value); + + return err ? err : size; +} +CONFIGFS_ATTR(cscfg_param_, value); + +static struct configfs_attribute *cscfg_param_view_attrs[] = { + &cscfg_param_attr_value, + NULL, +}; + +static const struct config_item_type cscfg_param_view_type = { + .ct_owner = THIS_MODULE, + .ct_attrs = cscfg_param_view_attrs, +}; + +/* + * configfs has far less functionality provided to add attributes dynamically than sysfs, + * and the show and store fns pass the enclosing config_item so the actual attribute cannot + * be determined. Therefore we add each item as a group directory, with a value attribute. + */ +static int cscfg_create_params_group_items(struct cscfg_feature_desc *feat_desc, + struct config_group *params_group) +{ + struct device *dev = cscfg_device(); + struct cscfg_fs_param *param_item; + int i; + + /* parameter items - as groups with default_value attribute */ + for (i = 0; i < feat_desc->nr_params; i++) { + param_item = devm_kzalloc(dev, sizeof(struct cscfg_fs_param), GFP_KERNEL); + if (!param_item) + return -ENOMEM; + param_item->feat_desc = feat_desc; + param_item->param_idx = i; + config_group_init_type_name(¶m_item->group, + feat_desc->params_desc[i].name, + &cscfg_param_view_type); + configfs_add_default_group(¶m_item->group, params_group); + } + return 0; +} + +static struct config_group *cscfg_create_feature_group(struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_fs_feature *feat_view; + struct config_item_type *params_group_type; + struct config_group *params_group = NULL; + struct device *dev = cscfg_device(); + int item_err; + + if (!dev) + return ERR_PTR(-EINVAL); + + feat_view = devm_kzalloc(dev, sizeof(struct cscfg_fs_feature), GFP_KERNEL); + if (!feat_view) + return ERR_PTR(-ENOMEM); + + if (feat_desc->nr_params) { + params_group = devm_kzalloc(dev, sizeof(struct config_group), GFP_KERNEL); + if (!params_group) + return ERR_PTR(-ENOMEM); + + params_group_type = cscfg_create_ci_type(); + if (!params_group_type) + return ERR_PTR(-ENOMEM); + } + + feat_view->feat_desc = feat_desc; + config_group_init_type_name(&feat_view->group, + feat_desc->name, + &cscfg_feature_view_type); + if (params_group) { + config_group_init_type_name(params_group, "params", params_group_type); + configfs_add_default_group(params_group, &feat_view->group); + item_err = cscfg_create_params_group_items(feat_desc, params_group); + if (item_err) + return ERR_PTR(item_err); + } + return &feat_view->group; +} + +static const struct config_item_type cscfg_configs_type = { + .ct_owner = THIS_MODULE, +}; + +static struct config_group cscfg_configs_grp = { + .cg_item = { + .ci_namebuf = "configurations", + .ci_type = &cscfg_configs_type, + }, +}; + +/* add configuration to configurations group */ +int cscfg_configfs_add_config(struct cscfg_config_desc *config_desc) +{ + struct config_group *new_group; + int err; + + new_group = cscfg_create_config_group(config_desc); + if (IS_ERR(new_group)) + return PTR_ERR(new_group); + err = configfs_register_group(&cscfg_configs_grp, new_group); + if (!err) + config_desc->fs_group = new_group; + return err; +} + +void cscfg_configfs_del_config(struct cscfg_config_desc *config_desc) +{ + if (config_desc->fs_group) { + configfs_unregister_group(config_desc->fs_group); + config_desc->fs_group = NULL; + } +} + +static const struct config_item_type cscfg_features_type = { + .ct_owner = THIS_MODULE, +}; + +static struct config_group cscfg_features_grp = { + .cg_item = { + .ci_namebuf = "features", + .ci_type = &cscfg_features_type, + }, +}; + +/* add feature to features group */ +int cscfg_configfs_add_feature(struct cscfg_feature_desc *feat_desc) +{ + struct config_group *new_group; + int err; + + new_group = cscfg_create_feature_group(feat_desc); + if (IS_ERR(new_group)) + return PTR_ERR(new_group); + err = configfs_register_group(&cscfg_features_grp, new_group); + if (!err) + feat_desc->fs_group = new_group; + return err; +} + +void cscfg_configfs_del_feature(struct cscfg_feature_desc *feat_desc) +{ + if (feat_desc->fs_group) { + configfs_unregister_group(feat_desc->fs_group); + feat_desc->fs_group = NULL; + } +} + +int cscfg_configfs_init(struct cscfg_manager *cscfg_mgr) +{ + struct configfs_subsystem *subsys; + struct config_item_type *ci_type; + + if (!cscfg_mgr) + return -EINVAL; + + ci_type = cscfg_create_ci_type(); + if (!ci_type) + return -ENOMEM; + + subsys = &cscfg_mgr->cfgfs_subsys; + config_item_set_name(&subsys->su_group.cg_item, CSCFG_FS_SUBSYS_NAME); + subsys->su_group.cg_item.ci_type = ci_type; + + config_group_init(&subsys->su_group); + mutex_init(&subsys->su_mutex); + + /* Add default groups to subsystem */ + config_group_init(&cscfg_configs_grp); + configfs_add_default_group(&cscfg_configs_grp, &subsys->su_group); + + config_group_init(&cscfg_features_grp); + configfs_add_default_group(&cscfg_features_grp, &subsys->su_group); + + return configfs_register_subsystem(subsys); +} + +void cscfg_configfs_release(struct cscfg_manager *cscfg_mgr) +{ + configfs_unregister_subsystem(&cscfg_mgr->cfgfs_subsys); +} diff --git a/drivers/hwtracing/coresight/coresight-syscfg-configfs.h b/drivers/hwtracing/coresight/coresight-syscfg-configfs.h new file mode 100644 index 000000000000..373d84d43268 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-syscfg-configfs.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Coresight system configuration driver - support for configfs. + */ + +#ifndef CORESIGHT_SYSCFG_CONFIGFS_H +#define CORESIGHT_SYSCFG_CONFIGFS_H + +#include <linux/configfs.h> +#include "coresight-syscfg.h" + +#define CSCFG_FS_SUBSYS_NAME "cs-syscfg" + +/* container for configuration view */ +struct cscfg_fs_config { + struct cscfg_config_desc *config_desc; + struct config_group group; + bool active; + int preset; +}; + +/* container for feature view */ +struct cscfg_fs_feature { + struct cscfg_feature_desc *feat_desc; + struct config_group group; +}; + +/* container for parameter view */ +struct cscfg_fs_param { + int param_idx; + struct cscfg_feature_desc *feat_desc; + struct config_group group; +}; + +/* container for preset view */ +struct cscfg_fs_preset { + int preset_num; + struct cscfg_config_desc *config_desc; + struct config_group group; +}; + +int cscfg_configfs_init(struct cscfg_manager *cscfg_mgr); +void cscfg_configfs_release(struct cscfg_manager *cscfg_mgr); +int cscfg_configfs_add_config(struct cscfg_config_desc *config_desc); +int cscfg_configfs_add_feature(struct cscfg_feature_desc *feat_desc); +void cscfg_configfs_del_config(struct cscfg_config_desc *config_desc); +void cscfg_configfs_del_feature(struct cscfg_feature_desc *feat_desc); + +#endif /* CORESIGHT_SYSCFG_CONFIGFS_H */ diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c new file mode 100644 index 000000000000..6836b05986e8 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-syscfg.c @@ -0,0 +1,1319 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2020 Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "coresight-config.h" +#include "coresight-etm-perf.h" +#include "coresight-syscfg.h" +#include "coresight-syscfg-configfs.h" + +/* + * cscfg_ API manages configurations and features for the entire coresight + * infrastructure. + * + * It allows the loading of configurations and features, and loads these into + * coresight devices as appropriate. + */ + +/* protect the cscsg_data and device */ +static DEFINE_MUTEX(cscfg_mutex); + +/* only one of these */ +static struct cscfg_manager *cscfg_mgr; + +/* load features and configuations into the lists */ + +/* get name feature instance from a coresight device list of features */ +static struct cscfg_feature_csdev * +cscfg_get_feat_csdev(struct coresight_device *csdev, const char *name) +{ + struct cscfg_feature_csdev *feat_csdev = NULL; + + list_for_each_entry(feat_csdev, &csdev->feature_csdev_list, node) { + if (strcmp(feat_csdev->feat_desc->name, name) == 0) + return feat_csdev; + } + return NULL; +} + +/* allocate the device config instance - with max number of used features */ +static struct cscfg_config_csdev * +cscfg_alloc_csdev_cfg(struct coresight_device *csdev, int nr_feats) +{ + struct cscfg_config_csdev *config_csdev = NULL; + struct device *dev = csdev->dev.parent; + + /* this is being allocated using the devm for the coresight device */ + config_csdev = devm_kzalloc(dev, + offsetof(struct cscfg_config_csdev, feats_csdev[nr_feats]), + GFP_KERNEL); + if (!config_csdev) + return NULL; + + config_csdev->csdev = csdev; + return config_csdev; +} + +/* Load a config into a device if there are any feature matches between config and device */ +static int cscfg_add_csdev_cfg(struct coresight_device *csdev, + struct cscfg_config_desc *config_desc) +{ + struct cscfg_config_csdev *config_csdev = NULL; + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + int i; + + /* look at each required feature and see if it matches any feature on the device */ + for (i = 0; i < config_desc->nr_feat_refs; i++) { + /* look for a matching name */ + feat_csdev = cscfg_get_feat_csdev(csdev, config_desc->feat_ref_names[i]); + if (feat_csdev) { + /* + * At least one feature on this device matches the config + * add a config instance to the device and a reference to the feature. + */ + if (!config_csdev) { + config_csdev = cscfg_alloc_csdev_cfg(csdev, + config_desc->nr_feat_refs); + if (!config_csdev) + return -ENOMEM; + config_csdev->config_desc = config_desc; + } + config_csdev->feats_csdev[config_csdev->nr_feat++] = feat_csdev; + } + } + /* if matched features, add config to device.*/ + if (config_csdev) { + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&config_csdev->node, &csdev->config_csdev_list); + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + } + + return 0; +} + +/* + * Add the config to the set of registered devices - call with mutex locked. + * Iterates through devices - any device that matches one or more of the + * configuration features will load it, the others will ignore it. + */ +static int cscfg_add_cfg_to_csdevs(struct cscfg_config_desc *config_desc) +{ + struct cscfg_registered_csdev *csdev_item; + int err; + + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + err = cscfg_add_csdev_cfg(csdev_item->csdev, config_desc); + if (err) + return err; + } + return 0; +} + +/* + * Allocate a feature object for load into a csdev. + * memory allocated using the csdev->dev object using devm managed allocator. + */ +static struct cscfg_feature_csdev * +cscfg_alloc_csdev_feat(struct coresight_device *csdev, struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_feature_csdev *feat_csdev = NULL; + struct device *dev = csdev->dev.parent; + int i; + + feat_csdev = devm_kzalloc(dev, sizeof(struct cscfg_feature_csdev), GFP_KERNEL); + if (!feat_csdev) + return NULL; + + /* parameters are optional - could be 0 */ + feat_csdev->nr_params = feat_desc->nr_params; + + /* + * if we need parameters, zero alloc the space here, the load routine in + * the csdev device driver will fill out some information according to + * feature descriptor. + */ + if (feat_csdev->nr_params) { + feat_csdev->params_csdev = devm_kcalloc(dev, feat_csdev->nr_params, + sizeof(struct cscfg_parameter_csdev), + GFP_KERNEL); + if (!feat_csdev->params_csdev) + return NULL; + + /* + * fill in the feature reference in the param - other fields + * handled by loader in csdev. + */ + for (i = 0; i < feat_csdev->nr_params; i++) + feat_csdev->params_csdev[i].feat_csdev = feat_csdev; + } + + /* + * Always have registers to program - again the load routine in csdev device + * will fill out according to feature descriptor and device requirements. + */ + feat_csdev->nr_regs = feat_desc->nr_regs; + feat_csdev->regs_csdev = devm_kcalloc(dev, feat_csdev->nr_regs, + sizeof(struct cscfg_regval_csdev), + GFP_KERNEL); + if (!feat_csdev->regs_csdev) + return NULL; + + /* load the feature default values */ + feat_csdev->feat_desc = feat_desc; + feat_csdev->csdev = csdev; + + return feat_csdev; +} + +/* load one feature into one coresight device */ +static int cscfg_load_feat_csdev(struct coresight_device *csdev, + struct cscfg_feature_desc *feat_desc, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + int err; + + if (!ops->load_feat) + return -EINVAL; + + feat_csdev = cscfg_alloc_csdev_feat(csdev, feat_desc); + if (!feat_csdev) + return -ENOMEM; + + /* load the feature into the device */ + err = ops->load_feat(csdev, feat_csdev); + if (err) + return err; + + /* add to internal csdev feature list & initialise using reset call */ + cscfg_reset_feat(feat_csdev); + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&feat_csdev->node, &csdev->feature_csdev_list); + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + return 0; +} + +/* + * Add feature to any matching devices - call with mutex locked. + * Iterates through devices - any device that matches the feature will be + * called to load it. + */ +static int cscfg_add_feat_to_csdevs(struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_registered_csdev *csdev_item; + int err; + + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + if (csdev_item->match_flags & feat_desc->match_flags) { + err = cscfg_load_feat_csdev(csdev_item->csdev, feat_desc, &csdev_item->ops); + if (err) + return err; + } + } + return 0; +} + +/* check feature list for a named feature - call with mutex locked. */ +static bool cscfg_match_list_feat(const char *name) +{ + struct cscfg_feature_desc *feat_desc; + + list_for_each_entry(feat_desc, &cscfg_mgr->feat_desc_list, item) { + if (strcmp(feat_desc->name, name) == 0) + return true; + } + return false; +} + +/* check all feat needed for cfg are in the list - call with mutex locked. */ +static int cscfg_check_feat_for_cfg(struct cscfg_config_desc *config_desc) +{ + int i; + + for (i = 0; i < config_desc->nr_feat_refs; i++) + if (!cscfg_match_list_feat(config_desc->feat_ref_names[i])) + return -EINVAL; + return 0; +} + +/* + * load feature - add to feature list. + */ +static int cscfg_load_feat(struct cscfg_feature_desc *feat_desc) +{ + int err; + struct cscfg_feature_desc *feat_desc_exist; + + /* new feature must have unique name */ + list_for_each_entry(feat_desc_exist, &cscfg_mgr->feat_desc_list, item) { + if (!strcmp(feat_desc_exist->name, feat_desc->name)) + return -EEXIST; + } + + /* add feature to any matching registered devices */ + err = cscfg_add_feat_to_csdevs(feat_desc); + if (err) + return err; + + list_add(&feat_desc->item, &cscfg_mgr->feat_desc_list); + return 0; +} + +/* + * load config into the system - validate used features exist then add to + * config list. + */ +static int cscfg_load_config(struct cscfg_config_desc *config_desc) +{ + int err; + struct cscfg_config_desc *config_desc_exist; + + /* new configuration must have a unique name */ + list_for_each_entry(config_desc_exist, &cscfg_mgr->config_desc_list, item) { + if (!strcmp(config_desc_exist->name, config_desc->name)) + return -EEXIST; + } + + /* validate features are present */ + err = cscfg_check_feat_for_cfg(config_desc); + if (err) + return err; + + /* add config to any matching registered device */ + err = cscfg_add_cfg_to_csdevs(config_desc); + if (err) + return err; + + /* add config to perf fs to allow selection */ + err = etm_perf_add_symlink_cscfg(cscfg_device(), config_desc); + if (err) + return err; + + list_add(&config_desc->item, &cscfg_mgr->config_desc_list); + atomic_set(&config_desc->active_cnt, 0); + return 0; +} + +/* get a feature descriptor by name */ +const struct cscfg_feature_desc *cscfg_get_named_feat_desc(const char *name) +{ + const struct cscfg_feature_desc *feat_desc = NULL, *feat_desc_item; + + mutex_lock(&cscfg_mutex); + + list_for_each_entry(feat_desc_item, &cscfg_mgr->feat_desc_list, item) { + if (strcmp(feat_desc_item->name, name) == 0) { + feat_desc = feat_desc_item; + break; + } + } + + mutex_unlock(&cscfg_mutex); + return feat_desc; +} + +/* called with cscfg_mutex held */ +static struct cscfg_feature_csdev * +cscfg_csdev_get_feat_from_desc(struct coresight_device *csdev, + struct cscfg_feature_desc *feat_desc) +{ + struct cscfg_feature_csdev *feat_csdev; + + list_for_each_entry(feat_csdev, &csdev->feature_csdev_list, node) { + if (feat_csdev->feat_desc == feat_desc) + return feat_csdev; + } + return NULL; +} + +int cscfg_update_feat_param_val(struct cscfg_feature_desc *feat_desc, + int param_idx, u64 value) +{ + int err = 0; + struct cscfg_feature_csdev *feat_csdev; + struct cscfg_registered_csdev *csdev_item; + + mutex_lock(&cscfg_mutex); + + /* check if any config active & return busy */ + if (atomic_read(&cscfg_mgr->sys_active_cnt)) { + err = -EBUSY; + goto unlock_exit; + } + + /* set the value */ + if ((param_idx < 0) || (param_idx >= feat_desc->nr_params)) { + err = -EINVAL; + goto unlock_exit; + } + feat_desc->params_desc[param_idx].value = value; + + /* update loaded instances.*/ + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + feat_csdev = cscfg_csdev_get_feat_from_desc(csdev_item->csdev, feat_desc); + if (feat_csdev) + feat_csdev->params_csdev[param_idx].current_value = value; + } + +unlock_exit: + mutex_unlock(&cscfg_mutex); + return err; +} + +/* + * Conditionally up reference count on owner to prevent unload. + * + * module loaded configs need to be locked in to prevent premature unload. + */ +static int cscfg_owner_get(struct cscfg_load_owner_info *owner_info) +{ + if ((owner_info->type == CSCFG_OWNER_MODULE) && + (!try_module_get(owner_info->owner_handle))) + return -EINVAL; + return 0; +} + +/* conditionally lower ref count on an owner */ +static void cscfg_owner_put(struct cscfg_load_owner_info *owner_info) +{ + if (owner_info->type == CSCFG_OWNER_MODULE) + module_put(owner_info->owner_handle); +} + +static void cscfg_remove_owned_csdev_configs(struct coresight_device *csdev, void *load_owner) +{ + struct cscfg_config_csdev *config_csdev, *tmp; + + if (list_empty(&csdev->config_csdev_list)) + return; + + guard(raw_spinlock_irqsave)(&csdev->cscfg_csdev_lock); + + list_for_each_entry_safe(config_csdev, tmp, &csdev->config_csdev_list, node) { + if (config_csdev->config_desc->load_owner == load_owner) + list_del(&config_csdev->node); + } +} + +static void cscfg_remove_owned_csdev_features(struct coresight_device *csdev, void *load_owner) +{ + struct cscfg_feature_csdev *feat_csdev, *tmp; + + if (list_empty(&csdev->feature_csdev_list)) + return; + + list_for_each_entry_safe(feat_csdev, tmp, &csdev->feature_csdev_list, node) { + if (feat_csdev->feat_desc->load_owner == load_owner) + list_del(&feat_csdev->node); + } +} + +/* + * Unregister all configuration and features from configfs owned by load_owner. + * Although this is called without the list mutex being held, it is in the + * context of an unload operation which are strictly serialised, + * so the lists cannot change during this call. + */ +static void cscfg_fs_unregister_cfgs_feats(void *load_owner) +{ + struct cscfg_config_desc *config_desc; + struct cscfg_feature_desc *feat_desc; + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + if (config_desc->load_owner == load_owner) + cscfg_configfs_del_config(config_desc); + } + list_for_each_entry(feat_desc, &cscfg_mgr->feat_desc_list, item) { + if (feat_desc->load_owner == load_owner) + cscfg_configfs_del_feature(feat_desc); + } +} + +/* + * removal is relatively easy - just remove from all lists, anything that + * matches the owner. Memory for the descriptors will be managed by the owner, + * memory for the csdev items is devm_ allocated with the individual csdev + * devices. + */ +static void cscfg_unload_owned_cfgs_feats(void *load_owner) +{ + struct cscfg_config_desc *config_desc, *cfg_tmp; + struct cscfg_feature_desc *feat_desc, *feat_tmp; + struct cscfg_registered_csdev *csdev_item; + + lockdep_assert_held(&cscfg_mutex); + + /* remove from each csdev instance feature and config lists */ + list_for_each_entry(csdev_item, &cscfg_mgr->csdev_desc_list, item) { + /* + * for each csdev, check the loaded lists and remove if + * referenced descriptor is owned + */ + cscfg_remove_owned_csdev_configs(csdev_item->csdev, load_owner); + cscfg_remove_owned_csdev_features(csdev_item->csdev, load_owner); + } + + /* remove from the config descriptor lists */ + list_for_each_entry_safe(config_desc, cfg_tmp, &cscfg_mgr->config_desc_list, item) { + if (config_desc->load_owner == load_owner) { + etm_perf_del_symlink_cscfg(config_desc); + list_del(&config_desc->item); + } + } + + /* remove from the feature descriptor lists */ + list_for_each_entry_safe(feat_desc, feat_tmp, &cscfg_mgr->feat_desc_list, item) { + if (feat_desc->load_owner == load_owner) { + list_del(&feat_desc->item); + } + } +} + +/* + * load the features and configs to the lists - called with list mutex held + */ +static int cscfg_load_owned_cfgs_feats(struct cscfg_config_desc **config_descs, + struct cscfg_feature_desc **feat_descs, + struct cscfg_load_owner_info *owner_info) +{ + int i, err; + + lockdep_assert_held(&cscfg_mutex); + + /* load features first */ + if (feat_descs) { + for (i = 0; feat_descs[i]; i++) { + err = cscfg_load_feat(feat_descs[i]); + if (err) { + pr_err("coresight-syscfg: Failed to load feature %s\n", + feat_descs[i]->name); + return err; + } + feat_descs[i]->load_owner = owner_info; + } + } + + /* next any configurations to check feature dependencies */ + if (config_descs) { + for (i = 0; config_descs[i]; i++) { + err = cscfg_load_config(config_descs[i]); + if (err) { + pr_err("coresight-syscfg: Failed to load configuration %s\n", + config_descs[i]->name); + return err; + } + config_descs[i]->load_owner = owner_info; + config_descs[i]->available = false; + } + } + return 0; +} + +/* set configurations as available to activate at the end of the load process */ +static void cscfg_set_configs_available(struct cscfg_config_desc **config_descs) +{ + int i; + + lockdep_assert_held(&cscfg_mutex); + + if (config_descs) { + for (i = 0; config_descs[i]; i++) + config_descs[i]->available = true; + } +} + +/* + * Create and register each of the configurations and features with configfs. + * Called without mutex being held. + */ +static int cscfg_fs_register_cfgs_feats(struct cscfg_config_desc **config_descs, + struct cscfg_feature_desc **feat_descs) +{ + int i, err; + + if (feat_descs) { + for (i = 0; feat_descs[i]; i++) { + err = cscfg_configfs_add_feature(feat_descs[i]); + if (err) + return err; + } + } + if (config_descs) { + for (i = 0; config_descs[i]; i++) { + err = cscfg_configfs_add_config(config_descs[i]); + if (err) + return err; + } + } + return 0; +} + +/** + * cscfg_load_config_sets - API function to load feature and config sets. + * + * Take a 0 terminated array of feature descriptors and/or configuration + * descriptors and load into the system. + * Features are loaded first to ensure configuration dependencies can be met. + * + * To facilitate dynamic loading and unloading, features and configurations + * have a "load_owner", to allow later unload by the same owner. An owner may + * be a loadable module or configuration dynamically created via configfs. + * As later loaded configurations can use earlier loaded features, creating load + * dependencies, a load order list is maintained. Unload is strictly in the + * reverse order to load. + * + * @config_descs: 0 terminated array of configuration descriptors. + * @feat_descs: 0 terminated array of feature descriptors. + * @owner_info: Information on the owner of this set. + */ +int cscfg_load_config_sets(struct cscfg_config_desc **config_descs, + struct cscfg_feature_desc **feat_descs, + struct cscfg_load_owner_info *owner_info) +{ + int err = 0; + + mutex_lock(&cscfg_mutex); + if (cscfg_mgr->load_state != CSCFG_NONE) { + mutex_unlock(&cscfg_mutex); + return -EBUSY; + } + cscfg_mgr->load_state = CSCFG_LOAD; + + /* first load and add to the lists */ + err = cscfg_load_owned_cfgs_feats(config_descs, feat_descs, owner_info); + if (err) + goto err_clean_load; + + /* add the load owner to the load order list */ + list_add_tail(&owner_info->item, &cscfg_mgr->load_order_list); + if (!list_is_singular(&cscfg_mgr->load_order_list)) { + /* lock previous item in load order list */ + err = cscfg_owner_get(list_prev_entry(owner_info, item)); + if (err) + goto err_clean_owner_list; + } + + /* + * make visible to configfs - configfs manipulation must occur outside + * the list mutex lock to avoid circular lockdep issues with configfs + * built in mutexes and semaphores. This is safe as it is not possible + * to start a new load/unload operation till the current one is done. + */ + mutex_unlock(&cscfg_mutex); + + /* create the configfs elements */ + err = cscfg_fs_register_cfgs_feats(config_descs, feat_descs); + mutex_lock(&cscfg_mutex); + + if (err) + goto err_clean_cfs; + + /* mark any new configs as available for activation */ + cscfg_set_configs_available(config_descs); + goto exit_unlock; + +err_clean_cfs: + /* cleanup after error registering with configfs */ + cscfg_fs_unregister_cfgs_feats(owner_info); + + if (!list_is_singular(&cscfg_mgr->load_order_list)) + cscfg_owner_put(list_prev_entry(owner_info, item)); + +err_clean_owner_list: + list_del(&owner_info->item); + +err_clean_load: + cscfg_unload_owned_cfgs_feats(owner_info); + +exit_unlock: + cscfg_mgr->load_state = CSCFG_NONE; + mutex_unlock(&cscfg_mutex); + return err; +} +EXPORT_SYMBOL_GPL(cscfg_load_config_sets); + +/** + * cscfg_unload_config_sets - unload a set of configurations by owner. + * + * Dynamic unload of configuration and feature sets is done on the basis of + * the load owner of that set. Later loaded configurations can depend on + * features loaded earlier. + * + * Therefore, unload is only possible if:- + * 1) no configurations are active. + * 2) the set being unloaded was the last to be loaded to maintain dependencies. + * + * Once the unload operation commences, we disallow any configuration being + * made active until it is complete. + * + * @owner_info: Information on owner for set being unloaded. + */ +int cscfg_unload_config_sets(struct cscfg_load_owner_info *owner_info) +{ + int err = 0; + struct cscfg_load_owner_info *load_list_item = NULL; + + mutex_lock(&cscfg_mutex); + if (cscfg_mgr->load_state != CSCFG_NONE) { + mutex_unlock(&cscfg_mutex); + return -EBUSY; + } + + /* unload op in progress also prevents activation of any config */ + cscfg_mgr->load_state = CSCFG_UNLOAD; + + /* cannot unload if anything is active */ + if (atomic_read(&cscfg_mgr->sys_active_cnt)) { + err = -EBUSY; + goto exit_unlock; + } + + /* cannot unload if not last loaded in load order */ + if (!list_empty(&cscfg_mgr->load_order_list)) { + load_list_item = list_last_entry(&cscfg_mgr->load_order_list, + struct cscfg_load_owner_info, item); + if (load_list_item != owner_info) + load_list_item = NULL; + } + + if (!load_list_item) { + err = -EINVAL; + goto exit_unlock; + } + + /* remove from configfs - again outside the scope of the list mutex */ + mutex_unlock(&cscfg_mutex); + cscfg_fs_unregister_cfgs_feats(owner_info); + mutex_lock(&cscfg_mutex); + + /* unload everything from lists belonging to load_owner */ + cscfg_unload_owned_cfgs_feats(owner_info); + + /* remove from load order list */ + if (!list_is_singular(&cscfg_mgr->load_order_list)) { + /* unlock previous item in load order list */ + cscfg_owner_put(list_prev_entry(owner_info, item)); + } + list_del(&owner_info->item); + +exit_unlock: + cscfg_mgr->load_state = CSCFG_NONE; + mutex_unlock(&cscfg_mutex); + return err; +} +EXPORT_SYMBOL_GPL(cscfg_unload_config_sets); + +/* Handle coresight device registration and add configs and features to devices */ + +/* iterate through config lists and load matching configs to device */ +static int cscfg_add_cfgs_csdev(struct coresight_device *csdev) +{ + struct cscfg_config_desc *config_desc; + int err = 0; + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + err = cscfg_add_csdev_cfg(csdev, config_desc); + if (err) + break; + } + return err; +} + +/* iterate through feature lists and load matching features to device */ +static int cscfg_add_feats_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_feature_desc *feat_desc; + int err = 0; + + if (!ops->load_feat) + return -EINVAL; + + list_for_each_entry(feat_desc, &cscfg_mgr->feat_desc_list, item) { + if (feat_desc->match_flags & match_flags) { + err = cscfg_load_feat_csdev(csdev, feat_desc, ops); + if (err) + break; + } + } + return err; +} + +/* Add coresight device to list and copy its matching info */ +static int cscfg_list_add_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + struct cscfg_registered_csdev *csdev_item; + + /* allocate the list entry structure */ + csdev_item = kzalloc(sizeof(struct cscfg_registered_csdev), GFP_KERNEL); + if (!csdev_item) + return -ENOMEM; + + csdev_item->csdev = csdev; + csdev_item->match_flags = match_flags; + csdev_item->ops.load_feat = ops->load_feat; + list_add(&csdev_item->item, &cscfg_mgr->csdev_desc_list); + + INIT_LIST_HEAD(&csdev->feature_csdev_list); + INIT_LIST_HEAD(&csdev->config_csdev_list); + raw_spin_lock_init(&csdev->cscfg_csdev_lock); + + return 0; +} + +/* remove a coresight device from the list and free data */ +static void cscfg_list_remove_csdev(struct coresight_device *csdev) +{ + struct cscfg_registered_csdev *csdev_item, *tmp; + + list_for_each_entry_safe(csdev_item, tmp, &cscfg_mgr->csdev_desc_list, item) { + if (csdev_item->csdev == csdev) { + list_del(&csdev_item->item); + kfree(csdev_item); + break; + } + } +} + +/** + * cscfg_register_csdev - register a coresight device with the syscfg manager. + * + * Registers the coresight device with the system. @match_flags used to check + * if the device is a match for registered features. Any currently registered + * configurations and features that match the device will be loaded onto it. + * + * @csdev: The coresight device to register. + * @match_flags: Matching information to load features. + * @ops: Standard operations supported by the device. + */ +int cscfg_register_csdev(struct coresight_device *csdev, + u32 match_flags, + struct cscfg_csdev_feat_ops *ops) +{ + int ret = 0; + + mutex_lock(&cscfg_mutex); + + /* add device to list of registered devices */ + ret = cscfg_list_add_csdev(csdev, match_flags, ops); + if (ret) + goto reg_csdev_unlock; + + /* now load any registered features and configs matching the device. */ + ret = cscfg_add_feats_csdev(csdev, match_flags, ops); + if (ret) { + cscfg_list_remove_csdev(csdev); + goto reg_csdev_unlock; + } + + ret = cscfg_add_cfgs_csdev(csdev); + if (ret) { + cscfg_list_remove_csdev(csdev); + goto reg_csdev_unlock; + } + + pr_info("CSCFG registered %s", dev_name(&csdev->dev)); + +reg_csdev_unlock: + mutex_unlock(&cscfg_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(cscfg_register_csdev); + +/** + * cscfg_unregister_csdev - remove coresight device from syscfg manager. + * + * @csdev: Device to remove. + */ +void cscfg_unregister_csdev(struct coresight_device *csdev) +{ + mutex_lock(&cscfg_mutex); + cscfg_list_remove_csdev(csdev); + mutex_unlock(&cscfg_mutex); +} +EXPORT_SYMBOL_GPL(cscfg_unregister_csdev); + +/** + * cscfg_csdev_reset_feats - reset features for a CoreSight device. + * + * Resets all parameters and register values for any features loaded + * into @csdev to their default values. + * + * @csdev: The CoreSight device. + */ +void cscfg_csdev_reset_feats(struct coresight_device *csdev) +{ + struct cscfg_feature_csdev *feat_csdev; + unsigned long flags; + + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + if (list_empty(&csdev->feature_csdev_list)) + goto unlock_exit; + + list_for_each_entry(feat_csdev, &csdev->feature_csdev_list, node) + cscfg_reset_feat(feat_csdev); + +unlock_exit: + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); +} +EXPORT_SYMBOL_GPL(cscfg_csdev_reset_feats); + +static bool cscfg_config_desc_get(struct cscfg_config_desc *config_desc) +{ + if (!atomic_fetch_inc(&config_desc->active_cnt)) { + /* must ensure that config cannot be unloaded in use */ + if (unlikely(cscfg_owner_get(config_desc->load_owner))) { + atomic_dec(&config_desc->active_cnt); + return false; + } + } + + return true; +} + +static void cscfg_config_desc_put(struct cscfg_config_desc *config_desc) +{ + if (!atomic_dec_return(&config_desc->active_cnt)) + cscfg_owner_put(config_desc->load_owner); +} + +/* + * This activate configuration for either perf or sysfs. Perf can have multiple + * active configs, selected per event, sysfs is limited to one. + * + * Increments the configuration descriptor active count and the global active + * count. + * + * @cfg_hash: Hash value of the selected configuration name. + */ +static int _cscfg_activate_config(unsigned long cfg_hash) +{ + struct cscfg_config_desc *config_desc; + int err = -EINVAL; + + if (cscfg_mgr->load_state == CSCFG_UNLOAD) + return -EBUSY; + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + if ((unsigned long)config_desc->event_ea->var == cfg_hash) { + /* if we happen upon a partly loaded config, can't use it */ + if (config_desc->available == false) + return -EBUSY; + + if (!cscfg_config_desc_get(config_desc)) { + err = -EINVAL; + break; + } + + /* + * increment the global active count - control changes to + * active configurations + */ + atomic_inc(&cscfg_mgr->sys_active_cnt); + + err = 0; + dev_dbg(cscfg_device(), "Activate config %s.\n", config_desc->name); + break; + } + } + return err; +} + +static void _cscfg_deactivate_config(unsigned long cfg_hash) +{ + struct cscfg_config_desc *config_desc; + + list_for_each_entry(config_desc, &cscfg_mgr->config_desc_list, item) { + if ((unsigned long)config_desc->event_ea->var == cfg_hash) { + atomic_dec(&cscfg_mgr->sys_active_cnt); + cscfg_config_desc_put(config_desc); + dev_dbg(cscfg_device(), "Deactivate config %s.\n", config_desc->name); + break; + } + } +} + +/* + * called from configfs to set/clear the active configuration for use when + * using sysfs to control trace. + */ +int cscfg_config_sysfs_activate(struct cscfg_config_desc *config_desc, bool activate) +{ + unsigned long cfg_hash; + int err = 0; + + mutex_lock(&cscfg_mutex); + + cfg_hash = (unsigned long)config_desc->event_ea->var; + + if (activate) { + /* cannot be a current active value to activate this */ + if (cscfg_mgr->sysfs_active_config) { + err = -EBUSY; + goto exit_unlock; + } + err = _cscfg_activate_config(cfg_hash); + if (!err) + cscfg_mgr->sysfs_active_config = cfg_hash; + } else { + /* disable if matching current value */ + if (cscfg_mgr->sysfs_active_config == cfg_hash) { + _cscfg_deactivate_config(cfg_hash); + cscfg_mgr->sysfs_active_config = 0; + } else + err = -EINVAL; + } + +exit_unlock: + mutex_unlock(&cscfg_mutex); + return err; +} + +/* set the sysfs preset value */ +void cscfg_config_sysfs_set_preset(int preset) +{ + mutex_lock(&cscfg_mutex); + cscfg_mgr->sysfs_active_preset = preset; + mutex_unlock(&cscfg_mutex); +} + +/* + * Used by a device to get the config and preset selected as active in configfs, + * when using sysfs to control trace. + */ +void cscfg_config_sysfs_get_active_cfg(unsigned long *cfg_hash, int *preset) +{ + mutex_lock(&cscfg_mutex); + *preset = cscfg_mgr->sysfs_active_preset; + *cfg_hash = cscfg_mgr->sysfs_active_config; + mutex_unlock(&cscfg_mutex); +} +EXPORT_SYMBOL_GPL(cscfg_config_sysfs_get_active_cfg); + +/** + * cscfg_activate_config - Mark a configuration descriptor as active. + * + * This will be seen when csdev devices are enabled in the system. + * Only activated configurations can be enabled on individual devices. + * Activation protects the configuration from alteration or removal while + * active. + * + * Selection by hash value - generated from the configuration name when it + * was loaded and added to the cs_etm/configurations file system for selection + * by perf. + * + * @cfg_hash: Hash value of the selected configuration name. + */ +int cscfg_activate_config(unsigned long cfg_hash) +{ + int err = 0; + + mutex_lock(&cscfg_mutex); + err = _cscfg_activate_config(cfg_hash); + mutex_unlock(&cscfg_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(cscfg_activate_config); + +/** + * cscfg_deactivate_config - Mark a config descriptor as inactive. + * + * Decrement the configuration and global active counts. + * + * @cfg_hash: Hash value of the selected configuration name. + */ +void cscfg_deactivate_config(unsigned long cfg_hash) +{ + mutex_lock(&cscfg_mutex); + _cscfg_deactivate_config(cfg_hash); + mutex_unlock(&cscfg_mutex); +} +EXPORT_SYMBOL_GPL(cscfg_deactivate_config); + +/** + * cscfg_csdev_enable_active_config - Enable matching active configuration for device. + * + * Enables the configuration selected by @cfg_hash if the configuration is supported + * on the device and has been activated. + * + * If active and supported the CoreSight device @csdev will be programmed with the + * configuration, using @preset parameters. + * + * Should be called before driver hardware enable for the requested device, prior to + * programming and enabling the physical hardware. + * + * @csdev: CoreSight device to program. + * @cfg_hash: Selector for the configuration. + * @preset: Preset parameter values to use, 0 for current / default values. + */ +int cscfg_csdev_enable_active_config(struct coresight_device *csdev, + unsigned long cfg_hash, int preset) +{ + struct cscfg_config_csdev *config_csdev_active = NULL, *config_csdev_item; + struct cscfg_config_desc *config_desc; + unsigned long flags; + int err = 0; + + /* quickly check global count */ + if (!atomic_read(&cscfg_mgr->sys_active_cnt)) + return 0; + + /* + * Look for matching configuration - set the active configuration + * context if found. + */ + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_for_each_entry(config_csdev_item, &csdev->config_csdev_list, node) { + config_desc = config_csdev_item->config_desc; + if (((unsigned long)config_desc->event_ea->var == cfg_hash) && + cscfg_config_desc_get(config_desc)) { + config_csdev_active = config_csdev_item; + csdev->active_cscfg_ctxt = (void *)config_csdev_active; + break; + } + } + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + /* + * If found, attempt to enable + */ + if (config_csdev_active) { + /* + * Call the generic routine that will program up the internal + * driver structures prior to programming up the hardware. + * This routine takes the driver spinlock saved in the configs. + */ + err = cscfg_csdev_enable_config(config_csdev_active, preset); + if (!err) { + /* + * Successful programming. Check the active_cscfg_ctxt + * pointer to ensure no pre-emption disabled it via + * cscfg_csdev_disable_active_config() before + * we could start. + * + * Set enabled if OK, err if not. + */ + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + if (csdev->active_cscfg_ctxt) + config_csdev_active->enabled = true; + else + err = -EBUSY; + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + } + + if (err) + cscfg_config_desc_put(config_desc); + } + + return err; +} +EXPORT_SYMBOL_GPL(cscfg_csdev_enable_active_config); + +/** + * cscfg_csdev_disable_active_config - disable an active config on the device. + * + * Disables the active configuration on the CoreSight device @csdev. + * Disable will save the values of any registers marked in the configurations + * as save on disable. + * + * Should be called after driver hardware disable for the requested device, + * after disabling the physical hardware and reading back registers. + * + * @csdev: The CoreSight device. + */ +void cscfg_csdev_disable_active_config(struct coresight_device *csdev) +{ + struct cscfg_config_csdev *config_csdev; + unsigned long flags; + + /* + * Check if we have an active config, and that it was successfully enabled. + * If it was not enabled, we have no work to do, otherwise mark as disabled. + * Clear the active config pointer. + */ + raw_spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + config_csdev = (struct cscfg_config_csdev *)csdev->active_cscfg_ctxt; + if (config_csdev) { + if (!config_csdev->enabled) + config_csdev = NULL; + else + config_csdev->enabled = false; + } + csdev->active_cscfg_ctxt = NULL; + raw_spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + + /* true if there was an enabled active config */ + if (config_csdev) { + cscfg_csdev_disable_config(config_csdev); + cscfg_config_desc_put(config_csdev->config_desc); + } +} +EXPORT_SYMBOL_GPL(cscfg_csdev_disable_active_config); + +/* Initialise system configuration management device. */ + +struct device *cscfg_device(void) +{ + return cscfg_mgr ? &cscfg_mgr->dev : NULL; +} + +/* Must have a release function or the kernel will complain on module unload */ +static void cscfg_dev_release(struct device *dev) +{ + mutex_lock(&cscfg_mutex); + kfree(cscfg_mgr); + cscfg_mgr = NULL; + mutex_unlock(&cscfg_mutex); +} + +/* a device is needed to "own" some kernel elements such as sysfs entries. */ +static int cscfg_create_device(void) +{ + struct device *dev; + int err = -ENOMEM; + + mutex_lock(&cscfg_mutex); + if (cscfg_mgr) { + err = -EINVAL; + goto create_dev_exit_unlock; + } + + cscfg_mgr = kzalloc(sizeof(struct cscfg_manager), GFP_KERNEL); + if (!cscfg_mgr) + goto create_dev_exit_unlock; + + /* initialise the cscfg_mgr structure */ + INIT_LIST_HEAD(&cscfg_mgr->csdev_desc_list); + INIT_LIST_HEAD(&cscfg_mgr->feat_desc_list); + INIT_LIST_HEAD(&cscfg_mgr->config_desc_list); + INIT_LIST_HEAD(&cscfg_mgr->load_order_list); + atomic_set(&cscfg_mgr->sys_active_cnt, 0); + cscfg_mgr->load_state = CSCFG_NONE; + + /* setup the device */ + dev = cscfg_device(); + dev->release = cscfg_dev_release; + dev->init_name = "cs_system_cfg"; + + err = device_register(dev); + if (err) + put_device(dev); + +create_dev_exit_unlock: + mutex_unlock(&cscfg_mutex); + return err; +} + +/* + * Loading and unloading is generally on user discretion. + * If exiting due to coresight module unload, we need to unload any configurations that remain, + * before we unregister the configfs intrastructure. + * + * Do this by walking the load_owner list and taking appropriate action, depending on the load + * owner type. + */ +static void cscfg_unload_cfgs_on_exit(void) +{ + struct cscfg_load_owner_info *owner_info = NULL; + + /* + * grab the mutex - even though we are exiting, some configfs files + * may still be live till we dump them, so ensure list data is + * protected from a race condition. + */ + mutex_lock(&cscfg_mutex); + while (!list_empty(&cscfg_mgr->load_order_list)) { + + /* remove in reverse order of loading */ + owner_info = list_last_entry(&cscfg_mgr->load_order_list, + struct cscfg_load_owner_info, item); + + /* action according to type */ + switch (owner_info->type) { + case CSCFG_OWNER_PRELOAD: + /* + * preloaded descriptors are statically allocated in + * this module - just need to unload dynamic items from + * csdev lists, and remove from configfs directories. + */ + pr_info("cscfg: unloading preloaded configurations\n"); + break; + + case CSCFG_OWNER_MODULE: + /* + * this is an error - the loadable module must have been unloaded prior + * to the coresight module unload. Therefore that module has not + * correctly unloaded configs in its own exit code. + * Nothing to do other than emit an error string as the static descriptor + * references we need to unload will have disappeared with the module. + */ + pr_err("cscfg: ERROR: prior module failed to unload configuration\n"); + goto list_remove; + } + + /* remove from configfs - outside the scope of the list mutex */ + mutex_unlock(&cscfg_mutex); + cscfg_fs_unregister_cfgs_feats(owner_info); + mutex_lock(&cscfg_mutex); + + /* Next unload from csdev lists. */ + cscfg_unload_owned_cfgs_feats(owner_info); + +list_remove: + /* remove from load order list */ + list_del(&owner_info->item); + } + mutex_unlock(&cscfg_mutex); +} + +static void cscfg_clear_device(void) +{ + cscfg_unload_cfgs_on_exit(); + cscfg_configfs_release(cscfg_mgr); + device_unregister(cscfg_device()); +} + +/* Initialise system config management API device */ +int __init cscfg_init(void) +{ + int err = 0; + + /* create the device and init cscfg_mgr */ + err = cscfg_create_device(); + if (err) + return err; + + /* initialise configfs subsystem */ + err = cscfg_configfs_init(cscfg_mgr); + if (err) + goto exit_err; + + /* preload built-in configurations */ + err = cscfg_preload(THIS_MODULE); + if (err) + goto exit_err; + + dev_info(cscfg_device(), "CoreSight Configuration manager initialised"); + return 0; + +exit_err: + cscfg_clear_device(); + return err; +} + +void cscfg_exit(void) +{ + cscfg_clear_device(); +} diff --git a/drivers/hwtracing/coresight/coresight-syscfg.h b/drivers/hwtracing/coresight/coresight-syscfg.h new file mode 100644 index 000000000000..66e2db890d82 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-syscfg.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Coresight system configuration driver. + */ + +#ifndef CORESIGHT_SYSCFG_H +#define CORESIGHT_SYSCFG_H + +#include <linux/configfs.h> +#include <linux/coresight.h> +#include <linux/device.h> + +#include "coresight-config.h" + +/* + * Load operation types. + * When loading or unloading, another load operation cannot be run. + * When unloading configurations cannot be activated. + */ +enum cscfg_load_ops { + CSCFG_NONE, + CSCFG_LOAD, + CSCFG_UNLOAD +}; + +/** + * System configuration manager device. + * + * Contains lists of the loaded configurations and features, plus a list of CoreSight devices + * registered with the system as supporting configuration management. + * + * Need a device to 'own' some coresight system wide sysfs entries in + * perf events, configfs etc. + * + * @dev: The device. + * @csdev_desc_list: List of coresight devices registered with the configuration manager. + * @feat_desc_list: List of feature descriptors to load into registered devices. + * @config_desc_list: List of system configuration descriptors to load into registered devices. + * @load_order_list: Ordered list of owners for dynamically loaded configurations. + * @sys_active_cnt: Total number of active config descriptor references. + * @cfgfs_subsys: configfs subsystem used to manage configurations. + * @sysfs_active_config:Active config hash used if CoreSight controlled from sysfs. + * @sysfs_active_preset:Active preset index used if CoreSight controlled from sysfs. + * @load_state: A multi-stage load/unload operation is in progress. + */ +struct cscfg_manager { + struct device dev; + struct list_head csdev_desc_list; + struct list_head feat_desc_list; + struct list_head config_desc_list; + struct list_head load_order_list; + atomic_t sys_active_cnt; + struct configfs_subsystem cfgfs_subsys; + u32 sysfs_active_config; + int sysfs_active_preset; + enum cscfg_load_ops load_state; +}; + +/* get reference to dev in cscfg_manager */ +struct device *cscfg_device(void); + +/** + * List entry for Coresight devices that are registered as supporting complex + * config operations. + * + * @csdev: The registered device. + * @match_flags: The matching type information for adding features. + * @ops: Operations supported by the registered device. + * @item: list entry. + */ +struct cscfg_registered_csdev { + struct coresight_device *csdev; + u32 match_flags; + struct cscfg_csdev_feat_ops ops; + struct list_head item; +}; + +/* owner types for loading and unloading of config and feature sets */ +enum cscfg_load_owner_type { + CSCFG_OWNER_PRELOAD, + CSCFG_OWNER_MODULE, +}; + +/** + * Load item - item to add to the load order list allowing dynamic load and + * unload of configurations and features. Caller loading a config + * set provides a context handle for unload. API ensures that + * items unloaded strictly in reverse order from load to ensure + * dependencies are respected. + * + * @item: list entry for load order list. + * @type: type of owner - allows interpretation of owner_handle. + * @owner_handle: load context - handle for owner of loaded configs. + */ +struct cscfg_load_owner_info { + struct list_head item; + int type; + void *owner_handle; +}; + +/* internal core operations for cscfg */ +int __init cscfg_init(void); +void cscfg_exit(void); +int cscfg_preload(void *owner_handle); +const struct cscfg_feature_desc *cscfg_get_named_feat_desc(const char *name); +int cscfg_update_feat_param_val(struct cscfg_feature_desc *feat_desc, + int param_idx, u64 value); +int cscfg_config_sysfs_activate(struct cscfg_config_desc *cfg_desc, bool activate); +void cscfg_config_sysfs_set_preset(int preset); + +/* syscfg manager external API */ +int cscfg_load_config_sets(struct cscfg_config_desc **cfg_descs, + struct cscfg_feature_desc **feat_descs, + struct cscfg_load_owner_info *owner_info); +int cscfg_unload_config_sets(struct cscfg_load_owner_info *owner_info); +int cscfg_register_csdev(struct coresight_device *csdev, u32 match_flags, + struct cscfg_csdev_feat_ops *ops); +void cscfg_unregister_csdev(struct coresight_device *csdev); +int cscfg_activate_config(unsigned long cfg_hash); +void cscfg_deactivate_config(unsigned long cfg_hash); +void cscfg_csdev_reset_feats(struct coresight_device *csdev); +int cscfg_csdev_enable_active_config(struct coresight_device *csdev, + unsigned long cfg_hash, int preset); +void cscfg_csdev_disable_active_config(struct coresight_device *csdev); +void cscfg_config_sysfs_get_active_cfg(unsigned long *cfg_hash, int *preset); + +#endif /* CORESIGHT_SYSCFG_H */ diff --git a/drivers/hwtracing/coresight/coresight-sysfs.c b/drivers/hwtracing/coresight/coresight-sysfs.c new file mode 100644 index 000000000000..d2a6ed8bcc74 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-sysfs.c @@ -0,0 +1,667 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019, Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/kernel.h> +#include <linux/property.h> + +#include "coresight-priv.h" +#include "coresight-trace-id.h" + +/* + * Use IDR to map the hash of the source's device name + * to the pointer of path for the source. The idr is for + * the sources which aren't associated with CPU. + */ +static DEFINE_IDR(path_idr); + +/* + * When operating Coresight drivers from the sysFS interface, only a single + * path can exist from a tracer (associated to a CPU) to a sink. + */ +static DEFINE_PER_CPU(struct coresight_path *, tracer_path); + +ssize_t coresight_simple_show_pair(struct device *_dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = container_of(_dev, struct coresight_device, dev); + struct cs_pair_attribute *cs_attr = container_of(attr, struct cs_pair_attribute, attr); + u64 val; + + pm_runtime_get_sync(_dev->parent); + val = csdev_access_relaxed_read_pair(&csdev->access, cs_attr->lo_off, cs_attr->hi_off); + pm_runtime_put_sync(_dev->parent); + return sysfs_emit(buf, "0x%llx\n", val); +} +EXPORT_SYMBOL_GPL(coresight_simple_show_pair); + +ssize_t coresight_simple_show32(struct device *_dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = container_of(_dev, struct coresight_device, dev); + struct cs_off_attribute *cs_attr = container_of(attr, struct cs_off_attribute, attr); + u64 val; + + pm_runtime_get_sync(_dev->parent); + val = csdev_access_relaxed_read32(&csdev->access, cs_attr->off); + pm_runtime_put_sync(_dev->parent); + return sysfs_emit(buf, "0x%llx\n", val); +} +EXPORT_SYMBOL_GPL(coresight_simple_show32); + +static int coresight_enable_source_sysfs(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path) +{ + int ret; + + /* + * Comparison with CS_MODE_SYSFS works without taking any device + * specific spinlock because the truthyness of that comparison can only + * change with coresight_mutex held, which we already have here. + */ + lockdep_assert_held(&coresight_mutex); + if (coresight_get_mode(csdev) != CS_MODE_SYSFS) { + ret = source_ops(csdev)->enable(csdev, NULL, mode, path); + if (ret) + return ret; + } + + csdev->refcnt++; + + return 0; +} + +/** + * coresight_disable_source_sysfs - Drop the reference count by 1 and disable + * the device if there are no users left. + * + * @csdev: The coresight device to disable + * @data: Opaque data to pass on to the disable function of the source device. + * For example in perf mode this is a pointer to the struct perf_event. + * + * Returns true if the device has been disabled. + */ +static bool coresight_disable_source_sysfs(struct coresight_device *csdev, + void *data) +{ + lockdep_assert_held(&coresight_mutex); + if (coresight_get_mode(csdev) != CS_MODE_SYSFS) + return false; + + csdev->refcnt--; + if (csdev->refcnt == 0) { + coresight_disable_source(csdev, data); + return true; + } + return false; +} + +/** + * coresight_find_activated_sysfs_sink - returns the first sink activated via + * sysfs using connection based search starting from the source reference. + * + * @csdev: Coresight source device reference + */ +static struct coresight_device * +coresight_find_activated_sysfs_sink(struct coresight_device *csdev) +{ + int i; + struct coresight_device *sink = NULL; + + if ((csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && + csdev->sysfs_sink_activated) + return csdev; + + /* + * Recursively explore each port found on this element. + */ + for (i = 0; i < csdev->pdata->nr_outconns; i++) { + struct coresight_device *child_dev; + + child_dev = csdev->pdata->out_conns[i]->dest_dev; + if (child_dev) + sink = coresight_find_activated_sysfs_sink(child_dev); + if (sink) + return sink; + } + + return NULL; +} + +/** coresight_validate_source - make sure a source has the right credentials to + * be used via sysfs. + * @csdev: the device structure for a source. + * @function: the function this was called from. + * + * Assumes the coresight_mutex is held. + */ +static int coresight_validate_source_sysfs(struct coresight_device *csdev, + const char *function) +{ + u32 type, subtype; + + type = csdev->type; + subtype = csdev->subtype.source_subtype; + + if (type != CORESIGHT_DEV_TYPE_SOURCE) { + dev_err(&csdev->dev, "wrong device type in %s\n", function); + return -EINVAL; + } + + if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC && + subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE && + subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM && + subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS) { + dev_err(&csdev->dev, "wrong device subtype in %s\n", function); + return -EINVAL; + } + + return 0; +} + +int coresight_enable_sysfs(struct coresight_device *csdev) +{ + int cpu, ret = 0; + struct coresight_device *sink; + struct coresight_path *path; + enum coresight_dev_subtype_source subtype; + u32 hash; + + subtype = csdev->subtype.source_subtype; + + mutex_lock(&coresight_mutex); + + ret = coresight_validate_source_sysfs(csdev, __func__); + if (ret) + goto out; + + /* + * mode == SYSFS implies that it's already enabled. Don't look at the + * refcount to determine this because we don't claim the source until + * coresight_enable_source() so can still race with Perf mode which + * doesn't hold coresight_mutex. + */ + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { + /* + * There could be multiple applications driving the software + * source. So keep the refcount for each such user when the + * source is already enabled. + */ + if (subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE) + csdev->refcnt++; + goto out; + } + + sink = coresight_find_activated_sysfs_sink(csdev); + if (!sink) { + ret = -EINVAL; + goto out; + } + + path = coresight_build_path(csdev, sink); + if (IS_ERR(path)) { + pr_err("building path(s) failed\n"); + ret = PTR_ERR(path); + goto out; + } + + coresight_path_assign_trace_id(path, CS_MODE_SYSFS); + if (!IS_VALID_CS_TRACE_ID(path->trace_id)) + goto err_path; + + ret = coresight_enable_path(path, CS_MODE_SYSFS); + if (ret) + goto err_path; + + ret = coresight_enable_source_sysfs(csdev, CS_MODE_SYSFS, path); + if (ret) + goto err_source; + + switch (subtype) { + case CORESIGHT_DEV_SUBTYPE_SOURCE_PROC: + /* + * When working from sysFS it is important to keep track + * of the paths that were created so that they can be + * undone in 'coresight_disable()'. Since there can only + * be a single session per tracer (when working from sysFS) + * a per-cpu variable will do just fine. + */ + cpu = source_ops(csdev)->cpu_id(csdev); + per_cpu(tracer_path, cpu) = path; + break; + case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: + case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM: + case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS: + /* + * Use the hash of source's device name as ID + * and map the ID to the pointer of the path. + */ + hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev))); + ret = idr_alloc_u32(&path_idr, path, &hash, hash, GFP_KERNEL); + if (ret) + goto err_source; + break; + default: + /* We can't be here */ + break; + } + +out: + mutex_unlock(&coresight_mutex); + return ret; + +err_source: + coresight_disable_path(path); + +err_path: + coresight_release_path(path); + goto out; +} +EXPORT_SYMBOL_GPL(coresight_enable_sysfs); + +void coresight_disable_sysfs(struct coresight_device *csdev) +{ + int cpu, ret; + struct coresight_path *path = NULL; + u32 hash; + + mutex_lock(&coresight_mutex); + + ret = coresight_validate_source_sysfs(csdev, __func__); + if (ret) + goto out; + + if (!coresight_disable_source_sysfs(csdev, NULL)) + goto out; + + switch (csdev->subtype.source_subtype) { + case CORESIGHT_DEV_SUBTYPE_SOURCE_PROC: + cpu = source_ops(csdev)->cpu_id(csdev); + path = per_cpu(tracer_path, cpu); + per_cpu(tracer_path, cpu) = NULL; + break; + case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: + case CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM: + case CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS: + hash = hashlen_hash(hashlen_string(NULL, dev_name(&csdev->dev))); + /* Find the path by the hash. */ + path = idr_find(&path_idr, hash); + if (path == NULL) { + pr_err("Path is not found for %s\n", dev_name(&csdev->dev)); + goto out; + } + idr_remove(&path_idr, hash); + break; + default: + /* We can't be here */ + break; + } + + coresight_disable_path(path); + coresight_release_path(path); + +out: + mutex_unlock(&coresight_mutex); +} +EXPORT_SYMBOL_GPL(coresight_disable_sysfs); + +static ssize_t enable_sink_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", csdev->sysfs_sink_activated); +} + +static ssize_t enable_sink_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct coresight_device *csdev = to_coresight_device(dev); + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + csdev->sysfs_sink_activated = !!val; + + return size; + +} +static DEVICE_ATTR_RW(enable_sink); + +static ssize_t enable_source_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + guard(mutex)(&coresight_mutex); + return scnprintf(buf, PAGE_SIZE, "%u\n", + coresight_get_mode(csdev) == CS_MODE_SYSFS); +} + +static ssize_t enable_source_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret = 0; + unsigned long val; + struct coresight_device *csdev = to_coresight_device(dev); + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val) { + ret = coresight_enable_sysfs(csdev); + if (ret) + return ret; + } else { + coresight_disable_sysfs(csdev); + } + + return size; +} +static DEVICE_ATTR_RW(enable_source); + +static ssize_t label_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + + const char *str; + int ret; + + ret = fwnode_property_read_string(dev_fwnode(dev), "label", &str); + if (ret == 0) + return sysfs_emit(buf, "%s\n", str); + else + return ret; +} +static DEVICE_ATTR_RO(label); + +static umode_t label_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + + if (attr == &dev_attr_label.attr) { + if (fwnode_property_present(dev_fwnode(dev), "label")) + return attr->mode; + else + return 0; + } + + return attr->mode; +} + +static struct attribute *coresight_sink_attrs[] = { + &dev_attr_enable_sink.attr, + &dev_attr_label.attr, + NULL, +}; + +static struct attribute_group coresight_sink_group = { + .attrs = coresight_sink_attrs, + .is_visible = label_is_visible, +}; +__ATTRIBUTE_GROUPS(coresight_sink); + +static struct attribute *coresight_source_attrs[] = { + &dev_attr_enable_source.attr, + &dev_attr_label.attr, + NULL, +}; + +static struct attribute_group coresight_source_group = { + .attrs = coresight_source_attrs, + .is_visible = label_is_visible, +}; +__ATTRIBUTE_GROUPS(coresight_source); + +static struct attribute *coresight_link_attrs[] = { + &dev_attr_label.attr, + NULL, +}; + +static struct attribute_group coresight_link_group = { + .attrs = coresight_link_attrs, + .is_visible = label_is_visible, +}; +__ATTRIBUTE_GROUPS(coresight_link); + +static struct attribute *coresight_helper_attrs[] = { + &dev_attr_label.attr, + NULL, +}; + +static struct attribute_group coresight_helper_group = { + .attrs = coresight_helper_attrs, + .is_visible = label_is_visible, +}; +__ATTRIBUTE_GROUPS(coresight_helper); + +const struct device_type coresight_dev_type[] = { + [CORESIGHT_DEV_TYPE_SINK] = { + .name = "sink", + .groups = coresight_sink_groups, + }, + [CORESIGHT_DEV_TYPE_LINK] = { + .name = "link", + .groups = coresight_link_groups, + }, + [CORESIGHT_DEV_TYPE_LINKSINK] = { + .name = "linksink", + .groups = coresight_sink_groups, + }, + [CORESIGHT_DEV_TYPE_SOURCE] = { + .name = "source", + .groups = coresight_source_groups, + }, + [CORESIGHT_DEV_TYPE_HELPER] = { + .name = "helper", + .groups = coresight_helper_groups, + } +}; +/* Ensure the enum matches the names and groups */ +static_assert(ARRAY_SIZE(coresight_dev_type) == CORESIGHT_DEV_TYPE_MAX); + +/* + * Connections group - links attribute. + * Count of created links between coresight components in the group. + */ +static ssize_t nr_links_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct coresight_device *csdev = to_coresight_device(dev); + + return sprintf(buf, "%d\n", csdev->nr_links); +} +static DEVICE_ATTR_RO(nr_links); + +static struct attribute *coresight_conns_attrs[] = { + &dev_attr_nr_links.attr, + NULL, +}; + +static struct attribute_group coresight_conns_group = { + .attrs = coresight_conns_attrs, + .name = "connections", +}; + +/* + * Create connections group for CoreSight devices. + * This group will then be used to collate the sysfs links between + * devices. + */ +int coresight_create_conns_sysfs_group(struct coresight_device *csdev) +{ + int ret = 0; + + if (!csdev) + return -EINVAL; + + ret = sysfs_create_group(&csdev->dev.kobj, &coresight_conns_group); + if (ret) + return ret; + + csdev->has_conns_grp = true; + return ret; +} + +void coresight_remove_conns_sysfs_group(struct coresight_device *csdev) +{ + if (!csdev) + return; + + if (csdev->has_conns_grp) { + sysfs_remove_group(&csdev->dev.kobj, &coresight_conns_group); + csdev->has_conns_grp = false; + } +} + +int coresight_add_sysfs_link(struct coresight_sysfs_link *info) +{ + int ret = 0; + + if (!info) + return -EINVAL; + if (!info->orig || !info->target || + !info->orig_name || !info->target_name) + return -EINVAL; + if (!info->orig->has_conns_grp || !info->target->has_conns_grp) + return -EINVAL; + + /* first link orig->target */ + ret = sysfs_add_link_to_group(&info->orig->dev.kobj, + coresight_conns_group.name, + &info->target->dev.kobj, + info->orig_name); + if (ret) + return ret; + + /* second link target->orig */ + ret = sysfs_add_link_to_group(&info->target->dev.kobj, + coresight_conns_group.name, + &info->orig->dev.kobj, + info->target_name); + + /* error in second link - remove first - otherwise inc counts */ + if (ret) { + sysfs_remove_link_from_group(&info->orig->dev.kobj, + coresight_conns_group.name, + info->orig_name); + } else { + info->orig->nr_links++; + info->target->nr_links++; + } + + return ret; +} +EXPORT_SYMBOL_GPL(coresight_add_sysfs_link); + +void coresight_remove_sysfs_link(struct coresight_sysfs_link *info) +{ + if (!info) + return; + if (!info->orig || !info->target || + !info->orig_name || !info->target_name) + return; + + sysfs_remove_link_from_group(&info->orig->dev.kobj, + coresight_conns_group.name, + info->orig_name); + + sysfs_remove_link_from_group(&info->target->dev.kobj, + coresight_conns_group.name, + info->target_name); + + info->orig->nr_links--; + info->target->nr_links--; +} +EXPORT_SYMBOL_GPL(coresight_remove_sysfs_link); + +/* + * coresight_make_links: Make a link for a connection from a @orig + * device to @target, represented by @conn. + * + * e.g, for devOrig[output_X] -> devTarget[input_Y] is represented + * as two symbolic links : + * + * /sys/.../devOrig/out:X -> /sys/.../devTarget/ + * /sys/.../devTarget/in:Y -> /sys/.../devOrig/ + * + * The link names are allocated for a device where it appears. i.e, the + * "out" link on the master and "in" link on the slave device. + * The link info is stored in the connection record for avoiding + * the reconstruction of names for removal. + */ +int coresight_make_links(struct coresight_device *orig, + struct coresight_connection *conn, + struct coresight_device *target) +{ + int ret = -ENOMEM; + char *outs = NULL, *ins = NULL; + struct coresight_sysfs_link *link = NULL; + + /* Helper devices aren't shown in sysfs */ + if (conn->dest_port == -1 && conn->src_port == -1) + return 0; + + do { + outs = devm_kasprintf(&orig->dev, GFP_KERNEL, + "out:%d", conn->src_port); + if (!outs) + break; + ins = devm_kasprintf(&target->dev, GFP_KERNEL, + "in:%d", conn->dest_port); + if (!ins) + break; + link = devm_kzalloc(&orig->dev, + sizeof(struct coresight_sysfs_link), + GFP_KERNEL); + if (!link) + break; + + link->orig = orig; + link->target = target; + link->orig_name = outs; + link->target_name = ins; + + ret = coresight_add_sysfs_link(link); + if (ret) + break; + + conn->link = link; + return 0; + } while (0); + + return ret; +} + +/* + * coresight_remove_links: Remove the sysfs links for a given connection @conn, + * from @orig device to @target device. See coresight_make_links() for more + * details. + */ +void coresight_remove_links(struct coresight_device *orig, + struct coresight_connection *conn) +{ + if (!orig || !conn->link) + return; + + coresight_remove_sysfs_link(conn->link); + + devm_kfree(&conn->dest_dev->dev, conn->link->target_name); + devm_kfree(&orig->dev, conn->link->orig_name); + devm_kfree(&orig->dev, conn->link); + conn->link = NULL; +} diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c new file mode 100644 index 000000000000..36599c431be6 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -0,0 +1,1066 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2012, The Linux Foundation. All rights reserved. + * + * Description: CoreSight Trace Memory Controller driver + */ + +#include <linux/acpi.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/types.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/miscdevice.h> +#include <linux/mutex.h> +#include <linux/property.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/dma-mapping.h> +#include <linux/spinlock.h> +#include <linux/pm_runtime.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> +#include <linux/coresight.h> +#include <linux/amba/bus.h> +#include <linux/platform_device.h> + +#include "coresight-priv.h" +#include "coresight-tmc.h" + +DEFINE_CORESIGHT_DEVLIST(etb_devs, "tmc_etb"); +DEFINE_CORESIGHT_DEVLIST(etf_devs, "tmc_etf"); +DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr"); + +int tmc_wait_for_tmcready(struct tmc_drvdata *drvdata) +{ + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa = &csdev->access; + + /* Ensure formatter, unformatter and hardware fifo are empty */ + if (coresight_timeout(csa, TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { + dev_err(&csdev->dev, + "timeout while waiting for TMC to be Ready\n"); + return -EBUSY; + } + return 0; +} + +void tmc_flush_and_stop(struct tmc_drvdata *drvdata) +{ + struct coresight_device *csdev = drvdata->csdev; + struct csdev_access *csa = &csdev->access; + u32 ffcr; + + ffcr = readl_relaxed(drvdata->base + TMC_FFCR); + ffcr |= TMC_FFCR_STOP_ON_FLUSH; + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); + ffcr |= BIT(TMC_FFCR_FLUSHMAN_BIT); + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); + /* Ensure flush completes */ + if (coresight_timeout(csa, TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { + dev_err(&csdev->dev, + "timeout while waiting for completion of Manual Flush\n"); + } + + tmc_wait_for_tmcready(drvdata); +} + +void tmc_enable_hw(struct tmc_drvdata *drvdata) +{ + writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL); +} + +void tmc_disable_hw(struct tmc_drvdata *drvdata) +{ + writel_relaxed(0x0, drvdata->base + TMC_CTL); +} + +u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata) +{ + u32 mask = 0; + + /* + * When moving RRP or an offset address forward, the new values must + * be byte-address aligned to the width of the trace memory databus + * _and_ to a frame boundary (16 byte), whichever is the biggest. For + * example, for 32-bit, 64-bit and 128-bit wide trace memory, the four + * LSBs must be 0s. For 256-bit wide trace memory, the five LSBs must + * be 0s. + */ + switch (drvdata->memwidth) { + case TMC_MEM_INTF_WIDTH_32BITS: + case TMC_MEM_INTF_WIDTH_64BITS: + case TMC_MEM_INTF_WIDTH_128BITS: + mask = GENMASK(31, 4); + break; + case TMC_MEM_INTF_WIDTH_256BITS: + mask = GENMASK(31, 5); + break; + } + + return mask; +} + +static bool is_tmc_crashdata_valid(struct tmc_drvdata *drvdata) +{ + struct tmc_crash_metadata *mdata; + + if (!tmc_has_reserved_buffer(drvdata) || + !tmc_has_crash_mdata_buffer(drvdata)) + return false; + + mdata = drvdata->crash_mdata.vaddr; + + /* Check version match */ + if (mdata->version != CS_CRASHDATA_VERSION) + return false; + + /* Check for valid metadata */ + if (!mdata->valid) { + dev_dbg(&drvdata->csdev->dev, + "Data invalid in tmc crash metadata\n"); + return false; + } + + /* + * Buffer address given by metadata for retrieval of trace data + * from previous boot is expected to be same as the reserved + * trace buffer memory region provided through DTS + */ + if (drvdata->resrv_buf.paddr != mdata->trace_paddr) { + dev_dbg(&drvdata->csdev->dev, + "Trace buffer address of previous boot invalid\n"); + return false; + } + + /* Check data integrity of metadata */ + if (mdata->crc32_mdata != find_crash_metadata_crc(mdata)) { + dev_err(&drvdata->csdev->dev, + "CRC mismatch in tmc crash metadata\n"); + return false; + } + /* Check data integrity of tracedata */ + if (mdata->crc32_tdata != find_crash_tracedata_crc(drvdata, mdata)) { + dev_err(&drvdata->csdev->dev, + "CRC mismatch in tmc crash tracedata\n"); + return false; + } + + return true; +} + +static inline ssize_t tmc_get_resvbuf_trace(struct tmc_drvdata *drvdata, + loff_t pos, size_t len, char **bufpp) +{ + s64 offset; + ssize_t actual = len; + struct tmc_resrv_buf *rbuf = &drvdata->resrv_buf; + + if (pos + actual > rbuf->len) + actual = rbuf->len - pos; + if (actual <= 0) + return 0; + + /* Compute the offset from which we read the data */ + offset = rbuf->offset + pos; + if (offset >= rbuf->size) + offset -= rbuf->size; + + /* Adjust the length to limit this transaction to end of buffer */ + actual = (actual < (rbuf->size - offset)) ? + actual : rbuf->size - offset; + + *bufpp = (char *)rbuf->vaddr + offset; + + return actual; +} + +static int tmc_prepare_crashdata(struct tmc_drvdata *drvdata) +{ + char *bufp; + ssize_t len; + u32 status, size; + u64 rrp, rwp, dba; + struct tmc_resrv_buf *rbuf; + struct tmc_crash_metadata *mdata; + + mdata = drvdata->crash_mdata.vaddr; + rbuf = &drvdata->resrv_buf; + + rrp = mdata->tmc_rrp; + rwp = mdata->tmc_rwp; + dba = mdata->tmc_dba; + status = mdata->tmc_sts; + size = mdata->tmc_ram_size << 2; + + /* Sync the buffer pointers */ + rbuf->offset = rrp - dba; + if (status & TMC_STS_FULL) + rbuf->len = size; + else + rbuf->len = rwp - rrp; + + /* Additional sanity checks for validating metadata */ + if ((rbuf->offset > size) || + (rbuf->len > size)) { + dev_dbg(&drvdata->csdev->dev, + "Offset and length invalid in tmc crash metadata\n"); + return -EINVAL; + } + + if (status & TMC_STS_FULL) { + len = tmc_get_resvbuf_trace(drvdata, 0x0, + CORESIGHT_BARRIER_PKT_SIZE, &bufp); + if (len >= CORESIGHT_BARRIER_PKT_SIZE) { + coresight_insert_barrier_packet(bufp); + /* Recalculate crc */ + mdata->crc32_tdata = find_crash_tracedata_crc(drvdata, + mdata); + mdata->crc32_mdata = find_crash_metadata_crc(mdata); + } + } + + return 0; +} + +static int tmc_read_prepare(struct tmc_drvdata *drvdata) +{ + int ret = 0; + + switch (drvdata->config_type) { + case TMC_CONFIG_TYPE_ETB: + case TMC_CONFIG_TYPE_ETF: + ret = tmc_read_prepare_etb(drvdata); + break; + case TMC_CONFIG_TYPE_ETR: + ret = tmc_read_prepare_etr(drvdata); + break; + default: + ret = -EINVAL; + } + + if (!ret) + dev_dbg(&drvdata->csdev->dev, "TMC read start\n"); + + return ret; +} + +static int tmc_read_unprepare(struct tmc_drvdata *drvdata) +{ + int ret = 0; + + switch (drvdata->config_type) { + case TMC_CONFIG_TYPE_ETB: + case TMC_CONFIG_TYPE_ETF: + ret = tmc_read_unprepare_etb(drvdata); + break; + case TMC_CONFIG_TYPE_ETR: + ret = tmc_read_unprepare_etr(drvdata); + break; + default: + ret = -EINVAL; + } + + if (!ret) + dev_dbg(&drvdata->csdev->dev, "TMC read end\n"); + + return ret; +} + +static int tmc_open(struct inode *inode, struct file *file) +{ + int ret; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + + ret = tmc_read_prepare(drvdata); + if (ret) + return ret; + + nonseekable_open(inode, file); + + dev_dbg(&drvdata->csdev->dev, "%s: successfully opened\n", __func__); + return 0; +} + +static ssize_t tmc_get_sysfs_trace(struct tmc_drvdata *drvdata, loff_t pos, size_t len, + char **bufpp) +{ + switch (drvdata->config_type) { + case TMC_CONFIG_TYPE_ETB: + case TMC_CONFIG_TYPE_ETF: + return tmc_etb_get_sysfs_trace(drvdata, pos, len, bufpp); + case TMC_CONFIG_TYPE_ETR: + return tmc_etr_get_sysfs_trace(drvdata, pos, len, bufpp); + } + + return -EINVAL; +} + +static ssize_t tmc_read(struct file *file, char __user *data, size_t len, + loff_t *ppos) +{ + char *bufp; + ssize_t actual; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + actual = tmc_get_sysfs_trace(drvdata, *ppos, len, &bufp); + if (actual <= 0) + return 0; + + if (copy_to_user(data, bufp, actual)) { + dev_dbg(&drvdata->csdev->dev, + "%s: copy_to_user failed\n", __func__); + return -EFAULT; + } + + *ppos += actual; + dev_dbg(&drvdata->csdev->dev, "%zu bytes copied\n", actual); + + return actual; +} + +static int tmc_release(struct inode *inode, struct file *file) +{ + int ret; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, miscdev); + + ret = tmc_read_unprepare(drvdata); + if (ret) + return ret; + + dev_dbg(&drvdata->csdev->dev, "%s: released\n", __func__); + return 0; +} + +static const struct file_operations tmc_fops = { + .owner = THIS_MODULE, + .open = tmc_open, + .read = tmc_read, + .release = tmc_release, +}; + +static int tmc_crashdata_open(struct inode *inode, struct file *file) +{ + int err = 0; + unsigned long flags; + struct tmc_resrv_buf *rbuf; + struct tmc_crash_metadata *mdata; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, + crashdev); + + mdata = drvdata->crash_mdata.vaddr; + rbuf = &drvdata->resrv_buf; + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (mdata->valid) + rbuf->reading = true; + else + err = -ENOENT; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + if (err) + goto exit; + + nonseekable_open(inode, file); + dev_dbg(&drvdata->csdev->dev, "%s: successfully opened\n", __func__); +exit: + return err; +} + +static ssize_t tmc_crashdata_read(struct file *file, char __user *data, + size_t len, loff_t *ppos) +{ + char *bufp; + ssize_t actual; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, + crashdev); + + actual = tmc_get_resvbuf_trace(drvdata, *ppos, len, &bufp); + if (actual <= 0) + return 0; + + if (copy_to_user(data, bufp, actual)) { + dev_dbg(&drvdata->csdev->dev, + "%s: copy_to_user failed\n", __func__); + return -EFAULT; + } + + *ppos += actual; + dev_dbg(&drvdata->csdev->dev, "%zu bytes copied\n", actual); + + return actual; +} + +static int tmc_crashdata_release(struct inode *inode, struct file *file) +{ + int ret = 0; + unsigned long flags; + struct tmc_resrv_buf *rbuf; + struct tmc_drvdata *drvdata = container_of(file->private_data, + struct tmc_drvdata, + crashdev); + + rbuf = &drvdata->resrv_buf; + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + rbuf->reading = false; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_dbg(&drvdata->csdev->dev, "%s: released\n", __func__); + return ret; +} + +static const struct file_operations tmc_crashdata_fops = { + .owner = THIS_MODULE, + .open = tmc_crashdata_open, + .read = tmc_crashdata_read, + .release = tmc_crashdata_release, +}; + +static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid) +{ + enum tmc_mem_intf_width memwidth; + + /* + * Excerpt from the TRM: + * + * DEVID::MEMWIDTH[10:8] + * 0x2 Memory interface databus is 32 bits wide. + * 0x3 Memory interface databus is 64 bits wide. + * 0x4 Memory interface databus is 128 bits wide. + * 0x5 Memory interface databus is 256 bits wide. + */ + switch (BMVAL(devid, 8, 10)) { + case 0x2: + memwidth = TMC_MEM_INTF_WIDTH_32BITS; + break; + case 0x3: + memwidth = TMC_MEM_INTF_WIDTH_64BITS; + break; + case 0x4: + memwidth = TMC_MEM_INTF_WIDTH_128BITS; + break; + case 0x5: + memwidth = TMC_MEM_INTF_WIDTH_256BITS; + break; + default: + memwidth = 0; + } + + return memwidth; +} + +static struct attribute *coresight_tmc_mgmt_attrs[] = { + coresight_simple_reg32(rsz, TMC_RSZ), + coresight_simple_reg32(sts, TMC_STS), + coresight_simple_reg64(rrp, TMC_RRP, TMC_RRPHI), + coresight_simple_reg64(rwp, TMC_RWP, TMC_RWPHI), + coresight_simple_reg32(trg, TMC_TRG), + coresight_simple_reg32(ctl, TMC_CTL), + coresight_simple_reg32(ffsr, TMC_FFSR), + coresight_simple_reg32(ffcr, TMC_FFCR), + coresight_simple_reg32(mode, TMC_MODE), + coresight_simple_reg32(pscr, TMC_PSCR), + coresight_simple_reg32(devid, CORESIGHT_DEVID), + coresight_simple_reg64(dba, TMC_DBALO, TMC_DBAHI), + coresight_simple_reg32(axictl, TMC_AXICTL), + coresight_simple_reg32(authstatus, TMC_AUTHSTATUS), + NULL, +}; + +static ssize_t trigger_cntr_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val = drvdata->trigger_cntr; + + return sprintf(buf, "%#lx\n", val); +} + +static ssize_t trigger_cntr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 16, &val); + if (ret) + return ret; + + drvdata->trigger_cntr = val; + return size; +} +static DEVICE_ATTR_RW(trigger_cntr); + +static ssize_t buffer_size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sprintf(buf, "%#x\n", drvdata->size); +} + +static ssize_t buffer_size_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + unsigned long val; + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + /* Only permitted for TMC-ETRs */ + if (drvdata->config_type != TMC_CONFIG_TYPE_ETR) + return -EPERM; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + /* The buffer size should be page aligned */ + if (val & (PAGE_SIZE - 1)) + return -EINVAL; + drvdata->size = val; + return size; +} + +static DEVICE_ATTR_RW(buffer_size); + +static ssize_t stop_on_flush_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sprintf(buf, "%#x\n", drvdata->stop_on_flush); +} + +static ssize_t stop_on_flush_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + int ret; + u8 val; + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtou8(buf, 0, &val); + if (ret) + return ret; + if (val) + drvdata->stop_on_flush = true; + else + drvdata->stop_on_flush = false; + + return size; +} + +static DEVICE_ATTR_RW(stop_on_flush); + + +static struct attribute *coresight_tmc_attrs[] = { + &dev_attr_trigger_cntr.attr, + &dev_attr_buffer_size.attr, + &dev_attr_stop_on_flush.attr, + NULL, +}; + +static const struct attribute_group coresight_tmc_group = { + .attrs = coresight_tmc_attrs, +}; + +static const struct attribute_group coresight_tmc_mgmt_group = { + .attrs = coresight_tmc_mgmt_attrs, + .name = "mgmt", +}; + +static const struct attribute_group *coresight_etf_groups[] = { + &coresight_tmc_group, + &coresight_tmc_mgmt_group, + NULL, +}; + +static const struct attribute_group *coresight_etr_groups[] = { + &coresight_etr_group, + &coresight_tmc_group, + &coresight_tmc_mgmt_group, + NULL, +}; + +static bool tmc_etr_can_use_sg(struct device *dev) +{ + int ret; + u8 val_u8; + + /* + * Presence of the property 'arm,scatter-gather' is checked + * on the platform for the feature support, rather than its + * value. + */ + if (is_of_node(dev->fwnode)) { + return fwnode_property_present(dev->fwnode, "arm,scatter-gather"); + } else if (is_acpi_device_node(dev->fwnode)) { + /* + * TMC_DEVID_NOSCAT test in tmc_etr_setup_caps(), has already ensured + * this property is only checked for Coresight SoC 400 TMC configured + * as ETR. + */ + ret = fwnode_property_read_u8(dev->fwnode, "arm-armhc97c-sg-enable", &val_u8); + if (!ret) + return !!val_u8; + + if (fwnode_property_present(dev->fwnode, "arm,scatter-gather")) { + pr_warn_once("Deprecated ACPI property - arm,scatter-gather\n"); + return true; + } + } + return false; +} + +static bool tmc_etr_has_non_secure_access(struct tmc_drvdata *drvdata) +{ + u32 auth = readl_relaxed(drvdata->base + TMC_AUTHSTATUS); + + return (auth & TMC_AUTH_NSID_MASK) == 0x3; +} + +static const struct amba_id tmc_ids[]; + +static int of_tmc_get_reserved_resource_by_name(struct device *dev, + const char *name, + struct resource *res) +{ + int rc = -ENODEV; + + rc = of_reserved_mem_region_to_resource_byname(dev->of_node, name, res); + if (rc < 0) + return rc; + + if (res->start == 0 || resource_size(res) == 0) + rc = -ENODEV; + + return rc; +} + +static void tmc_get_reserved_region(struct device *parent) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(parent); + struct resource res; + + if (of_tmc_get_reserved_resource_by_name(parent, "tracedata", &res)) + return; + + drvdata->resrv_buf.vaddr = memremap(res.start, + resource_size(&res), + MEMREMAP_WC); + if (IS_ERR_OR_NULL(drvdata->resrv_buf.vaddr)) { + dev_err(parent, "Reserved trace buffer mapping failed\n"); + return; + } + + drvdata->resrv_buf.paddr = res.start; + drvdata->resrv_buf.size = resource_size(&res); + + if (of_tmc_get_reserved_resource_by_name(parent, "metadata", &res)) + return; + + drvdata->crash_mdata.vaddr = memremap(res.start, + resource_size(&res), + MEMREMAP_WC); + if (IS_ERR_OR_NULL(drvdata->crash_mdata.vaddr)) { + dev_err(parent, "Metadata memory mapping failed\n"); + return; + } + + drvdata->crash_mdata.paddr = res.start; + drvdata->crash_mdata.size = resource_size(&res); +} + +/* Detect and initialise the capabilities of a TMC ETR */ +static int tmc_etr_setup_caps(struct device *parent, u32 devid, + struct csdev_access *access) +{ + int rc; + u32 tmc_pid, dma_mask = 0; + struct tmc_drvdata *drvdata = dev_get_drvdata(parent); + void *dev_caps; + + if (!tmc_etr_has_non_secure_access(drvdata)) + return -EACCES; + + tmc_pid = coresight_get_pid(access); + dev_caps = coresight_get_uci_data_from_amba(tmc_ids, tmc_pid); + + /* Set the unadvertised capabilities */ + tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps); + + if (!(devid & TMC_DEVID_NOSCAT) && tmc_etr_can_use_sg(parent)) + tmc_etr_set_cap(drvdata, TMC_ETR_SG); + + /* Check if the AXI address width is available */ + if (devid & TMC_DEVID_AXIAW_VALID) + dma_mask = ((devid >> TMC_DEVID_AXIAW_SHIFT) & + TMC_DEVID_AXIAW_MASK); + + /* + * Unless specified in the device configuration, ETR uses a 40-bit + * AXI master in place of the embedded SRAM of ETB/ETF. + */ + switch (dma_mask) { + case 32: + case 40: + case 44: + case 48: + case 52: + dev_info(parent, "Detected dma mask %dbits\n", dma_mask); + break; + default: + dma_mask = 40; + } + + rc = dma_set_mask_and_coherent(parent, DMA_BIT_MASK(dma_mask)); + if (rc) + dev_err(parent, "Failed to setup DMA mask: %d\n", rc); + return rc; +} + +static u32 tmc_etr_get_default_buffer_size(struct device *dev) +{ + u32 size; + + if (fwnode_property_read_u32(dev->fwnode, "arm,buffer-size", &size)) + size = SZ_1M; + return size; +} + +static u32 tmc_etr_get_max_burst_size(struct device *dev) +{ + u32 burst_size; + + if (fwnode_property_read_u32(dev->fwnode, "arm,max-burst-size", + &burst_size)) + return TMC_AXICTL_WR_BURST_16; + + /* Only permissible values are 0 to 15 */ + if (burst_size > 0xF) + burst_size = TMC_AXICTL_WR_BURST_16; + + return burst_size; +} + +static void register_crash_dev_interface(struct tmc_drvdata *drvdata, + const char *name) +{ + drvdata->crashdev.name = + devm_kasprintf(&drvdata->csdev->dev, GFP_KERNEL, "%s_%s", "crash", name); + drvdata->crashdev.minor = MISC_DYNAMIC_MINOR; + drvdata->crashdev.fops = &tmc_crashdata_fops; + if (misc_register(&drvdata->crashdev)) { + dev_dbg(&drvdata->csdev->dev, + "Failed to setup user interface for crashdata\n"); + drvdata->crashdev.fops = NULL; + } else + dev_info(&drvdata->csdev->dev, + "Valid crash tracedata found\n"); +} + +static int __tmc_probe(struct device *dev, struct resource *res) +{ + int ret = 0; + u32 devid; + void __iomem *base; + struct coresight_platform_data *pdata = NULL; + struct tmc_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + struct coresight_dev_list *dev_list = NULL; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + dev_set_drvdata(dev, drvdata); + + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + + ret = -ENOMEM; + + /* Validity for the resource is already checked by the AMBA core */ + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto out; + } + + drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); + + raw_spin_lock_init(&drvdata->spinlock); + + devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID); + drvdata->config_type = BMVAL(devid, 6, 7); + drvdata->memwidth = tmc_get_memwidth(devid); + /* This device is not associated with a session */ + drvdata->pid = -1; + drvdata->etr_mode = ETR_MODE_AUTO; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { + drvdata->size = tmc_etr_get_default_buffer_size(dev); + drvdata->max_burst_size = tmc_etr_get_max_burst_size(dev); + } else { + drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; + } + + tmc_get_reserved_region(dev); + + desc.dev = dev; + + switch (drvdata->config_type) { + case TMC_CONFIG_TYPE_ETB: + desc.groups = coresight_etf_groups; + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + desc.ops = &tmc_etb_cs_ops; + dev_list = &etb_devs; + break; + case TMC_CONFIG_TYPE_ETR: + desc.groups = coresight_etr_groups; + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM; + desc.ops = &tmc_etr_cs_ops; + ret = tmc_etr_setup_caps(dev, devid, &desc.access); + if (ret) + goto out; + idr_init(&drvdata->idr); + mutex_init(&drvdata->idr_mutex); + dev_list = &etr_devs; + break; + case TMC_CONFIG_TYPE_ETF: + desc.groups = coresight_etf_groups; + desc.type = CORESIGHT_DEV_TYPE_LINKSINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO; + desc.ops = &tmc_etf_cs_ops; + dev_list = &etf_devs; + break; + default: + pr_err("%s: Unsupported TMC config\n", desc.name); + ret = -EINVAL; + goto out; + } + + desc.name = coresight_alloc_device_name(dev_list, dev); + if (!desc.name) { + ret = -ENOMEM; + goto out; + } + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) { + ret = PTR_ERR(pdata); + goto out; + } + dev->platform_data = pdata; + desc.pdata = pdata; + + coresight_clear_self_claim_tag(&desc.access); + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto out; + } + + drvdata->miscdev.name = desc.name; + drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; + drvdata->miscdev.fops = &tmc_fops; + ret = misc_register(&drvdata->miscdev); + if (ret) { + coresight_unregister(drvdata->csdev); + goto out; + } + +out: + if (is_tmc_crashdata_valid(drvdata) && + !tmc_prepare_crashdata(drvdata)) + register_crash_dev_interface(drvdata, desc.name); + return ret; +} + +static int tmc_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + + ret = __tmc_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void tmc_shutdown(struct amba_device *adev) +{ + unsigned long flags; + struct tmc_drvdata *drvdata = amba_get_drvdata(adev); + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + if (coresight_get_mode(drvdata->csdev) == CS_MODE_DISABLED) + goto out; + + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) + tmc_etr_disable_hw(drvdata); + + /* + * We do not care about coresight unregister here unlike remove + * callback which is required for making coresight modular since + * the system is going down after this. + */ +out: + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); +} + +static void __tmc_remove(struct device *dev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev); + + /* + * Since misc_open() holds a refcount on the f_ops, which is + * etb fops in this case, device is there until last file + * handler to this device is closed. + */ + misc_deregister(&drvdata->miscdev); + if (drvdata->crashdev.fops) + misc_deregister(&drvdata->crashdev); + coresight_unregister(drvdata->csdev); +} + +static void tmc_remove(struct amba_device *adev) +{ + __tmc_remove(&adev->dev); +} + +static const struct amba_id tmc_ids[] = { + CS_AMBA_ID(0x000bb961), + /* Coresight SoC 600 TMC-ETR/ETS */ + CS_AMBA_ID_DATA(0x000bb9e8, (unsigned long)CORESIGHT_SOC_600_ETR_CAPS), + /* Coresight SoC 600 TMC-ETB */ + CS_AMBA_ID(0x000bb9e9), + /* Coresight SoC 600 TMC-ETF */ + CS_AMBA_ID(0x000bb9ea), + { 0, 0, NULL }, +}; + +MODULE_DEVICE_TABLE(amba, tmc_ids); + +static struct amba_driver tmc_driver = { + .drv = { + .name = "coresight-tmc", + .suppress_bind_attrs = true, + }, + .probe = tmc_probe, + .shutdown = tmc_shutdown, + .remove = tmc_remove, + .id_table = tmc_ids, +}; + +static int tmc_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret = 0; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = __tmc_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void tmc_platform_remove(struct platform_device *pdev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + __tmc_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_PM +static int tmc_runtime_suspend(struct device *dev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev); + + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); + + return 0; +} + +static int tmc_runtime_resume(struct device *dev) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev); + int ret; + + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; + + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; +} +#endif + +static const struct dev_pm_ops tmc_dev_pm_ops = { + SET_RUNTIME_PM_OPS(tmc_runtime_suspend, tmc_runtime_resume, NULL) +}; + +#ifdef CONFIG_ACPI +static const struct acpi_device_id tmc_acpi_ids[] = { + {"ARMHC501", 0, 0, 0}, /* ARM CoreSight ETR */ + {"ARMHC97C", 0, 0, 0}, /* ARM CoreSight SoC-400 TMC, SoC-600 ETF/ETB */ + {}, +}; +MODULE_DEVICE_TABLE(acpi, tmc_acpi_ids); +#endif + +static struct platform_driver tmc_platform_driver = { + .probe = tmc_platform_probe, + .remove = tmc_platform_remove, + .driver = { + .name = "coresight-tmc-platform", + .acpi_match_table = ACPI_PTR(tmc_acpi_ids), + .suppress_bind_attrs = true, + .pm = &tmc_dev_pm_ops, + }, +}; + +static int __init tmc_init(void) +{ + return coresight_init_driver("tmc", &tmc_driver, &tmc_platform_driver, THIS_MODULE); +} + +static void __exit tmc_exit(void) +{ + coresight_remove_driver(&tmc_driver, &tmc_platform_driver); +} +module_init(tmc_init); +module_exit(tmc_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_DESCRIPTION("Arm CoreSight Trace Memory Controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index a5f053f2db2c..8882b1c4cdc0 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/atomic.h> #include <linux/circ_buf.h> #include <linux/coresight.h> #include <linux/perf_event.h> @@ -15,34 +16,48 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev, struct perf_output_handle *handle); -static void __tmc_etb_enable_hw(struct tmc_drvdata *drvdata) +static int __tmc_etb_enable_hw(struct tmc_drvdata *drvdata) { + int rc = 0; + u32 ffcr; + CS_UNLOCK(drvdata->base); /* Wait for TMCSReady bit to be set */ - tmc_wait_for_tmcready(drvdata); + rc = tmc_wait_for_tmcready(drvdata); + if (rc) { + dev_err(&drvdata->csdev->dev, + "Failed to enable: TMC not ready\n"); + CS_LOCK(drvdata->base); + return rc; + } writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE); - writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | - TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT | - TMC_FFCR_TRIGON_TRIGIN, - drvdata->base + TMC_FFCR); + + ffcr = TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | TMC_FFCR_FON_FLIN | + TMC_FFCR_FON_TRIG_EVT | TMC_FFCR_TRIGON_TRIGIN; + if (drvdata->stop_on_flush) + ffcr |= TMC_FFCR_STOP_ON_FLUSH; + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG); tmc_enable_hw(drvdata); CS_LOCK(drvdata->base); + return rc; } static int tmc_etb_enable_hw(struct tmc_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; - __tmc_etb_enable_hw(drvdata); - return 0; + rc = __tmc_etb_enable_hw(drvdata); + if (rc) + coresight_disclaim_device(drvdata->csdev); + return rc; } static void tmc_etb_dump_hw(struct tmc_drvdata *drvdata) @@ -77,7 +92,7 @@ static void __tmc_etb_disable_hw(struct tmc_drvdata *drvdata) * When operating in sysFS mode the content of the buffer needs to be * read before the TMC is disabled. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) tmc_etb_dump_hw(drvdata); tmc_disable_hw(drvdata); @@ -87,15 +102,23 @@ static void __tmc_etb_disable_hw(struct tmc_drvdata *drvdata) static void tmc_etb_disable_hw(struct tmc_drvdata *drvdata) { __tmc_etb_disable_hw(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); } -static void __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) +static int __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) { + int rc = 0; + CS_UNLOCK(drvdata->base); /* Wait for TMCSReady bit to be set */ - tmc_wait_for_tmcready(drvdata); + rc = tmc_wait_for_tmcready(drvdata); + if (rc) { + dev_err(&drvdata->csdev->dev, + "Failed to enable : TMC is not ready\n"); + CS_LOCK(drvdata->base); + return rc; + } writel_relaxed(TMC_MODE_HARDWARE_FIFO, drvdata->base + TMC_MODE); writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI, @@ -104,26 +127,31 @@ static void __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) tmc_enable_hw(drvdata); CS_LOCK(drvdata->base); + return rc; } static int tmc_etf_enable_hw(struct tmc_drvdata *drvdata) { - int rc = coresight_claim_device(drvdata->base); + int rc = coresight_claim_device(drvdata->csdev); if (rc) return rc; - __tmc_etf_enable_hw(drvdata); - return 0; + rc = __tmc_etf_enable_hw(drvdata); + if (rc) + coresight_disclaim_device(drvdata->csdev); + return rc; } static void tmc_etf_disable_hw(struct tmc_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + CS_UNLOCK(drvdata->base); tmc_flush_and_stop(drvdata); tmc_disable_hw(drvdata); - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } @@ -157,9 +185,9 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) * If we don't have a buffer release the lock and allocate memory. * Otherwise keep the lock and move along. */ - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); if (!drvdata->buf) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* Allocating the memory here while outside of the spinlock */ buf = kzalloc(drvdata->size, GFP_KERNEL); @@ -167,7 +195,7 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) return -ENOMEM; /* Let's try again */ - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); } if (drvdata->reading) { @@ -180,8 +208,10 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) * sink is already enabled no memory is needed and the HW need not be * touched. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { + csdev->refcnt++; goto out; + } /* * If drvdata::buf isn't NULL, memory was allocated for a previous @@ -198,15 +228,16 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) used = true; drvdata->buf = buf; } - ret = tmc_etb_enable_hw(drvdata); - if (!ret) - drvdata->mode = CS_MODE_SYSFS; - else + if (!ret) { + coresight_set_mode(csdev, CS_MODE_SYSFS); + csdev->refcnt++; + } else { /* Free up the buffer if we failed to enable */ used = false; + } out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* Free memory outside the spinlock if need be */ if (!used) @@ -215,50 +246,76 @@ out: return ret; } -static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) +static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, + struct coresight_path *path) { int ret = 0; + pid_t pid; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - struct perf_output_handle *handle = data; + struct perf_output_handle *handle = path->handle; + struct cs_buffers *buf = etm_perf_sink_config(handle); - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); do { ret = -EINVAL; if (drvdata->reading) break; /* - * In Perf mode there can be only one writer per sink. There - * is also no need to continue if the ETB/ETF is already - * operated from sysFS. + * No need to continue if the ETB/ETF is already operated + * from sysFS. */ - if (drvdata->mode != CS_MODE_DISABLED) + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { + ret = -EBUSY; break; + } + + /* Get a handle on the pid of the process to monitor */ + pid = buf->pid; + + if (drvdata->pid != -1 && drvdata->pid != pid) { + ret = -EBUSY; + break; + } ret = tmc_set_etf_buffer(csdev, handle); if (ret) break; + + /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + csdev->refcnt++; + break; + } + ret = tmc_etb_enable_hw(drvdata); - if (!ret) - drvdata->mode = CS_MODE_PERF; + if (!ret) { + /* Associate with monitored process. */ + drvdata->pid = pid; + coresight_set_mode(csdev, CS_MODE_PERF); + csdev->refcnt++; + } } while (0); - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } static int tmc_enable_etf_sink(struct coresight_device *csdev, - u32 mode, void *data) + enum cs_mode mode, + struct coresight_path *path) { int ret; - struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); switch (mode) { case CS_MODE_SYSFS: ret = tmc_enable_etf_sink_sysfs(csdev); break; case CS_MODE_PERF: - ret = tmc_enable_etf_sink_perf(csdev, data); + ret = tmc_enable_etf_sink_perf(csdev, path); break; /* We shouldn't be here */ default: @@ -269,89 +326,113 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, if (ret) return ret; - dev_dbg(drvdata->dev, "TMC-ETB/ETF enabled\n"); + dev_dbg(&csdev->dev, "TMC-ETB/ETF enabled\n"); return 0; } -static void tmc_disable_etf_sink(struct coresight_device *csdev) +static int tmc_disable_etf_sink(struct coresight_device *csdev) { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); - return; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; } - /* Disable the TMC only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - tmc_etb_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; + csdev->refcnt--; + if (csdev->refcnt) { + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; } - spin_unlock_irqrestore(&drvdata->spinlock, flags); + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(coresight_get_mode(csdev) == CS_MODE_DISABLED); + tmc_etb_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; + coresight_set_mode(csdev, CS_MODE_DISABLED); - dev_dbg(drvdata->dev, "TMC-ETB/ETF disabled\n"); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_dbg(&csdev->dev, "TMC-ETB/ETF disabled\n"); + return 0; } static int tmc_enable_etf_link(struct coresight_device *csdev, - int inport, int outport) + struct coresight_connection *in, + struct coresight_connection *out) { - int ret; + int ret = 0; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + bool first_enable = false; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return -EBUSY; } - ret = tmc_etf_enable_hw(drvdata); + if (csdev->refcnt == 0) { + ret = tmc_etf_enable_hw(drvdata); + if (!ret) { + coresight_set_mode(csdev, CS_MODE_SYSFS); + first_enable = true; + } + } if (!ret) - drvdata->mode = CS_MODE_SYSFS; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + csdev->refcnt++; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); - if (!ret) - dev_dbg(drvdata->dev, "TMC-ETF enabled\n"); + if (first_enable) + dev_dbg(&csdev->dev, "TMC-ETF enabled\n"); return ret; } static void tmc_disable_etf_link(struct coresight_device *csdev, - int inport, int outport) + struct coresight_connection *in, + struct coresight_connection *out) { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + bool last_disable = false; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return; } - tmc_etf_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + csdev->refcnt--; + if (csdev->refcnt == 0) { + tmc_etf_disable_hw(drvdata); + coresight_set_mode(csdev, CS_MODE_DISABLED); + last_disable = true; + } + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); - dev_dbg(drvdata->dev, "TMC-ETF disabled\n"); + if (last_disable) + dev_dbg(&csdev->dev, "TMC-ETF disabled\n"); } -static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu, - void **pages, int nr_pages, bool overwrite) +static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite) { int node; struct cs_buffers *buf; - if (cpu == -1) - cpu = smp_processor_id(); - node = cpu_to_node(cpu); + node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu); /* Allocate memory structure for interaction with Perf */ buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node); if (!buf) return NULL; + buf->pid = task_pid_nr(event->owner); buf->snapshot = overwrite; buf->nr_pages = nr_pages; buf->data_pages = pages; @@ -377,7 +458,7 @@ static int tmc_set_etf_buffer(struct coresight_device *csdev, return -EINVAL; /* wrap head around to the amount of space we have */ - head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + head = handle->head & (((unsigned long)buf->nr_pages << PAGE_SHIFT) - 1); /* find the page to write to */ buf->cur = head / PAGE_SIZE; @@ -400,17 +481,24 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, u32 *buf_ptr; u64 read_ptr, write_ptr; u32 status; - unsigned long offset, to_read; + unsigned long offset, to_read = 0, flags; struct cs_buffers *buf = sink_config; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_event *event = handle->event; if (!buf) return 0; /* This shouldn't happen */ - if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF)) + if (WARN_ON_ONCE(coresight_get_mode(csdev) != CS_MODE_PERF)) return 0; + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* Don't do anything if another tracer is using this sink */ + if (csdev->refcnt != 1) + goto out; + CS_UNLOCK(drvdata->base); tmc_flush_and_stop(drvdata); @@ -433,33 +521,16 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, /* * The TMC RAM buffer may be bigger than the space available in the * perf ring buffer (handle->size). If so advance the RRP so that we - * get the latest trace data. + * get the latest trace data. In snapshot mode none of that matters + * since we are expected to clobber stale data in favour of the latest + * traces. */ - if (to_read > handle->size) { - u32 mask = 0; - - /* - * The value written to RRP must be byte-address aligned to - * the width of the trace memory databus _and_ to a frame - * boundary (16 byte), whichever is the biggest. For example, - * for 32-bit, 64-bit and 128-bit wide trace memory, the four - * LSBs must be 0s. For 256-bit wide trace memory, the five - * LSBs must be 0s. - */ - switch (drvdata->memwidth) { - case TMC_MEM_INTF_WIDTH_32BITS: - case TMC_MEM_INTF_WIDTH_64BITS: - case TMC_MEM_INTF_WIDTH_128BITS: - mask = GENMASK(31, 4); - break; - case TMC_MEM_INTF_WIDTH_256BITS: - mask = GENMASK(31, 5); - break; - } + if (!buf->snapshot && to_read > handle->size) { + u32 mask = tmc_get_memwidth_mask(drvdata); /* * Make sure the new size is aligned in accordance with the - * requirement explained above. + * requirement explained in function tmc_get_memwidth_mask(). */ to_read = handle->size & mask; /* Move the RAM read pointer up */ @@ -472,19 +543,25 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, lost = true; } - if (lost) + /* + * Don't set the TRUNCATED flag in snapshot mode because 1) the + * captured buffer is expected to be truncated and 2) a full buffer + * prevents the event from being re-enabled by the perf core, + * resulting in stale data being send to user space. + */ + if (!buf->snapshot && lost) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); cur = buf->cur; offset = buf->offset; - barrier = barrier_pkt; + barrier = coresight_barrier_pkt; /* for every byte to read */ for (i = 0; i < to_read; i += 4) { buf_ptr = buf->data_pages[cur] + offset; *buf_ptr = readl_relaxed(drvdata->base + TMC_RRD); - if (lost && *barrier) { + if (lost && i < CORESIGHT_BARRIER_PKT_SIZE) { *buf_ptr = *barrier; barrier++; } @@ -498,16 +575,109 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, } } - /* In snapshot mode we have to update the head */ - if (buf->snapshot) { - handle->head = (cur * PAGE_SIZE) + offset; - to_read = buf->nr_pages << PAGE_SHIFT; - } + /* + * In snapshot mode we simply increment the head by the number of byte + * that were written. User space will figure out how many bytes to get + * from the AUX buffer based on the position of the head. + */ + if (buf->snapshot) + handle->head += to_read; + + /* + * CS_LOCK() contains mb() so it can ensure visibility of the AUX trace + * data before the aux_head is updated via perf_aux_output_end(), which + * is expected by the perf ring buffer. + */ CS_LOCK(drvdata->base); + /* + * If the event is active, it is triggered during an AUX pause. + * Re-enable the sink so that it is ready when AUX resume is invoked. + */ + if (!event->hw.state) + __tmc_etb_enable_hw(drvdata); + +out: + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return to_read; } +static int tmc_panic_sync_etf(struct coresight_device *csdev) +{ + u32 val; + struct tmc_crash_metadata *mdata; + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + mdata = (struct tmc_crash_metadata *)drvdata->crash_mdata.vaddr; + + /* Make sure we have valid reserved memory */ + if (!tmc_has_reserved_buffer(drvdata) || + !tmc_has_crash_mdata_buffer(drvdata)) + return 0; + + tmc_crashdata_set_invalid(drvdata); + + CS_UNLOCK(drvdata->base); + + /* Proceed only if ETF is enabled or configured as sink */ + val = readl(drvdata->base + TMC_CTL); + if (!(val & TMC_CTL_CAPT_EN)) + goto out; + val = readl(drvdata->base + TMC_MODE); + if (val != TMC_MODE_CIRCULAR_BUFFER) + goto out; + + val = readl(drvdata->base + TMC_FFSR); + /* Do manual flush and stop only if its not auto-stopped */ + if (!(val & TMC_FFSR_FT_STOPPED)) { + dev_dbg(&csdev->dev, + "%s: Triggering manual flush\n", __func__); + tmc_flush_and_stop(drvdata); + } else + tmc_wait_for_tmcready(drvdata); + + /* Sync registers from hardware to metadata region */ + mdata->tmc_sts = readl(drvdata->base + TMC_STS); + mdata->tmc_mode = readl(drvdata->base + TMC_MODE); + mdata->tmc_ffcr = readl(drvdata->base + TMC_FFCR); + mdata->tmc_ffsr = readl(drvdata->base + TMC_FFSR); + + /* Sync Internal SRAM to reserved trace buffer region */ + drvdata->buf = drvdata->resrv_buf.vaddr; + tmc_etb_dump_hw(drvdata); + /* Store as per RSZ register convention */ + mdata->tmc_ram_size = drvdata->len >> 2; + + /* Other fields for processing trace buffer reads */ + mdata->tmc_rrp = 0; + mdata->tmc_dba = 0; + mdata->tmc_rwp = drvdata->len; + mdata->trace_paddr = drvdata->resrv_buf.paddr; + + mdata->version = CS_CRASHDATA_VERSION; + + /* + * Make sure all previous writes are ordered, + * before we mark valid + */ + dmb(sy); + mdata->valid = true; + /* + * Below order need to maintained, since crc of metadata + * is dependent on first + */ + mdata->crc32_tdata = find_crash_tracedata_crc(drvdata, mdata); + mdata->crc32_mdata = find_crash_metadata_crc(mdata); + + tmc_disable_hw(drvdata); + + dev_dbg(&csdev->dev, "%s: success\n", __func__); +out: + CS_UNLOCK(drvdata->base); + return 0; +} + static const struct coresight_ops_sink tmc_etf_sink_ops = { .enable = tmc_enable_etf_sink, .disable = tmc_disable_etf_sink, @@ -521,6 +691,10 @@ static const struct coresight_ops_link tmc_etf_link_ops = { .disable = tmc_disable_etf_link, }; +static const struct coresight_ops_panic tmc_etf_sync_ops = { + .sync = tmc_panic_sync_etf, +}; + const struct coresight_ops tmc_etb_cs_ops = { .sink_ops = &tmc_etf_sink_ops, }; @@ -528,6 +702,7 @@ const struct coresight_ops tmc_etb_cs_ops = { const struct coresight_ops tmc_etf_cs_ops = { .sink_ops = &tmc_etf_sink_ops, .link_ops = &tmc_etf_link_ops, + .panic_ops = &tmc_etf_sync_ops, }; int tmc_read_prepare_etb(struct tmc_drvdata *drvdata) @@ -541,22 +716,15 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata) drvdata->config_type != TMC_CONFIG_TYPE_ETF)) return -EINVAL; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { ret = -EBUSY; goto out; } - /* There is no point in reading a TMC in HW FIFO mode */ - mode = readl_relaxed(drvdata->base + TMC_MODE); - if (mode != TMC_MODE_CIRCULAR_BUFFER) { - ret = -EINVAL; - goto out; - } - /* Don't interfere if operated from Perf */ - if (drvdata->mode == CS_MODE_PERF) { + if (coresight_get_mode(drvdata->csdev) == CS_MODE_PERF) { ret = -EINVAL; goto out; } @@ -568,12 +736,19 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata) } /* Disable the TMC if need be */ - if (drvdata->mode == CS_MODE_SYSFS) + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) { + /* There is no point in reading a TMC in HW FIFO mode */ + mode = readl_relaxed(drvdata->base + TMC_MODE); + if (mode != TMC_MODE_CIRCULAR_BUFFER) { + ret = -EINVAL; + goto out; + } __tmc_etb_disable_hw(drvdata); + } drvdata->reading = true; out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } @@ -589,17 +764,16 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata) drvdata->config_type != TMC_CONFIG_TYPE_ETF)) return -EINVAL; - spin_lock_irqsave(&drvdata->spinlock, flags); - - /* There is no point in reading a TMC in HW FIFO mode */ - mode = readl_relaxed(drvdata->base + TMC_MODE); - if (mode != TMC_MODE_CIRCULAR_BUFFER) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); - return -EINVAL; - } + raw_spin_lock_irqsave(&drvdata->spinlock, flags); /* Re-enable the TMC if need be */ - if (drvdata->mode == CS_MODE_SYSFS) { + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) { + /* There is no point in reading a TMC in HW FIFO mode */ + mode = readl_relaxed(drvdata->base + TMC_MODE); + if (mode != TMC_MODE_CIRCULAR_BUFFER) { + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EINVAL; + } /* * The trace run will continue with the same allocated trace * buffer. As such zero-out the buffer so that we don't end @@ -609,6 +783,10 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata) * can't be NULL. */ memset(drvdata->buf, 0, drvdata->size); + /* + * Ignore failures to enable the TMC to make sure, we don't + * leave the TMC in a "reading" state. + */ __tmc_etb_enable_hw(drvdata); } else { /* @@ -620,7 +798,7 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata) } drvdata->reading = false; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* * Free allocated memory outside of the spinlock. There is no need diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index f684283890d3..e0d83ee01b77 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -4,10 +4,15 @@ * Author: Mathieu Poirier <mathieu.poirier@linaro.org> */ +#include <linux/atomic.h> #include <linux/coresight.h> #include <linux/dma-mapping.h> #include <linux/iommu.h> +#include <linux/idr.h> +#include <linux/mutex.h> +#include <linux/refcount.h> #include <linux/slab.h> +#include <linux/types.h> #include <linux/vmalloc.h> #include "coresight-catu.h" #include "coresight-etm-perf.h" @@ -21,24 +26,35 @@ struct etr_flat_buf { size_t size; }; +struct etr_buf_hw { + bool has_iommu; + bool has_etr_sg; + bool has_catu; + bool has_resrv; +}; + /* * etr_perf_buffer - Perf buffer used for ETR + * @drvdata - The ETR drvdaga this buffer has been allocated for. * @etr_buf - Actual buffer used by the ETR + * @pid - The PID of the session owner that etr_perf_buffer + * belongs to. * @snaphost - Perf session mode - * @head - handle->head at the beginning of the session. * @nr_pages - Number of pages in the ring buffer. * @pages - Array of Pages in the ring buffer. */ struct etr_perf_buffer { + struct tmc_drvdata *drvdata; struct etr_buf *etr_buf; + pid_t pid; bool snapshot; - unsigned long head; int nr_pages; void **pages; }; /* Convert the perf index to an offset within the ETR buffer */ -#define PERF_IDX2OFF(idx, buf) ((idx) % ((buf)->nr_pages << PAGE_SHIFT)) +#define PERF_IDX2OFF(idx, buf) \ + ((idx) % ((unsigned long)(buf)->nr_pages << PAGE_SHIFT)) /* Lower limit for ETR hardware buffer */ #define TMC_ETR_PERF_MIN_BUF_SIZE SZ_1M @@ -109,7 +125,7 @@ struct etr_sg_table { * If we spill over to a new page for mapping 1 entry, we could as * well replace the link entry of the previous page with the last entry. */ -static inline unsigned long __attribute_const__ +static unsigned long __attribute_const__ tmc_etr_sg_table_entries(int nr_pages) { unsigned long nr_sgpages = nr_pages * ETR_SG_PAGES_PER_SYSPAGE; @@ -153,10 +169,11 @@ static void tmc_pages_free(struct tmc_pages *tmc_pages, struct device *dev, enum dma_data_direction dir) { int i; + struct device *real_dev = dev->parent; for (i = 0; i < tmc_pages->nr_pages; i++) { if (tmc_pages->daddrs && tmc_pages->daddrs[i]) - dma_unmap_page(dev, tmc_pages->daddrs[i], + dma_unmap_page(real_dev, tmc_pages->daddrs[i], PAGE_SIZE, dir); if (tmc_pages->pages && tmc_pages->pages[i]) __free_page(tmc_pages->pages[i]); @@ -184,6 +201,7 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages, int i, nr_pages; dma_addr_t paddr; struct page *page; + struct device *real_dev = dev->parent; nr_pages = tmc_pages->nr_pages; tmc_pages->daddrs = kcalloc(nr_pages, sizeof(*tmc_pages->daddrs), @@ -206,9 +224,11 @@ static int tmc_pages_alloc(struct tmc_pages *tmc_pages, } else { page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!page) + goto err; } - paddr = dma_map_page(dev, page, 0, PAGE_SIZE, dir); - if (dma_mapping_error(dev, paddr)) + paddr = dma_map_page(real_dev, page, 0, PAGE_SIZE, dir); + if (dma_mapping_error(real_dev, paddr)) goto err; tmc_pages->daddrs[i] = paddr; tmc_pages->pages[i] = page; @@ -219,13 +239,13 @@ err: return -ENOMEM; } -static inline long +static long tmc_sg_get_data_page_offset(struct tmc_sg_table *sg_table, dma_addr_t addr) { return tmc_pages_get_offset(&sg_table->data_pages, addr); } -static inline void tmc_free_table_pages(struct tmc_sg_table *sg_table) +static void tmc_free_table_pages(struct tmc_sg_table *sg_table) { if (sg_table->table_vaddr) vunmap(sg_table->table_vaddr); @@ -243,7 +263,9 @@ void tmc_free_sg_table(struct tmc_sg_table *sg_table) { tmc_free_table_pages(sg_table); tmc_free_data_pages(sg_table); + kfree(sg_table); } +EXPORT_SYMBOL_GPL(tmc_free_sg_table); /* * Alloc pages for the table. Since this will be used by the device, @@ -295,7 +317,7 @@ static int tmc_alloc_data_pages(struct tmc_sg_table *sg_table, void **pages) * and data buffers. TMC writes to the data buffers and reads from the SG * Table pages. * - * @dev - Device to which page should be DMA mapped. + * @dev - Coresight device to which page should be DMA mapped. * @node - Numa node for mem allocations * @nr_tpages - Number of pages for the table entries. * @nr_dpages - Number of pages for Data buffer. @@ -323,12 +345,12 @@ struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev, rc = tmc_alloc_table_pages(sg_table); if (rc) { tmc_free_sg_table(sg_table); - kfree(sg_table); return ERR_PTR(rc); } return sg_table; } +EXPORT_SYMBOL_GPL(tmc_alloc_sg_table); /* * tmc_sg_table_sync_data_range: Sync the data buffer written @@ -339,28 +361,30 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table, { int i, index, start; int npages = DIV_ROUND_UP(size, PAGE_SIZE); - struct device *dev = table->dev; + struct device *real_dev = table->dev->parent; struct tmc_pages *data = &table->data_pages; start = offset >> PAGE_SHIFT; for (i = start; i < (start + npages); i++) { index = i % data->nr_pages; - dma_sync_single_for_cpu(dev, data->daddrs[index], + dma_sync_single_for_cpu(real_dev, data->daddrs[index], PAGE_SIZE, DMA_FROM_DEVICE); } } +EXPORT_SYMBOL_GPL(tmc_sg_table_sync_data_range); /* tmc_sg_sync_table: Sync the page table */ void tmc_sg_table_sync_table(struct tmc_sg_table *sg_table) { int i; - struct device *dev = sg_table->dev; + struct device *real_dev = sg_table->dev->parent; struct tmc_pages *table_pages = &sg_table->table_pages; for (i = 0; i < table_pages->nr_pages; i++) - dma_sync_single_for_device(dev, table_pages->daddrs[i], + dma_sync_single_for_device(real_dev, table_pages->daddrs[i], PAGE_SIZE, DMA_TO_DEVICE); } +EXPORT_SYMBOL_GPL(tmc_sg_table_sync_table); /* * tmc_sg_table_get_data: Get the buffer pointer for data @offset @@ -390,6 +414,7 @@ ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table, *bufpp = page_address(data_pages->pages[pg_idx]) + pg_offset; return len; } +EXPORT_SYMBOL_GPL(tmc_sg_table_get_data); #ifdef ETR_SG_DEBUG /* Map a dma address to virtual address */ @@ -456,7 +481,7 @@ static void tmc_etr_sg_table_dump(struct etr_sg_table *etr_table) dev_dbg(sg_table->dev, "******* End of Table *****\n"); } #else -static inline void tmc_etr_sg_table_dump(struct etr_sg_table *etr_table) {} +static void tmc_etr_sg_table_dump(struct etr_sg_table *etr_table) {} #endif /* @@ -581,6 +606,7 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, void **pages) { struct etr_flat_buf *flat_buf; + struct device *real_dev = drvdata->csdev->dev.parent; /* We cannot reuse existing pages for flat buf */ if (pages) @@ -590,15 +616,17 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, if (!flat_buf) return -ENOMEM; - flat_buf->vaddr = dma_alloc_coherent(drvdata->dev, etr_buf->size, - &flat_buf->daddr, GFP_KERNEL); + flat_buf->vaddr = dma_alloc_noncoherent(real_dev, etr_buf->size, + &flat_buf->daddr, + DMA_FROM_DEVICE, + GFP_KERNEL | __GFP_NOWARN); if (!flat_buf->vaddr) { kfree(flat_buf); return -ENOMEM; } flat_buf->size = etr_buf->size; - flat_buf->dev = drvdata->dev; + flat_buf->dev = &drvdata->csdev->dev; etr_buf->hwaddr = flat_buf->daddr; etr_buf->mode = ETR_MODE_FLAT; etr_buf->private = flat_buf; @@ -609,14 +637,21 @@ static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf) { struct etr_flat_buf *flat_buf = etr_buf->private; - if (flat_buf && flat_buf->daddr) - dma_free_coherent(flat_buf->dev, flat_buf->size, - flat_buf->vaddr, flat_buf->daddr); + if (flat_buf && flat_buf->daddr) { + struct device *real_dev = flat_buf->dev->parent; + + dma_free_noncoherent(real_dev, etr_buf->size, + flat_buf->vaddr, flat_buf->daddr, + DMA_FROM_DEVICE); + } kfree(flat_buf); } static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp) { + struct etr_flat_buf *flat_buf = etr_buf->private; + struct device *real_dev = flat_buf->dev->parent; + /* * Adjust the buffer to point to the beginning of the trace data * and update the available trace data. @@ -626,6 +661,19 @@ static void tmc_etr_sync_flat_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp) etr_buf->len = etr_buf->size; else etr_buf->len = rwp - rrp; + + /* + * The driver always starts tracing at the beginning of the buffer, + * the only reason why we would get a wrap around is when the buffer + * is full. Sync the entire buffer in one go for this case. + */ + if (etr_buf->offset + etr_buf->len > etr_buf->size) + dma_sync_single_for_cpu(real_dev, flat_buf->daddr, + etr_buf->size, DMA_FROM_DEVICE); + else + dma_sync_single_for_cpu(real_dev, + flat_buf->daddr + etr_buf->offset, + etr_buf->len, DMA_FROM_DEVICE); } static ssize_t tmc_etr_get_data_flat_buf(struct etr_buf *etr_buf, @@ -649,6 +697,75 @@ static const struct etr_buf_operations etr_flat_buf_ops = { }; /* + * tmc_etr_alloc_resrv_buf: Allocate a contiguous DMA buffer from reserved region. + */ +static int tmc_etr_alloc_resrv_buf(struct tmc_drvdata *drvdata, + struct etr_buf *etr_buf, int node, + void **pages) +{ + struct etr_flat_buf *resrv_buf; + struct device *real_dev = drvdata->csdev->dev.parent; + + /* We cannot reuse existing pages for resrv buf */ + if (pages) + return -EINVAL; + + resrv_buf = kzalloc(sizeof(*resrv_buf), GFP_KERNEL); + if (!resrv_buf) + return -ENOMEM; + + resrv_buf->daddr = dma_map_resource(real_dev, drvdata->resrv_buf.paddr, + drvdata->resrv_buf.size, + DMA_FROM_DEVICE, 0); + if (dma_mapping_error(real_dev, resrv_buf->daddr)) { + dev_err(real_dev, "failed to map source buffer address\n"); + kfree(resrv_buf); + return -ENOMEM; + } + + resrv_buf->vaddr = drvdata->resrv_buf.vaddr; + resrv_buf->size = etr_buf->size = drvdata->resrv_buf.size; + resrv_buf->dev = &drvdata->csdev->dev; + etr_buf->hwaddr = resrv_buf->daddr; + etr_buf->mode = ETR_MODE_RESRV; + etr_buf->private = resrv_buf; + return 0; +} + +static void tmc_etr_free_resrv_buf(struct etr_buf *etr_buf) +{ + struct etr_flat_buf *resrv_buf = etr_buf->private; + + if (resrv_buf && resrv_buf->daddr) { + struct device *real_dev = resrv_buf->dev->parent; + + dma_unmap_resource(real_dev, resrv_buf->daddr, + resrv_buf->size, DMA_FROM_DEVICE, 0); + } + kfree(resrv_buf); +} + +static void tmc_etr_sync_resrv_buf(struct etr_buf *etr_buf, u64 rrp, u64 rwp) +{ + /* + * Adjust the buffer to point to the beginning of the trace data + * and update the available trace data. + */ + etr_buf->offset = rrp - etr_buf->hwaddr; + if (etr_buf->full) + etr_buf->len = etr_buf->size; + else + etr_buf->len = rwp - rrp; +} + +static const struct etr_buf_operations etr_resrv_buf_ops = { + .alloc = tmc_etr_alloc_resrv_buf, + .free = tmc_etr_free_resrv_buf, + .sync = tmc_etr_sync_resrv_buf, + .get_data = tmc_etr_get_data_flat_buf, +}; + +/* * tmc_etr_alloc_sg_buf: Allocate an SG buf @etr_buf. Setup the parameters * appropriately. */ @@ -657,8 +774,9 @@ static int tmc_etr_alloc_sg_buf(struct tmc_drvdata *drvdata, void **pages) { struct etr_sg_table *etr_table; + struct device *dev = &drvdata->csdev->dev; - etr_table = tmc_init_etr_sg_table(drvdata->dev, node, + etr_table = tmc_init_etr_sg_table(dev, node, etr_buf->size, pages); if (IS_ERR(etr_table)) return -ENOMEM; @@ -736,49 +854,40 @@ static const struct etr_buf_operations etr_sg_buf_ops = { struct coresight_device * tmc_etr_get_catu_device(struct tmc_drvdata *drvdata) { - int i; - struct coresight_device *tmp, *etr = drvdata->csdev; + struct coresight_device *etr = drvdata->csdev; + union coresight_dev_subtype catu_subtype = { + .helper_subtype = CORESIGHT_DEV_SUBTYPE_HELPER_CATU + }; if (!IS_ENABLED(CONFIG_CORESIGHT_CATU)) return NULL; - for (i = 0; i < etr->nr_outport; i++) { - tmp = etr->conns[i].child_dev; - if (tmp && coresight_is_catu_device(tmp)) - return tmp; - } - - return NULL; + return coresight_find_output_type(etr->pdata, CORESIGHT_DEV_TYPE_HELPER, + catu_subtype); } +EXPORT_SYMBOL_GPL(tmc_etr_get_catu_device); -static inline int tmc_etr_enable_catu(struct tmc_drvdata *drvdata, - struct etr_buf *etr_buf) -{ - struct coresight_device *catu = tmc_etr_get_catu_device(drvdata); +static const struct etr_buf_operations *etr_buf_ops[] = { + [ETR_MODE_FLAT] = &etr_flat_buf_ops, + [ETR_MODE_ETR_SG] = &etr_sg_buf_ops, + [ETR_MODE_CATU] = NULL, + [ETR_MODE_RESRV] = &etr_resrv_buf_ops +}; - if (catu && helper_ops(catu)->enable) - return helper_ops(catu)->enable(catu, etr_buf); - return 0; +void tmc_etr_set_catu_ops(const struct etr_buf_operations *catu) +{ + etr_buf_ops[ETR_MODE_CATU] = catu; } +EXPORT_SYMBOL_GPL(tmc_etr_set_catu_ops); -static inline void tmc_etr_disable_catu(struct tmc_drvdata *drvdata) +void tmc_etr_remove_catu_ops(void) { - struct coresight_device *catu = tmc_etr_get_catu_device(drvdata); - - if (catu && helper_ops(catu)->disable) - helper_ops(catu)->disable(catu, drvdata->etr_buf); + etr_buf_ops[ETR_MODE_CATU] = NULL; } +EXPORT_SYMBOL_GPL(tmc_etr_remove_catu_ops); -static const struct etr_buf_operations *etr_buf_ops[] = { - [ETR_MODE_FLAT] = &etr_flat_buf_ops, - [ETR_MODE_ETR_SG] = &etr_sg_buf_ops, - [ETR_MODE_CATU] = &etr_catu_buf_ops, -}; - -static inline int tmc_etr_mode_alloc_buf(int mode, - struct tmc_drvdata *drvdata, - struct etr_buf *etr_buf, int node, - void **pages) +static int tmc_etr_mode_alloc_buf(int mode, struct tmc_drvdata *drvdata, struct etr_buf *etr_buf, + int node, void **pages) { int rc = -EINVAL; @@ -786,7 +895,8 @@ static inline int tmc_etr_mode_alloc_buf(int mode, case ETR_MODE_FLAT: case ETR_MODE_ETR_SG: case ETR_MODE_CATU: - if (etr_buf_ops[mode]->alloc) + case ETR_MODE_RESRV: + if (etr_buf_ops[mode] && etr_buf_ops[mode]->alloc) rc = etr_buf_ops[mode]->alloc(drvdata, etr_buf, node, pages); if (!rc) @@ -797,6 +907,23 @@ static inline int tmc_etr_mode_alloc_buf(int mode, } } +static void get_etr_buf_hw(struct device *dev, struct etr_buf_hw *buf_hw) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + buf_hw->has_iommu = iommu_get_domain_for_dev(dev->parent); + buf_hw->has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG); + buf_hw->has_catu = !!tmc_etr_get_catu_device(drvdata); + buf_hw->has_resrv = tmc_has_reserved_buffer(drvdata); +} + +static bool etr_can_use_flat_mode(struct etr_buf_hw *buf_hw, ssize_t etr_buf_size) +{ + bool has_sg = buf_hw->has_catu || buf_hw->has_etr_sg; + + return !has_sg || buf_hw->has_iommu || etr_buf_size < SZ_1M; +} + /* * tmc_alloc_etr_buf: Allocate a buffer use by ETR. * @drvdata : ETR device details. @@ -810,22 +937,22 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata, int node, void **pages) { int rc = -ENOMEM; - bool has_etr_sg, has_iommu; - bool has_sg, has_catu; struct etr_buf *etr_buf; + struct etr_buf_hw buf_hw; + struct device *dev = &drvdata->csdev->dev; - has_etr_sg = tmc_etr_has_cap(drvdata, TMC_ETR_SG); - has_iommu = iommu_get_domain_for_dev(drvdata->dev); - has_catu = !!tmc_etr_get_catu_device(drvdata); - - has_sg = has_catu || has_etr_sg; - + get_etr_buf_hw(dev, &buf_hw); etr_buf = kzalloc(sizeof(*etr_buf), GFP_KERNEL); if (!etr_buf) return ERR_PTR(-ENOMEM); etr_buf->size = size; + /* If there is user directive for buffer mode, try that first */ + if (drvdata->etr_mode != ETR_MODE_AUTO) + rc = tmc_etr_mode_alloc_buf(drvdata->etr_mode, drvdata, + etr_buf, node, pages); + /* * If we have to use an existing list of pages, we cannot reliably * use a contiguous DMA memory (even if we have an IOMMU). Otherwise, @@ -838,14 +965,13 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata, * Fallback to available mechanisms. * */ - if (!pages && - (!has_sg || has_iommu || size < SZ_1M)) + if (rc && !pages && etr_can_use_flat_mode(&buf_hw, size)) rc = tmc_etr_mode_alloc_buf(ETR_MODE_FLAT, drvdata, etr_buf, node, pages); - if (rc && has_etr_sg) + if (rc && buf_hw.has_etr_sg) rc = tmc_etr_mode_alloc_buf(ETR_MODE_ETR_SG, drvdata, etr_buf, node, pages); - if (rc && has_catu) + if (rc && buf_hw.has_catu) rc = tmc_etr_mode_alloc_buf(ETR_MODE_CATU, drvdata, etr_buf, node, pages); if (rc) { @@ -853,7 +979,8 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata, return ERR_PTR(rc); } - dev_dbg(drvdata->dev, "allocated buffer of size %ldKB in mode %d\n", + refcount_set(&etr_buf->refcount, 1); + dev_dbg(dev, "allocated buffer of size %ldKB in mode %d\n", (unsigned long)size >> 10, etr_buf->mode); return etr_buf; } @@ -880,7 +1007,7 @@ static ssize_t tmc_etr_buf_get_data(struct etr_buf *etr_buf, return etr_buf->ops->get_data(etr_buf, (u64)offset, len, bufpp); } -static inline s64 +static s64 tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset) { ssize_t len; @@ -888,7 +1015,7 @@ tmc_etr_buf_insert_barrier_packet(struct etr_buf *etr_buf, u64 offset) len = tmc_etr_buf_get_data(etr_buf, offset, CORESIGHT_BARRIER_PKT_SIZE, &bufp); - if (WARN_ON(len < CORESIGHT_BARRIER_PKT_SIZE)) + if (WARN_ON(len < 0 || len < CORESIGHT_BARRIER_PKT_SIZE)) return -EINVAL; coresight_insert_barrier_packet(bufp); return offset + CORESIGHT_BARRIER_PKT_SIZE; @@ -909,33 +1036,50 @@ static void tmc_sync_etr_buf(struct tmc_drvdata *drvdata) rrp = tmc_read_rrp(drvdata); rwp = tmc_read_rwp(drvdata); status = readl_relaxed(drvdata->base + TMC_STS); - etr_buf->full = status & TMC_STS_FULL; + + /* + * If there were memory errors in the session, truncate the + * buffer. + */ + if (WARN_ON_ONCE(status & TMC_STS_MEMERR)) { + dev_dbg(&drvdata->csdev->dev, + "tmc memory error detected, truncating buffer\n"); + etr_buf->len = 0; + etr_buf->full = false; + return; + } + + etr_buf->full = !!(status & TMC_STS_FULL); WARN_ON(!etr_buf->ops || !etr_buf->ops->sync); etr_buf->ops->sync(etr_buf, rrp, rwp); - - /* Insert barrier packets at the beginning, if there was an overflow */ - if (etr_buf->full) - tmc_etr_buf_insert_barrier_packet(etr_buf, etr_buf->offset); } -static void __tmc_etr_enable_hw(struct tmc_drvdata *drvdata) +static int __tmc_etr_enable_hw(struct tmc_drvdata *drvdata) { - u32 axictl, sts; + u32 axictl, sts, ffcr; struct etr_buf *etr_buf = drvdata->etr_buf; + int rc = 0; CS_UNLOCK(drvdata->base); /* Wait for TMCSReady bit to be set */ - tmc_wait_for_tmcready(drvdata); + rc = tmc_wait_for_tmcready(drvdata); + if (rc) { + dev_err(&drvdata->csdev->dev, + "Failed to enable : TMC not ready\n"); + CS_LOCK(drvdata->base); + return rc; + } writel_relaxed(etr_buf->size / 4, drvdata->base + TMC_RSZ); writel_relaxed(TMC_MODE_CIRCULAR_BUFFER, drvdata->base + TMC_MODE); axictl = readl_relaxed(drvdata->base + TMC_AXICTL); axictl &= ~TMC_AXICTL_CLEAR_MASK; - axictl |= (TMC_AXICTL_PROT_CTL_B1 | TMC_AXICTL_WR_BURST_16); + axictl |= TMC_AXICTL_PROT_CTL_B1; + axictl |= TMC_AXICTL_WR_BURST(drvdata->max_burst_size); axictl |= TMC_AXICTL_AXCACHE_OS; if (tmc_etr_has_cap(drvdata, TMC_ETR_AXI_ARCACHE)) { @@ -960,14 +1104,17 @@ static void __tmc_etr_enable_hw(struct tmc_drvdata *drvdata) writel_relaxed(sts, drvdata->base + TMC_STS); } - writel_relaxed(TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | - TMC_FFCR_FON_FLIN | TMC_FFCR_FON_TRIG_EVT | - TMC_FFCR_TRIGON_TRIGIN, - drvdata->base + TMC_FFCR); + ffcr = TMC_FFCR_EN_FMT | TMC_FFCR_EN_TI | TMC_FFCR_FON_FLIN | + TMC_FFCR_FON_TRIG_EVT | TMC_FFCR_TRIGON_TRIGIN; + if (drvdata->stop_on_flush) + ffcr |= TMC_FFCR_STOP_ON_FLUSH; + writel_relaxed(ffcr, drvdata->base + TMC_FFCR); + writel_relaxed(drvdata->trigger_cntr, drvdata->base + TMC_TRG); tmc_enable_hw(drvdata); CS_LOCK(drvdata->base); + return rc; } static int tmc_etr_enable_hw(struct tmc_drvdata *drvdata, @@ -986,17 +1133,14 @@ static int tmc_etr_enable_hw(struct tmc_drvdata *drvdata, if (WARN_ON(drvdata->etr_buf)) return -EBUSY; - /* - * If this ETR is connected to a CATU, enable it before we turn - * this on. - */ - rc = tmc_etr_enable_catu(drvdata, etr_buf); - if (rc) - return rc; - rc = coresight_claim_device(drvdata->base); + rc = coresight_claim_device(drvdata->csdev); if (!rc) { drvdata->etr_buf = etr_buf; - __tmc_etr_enable_hw(drvdata); + rc = __tmc_etr_enable_hw(drvdata); + if (rc) { + drvdata->etr_buf = NULL; + coresight_disclaim_device(drvdata->csdev); + } } return rc; @@ -1054,6 +1198,13 @@ static void tmc_etr_sync_sysfs_buf(struct tmc_drvdata *drvdata) drvdata->sysfs_buf = NULL; } else { tmc_sync_etr_buf(drvdata); + /* + * Insert barrier packets at the beginning, if there was + * an overflow. + */ + if (etr_buf->full) + tmc_etr_buf_insert_barrier_packet(etr_buf, + etr_buf->offset); } } @@ -1066,7 +1217,7 @@ static void __tmc_etr_disable_hw(struct tmc_drvdata *drvdata) * When operating in sysFS mode the content of the buffer needs to be * read before the TMC is disabled. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) tmc_etr_sync_sysfs_buf(drvdata); tmc_disable_hw(drvdata); @@ -1075,17 +1226,15 @@ static void __tmc_etr_disable_hw(struct tmc_drvdata *drvdata) } -static void tmc_etr_disable_hw(struct tmc_drvdata *drvdata) +void tmc_etr_disable_hw(struct tmc_drvdata *drvdata) { __tmc_etr_disable_hw(drvdata); - /* Disable CATU device if this ETR is connected to one */ - tmc_etr_disable_catu(drvdata); - coresight_disclaim_device(drvdata->base); + coresight_disclaim_device(drvdata->csdev); /* Reset the ETR buf used by hardware */ drvdata->etr_buf = NULL; } -static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) +static struct etr_buf *tmc_etr_get_sysfs_buffer(struct coresight_device *csdev) { int ret = 0; unsigned long flags; @@ -1100,34 +1249,33 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) * buffer, provided the size matches. Any allocation has to be done * with the lock released. */ - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* + * If the ETR is already enabled, continue with the existing buffer. + */ + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) + goto out; + sysfs_buf = READ_ONCE(drvdata->sysfs_buf); if (!sysfs_buf || (sysfs_buf->size != drvdata->size)) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* Allocate memory with the locks released */ free_buf = new_buf = tmc_etr_setup_sysfs_buf(drvdata); if (IS_ERR(new_buf)) - return PTR_ERR(new_buf); + return new_buf; /* Let's try again */ - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); } - if (drvdata->reading || drvdata->mode == CS_MODE_PERF) { + if (drvdata->reading || coresight_get_mode(csdev) == CS_MODE_PERF) { ret = -EBUSY; goto out; } /* - * In sysFS mode we can have multiple writers per sink. Since this - * sink is already enabled no memory is needed and the HW need not be - * touched, even if the buffer size has changed. - */ - if (drvdata->mode == CS_MODE_SYSFS) - goto out; - - /* * If we don't have a buffer or it doesn't match the requested size, * use the buffer allocated above. Otherwise reuse the existing buffer. */ @@ -1137,47 +1285,95 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) drvdata->sysfs_buf = new_buf; } - ret = tmc_etr_enable_hw(drvdata, drvdata->sysfs_buf); - if (!ret) - drvdata->mode = CS_MODE_SYSFS; out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* Free memory outside the spinlock if need be */ if (free_buf) tmc_etr_free_sysfs_buf(free_buf); + return ret ? ERR_PTR(ret) : drvdata->sysfs_buf; +} + +static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) +{ + int ret = 0; + unsigned long flags; + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct etr_buf *sysfs_buf = tmc_etr_get_sysfs_buffer(csdev); + + if (IS_ERR(sysfs_buf)) + return PTR_ERR(sysfs_buf); + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + + /* + * In sysFS mode we can have multiple writers per sink. Since this + * sink is already enabled no memory is needed and the HW need not be + * touched, even if the buffer size has changed. + */ + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { + csdev->refcnt++; + goto out; + } + + ret = tmc_etr_enable_hw(drvdata, sysfs_buf); + if (!ret) { + coresight_set_mode(csdev, CS_MODE_SYSFS); + csdev->refcnt++; + } + +out: + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); if (!ret) - dev_dbg(drvdata->dev, "TMC-ETR enabled\n"); + dev_dbg(&csdev->dev, "TMC-ETR enabled\n"); return ret; } +struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path) +{ + struct perf_output_handle *handle = path->handle; + struct etr_perf_buffer *etr_perf; + + switch (mode) { + case CS_MODE_SYSFS: + return tmc_etr_get_sysfs_buffer(csdev); + case CS_MODE_PERF: + etr_perf = etm_perf_sink_config(handle); + if (WARN_ON(!etr_perf || !etr_perf->etr_buf)) + return ERR_PTR(-EINVAL); + return etr_perf->etr_buf; + default: + return ERR_PTR(-EINVAL); + } +} +EXPORT_SYMBOL_GPL(tmc_etr_get_buffer); + /* - * tmc_etr_setup_perf_buf: Allocate ETR buffer for use by perf. + * alloc_etr_buf: Allocate ETR buffer for use by perf. * The size of the hardware buffer is dependent on the size configured * via sysfs and the perf ring buffer size. We prefer to allocate the * largest possible size, scaling down the size by half until it * reaches a minimum limit (1M), beyond which we give up. */ -static struct etr_perf_buffer * -tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages, - void **pages, bool snapshot) +static struct etr_buf * +alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) { + int node; struct etr_buf *etr_buf; - struct etr_perf_buffer *etr_perf; unsigned long size; - etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node); - if (!etr_perf) - return ERR_PTR(-ENOMEM); - + node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu); /* * Try to match the perf ring buffer size if it is larger * than the size requested via sysfs. */ if ((nr_pages << PAGE_SHIFT) > drvdata->size) { - etr_buf = tmc_alloc_etr_buf(drvdata, (nr_pages << PAGE_SHIFT), + etr_buf = tmc_alloc_etr_buf(drvdata, ((ssize_t)nr_pages << PAGE_SHIFT), 0, node, NULL); if (!IS_ERR(etr_buf)) goto done; @@ -1195,32 +1391,148 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages, size /= 2; } while (size >= TMC_ETR_PERF_MIN_BUF_SIZE); + return ERR_PTR(-ENOMEM); + +done: + return etr_buf; +} + +static struct etr_buf * +get_perf_etr_buf_cpu_wide(struct tmc_drvdata *drvdata, + struct perf_event *event, int nr_pages, + void **pages, bool snapshot) +{ + int ret; + pid_t pid = task_pid_nr(event->owner); + struct etr_buf *etr_buf; + +retry: + /* + * An etr_perf_buffer is associated with an event and holds a reference + * to the AUX ring buffer that was created for that event. In CPU-wide + * N:1 mode multiple events (one per CPU), each with its own AUX ring + * buffer, share a sink. As such an etr_perf_buffer is created for each + * event but a single etr_buf associated with the ETR is shared between + * them. The last event in a trace session will copy the content of the + * etr_buf to its AUX ring buffer. Ring buffer associated to other + * events are simply not used an freed as events are destoyed. We still + * need to allocate a ring buffer for each event since we don't know + * which event will be last. + */ + + /* + * The first thing to do here is check if an etr_buf has already been + * allocated for this session. If so it is shared with this event, + * otherwise it is created. + */ + mutex_lock(&drvdata->idr_mutex); + etr_buf = idr_find(&drvdata->idr, pid); + if (etr_buf) { + refcount_inc(&etr_buf->refcount); + mutex_unlock(&drvdata->idr_mutex); + return etr_buf; + } + + /* If we made it here no buffer has been allocated, do so now. */ + mutex_unlock(&drvdata->idr_mutex); + + etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + if (IS_ERR(etr_buf)) + return etr_buf; + + /* Now that we have a buffer, add it to the IDR. */ + mutex_lock(&drvdata->idr_mutex); + ret = idr_alloc(&drvdata->idr, etr_buf, pid, pid + 1, GFP_KERNEL); + mutex_unlock(&drvdata->idr_mutex); + + /* Another event with this session ID has allocated this buffer. */ + if (ret == -ENOSPC) { + tmc_free_etr_buf(etr_buf); + goto retry; + } + + /* The IDR can't allocate room for a new session, abandon ship. */ + if (ret == -ENOMEM) { + tmc_free_etr_buf(etr_buf); + return ERR_PTR(ret); + } + + + return etr_buf; +} + +static struct etr_buf * +get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata, + struct perf_event *event, int nr_pages, + void **pages, bool snapshot) +{ + /* + * In per-thread mode the etr_buf isn't shared, so just go ahead + * with memory allocation. + */ + return alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); +} + +static struct etr_buf * +get_perf_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) +{ + if (event->cpu == -1) + return get_perf_etr_buf_per_thread(drvdata, event, nr_pages, + pages, snapshot); + + return get_perf_etr_buf_cpu_wide(drvdata, event, nr_pages, + pages, snapshot); +} + +static struct etr_perf_buffer * +tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) +{ + int node; + struct etr_buf *etr_buf; + struct etr_perf_buffer *etr_perf; + + node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu); + + etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node); + if (!etr_perf) + return ERR_PTR(-ENOMEM); + + etr_buf = get_perf_etr_buf(drvdata, event, nr_pages, pages, snapshot); + if (!IS_ERR(etr_buf)) + goto done; + kfree(etr_perf); return ERR_PTR(-ENOMEM); done: + /* + * Keep a reference to the ETR this buffer has been allocated for + * in order to have access to the IDR in tmc_free_etr_buffer(). + */ + etr_perf->drvdata = drvdata; etr_perf->etr_buf = etr_buf; + return etr_perf; } static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, - int cpu, void **pages, int nr_pages, - bool snapshot) + struct perf_event *event, void **pages, + int nr_pages, bool snapshot) { struct etr_perf_buffer *etr_perf; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - if (cpu == -1) - cpu = smp_processor_id(); - - etr_perf = tmc_etr_setup_perf_buf(drvdata, cpu_to_node(cpu), + etr_perf = tmc_etr_setup_perf_buf(drvdata, event, nr_pages, pages, snapshot); if (IS_ERR(etr_perf)) { - dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n"); + dev_dbg(&csdev->dev, "Unable to allocate ETR buffer\n"); return NULL; } + etr_perf->pid = task_pid_nr(event->owner); etr_perf->snapshot = snapshot; etr_perf->nr_pages = nr_pages; etr_perf->pages = pages; @@ -1231,9 +1543,33 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, static void tmc_free_etr_buffer(void *config) { struct etr_perf_buffer *etr_perf = config; + struct tmc_drvdata *drvdata = etr_perf->drvdata; + struct etr_buf *buf, *etr_buf = etr_perf->etr_buf; + + if (!etr_buf) + goto free_etr_perf_buffer; + + mutex_lock(&drvdata->idr_mutex); + /* If we are not the last one to use the buffer, don't touch it. */ + if (!refcount_dec_and_test(&etr_buf->refcount)) { + mutex_unlock(&drvdata->idr_mutex); + goto free_etr_perf_buffer; + } + + /* We are the last one, remove from the IDR and free the buffer. */ + buf = idr_remove(&drvdata->idr, etr_perf->pid); + mutex_unlock(&drvdata->idr_mutex); + + /* + * Something went very wrong if the buffer associated with this ID + * is not the same in the IDR. Leak to avoid use after free. + */ + if (buf && WARN_ON(buf != etr_buf)) + goto free_etr_perf_buffer; + + tmc_free_etr_buf(etr_perf->etr_buf); - if (etr_perf->etr_buf) - tmc_free_etr_buf(etr_perf->etr_buf); +free_etr_perf_buffer: kfree(etr_perf); } @@ -1241,20 +1577,20 @@ static void tmc_free_etr_buffer(void *config) * tmc_etr_sync_perf_buffer: Copy the actual trace data from the hardware * buffer to the perf ring buffer. */ -static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) +static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf, + unsigned long head, + unsigned long src_offset, + unsigned long to_copy) { - long bytes, to_copy; - long pg_idx, pg_offset, src_offset; - unsigned long head = etr_perf->head; + long bytes; + long pg_idx, pg_offset; char **dst_pages, *src_buf; struct etr_buf *etr_buf = etr_perf->etr_buf; - head = etr_perf->head; + head = PERF_IDX2OFF(head, etr_perf); pg_idx = head >> PAGE_SHIFT; pg_offset = head & (PAGE_SIZE - 1); dst_pages = (char **)etr_perf->pages; - src_offset = etr_buf->offset; - to_copy = etr_buf->len; while (to_copy > 0) { /* @@ -1265,6 +1601,8 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) * 3) what is available in the destination page. * in one iteration. */ + if (src_offset >= etr_buf->size) + src_offset -= etr_buf->size; bytes = tmc_etr_buf_get_data(etr_buf, src_offset, to_copy, &src_buf); if (WARN_ON_ONCE(bytes <= 0)) @@ -1285,8 +1623,6 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) /* Move source pointers */ src_offset += bytes; - if (src_offset >= etr_buf->size) - src_offset -= etr_buf->size; } } @@ -1302,15 +1638,23 @@ tmc_update_etr_buffer(struct coresight_device *csdev, void *config) { bool lost = false; - unsigned long flags, size = 0; + unsigned long flags, offset, size = 0; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct etr_perf_buffer *etr_perf = config; struct etr_buf *etr_buf = etr_perf->etr_buf; + struct perf_event *event = handle->event; + + raw_spin_lock_irqsave(&drvdata->spinlock, flags); - spin_lock_irqsave(&drvdata->spinlock, flags); - if (WARN_ON(drvdata->perf_data != etr_perf)) { + /* Don't do anything if another tracer is using this sink */ + if (csdev->refcnt != 1) { + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + goto out; + } + + if (WARN_ON(drvdata->perf_buf != etr_buf)) { lost = true; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); goto out; } @@ -1320,44 +1664,88 @@ tmc_update_etr_buffer(struct coresight_device *csdev, tmc_sync_etr_buf(drvdata); CS_LOCK(drvdata->base); - /* Reset perf specific data */ - drvdata->perf_data = NULL; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + lost = etr_buf->full; + offset = etr_buf->offset; size = etr_buf->len; - tmc_etr_sync_perf_buffer(etr_perf); /* - * Update handle->head in snapshot mode. Also update the size to the - * hardware buffer size if there was an overflow. + * The ETR buffer may be bigger than the space available in the + * perf ring buffer (handle->size). If so advance the offset so that we + * get the latest trace data. In snapshot mode none of that matters + * since we are expected to clobber stale data in favour of the latest + * traces. */ - if (etr_perf->snapshot) { - handle->head += size; - if (etr_buf->full) - size = etr_buf->size; + if (!etr_perf->snapshot && size > handle->size) { + u32 mask = tmc_get_memwidth_mask(drvdata); + + /* + * Make sure the new size is aligned in accordance with the + * requirement explained in function tmc_get_memwidth_mask(). + */ + size = handle->size & mask; + offset = etr_buf->offset + etr_buf->len - size; + + if (offset >= etr_buf->size) + offset -= etr_buf->size; + lost = true; } - lost |= etr_buf->full; -out: + /* Insert barrier packets at the beginning, if there was an overflow */ if (lost) + tmc_etr_buf_insert_barrier_packet(etr_buf, offset); + tmc_etr_sync_perf_buffer(etr_perf, handle->head, offset, size); + + /* + * In snapshot mode we simply increment the head by the number of byte + * that were written. User space will figure out how many bytes to get + * from the AUX buffer based on the position of the head. + */ + if (etr_perf->snapshot) + handle->head += size; + + /* + * Ensure that the AUX trace data is visible before the aux_head + * is updated via perf_aux_output_end(), as expected by the + * perf ring buffer. + */ + smp_wmb(); + + /* + * If the event is active, it is triggered during an AUX pause. + * Re-enable the sink so that it is ready when AUX resume is invoked. + */ + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (csdev->refcnt && !event->hw.state) + __tmc_etr_enable_hw(drvdata); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + +out: + /* + * Don't set the TRUNCATED flag in snapshot mode because 1) the + * captured buffer is expected to be truncated and 2) a full buffer + * prevents the event from being re-enabled by the perf core, + * resulting in stale data being send to user space. + */ + if (!etr_perf->snapshot && lost) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); return size; } -static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) +static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, + struct coresight_path *path) { int rc = 0; + pid_t pid; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - struct perf_output_handle *handle = data; + struct perf_output_handle *handle = path->handle; struct etr_perf_buffer *etr_perf = etm_perf_sink_config(handle); - spin_lock_irqsave(&drvdata->spinlock, flags); - /* - * There can be only one writer per sink in perf mode. If the sink - * is already open in SYSFS mode, we can't use it. - */ - if (drvdata->mode != CS_MODE_DISABLED || WARN_ON(drvdata->perf_data)) { + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + /* Don't use this sink if it is already claimed by sysFS */ + if (coresight_get_mode(csdev) == CS_MODE_SYSFS) { rc = -EBUSY; goto unlock_out; } @@ -1367,51 +1755,151 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) goto unlock_out; } - etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf); - drvdata->perf_data = etr_perf; + /* Get a handle on the pid of the session owner */ + pid = etr_perf->pid; + + /* Do not proceed if this device is associated with another session */ + if (drvdata->pid != -1 && drvdata->pid != pid) { + rc = -EBUSY; + goto unlock_out; + } + + /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + csdev->refcnt++; + goto unlock_out; + } + rc = tmc_etr_enable_hw(drvdata, etr_perf->etr_buf); - if (!rc) - drvdata->mode = CS_MODE_PERF; + if (!rc) { + /* Associate with monitored process. */ + drvdata->pid = pid; + coresight_set_mode(csdev, CS_MODE_PERF); + drvdata->perf_buf = etr_perf->etr_buf; + csdev->refcnt++; + } unlock_out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return rc; } static int tmc_enable_etr_sink(struct coresight_device *csdev, - u32 mode, void *data) + enum cs_mode mode, + struct coresight_path *path) { switch (mode) { case CS_MODE_SYSFS: return tmc_enable_etr_sink_sysfs(csdev); case CS_MODE_PERF: - return tmc_enable_etr_sink_perf(csdev, data); + return tmc_enable_etr_sink_perf(csdev, path); + default: + return -EINVAL; } - - /* We shouldn't be here */ - return -EINVAL; } -static void tmc_disable_etr_sink(struct coresight_device *csdev) +static int tmc_disable_etr_sink(struct coresight_device *csdev) { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) { - spin_unlock_irqrestore(&drvdata->spinlock, flags); - return; + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; } - /* Disable the TMC only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - tmc_etr_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; + csdev->refcnt--; + if (csdev->refcnt) { + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; } - spin_unlock_irqrestore(&drvdata->spinlock, flags); + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(coresight_get_mode(csdev) == CS_MODE_DISABLED); + tmc_etr_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; + coresight_set_mode(csdev, CS_MODE_DISABLED); + /* Reset perf specific data */ + drvdata->perf_buf = NULL; + + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + + dev_dbg(&csdev->dev, "TMC-ETR disabled\n"); + return 0; +} + +static int tmc_panic_sync_etr(struct coresight_device *csdev) +{ + u32 val; + struct tmc_crash_metadata *mdata; + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + mdata = (struct tmc_crash_metadata *)drvdata->crash_mdata.vaddr; + + if (!drvdata->etr_buf) + return 0; + + /* Being in RESRV mode implies valid reserved memory as well */ + if (drvdata->etr_buf->mode != ETR_MODE_RESRV) + return 0; + + if (!tmc_has_crash_mdata_buffer(drvdata)) + return 0; + + CS_UNLOCK(drvdata->base); + + /* Proceed only if ETR is enabled */ + val = readl(drvdata->base + TMC_CTL); + if (!(val & TMC_CTL_CAPT_EN)) + goto out; + + val = readl(drvdata->base + TMC_FFSR); + /* Do manual flush and stop only if its not auto-stopped */ + if (!(val & TMC_FFSR_FT_STOPPED)) { + dev_dbg(&csdev->dev, + "%s: Triggering manual flush\n", __func__); + tmc_flush_and_stop(drvdata); + } else + tmc_wait_for_tmcready(drvdata); + + /* Sync registers from hardware to metadata region */ + mdata->tmc_ram_size = readl(drvdata->base + TMC_RSZ); + mdata->tmc_sts = readl(drvdata->base + TMC_STS); + mdata->tmc_mode = readl(drvdata->base + TMC_MODE); + mdata->tmc_ffcr = readl(drvdata->base + TMC_FFCR); + mdata->tmc_ffsr = readl(drvdata->base + TMC_FFSR); + mdata->tmc_rrp = tmc_read_rrp(drvdata); + mdata->tmc_rwp = tmc_read_rwp(drvdata); + mdata->tmc_dba = tmc_read_dba(drvdata); + mdata->trace_paddr = drvdata->resrv_buf.paddr; + mdata->version = CS_CRASHDATA_VERSION; + + /* + * Make sure all previous writes are ordered, + * before we mark valid + */ + dmb(sy); + mdata->valid = true; + /* + * Below order need to maintained, since crc of metadata + * is dependent on first + */ + mdata->crc32_tdata = find_crash_tracedata_crc(drvdata, mdata); + mdata->crc32_mdata = find_crash_metadata_crc(mdata); + + tmc_disable_hw(drvdata); - dev_dbg(drvdata->dev, "TMC-ETR disabled\n"); + dev_dbg(&csdev->dev, "%s: success\n", __func__); +out: + CS_UNLOCK(drvdata->base); + + return 0; } static const struct coresight_ops_sink tmc_etr_sink_ops = { @@ -1422,8 +1910,13 @@ static const struct coresight_ops_sink tmc_etr_sink_ops = { .free_buffer = tmc_free_etr_buffer, }; +static const struct coresight_ops_panic tmc_etr_sync_ops = { + .sync = tmc_panic_sync_etr, +}; + const struct coresight_ops tmc_etr_cs_ops = { .sink_ops = &tmc_etr_sink_ops, + .panic_ops = &tmc_etr_sync_ops, }; int tmc_read_prepare_etr(struct tmc_drvdata *drvdata) @@ -1435,7 +1928,7 @@ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata) if (WARN_ON_ONCE(drvdata->config_type != TMC_CONFIG_TYPE_ETR)) return -EINVAL; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { ret = -EBUSY; goto out; @@ -1452,12 +1945,12 @@ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata) } /* Disable the TMC if we are trying to read from a running session. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) __tmc_etr_disable_hw(drvdata); drvdata->reading = true; out: - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; } @@ -1471,10 +1964,10 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata) if (WARN_ON_ONCE(drvdata->config_type != TMC_CONFIG_TYPE_ETR)) return -EINVAL; - spin_lock_irqsave(&drvdata->spinlock, flags); + raw_spin_lock_irqsave(&drvdata->spinlock, flags); /* RE-enable the TMC if need be */ - if (drvdata->mode == CS_MODE_SYSFS) { + if (coresight_get_mode(drvdata->csdev) == CS_MODE_SYSFS) { /* * The trace run will continue with the same allocated trace * buffer. Since the tracer is still enabled drvdata::buf can't @@ -1491,7 +1984,7 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata) } drvdata->reading = false; - spin_unlock_irqrestore(&drvdata->spinlock, flags); + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); /* Free allocated memory out side of the spinlock */ if (sysfs_buf) @@ -1499,3 +1992,96 @@ int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata) return 0; } + +static const char *const buf_modes_str[] = { + [ETR_MODE_FLAT] = "flat", + [ETR_MODE_ETR_SG] = "tmc-sg", + [ETR_MODE_CATU] = "catu", + [ETR_MODE_RESRV] = "resrv", + [ETR_MODE_AUTO] = "auto", +}; + +static ssize_t buf_modes_available_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct etr_buf_hw buf_hw; + ssize_t size = 0; + + get_etr_buf_hw(dev, &buf_hw); + size += sysfs_emit(buf, "%s ", buf_modes_str[ETR_MODE_AUTO]); + size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_FLAT]); + if (buf_hw.has_etr_sg) + size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_ETR_SG]); + + if (buf_hw.has_catu) + size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_CATU]); + + if (buf_hw.has_resrv) + size += sysfs_emit_at(buf, size, "%s ", buf_modes_str[ETR_MODE_RESRV]); + + size += sysfs_emit_at(buf, size, "\n"); + return size; +} +static DEVICE_ATTR_RO(buf_modes_available); + +static ssize_t buf_mode_preferred_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%s\n", buf_modes_str[drvdata->etr_mode]); +} + +static int buf_mode_set_resrv(struct tmc_drvdata *drvdata) +{ + int err = -EBUSY; + unsigned long flags; + struct tmc_resrv_buf *rbuf; + + rbuf = &drvdata->resrv_buf; + + /* Ensure there are no active crashdata read sessions */ + raw_spin_lock_irqsave(&drvdata->spinlock, flags); + if (!rbuf->reading) { + tmc_crashdata_set_invalid(drvdata); + rbuf->len = 0; + drvdata->etr_mode = ETR_MODE_RESRV; + err = 0; + } + raw_spin_unlock_irqrestore(&drvdata->spinlock, flags); + return err; +} + +static ssize_t buf_mode_preferred_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct etr_buf_hw buf_hw; + + get_etr_buf_hw(dev, &buf_hw); + if (sysfs_streq(buf, buf_modes_str[ETR_MODE_FLAT])) + drvdata->etr_mode = ETR_MODE_FLAT; + else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_ETR_SG]) && buf_hw.has_etr_sg) + drvdata->etr_mode = ETR_MODE_ETR_SG; + else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_CATU]) && buf_hw.has_catu) + drvdata->etr_mode = ETR_MODE_CATU; + else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_RESRV]) && buf_hw.has_resrv) + return buf_mode_set_resrv(drvdata) ? : size; + else if (sysfs_streq(buf, buf_modes_str[ETR_MODE_AUTO])) + drvdata->etr_mode = ETR_MODE_AUTO; + else + return -EINVAL; + return size; +} +static DEVICE_ATTR_RW(buf_mode_preferred); + +static struct attribute *coresight_etr_attrs[] = { + &dev_attr_buf_modes_available.attr, + &dev_attr_buf_mode_preferred.attr, + NULL, +}; + +const struct attribute_group coresight_etr_group = { + .attrs = coresight_etr_attrs, +}; diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c deleted file mode 100644 index ea249f0bcd73..000000000000 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ /dev/null @@ -1,510 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2012, The Linux Foundation. All rights reserved. - * - * Description: CoreSight Trace Memory Controller driver - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/device.h> -#include <linux/io.h> -#include <linux/err.h> -#include <linux/fs.h> -#include <linux/miscdevice.h> -#include <linux/property.h> -#include <linux/uaccess.h> -#include <linux/slab.h> -#include <linux/dma-mapping.h> -#include <linux/spinlock.h> -#include <linux/pm_runtime.h> -#include <linux/of.h> -#include <linux/coresight.h> -#include <linux/amba/bus.h> - -#include "coresight-priv.h" -#include "coresight-tmc.h" - -void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata) -{ - /* Ensure formatter, unformatter and hardware fifo are empty */ - if (coresight_timeout(drvdata->base, - TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { - dev_err(drvdata->dev, - "timeout while waiting for TMC to be Ready\n"); - } -} - -void tmc_flush_and_stop(struct tmc_drvdata *drvdata) -{ - u32 ffcr; - - ffcr = readl_relaxed(drvdata->base + TMC_FFCR); - ffcr |= TMC_FFCR_STOP_ON_FLUSH; - writel_relaxed(ffcr, drvdata->base + TMC_FFCR); - ffcr |= BIT(TMC_FFCR_FLUSHMAN_BIT); - writel_relaxed(ffcr, drvdata->base + TMC_FFCR); - /* Ensure flush completes */ - if (coresight_timeout(drvdata->base, - TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { - dev_err(drvdata->dev, - "timeout while waiting for completion of Manual Flush\n"); - } - - tmc_wait_for_tmcready(drvdata); -} - -void tmc_enable_hw(struct tmc_drvdata *drvdata) -{ - writel_relaxed(TMC_CTL_CAPT_EN, drvdata->base + TMC_CTL); -} - -void tmc_disable_hw(struct tmc_drvdata *drvdata) -{ - writel_relaxed(0x0, drvdata->base + TMC_CTL); -} - -static int tmc_read_prepare(struct tmc_drvdata *drvdata) -{ - int ret = 0; - - switch (drvdata->config_type) { - case TMC_CONFIG_TYPE_ETB: - case TMC_CONFIG_TYPE_ETF: - ret = tmc_read_prepare_etb(drvdata); - break; - case TMC_CONFIG_TYPE_ETR: - ret = tmc_read_prepare_etr(drvdata); - break; - default: - ret = -EINVAL; - } - - if (!ret) - dev_dbg(drvdata->dev, "TMC read start\n"); - - return ret; -} - -static int tmc_read_unprepare(struct tmc_drvdata *drvdata) -{ - int ret = 0; - - switch (drvdata->config_type) { - case TMC_CONFIG_TYPE_ETB: - case TMC_CONFIG_TYPE_ETF: - ret = tmc_read_unprepare_etb(drvdata); - break; - case TMC_CONFIG_TYPE_ETR: - ret = tmc_read_unprepare_etr(drvdata); - break; - default: - ret = -EINVAL; - } - - if (!ret) - dev_dbg(drvdata->dev, "TMC read end\n"); - - return ret; -} - -static int tmc_open(struct inode *inode, struct file *file) -{ - int ret; - struct tmc_drvdata *drvdata = container_of(file->private_data, - struct tmc_drvdata, miscdev); - - ret = tmc_read_prepare(drvdata); - if (ret) - return ret; - - nonseekable_open(inode, file); - - dev_dbg(drvdata->dev, "%s: successfully opened\n", __func__); - return 0; -} - -static inline ssize_t tmc_get_sysfs_trace(struct tmc_drvdata *drvdata, - loff_t pos, size_t len, char **bufpp) -{ - switch (drvdata->config_type) { - case TMC_CONFIG_TYPE_ETB: - case TMC_CONFIG_TYPE_ETF: - return tmc_etb_get_sysfs_trace(drvdata, pos, len, bufpp); - case TMC_CONFIG_TYPE_ETR: - return tmc_etr_get_sysfs_trace(drvdata, pos, len, bufpp); - } - - return -EINVAL; -} - -static ssize_t tmc_read(struct file *file, char __user *data, size_t len, - loff_t *ppos) -{ - char *bufp; - ssize_t actual; - struct tmc_drvdata *drvdata = container_of(file->private_data, - struct tmc_drvdata, miscdev); - actual = tmc_get_sysfs_trace(drvdata, *ppos, len, &bufp); - if (actual <= 0) - return 0; - - if (copy_to_user(data, bufp, actual)) { - dev_dbg(drvdata->dev, "%s: copy_to_user failed\n", __func__); - return -EFAULT; - } - - *ppos += actual; - dev_dbg(drvdata->dev, "%zu bytes copied\n", actual); - - return actual; -} - -static int tmc_release(struct inode *inode, struct file *file) -{ - int ret; - struct tmc_drvdata *drvdata = container_of(file->private_data, - struct tmc_drvdata, miscdev); - - ret = tmc_read_unprepare(drvdata); - if (ret) - return ret; - - dev_dbg(drvdata->dev, "%s: released\n", __func__); - return 0; -} - -static const struct file_operations tmc_fops = { - .owner = THIS_MODULE, - .open = tmc_open, - .read = tmc_read, - .release = tmc_release, - .llseek = no_llseek, -}; - -static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid) -{ - enum tmc_mem_intf_width memwidth; - - /* - * Excerpt from the TRM: - * - * DEVID::MEMWIDTH[10:8] - * 0x2 Memory interface databus is 32 bits wide. - * 0x3 Memory interface databus is 64 bits wide. - * 0x4 Memory interface databus is 128 bits wide. - * 0x5 Memory interface databus is 256 bits wide. - */ - switch (BMVAL(devid, 8, 10)) { - case 0x2: - memwidth = TMC_MEM_INTF_WIDTH_32BITS; - break; - case 0x3: - memwidth = TMC_MEM_INTF_WIDTH_64BITS; - break; - case 0x4: - memwidth = TMC_MEM_INTF_WIDTH_128BITS; - break; - case 0x5: - memwidth = TMC_MEM_INTF_WIDTH_256BITS; - break; - default: - memwidth = 0; - } - - return memwidth; -} - -#define coresight_tmc_reg(name, offset) \ - coresight_simple_reg32(struct tmc_drvdata, name, offset) -#define coresight_tmc_reg64(name, lo_off, hi_off) \ - coresight_simple_reg64(struct tmc_drvdata, name, lo_off, hi_off) - -coresight_tmc_reg(rsz, TMC_RSZ); -coresight_tmc_reg(sts, TMC_STS); -coresight_tmc_reg(trg, TMC_TRG); -coresight_tmc_reg(ctl, TMC_CTL); -coresight_tmc_reg(ffsr, TMC_FFSR); -coresight_tmc_reg(ffcr, TMC_FFCR); -coresight_tmc_reg(mode, TMC_MODE); -coresight_tmc_reg(pscr, TMC_PSCR); -coresight_tmc_reg(axictl, TMC_AXICTL); -coresight_tmc_reg(devid, CORESIGHT_DEVID); -coresight_tmc_reg64(rrp, TMC_RRP, TMC_RRPHI); -coresight_tmc_reg64(rwp, TMC_RWP, TMC_RWPHI); -coresight_tmc_reg64(dba, TMC_DBALO, TMC_DBAHI); - -static struct attribute *coresight_tmc_mgmt_attrs[] = { - &dev_attr_rsz.attr, - &dev_attr_sts.attr, - &dev_attr_rrp.attr, - &dev_attr_rwp.attr, - &dev_attr_trg.attr, - &dev_attr_ctl.attr, - &dev_attr_ffsr.attr, - &dev_attr_ffcr.attr, - &dev_attr_mode.attr, - &dev_attr_pscr.attr, - &dev_attr_devid.attr, - &dev_attr_dba.attr, - &dev_attr_axictl.attr, - NULL, -}; - -static ssize_t trigger_cntr_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); - unsigned long val = drvdata->trigger_cntr; - - return sprintf(buf, "%#lx\n", val); -} - -static ssize_t trigger_cntr_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret; - unsigned long val; - struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); - - ret = kstrtoul(buf, 16, &val); - if (ret) - return ret; - - drvdata->trigger_cntr = val; - return size; -} -static DEVICE_ATTR_RW(trigger_cntr); - -static ssize_t buffer_size_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); - - return sprintf(buf, "%#x\n", drvdata->size); -} - -static ssize_t buffer_size_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret; - unsigned long val; - struct tmc_drvdata *drvdata = dev_get_drvdata(dev->parent); - - /* Only permitted for TMC-ETRs */ - if (drvdata->config_type != TMC_CONFIG_TYPE_ETR) - return -EPERM; - - ret = kstrtoul(buf, 0, &val); - if (ret) - return ret; - /* The buffer size should be page aligned */ - if (val & (PAGE_SIZE - 1)) - return -EINVAL; - drvdata->size = val; - return size; -} - -static DEVICE_ATTR_RW(buffer_size); - -static struct attribute *coresight_tmc_attrs[] = { - &dev_attr_trigger_cntr.attr, - &dev_attr_buffer_size.attr, - NULL, -}; - -static const struct attribute_group coresight_tmc_group = { - .attrs = coresight_tmc_attrs, -}; - -static const struct attribute_group coresight_tmc_mgmt_group = { - .attrs = coresight_tmc_mgmt_attrs, - .name = "mgmt", -}; - -const struct attribute_group *coresight_tmc_groups[] = { - &coresight_tmc_group, - &coresight_tmc_mgmt_group, - NULL, -}; - -static inline bool tmc_etr_can_use_sg(struct tmc_drvdata *drvdata) -{ - return fwnode_property_present(drvdata->dev->fwnode, - "arm,scatter-gather"); -} - -/* Detect and initialise the capabilities of a TMC ETR */ -static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata, - u32 devid, void *dev_caps) -{ - u32 dma_mask = 0; - - /* Set the unadvertised capabilities */ - tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps); - - if (!(devid & TMC_DEVID_NOSCAT) && tmc_etr_can_use_sg(drvdata)) - tmc_etr_set_cap(drvdata, TMC_ETR_SG); - - /* Check if the AXI address width is available */ - if (devid & TMC_DEVID_AXIAW_VALID) - dma_mask = ((devid >> TMC_DEVID_AXIAW_SHIFT) & - TMC_DEVID_AXIAW_MASK); - - /* - * Unless specified in the device configuration, ETR uses a 40-bit - * AXI master in place of the embedded SRAM of ETB/ETF. - */ - switch (dma_mask) { - case 32: - case 40: - case 44: - case 48: - case 52: - dev_info(drvdata->dev, "Detected dma mask %dbits\n", dma_mask); - break; - default: - dma_mask = 40; - } - - return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask)); -} - -static int tmc_probe(struct amba_device *adev, const struct amba_id *id) -{ - int ret = 0; - u32 devid; - void __iomem *base; - struct device *dev = &adev->dev; - struct coresight_platform_data *pdata = NULL; - struct tmc_drvdata *drvdata; - struct resource *res = &adev->res; - struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; - - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) { - ret = PTR_ERR(pdata); - goto out; - } - adev->dev.platform_data = pdata; - } - - ret = -ENOMEM; - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - goto out; - - drvdata->dev = &adev->dev; - dev_set_drvdata(dev, drvdata); - - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) { - ret = PTR_ERR(base); - goto out; - } - - drvdata->base = base; - - spin_lock_init(&drvdata->spinlock); - - devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID); - drvdata->config_type = BMVAL(devid, 6, 7); - drvdata->memwidth = tmc_get_memwidth(devid); - - if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { - if (np) - ret = of_property_read_u32(np, - "arm,buffer-size", - &drvdata->size); - if (ret) - drvdata->size = SZ_1M; - } else { - drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; - } - - pm_runtime_put(&adev->dev); - - desc.pdata = pdata; - desc.dev = dev; - desc.groups = coresight_tmc_groups; - - switch (drvdata->config_type) { - case TMC_CONFIG_TYPE_ETB: - desc.type = CORESIGHT_DEV_TYPE_SINK; - desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; - desc.ops = &tmc_etb_cs_ops; - break; - case TMC_CONFIG_TYPE_ETR: - desc.type = CORESIGHT_DEV_TYPE_SINK; - desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; - desc.ops = &tmc_etr_cs_ops; - ret = tmc_etr_setup_caps(drvdata, devid, id->data); - if (ret) - goto out; - break; - case TMC_CONFIG_TYPE_ETF: - desc.type = CORESIGHT_DEV_TYPE_LINKSINK; - desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_FIFO; - desc.ops = &tmc_etf_cs_ops; - break; - default: - pr_err("%s: Unsupported TMC config\n", pdata->name); - ret = -EINVAL; - goto out; - } - - drvdata->csdev = coresight_register(&desc); - if (IS_ERR(drvdata->csdev)) { - ret = PTR_ERR(drvdata->csdev); - goto out; - } - - drvdata->miscdev.name = pdata->name; - drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; - drvdata->miscdev.fops = &tmc_fops; - ret = misc_register(&drvdata->miscdev); - if (ret) - coresight_unregister(drvdata->csdev); -out: - return ret; -} - -static const struct amba_id tmc_ids[] = { - { - .id = 0x000bb961, - .mask = 0x000fffff, - }, - { - /* Coresight SoC 600 TMC-ETR/ETS */ - .id = 0x000bb9e8, - .mask = 0x000fffff, - .data = (void *)(unsigned long)CORESIGHT_SOC_600_ETR_CAPS, - }, - { - /* Coresight SoC 600 TMC-ETB */ - .id = 0x000bb9e9, - .mask = 0x000fffff, - }, - { - /* Coresight SoC 600 TMC-ETF */ - .id = 0x000bb9ea, - .mask = 0x000fffff, - }, - { 0, 0}, -}; - -static struct amba_driver tmc_driver = { - .drv = { - .name = "coresight-tmc", - .owner = THIS_MODULE, - .suppress_bind_attrs = true, - }, - .probe = tmc_probe, - .id_table = tmc_ids, -}; -builtin_amba_driver(tmc_driver); diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index 487c53701e9c..95473d131032 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -8,7 +8,11 @@ #define _CORESIGHT_TMC_H #include <linux/dma-mapping.h> +#include <linux/idr.h> #include <linux/miscdevice.h> +#include <linux/mutex.h> +#include <linux/refcount.h> +#include <linux/crc32.h> #define TMC_RSZ 0x004 #define TMC_STS 0x00c @@ -36,6 +40,7 @@ #define TMC_ITATBCTR2 0xef0 #define TMC_ITATBCTR1 0xef4 #define TMC_ITATBCTR0 0xef8 +#define TMC_AUTHSTATUS 0xfb8 /* register description */ /* TMC_CTL - 0x020 */ @@ -44,6 +49,7 @@ #define TMC_STS_TMCREADY_BIT 2 #define TMC_STS_FULL BIT(0) #define TMC_STS_TRIGGERED BIT(1) +#define TMC_STS_MEMERR BIT(5) /* * TMC_AXICTL - 0x110 * @@ -65,11 +71,15 @@ #define TMC_AXICTL_PROT_CTL_B0 BIT(0) #define TMC_AXICTL_PROT_CTL_B1 BIT(1) #define TMC_AXICTL_SCT_GAT_MODE BIT(7) -#define TMC_AXICTL_WR_BURST_16 0xF00 +#define TMC_AXICTL_WR_BURST(v) (((v) & 0xf) << 8) +#define TMC_AXICTL_WR_BURST_16 0xf /* Write-back Read and Write-allocate */ #define TMC_AXICTL_AXCACHE_OS (0xf << 2) #define TMC_AXICTL_ARCACHE_OS (0xf << 16) +/* TMC_FFSR - 0x300 */ +#define TMC_FFSR_FT_STOPPED BIT(1) + /* TMC_FFCR - 0x304 */ #define TMC_FFCR_FLUSHMAN_BIT 6 #define TMC_FFCR_EN_FMT BIT(0) @@ -86,6 +96,11 @@ #define TMC_DEVID_AXIAW_SHIFT 17 #define TMC_DEVID_AXIAW_MASK 0x7f +#define TMC_AUTH_NSID_MASK GENMASK(1, 0) + +/* Major version 1 Minor version 0 */ +#define CS_CRASHDATA_VERSION (1 << 16) + enum tmc_config_type { TMC_CONFIG_TYPE_ETB, TMC_CONFIG_TYPE_ETR, @@ -123,16 +138,38 @@ enum tmc_mem_intf_width { #define CORESIGHT_SOC_600_ETR_CAPS \ (TMC_ETR_SAVE_RESTORE | TMC_ETR_AXI_ARCACHE) +/* TMC metadata region for ETR and ETF configurations */ +struct tmc_crash_metadata { + uint32_t crc32_mdata; /* crc of metadata */ + uint32_t crc32_tdata; /* crc of tracedata */ + uint32_t version; /* 31:16 Major version, 15:0 Minor version */ + uint32_t valid; /* Indicate if this ETF/ETR was enabled */ + uint32_t tmc_ram_size; /* Ram Size register */ + uint32_t tmc_sts; /* Status register */ + uint32_t tmc_mode; /* Mode register */ + uint32_t tmc_ffcr; /* Formatter and flush control register */ + uint32_t tmc_ffsr; /* Formatter and flush status register */ + uint32_t reserved32; + uint64_t tmc_rrp; /* Ram Read pointer register */ + uint64_t tmc_rwp; /* Ram Write pointer register */ + uint64_t tmc_dba; /* Data buffer address register */ + uint64_t trace_paddr; /* Phys address of trace buffer */ + uint64_t reserved64[3]; +}; + enum etr_mode { ETR_MODE_FLAT, /* Uses contiguous flat buffer */ ETR_MODE_ETR_SG, /* Uses in-built TMC ETR SG mechanism */ ETR_MODE_CATU, /* Use SG mechanism in CATU */ + ETR_MODE_RESRV, /* Use reserved region contiguous buffer */ + ETR_MODE_AUTO, /* Use the default mechanism */ }; struct etr_buf_operations; /** * struct etr_buf - Details of the buffer used by ETR + * refcount ; Number of sources currently using this etr_buf. * @mode : Mode of the ETR buffer, contiguous, Scatter Gather etc. * @full : Trace data overflow * @size : Size of the buffer. @@ -143,6 +180,7 @@ struct etr_buf_operations; * @private : Backend specific information for the buf */ struct etr_buf { + refcount_t refcount; enum etr_mode mode; bool full; ssize_t size; @@ -154,45 +192,87 @@ struct etr_buf { }; /** + * @paddr : Start address of reserved memory region. + * @vaddr : Corresponding CPU virtual address. + * @size : Size of reserved memory region. + * @offset : Offset of the trace data in the buffer for consumption. + * @reading : Flag to indicate if reading is active + * @len : Available trace data @buf (may round up to the beginning). + */ +struct tmc_resrv_buf { + phys_addr_t paddr; + void *vaddr; + size_t size; + unsigned long offset; + bool reading; + s64 len; +}; + +/** * struct tmc_drvdata - specifics associated to an TMC component + * @atclk: optional clock for the core parts of the TMC. + * @pclk: APB clock if present, otherwise NULL * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @csdev: component vitals needed by the framework. * @miscdev: specifics to handle "/dev/xyz.tmc" entry. + * @crashdev: specifics to handle "/dev/crash_tmc_xyz" entry for reading + * crash tracedata. * @spinlock: only one at a time pls. + * @pid: Process ID of the process that owns the session that is using + * this component. For example this would be the pid of the Perf + * process. + * @stop_on_flush: Stop on flush trigger user configuration. * @buf: Snapshot of the trace data for ETF/ETB. * @etr_buf: details of buffer used in TMC-ETR * @len: size of the available trace for ETF/ETB. * @size: trace buffer size for this TMC (common for all modes). - * @mode: how this TMC is being used. + * @max_burst_size: The maximum burst size that can be initiated by + * TMC-ETR on AXI bus. * @config_type: TMC variant, must be of type @tmc_config_type. * @memwidth: width of the memory interface databus, in bytes. * @trigger_cntr: amount of words to store after a trigger. * @etr_caps: Bitmask of capabilities of the TMC ETR, inferred from the * device configuration register (DEVID) - * @perf_data: PERF buffer for ETR. - * @sysfs_data: SYSFS buffer for ETR. + * @idr: Holds etr_bufs allocated for this ETR. + * @idr_mutex: Access serialisation for idr. + * @sysfs_buf: SYSFS buffer for ETR. + * @perf_buf: PERF buffer for ETR. + * @resrv_buf: Used by ETR as hardware trace buffer and for trace data + * retention (after crash) only when ETR_MODE_RESRV buffer + * mode is enabled. Used by ETF for trace data retention + * (after crash) by default. + * @crash_mdata: Reserved memory for storing tmc crash metadata. + * Used by ETR/ETF. */ struct tmc_drvdata { + struct clk *atclk; + struct clk *pclk; void __iomem *base; - struct device *dev; struct coresight_device *csdev; struct miscdevice miscdev; - spinlock_t spinlock; + struct miscdevice crashdev; + raw_spinlock_t spinlock; + pid_t pid; bool reading; + bool stop_on_flush; union { char *buf; /* TMC ETB */ struct etr_buf *etr_buf; /* TMC ETR */ }; u32 len; u32 size; - u32 mode; + u32 max_burst_size; enum tmc_config_type config_type; enum tmc_mem_intf_width memwidth; u32 trigger_cntr; u32 etr_caps; + enum etr_mode etr_mode; + struct idr idr; + struct mutex idr_mutex; struct etr_buf *sysfs_buf; - void *perf_data; + struct etr_buf *perf_buf; + struct tmc_resrv_buf resrv_buf; + struct tmc_resrv_buf crash_mdata; }; struct etr_buf_operations { @@ -237,10 +317,12 @@ struct tmc_sg_table { }; /* Generic functions */ -void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata); +int tmc_wait_for_tmcready(struct tmc_drvdata *drvdata); void tmc_flush_and_stop(struct tmc_drvdata *drvdata); void tmc_enable_hw(struct tmc_drvdata *drvdata); void tmc_disable_hw(struct tmc_drvdata *drvdata); +u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata); +int tmc_read_prepare_crashdata(struct tmc_drvdata *drvdata); /* ETB/ETF functions */ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata); @@ -253,6 +335,7 @@ ssize_t tmc_etb_get_sysfs_trace(struct tmc_drvdata *drvdata, /* ETR functions */ int tmc_read_prepare_etr(struct tmc_drvdata *drvdata); int tmc_read_unprepare_etr(struct tmc_drvdata *drvdata); +void tmc_etr_disable_hw(struct tmc_drvdata *drvdata); extern const struct coresight_ops tmc_etr_cs_ops; ssize_t tmc_etr_get_sysfs_trace(struct tmc_drvdata *drvdata, loff_t pos, size_t len, char **bufpp); @@ -262,12 +345,12 @@ ssize_t tmc_etr_get_sysfs_trace(struct tmc_drvdata *drvdata, static inline u64 \ tmc_read_##name(struct tmc_drvdata *drvdata) \ { \ - return coresight_read_reg_pair(drvdata->base, lo_off, hi_off); \ + return csdev_access_relaxed_read_pair(&drvdata->csdev->access, lo_off, hi_off); \ } \ static inline void \ tmc_write_##name(struct tmc_drvdata *drvdata, u64 val) \ { \ - coresight_write_reg_pair(drvdata->base, val, lo_off, hi_off); \ + csdev_access_relaxed_write_pair(&drvdata->csdev->access, val, lo_off, hi_off); \ } TMC_REG_PAIR(rrp, TMC_RRP, TMC_RRPHI) @@ -302,12 +385,65 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table, u64 offset, u64 size); ssize_t tmc_sg_table_get_data(struct tmc_sg_table *sg_table, u64 offset, size_t len, char **bufpp); + static inline unsigned long tmc_sg_table_buf_size(struct tmc_sg_table *sg_table) { - return sg_table->data_pages.nr_pages << PAGE_SHIFT; + return (unsigned long)sg_table->data_pages.nr_pages << PAGE_SHIFT; +} + +static inline bool tmc_has_reserved_buffer(struct tmc_drvdata *drvdata) +{ + if (drvdata->resrv_buf.vaddr && + drvdata->resrv_buf.size) + return true; + return false; +} + +static inline bool tmc_has_crash_mdata_buffer(struct tmc_drvdata *drvdata) +{ + if (drvdata->crash_mdata.vaddr && + drvdata->crash_mdata.size) + return true; + return false; +} + +static inline void tmc_crashdata_set_invalid(struct tmc_drvdata *drvdata) +{ + struct tmc_crash_metadata *mdata; + + mdata = (struct tmc_crash_metadata *)drvdata->crash_mdata.vaddr; + + if (tmc_has_crash_mdata_buffer(drvdata)) + mdata->valid = false; +} + +static inline uint32_t find_crash_metadata_crc(struct tmc_crash_metadata *md) +{ + unsigned long crc_size; + + crc_size = sizeof(struct tmc_crash_metadata) - + offsetof(struct tmc_crash_metadata, crc32_tdata); + return crc32_le(0, (void *)&md->crc32_tdata, crc_size); +} + +static inline uint32_t find_crash_tracedata_crc(struct tmc_drvdata *drvdata, + struct tmc_crash_metadata *md) +{ + unsigned long crc_size; + + /* Take CRC of configured buffer size to keep it simple */ + crc_size = md->tmc_ram_size << 2; + return crc32_le(0, (void *)drvdata->resrv_buf.vaddr, crc_size); } struct coresight_device *tmc_etr_get_catu_device(struct tmc_drvdata *drvdata); +void tmc_etr_set_catu_ops(const struct etr_buf_operations *catu); +void tmc_etr_remove_catu_ops(void); +struct etr_buf *tmc_etr_get_buffer(struct coresight_device *csdev, + enum cs_mode mode, + struct coresight_path *path); +extern const struct attribute_group coresight_etr_group; + #endif diff --git a/drivers/hwtracing/coresight/coresight-tnoc.c b/drivers/hwtracing/coresight/coresight-tnoc.c new file mode 100644 index 000000000000..ff9a0a9cfe96 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tnoc.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + + #include <linux/amba/bus.h> + #include <linux/coresight.h> + #include <linux/device.h> + #include <linux/io.h> + #include <linux/kernel.h> + #include <linux/module.h> + #include <linux/of.h> + #include <linux/platform_device.h> + +#include "coresight-priv.h" +#include "coresight-trace-id.h" + +#define TRACE_NOC_CTRL 0x008 +#define TRACE_NOC_XLD 0x010 +#define TRACE_NOC_FREQVAL 0x018 +#define TRACE_NOC_SYNCR 0x020 + +/* Enable generation of output ATB traffic.*/ +#define TRACE_NOC_CTRL_PORTEN BIT(0) +/* Sets the type of issued ATB FLAG packets.*/ +#define TRACE_NOC_CTRL_FLAGTYPE BIT(7) +/* Sets the type of issued ATB FREQ packet*/ +#define TRACE_NOC_CTRL_FREQTYPE BIT(8) + +#define TRACE_NOC_SYNC_INTERVAL 0xFFFF + +/* + * struct trace_noc_drvdata - specifics associated to a trace noc component + * @base: memory mapped base address for this component. + * @dev: device node for trace_noc_drvdata. + * @csdev: component vitals needed by the framework. + * @spinlock: serialize enable/disable operation. + * @atid: id for the trace packet. + */ +struct trace_noc_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + spinlock_t spinlock; + u32 atid; +}; + +DEFINE_CORESIGHT_DEVLIST(trace_noc_devs, "traceNoc"); + +static void trace_noc_enable_hw(struct trace_noc_drvdata *drvdata) +{ + u32 val; + + /* Set ATID */ + writel_relaxed(drvdata->atid, drvdata->base + TRACE_NOC_XLD); + + /* Set the data word count between 'SYNC' packets */ + writel_relaxed(TRACE_NOC_SYNC_INTERVAL, drvdata->base + TRACE_NOC_SYNCR); + + /* Set the Control register: + * - Set the FLAG packets to 'FLAG' packets + * - Set the FREQ packets to 'FREQ_TS' packets + * - Enable generation of output ATB traffic + */ + + val = readl_relaxed(drvdata->base + TRACE_NOC_CTRL); + + val &= ~TRACE_NOC_CTRL_FLAGTYPE; + val |= TRACE_NOC_CTRL_FREQTYPE; + val |= TRACE_NOC_CTRL_PORTEN; + + writel(val, drvdata->base + TRACE_NOC_CTRL); +} + +static int trace_noc_enable(struct coresight_device *csdev, struct coresight_connection *inport, + struct coresight_connection *outport) +{ + struct trace_noc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + scoped_guard(spinlock, &drvdata->spinlock) { + if (csdev->refcnt == 0) + trace_noc_enable_hw(drvdata); + + csdev->refcnt++; + } + + dev_dbg(drvdata->dev, "Trace NOC is enabled\n"); + return 0; +} + +static void trace_noc_disable(struct coresight_device *csdev, struct coresight_connection *inport, + struct coresight_connection *outport) +{ + struct trace_noc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + scoped_guard(spinlock, &drvdata->spinlock) { + if (--csdev->refcnt == 0) + writel(0x0, drvdata->base + TRACE_NOC_CTRL); + } + dev_dbg(drvdata->dev, "Trace NOC is disabled\n"); +} + +static int trace_noc_id(struct coresight_device *csdev, __maybe_unused enum cs_mode mode, + __maybe_unused struct coresight_device *sink) +{ + struct trace_noc_drvdata *drvdata; + + drvdata = dev_get_drvdata(csdev->dev.parent); + + return drvdata->atid; +} + +static const struct coresight_ops_link trace_noc_link_ops = { + .enable = trace_noc_enable, + .disable = trace_noc_disable, +}; + +static const struct coresight_ops trace_noc_cs_ops = { + .trace_id = trace_noc_id, + .link_ops = &trace_noc_link_ops, +}; + +static int trace_noc_init_default_data(struct trace_noc_drvdata *drvdata) +{ + int atid; + + atid = coresight_trace_id_get_system_id(); + if (atid < 0) + return atid; + + drvdata->atid = atid; + + return 0; +} + +static ssize_t traceid_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + unsigned long val; + struct trace_noc_drvdata *drvdata = dev_get_drvdata(dev->parent); + + val = drvdata->atid; + return sprintf(buf, "%#lx\n", val); +} +static DEVICE_ATTR_RO(traceid); + +static struct attribute *coresight_tnoc_attrs[] = { + &dev_attr_traceid.attr, + NULL, +}; + +static const struct attribute_group coresight_tnoc_group = { + .attrs = coresight_tnoc_attrs, +}; + +static const struct attribute_group *coresight_tnoc_groups[] = { + &coresight_tnoc_group, + NULL, +}; + +static int trace_noc_probe(struct amba_device *adev, const struct amba_id *id) +{ + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata; + struct trace_noc_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + int ret; + + desc.name = coresight_alloc_device_name(&trace_noc_devs, dev); + if (!desc.name) + return -ENOMEM; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + drvdata->base = devm_ioremap_resource(dev, &adev->res); + if (IS_ERR(drvdata->base)) + return PTR_ERR(drvdata->base); + + spin_lock_init(&drvdata->spinlock); + + ret = trace_noc_init_default_data(drvdata); + if (ret) + return ret; + + desc.ops = &trace_noc_cs_ops; + desc.type = CORESIGHT_DEV_TYPE_LINK; + desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG; + desc.pdata = adev->dev.platform_data; + desc.dev = &adev->dev; + desc.access = CSDEV_ACCESS_IOMEM(drvdata->base); + desc.groups = coresight_tnoc_groups; + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) { + coresight_trace_id_put_system_id(drvdata->atid); + return PTR_ERR(drvdata->csdev); + } + pm_runtime_put(&adev->dev); + + return 0; +} + +static void trace_noc_remove(struct amba_device *adev) +{ + struct trace_noc_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_unregister(drvdata->csdev); + coresight_trace_id_put_system_id(drvdata->atid); +} + +static struct amba_id trace_noc_ids[] = { + { + .id = 0x000f0c00, + .mask = 0x00ffff00, + }, + { + .id = 0x001f0c00, + .mask = 0x00ffff00, + }, + {}, +}; +MODULE_DEVICE_TABLE(amba, trace_noc_ids); + +static struct amba_driver trace_noc_driver = { + .drv = { + .name = "coresight-trace-noc", + .suppress_bind_attrs = true, + }, + .probe = trace_noc_probe, + .remove = trace_noc_remove, + .id_table = trace_noc_ids, +}; + +module_amba_driver(trace_noc_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Trace NOC driver"); diff --git a/drivers/hwtracing/coresight/coresight-tpda.c b/drivers/hwtracing/coresight/coresight-tpda.c new file mode 100644 index 000000000000..3a3825d27f86 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpda.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/amba/bus.h> +#include <linux/bitfield.h> +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/platform_device.h> + +#include "coresight-priv.h" +#include "coresight-tpda.h" +#include "coresight-trace-id.h" +#include "coresight-tpdm.h" + +DEFINE_CORESIGHT_DEVLIST(tpda_devs, "tpda"); + +static void tpda_clear_element_size(struct coresight_device *csdev) +{ + struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + drvdata->dsb_esize = 0; + drvdata->cmb_esize = 0; +} + +static void tpda_set_element_size(struct tpda_drvdata *drvdata, u32 *val) +{ + /* Clear all relevant fields */ + *val &= ~(TPDA_Pn_CR_DSBSIZE | TPDA_Pn_CR_CMBSIZE); + + if (drvdata->dsb_esize == 64) + *val |= TPDA_Pn_CR_DSBSIZE; + else if (drvdata->dsb_esize == 32) + *val &= ~TPDA_Pn_CR_DSBSIZE; + + if (drvdata->cmb_esize == 64) + *val |= FIELD_PREP(TPDA_Pn_CR_CMBSIZE, 0x2); + else if (drvdata->cmb_esize == 32) + *val |= FIELD_PREP(TPDA_Pn_CR_CMBSIZE, 0x1); + else if (drvdata->cmb_esize == 8) + *val &= ~TPDA_Pn_CR_CMBSIZE; +} + +/* + * Read the element size from the TPDM device. One TPDM must have at least one of the + * element size property. + * Returns + * 0 - The element size property is read + * Others - Cannot read the property of the element size + */ +static int tpdm_read_element_size(struct tpda_drvdata *drvdata, + struct coresight_device *csdev) +{ + int rc = -EINVAL; + struct tpdm_drvdata *tpdm_data = dev_get_drvdata(csdev->dev.parent); + + if (tpdm_data->dsb) { + rc = fwnode_property_read_u32(dev_fwnode(csdev->dev.parent), + "qcom,dsb-element-bits", &drvdata->dsb_esize); + if (rc) + goto out; + } + + if (tpdm_data->cmb) { + rc = fwnode_property_read_u32(dev_fwnode(csdev->dev.parent), + "qcom,cmb-element-bits", &drvdata->cmb_esize); + } + +out: + if (rc) + dev_warn_once(&csdev->dev, + "Failed to read TPDM Element size: %d\n", rc); + + return rc; +} + +/* + * Search and read element data size from the TPDM node in + * the devicetree. Each input port of TPDA is connected to + * a TPDM. Different TPDM supports different types of dataset, + * and some may support more than one type of dataset. + * Parameter "inport" is used to pass in the input port number + * of TPDA, and it is set to -1 in the recursize call. + */ +static int tpda_get_element_size(struct tpda_drvdata *drvdata, + struct coresight_device *csdev, + int inport) +{ + int rc = 0; + int i; + struct coresight_device *in; + + for (i = 0; i < csdev->pdata->nr_inconns; i++) { + in = csdev->pdata->in_conns[i]->src_dev; + if (!in) + continue; + + /* Ignore the paths that do not match port */ + if (inport >= 0 && + csdev->pdata->in_conns[i]->dest_port != inport) + continue; + + /* + * If this port has a hardcoded filter, use the source + * device directly. + */ + if (csdev->pdata->in_conns[i]->filter_src_fwnode) { + in = csdev->pdata->in_conns[i]->filter_src_dev; + if (!in) + continue; + } + + if (coresight_device_is_tpdm(in)) { + if (drvdata->dsb_esize || drvdata->cmb_esize) + return -EEXIST; + rc = tpdm_read_element_size(drvdata, in); + if (rc) + return rc; + } else { + /* Recurse down the path */ + rc = tpda_get_element_size(drvdata, in, -1); + if (rc) + return rc; + } + } + + return rc; +} + +/* Settings pre enabling port control register */ +static void tpda_enable_pre_port(struct tpda_drvdata *drvdata) +{ + u32 val; + + val = readl_relaxed(drvdata->base + TPDA_CR); + val &= ~TPDA_CR_ATID; + val |= FIELD_PREP(TPDA_CR_ATID, drvdata->atid); + writel_relaxed(val, drvdata->base + TPDA_CR); +} + +static int tpda_enable_port(struct tpda_drvdata *drvdata, int port) +{ + u32 val; + int rc; + + val = readl_relaxed(drvdata->base + TPDA_Pn_CR(port)); + tpda_clear_element_size(drvdata->csdev); + rc = tpda_get_element_size(drvdata, drvdata->csdev, port); + if (!rc && (drvdata->dsb_esize || drvdata->cmb_esize)) { + tpda_set_element_size(drvdata, &val); + /* Enable the port */ + val |= TPDA_Pn_CR_ENA; + writel_relaxed(val, drvdata->base + TPDA_Pn_CR(port)); + } else if (rc == -EEXIST) + dev_warn_once(&drvdata->csdev->dev, + "Detected multiple TPDMs on port %d", port); + else + dev_warn_once(&drvdata->csdev->dev, + "Didn't find TPDM element size"); + + return rc; +} + +static int __tpda_enable(struct tpda_drvdata *drvdata, int port) +{ + int ret; + + CS_UNLOCK(drvdata->base); + + /* + * Only do pre-port enable for first port that calls enable when the + * device's main refcount is still 0 + */ + lockdep_assert_held(&drvdata->spinlock); + if (!drvdata->csdev->refcnt) + tpda_enable_pre_port(drvdata); + + ret = tpda_enable_port(drvdata, port); + CS_LOCK(drvdata->base); + + return ret; +} + +static int tpda_enable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) +{ + struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret = 0; + + spin_lock(&drvdata->spinlock); + if (in->dest_refcnt == 0) { + ret = __tpda_enable(drvdata, in->dest_port); + if (!ret) { + in->dest_refcnt++; + csdev->refcnt++; + dev_dbg(drvdata->dev, "TPDA inport %d enabled.\n", in->dest_port); + } + } + + spin_unlock(&drvdata->spinlock); + return ret; +} + +static void __tpda_disable(struct tpda_drvdata *drvdata, int port) +{ + u32 val; + + CS_UNLOCK(drvdata->base); + + val = readl_relaxed(drvdata->base + TPDA_Pn_CR(port)); + val &= ~TPDA_Pn_CR_ENA; + writel_relaxed(val, drvdata->base + TPDA_Pn_CR(port)); + + CS_LOCK(drvdata->base); +} + +static void tpda_disable(struct coresight_device *csdev, + struct coresight_connection *in, + struct coresight_connection *out) +{ + struct tpda_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + spin_lock(&drvdata->spinlock); + if (--in->dest_refcnt == 0) { + __tpda_disable(drvdata, in->dest_port); + csdev->refcnt--; + } + spin_unlock(&drvdata->spinlock); + + dev_dbg(drvdata->dev, "TPDA inport %d disabled\n", in->dest_port); +} + +static int tpda_trace_id(struct coresight_device *csdev, __maybe_unused enum cs_mode mode, + __maybe_unused struct coresight_device *sink) +{ + struct tpda_drvdata *drvdata; + + drvdata = dev_get_drvdata(csdev->dev.parent); + + return drvdata->atid; +} + +static const struct coresight_ops_link tpda_link_ops = { + .enable = tpda_enable, + .disable = tpda_disable, +}; + +static const struct coresight_ops tpda_cs_ops = { + .trace_id = tpda_trace_id, + .link_ops = &tpda_link_ops, +}; + +static int tpda_init_default_data(struct tpda_drvdata *drvdata) +{ + int atid; + /* + * TPDA must has a unique atid. This atid can uniquely + * identify the TPDM trace source connected to the TPDA. + * The TPDMs which are connected to same TPDA share the + * same trace-id. When TPDA does packetization, different + * port will have unique channel number for decoding. + */ + atid = coresight_trace_id_get_system_id(); + if (atid < 0) + return atid; + + drvdata->atid = atid; + return 0; +} + +static int tpda_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + struct device *dev = &adev->dev; + struct coresight_platform_data *pdata; + struct tpda_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + void __iomem *base; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->dev = &adev->dev; + dev_set_drvdata(dev, drvdata); + + base = devm_ioremap_resource(dev, &adev->res); + if (IS_ERR(base)) + return PTR_ERR(base); + drvdata->base = base; + + spin_lock_init(&drvdata->spinlock); + + ret = tpda_init_default_data(drvdata); + if (ret) + return ret; + + desc.name = coresight_alloc_device_name(&tpda_devs, dev); + if (!desc.name) + return -ENOMEM; + desc.type = CORESIGHT_DEV_TYPE_LINK; + desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG; + desc.ops = &tpda_cs_ops; + desc.pdata = adev->dev.platform_data; + desc.dev = &adev->dev; + desc.access = CSDEV_ACCESS_IOMEM(base); + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + pm_runtime_put(&adev->dev); + + dev_dbg(drvdata->dev, "TPDA initialized\n"); + return 0; +} + +static void tpda_remove(struct amba_device *adev) +{ + struct tpda_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_trace_id_put_system_id(drvdata->atid); + coresight_unregister(drvdata->csdev); +} + +/* + * Different TPDA has different periph id. + * The difference is 0-7 bits' value. So ignore 0-7 bits. + */ +static const struct amba_id tpda_ids[] = { + { + .id = 0x000f0f00, + .mask = 0x000fff00, + }, + { 0, 0, NULL }, +}; + +static struct amba_driver tpda_driver = { + .drv = { + .name = "coresight-tpda", + .suppress_bind_attrs = true, + }, + .probe = tpda_probe, + .remove = tpda_remove, + .id_table = tpda_ids, +}; + +module_amba_driver(tpda_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Trace, Profiling & Diagnostic Aggregator driver"); diff --git a/drivers/hwtracing/coresight/coresight-tpda.h b/drivers/hwtracing/coresight/coresight-tpda.h new file mode 100644 index 000000000000..c6af3d2da3ef --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpda.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _CORESIGHT_CORESIGHT_TPDA_H +#define _CORESIGHT_CORESIGHT_TPDA_H + +#define TPDA_CR (0x000) +#define TPDA_Pn_CR(n) (0x004 + (n * 4)) +/* Aggregator port enable bit */ +#define TPDA_Pn_CR_ENA BIT(0) +/* Aggregator port CMB data set element size bit */ +#define TPDA_Pn_CR_CMBSIZE GENMASK(7, 6) +/* Aggregator port DSB data set element size bit */ +#define TPDA_Pn_CR_DSBSIZE BIT(8) + +#define TPDA_MAX_INPORTS 32 + +/* Bits 6 ~ 12 is for atid value */ +#define TPDA_CR_ATID GENMASK(12, 6) + +/** + * struct tpda_drvdata - specifics associated to an TPDA component + * @base: memory mapped base address for this component. + * @dev: The device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @spinlock: lock for the drvdata value. + * @enable: enable status of the component. + * @dsb_esize Record the DSB element size. + * @cmb_esize Record the CMB element size. + */ +struct tpda_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + spinlock_t spinlock; + u8 atid; + u32 dsb_esize; + u32 cmb_esize; +}; + +#endif /* _CORESIGHT_CORESIGHT_TPDA_H */ diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c new file mode 100644 index 000000000000..06e0a905a67d --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -0,0 +1,1549 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023-2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/amba/bus.h> +#include <linux/bitfield.h> +#include <linux/bitmap.h> +#include <linux/coresight.h> +#include <linux/coresight-pmu.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> + +#include "coresight-priv.h" +#include "coresight-tpdm.h" + +DEFINE_CORESIGHT_DEVLIST(tpdm_devs, "tpdm"); + +static bool tpdm_has_dsb_dataset(struct tpdm_drvdata *drvdata) +{ + return (drvdata->datasets & TPDM_PIDR0_DS_DSB); +} + +static bool tpdm_has_cmb_dataset(struct tpdm_drvdata *drvdata) +{ + return (drvdata->datasets & TPDM_PIDR0_DS_CMB); +} + +static bool tpdm_has_mcmb_dataset(struct tpdm_drvdata *drvdata) +{ + return (drvdata->datasets & TPDM_PIDR0_DS_MCMB); +} + +/* Read dataset array member with the index number */ +static ssize_t tpdm_simple_dataset_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(attr, struct tpdm_dataset_attribute, attr); + + switch (tpdm_attr->mem) { + case DSB_EDGE_CTRL: + if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCR) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->edge_ctrl[tpdm_attr->idx]); + case DSB_EDGE_CTRL_MASK: + if (tpdm_attr->idx >= TPDM_DSB_MAX_EDCMR) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->edge_ctrl_mask[tpdm_attr->idx]); + case DSB_TRIG_PATT: + if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->trig_patt[tpdm_attr->idx]); + case DSB_TRIG_PATT_MASK: + if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->trig_patt_mask[tpdm_attr->idx]); + case DSB_PATT: + if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->patt_val[tpdm_attr->idx]); + case DSB_PATT_MASK: + if (tpdm_attr->idx >= TPDM_DSB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->patt_mask[tpdm_attr->idx]); + case DSB_MSR: + if (tpdm_attr->idx >= drvdata->dsb_msr_num) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->dsb->msr[tpdm_attr->idx]); + case CMB_TRIG_PATT: + if (tpdm_attr->idx >= TPDM_CMB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->cmb->trig_patt[tpdm_attr->idx]); + case CMB_TRIG_PATT_MASK: + if (tpdm_attr->idx >= TPDM_CMB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->cmb->trig_patt_mask[tpdm_attr->idx]); + case CMB_PATT: + if (tpdm_attr->idx >= TPDM_CMB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->cmb->patt_val[tpdm_attr->idx]); + case CMB_PATT_MASK: + if (tpdm_attr->idx >= TPDM_CMB_MAX_PATT) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->cmb->patt_mask[tpdm_attr->idx]); + case CMB_MSR: + if (tpdm_attr->idx >= drvdata->cmb_msr_num) + return -EINVAL; + return sysfs_emit(buf, "0x%x\n", + drvdata->cmb->msr[tpdm_attr->idx]); + } + return -EINVAL; +} + +/* Write dataset array member with the index number */ +static ssize_t tpdm_simple_dataset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + unsigned long val; + ssize_t ret = -EINVAL; + + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(attr, struct tpdm_dataset_attribute, attr); + + if (kstrtoul(buf, 0, &val)) + return ret; + + guard(spinlock)(&drvdata->spinlock); + switch (tpdm_attr->mem) { + case DSB_TRIG_PATT: + if (tpdm_attr->idx < TPDM_DSB_MAX_PATT) { + drvdata->dsb->trig_patt[tpdm_attr->idx] = val; + ret = size; + } + break; + case DSB_TRIG_PATT_MASK: + if (tpdm_attr->idx < TPDM_DSB_MAX_PATT) { + drvdata->dsb->trig_patt_mask[tpdm_attr->idx] = val; + ret = size; + } + break; + case DSB_PATT: + if (tpdm_attr->idx < TPDM_DSB_MAX_PATT) { + drvdata->dsb->patt_val[tpdm_attr->idx] = val; + ret = size; + } + break; + case DSB_PATT_MASK: + if (tpdm_attr->idx < TPDM_DSB_MAX_PATT) { + drvdata->dsb->patt_mask[tpdm_attr->idx] = val; + ret = size; + } + break; + case DSB_MSR: + if (tpdm_attr->idx < drvdata->dsb_msr_num) { + drvdata->dsb->msr[tpdm_attr->idx] = val; + ret = size; + } + break; + case CMB_TRIG_PATT: + if (tpdm_attr->idx < TPDM_CMB_MAX_PATT) { + drvdata->cmb->trig_patt[tpdm_attr->idx] = val; + ret = size; + } + break; + case CMB_TRIG_PATT_MASK: + if (tpdm_attr->idx < TPDM_CMB_MAX_PATT) { + drvdata->cmb->trig_patt_mask[tpdm_attr->idx] = val; + ret = size; + } + break; + case CMB_PATT: + if (tpdm_attr->idx < TPDM_CMB_MAX_PATT) { + drvdata->cmb->patt_val[tpdm_attr->idx] = val; + ret = size; + } + break; + case CMB_PATT_MASK: + if (tpdm_attr->idx < TPDM_CMB_MAX_PATT) { + drvdata->cmb->patt_mask[tpdm_attr->idx] = val; + ret = size; + } + break; + case CMB_MSR: + if (tpdm_attr->idx < drvdata->cmb_msr_num) { + drvdata->cmb->msr[tpdm_attr->idx] = val; + ret = size; + } + break; + default: + break; + } + + return ret; +} + +static umode_t tpdm_dsb_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (drvdata && tpdm_has_dsb_dataset(drvdata)) + return attr->mode; + + return 0; +} + +static umode_t tpdm_cmb_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (drvdata && drvdata->cmb) + return attr->mode; + + return 0; +} + +static umode_t tpdm_dsb_msr_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct device_attribute *dev_attr = + container_of(attr, struct device_attribute, attr); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(dev_attr, struct tpdm_dataset_attribute, attr); + + if (tpdm_attr->idx < drvdata->dsb_msr_num) + return attr->mode; + + return 0; +} + +static umode_t tpdm_cmb_msr_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + struct device_attribute *dev_attr = + container_of(attr, struct device_attribute, attr); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(dev_attr, struct tpdm_dataset_attribute, attr); + + if (tpdm_attr->idx < drvdata->cmb_msr_num) + return attr->mode; + + return 0; +} + +static umode_t tpdm_mcmb_is_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + if (drvdata && tpdm_has_mcmb_dataset(drvdata)) + return attr->mode; + + return 0; +} + +static void tpdm_reset_datasets(struct tpdm_drvdata *drvdata) +{ + if (tpdm_has_dsb_dataset(drvdata)) { + memset(drvdata->dsb, 0, sizeof(struct dsb_dataset)); + + drvdata->dsb->trig_ts = true; + drvdata->dsb->trig_type = false; + } + + if (drvdata->cmb) + memset(drvdata->cmb, 0, sizeof(struct cmb_dataset)); +} + +static void set_dsb_mode(struct tpdm_drvdata *drvdata, u32 *val) +{ + u32 mode; + + /* Set the test accurate mode */ + mode = TPDM_DSB_MODE_TEST(drvdata->dsb->mode); + *val &= ~TPDM_DSB_CR_TEST_MODE; + *val |= FIELD_PREP(TPDM_DSB_CR_TEST_MODE, mode); + + /* Set the byte lane for high-performance mode */ + mode = TPDM_DSB_MODE_HPBYTESEL(drvdata->dsb->mode); + *val &= ~TPDM_DSB_CR_HPSEL; + *val |= FIELD_PREP(TPDM_DSB_CR_HPSEL, mode); + + /* Set the performance mode */ + if (drvdata->dsb->mode & TPDM_DSB_MODE_PERF) + *val |= TPDM_DSB_CR_MODE; + else + *val &= ~TPDM_DSB_CR_MODE; +} + +static void set_dsb_tier(struct tpdm_drvdata *drvdata) +{ + u32 val; + + val = readl_relaxed(drvdata->base + TPDM_DSB_TIER); + + /* Clear all relevant fields */ + val &= ~(TPDM_DSB_TIER_PATT_TSENAB | TPDM_DSB_TIER_PATT_TYPE | + TPDM_DSB_TIER_XTRIG_TSENAB); + + /* Set pattern timestamp type and enablement */ + if (drvdata->dsb->patt_ts) { + val |= TPDM_DSB_TIER_PATT_TSENAB; + if (drvdata->dsb->patt_type) + val |= TPDM_DSB_TIER_PATT_TYPE; + else + val &= ~TPDM_DSB_TIER_PATT_TYPE; + } else { + val &= ~TPDM_DSB_TIER_PATT_TSENAB; + } + + /* Set trigger timestamp */ + if (drvdata->dsb->trig_ts) + val |= TPDM_DSB_TIER_XTRIG_TSENAB; + else + val &= ~TPDM_DSB_TIER_XTRIG_TSENAB; + + writel_relaxed(val, drvdata->base + TPDM_DSB_TIER); +} + +static void set_dsb_msr(struct tpdm_drvdata *drvdata) +{ + int i; + + for (i = 0; i < drvdata->dsb_msr_num; i++) + writel_relaxed(drvdata->dsb->msr[i], + drvdata->base + TPDM_DSB_MSR(i)); +} + +static void tpdm_enable_dsb(struct tpdm_drvdata *drvdata) +{ + u32 val, i; + + if (!tpdm_has_dsb_dataset(drvdata)) + return; + + for (i = 0; i < TPDM_DSB_MAX_EDCR; i++) + writel_relaxed(drvdata->dsb->edge_ctrl[i], + drvdata->base + TPDM_DSB_EDCR(i)); + for (i = 0; i < TPDM_DSB_MAX_EDCMR; i++) + writel_relaxed(drvdata->dsb->edge_ctrl_mask[i], + drvdata->base + TPDM_DSB_EDCMR(i)); + for (i = 0; i < TPDM_DSB_MAX_PATT; i++) { + writel_relaxed(drvdata->dsb->patt_val[i], + drvdata->base + TPDM_DSB_TPR(i)); + writel_relaxed(drvdata->dsb->patt_mask[i], + drvdata->base + TPDM_DSB_TPMR(i)); + writel_relaxed(drvdata->dsb->trig_patt[i], + drvdata->base + TPDM_DSB_XPR(i)); + writel_relaxed(drvdata->dsb->trig_patt_mask[i], + drvdata->base + TPDM_DSB_XPMR(i)); + } + + set_dsb_tier(drvdata); + set_dsb_msr(drvdata); + + val = readl_relaxed(drvdata->base + TPDM_DSB_CR); + /* Set the mode of DSB dataset */ + set_dsb_mode(drvdata, &val); + /* Set trigger type */ + if (drvdata->dsb->trig_type) + val |= TPDM_DSB_CR_TRIG_TYPE; + else + val &= ~TPDM_DSB_CR_TRIG_TYPE; + /* Set the enable bit of DSB control register to 1 */ + val |= TPDM_DSB_CR_ENA; + writel_relaxed(val, drvdata->base + TPDM_DSB_CR); +} + +static void set_cmb_tier(struct tpdm_drvdata *drvdata) +{ + u32 val; + + val = readl_relaxed(drvdata->base + TPDM_CMB_TIER); + + /* Clear all relevant fields */ + val &= ~(TPDM_CMB_TIER_PATT_TSENAB | TPDM_CMB_TIER_TS_ALL | + TPDM_CMB_TIER_XTRIG_TSENAB); + + /* Set pattern timestamp type and enablement */ + if (drvdata->cmb->patt_ts) + val |= TPDM_CMB_TIER_PATT_TSENAB; + + /* Set trigger timestamp */ + if (drvdata->cmb->trig_ts) + val |= TPDM_CMB_TIER_XTRIG_TSENAB; + + /* Set all timestamp enablement*/ + if (drvdata->cmb->ts_all) + val |= TPDM_CMB_TIER_TS_ALL; + + writel_relaxed(val, drvdata->base + TPDM_CMB_TIER); +} + +static void set_cmb_msr(struct tpdm_drvdata *drvdata) +{ + int i; + + for (i = 0; i < drvdata->cmb_msr_num; i++) + writel_relaxed(drvdata->cmb->msr[i], + drvdata->base + TPDM_CMB_MSR(i)); +} + +static void tpdm_enable_cmb(struct tpdm_drvdata *drvdata) +{ + u32 val, i; + + if (!drvdata->cmb) + return; + + /* Configure pattern registers */ + for (i = 0; i < TPDM_CMB_MAX_PATT; i++) { + writel_relaxed(drvdata->cmb->patt_val[i], + drvdata->base + TPDM_CMB_TPR(i)); + writel_relaxed(drvdata->cmb->patt_mask[i], + drvdata->base + TPDM_CMB_TPMR(i)); + writel_relaxed(drvdata->cmb->trig_patt[i], + drvdata->base + TPDM_CMB_XPR(i)); + writel_relaxed(drvdata->cmb->trig_patt_mask[i], + drvdata->base + TPDM_CMB_XPMR(i)); + } + + set_cmb_tier(drvdata); + set_cmb_msr(drvdata); + + val = readl_relaxed(drvdata->base + TPDM_CMB_CR); + /* + * Set to 0 for continuous CMB collection mode, + * 1 for trace-on-change CMB collection mode. + */ + if (drvdata->cmb->trace_mode) + val |= TPDM_CMB_CR_MODE; + else + val &= ~TPDM_CMB_CR_MODE; + + if (tpdm_has_mcmb_dataset(drvdata)) { + val &= ~TPDM_CMB_CR_XTRIG_LNSEL; + /* Set the lane participates in the output pattern */ + val |= FIELD_PREP(TPDM_CMB_CR_XTRIG_LNSEL, + drvdata->cmb->mcmb.trig_lane); + + /* Set the enablement of the lane */ + val &= ~TPDM_CMB_CR_E_LN; + val |= FIELD_PREP(TPDM_CMB_CR_E_LN, + drvdata->cmb->mcmb.lane_select); + } + + /* Set the enable bit of CMB control register to 1 */ + val |= TPDM_CMB_CR_ENA; + writel_relaxed(val, drvdata->base + TPDM_CMB_CR); +} + +/* + * TPDM enable operations + * The TPDM or Monitor serves as data collection component for various + * dataset types. It covers Basic Counts(BC), Tenure Counts(TC), + * Continuous Multi-Bit(CMB), Multi-lane CMB(MCMB) and Discrete Single + * Bit(DSB). This function will initialize the configuration according + * to the dataset type supported by the TPDM. + */ +static void __tpdm_enable(struct tpdm_drvdata *drvdata) +{ + if (coresight_is_static_tpdm(drvdata->csdev)) + return; + + CS_UNLOCK(drvdata->base); + + tpdm_enable_dsb(drvdata); + tpdm_enable_cmb(drvdata); + + CS_LOCK(drvdata->base); +} + +static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event, + enum cs_mode mode, + __maybe_unused struct coresight_path *path) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + spin_lock(&drvdata->spinlock); + if (drvdata->enable) { + spin_unlock(&drvdata->spinlock); + return -EBUSY; + } + + if (!coresight_take_mode(csdev, mode)) { + spin_unlock(&drvdata->spinlock); + return -EBUSY; + } + + __tpdm_enable(drvdata); + drvdata->enable = true; + spin_unlock(&drvdata->spinlock); + + dev_dbg(drvdata->dev, "TPDM tracing enabled\n"); + return 0; +} + +static void tpdm_disable_dsb(struct tpdm_drvdata *drvdata) +{ + u32 val; + + if (!tpdm_has_dsb_dataset(drvdata)) + return; + + /* Set the enable bit of DSB control register to 0 */ + val = readl_relaxed(drvdata->base + TPDM_DSB_CR); + val &= ~TPDM_DSB_CR_ENA; + writel_relaxed(val, drvdata->base + TPDM_DSB_CR); +} + +static void tpdm_disable_cmb(struct tpdm_drvdata *drvdata) +{ + u32 val; + + if (!drvdata->cmb) + return; + + val = readl_relaxed(drvdata->base + TPDM_CMB_CR); + /* Set the enable bit of CMB control register to 0 */ + val &= ~TPDM_CMB_CR_ENA; + writel_relaxed(val, drvdata->base + TPDM_CMB_CR); +} + +/* TPDM disable operations */ +static void __tpdm_disable(struct tpdm_drvdata *drvdata) +{ + if (coresight_is_static_tpdm(drvdata->csdev)) + return; + + CS_UNLOCK(drvdata->base); + + tpdm_disable_dsb(drvdata); + tpdm_disable_cmb(drvdata); + + CS_LOCK(drvdata->base); +} + +static void tpdm_disable(struct coresight_device *csdev, + struct perf_event *event) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + spin_lock(&drvdata->spinlock); + if (!drvdata->enable) { + spin_unlock(&drvdata->spinlock); + return; + } + + __tpdm_disable(drvdata); + coresight_set_mode(csdev, CS_MODE_DISABLED); + drvdata->enable = false; + spin_unlock(&drvdata->spinlock); + + dev_dbg(drvdata->dev, "TPDM tracing disabled\n"); +} + +static const struct coresight_ops_source tpdm_source_ops = { + .enable = tpdm_enable, + .disable = tpdm_disable, +}; + +static const struct coresight_ops tpdm_cs_ops = { + .source_ops = &tpdm_source_ops, +}; + +static int tpdm_datasets_setup(struct tpdm_drvdata *drvdata) +{ + u32 pidr; + + /* Get the datasets present on the TPDM. */ + pidr = readl_relaxed(drvdata->base + CORESIGHT_PERIPHIDR0); + drvdata->datasets |= pidr & GENMASK(TPDM_DATASETS - 1, 0); + + if (tpdm_has_dsb_dataset(drvdata) && (!drvdata->dsb)) { + drvdata->dsb = devm_kzalloc(drvdata->dev, + sizeof(*drvdata->dsb), GFP_KERNEL); + if (!drvdata->dsb) + return -ENOMEM; + } + if ((tpdm_has_cmb_dataset(drvdata) || tpdm_has_mcmb_dataset(drvdata)) + && (!drvdata->cmb)) { + drvdata->cmb = devm_kzalloc(drvdata->dev, + sizeof(*drvdata->cmb), GFP_KERNEL); + if (!drvdata->cmb) + return -ENOMEM; + } + + tpdm_reset_datasets(drvdata); + + return 0; +} + +static int static_tpdm_datasets_setup(struct tpdm_drvdata *drvdata, struct device *dev) +{ + /* setup datasets for static TPDM */ + if (fwnode_property_present(dev->fwnode, "qcom,dsb-element-bits") && + (!drvdata->dsb)) { + drvdata->dsb = devm_kzalloc(drvdata->dev, + sizeof(*drvdata->dsb), GFP_KERNEL); + + if (!drvdata->dsb) + return -ENOMEM; + } + + if (fwnode_property_present(dev->fwnode, "qcom,cmb-element-bits") && + (!drvdata->cmb)) { + drvdata->cmb = devm_kzalloc(drvdata->dev, + sizeof(*drvdata->cmb), GFP_KERNEL); + + if (!drvdata->cmb) + return -ENOMEM; + } + + return 0; +} + +static ssize_t reset_dataset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + int ret = 0; + unsigned long val; + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 0, &val); + if (ret || val != 1) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + tpdm_reset_datasets(drvdata); + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_WO(reset_dataset); + +/* + * value 1: 64 bits test data + * value 2: 32 bits test data + */ +static ssize_t integration_test_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + int i, ret = 0; + unsigned long val; + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val != 1 && val != 2) + return -EINVAL; + + if (!drvdata->enable) + return -EINVAL; + + if (val == 1) + val = ATBCNTRL_VAL_64; + else + val = ATBCNTRL_VAL_32; + CS_UNLOCK(drvdata->base); + writel_relaxed(0x1, drvdata->base + TPDM_ITCNTRL); + + for (i = 0; i < INTEGRATION_TEST_CYCLE; i++) + writel_relaxed(val, drvdata->base + TPDM_ITATBCNTRL); + + writel_relaxed(0, drvdata->base + TPDM_ITCNTRL); + CS_LOCK(drvdata->base); + return size; +} +static DEVICE_ATTR_WO(integration_test); + +static struct attribute *tpdm_attrs[] = { + &dev_attr_reset_dataset.attr, + &dev_attr_integration_test.attr, + NULL, +}; + +static struct attribute_group tpdm_attr_grp = { + .attrs = tpdm_attrs, +}; + +static ssize_t dsb_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%x\n", drvdata->dsb->mode); +} + +static ssize_t dsb_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~TPDM_DSB_MODE_MASK)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + drvdata->dsb->mode = val & TPDM_DSB_MODE_MASK; + spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(dsb_mode); + +static ssize_t ctrl_idx_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->dsb->edge_ctrl_idx); +} + +/* + * The EDCR registers can include up to 16 32-bit registers, and each + * one can be configured to control up to 16 edge detections(2 bits + * control one edge detection). So a total 256 edge detections can be + * configured. This function provides a way to set the index number of + * the edge detection which needs to be configured. + */ +static ssize_t ctrl_idx_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val >= TPDM_DSB_MAX_LINES)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + drvdata->dsb->edge_ctrl_idx = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_RW(ctrl_idx); + +/* + * This function is used to control the edge detection according + * to the index number that has been set. + * "edge_ctrl" should be one of the following values. + * 0 - Rising edge detection + * 1 - Falling edge detection + * 2 - Rising and falling edge detection (toggle detection) + */ +static ssize_t ctrl_val_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val, edge_ctrl; + int reg; + + if ((kstrtoul(buf, 0, &edge_ctrl)) || (edge_ctrl > 0x2)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + /* + * There are 2 bit per DSB Edge Control line. + * Thus we have 16 lines in a 32bit word. + */ + reg = EDCR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx); + val = drvdata->dsb->edge_ctrl[reg]; + val &= ~EDCR_TO_WORD_MASK(drvdata->dsb->edge_ctrl_idx); + val |= EDCR_TO_WORD_VAL(edge_ctrl, drvdata->dsb->edge_ctrl_idx); + drvdata->dsb->edge_ctrl[reg] = val; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_WO(ctrl_val); + +static ssize_t ctrl_mask_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + u32 set; + int reg; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + /* + * There is 1 bit per DSB Edge Control Mark line. + * Thus we have 32 lines in a 32bit word. + */ + reg = EDCMR_TO_WORD_IDX(drvdata->dsb->edge_ctrl_idx); + set = drvdata->dsb->edge_ctrl_mask[reg]; + if (val) + set |= BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx)); + else + set &= ~BIT(EDCMR_TO_WORD_SHIFT(drvdata->dsb->edge_ctrl_idx)); + drvdata->dsb->edge_ctrl_mask[reg] = set; + spin_unlock(&drvdata->spinlock); + + return size; +} +static DEVICE_ATTR_WO(ctrl_mask); + +static ssize_t enable_ts_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(attr, struct tpdm_dataset_attribute, attr); + ssize_t size = -EINVAL; + + if (tpdm_attr->mem == DSB_PATT) + size = sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->dsb->patt_ts); + else if (tpdm_attr->mem == CMB_PATT) + size = sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->cmb->patt_ts); + + return size; +} + +/* + * value 1: Enable/Disable DSB pattern timestamp + */ +static ssize_t enable_ts_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + struct tpdm_dataset_attribute *tpdm_attr = + container_of(attr, struct tpdm_dataset_attribute, attr); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + guard(spinlock)(&drvdata->spinlock); + if (tpdm_attr->mem == DSB_PATT) + drvdata->dsb->patt_ts = !!val; + else if (tpdm_attr->mem == CMB_PATT) + drvdata->cmb->patt_ts = !!val; + else + return -EINVAL; + + return size; +} + +static ssize_t set_type_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->dsb->patt_type); +} + +/* + * value 1: Set DSB pattern type + */ +static ssize_t set_type_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + drvdata->dsb->patt_type = val; + spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(set_type); + +static ssize_t dsb_trig_type_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->dsb->trig_type); +} + +/* + * Trigger type (boolean): + * false - Disable trigger type. + * true - Enable trigger type. + */ +static ssize_t dsb_trig_type_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + if (val) + drvdata->dsb->trig_type = true; + else + drvdata->dsb->trig_type = false; + spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(dsb_trig_type); + +static ssize_t dsb_trig_ts_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->dsb->trig_ts); +} + +/* + * Trigger timestamp (boolean): + * false - Disable trigger timestamp. + * true - Enable trigger timestamp. + */ +static ssize_t dsb_trig_ts_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + if (val) + drvdata->dsb->trig_ts = true; + else + drvdata->dsb->trig_ts = false; + spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(dsb_trig_ts); + +static ssize_t cmb_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%x\n", drvdata->cmb->trace_mode); + +} + +static ssize_t cmb_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long trace_mode; + + if (kstrtoul(buf, 0, &trace_mode) || (trace_mode & ~1UL)) + return -EINVAL; + + spin_lock(&drvdata->spinlock); + drvdata->cmb->trace_mode = trace_mode; + spin_unlock(&drvdata->spinlock); + return size; +} +static DEVICE_ATTR_RW(cmb_mode); + +static ssize_t cmb_ts_all_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->cmb->ts_all); +} + +static ssize_t cmb_ts_all_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + guard(spinlock)(&drvdata->spinlock); + if (val) + drvdata->cmb->ts_all = true; + else + drvdata->cmb->ts_all = false; + + return size; +} +static DEVICE_ATTR_RW(cmb_ts_all); + +static ssize_t cmb_trig_ts_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->cmb->trig_ts); +} + +static ssize_t cmb_trig_ts_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val & ~1UL)) + return -EINVAL; + + guard(spinlock)(&drvdata->spinlock); + if (val) + drvdata->cmb->trig_ts = true; + else + drvdata->cmb->trig_ts = false; + + return size; +} +static DEVICE_ATTR_RW(cmb_trig_ts); + +static ssize_t mcmb_trig_lane_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->cmb->mcmb.trig_lane); +} + +static ssize_t mcmb_trig_lane_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if ((kstrtoul(buf, 0, &val)) || (val >= TPDM_MCMB_MAX_LANES)) + return -EINVAL; + + guard(spinlock)(&drvdata->spinlock); + drvdata->cmb->mcmb.trig_lane = val; + + return size; +} +static DEVICE_ATTR_RW(mcmb_trig_lane); + +static ssize_t mcmb_lanes_select_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "%u\n", + (unsigned int)drvdata->cmb->mcmb.lane_select); +} + +static ssize_t mcmb_lanes_select_store(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t size) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev->parent); + unsigned long val; + + if (kstrtoul(buf, 0, &val) || (val & ~TPDM_MCMB_E_LN_MASK)) + return -EINVAL; + + guard(spinlock)(&drvdata->spinlock); + drvdata->cmb->mcmb.lane_select = val & TPDM_MCMB_E_LN_MASK; + + return size; +} +static DEVICE_ATTR_RW(mcmb_lanes_select); + +static struct attribute *tpdm_dsb_edge_attrs[] = { + &dev_attr_ctrl_idx.attr, + &dev_attr_ctrl_val.attr, + &dev_attr_ctrl_mask.attr, + DSB_EDGE_CTRL_ATTR(0), + DSB_EDGE_CTRL_ATTR(1), + DSB_EDGE_CTRL_ATTR(2), + DSB_EDGE_CTRL_ATTR(3), + DSB_EDGE_CTRL_ATTR(4), + DSB_EDGE_CTRL_ATTR(5), + DSB_EDGE_CTRL_ATTR(6), + DSB_EDGE_CTRL_ATTR(7), + DSB_EDGE_CTRL_ATTR(8), + DSB_EDGE_CTRL_ATTR(9), + DSB_EDGE_CTRL_ATTR(10), + DSB_EDGE_CTRL_ATTR(11), + DSB_EDGE_CTRL_ATTR(12), + DSB_EDGE_CTRL_ATTR(13), + DSB_EDGE_CTRL_ATTR(14), + DSB_EDGE_CTRL_ATTR(15), + DSB_EDGE_CTRL_MASK_ATTR(0), + DSB_EDGE_CTRL_MASK_ATTR(1), + DSB_EDGE_CTRL_MASK_ATTR(2), + DSB_EDGE_CTRL_MASK_ATTR(3), + DSB_EDGE_CTRL_MASK_ATTR(4), + DSB_EDGE_CTRL_MASK_ATTR(5), + DSB_EDGE_CTRL_MASK_ATTR(6), + DSB_EDGE_CTRL_MASK_ATTR(7), + NULL, +}; + +static struct attribute *tpdm_dsb_trig_patt_attrs[] = { + DSB_TRIG_PATT_ATTR(0), + DSB_TRIG_PATT_ATTR(1), + DSB_TRIG_PATT_ATTR(2), + DSB_TRIG_PATT_ATTR(3), + DSB_TRIG_PATT_ATTR(4), + DSB_TRIG_PATT_ATTR(5), + DSB_TRIG_PATT_ATTR(6), + DSB_TRIG_PATT_ATTR(7), + DSB_TRIG_PATT_MASK_ATTR(0), + DSB_TRIG_PATT_MASK_ATTR(1), + DSB_TRIG_PATT_MASK_ATTR(2), + DSB_TRIG_PATT_MASK_ATTR(3), + DSB_TRIG_PATT_MASK_ATTR(4), + DSB_TRIG_PATT_MASK_ATTR(5), + DSB_TRIG_PATT_MASK_ATTR(6), + DSB_TRIG_PATT_MASK_ATTR(7), + NULL, +}; + +static struct attribute *tpdm_dsb_patt_attrs[] = { + DSB_PATT_ATTR(0), + DSB_PATT_ATTR(1), + DSB_PATT_ATTR(2), + DSB_PATT_ATTR(3), + DSB_PATT_ATTR(4), + DSB_PATT_ATTR(5), + DSB_PATT_ATTR(6), + DSB_PATT_ATTR(7), + DSB_PATT_MASK_ATTR(0), + DSB_PATT_MASK_ATTR(1), + DSB_PATT_MASK_ATTR(2), + DSB_PATT_MASK_ATTR(3), + DSB_PATT_MASK_ATTR(4), + DSB_PATT_MASK_ATTR(5), + DSB_PATT_MASK_ATTR(6), + DSB_PATT_MASK_ATTR(7), + DSB_PATT_ENABLE_TS, + &dev_attr_set_type.attr, + NULL, +}; + +static struct attribute *tpdm_dsb_msr_attrs[] = { + DSB_MSR_ATTR(0), + DSB_MSR_ATTR(1), + DSB_MSR_ATTR(2), + DSB_MSR_ATTR(3), + DSB_MSR_ATTR(4), + DSB_MSR_ATTR(5), + DSB_MSR_ATTR(6), + DSB_MSR_ATTR(7), + DSB_MSR_ATTR(8), + DSB_MSR_ATTR(9), + DSB_MSR_ATTR(10), + DSB_MSR_ATTR(11), + DSB_MSR_ATTR(12), + DSB_MSR_ATTR(13), + DSB_MSR_ATTR(14), + DSB_MSR_ATTR(15), + DSB_MSR_ATTR(16), + DSB_MSR_ATTR(17), + DSB_MSR_ATTR(18), + DSB_MSR_ATTR(19), + DSB_MSR_ATTR(20), + DSB_MSR_ATTR(21), + DSB_MSR_ATTR(22), + DSB_MSR_ATTR(23), + DSB_MSR_ATTR(24), + DSB_MSR_ATTR(25), + DSB_MSR_ATTR(26), + DSB_MSR_ATTR(27), + DSB_MSR_ATTR(28), + DSB_MSR_ATTR(29), + DSB_MSR_ATTR(30), + DSB_MSR_ATTR(31), + NULL, +}; + +static struct attribute *tpdm_cmb_trig_patt_attrs[] = { + CMB_TRIG_PATT_ATTR(0), + CMB_TRIG_PATT_ATTR(1), + CMB_TRIG_PATT_MASK_ATTR(0), + CMB_TRIG_PATT_MASK_ATTR(1), + NULL, +}; + +static struct attribute *tpdm_cmb_patt_attrs[] = { + CMB_PATT_ATTR(0), + CMB_PATT_ATTR(1), + CMB_PATT_MASK_ATTR(0), + CMB_PATT_MASK_ATTR(1), + CMB_PATT_ENABLE_TS, + NULL, +}; + +static struct attribute *tpdm_cmb_msr_attrs[] = { + CMB_MSR_ATTR(0), + CMB_MSR_ATTR(1), + CMB_MSR_ATTR(2), + CMB_MSR_ATTR(3), + CMB_MSR_ATTR(4), + CMB_MSR_ATTR(5), + CMB_MSR_ATTR(6), + CMB_MSR_ATTR(7), + CMB_MSR_ATTR(8), + CMB_MSR_ATTR(9), + CMB_MSR_ATTR(10), + CMB_MSR_ATTR(11), + CMB_MSR_ATTR(12), + CMB_MSR_ATTR(13), + CMB_MSR_ATTR(14), + CMB_MSR_ATTR(15), + CMB_MSR_ATTR(16), + CMB_MSR_ATTR(17), + CMB_MSR_ATTR(18), + CMB_MSR_ATTR(19), + CMB_MSR_ATTR(20), + CMB_MSR_ATTR(21), + CMB_MSR_ATTR(22), + CMB_MSR_ATTR(23), + CMB_MSR_ATTR(24), + CMB_MSR_ATTR(25), + CMB_MSR_ATTR(26), + CMB_MSR_ATTR(27), + CMB_MSR_ATTR(28), + CMB_MSR_ATTR(29), + CMB_MSR_ATTR(30), + CMB_MSR_ATTR(31), + NULL, +}; + +static struct attribute *tpdm_mcmb_attrs[] = { + &dev_attr_mcmb_trig_lane.attr, + &dev_attr_mcmb_lanes_select.attr, + NULL, +}; + +static struct attribute *tpdm_dsb_attrs[] = { + &dev_attr_dsb_mode.attr, + &dev_attr_dsb_trig_ts.attr, + &dev_attr_dsb_trig_type.attr, + NULL, +}; + +static struct attribute *tpdm_cmb_attrs[] = { + &dev_attr_cmb_mode.attr, + &dev_attr_cmb_ts_all.attr, + &dev_attr_cmb_trig_ts.attr, + NULL, +}; + +static struct attribute_group tpdm_dsb_attr_grp = { + .attrs = tpdm_dsb_attrs, + .is_visible = tpdm_dsb_is_visible, +}; + +static struct attribute_group tpdm_dsb_edge_grp = { + .attrs = tpdm_dsb_edge_attrs, + .is_visible = tpdm_dsb_is_visible, + .name = "dsb_edge", +}; + +static struct attribute_group tpdm_dsb_trig_patt_grp = { + .attrs = tpdm_dsb_trig_patt_attrs, + .is_visible = tpdm_dsb_is_visible, + .name = "dsb_trig_patt", +}; + +static struct attribute_group tpdm_dsb_patt_grp = { + .attrs = tpdm_dsb_patt_attrs, + .is_visible = tpdm_dsb_is_visible, + .name = "dsb_patt", +}; + +static struct attribute_group tpdm_dsb_msr_grp = { + .attrs = tpdm_dsb_msr_attrs, + .is_visible = tpdm_dsb_msr_is_visible, + .name = "dsb_msr", +}; + +static struct attribute_group tpdm_cmb_attr_grp = { + .attrs = tpdm_cmb_attrs, + .is_visible = tpdm_cmb_is_visible, +}; + +static struct attribute_group tpdm_cmb_trig_patt_grp = { + .attrs = tpdm_cmb_trig_patt_attrs, + .is_visible = tpdm_cmb_is_visible, + .name = "cmb_trig_patt", +}; + +static struct attribute_group tpdm_cmb_patt_grp = { + .attrs = tpdm_cmb_patt_attrs, + .is_visible = tpdm_cmb_is_visible, + .name = "cmb_patt", +}; + +static struct attribute_group tpdm_cmb_msr_grp = { + .attrs = tpdm_cmb_msr_attrs, + .is_visible = tpdm_cmb_msr_is_visible, + .name = "cmb_msr", +}; + +static struct attribute_group tpdm_mcmb_attr_grp = { + .attrs = tpdm_mcmb_attrs, + .is_visible = tpdm_mcmb_is_visible, +}; + +static const struct attribute_group *tpdm_attr_grps[] = { + &tpdm_attr_grp, + &tpdm_dsb_attr_grp, + &tpdm_dsb_edge_grp, + &tpdm_dsb_trig_patt_grp, + &tpdm_dsb_patt_grp, + &tpdm_dsb_msr_grp, + &tpdm_cmb_attr_grp, + &tpdm_cmb_trig_patt_grp, + &tpdm_cmb_patt_grp, + &tpdm_cmb_msr_grp, + &tpdm_mcmb_attr_grp, + NULL, +}; + +static int tpdm_probe(struct device *dev, struct resource *res) +{ + void __iomem *base; + struct coresight_platform_data *pdata; + struct tpdm_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + int ret; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + dev->platform_data = pdata; + + /* driver data*/ + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + drvdata->dev = dev; + dev_set_drvdata(dev, drvdata); + + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + drvdata->base = base; + ret = tpdm_datasets_setup(drvdata); + if (ret) + return ret; + + if (tpdm_has_dsb_dataset(drvdata)) + of_property_read_u32(drvdata->dev->of_node, + "qcom,dsb-msrs-num", &drvdata->dsb_msr_num); + + if (tpdm_has_cmb_dataset(drvdata)) + of_property_read_u32(drvdata->dev->of_node, + "qcom,cmb-msrs-num", &drvdata->cmb_msr_num); + } else { + ret = static_tpdm_datasets_setup(drvdata, dev); + if (ret) + return ret; + } + + /* Set up coresight component description */ + desc.name = coresight_alloc_device_name(&tpdm_devs, dev); + if (!desc.name) + return -ENOMEM; + desc.type = CORESIGHT_DEV_TYPE_SOURCE; + desc.subtype.source_subtype = CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM; + desc.ops = &tpdm_cs_ops; + desc.pdata = dev->platform_data; + desc.dev = dev; + desc.access = CSDEV_ACCESS_IOMEM(base); + if (res) + desc.groups = tpdm_attr_grps; + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + spin_lock_init(&drvdata->spinlock); + + return 0; +} + +static int tpdm_remove(struct device *dev) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); + + return 0; +} + +static int dynamic_tpdm_probe(struct amba_device *adev, + const struct amba_id *id) +{ + int ret; + + ret = tpdm_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static void dynamic_tpdm_remove(struct amba_device *adev) +{ + tpdm_remove(&adev->dev); +} + +/* + * Different TPDM has different periph id. + * The difference is 0-7 bits' value. So ignore 0-7 bits. + */ +static const struct amba_id dynamic_tpdm_ids[] = { + { + .id = 0x001f0e00, + .mask = 0x00ffff00, + }, + { 0, 0, NULL }, +}; + +MODULE_DEVICE_TABLE(amba, dynamic_tpdm_ids); + +static struct amba_driver dynamic_tpdm_driver = { + .drv = { + .name = "coresight-tpdm", + .suppress_bind_attrs = true, + }, + .probe = dynamic_tpdm_probe, + .id_table = dynamic_tpdm_ids, + .remove = dynamic_tpdm_remove, +}; + +static int tpdm_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = tpdm_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void tpdm_platform_remove(struct platform_device *pdev) +{ + struct tpdm_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + tpdm_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +static const struct of_device_id static_tpdm_match[] = { + {.compatible = "qcom,coresight-static-tpdm"}, + {} +}; + +MODULE_DEVICE_TABLE(of, static_tpdm_match); + +static struct platform_driver static_tpdm_driver = { + .probe = tpdm_platform_probe, + .remove = tpdm_platform_remove, + .driver = { + .name = "coresight-static-tpdm", + .of_match_table = static_tpdm_match, + .suppress_bind_attrs = true, + }, +}; + +static int __init tpdm_init(void) +{ + return coresight_init_driver("tpdm", &dynamic_tpdm_driver, &static_tpdm_driver, + THIS_MODULE); +} + +static void __exit tpdm_exit(void) +{ + coresight_remove_driver(&dynamic_tpdm_driver, &static_tpdm_driver); +} + +module_init(tpdm_init); +module_exit(tpdm_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Trace, Profiling & Diagnostic Monitor driver"); diff --git a/drivers/hwtracing/coresight/coresight-tpdm.h b/drivers/hwtracing/coresight/coresight-tpdm.h new file mode 100644 index 000000000000..2867f3ab8186 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-tpdm.h @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023-2025 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _CORESIGHT_CORESIGHT_TPDM_H +#define _CORESIGHT_CORESIGHT_TPDM_H + +/* The max number of the datasets that TPDM supports */ +#define TPDM_DATASETS 7 + +/* CMB/MCMB Subunit Registers */ +#define TPDM_CMB_CR (0xA00) +/* CMB subunit timestamp insertion enable register */ +#define TPDM_CMB_TIER (0xA04) +/* CMB subunit timestamp pattern registers */ +#define TPDM_CMB_TPR(n) (0xA08 + (n * 4)) +/* CMB subunit timestamp pattern mask registers */ +#define TPDM_CMB_TPMR(n) (0xA10 + (n * 4)) +/* CMB subunit trigger pattern registers */ +#define TPDM_CMB_XPR(n) (0xA18 + (n * 4)) +/* CMB subunit trigger pattern mask registers */ +#define TPDM_CMB_XPMR(n) (0xA20 + (n * 4)) +/* CMB MSR register */ +#define TPDM_CMB_MSR(n) (0xA80 + (n * 4)) + +/* Enable bit for CMB subunit */ +#define TPDM_CMB_CR_ENA BIT(0) +/* Trace collection mode for CMB subunit */ +#define TPDM_CMB_CR_MODE BIT(1) +/* MCMB trigger lane select */ +#define TPDM_CMB_CR_XTRIG_LNSEL GENMASK(20, 18) +/* MCMB lane enablement */ +#define TPDM_CMB_CR_E_LN GENMASK(17, 10) +/* Timestamp control for pattern match */ +#define TPDM_CMB_TIER_PATT_TSENAB BIT(0) +/* CMB CTI timestamp request */ +#define TPDM_CMB_TIER_XTRIG_TSENAB BIT(1) +/* For timestamp fo all trace */ +#define TPDM_CMB_TIER_TS_ALL BIT(2) + +/* Patten register number */ +#define TPDM_CMB_MAX_PATT 2 + +/* MAX number of DSB MSR */ +#define TPDM_CMB_MAX_MSR 32 + +/* MAX lanes in the output pattern for MCMB configurations*/ +#define TPDM_MCMB_MAX_LANES 8 + +/* Filter bit 0~7 from the value for CR_E_LN */ +#define TPDM_MCMB_E_LN_MASK GENMASK(7, 0) + +/* DSB Subunit Registers */ +#define TPDM_DSB_CR (0x780) +#define TPDM_DSB_TIER (0x784) +#define TPDM_DSB_TPR(n) (0x788 + (n * 4)) +#define TPDM_DSB_TPMR(n) (0x7A8 + (n * 4)) +#define TPDM_DSB_XPR(n) (0x7C8 + (n * 4)) +#define TPDM_DSB_XPMR(n) (0x7E8 + (n * 4)) +#define TPDM_DSB_EDCR(n) (0x808 + (n * 4)) +#define TPDM_DSB_EDCMR(n) (0x848 + (n * 4)) +#define TPDM_DSB_MSR(n) (0x980 + (n * 4)) + +/* Enable bit for DSB subunit */ +#define TPDM_DSB_CR_ENA BIT(0) +/* Enable bit for DSB subunit perfmance mode */ +#define TPDM_DSB_CR_MODE BIT(1) +/* Enable bit for DSB subunit trigger type */ +#define TPDM_DSB_CR_TRIG_TYPE BIT(12) +/* Data bits for DSB high performace mode */ +#define TPDM_DSB_CR_HPSEL GENMASK(6, 2) +/* Data bits for DSB test mode */ +#define TPDM_DSB_CR_TEST_MODE GENMASK(10, 9) + +/* Enable bit for DSB subunit pattern timestamp */ +#define TPDM_DSB_TIER_PATT_TSENAB BIT(0) +/* Enable bit for DSB subunit trigger timestamp */ +#define TPDM_DSB_TIER_XTRIG_TSENAB BIT(1) +/* Bit for DSB subunit pattern type */ +#define TPDM_DSB_TIER_PATT_TYPE BIT(2) + +/* DSB programming modes */ +/* DSB mode bits mask */ +#define TPDM_DSB_MODE_MASK GENMASK(8, 0) +/* Test mode control bit*/ +#define TPDM_DSB_MODE_TEST(val) (val & GENMASK(1, 0)) +/* Performance mode */ +#define TPDM_DSB_MODE_PERF BIT(3) +/* High performance mode */ +#define TPDM_DSB_MODE_HPBYTESEL(val) (val & GENMASK(8, 4)) + +#define EDCRS_PER_WORD 16 +#define EDCR_TO_WORD_IDX(r) ((r) / EDCRS_PER_WORD) +#define EDCR_TO_WORD_SHIFT(r) ((r % EDCRS_PER_WORD) * 2) +#define EDCR_TO_WORD_VAL(val, r) (val << EDCR_TO_WORD_SHIFT(r)) +#define EDCR_TO_WORD_MASK(r) EDCR_TO_WORD_VAL(0x3, r) + +#define EDCMRS_PER_WORD 32 +#define EDCMR_TO_WORD_IDX(r) ((r) / EDCMRS_PER_WORD) +#define EDCMR_TO_WORD_SHIFT(r) ((r) % EDCMRS_PER_WORD) + +/* TPDM integration test registers */ +#define TPDM_ITATBCNTRL (0xEF0) +#define TPDM_ITCNTRL (0xF00) + +/* Register value for integration test */ +#define ATBCNTRL_VAL_32 0xC00F1409 +#define ATBCNTRL_VAL_64 0xC01F1409 + +/* + * Number of cycles to write value when + * integration test. + */ +#define INTEGRATION_TEST_CYCLE 10 + +/** + * The bits of PERIPHIDR0 register. + * The fields [6:0] of PERIPHIDR0 are used to determine what + * interfaces and subunits are present on a given TPDM. + * + * PERIPHIDR0[0] : Fix to 1 if ImplDef subunit present, else 0 + * PERIPHIDR0[1] : Fix to 1 if DSB subunit present, else 0 + * PERIPHIDR0[2] : Fix to 1 if CMB subunit present, else 0 + * PERIPHIDR0[6] : Fix to 1 if MCMB subunit present, else 0 + */ + +#define TPDM_PIDR0_DS_IMPDEF BIT(0) +#define TPDM_PIDR0_DS_DSB BIT(1) +#define TPDM_PIDR0_DS_CMB BIT(2) +#define TPDM_PIDR0_DS_MCMB BIT(6) + +#define TPDM_DSB_MAX_LINES 256 +/* MAX number of EDCR registers */ +#define TPDM_DSB_MAX_EDCR 16 +/* MAX number of EDCMR registers */ +#define TPDM_DSB_MAX_EDCMR 8 +/* MAX number of DSB pattern */ +#define TPDM_DSB_MAX_PATT 8 +/* MAX number of DSB MSR */ +#define TPDM_DSB_MAX_MSR 32 + +#define tpdm_simple_dataset_ro(name, mem, idx) \ + (&((struct tpdm_dataset_attribute[]) { \ + { \ + __ATTR(name, 0444, tpdm_simple_dataset_show, NULL), \ + mem, \ + idx, \ + } \ + })[0].attr.attr) + +#define tpdm_simple_dataset_rw(name, mem, idx) \ + (&((struct tpdm_dataset_attribute[]) { \ + { \ + __ATTR(name, 0644, tpdm_simple_dataset_show, \ + tpdm_simple_dataset_store), \ + mem, \ + idx, \ + } \ + })[0].attr.attr) + +#define tpdm_patt_enable_ts(name, mem) \ + (&((struct tpdm_dataset_attribute[]) { \ + { \ + __ATTR(name, 0644, enable_ts_show, \ + enable_ts_store), \ + mem, \ + 0, \ + } \ + })[0].attr.attr) + +#define DSB_EDGE_CTRL_ATTR(nr) \ + tpdm_simple_dataset_ro(edcr##nr, \ + DSB_EDGE_CTRL, nr) + +#define DSB_EDGE_CTRL_MASK_ATTR(nr) \ + tpdm_simple_dataset_ro(edcmr##nr, \ + DSB_EDGE_CTRL_MASK, nr) + +#define DSB_TRIG_PATT_ATTR(nr) \ + tpdm_simple_dataset_rw(xpr##nr, \ + DSB_TRIG_PATT, nr) + +#define DSB_TRIG_PATT_MASK_ATTR(nr) \ + tpdm_simple_dataset_rw(xpmr##nr, \ + DSB_TRIG_PATT_MASK, nr) + +#define DSB_PATT_ATTR(nr) \ + tpdm_simple_dataset_rw(tpr##nr, \ + DSB_PATT, nr) + +#define DSB_PATT_MASK_ATTR(nr) \ + tpdm_simple_dataset_rw(tpmr##nr, \ + DSB_PATT_MASK, nr) + +#define DSB_PATT_ENABLE_TS \ + tpdm_patt_enable_ts(enable_ts, \ + DSB_PATT) + +#define DSB_MSR_ATTR(nr) \ + tpdm_simple_dataset_rw(msr##nr, \ + DSB_MSR, nr) + +#define CMB_TRIG_PATT_ATTR(nr) \ + tpdm_simple_dataset_rw(xpr##nr, \ + CMB_TRIG_PATT, nr) + +#define CMB_TRIG_PATT_MASK_ATTR(nr) \ + tpdm_simple_dataset_rw(xpmr##nr, \ + CMB_TRIG_PATT_MASK, nr) + +#define CMB_PATT_ATTR(nr) \ + tpdm_simple_dataset_rw(tpr##nr, \ + CMB_PATT, nr) + +#define CMB_PATT_MASK_ATTR(nr) \ + tpdm_simple_dataset_rw(tpmr##nr, \ + CMB_PATT_MASK, nr) + +#define CMB_PATT_ENABLE_TS \ + tpdm_patt_enable_ts(enable_ts, \ + CMB_PATT) + +#define CMB_MSR_ATTR(nr) \ + tpdm_simple_dataset_rw(msr##nr, \ + CMB_MSR, nr) + +/** + * struct dsb_dataset - specifics associated to dsb dataset + * @mode: DSB programming mode + * @edge_ctrl_idx Index number of the edge control + * @edge_ctrl: Save value for edge control + * @edge_ctrl_mask: Save value for edge control mask + * @patt_val: Save value for pattern + * @patt_mask: Save value for pattern mask + * @trig_patt: Save value for trigger pattern + * @trig_patt_mask: Save value for trigger pattern mask + * @msr Save value for MSR + * @patt_ts: Enable/Disable pattern timestamp + * @patt_type: Set pattern type + * @trig_ts: Enable/Disable trigger timestamp. + * @trig_type: Enable/Disable trigger type. + */ +struct dsb_dataset { + u32 mode; + u32 edge_ctrl_idx; + u32 edge_ctrl[TPDM_DSB_MAX_EDCR]; + u32 edge_ctrl_mask[TPDM_DSB_MAX_EDCMR]; + u32 patt_val[TPDM_DSB_MAX_PATT]; + u32 patt_mask[TPDM_DSB_MAX_PATT]; + u32 trig_patt[TPDM_DSB_MAX_PATT]; + u32 trig_patt_mask[TPDM_DSB_MAX_PATT]; + u32 msr[TPDM_DSB_MAX_MSR]; + bool patt_ts; + bool patt_type; + bool trig_ts; + bool trig_type; +}; + +/** + * struct cmb_dataset + * @trace_mode: Dataset collection mode + * @patt_val: Save value for pattern + * @patt_mask: Save value for pattern mask + * @trig_patt: Save value for trigger pattern + * @trig_patt_mask: Save value for trigger pattern mask + * @msr Save value for MSR + * @patt_ts: Indicates if pattern match for timestamp is enabled. + * @trig_ts: Indicates if CTI trigger for timestamp is enabled. + * @ts_all: Indicates if timestamp is enabled for all packets. + * struct mcmb_dataset + * @mcmb_trig_lane: Save data for trigger lane + * @mcmb_lane_select: Save data for lane enablement + */ +struct cmb_dataset { + u32 trace_mode; + u32 patt_val[TPDM_CMB_MAX_PATT]; + u32 patt_mask[TPDM_CMB_MAX_PATT]; + u32 trig_patt[TPDM_CMB_MAX_PATT]; + u32 trig_patt_mask[TPDM_CMB_MAX_PATT]; + u32 msr[TPDM_CMB_MAX_MSR]; + bool patt_ts; + bool trig_ts; + bool ts_all; + struct { + u8 trig_lane; + u8 lane_select; + } mcmb; +}; + +/** + * struct tpdm_drvdata - specifics associated to an TPDM component + * @base: memory mapped base address for this component. + * @dev: The device entity associated to this component. + * @csdev: component vitals needed by the framework. + * @spinlock: lock for the drvdata value. + * @enable: enable status of the component. + * @datasets: The datasets types present of the TPDM. + * @dsb Specifics associated to TPDM DSB. + * @cmb Specifics associated to TPDM CMB. + * @dsb_msr_num Number of MSR supported by DSB TPDM + * @cmb_msr_num Number of MSR supported by CMB TPDM + */ + +struct tpdm_drvdata { + void __iomem *base; + struct device *dev; + struct coresight_device *csdev; + spinlock_t spinlock; + bool enable; + unsigned long datasets; + struct dsb_dataset *dsb; + struct cmb_dataset *cmb; + u32 dsb_msr_num; + u32 cmb_msr_num; +}; + +/* Enumerate members of various datasets */ +enum dataset_mem { + DSB_EDGE_CTRL, + DSB_EDGE_CTRL_MASK, + DSB_TRIG_PATT, + DSB_TRIG_PATT_MASK, + DSB_PATT, + DSB_PATT_MASK, + DSB_MSR, + CMB_TRIG_PATT, + CMB_TRIG_PATT_MASK, + CMB_PATT, + CMB_PATT_MASK, + CMB_MSR +}; + +/** + * struct tpdm_dataset_attribute - Record the member variables and + * index number of datasets that need to be operated by sysfs file + * @attr: The device attribute + * @mem: The member in the dataset data structure + * @idx: The index number of the array data + */ +struct tpdm_dataset_attribute { + struct device_attribute attr; + enum dataset_mem mem; + u32 idx; +}; + +static inline bool coresight_device_is_tpdm(struct coresight_device *csdev) +{ + return (coresight_is_device_source(csdev)) && + (csdev->subtype.source_subtype == + CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM); +} + +static inline bool coresight_is_static_tpdm(struct coresight_device *csdev) +{ + return (coresight_device_is_tpdm(csdev) && !csdev->access.base); +} +#endif /* _CORESIGHT_CORESIGHT_TPDM_H */ diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index b2f72a1fa402..aaa44bc521c3 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -5,16 +5,19 @@ * Description: CoreSight Trace Port Interface Unit driver */ -#include <linux/kernel.h> -#include <linux/init.h> +#include <linux/acpi.h> +#include <linux/amba/bus.h> +#include <linux/atomic.h> +#include <linux/clk.h> +#include <linux/coresight.h> #include <linux/device.h> -#include <linux/io.h> #include <linux/err.h> -#include <linux/slab.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/platform_device.h> #include <linux/pm_runtime.h> -#include <linux/coresight.h> -#include <linux/amba/bus.h> -#include <linux/clk.h> +#include <linux/slab.h> #include "coresight-priv.h" @@ -46,61 +49,72 @@ #define FFCR_FON_MAN BIT(6) #define FFCR_STOP_FI BIT(12) -/** +DEFINE_CORESIGHT_DEVLIST(tpiu_devs, "tpiu"); + +/* * @base: memory mapped base address for this component. - * @dev: the device entity associated to this component. * @atclk: optional clock for the core parts of the TPIU. + * @pclk: APB clock if present, otherwise NULL * @csdev: component vitals needed by the framework. */ struct tpiu_drvdata { void __iomem *base; - struct device *dev; struct clk *atclk; + struct clk *pclk; struct coresight_device *csdev; + spinlock_t spinlock; }; -static void tpiu_enable_hw(struct tpiu_drvdata *drvdata) +static void tpiu_enable_hw(struct csdev_access *csa) { - CS_UNLOCK(drvdata->base); + CS_UNLOCK(csa->base); /* TODO: fill this up */ - CS_LOCK(drvdata->base); + CS_LOCK(csa->base); } -static int tpiu_enable(struct coresight_device *csdev, u32 mode, void *__unused) +static int tpiu_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) { struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - tpiu_enable_hw(drvdata); - - dev_dbg(drvdata->dev, "TPIU enabled\n"); + guard(spinlock)(&drvdata->spinlock); + tpiu_enable_hw(&csdev->access); + csdev->refcnt++; + dev_dbg(&csdev->dev, "TPIU enabled\n"); return 0; } -static void tpiu_disable_hw(struct tpiu_drvdata *drvdata) +static void tpiu_disable_hw(struct csdev_access *csa) { - CS_UNLOCK(drvdata->base); + CS_UNLOCK(csa->base); /* Clear formatter and stop on flush */ - writel_relaxed(FFCR_STOP_FI, drvdata->base + TPIU_FFCR); + csdev_access_relaxed_write32(csa, FFCR_STOP_FI, TPIU_FFCR); /* Generate manual flush */ - writel_relaxed(FFCR_STOP_FI | FFCR_FON_MAN, drvdata->base + TPIU_FFCR); + csdev_access_relaxed_write32(csa, FFCR_STOP_FI | FFCR_FON_MAN, TPIU_FFCR); /* Wait for flush to complete */ - coresight_timeout(drvdata->base, TPIU_FFCR, FFCR_FON_MAN_BIT, 0); + coresight_timeout(csa, TPIU_FFCR, FFCR_FON_MAN_BIT, 0); /* Wait for formatter to stop */ - coresight_timeout(drvdata->base, TPIU_FFSR, FFSR_FT_STOPPED_BIT, 1); + coresight_timeout(csa, TPIU_FFSR, FFSR_FT_STOPPED_BIT, 1); - CS_LOCK(drvdata->base); + CS_LOCK(csa->base); } -static void tpiu_disable(struct coresight_device *csdev) +static int tpiu_disable(struct coresight_device *csdev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - tpiu_disable_hw(drvdata); + guard(spinlock)(&drvdata->spinlock); + csdev->refcnt--; + if (csdev->refcnt) + return -EBUSY; + + tpiu_disable_hw(&csdev->access); - dev_dbg(drvdata->dev, "TPIU disabled\n"); + dev_dbg(&csdev->dev, "TPIU disabled\n"); + return 0; } static const struct coresight_ops_sink tpiu_sink_ops = { @@ -112,35 +126,28 @@ static const struct coresight_ops tpiu_cs_ops = { .sink_ops = &tpiu_sink_ops, }; -static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) +static int __tpiu_probe(struct device *dev, struct resource *res) { - int ret; void __iomem *base; - struct device *dev = &adev->dev; struct coresight_platform_data *pdata = NULL; struct tpiu_drvdata *drvdata; - struct resource *res = &adev->res; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; + int ret; - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - adev->dev.platform_data = pdata; - } + desc.name = coresight_alloc_device_name(&tpiu_devs, dev); + if (!desc.name) + return -ENOMEM; drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } + spin_lock_init(&drvdata->spinlock); + + ret = coresight_get_enable_clocks(dev, &drvdata->pclk, &drvdata->atclk); + if (ret) + return ret; + dev_set_drvdata(dev, drvdata); /* Validity for the resource is already checked by the AMBA core */ @@ -149,11 +156,15 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); /* Disable tpiu to support older devices */ - tpiu_disable_hw(drvdata); + tpiu_disable_hw(&desc.access); - pm_runtime_put(&adev->dev); + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + dev->platform_data = pdata; desc.type = CORESIGHT_DEV_TYPE_SINK; desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT; @@ -162,7 +173,32 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) desc.dev = dev; drvdata->csdev = coresight_register(&desc); - return PTR_ERR_OR_ZERO(drvdata->csdev); + if (!IS_ERR(drvdata->csdev)) + return 0; + + return PTR_ERR(drvdata->csdev); +} + +static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) +{ + int ret; + + ret = __tpiu_probe(&adev->dev, &adev->res); + if (!ret) + pm_runtime_put(&adev->dev); + return ret; +} + +static void __tpiu_remove(struct device *dev) +{ + struct tpiu_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); +} + +static void tpiu_remove(struct amba_device *adev) +{ + __tpiu_remove(&adev->dev); } #ifdef CONFIG_PM @@ -170,8 +206,8 @@ static int tpiu_runtime_suspend(struct device *dev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(dev); - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->atclk); + clk_disable_unprepare(drvdata->pclk); return 0; } @@ -179,11 +215,17 @@ static int tpiu_runtime_suspend(struct device *dev) static int tpiu_runtime_resume(struct device *dev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(dev); + int ret; - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); + ret = clk_prepare_enable(drvdata->pclk); + if (ret) + return ret; - return 0; + ret = clk_prepare_enable(drvdata->atclk); + if (ret) + clk_disable_unprepare(drvdata->pclk); + + return ret; } #endif @@ -205,17 +247,82 @@ static const struct amba_id tpiu_ids[] = { .id = 0x000bb9e7, .mask = 0x000fffff, }, - { 0, 0}, + { 0, 0, NULL }, }; +MODULE_DEVICE_TABLE(amba, tpiu_ids); + static struct amba_driver tpiu_driver = { .drv = { .name = "coresight-tpiu", - .owner = THIS_MODULE, .pm = &tpiu_dev_pm_ops, .suppress_bind_attrs = true, }, .probe = tpiu_probe, + .remove = tpiu_remove, .id_table = tpiu_ids, }; -builtin_amba_driver(tpiu_driver); + +static int tpiu_platform_probe(struct platform_device *pdev) +{ + struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = __tpiu_probe(&pdev->dev, res); + pm_runtime_put(&pdev->dev); + if (ret) + pm_runtime_disable(&pdev->dev); + + return ret; +} + +static void tpiu_platform_remove(struct platform_device *pdev) +{ + struct tpiu_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (WARN_ON(!drvdata)) + return; + + __tpiu_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); +} + +#ifdef CONFIG_ACPI +static const struct acpi_device_id tpiu_acpi_ids[] = { + {"ARMHC979", 0, 0, 0}, /* ARM CoreSight TPIU */ + {} +}; +MODULE_DEVICE_TABLE(acpi, tpiu_acpi_ids); +#endif + +static struct platform_driver tpiu_platform_driver = { + .probe = tpiu_platform_probe, + .remove = tpiu_platform_remove, + .driver = { + .name = "coresight-tpiu-platform", + .acpi_match_table = ACPI_PTR(tpiu_acpi_ids), + .suppress_bind_attrs = true, + .pm = &tpiu_dev_pm_ops, + }, +}; + +static int __init tpiu_init(void) +{ + return coresight_init_driver("tpiu", &tpiu_driver, &tpiu_platform_driver, THIS_MODULE); +} + +static void __exit tpiu_exit(void) +{ + coresight_remove_driver(&tpiu_driver, &tpiu_platform_driver); +} +module_init(tpiu_init); +module_exit(tpiu_exit); + +MODULE_AUTHOR("Pratik Patel <pratikp@codeaurora.org>"); +MODULE_AUTHOR("Mathieu Poirier <mathieu.poirier@linaro.org>"); +MODULE_DESCRIPTION("Arm CoreSight TPIU (Trace Port Interface Unit) driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c new file mode 100644 index 000000000000..7ed337d54d3e --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -0,0 +1,300 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022, Linaro Limited, All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ +#include <linux/coresight.h> +#include <linux/coresight-pmu.h> +#include <linux/cpumask.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "coresight-trace-id.h" + +enum trace_id_flags { + TRACE_ID_ANY = 0x0, + TRACE_ID_PREFER_ODD = 0x1, + TRACE_ID_REQ_STATIC = 0x2, +}; + +/* Default trace ID map. Used in sysfs mode and for system sources */ +static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); +static struct coresight_trace_id_map id_map_default = { + .cpu_map = &id_map_default_cpu_ids, + .lock = __RAW_SPIN_LOCK_UNLOCKED(id_map_default.lock) +}; + +/* #define TRACE_ID_DEBUG 1 */ +#if defined(TRACE_ID_DEBUG) || defined(CONFIG_COMPILE_TEST) + +static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, + const char *func_name) +{ + pr_debug("%s id_map::\n", func_name); + pr_debug("Used = %*pb\n", CORESIGHT_TRACE_IDS_MAX, id_map->used_ids); +} +#define DUMP_ID_MAP(map) coresight_trace_id_dump_table(map, __func__) +#define DUMP_ID_CPU(cpu, id) pr_debug("%s called; cpu=%d, id=%d\n", __func__, cpu, id) +#define DUMP_ID(id) pr_debug("%s called; id=%d\n", __func__, id) +#define PERF_SESSION(n) pr_debug("%s perf count %d\n", __func__, n) +#else +#define DUMP_ID_MAP(map) +#define DUMP_ID(id) +#define DUMP_ID_CPU(cpu, id) +#define PERF_SESSION(n) +#endif + +/* unlocked read of current trace ID value for given CPU */ +static int _coresight_trace_id_read_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + return atomic_read(per_cpu_ptr(id_map->cpu_map, cpu)); +} + +/* look for next available odd ID, return 0 if none found */ +static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map) +{ + int found_id = 0, bit = 1, next_id; + + while ((bit < CORESIGHT_TRACE_ID_RES_TOP) && !found_id) { + /* + * bitmap length of CORESIGHT_TRACE_ID_RES_TOP, + * search from offset `bit`. + */ + next_id = find_next_zero_bit(id_map->used_ids, + CORESIGHT_TRACE_ID_RES_TOP, bit); + if ((next_id < CORESIGHT_TRACE_ID_RES_TOP) && (next_id & 0x1)) + found_id = next_id; + else + bit = next_id + 1; + } + return found_id; +} + +/* + * Allocate new ID and set in use + * + * if @preferred_id is a valid id then try to use that value if available. + * if @preferred_id is not valid and @prefer_odd_id is true, try for odd id. + * + * Otherwise allocate next available ID. + */ +static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map, + int preferred_id, unsigned int flags) +{ + int id = 0; + + /* for backwards compatibility, cpu IDs may use preferred value */ + if (IS_VALID_CS_TRACE_ID(preferred_id)) { + if (!test_bit(preferred_id, id_map->used_ids)) { + id = preferred_id; + goto trace_id_allocated; + } else if (flags & TRACE_ID_REQ_STATIC) + return -EBUSY; + } else if (flags & TRACE_ID_PREFER_ODD) { + /* may use odd ids to avoid preferred legacy cpu IDs */ + id = coresight_trace_id_find_odd_id(id_map); + if (id) + goto trace_id_allocated; + } else if (!IS_VALID_CS_TRACE_ID(preferred_id) && + (flags & TRACE_ID_REQ_STATIC)) + return -EINVAL; + + /* + * skip reserved bit 0, look at bitmap length of + * CORESIGHT_TRACE_ID_RES_TOP from offset of bit 1. + */ + id = find_next_zero_bit(id_map->used_ids, CORESIGHT_TRACE_ID_RES_TOP, 1); + if (id >= CORESIGHT_TRACE_ID_RES_TOP) + return -EINVAL; + + /* mark as used */ +trace_id_allocated: + set_bit(id, id_map->used_ids); + return id; +} + +static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + if (WARN(!test_bit(id, id_map->used_ids), "Freeing unused ID %d\n", id)) + return; + clear_bit(id, id_map->used_ids); +} + +/* + * Release all IDs and clear CPU associations. + */ +static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int cpu; + + raw_spin_lock_irqsave(&id_map->lock, flags); + bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); + for_each_possible_cpu(cpu) + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); + raw_spin_unlock_irqrestore(&id_map->lock, flags); + DUMP_ID_MAP(id_map); +} + +static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + raw_spin_lock_irqsave(&id_map->lock, flags); + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu, id_map); + if (id) + goto get_cpu_id_out_unlock; + + /* + * Find a new ID. + * + * Use legacy values where possible in the dynamic trace ID allocator to + * allow older tools to continue working if they are not upgraded at the + * same time as the kernel drivers. + * + * If the generated legacy ID is invalid, or not available then the next + * available dynamic ID will be used. + */ + id = coresight_trace_id_alloc_new_id(id_map, + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu), + TRACE_ID_ANY); + if (!IS_VALID_CS_TRACE_ID(id)) + goto get_cpu_id_out_unlock; + + /* allocate the new id to the cpu */ + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); + +get_cpu_id_out_unlock: + raw_spin_unlock_irqrestore(&id_map->lock, flags); + + DUMP_ID_CPU(cpu, id); + DUMP_ID_MAP(id_map); + return id; +} + +static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu, id_map); + if (!id) + return; + + raw_spin_lock_irqsave(&id_map->lock, flags); + + coresight_trace_id_free(id, id_map); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); + + raw_spin_unlock_irqrestore(&id_map->lock, flags); + DUMP_ID_CPU(cpu, id); + DUMP_ID_MAP(id_map); +} + +static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map, + int preferred_id, unsigned int traceid_flags) +{ + unsigned long flags; + int id; + + raw_spin_lock_irqsave(&id_map->lock, flags); + id = coresight_trace_id_alloc_new_id(id_map, preferred_id, traceid_flags); + raw_spin_unlock_irqrestore(&id_map->lock, flags); + + DUMP_ID(id); + DUMP_ID_MAP(id_map); + return id; +} + +static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map *id_map, int id) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&id_map->lock, flags); + coresight_trace_id_free(id, id_map); + raw_spin_unlock_irqrestore(&id_map->lock, flags); + + DUMP_ID(id); + DUMP_ID_MAP(id_map); +} + +/* API functions */ + +int coresight_trace_id_get_cpu_id(int cpu) +{ + return _coresight_trace_id_get_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id); + +int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + return _coresight_trace_id_get_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id_map); + +void coresight_trace_id_put_cpu_id(int cpu) +{ + _coresight_trace_id_put_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id); + +void coresight_trace_id_put_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + _coresight_trace_id_put_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id_map); + +int coresight_trace_id_read_cpu_id(int cpu) +{ + return _coresight_trace_id_read_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id); + +int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + return _coresight_trace_id_read_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id_map); + +int coresight_trace_id_get_system_id(void) +{ + /* prefer odd IDs for system components to avoid legacy CPU IDS */ + return coresight_trace_id_map_get_system_id(&id_map_default, 0, + TRACE_ID_PREFER_ODD); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id); + +int coresight_trace_id_get_static_system_id(int trace_id) +{ + return coresight_trace_id_map_get_system_id(&id_map_default, + trace_id, TRACE_ID_REQ_STATIC); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_static_system_id); + +void coresight_trace_id_put_system_id(int id) +{ + coresight_trace_id_map_put_system_id(&id_map_default, id); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); + +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map) +{ + atomic_inc(&id_map->perf_cs_etm_session_active); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); + +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map) +{ + if (!atomic_dec_return(&id_map->perf_cs_etm_session_active)) + coresight_trace_id_release_all(id_map); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h new file mode 100644 index 000000000000..db68e1ec56b6 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2022 Linaro Limited. All rights reserved. + * Author: Mike Leach <mike.leach@linaro.org> + */ + +#ifndef _CORESIGHT_TRACE_ID_H +#define _CORESIGHT_TRACE_ID_H + +/* + * Coresight trace ID allocation API + * + * With multi cpu systems, and more additional trace sources a scalable + * trace ID reservation system is required. + * + * The system will allocate Ids on a demand basis, and allow them to be + * released when done. + * + * In order to ensure that a consistent cpu / ID matching is maintained + * throughout a perf cs_etm event session - a session in progress flag will be + * maintained for each sink, and IDs are cleared when all the perf sessions + * complete. This allows the same CPU to be re-allocated its prior ID when + * events are scheduled in and out. + * + * + * Trace ID maps will be created and initialised to prevent architecturally + * reserved IDs from being allocated. + * + * API permits multiple maps to be maintained - for large systems where + * different sets of cpus trace into different independent sinks. + */ + +#include <linux/bitops.h> +#include <linux/types.h> + +/* ID 0 is reserved */ +#define CORESIGHT_TRACE_ID_RES_0 0 + +/* ID 0x70 onwards are reserved */ +#define CORESIGHT_TRACE_ID_RES_TOP 0x70 + +/* check an ID is in the valid range */ +#define IS_VALID_CS_TRACE_ID(id) \ + ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) + +/** + * Read and optionally allocate a CoreSight trace ID and associate with a CPU. + * + * Function will read the current trace ID for the associated CPU, + * allocating an new ID if one is not currently allocated. + * + * Numeric ID values allocated use legacy allocation algorithm if possible, + * otherwise any available ID is used. + * + * @cpu: The CPU index to allocate for. + * + * return: CoreSight trace ID or -EINVAL if allocation impossible. + */ +int coresight_trace_id_get_cpu_id(int cpu); + +/** + * Version of coresight_trace_id_get_cpu_id() that allows the ID map to operate + * on to be provided. + */ +int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + +/** + * Release an allocated trace ID associated with the CPU. + * + * This will release the CoreSight trace ID associated with the CPU. + * + * @cpu: The CPU index to release the associated trace ID. + */ +void coresight_trace_id_put_cpu_id(int cpu); + +/** + * Version of coresight_trace_id_put_cpu_id() that allows the ID map to operate + * on to be provided. + */ +void coresight_trace_id_put_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + +/** + * Read the current allocated CoreSight Trace ID value for the CPU. + * + * Fast read of the current value that does not allocate if no ID allocated + * for the CPU. + * + * Used in perf context where it is known that the value for the CPU will not + * be changing, when perf starts and event on a core and outputs the Trace ID + * for the CPU as a packet in the data file. IDs cannot change during a perf + * session. + * + * This function does not take the lock protecting the ID lists, avoiding + * locking dependency issues with perf locks. + * + * @cpu: The CPU index to read. + * + * return: current value, will be 0 if unallocated. + */ +int coresight_trace_id_read_cpu_id(int cpu); + +/** + * Version of coresight_trace_id_read_cpu_id() that allows the ID map to operate + * on to be provided. + */ +int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + +/** + * Allocate a CoreSight trace ID for a system component. + * + * Unconditionally allocates a Trace ID, without associating the ID with a CPU. + * + * Used to allocate IDs for system trace sources such as STM. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_system_id(void); + +/** + * Allocate a CoreSight static trace ID for a system component. + * + * Used to allocate static IDs for system trace sources such as dummy source. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_static_system_id(int id); + +/** + * Release an allocated system trace ID. + * + * Unconditionally release a trace ID allocated to a system component. + * + * @id: value of trace ID allocated. + */ +void coresight_trace_id_put_system_id(int id); + +/* notifiers for perf session start and stop */ + +/** + * Notify the Trace ID allocator that a perf session is starting. + * + * Increase the perf session reference count - called by perf when setting up a + * trace event. + * + * Perf sessions never free trace IDs to ensure that the ID associated with a + * CPU cannot change during their and other's concurrent sessions. Instead, + * this refcount is used so that the last event to finish always frees all IDs. + */ +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map); + +/** + * Notify the ID allocator that a perf session is stopping. + * + * Decrease the perf session reference count. If this causes the count to go to + * zero, then all Trace IDs will be released. + */ +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map); + +#endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/drivers/hwtracing/coresight/coresight-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c new file mode 100644 index 000000000000..474861903f6c --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -0,0 +1,1605 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This driver enables Trace Buffer Extension (TRBE) as a per-cpu coresight + * sink device could then pair with an appropriate per-cpu coresight source + * device (ETE) thus generating required trace data. Trace can be enabled + * via the perf framework. + * + * The AUX buffer handling is inspired from Arm SPE PMU driver. + * + * Copyright (C) 2020 ARM Ltd. + * + * Author: Anshuman Khandual <anshuman.khandual@arm.com> + */ +#define DRVNAME "arm_trbe" + +#define pr_fmt(fmt) DRVNAME ": " fmt + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <linux/kvm_host.h> +#include <linux/vmalloc.h> + +#include "coresight-self-hosted-trace.h" +#include "coresight-trbe.h" + +#define PERF_IDX2OFF(idx, buf) \ + ((idx) % ((unsigned long)(buf)->nr_pages << PAGE_SHIFT)) + +/* + * A padding packet that will help the user space tools + * in skipping relevant sections in the captured trace + * data which could not be decoded. TRBE doesn't support + * formatting the trace data, unlike the legacy CoreSight + * sinks and thus we use ETE trace packets to pad the + * sections of the buffer. + */ +#define ETE_IGNORE_PACKET 0x70 + +/* + * Minimum amount of meaningful trace will contain: + * A-Sync, Trace Info, Trace On, Address, Atom. + * This is about 44bytes of ETE trace. To be on + * the safer side, we assume 64bytes is the minimum + * space required for a meaningful session, before + * we hit a "WRAP" event. + */ +#define TRBE_TRACE_MIN_BUF_SIZE 64 + +enum trbe_fault_action { + TRBE_FAULT_ACT_WRAP, + TRBE_FAULT_ACT_SPURIOUS, + TRBE_FAULT_ACT_FATAL, +}; + +struct trbe_buf { + /* + * Even though trbe_base represents vmap() + * mapped allocated buffer's start address, + * it's being as unsigned long for various + * arithmetic and comparision operations & + * also to be consistent with trbe_write & + * trbe_limit sibling pointers. + */ + unsigned long trbe_base; + /* The base programmed into the TRBE */ + unsigned long trbe_hw_base; + unsigned long trbe_limit; + unsigned long trbe_write; + int nr_pages; + void **pages; + bool snapshot; + struct trbe_cpudata *cpudata; +}; + +/* + * TRBE erratum list + * + * The errata are defined in arm64 generic cpu_errata framework. + * Since the errata work arounds could be applied individually + * to the affected CPUs inside the TRBE driver, we need to know if + * a given CPU is affected by the erratum. Unlike the other erratum + * work arounds, TRBE driver needs to check multiple times during + * a trace session. Thus we need a quicker access to per-CPU + * errata and not issue costly this_cpu_has_cap() everytime. + * We keep a set of the affected errata in trbe_cpudata, per TRBE. + * + * We rely on the corresponding cpucaps to be defined for a given + * TRBE erratum. We map the given cpucap into a TRBE internal number + * to make the tracking of the errata lean. + * + * This helps in : + * - Not duplicating the detection logic + * - Streamlined detection of erratum across the system + */ +#define TRBE_WORKAROUND_OVERWRITE_FILL_MODE 0 +#define TRBE_WORKAROUND_WRITE_OUT_OF_RANGE 1 +#define TRBE_NEEDS_DRAIN_AFTER_DISABLE 2 +#define TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE 3 +#define TRBE_IS_BROKEN 4 + +static int trbe_errata_cpucaps[] = { + [TRBE_WORKAROUND_OVERWRITE_FILL_MODE] = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE, + [TRBE_WORKAROUND_WRITE_OUT_OF_RANGE] = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE, + [TRBE_NEEDS_DRAIN_AFTER_DISABLE] = ARM64_WORKAROUND_2064142, + [TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE] = ARM64_WORKAROUND_2038923, + [TRBE_IS_BROKEN] = ARM64_WORKAROUND_1902691, + -1, /* Sentinel, must be the last entry */ +}; + +/* The total number of listed errata in trbe_errata_cpucaps */ +#define TRBE_ERRATA_MAX (ARRAY_SIZE(trbe_errata_cpucaps) - 1) + +/* + * Safe limit for the number of bytes that may be overwritten + * when ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE is triggered. + */ +#define TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES 256 + +/* + * struct trbe_cpudata: TRBE instance specific data + * @trbe_flag - TRBE dirty/access flag support + * @trbe_hw_align - Actual TRBE alignment required for TRBPTR_EL1. + * @trbe_align - Software alignment used for the TRBPTR_EL1. + * @cpu - CPU this TRBE belongs to. + * @mode - Mode of current operation. (perf/disabled) + * @drvdata - TRBE specific drvdata + * @errata - Bit map for the errata on this TRBE. + */ +struct trbe_cpudata { + bool trbe_flag; + u64 trbe_hw_align; + u64 trbe_align; + int cpu; + enum cs_mode mode; + struct trbe_buf *buf; + struct trbe_drvdata *drvdata; + DECLARE_BITMAP(errata, TRBE_ERRATA_MAX); +}; + +struct trbe_drvdata { + struct trbe_cpudata __percpu *cpudata; + struct perf_output_handle * __percpu *handle; + struct hlist_node hotplug_node; + int irq; + cpumask_t supported_cpus; + enum cpuhp_state trbe_online; + struct platform_device *pdev; +}; + +static void trbe_check_errata(struct trbe_cpudata *cpudata) +{ + int i; + + for (i = 0; i < TRBE_ERRATA_MAX; i++) { + int cap = trbe_errata_cpucaps[i]; + + if (WARN_ON_ONCE(cap < 0)) + return; + if (this_cpu_has_cap(cap)) + set_bit(i, cpudata->errata); + } +} + +static bool trbe_has_erratum(struct trbe_cpudata *cpudata, int i) +{ + return (i < TRBE_ERRATA_MAX) && test_bit(i, cpudata->errata); +} + +static bool trbe_may_overwrite_in_fill_mode(struct trbe_cpudata *cpudata) +{ + return trbe_has_erratum(cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE); +} + +static bool trbe_may_write_out_of_range(struct trbe_cpudata *cpudata) +{ + return trbe_has_erratum(cpudata, TRBE_WORKAROUND_WRITE_OUT_OF_RANGE); +} + +static bool trbe_needs_drain_after_disable(struct trbe_cpudata *cpudata) +{ + /* + * Errata affected TRBE implementation will need TSB CSYNC and + * DSB in order to prevent subsequent writes into certain TRBE + * system registers from being ignored and not effected. + */ + return trbe_has_erratum(cpudata, TRBE_NEEDS_DRAIN_AFTER_DISABLE); +} + +static bool trbe_needs_ctxt_sync_after_enable(struct trbe_cpudata *cpudata) +{ + /* + * Errata affected TRBE implementation will need an additional + * context synchronization in order to prevent an inconsistent + * TRBE prohibited region view on the CPU which could possibly + * corrupt the TRBE buffer or the TRBE state. + */ + return trbe_has_erratum(cpudata, TRBE_NEEDS_CTXT_SYNC_AFTER_ENABLE); +} + +static bool trbe_is_broken(struct trbe_cpudata *cpudata) +{ + return trbe_has_erratum(cpudata, TRBE_IS_BROKEN); +} + +static int trbe_alloc_node(struct perf_event *event) +{ + if (event->cpu == -1) + return NUMA_NO_NODE; + return cpu_to_node(event->cpu); +} + +static void trbe_drain_buffer(void) +{ + tsb_csync(); + dsb(nsh); +} + +static void set_trbe_enabled(struct trbe_cpudata *cpudata, u64 trblimitr) +{ + /* + * Enable the TRBE without clearing LIMITPTR which + * might be required for fetching the buffer limits. + */ + trblimitr |= TRBLIMITR_EL1_E; + write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_enable_trbe(); + + /* Synchronize the TRBE enable event */ + isb(); + + if (trbe_needs_ctxt_sync_after_enable(cpudata)) + isb(); +} + +static void set_trbe_disabled(struct trbe_cpudata *cpudata) +{ + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + + /* + * Disable the TRBE without clearing LIMITPTR which + * might be required for fetching the buffer limits. + */ + trblimitr &= ~TRBLIMITR_EL1_E; + write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + kvm_disable_trbe(); + + if (trbe_needs_drain_after_disable(cpudata)) + trbe_drain_buffer(); + isb(); +} + +static void trbe_drain_and_disable_local(struct trbe_cpudata *cpudata) +{ + trbe_drain_buffer(); + set_trbe_disabled(cpudata); +} + +static void trbe_reset_local(struct trbe_cpudata *cpudata) +{ + write_sysreg_s(0, SYS_TRBLIMITR_EL1); + isb(); + trbe_drain_buffer(); + write_sysreg_s(0, SYS_TRBPTR_EL1); + write_sysreg_s(0, SYS_TRBBASER_EL1); + write_sysreg_s(0, SYS_TRBSR_EL1); +} + +static void trbe_report_wrap_event(struct perf_output_handle *handle) +{ + /* + * Mark the buffer to indicate that there was a WRAP event by + * setting the COLLISION flag. This indicates to the user that + * the TRBE trace collection was stopped without stopping the + * ETE and thus there might be some amount of trace that was + * lost between the time the WRAP was detected and the IRQ + * was consumed by the CPU. + * + * Setting the TRUNCATED flag would move the event to STOPPED + * state unnecessarily, even when there is space left in the + * ring buffer. Using the COLLISION flag doesn't have this side + * effect. We only set TRUNCATED flag when there is no space + * left in the ring buffer. + */ + perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION); +} + +static void trbe_stop_and_truncate_event(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + + /* + * We cannot proceed with the buffer collection and we + * do not have any data for the current session. The + * etm_perf driver expects to close out the aux_buffer + * at event_stop(). So disable the TRBE here and leave + * the update_buffer() to return a 0 size. + */ + trbe_drain_and_disable_local(buf->cpudata); + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); + perf_aux_output_end(handle, 0); + *this_cpu_ptr(buf->cpudata->drvdata->handle) = NULL; +} + +/* + * TRBE Buffer Management + * + * The TRBE buffer spans from the base pointer till the limit pointer. When enabled, + * it starts writing trace data from the write pointer onward till the limit pointer. + * When the write pointer reaches the address just before the limit pointer, it gets + * wrapped around again to the base pointer. This is called a TRBE wrap event, which + * generates a maintenance interrupt when operated in WRAP or FILL mode. This driver + * uses FILL mode, where the TRBE stops the trace collection at wrap event. The IRQ + * handler updates the AUX buffer and re-enables the TRBE with updated WRITE and + * LIMIT pointers. + * + * Wrap around with an IRQ + * ------ < ------ < ------- < ----- < ----- + * | | + * ------ > ------ > ------- > ----- > ----- + * + * +---------------+-----------------------+ + * | | | + * +---------------+-----------------------+ + * Base Pointer Write Pointer Limit Pointer + * + * The base and limit pointers always needs to be PAGE_SIZE aligned. But the write + * pointer can be aligned to the implementation defined TRBE trace buffer alignment + * as captured in trbe_cpudata->trbe_align. + * + * + * head tail wakeup + * +---------------------------------------+----- ~ ~ ------ + * |$$$$$$$|################|$$$$$$$$$$$$$$| | + * +---------------------------------------+----- ~ ~ ------ + * Base Pointer Write Pointer Limit Pointer + * + * The perf_output_handle indices (head, tail, wakeup) are monotonically increasing + * values which tracks all the driver writes and user reads from the perf auxiliary + * buffer. Generally [head..tail] is the area where the driver can write into unless + * the wakeup is behind the tail. Enabled TRBE buffer span needs to be adjusted and + * configured depending on the perf_output_handle indices, so that the driver does + * not override into areas in the perf auxiliary buffer which is being or yet to be + * consumed from the user space. The enabled TRBE buffer area is a moving subset of + * the allocated perf auxiliary buffer. + */ + +static void __trbe_pad_buf(struct trbe_buf *buf, u64 offset, int len) +{ + memset((void *)buf->trbe_base + offset, ETE_IGNORE_PACKET, len); +} + +static void trbe_pad_buf(struct perf_output_handle *handle, int len) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + u64 head = PERF_IDX2OFF(handle->head, buf); + + __trbe_pad_buf(buf, head, len); + if (!buf->snapshot) + perf_aux_output_skip(handle, len); +} + +static unsigned long trbe_snapshot_offset(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + + /* + * The ETE trace has alignment synchronization packets allowing + * the decoder to reset in case of an overflow or corruption. + * So we can use the entire buffer for the snapshot mode. + */ + return buf->nr_pages * PAGE_SIZE; +} + +static u64 trbe_min_trace_buf_size(struct perf_output_handle *handle) +{ + u64 size = TRBE_TRACE_MIN_BUF_SIZE; + struct trbe_buf *buf = etm_perf_sink_config(handle); + struct trbe_cpudata *cpudata = buf->cpudata; + + /* + * When the TRBE is affected by an erratum that could make it + * write to the next "virtually addressed" page beyond the LIMIT. + * We need to make sure there is always a PAGE after the LIMIT, + * within the buffer. Thus we ensure there is at least an extra + * page than normal. With this we could then adjust the LIMIT + * pointer down by a PAGE later. + */ + if (trbe_may_write_out_of_range(cpudata)) + size += PAGE_SIZE; + return size; +} + +/* + * TRBE Limit Calculation + * + * The following markers are used to illustrate various TRBE buffer situations. + * + * $$$$ - Data area, unconsumed captured trace data, not to be overridden + * #### - Free area, enabled, trace will be written + * %%%% - Free area, disabled, trace will not be written + * ==== - Free area, padded with ETE_IGNORE_PACKET, trace will be skipped + */ +static unsigned long __trbe_normal_offset(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + struct trbe_cpudata *cpudata = buf->cpudata; + const u64 bufsize = buf->nr_pages * PAGE_SIZE; + u64 limit = bufsize; + u64 head, tail, wakeup; + + head = PERF_IDX2OFF(handle->head, buf); + + /* + * head + * ------->| + * | + * head TRBE align tail + * +----|-------|---------------|-------+ + * |$$$$|=======|###############|$$$$$$$| + * +----|-------|---------------|-------+ + * trbe_base trbe_base + nr_pages + * + * Perf aux buffer output head position can be misaligned depending on + * various factors including user space reads. In case misaligned, head + * needs to be aligned before TRBE can be configured. Pad the alignment + * gap with ETE_IGNORE_PACKET bytes that will be ignored by user tools + * and skip this section thus advancing the head. + */ + if (!IS_ALIGNED(head, cpudata->trbe_align)) { + unsigned long delta = roundup(head, cpudata->trbe_align) - head; + + delta = min(delta, handle->size); + trbe_pad_buf(handle, delta); + head = PERF_IDX2OFF(handle->head, buf); + } + + /* + * head = tail (size = 0) + * +----|-------------------------------+ + * |$$$$|$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ | + * +----|-------------------------------+ + * trbe_base trbe_base + nr_pages + * + * Perf aux buffer does not have any space for the driver to write into. + */ + if (!handle->size) + return 0; + + /* Compute the tail and wakeup indices now that we've aligned head */ + tail = PERF_IDX2OFF(handle->head + handle->size, buf); + wakeup = PERF_IDX2OFF(handle->wakeup, buf); + + /* + * Lets calculate the buffer area which TRBE could write into. There + * are three possible scenarios here. Limit needs to be aligned with + * PAGE_SIZE per the TRBE requirement. Always avoid clobbering the + * unconsumed data. + * + * 1) head < tail + * + * head tail + * +----|-----------------------|-------+ + * |$$$$|#######################|$$$$$$$| + * +----|-----------------------|-------+ + * trbe_base limit trbe_base + nr_pages + * + * TRBE could write into [head..tail] area. Unless the tail is right at + * the end of the buffer, neither an wrap around nor an IRQ is expected + * while being enabled. + * + * 2) head == tail + * + * head = tail (size > 0) + * +----|-------------------------------+ + * |%%%%|###############################| + * +----|-------------------------------+ + * trbe_base limit = trbe_base + nr_pages + * + * TRBE should just write into [head..base + nr_pages] area even though + * the entire buffer is empty. Reason being, when the trace reaches the + * end of the buffer, it will just wrap around with an IRQ giving an + * opportunity to reconfigure the buffer. + * + * 3) tail < head + * + * tail head + * +----|-----------------------|-------+ + * |%%%%|$$$$$$$$$$$$$$$$$$$$$$$|#######| + * +----|-----------------------|-------+ + * trbe_base limit = trbe_base + nr_pages + * + * TRBE should just write into [head..base + nr_pages] area even though + * the [trbe_base..tail] is also empty. Reason being, when the trace + * reaches the end of the buffer, it will just wrap around with an IRQ + * giving an opportunity to reconfigure the buffer. + */ + if (head < tail) + limit = round_down(tail, PAGE_SIZE); + + /* + * Wakeup may be arbitrarily far into the future. If it's not in the + * current generation, either we'll wrap before hitting it, or it's + * in the past and has been handled already. + * + * If there's a wakeup before we wrap, arrange to be woken up by the + * page boundary following it. Keep the tail boundary if that's lower. + * + * head wakeup tail + * +----|---------------|-------|-------+ + * |$$$$|###############|%%%%%%%|$$$$$$$| + * +----|---------------|-------|-------+ + * trbe_base limit trbe_base + nr_pages + */ + if (handle->wakeup < (handle->head + handle->size) && head <= wakeup) + limit = min(limit, round_up(wakeup, PAGE_SIZE)); + + /* + * There are two situation when this can happen i.e limit is before + * the head and hence TRBE cannot be configured. + * + * 1) head < tail (aligned down with PAGE_SIZE) and also they are both + * within the same PAGE size range. + * + * PAGE_SIZE + * |----------------------| + * + * limit head tail + * +------------|------|--------|-------+ + * |$$$$$$$$$$$$$$$$$$$|========|$$$$$$$| + * +------------|------|--------|-------+ + * trbe_base trbe_base + nr_pages + * + * 2) head < wakeup (aligned up with PAGE_SIZE) < tail and also both + * head and wakeup are within same PAGE size range. + * + * PAGE_SIZE + * |----------------------| + * + * limit head wakeup tail + * +----|------|-------|--------|-------+ + * |$$$$$$$$$$$|=======|========|$$$$$$$| + * +----|------|-------|--------|-------+ + * trbe_base trbe_base + nr_pages + */ + if (limit > head) + return limit; + + trbe_pad_buf(handle, handle->size); + return 0; +} + +static unsigned long trbe_normal_offset(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + u64 limit = __trbe_normal_offset(handle); + u64 head = PERF_IDX2OFF(handle->head, buf); + + /* + * If the head is too close to the limit and we don't + * have space for a meaningful run, we rather pad it + * and start fresh. + * + * We might have to do this more than once to make sure + * we have enough required space. + */ + while (limit && ((limit - head) < trbe_min_trace_buf_size(handle))) { + trbe_pad_buf(handle, limit - head); + limit = __trbe_normal_offset(handle); + head = PERF_IDX2OFF(handle->head, buf); + } + return limit; +} + +static unsigned long compute_trbe_buffer_limit(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + unsigned long offset; + + if (buf->snapshot) + offset = trbe_snapshot_offset(handle); + else + offset = trbe_normal_offset(handle); + return buf->trbe_base + offset; +} + +static void clr_trbe_status(void) +{ + u64 trbsr = read_sysreg_s(SYS_TRBSR_EL1); + + WARN_ON(is_trbe_enabled()); + trbsr &= ~TRBSR_EL1_IRQ; + trbsr &= ~TRBSR_EL1_TRG; + trbsr &= ~TRBSR_EL1_WRAP; + trbsr &= ~TRBSR_EL1_EC_MASK; + trbsr &= ~TRBSR_EL1_BSC_MASK; + trbsr &= ~TRBSR_EL1_S; + write_sysreg_s(trbsr, SYS_TRBSR_EL1); +} + +static void set_trbe_limit_pointer_enabled(struct trbe_buf *buf) +{ + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + unsigned long addr = buf->trbe_limit; + + WARN_ON(!IS_ALIGNED(addr, (1UL << TRBLIMITR_EL1_LIMIT_SHIFT))); + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + + trblimitr &= ~TRBLIMITR_EL1_nVM; + trblimitr &= ~TRBLIMITR_EL1_FM_MASK; + trblimitr &= ~TRBLIMITR_EL1_TM_MASK; + trblimitr &= ~TRBLIMITR_EL1_LIMIT_MASK; + + /* + * Fill trace buffer mode is used here while configuring the + * TRBE for trace capture. In this particular mode, the trace + * collection is stopped and a maintenance interrupt is raised + * when the current write pointer wraps. This pause in trace + * collection gives the software an opportunity to capture the + * trace data in the interrupt handler, before reconfiguring + * the TRBE. + */ + trblimitr |= (TRBLIMITR_EL1_FM_FILL << TRBLIMITR_EL1_FM_SHIFT) & + TRBLIMITR_EL1_FM_MASK; + + /* + * Trigger mode is not used here while configuring the TRBE for + * the trace capture. Hence just keep this in the ignore mode. + */ + trblimitr |= (TRBLIMITR_EL1_TM_IGNR << TRBLIMITR_EL1_TM_SHIFT) & + TRBLIMITR_EL1_TM_MASK; + trblimitr |= (addr & PAGE_MASK); + set_trbe_enabled(buf->cpudata, trblimitr); +} + +static void trbe_enable_hw(struct trbe_buf *buf) +{ + WARN_ON(buf->trbe_hw_base < buf->trbe_base); + WARN_ON(buf->trbe_write < buf->trbe_hw_base); + WARN_ON(buf->trbe_write >= buf->trbe_limit); + set_trbe_disabled(buf->cpudata); + clr_trbe_status(); + set_trbe_base_pointer(buf->trbe_hw_base); + set_trbe_write_pointer(buf->trbe_write); + + /* + * Synchronize all the register updates + * till now before enabling the TRBE. + */ + isb(); + set_trbe_limit_pointer_enabled(buf); +} + +static enum trbe_fault_action trbe_get_fault_act(struct perf_output_handle *handle, + u64 trbsr) +{ + int ec = get_trbe_ec(trbsr); + int bsc = get_trbe_bsc(trbsr); + struct trbe_buf *buf = etm_perf_sink_config(handle); + struct trbe_cpudata *cpudata = buf->cpudata; + + WARN_ON(is_trbe_running(trbsr)); + if (is_trbe_trg(trbsr) || is_trbe_abort(trbsr)) + return TRBE_FAULT_ACT_FATAL; + + if ((ec == TRBE_EC_STAGE1_ABORT) || (ec == TRBE_EC_STAGE2_ABORT)) + return TRBE_FAULT_ACT_FATAL; + + /* + * If the trbe is affected by TRBE_WORKAROUND_OVERWRITE_FILL_MODE, + * it might write data after a WRAP event in the fill mode. + * Thus the check TRBPTR == TRBBASER will not be honored. + */ + if ((is_trbe_wrap(trbsr) && (ec == TRBE_EC_OTHERS) && (bsc == TRBE_BSC_FILLED)) && + (trbe_may_overwrite_in_fill_mode(cpudata) || + get_trbe_write_pointer() == get_trbe_base_pointer())) + return TRBE_FAULT_ACT_WRAP; + + return TRBE_FAULT_ACT_SPURIOUS; +} + +static unsigned long trbe_get_trace_size(struct perf_output_handle *handle, + struct trbe_buf *buf, bool wrap) +{ + u64 write; + u64 start_off, end_off; + u64 size; + u64 overwrite_skip = TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES; + + /* + * If the TRBE has wrapped around the write pointer has + * wrapped and should be treated as limit. + * + * When the TRBE is affected by TRBE_WORKAROUND_WRITE_OUT_OF_RANGE, + * it may write upto 64bytes beyond the "LIMIT". The driver already + * keeps a valid page next to the LIMIT and we could potentially + * consume the trace data that may have been collected there. But we + * cannot be really sure it is available, and the TRBPTR may not + * indicate the same. Also, affected cores are also affected by another + * erratum which forces the PAGE_SIZE alignment on the TRBPTR, and thus + * could potentially pad an entire PAGE_SIZE - 64bytes, to get those + * 64bytes. Thus we ignore the potential triggering of the erratum + * on WRAP and limit the data to LIMIT. + */ + if (wrap) + write = get_trbe_limit_pointer(); + else + write = get_trbe_write_pointer(); + + /* + * TRBE may use a different base address than the base + * of the ring buffer. Thus use the beginning of the ring + * buffer to compute the offsets. + */ + end_off = write - buf->trbe_base; + start_off = PERF_IDX2OFF(handle->head, buf); + + if (WARN_ON_ONCE(end_off < start_off)) + return 0; + + size = end_off - start_off; + /* + * If the TRBE is affected by the following erratum, we must fill + * the space we skipped with IGNORE packets. And we are always + * guaranteed to have at least a PAGE_SIZE space in the buffer. + */ + if (trbe_has_erratum(buf->cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE) && + !WARN_ON(size < overwrite_skip)) + __trbe_pad_buf(buf, start_off, overwrite_skip); + + return size; +} + +static void *arm_trbe_alloc_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool snapshot) +{ + struct trbe_buf *buf; + struct page **pglist; + int i; + + /* + * TRBE LIMIT and TRBE WRITE pointers must be page aligned. But with + * just a single page, there would not be any room left while writing + * into a partially filled TRBE buffer after the page size alignment. + * Hence restrict the minimum buffer size as two pages. + */ + if (nr_pages < 2) + return NULL; + + buf = kzalloc_node(sizeof(*buf), GFP_KERNEL, trbe_alloc_node(event)); + if (!buf) + return NULL; + + pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL); + if (!pglist) { + kfree(buf); + return NULL; + } + + for (i = 0; i < nr_pages; i++) + pglist[i] = virt_to_page(pages[i]); + + buf->trbe_base = (unsigned long)vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL); + if (!buf->trbe_base) { + kfree(pglist); + kfree(buf); + return NULL; + } + buf->trbe_limit = buf->trbe_base + nr_pages * PAGE_SIZE; + buf->trbe_write = buf->trbe_base; + buf->snapshot = snapshot; + buf->nr_pages = nr_pages; + buf->pages = pages; + kfree(pglist); + return buf; +} + +static void arm_trbe_free_buffer(void *config) +{ + struct trbe_buf *buf = config; + + vunmap((void *)buf->trbe_base); + kfree(buf); +} + +static unsigned long arm_trbe_update_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *config) +{ + struct trbe_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct trbe_cpudata *cpudata = dev_get_drvdata(&csdev->dev); + struct trbe_buf *buf = config; + enum trbe_fault_action act; + unsigned long size, status; + unsigned long flags; + bool wrap = false; + + WARN_ON(buf->cpudata != cpudata); + WARN_ON(cpudata->cpu != smp_processor_id()); + WARN_ON(cpudata->drvdata != drvdata); + if (cpudata->mode != CS_MODE_PERF) + return 0; + + /* + * We are about to disable the TRBE. And this could in turn + * fill up the buffer triggering, an IRQ. This could be consumed + * by the PE asynchronously, causing a race here against + * the IRQ handler in closing out the handle. So, let us + * make sure the IRQ can't trigger while we are collecting + * the buffer. We also make sure that a WRAP event is handled + * accordingly. + */ + local_irq_save(flags); + + /* + * If the TRBE was disabled due to lack of space in the AUX buffer or a + * spurious fault, the driver leaves it disabled, truncating the buffer. + * Since the etm_perf driver expects to close out the AUX buffer, the + * driver skips it. Thus, just pass in 0 size here to indicate that the + * buffer was truncated. + */ + if (!is_trbe_enabled()) { + size = 0; + goto done; + } + /* + * perf handle structure needs to be shared with the TRBE IRQ handler for + * capturing trace data and restarting the handle. There is a probability + * of an undefined reference based crash when etm event is being stopped + * while a TRBE IRQ also getting processed. This happens due the release + * of perf handle via perf_aux_output_end() in etm_event_stop(). Stopping + * the TRBE here will ensure that no IRQ could be generated when the perf + * handle gets freed in etm_event_stop(). + */ + trbe_drain_and_disable_local(cpudata); + + /* Check if there is a pending interrupt and handle it here */ + status = read_sysreg_s(SYS_TRBSR_EL1); + if (is_trbe_irq(status)) { + + /* + * Now that we are handling the IRQ here, clear the IRQ + * from the status, to let the irq handler know that it + * is taken care of. + */ + clr_trbe_irq(); + isb(); + + act = trbe_get_fault_act(handle, status); + /* + * If this was not due to a WRAP event, we have some + * errors and as such buffer is empty. + */ + if (act != TRBE_FAULT_ACT_WRAP) { + size = 0; + goto done; + } + + trbe_report_wrap_event(handle); + wrap = true; + } + + size = trbe_get_trace_size(handle, buf, wrap); + +done: + local_irq_restore(flags); + + if (buf->snapshot) + handle->head += size; + return size; +} + + +static int trbe_apply_work_around_before_enable(struct trbe_buf *buf) +{ + /* + * TRBE_WORKAROUND_OVERWRITE_FILL_MODE causes the TRBE to overwrite a few cache + * line size from the "TRBBASER_EL1" in the event of a "FILL". + * Thus, we could loose some amount of the trace at the base. + * + * Before Fix: + * + * normal-BASE head (normal-TRBPTR) tail (normal-LIMIT) + * | \/ / + * ------------------------------------------------------------- + * | Pg0 | Pg1 | | | PgN | + * ------------------------------------------------------------- + * + * In the normal course of action, we would set the TRBBASER to the + * beginning of the ring-buffer (normal-BASE). But with the erratum, + * the TRBE could overwrite the contents at the "normal-BASE", after + * hitting the "normal-LIMIT", since it doesn't stop as expected. And + * this is wrong. This could result in overwriting trace collected in + * one of the previous runs, being consumed by the user. So we must + * always make sure that the TRBBASER is within the region + * [head, head+size]. Note that TRBBASER must be PAGE aligned, + * + * After moving the BASE: + * + * normal-BASE head (normal-TRBPTR) tail (normal-LIMIT) + * | \/ / + * ------------------------------------------------------------- + * | | |xyzdef. |.. tuvw| | + * ------------------------------------------------------------- + * / + * New-BASER + * + * Also, we would set the TRBPTR to head (after adjusting for + * alignment) at normal-PTR. This would mean that the last few bytes + * of the trace (say, "xyz") might overwrite the first few bytes of + * trace written ("abc"). More importantly they will appear in what + * userspace sees as the beginning of the trace, which is wrong. We may + * not always have space to move the latest trace "xyz" to the correct + * order as it must appear beyond the LIMIT. (i.e, [head..head+size]). + * Thus it is easier to ignore those bytes than to complicate the + * driver to move it, assuming that the erratum was triggered and + * doing additional checks to see if there is indeed allowed space at + * TRBLIMITR.LIMIT. + * + * Thus the full workaround will move the BASE and the PTR and would + * look like (after padding at the skipped bytes at the end of + * session) : + * + * normal-BASE head (normal-TRBPTR) tail (normal-LIMIT) + * | \/ / + * ------------------------------------------------------------- + * | | |///abc.. |.. rst| | + * ------------------------------------------------------------- + * / | + * New-BASER New-TRBPTR + * + * To summarize, with the work around: + * + * - We always align the offset for the next session to PAGE_SIZE + * (This is to ensure we can program the TRBBASER to this offset + * within the region [head...head+size]). + * + * - At TRBE enable: + * - Set the TRBBASER to the page aligned offset of the current + * proposed write offset. (which is guaranteed to be aligned + * as above) + * - Move the TRBPTR to skip first 256bytes (that might be + * overwritten with the erratum). This ensures that the trace + * generated in the session is not re-written. + * + * - At trace collection: + * - Pad the 256bytes skipped above again with IGNORE packets. + */ + if (trbe_has_erratum(buf->cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE)) { + if (WARN_ON(!IS_ALIGNED(buf->trbe_write, PAGE_SIZE))) + return -EINVAL; + buf->trbe_hw_base = buf->trbe_write; + buf->trbe_write += TRBE_WORKAROUND_OVERWRITE_FILL_MODE_SKIP_BYTES; + } + + /* + * TRBE_WORKAROUND_WRITE_OUT_OF_RANGE could cause the TRBE to write to + * the next page after the TRBLIMITR.LIMIT. For perf, the "next page" + * may be: + * - The page beyond the ring buffer. This could mean, TRBE could + * corrupt another entity (kernel / user) + * - A portion of the "ring buffer" consumed by the userspace. + * i.e, a page outisde [head, head + size]. + * + * We work around this by: + * - Making sure that we have at least an extra space of PAGE left + * in the ring buffer [head, head + size], than we normally do + * without the erratum. See trbe_min_trace_buf_size(). + * + * - Adjust the TRBLIMITR.LIMIT to leave the extra PAGE outside + * the TRBE's range (i.e [TRBBASER, TRBLIMITR.LIMI] ). + */ + if (trbe_has_erratum(buf->cpudata, TRBE_WORKAROUND_WRITE_OUT_OF_RANGE)) { + s64 space = buf->trbe_limit - buf->trbe_write; + /* + * We must have more than a PAGE_SIZE worth space in the proposed + * range for the TRBE. + */ + if (WARN_ON(space <= PAGE_SIZE || + !IS_ALIGNED(buf->trbe_limit, PAGE_SIZE))) + return -EINVAL; + buf->trbe_limit -= PAGE_SIZE; + } + + return 0; +} + +static int __arm_trbe_enable(struct trbe_buf *buf, + struct perf_output_handle *handle) +{ + int ret = 0; + + perf_aux_output_flag(handle, PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW); + buf->trbe_limit = compute_trbe_buffer_limit(handle); + buf->trbe_write = buf->trbe_base + PERF_IDX2OFF(handle->head, buf); + if (buf->trbe_limit == buf->trbe_base) { + ret = -ENOSPC; + goto err; + } + /* Set the base of the TRBE to the buffer base */ + buf->trbe_hw_base = buf->trbe_base; + + ret = trbe_apply_work_around_before_enable(buf); + if (ret) + goto err; + + *this_cpu_ptr(buf->cpudata->drvdata->handle) = handle; + trbe_enable_hw(buf); + return 0; +err: + trbe_stop_and_truncate_event(handle); + return ret; +} + +static int arm_trbe_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) +{ + struct trbe_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct trbe_cpudata *cpudata = dev_get_drvdata(&csdev->dev); + struct perf_output_handle *handle = path->handle; + struct trbe_buf *buf = etm_perf_sink_config(handle); + + WARN_ON(cpudata->cpu != smp_processor_id()); + WARN_ON(cpudata->drvdata != drvdata); + if (mode != CS_MODE_PERF) + return -EINVAL; + + cpudata->buf = buf; + cpudata->mode = mode; + buf->cpudata = cpudata; + + return __arm_trbe_enable(buf, handle); +} + +static int arm_trbe_disable(struct coresight_device *csdev) +{ + struct trbe_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct trbe_cpudata *cpudata = dev_get_drvdata(&csdev->dev); + struct trbe_buf *buf = cpudata->buf; + + WARN_ON(buf->cpudata != cpudata); + WARN_ON(cpudata->cpu != smp_processor_id()); + WARN_ON(cpudata->drvdata != drvdata); + if (cpudata->mode != CS_MODE_PERF) + return -EINVAL; + + trbe_drain_and_disable_local(cpudata); + buf->cpudata = NULL; + cpudata->buf = NULL; + cpudata->mode = CS_MODE_DISABLED; + return 0; +} + +static void trbe_handle_spurious(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + + /* + * If the IRQ was spurious, simply re-enable the TRBE + * back without modifying the buffer parameters to + * retain the trace collected so far. + */ + set_trbe_enabled(buf->cpudata, trblimitr); +} + +static int trbe_handle_overflow(struct perf_output_handle *handle) +{ + struct perf_event *event = handle->event; + struct trbe_buf *buf = etm_perf_sink_config(handle); + unsigned long size; + struct etm_event_data *event_data; + + size = trbe_get_trace_size(handle, buf, true); + if (buf->snapshot) + handle->head += size; + + trbe_report_wrap_event(handle); + perf_aux_output_end(handle, size); + event_data = perf_aux_output_begin(handle, event); + if (!event_data) { + /* + * We are unable to restart the trace collection, + * thus leave the TRBE disabled. The etm-perf driver + * is able to detect this with a disconnected handle + * (handle->event = NULL). + */ + trbe_drain_and_disable_local(buf->cpudata); + *this_cpu_ptr(buf->cpudata->drvdata->handle) = NULL; + return -EINVAL; + } + + return __arm_trbe_enable(buf, handle); +} + +static bool is_perf_trbe(struct perf_output_handle *handle) +{ + struct trbe_buf *buf = etm_perf_sink_config(handle); + struct trbe_cpudata *cpudata = buf->cpudata; + struct trbe_drvdata *drvdata = cpudata->drvdata; + int cpu = smp_processor_id(); + + WARN_ON(buf->trbe_hw_base != get_trbe_base_pointer()); + WARN_ON(buf->trbe_limit != get_trbe_limit_pointer()); + + if (cpudata->mode != CS_MODE_PERF) + return false; + + if (cpudata->cpu != cpu) + return false; + + if (!cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + return false; + + return true; +} + +static u64 cpu_prohibit_trace(void) +{ + u64 trfcr = read_trfcr(); + + /* Prohibit tracing at EL0 & the kernel EL */ + write_trfcr(trfcr & ~(TRFCR_EL1_ExTRE | TRFCR_EL1_E0TRE)); + /* Return the original value of the TRFCR */ + return trfcr; +} + +static irqreturn_t arm_trbe_irq_handler(int irq, void *dev) +{ + struct perf_output_handle **handle_ptr = dev; + struct perf_output_handle *handle = *handle_ptr; + struct trbe_buf *buf = etm_perf_sink_config(handle); + enum trbe_fault_action act; + u64 status; + bool truncated = false; + u64 trfcr; + + /* Reads to TRBSR_EL1 is fine when TRBE is active */ + status = read_sysreg_s(SYS_TRBSR_EL1); + /* + * If the pending IRQ was handled by update_buffer callback + * we have nothing to do here. + */ + if (!is_trbe_irq(status)) + return IRQ_NONE; + + /* Prohibit the CPU from tracing before we disable the TRBE */ + trfcr = cpu_prohibit_trace(); + /* + * Ensure the trace is visible to the CPUs and + * any external aborts have been resolved. + */ + trbe_drain_and_disable_local(buf->cpudata); + clr_trbe_irq(); + isb(); + + if (WARN_ON_ONCE(!handle) || !perf_get_aux(handle)) + return IRQ_NONE; + + if (!is_perf_trbe(handle)) + return IRQ_NONE; + + act = trbe_get_fault_act(handle, status); + switch (act) { + case TRBE_FAULT_ACT_WRAP: + truncated = !!trbe_handle_overflow(handle); + break; + case TRBE_FAULT_ACT_SPURIOUS: + trbe_handle_spurious(handle); + break; + case TRBE_FAULT_ACT_FATAL: + trbe_stop_and_truncate_event(handle); + truncated = true; + break; + } + + /* + * If the buffer was truncated, ensure perf callbacks + * have completed, which will disable the event. + * + * Otherwise, restore the trace filter controls to + * allow the tracing. + */ + if (truncated) + irq_work_run(); + else + write_trfcr(trfcr); + + return IRQ_HANDLED; +} + +static const struct coresight_ops_sink arm_trbe_sink_ops = { + .enable = arm_trbe_enable, + .disable = arm_trbe_disable, + .alloc_buffer = arm_trbe_alloc_buffer, + .free_buffer = arm_trbe_free_buffer, + .update_buffer = arm_trbe_update_buffer, +}; + +static const struct coresight_ops arm_trbe_cs_ops = { + .sink_ops = &arm_trbe_sink_ops, +}; + +static ssize_t align_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct trbe_cpudata *cpudata = dev_get_drvdata(dev); + + return sprintf(buf, "%llx\n", cpudata->trbe_hw_align); +} +static DEVICE_ATTR_RO(align); + +static ssize_t flag_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct trbe_cpudata *cpudata = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", cpudata->trbe_flag); +} +static DEVICE_ATTR_RO(flag); + +static struct attribute *arm_trbe_attrs[] = { + &dev_attr_align.attr, + &dev_attr_flag.attr, + NULL, +}; + +static const struct attribute_group arm_trbe_group = { + .attrs = arm_trbe_attrs, +}; + +static const struct attribute_group *arm_trbe_groups[] = { + &arm_trbe_group, + NULL, +}; + +static void arm_trbe_enable_cpu(void *info) +{ + struct trbe_drvdata *drvdata = info; + struct trbe_cpudata *cpudata = this_cpu_ptr(drvdata->cpudata); + + trbe_reset_local(cpudata); + enable_percpu_irq(drvdata->irq, IRQ_TYPE_NONE); +} + +static void arm_trbe_disable_cpu(void *info) +{ + struct trbe_drvdata *drvdata = info; + struct trbe_cpudata *cpudata = this_cpu_ptr(drvdata->cpudata); + + disable_percpu_irq(drvdata->irq); + trbe_reset_local(cpudata); +} + + +static void arm_trbe_register_coresight_cpu(struct trbe_drvdata *drvdata, int cpu) +{ + struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); + struct coresight_device *trbe_csdev = coresight_get_percpu_sink(cpu); + struct coresight_desc desc = { 0 }; + struct device *dev; + + if (WARN_ON(trbe_csdev)) + return; + + /* If the TRBE was not probed on the CPU, we shouldn't be here */ + if (WARN_ON(!cpudata->drvdata)) + return; + + dev = &cpudata->drvdata->pdev->dev; + desc.name = devm_kasprintf(dev, GFP_KERNEL, "trbe%d", cpu); + if (!desc.name) + goto cpu_clear; + /* + * TRBE coresight devices do not need regular connections + * information, as the paths get built between all percpu + * source and their respective percpu sink devices. Though + * coresight_register() expect device connections via the + * platform_data, which TRBE devices do not have. As they + * are not real ACPI devices, coresight_get_platform_data() + * ends up failing. Instead let's allocate a dummy zeroed + * coresight_platform_data structure and assign that back + * into the device for that purpose. + */ + desc.pdata = devm_kzalloc(dev, sizeof(*desc.pdata), GFP_KERNEL); + if (!desc.pdata) + goto cpu_clear; + + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM; + desc.ops = &arm_trbe_cs_ops; + desc.groups = arm_trbe_groups; + desc.dev = dev; + trbe_csdev = coresight_register(&desc); + if (IS_ERR(trbe_csdev)) + goto cpu_clear; + + dev_set_drvdata(&trbe_csdev->dev, cpudata); + coresight_set_percpu_sink(cpu, trbe_csdev); + return; +cpu_clear: + cpumask_clear_cpu(cpu, &drvdata->supported_cpus); +} + +/* + * Must be called with preemption disabled, for trbe_check_errata(). + */ +static void arm_trbe_probe_cpu(void *info) +{ + struct trbe_drvdata *drvdata = info; + int cpu = smp_processor_id(); + struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); + u64 trbidr; + + if (WARN_ON(!cpudata)) + goto cpu_clear; + + if (!is_trbe_available()) { + pr_err("TRBE is not implemented on cpu %d\n", cpu); + goto cpu_clear; + } + + trbidr = read_sysreg_s(SYS_TRBIDR_EL1); + if (!is_trbe_programmable(trbidr)) { + pr_err("TRBE is owned in higher exception level on cpu %d\n", cpu); + goto cpu_clear; + } + + cpudata->trbe_hw_align = 1ULL << get_trbe_address_align(trbidr); + if (cpudata->trbe_hw_align > SZ_2K) { + pr_err("Unsupported alignment on cpu %d\n", cpu); + goto cpu_clear; + } + + /* + * Run the TRBE erratum checks, now that we know + * this instance is about to be registered. + */ + trbe_check_errata(cpudata); + + if (trbe_is_broken(cpudata)) { + pr_err("Disabling TRBE on cpu%d due to erratum\n", cpu); + goto cpu_clear; + } + + /* + * If the TRBE is affected by erratum TRBE_WORKAROUND_OVERWRITE_FILL_MODE, + * we must always program the TBRPTR_EL1, 256bytes from a page + * boundary, with TRBBASER_EL1 set to the page, to prevent + * TRBE over-writing 256bytes at TRBBASER_EL1 on FILL event. + * + * Thus make sure we always align our write pointer to a PAGE_SIZE, + * which also guarantees that we have at least a PAGE_SIZE space in + * the buffer (TRBLIMITR is PAGE aligned) and thus we can skip + * the required bytes at the base. + */ + if (trbe_may_overwrite_in_fill_mode(cpudata)) + cpudata->trbe_align = PAGE_SIZE; + else + cpudata->trbe_align = cpudata->trbe_hw_align; + + cpudata->trbe_flag = get_trbe_flag_update(trbidr); + cpudata->cpu = cpu; + cpudata->drvdata = drvdata; + return; +cpu_clear: + cpumask_clear_cpu(cpu, &drvdata->supported_cpus); +} + +static void arm_trbe_remove_coresight_cpu(struct trbe_drvdata *drvdata, int cpu) +{ + struct coresight_device *trbe_csdev = coresight_get_percpu_sink(cpu); + + if (trbe_csdev) { + coresight_unregister(trbe_csdev); + coresight_set_percpu_sink(cpu, NULL); + } +} + +static int arm_trbe_probe_coresight(struct trbe_drvdata *drvdata) +{ + int cpu; + + drvdata->cpudata = alloc_percpu(typeof(*drvdata->cpudata)); + if (!drvdata->cpudata) + return -ENOMEM; + + for_each_cpu(cpu, &drvdata->supported_cpus) { + /* If we fail to probe the CPU, let us defer it to hotplug callbacks */ + if (smp_call_function_single(cpu, arm_trbe_probe_cpu, drvdata, 1)) + continue; + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + arm_trbe_register_coresight_cpu(drvdata, cpu); + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + smp_call_function_single(cpu, arm_trbe_enable_cpu, drvdata, 1); + } + return 0; +} + +static int arm_trbe_remove_coresight(struct trbe_drvdata *drvdata) +{ + int cpu; + + for_each_cpu(cpu, &drvdata->supported_cpus) { + smp_call_function_single(cpu, arm_trbe_disable_cpu, drvdata, 1); + arm_trbe_remove_coresight_cpu(drvdata, cpu); + } + free_percpu(drvdata->cpudata); + return 0; +} + +static void arm_trbe_probe_hotplugged_cpu(struct trbe_drvdata *drvdata) +{ + preempt_disable(); + arm_trbe_probe_cpu(drvdata); + preempt_enable(); +} + +static int arm_trbe_cpu_startup(unsigned int cpu, struct hlist_node *node) +{ + struct trbe_drvdata *drvdata = hlist_entry_safe(node, struct trbe_drvdata, hotplug_node); + + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) { + + /* + * If this CPU was not probed for TRBE, + * initialize it now. + */ + if (!coresight_get_percpu_sink(cpu)) { + arm_trbe_probe_hotplugged_cpu(drvdata); + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + arm_trbe_register_coresight_cpu(drvdata, cpu); + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + arm_trbe_enable_cpu(drvdata); + } else { + arm_trbe_enable_cpu(drvdata); + } + } + return 0; +} + +static int arm_trbe_cpu_teardown(unsigned int cpu, struct hlist_node *node) +{ + struct trbe_drvdata *drvdata = hlist_entry_safe(node, struct trbe_drvdata, hotplug_node); + + if (cpumask_test_cpu(cpu, &drvdata->supported_cpus)) + arm_trbe_disable_cpu(drvdata); + return 0; +} + +static int arm_trbe_probe_cpuhp(struct trbe_drvdata *drvdata) +{ + enum cpuhp_state trbe_online; + int ret; + + trbe_online = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DRVNAME, + arm_trbe_cpu_startup, arm_trbe_cpu_teardown); + if (trbe_online < 0) + return trbe_online; + + ret = cpuhp_state_add_instance(trbe_online, &drvdata->hotplug_node); + if (ret) { + cpuhp_remove_multi_state(trbe_online); + return ret; + } + drvdata->trbe_online = trbe_online; + return 0; +} + +static void arm_trbe_remove_cpuhp(struct trbe_drvdata *drvdata) +{ + cpuhp_state_remove_instance(drvdata->trbe_online, &drvdata->hotplug_node); + cpuhp_remove_multi_state(drvdata->trbe_online); +} + +static int arm_trbe_probe_irq(struct platform_device *pdev, + struct trbe_drvdata *drvdata) +{ + const struct cpumask *affinity; + int ret; + + drvdata->irq = platform_get_irq_affinity(pdev, 0, &affinity); + if (drvdata->irq < 0) { + pr_err("IRQ not found for the platform device\n"); + return drvdata->irq; + } + + if (!irq_is_percpu(drvdata->irq)) { + pr_err("IRQ is not a PPI\n"); + return -EINVAL; + } + + cpumask_copy(&drvdata->supported_cpus, affinity); + + drvdata->handle = alloc_percpu(struct perf_output_handle *); + if (!drvdata->handle) + return -ENOMEM; + + ret = request_percpu_irq_affinity(drvdata->irq, arm_trbe_irq_handler, DRVNAME, + affinity, drvdata->handle); + if (ret) { + free_percpu(drvdata->handle); + return ret; + } + return 0; +} + +static void arm_trbe_remove_irq(struct trbe_drvdata *drvdata) +{ + free_percpu_irq(drvdata->irq, drvdata->handle); + free_percpu(drvdata->handle); +} + +static int arm_trbe_device_probe(struct platform_device *pdev) +{ + struct trbe_drvdata *drvdata; + struct device *dev = &pdev->dev; + int ret; + + /* Trace capture is not possible with kernel page table isolation */ + if (arm64_kernel_unmapped_at_el0()) { + pr_err("TRBE wouldn't work if kernel gets unmapped at EL0\n"); + return -EOPNOTSUPP; + } + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + dev_set_drvdata(dev, drvdata); + drvdata->pdev = pdev; + ret = arm_trbe_probe_irq(pdev, drvdata); + if (ret) + return ret; + + ret = arm_trbe_probe_coresight(drvdata); + if (ret) + goto probe_failed; + + ret = arm_trbe_probe_cpuhp(drvdata); + if (ret) + goto cpuhp_failed; + + return 0; +cpuhp_failed: + arm_trbe_remove_coresight(drvdata); +probe_failed: + arm_trbe_remove_irq(drvdata); + return ret; +} + +static void arm_trbe_device_remove(struct platform_device *pdev) +{ + struct trbe_drvdata *drvdata = platform_get_drvdata(pdev); + + arm_trbe_remove_cpuhp(drvdata); + arm_trbe_remove_coresight(drvdata); + arm_trbe_remove_irq(drvdata); +} + +static const struct of_device_id arm_trbe_of_match[] = { + { .compatible = "arm,trace-buffer-extension"}, + {}, +}; +MODULE_DEVICE_TABLE(of, arm_trbe_of_match); + +#ifdef CONFIG_ACPI +static const struct platform_device_id arm_trbe_acpi_match[] = { + { ARMV8_TRBE_PDEV_NAME, 0 }, + { } +}; +MODULE_DEVICE_TABLE(platform, arm_trbe_acpi_match); +#endif + +static struct platform_driver arm_trbe_driver = { + .id_table = ACPI_PTR(arm_trbe_acpi_match), + .driver = { + .name = DRVNAME, + .of_match_table = of_match_ptr(arm_trbe_of_match), + .suppress_bind_attrs = true, + }, + .probe = arm_trbe_device_probe, + .remove = arm_trbe_device_remove, +}; + +static int __init arm_trbe_init(void) +{ + int ret; + + ret = platform_driver_register(&arm_trbe_driver); + if (!ret) + return 0; + + pr_err("Error registering %s platform driver\n", DRVNAME); + return ret; +} + +static void __exit arm_trbe_exit(void) +{ + platform_driver_unregister(&arm_trbe_driver); +} +module_init(arm_trbe_init); +module_exit(arm_trbe_exit); + +MODULE_AUTHOR("Anshuman Khandual <anshuman.khandual@arm.com>"); +MODULE_DESCRIPTION("Arm Trace Buffer Extension (TRBE) driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/coresight/coresight-trbe.h b/drivers/hwtracing/coresight/coresight-trbe.h new file mode 100644 index 000000000000..45202c48acce --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trbe.h @@ -0,0 +1,139 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This contains all required hardware related helper functions for + * Trace Buffer Extension (TRBE) driver in the coresight framework. + * + * Copyright (C) 2020 ARM Ltd. + * + * Author: Anshuman Khandual <anshuman.khandual@arm.com> + */ +#include <linux/acpi.h> +#include <linux/coresight.h> +#include <linux/device.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/perf/arm_pmu.h> +#include <linux/platform_device.h> +#include <linux/smp.h> + +#include "coresight-etm-perf.h" + +static inline bool is_trbe_available(void) +{ + u64 aa64dfr0 = read_sysreg_s(SYS_ID_AA64DFR0_EL1); + unsigned int trbe = cpuid_feature_extract_unsigned_field(aa64dfr0, + ID_AA64DFR0_EL1_TraceBuffer_SHIFT); + + return trbe >= ID_AA64DFR0_EL1_TraceBuffer_IMP; +} + +static inline bool is_trbe_enabled(void) +{ + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + + return trblimitr & TRBLIMITR_EL1_E; +} + +#define TRBE_EC_OTHERS 0 +#define TRBE_EC_STAGE1_ABORT 36 +#define TRBE_EC_STAGE2_ABORT 37 + +static inline int get_trbe_ec(u64 trbsr) +{ + return (trbsr & TRBSR_EL1_EC_MASK) >> TRBSR_EL1_EC_SHIFT; +} + +#define TRBE_BSC_NOT_STOPPED 0 +#define TRBE_BSC_FILLED 1 +#define TRBE_BSC_TRIGGERED 2 + +static inline int get_trbe_bsc(u64 trbsr) +{ + return (trbsr & TRBSR_EL1_BSC_MASK) >> TRBSR_EL1_BSC_SHIFT; +} + +static inline void clr_trbe_irq(void) +{ + u64 trbsr = read_sysreg_s(SYS_TRBSR_EL1); + + trbsr &= ~TRBSR_EL1_IRQ; + write_sysreg_s(trbsr, SYS_TRBSR_EL1); +} + +static inline bool is_trbe_irq(u64 trbsr) +{ + return trbsr & TRBSR_EL1_IRQ; +} + +static inline bool is_trbe_trg(u64 trbsr) +{ + return trbsr & TRBSR_EL1_TRG; +} + +static inline bool is_trbe_wrap(u64 trbsr) +{ + return trbsr & TRBSR_EL1_WRAP; +} + +static inline bool is_trbe_abort(u64 trbsr) +{ + return trbsr & TRBSR_EL1_EA; +} + +static inline bool is_trbe_running(u64 trbsr) +{ + return !(trbsr & TRBSR_EL1_S); +} + +static inline bool get_trbe_flag_update(u64 trbidr) +{ + return trbidr & TRBIDR_EL1_F; +} + +static inline bool is_trbe_programmable(u64 trbidr) +{ + return !(trbidr & TRBIDR_EL1_P); +} + +static inline int get_trbe_address_align(u64 trbidr) +{ + return (trbidr & TRBIDR_EL1_Align_MASK) >> TRBIDR_EL1_Align_SHIFT; +} + +static inline unsigned long get_trbe_write_pointer(void) +{ + return read_sysreg_s(SYS_TRBPTR_EL1); +} + +static inline void set_trbe_write_pointer(unsigned long addr) +{ + WARN_ON(is_trbe_enabled()); + write_sysreg_s(addr, SYS_TRBPTR_EL1); +} + +static inline unsigned long get_trbe_limit_pointer(void) +{ + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + unsigned long addr = trblimitr & TRBLIMITR_EL1_LIMIT_MASK; + + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + return addr; +} + +static inline unsigned long get_trbe_base_pointer(void) +{ + u64 trbbaser = read_sysreg_s(SYS_TRBBASER_EL1); + unsigned long addr = trbbaser & TRBBASER_EL1_BASE_MASK; + + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + return addr; +} + +static inline void set_trbe_base_pointer(unsigned long addr) +{ + WARN_ON(is_trbe_enabled()); + WARN_ON(!IS_ALIGNED(addr, (1UL << TRBBASER_EL1_BASE_SHIFT))); + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + write_sysreg_s(addr, SYS_TRBBASER_EL1); +} diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c deleted file mode 100644 index 2b0df1a0a8df..000000000000 --- a/drivers/hwtracing/coresight/coresight.c +++ /dev/null @@ -1,1192 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2012, The Linux Foundation. All rights reserved. - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/types.h> -#include <linux/device.h> -#include <linux/io.h> -#include <linux/err.h> -#include <linux/export.h> -#include <linux/slab.h> -#include <linux/mutex.h> -#include <linux/clk.h> -#include <linux/coresight.h> -#include <linux/of_platform.h> -#include <linux/delay.h> -#include <linux/pm_runtime.h> - -#include "coresight-priv.h" - -static DEFINE_MUTEX(coresight_mutex); - -/** - * struct coresight_node - elements of a path, from source to sink - * @csdev: Address of an element. - * @link: hook to the list. - */ -struct coresight_node { - struct coresight_device *csdev; - struct list_head link; -}; - -/* - * When operating Coresight drivers from the sysFS interface, only a single - * path can exist from a tracer (associated to a CPU) to a sink. - */ -static DEFINE_PER_CPU(struct list_head *, tracer_path); - -/* - * As of this writing only a single STM can be found in CS topologies. Since - * there is no way to know if we'll ever see more and what kind of - * configuration they will enact, for the time being only define a single path - * for STM. - */ -static struct list_head *stm_path; - -/* - * When losing synchronisation a new barrier packet needs to be inserted at the - * beginning of the data collected in a buffer. That way the decoder knows that - * it needs to look for another sync sequence. - */ -const u32 barrier_pkt[4] = {0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff}; - -static int coresight_id_match(struct device *dev, void *data) -{ - int trace_id, i_trace_id; - struct coresight_device *csdev, *i_csdev; - - csdev = data; - i_csdev = to_coresight_device(dev); - - /* - * No need to care about oneself and components that are not - * sources or not enabled - */ - if (i_csdev == csdev || !i_csdev->enable || - i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE) - return 0; - - /* Get the source ID for both compoment */ - trace_id = source_ops(csdev)->trace_id(csdev); - i_trace_id = source_ops(i_csdev)->trace_id(i_csdev); - - /* All you need is one */ - if (trace_id == i_trace_id) - return 1; - - return 0; -} - -static int coresight_source_is_unique(struct coresight_device *csdev) -{ - int trace_id = source_ops(csdev)->trace_id(csdev); - - /* this shouldn't happen */ - if (trace_id < 0) - return 0; - - return !bus_for_each_dev(&coresight_bustype, NULL, - csdev, coresight_id_match); -} - -static int coresight_find_link_inport(struct coresight_device *csdev, - struct coresight_device *parent) -{ - int i; - struct coresight_connection *conn; - - for (i = 0; i < parent->nr_outport; i++) { - conn = &parent->conns[i]; - if (conn->child_dev == csdev) - return conn->child_port; - } - - dev_err(&csdev->dev, "couldn't find inport, parent: %s, child: %s\n", - dev_name(&parent->dev), dev_name(&csdev->dev)); - - return -ENODEV; -} - -static int coresight_find_link_outport(struct coresight_device *csdev, - struct coresight_device *child) -{ - int i; - struct coresight_connection *conn; - - for (i = 0; i < csdev->nr_outport; i++) { - conn = &csdev->conns[i]; - if (conn->child_dev == child) - return conn->outport; - } - - dev_err(&csdev->dev, "couldn't find outport, parent: %s, child: %s\n", - dev_name(&csdev->dev), dev_name(&child->dev)); - - return -ENODEV; -} - -static inline u32 coresight_read_claim_tags(void __iomem *base) -{ - return readl_relaxed(base + CORESIGHT_CLAIMCLR); -} - -static inline bool coresight_is_claimed_self_hosted(void __iomem *base) -{ - return coresight_read_claim_tags(base) == CORESIGHT_CLAIM_SELF_HOSTED; -} - -static inline bool coresight_is_claimed_any(void __iomem *base) -{ - return coresight_read_claim_tags(base) != 0; -} - -static inline void coresight_set_claim_tags(void __iomem *base) -{ - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMSET); - isb(); -} - -static inline void coresight_clear_claim_tags(void __iomem *base) -{ - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMCLR); - isb(); -} - -/* - * coresight_claim_device_unlocked : Claim the device for self-hosted usage - * to prevent an external tool from touching this device. As per PSCI - * standards, section "Preserving the execution context" => "Debug and Trace - * save and Restore", DBGCLAIM[1] is reserved for Self-hosted debug/trace and - * DBGCLAIM[0] is reserved for external tools. - * - * Called with CS_UNLOCKed for the component. - * Returns : 0 on success - */ -int coresight_claim_device_unlocked(void __iomem *base) -{ - if (coresight_is_claimed_any(base)) - return -EBUSY; - - coresight_set_claim_tags(base); - if (coresight_is_claimed_self_hosted(base)) - return 0; - /* There was a race setting the tags, clean up and fail */ - coresight_clear_claim_tags(base); - return -EBUSY; -} - -int coresight_claim_device(void __iomem *base) -{ - int rc; - - CS_UNLOCK(base); - rc = coresight_claim_device_unlocked(base); - CS_LOCK(base); - - return rc; -} - -/* - * coresight_disclaim_device_unlocked : Clear the claim tags for the device. - * Called with CS_UNLOCKed for the component. - */ -void coresight_disclaim_device_unlocked(void __iomem *base) -{ - - if (coresight_is_claimed_self_hosted(base)) - coresight_clear_claim_tags(base); - else - /* - * The external agent may have not honoured our claim - * and has manipulated it. Or something else has seriously - * gone wrong in our driver. - */ - WARN_ON_ONCE(1); -} - -void coresight_disclaim_device(void __iomem *base) -{ - CS_UNLOCK(base); - coresight_disclaim_device_unlocked(base); - CS_LOCK(base); -} - -static int coresight_enable_sink(struct coresight_device *csdev, - u32 mode, void *data) -{ - int ret; - - /* - * We need to make sure the "new" session is compatible with the - * existing "mode" of operation. - */ - if (sink_ops(csdev)->enable) { - ret = sink_ops(csdev)->enable(csdev, mode, data); - if (ret) - return ret; - csdev->enable = true; - } - - atomic_inc(csdev->refcnt); - - return 0; -} - -static void coresight_disable_sink(struct coresight_device *csdev) -{ - if (atomic_dec_return(csdev->refcnt) == 0) { - if (sink_ops(csdev)->disable) { - sink_ops(csdev)->disable(csdev); - csdev->enable = false; - } - } -} - -static int coresight_enable_link(struct coresight_device *csdev, - struct coresight_device *parent, - struct coresight_device *child) -{ - int ret; - int link_subtype; - int refport, inport, outport; - - if (!parent || !child) - return -EINVAL; - - inport = coresight_find_link_inport(csdev, parent); - outport = coresight_find_link_outport(csdev, child); - link_subtype = csdev->subtype.link_subtype; - - if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) - refport = inport; - else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) - refport = outport; - else - refport = 0; - - if (refport < 0) - return refport; - - if (atomic_inc_return(&csdev->refcnt[refport]) == 1) { - if (link_ops(csdev)->enable) { - ret = link_ops(csdev)->enable(csdev, inport, outport); - if (ret) { - atomic_dec(&csdev->refcnt[refport]); - return ret; - } - } - } - - csdev->enable = true; - - return 0; -} - -static void coresight_disable_link(struct coresight_device *csdev, - struct coresight_device *parent, - struct coresight_device *child) -{ - int i, nr_conns; - int link_subtype; - int refport, inport, outport; - - if (!parent || !child) - return; - - inport = coresight_find_link_inport(csdev, parent); - outport = coresight_find_link_outport(csdev, child); - link_subtype = csdev->subtype.link_subtype; - - if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) { - refport = inport; - nr_conns = csdev->nr_inport; - } else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) { - refport = outport; - nr_conns = csdev->nr_outport; - } else { - refport = 0; - nr_conns = 1; - } - - if (atomic_dec_return(&csdev->refcnt[refport]) == 0) { - if (link_ops(csdev)->disable) - link_ops(csdev)->disable(csdev, inport, outport); - } - - for (i = 0; i < nr_conns; i++) - if (atomic_read(&csdev->refcnt[i]) != 0) - return; - - csdev->enable = false; -} - -static int coresight_enable_source(struct coresight_device *csdev, u32 mode) -{ - int ret; - - if (!coresight_source_is_unique(csdev)) { - dev_warn(&csdev->dev, "traceID %d not unique\n", - source_ops(csdev)->trace_id(csdev)); - return -EINVAL; - } - - if (!csdev->enable) { - if (source_ops(csdev)->enable) { - ret = source_ops(csdev)->enable(csdev, NULL, mode); - if (ret) - return ret; - } - csdev->enable = true; - } - - atomic_inc(csdev->refcnt); - - return 0; -} - -/** - * coresight_disable_source - Drop the reference count by 1 and disable - * the device if there are no users left. - * - * @csdev - The coresight device to disable - * - * Returns true if the device has been disabled. - */ -static bool coresight_disable_source(struct coresight_device *csdev) -{ - if (atomic_dec_return(csdev->refcnt) == 0) { - if (source_ops(csdev)->disable) - source_ops(csdev)->disable(csdev, NULL); - csdev->enable = false; - } - return !csdev->enable; -} - -/* - * coresight_disable_path_from : Disable components in the given path beyond - * @nd in the list. If @nd is NULL, all the components, except the SOURCE are - * disabled. - */ -static void coresight_disable_path_from(struct list_head *path, - struct coresight_node *nd) -{ - u32 type; - struct coresight_device *csdev, *parent, *child; - - if (!nd) - nd = list_first_entry(path, struct coresight_node, link); - - list_for_each_entry_continue(nd, path, link) { - csdev = nd->csdev; - type = csdev->type; - - /* - * ETF devices are tricky... They can be a link or a sink, - * depending on how they are configured. If an ETF has been - * "activated" it will be configured as a sink, otherwise - * go ahead with the link configuration. - */ - if (type == CORESIGHT_DEV_TYPE_LINKSINK) - type = (csdev == coresight_get_sink(path)) ? - CORESIGHT_DEV_TYPE_SINK : - CORESIGHT_DEV_TYPE_LINK; - - switch (type) { - case CORESIGHT_DEV_TYPE_SINK: - coresight_disable_sink(csdev); - break; - case CORESIGHT_DEV_TYPE_SOURCE: - /* - * We skip the first node in the path assuming that it - * is the source. So we don't expect a source device in - * the middle of a path. - */ - WARN_ON(1); - break; - case CORESIGHT_DEV_TYPE_LINK: - parent = list_prev_entry(nd, link)->csdev; - child = list_next_entry(nd, link)->csdev; - coresight_disable_link(csdev, parent, child); - break; - default: - break; - } - } -} - -void coresight_disable_path(struct list_head *path) -{ - coresight_disable_path_from(path, NULL); -} - -int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data) -{ - - int ret = 0; - u32 type; - struct coresight_node *nd; - struct coresight_device *csdev, *parent, *child; - - list_for_each_entry_reverse(nd, path, link) { - csdev = nd->csdev; - type = csdev->type; - - /* - * ETF devices are tricky... They can be a link or a sink, - * depending on how they are configured. If an ETF has been - * "activated" it will be configured as a sink, otherwise - * go ahead with the link configuration. - */ - if (type == CORESIGHT_DEV_TYPE_LINKSINK) - type = (csdev == coresight_get_sink(path)) ? - CORESIGHT_DEV_TYPE_SINK : - CORESIGHT_DEV_TYPE_LINK; - - switch (type) { - case CORESIGHT_DEV_TYPE_SINK: - ret = coresight_enable_sink(csdev, mode, sink_data); - /* - * Sink is the first component turned on. If we - * failed to enable the sink, there are no components - * that need disabling. Disabling the path here - * would mean we could disrupt an existing session. - */ - if (ret) - goto out; - break; - case CORESIGHT_DEV_TYPE_SOURCE: - /* sources are enabled from either sysFS or Perf */ - break; - case CORESIGHT_DEV_TYPE_LINK: - parent = list_prev_entry(nd, link)->csdev; - child = list_next_entry(nd, link)->csdev; - ret = coresight_enable_link(csdev, parent, child); - if (ret) - goto err; - break; - default: - goto err; - } - } - -out: - return ret; -err: - coresight_disable_path_from(path, nd); - goto out; -} - -struct coresight_device *coresight_get_sink(struct list_head *path) -{ - struct coresight_device *csdev; - - if (!path) - return NULL; - - csdev = list_last_entry(path, struct coresight_node, link)->csdev; - if (csdev->type != CORESIGHT_DEV_TYPE_SINK && - csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) - return NULL; - - return csdev; -} - -static int coresight_enabled_sink(struct device *dev, void *data) -{ - bool *reset = data; - struct coresight_device *csdev = to_coresight_device(dev); - - if ((csdev->type == CORESIGHT_DEV_TYPE_SINK || - csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) && - csdev->activated) { - /* - * Now that we have a handle on the sink for this session, - * disable the sysFS "enable_sink" flag so that possible - * concurrent perf session that wish to use another sink don't - * trip on it. Doing so has no ramification for the current - * session. - */ - if (*reset) - csdev->activated = false; - - return 1; - } - - return 0; -} - -/** - * coresight_get_enabled_sink - returns the first enabled sink found on the bus - * @deactivate: Whether the 'enable_sink' flag should be reset - * - * When operated from perf the deactivate parameter should be set to 'true'. - * That way the "enabled_sink" flag of the sink that was selected can be reset, - * allowing for other concurrent perf sessions to choose a different sink. - * - * When operated from sysFS users have full control and as such the deactivate - * parameter should be set to 'false', hence mandating users to explicitly - * clear the flag. - */ -struct coresight_device *coresight_get_enabled_sink(bool deactivate) -{ - struct device *dev = NULL; - - dev = bus_find_device(&coresight_bustype, NULL, &deactivate, - coresight_enabled_sink); - - return dev ? to_coresight_device(dev) : NULL; -} - -/* - * coresight_grab_device - Power up this device and any of the helper - * devices connected to it for trace operation. Since the helper devices - * don't appear on the trace path, they should be handled along with the - * the master device. - */ -static void coresight_grab_device(struct coresight_device *csdev) -{ - int i; - - for (i = 0; i < csdev->nr_outport; i++) { - struct coresight_device *child = csdev->conns[i].child_dev; - - if (child && child->type == CORESIGHT_DEV_TYPE_HELPER) - pm_runtime_get_sync(child->dev.parent); - } - pm_runtime_get_sync(csdev->dev.parent); -} - -/* - * coresight_drop_device - Release this device and any of the helper - * devices connected to it. - */ -static void coresight_drop_device(struct coresight_device *csdev) -{ - int i; - - pm_runtime_put(csdev->dev.parent); - for (i = 0; i < csdev->nr_outport; i++) { - struct coresight_device *child = csdev->conns[i].child_dev; - - if (child && child->type == CORESIGHT_DEV_TYPE_HELPER) - pm_runtime_put(child->dev.parent); - } -} - -/** - * _coresight_build_path - recursively build a path from a @csdev to a sink. - * @csdev: The device to start from. - * @path: The list to add devices to. - * - * The tree of Coresight device is traversed until an activated sink is - * found. From there the sink is added to the list along with all the - * devices that led to that point - the end result is a list from source - * to sink. In that list the source is the first device and the sink the - * last one. - */ -static int _coresight_build_path(struct coresight_device *csdev, - struct coresight_device *sink, - struct list_head *path) -{ - int i; - bool found = false; - struct coresight_node *node; - - /* An activated sink has been found. Enqueue the element */ - if (csdev == sink) - goto out; - - /* Not a sink - recursively explore each port found on this element */ - for (i = 0; i < csdev->nr_outport; i++) { - struct coresight_device *child_dev = csdev->conns[i].child_dev; - - if (child_dev && - _coresight_build_path(child_dev, sink, path) == 0) { - found = true; - break; - } - } - - if (!found) - return -ENODEV; - -out: - /* - * A path from this element to a sink has been found. The elements - * leading to the sink are already enqueued, all that is left to do - * is tell the PM runtime core we need this element and add a node - * for it. - */ - node = kzalloc(sizeof(struct coresight_node), GFP_KERNEL); - if (!node) - return -ENOMEM; - - coresight_grab_device(csdev); - node->csdev = csdev; - list_add(&node->link, path); - - return 0; -} - -struct list_head *coresight_build_path(struct coresight_device *source, - struct coresight_device *sink) -{ - struct list_head *path; - int rc; - - if (!sink) - return ERR_PTR(-EINVAL); - - path = kzalloc(sizeof(struct list_head), GFP_KERNEL); - if (!path) - return ERR_PTR(-ENOMEM); - - INIT_LIST_HEAD(path); - - rc = _coresight_build_path(source, sink, path); - if (rc) { - kfree(path); - return ERR_PTR(rc); - } - - return path; -} - -/** - * coresight_release_path - release a previously built path. - * @path: the path to release. - * - * Go through all the elements of a path and 1) removed it from the list and - * 2) free the memory allocated for each node. - */ -void coresight_release_path(struct list_head *path) -{ - struct coresight_device *csdev; - struct coresight_node *nd, *next; - - list_for_each_entry_safe(nd, next, path, link) { - csdev = nd->csdev; - - coresight_drop_device(csdev); - list_del(&nd->link); - kfree(nd); - } - - kfree(path); - path = NULL; -} - -/** coresight_validate_source - make sure a source has the right credentials - * @csdev: the device structure for a source. - * @function: the function this was called from. - * - * Assumes the coresight_mutex is held. - */ -static int coresight_validate_source(struct coresight_device *csdev, - const char *function) -{ - u32 type, subtype; - - type = csdev->type; - subtype = csdev->subtype.source_subtype; - - if (type != CORESIGHT_DEV_TYPE_SOURCE) { - dev_err(&csdev->dev, "wrong device type in %s\n", function); - return -EINVAL; - } - - if (subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_PROC && - subtype != CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE) { - dev_err(&csdev->dev, "wrong device subtype in %s\n", function); - return -EINVAL; - } - - return 0; -} - -int coresight_enable(struct coresight_device *csdev) -{ - int cpu, ret = 0; - struct coresight_device *sink; - struct list_head *path; - enum coresight_dev_subtype_source subtype; - - subtype = csdev->subtype.source_subtype; - - mutex_lock(&coresight_mutex); - - ret = coresight_validate_source(csdev, __func__); - if (ret) - goto out; - - if (csdev->enable) { - /* - * There could be multiple applications driving the software - * source. So keep the refcount for each such user when the - * source is already enabled. - */ - if (subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE) - atomic_inc(csdev->refcnt); - goto out; - } - - /* - * Search for a valid sink for this session but don't reset the - * "enable_sink" flag in sysFS. Users get to do that explicitly. - */ - sink = coresight_get_enabled_sink(false); - if (!sink) { - ret = -EINVAL; - goto out; - } - - path = coresight_build_path(csdev, sink); - if (IS_ERR(path)) { - pr_err("building path(s) failed\n"); - ret = PTR_ERR(path); - goto out; - } - - ret = coresight_enable_path(path, CS_MODE_SYSFS, NULL); - if (ret) - goto err_path; - - ret = coresight_enable_source(csdev, CS_MODE_SYSFS); - if (ret) - goto err_source; - - switch (subtype) { - case CORESIGHT_DEV_SUBTYPE_SOURCE_PROC: - /* - * When working from sysFS it is important to keep track - * of the paths that were created so that they can be - * undone in 'coresight_disable()'. Since there can only - * be a single session per tracer (when working from sysFS) - * a per-cpu variable will do just fine. - */ - cpu = source_ops(csdev)->cpu_id(csdev); - per_cpu(tracer_path, cpu) = path; - break; - case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: - stm_path = path; - break; - default: - /* We can't be here */ - break; - } - -out: - mutex_unlock(&coresight_mutex); - return ret; - -err_source: - coresight_disable_path(path); - -err_path: - coresight_release_path(path); - goto out; -} -EXPORT_SYMBOL_GPL(coresight_enable); - -void coresight_disable(struct coresight_device *csdev) -{ - int cpu, ret; - struct list_head *path = NULL; - - mutex_lock(&coresight_mutex); - - ret = coresight_validate_source(csdev, __func__); - if (ret) - goto out; - - if (!csdev->enable || !coresight_disable_source(csdev)) - goto out; - - switch (csdev->subtype.source_subtype) { - case CORESIGHT_DEV_SUBTYPE_SOURCE_PROC: - cpu = source_ops(csdev)->cpu_id(csdev); - path = per_cpu(tracer_path, cpu); - per_cpu(tracer_path, cpu) = NULL; - break; - case CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE: - path = stm_path; - stm_path = NULL; - break; - default: - /* We can't be here */ - break; - } - - coresight_disable_path(path); - coresight_release_path(path); - -out: - mutex_unlock(&coresight_mutex); -} -EXPORT_SYMBOL_GPL(coresight_disable); - -static ssize_t enable_sink_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct coresight_device *csdev = to_coresight_device(dev); - - return scnprintf(buf, PAGE_SIZE, "%u\n", csdev->activated); -} - -static ssize_t enable_sink_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret; - unsigned long val; - struct coresight_device *csdev = to_coresight_device(dev); - - ret = kstrtoul(buf, 10, &val); - if (ret) - return ret; - - if (val) - csdev->activated = true; - else - csdev->activated = false; - - return size; - -} -static DEVICE_ATTR_RW(enable_sink); - -static ssize_t enable_source_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct coresight_device *csdev = to_coresight_device(dev); - - return scnprintf(buf, PAGE_SIZE, "%u\n", csdev->enable); -} - -static ssize_t enable_source_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t size) -{ - int ret = 0; - unsigned long val; - struct coresight_device *csdev = to_coresight_device(dev); - - ret = kstrtoul(buf, 10, &val); - if (ret) - return ret; - - if (val) { - ret = coresight_enable(csdev); - if (ret) - return ret; - } else { - coresight_disable(csdev); - } - - return size; -} -static DEVICE_ATTR_RW(enable_source); - -static struct attribute *coresight_sink_attrs[] = { - &dev_attr_enable_sink.attr, - NULL, -}; -ATTRIBUTE_GROUPS(coresight_sink); - -static struct attribute *coresight_source_attrs[] = { - &dev_attr_enable_source.attr, - NULL, -}; -ATTRIBUTE_GROUPS(coresight_source); - -static struct device_type coresight_dev_type[] = { - { - .name = "none", - }, - { - .name = "sink", - .groups = coresight_sink_groups, - }, - { - .name = "link", - }, - { - .name = "linksink", - .groups = coresight_sink_groups, - }, - { - .name = "source", - .groups = coresight_source_groups, - }, - { - .name = "helper", - }, -}; - -static void coresight_device_release(struct device *dev) -{ - struct coresight_device *csdev = to_coresight_device(dev); - - kfree(csdev->conns); - kfree(csdev->refcnt); - kfree(csdev); -} - -static int coresight_orphan_match(struct device *dev, void *data) -{ - int i; - bool still_orphan = false; - struct coresight_device *csdev, *i_csdev; - struct coresight_connection *conn; - - csdev = data; - i_csdev = to_coresight_device(dev); - - /* No need to check oneself */ - if (csdev == i_csdev) - return 0; - - /* Move on to another component if no connection is orphan */ - if (!i_csdev->orphan) - return 0; - /* - * Circle throuch all the connection of that component. If we find - * an orphan connection whose name matches @csdev, link it. - */ - for (i = 0; i < i_csdev->nr_outport; i++) { - conn = &i_csdev->conns[i]; - - /* We have found at least one orphan connection */ - if (conn->child_dev == NULL) { - /* Does it match this newly added device? */ - if (conn->child_name && - !strcmp(dev_name(&csdev->dev), conn->child_name)) { - conn->child_dev = csdev; - } else { - /* This component still has an orphan */ - still_orphan = true; - } - } - } - - i_csdev->orphan = still_orphan; - - /* - * Returning '0' ensures that all known component on the - * bus will be checked. - */ - return 0; -} - -static void coresight_fixup_orphan_conns(struct coresight_device *csdev) -{ - /* - * No need to check for a return value as orphan connection(s) - * are hooked-up with each newly added component. - */ - bus_for_each_dev(&coresight_bustype, NULL, - csdev, coresight_orphan_match); -} - - -static void coresight_fixup_device_conns(struct coresight_device *csdev) -{ - int i; - - for (i = 0; i < csdev->nr_outport; i++) { - struct coresight_connection *conn = &csdev->conns[i]; - struct device *dev = NULL; - - if (conn->child_name) - dev = bus_find_device_by_name(&coresight_bustype, NULL, - conn->child_name); - if (dev) { - conn->child_dev = to_coresight_device(dev); - /* and put reference from 'bus_find_device()' */ - put_device(dev); - } else { - csdev->orphan = true; - conn->child_dev = NULL; - } - } -} - -static int coresight_remove_match(struct device *dev, void *data) -{ - int i; - struct coresight_device *csdev, *iterator; - struct coresight_connection *conn; - - csdev = data; - iterator = to_coresight_device(dev); - - /* No need to check oneself */ - if (csdev == iterator) - return 0; - - /* - * Circle throuch all the connection of that component. If we find - * a connection whose name matches @csdev, remove it. - */ - for (i = 0; i < iterator->nr_outport; i++) { - conn = &iterator->conns[i]; - - if (conn->child_dev == NULL) - continue; - - if (!strcmp(dev_name(&csdev->dev), conn->child_name)) { - iterator->orphan = true; - conn->child_dev = NULL; - /* No need to continue */ - break; - } - } - - /* - * Returning '0' ensures that all known component on the - * bus will be checked. - */ - return 0; -} - -static void coresight_remove_conns(struct coresight_device *csdev) -{ - bus_for_each_dev(&coresight_bustype, NULL, - csdev, coresight_remove_match); -} - -/** - * coresight_timeout - loop until a bit has changed to a specific state. - * @addr: base address of the area of interest. - * @offset: address of a register, starting from @addr. - * @position: the position of the bit of interest. - * @value: the value the bit should have. - * - * Return: 0 as soon as the bit has taken the desired state or -EAGAIN if - * TIMEOUT_US has elapsed, which ever happens first. - */ - -int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) -{ - int i; - u32 val; - - for (i = TIMEOUT_US; i > 0; i--) { - val = __raw_readl(addr + offset); - /* waiting on the bit to go from 0 to 1 */ - if (value) { - if (val & BIT(position)) - return 0; - /* waiting on the bit to go from 1 to 0 */ - } else { - if (!(val & BIT(position))) - return 0; - } - - /* - * Delay is arbitrary - the specification doesn't say how long - * we are expected to wait. Extra check required to make sure - * we don't wait needlessly on the last iteration. - */ - if (i - 1) - udelay(1); - } - - return -EAGAIN; -} - -struct bus_type coresight_bustype = { - .name = "coresight", -}; - -static int __init coresight_init(void) -{ - return bus_register(&coresight_bustype); -} -postcore_initcall(coresight_init); - -struct coresight_device *coresight_register(struct coresight_desc *desc) -{ - int ret; - int link_subtype; - int nr_refcnts = 1; - atomic_t *refcnts = NULL; - struct coresight_device *csdev; - - csdev = kzalloc(sizeof(*csdev), GFP_KERNEL); - if (!csdev) { - ret = -ENOMEM; - goto err_out; - } - - if (desc->type == CORESIGHT_DEV_TYPE_LINK || - desc->type == CORESIGHT_DEV_TYPE_LINKSINK) { - link_subtype = desc->subtype.link_subtype; - - if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_MERG) - nr_refcnts = desc->pdata->nr_inport; - else if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT) - nr_refcnts = desc->pdata->nr_outport; - } - - refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL); - if (!refcnts) { - ret = -ENOMEM; - goto err_free_csdev; - } - - csdev->refcnt = refcnts; - - csdev->nr_inport = desc->pdata->nr_inport; - csdev->nr_outport = desc->pdata->nr_outport; - - csdev->conns = desc->pdata->conns; - - csdev->type = desc->type; - csdev->subtype = desc->subtype; - csdev->ops = desc->ops; - csdev->orphan = false; - - csdev->dev.type = &coresight_dev_type[desc->type]; - csdev->dev.groups = desc->groups; - csdev->dev.parent = desc->dev; - csdev->dev.release = coresight_device_release; - csdev->dev.bus = &coresight_bustype; - dev_set_name(&csdev->dev, "%s", desc->pdata->name); - - ret = device_register(&csdev->dev); - if (ret) { - put_device(&csdev->dev); - /* - * All resources are free'd explicitly via - * coresight_device_release(), triggered from put_device(). - */ - goto err_out; - } - - mutex_lock(&coresight_mutex); - - coresight_fixup_device_conns(csdev); - coresight_fixup_orphan_conns(csdev); - - mutex_unlock(&coresight_mutex); - - return csdev; - -err_free_csdev: - kfree(csdev); -err_out: - return ERR_PTR(ret); -} -EXPORT_SYMBOL_GPL(coresight_register); - -void coresight_unregister(struct coresight_device *csdev) -{ - /* Remove references of that device in the topology */ - coresight_remove_conns(csdev); - device_unregister(&csdev->dev); -} -EXPORT_SYMBOL_GPL(coresight_unregister); diff --git a/drivers/hwtracing/coresight/of_coresight.c b/drivers/hwtracing/coresight/of_coresight.c deleted file mode 100644 index 89092f83567e..000000000000 --- a/drivers/hwtracing/coresight/of_coresight.c +++ /dev/null @@ -1,297 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2012, The Linux Foundation. All rights reserved. - */ - -#include <linux/types.h> -#include <linux/err.h> -#include <linux/slab.h> -#include <linux/clk.h> -#include <linux/of.h> -#include <linux/of_address.h> -#include <linux/of_graph.h> -#include <linux/of_platform.h> -#include <linux/platform_device.h> -#include <linux/amba/bus.h> -#include <linux/coresight.h> -#include <linux/cpumask.h> -#include <asm/smp_plat.h> - - -static int of_dev_node_match(struct device *dev, void *data) -{ - return dev->of_node == data; -} - -static struct device * -of_coresight_get_endpoint_device(struct device_node *endpoint) -{ - struct device *dev = NULL; - - /* - * If we have a non-configurable replicator, it will be found on the - * platform bus. - */ - dev = bus_find_device(&platform_bus_type, NULL, - endpoint, of_dev_node_match); - if (dev) - return dev; - - /* - * We have a configurable component - circle through the AMBA bus - * looking for the device that matches the endpoint node. - */ - return bus_find_device(&amba_bustype, NULL, - endpoint, of_dev_node_match); -} - -static inline bool of_coresight_legacy_ep_is_input(struct device_node *ep) -{ - return of_property_read_bool(ep, "slave-mode"); -} - -static void of_coresight_get_ports_legacy(const struct device_node *node, - int *nr_inport, int *nr_outport) -{ - struct device_node *ep = NULL; - int in = 0, out = 0; - - do { - ep = of_graph_get_next_endpoint(node, ep); - if (!ep) - break; - - if (of_coresight_legacy_ep_is_input(ep)) - in++; - else - out++; - - } while (ep); - - *nr_inport = in; - *nr_outport = out; -} - -static struct device_node *of_coresight_get_port_parent(struct device_node *ep) -{ - struct device_node *parent = of_graph_get_port_parent(ep); - - /* - * Skip one-level up to the real device node, if we - * are using the new bindings. - */ - if (!of_node_cmp(parent->name, "in-ports") || - !of_node_cmp(parent->name, "out-ports")) - parent = of_get_next_parent(parent); - - return parent; -} - -static inline struct device_node * -of_coresight_get_input_ports_node(const struct device_node *node) -{ - return of_get_child_by_name(node, "in-ports"); -} - -static inline struct device_node * -of_coresight_get_output_ports_node(const struct device_node *node) -{ - return of_get_child_by_name(node, "out-ports"); -} - -static inline int -of_coresight_count_ports(struct device_node *port_parent) -{ - int i = 0; - struct device_node *ep = NULL; - - while ((ep = of_graph_get_next_endpoint(port_parent, ep))) - i++; - return i; -} - -static void of_coresight_get_ports(const struct device_node *node, - int *nr_inport, int *nr_outport) -{ - struct device_node *input_ports = NULL, *output_ports = NULL; - - input_ports = of_coresight_get_input_ports_node(node); - output_ports = of_coresight_get_output_ports_node(node); - - if (input_ports || output_ports) { - if (input_ports) { - *nr_inport = of_coresight_count_ports(input_ports); - of_node_put(input_ports); - } - if (output_ports) { - *nr_outport = of_coresight_count_ports(output_ports); - of_node_put(output_ports); - } - } else { - /* Fall back to legacy DT bindings parsing */ - of_coresight_get_ports_legacy(node, nr_inport, nr_outport); - } -} - -static int of_coresight_alloc_memory(struct device *dev, - struct coresight_platform_data *pdata) -{ - if (pdata->nr_outport) { - pdata->conns = devm_kzalloc(dev, pdata->nr_outport * - sizeof(*pdata->conns), - GFP_KERNEL); - if (!pdata->conns) - return -ENOMEM; - } - - return 0; -} - -int of_coresight_get_cpu(const struct device_node *node) -{ - int cpu; - struct device_node *dn; - - dn = of_parse_phandle(node, "cpu", 0); - /* Affinity defaults to CPU0 */ - if (!dn) - return 0; - cpu = of_cpu_node_to_id(dn); - of_node_put(dn); - - /* Affinity to CPU0 if no cpu nodes are found */ - return (cpu < 0) ? 0 : cpu; -} -EXPORT_SYMBOL_GPL(of_coresight_get_cpu); - -/* - * of_coresight_parse_endpoint : Parse the given output endpoint @ep - * and fill the connection information in @conn - * - * Parses the local port, remote device name and the remote port. - * - * Returns : - * 1 - If the parsing is successful and a connection record - * was created for an output connection. - * 0 - If the parsing completed without any fatal errors. - * -Errno - Fatal error, abort the scanning. - */ -static int of_coresight_parse_endpoint(struct device *dev, - struct device_node *ep, - struct coresight_connection *conn) -{ - int ret = 0; - struct of_endpoint endpoint, rendpoint; - struct device_node *rparent = NULL; - struct device_node *rep = NULL; - struct device *rdev = NULL; - - do { - /* Parse the local port details */ - if (of_graph_parse_endpoint(ep, &endpoint)) - break; - /* - * Get a handle on the remote endpoint and the device it is - * attached to. - */ - rep = of_graph_get_remote_endpoint(ep); - if (!rep) - break; - rparent = of_coresight_get_port_parent(rep); - if (!rparent) - break; - if (of_graph_parse_endpoint(rep, &rendpoint)) - break; - - /* If the remote device is not available, defer probing */ - rdev = of_coresight_get_endpoint_device(rparent); - if (!rdev) { - ret = -EPROBE_DEFER; - break; - } - - conn->outport = endpoint.port; - conn->child_name = devm_kstrdup(dev, - dev_name(rdev), - GFP_KERNEL); - conn->child_port = rendpoint.port; - /* Connection record updated */ - ret = 1; - } while (0); - - of_node_put(rparent); - of_node_put(rep); - put_device(rdev); - - return ret; -} - -struct coresight_platform_data * -of_get_coresight_platform_data(struct device *dev, - const struct device_node *node) -{ - int ret = 0; - struct coresight_platform_data *pdata; - struct coresight_connection *conn; - struct device_node *ep = NULL; - const struct device_node *parent = NULL; - bool legacy_binding = false; - - pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return ERR_PTR(-ENOMEM); - - /* Use device name as sysfs handle */ - pdata->name = dev_name(dev); - pdata->cpu = of_coresight_get_cpu(node); - - /* Get the number of input and output port for this component */ - of_coresight_get_ports(node, &pdata->nr_inport, &pdata->nr_outport); - - /* If there are no output connections, we are done */ - if (!pdata->nr_outport) - return pdata; - - ret = of_coresight_alloc_memory(dev, pdata); - if (ret) - return ERR_PTR(ret); - - parent = of_coresight_get_output_ports_node(node); - /* - * If the DT uses obsoleted bindings, the ports are listed - * under the device and we need to filter out the input - * ports. - */ - if (!parent) { - legacy_binding = true; - parent = node; - dev_warn_once(dev, "Uses obsolete Coresight DT bindings\n"); - } - - conn = pdata->conns; - - /* Iterate through each output port to discover topology */ - while ((ep = of_graph_get_next_endpoint(parent, ep))) { - /* - * Legacy binding mixes input/output ports under the - * same parent. So, skip the input ports if we are dealing - * with legacy binding, as they processed with their - * connected output ports. - */ - if (legacy_binding && of_coresight_legacy_ep_is_input(ep)) - continue; - - ret = of_coresight_parse_endpoint(dev, ep, conn); - switch (ret) { - case 1: - conn++; /* Fall through */ - case 0: - break; - default: - return ERR_PTR(ret); - } - } - - return pdata; -} -EXPORT_SYMBOL_GPL(of_get_coresight_platform_data); diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c new file mode 100644 index 000000000000..8f7922a5e534 --- /dev/null +++ b/drivers/hwtracing/coresight/ultrasoc-smb.c @@ -0,0 +1,611 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Siemens System Memory Buffer driver. + * Copyright(c) 2022, HiSilicon Limited. + */ + +#include <linux/atomic.h> +#include <linux/acpi.h> +#include <linux/circ_buf.h> +#include <linux/err.h> +#include <linux/fs.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/platform_device.h> + +#include "coresight-etm-perf.h" +#include "coresight-priv.h" +#include "ultrasoc-smb.h" + +DEFINE_CORESIGHT_DEVLIST(sink_devs, "ultra_smb"); + +#define ULTRASOC_SMB_DSM_UUID "82ae1283-7f6a-4cbe-aa06-53e8fb24db18" + +static bool smb_buffer_not_empty(struct smb_drv_data *drvdata) +{ + u32 buf_status = readl(drvdata->base + SMB_LB_INT_STS_REG); + + return FIELD_GET(SMB_LB_INT_STS_NOT_EMPTY_MSK, buf_status); +} + +static void smb_update_data_size(struct smb_drv_data *drvdata) +{ + struct smb_data_buffer *sdb = &drvdata->sdb; + u32 buf_wrptr; + + buf_wrptr = readl(drvdata->base + SMB_LB_WR_ADDR_REG) - + sdb->buf_hw_base; + + /* Buffer is full */ + if (buf_wrptr == sdb->buf_rdptr && smb_buffer_not_empty(drvdata)) { + sdb->data_size = sdb->buf_size; + return; + } + + /* The buffer mode is circular buffer mode */ + sdb->data_size = CIRC_CNT(buf_wrptr, sdb->buf_rdptr, + sdb->buf_size); +} + +/* + * The read pointer adds @nbytes bytes (may round up to the beginning) + * after the data is read or discarded, while needing to update the + * available data size. + */ +static void smb_update_read_ptr(struct smb_drv_data *drvdata, u32 nbytes) +{ + struct smb_data_buffer *sdb = &drvdata->sdb; + + sdb->buf_rdptr += nbytes; + sdb->buf_rdptr %= sdb->buf_size; + writel(sdb->buf_hw_base + sdb->buf_rdptr, + drvdata->base + SMB_LB_RD_ADDR_REG); + + sdb->data_size -= nbytes; +} + +static void smb_reset_buffer(struct smb_drv_data *drvdata) +{ + struct smb_data_buffer *sdb = &drvdata->sdb; + u32 write_ptr; + + /* + * We must flush and discard any data left in hardware path + * to avoid corrupting the next session. + * Note: The write pointer will never exceed the read pointer. + */ + writel(SMB_LB_PURGE_PURGED, drvdata->base + SMB_LB_PURGE_REG); + + /* Reset SMB logical buffer status flags */ + writel(SMB_LB_INT_STS_RESET, drvdata->base + SMB_LB_INT_STS_REG); + + write_ptr = readl(drvdata->base + SMB_LB_WR_ADDR_REG); + + /* Do nothing, not data left in hardware path */ + if (!write_ptr || write_ptr == sdb->buf_rdptr + sdb->buf_hw_base) + return; + + /* + * The SMB_LB_WR_ADDR_REG register is read-only, + * Synchronize the read pointer to write pointer. + */ + writel(write_ptr, drvdata->base + SMB_LB_RD_ADDR_REG); + sdb->buf_rdptr = write_ptr - sdb->buf_hw_base; +} + +static int smb_open(struct inode *inode, struct file *file) +{ + struct smb_drv_data *drvdata = container_of(file->private_data, + struct smb_drv_data, miscdev); + + guard(raw_spinlock)(&drvdata->spinlock); + + if (drvdata->reading) + return -EBUSY; + + if (drvdata->csdev->refcnt) + return -EBUSY; + + smb_update_data_size(drvdata); + drvdata->reading = true; + + return 0; +} + +static ssize_t smb_read(struct file *file, char __user *data, size_t len, + loff_t *ppos) +{ + struct smb_drv_data *drvdata = container_of(file->private_data, + struct smb_drv_data, miscdev); + struct smb_data_buffer *sdb = &drvdata->sdb; + struct device *dev = &drvdata->csdev->dev; + ssize_t to_copy = 0; + + if (!len) + return 0; + + if (!sdb->data_size) + return 0; + + to_copy = min(sdb->data_size, len); + + /* Copy parts of trace data when read pointer wrap around SMB buffer */ + if (sdb->buf_rdptr + to_copy > sdb->buf_size) + to_copy = sdb->buf_size - sdb->buf_rdptr; + + if (copy_to_user(data, sdb->buf_base + sdb->buf_rdptr, to_copy)) { + dev_dbg(dev, "Failed to copy data to user\n"); + return -EFAULT; + } + + *ppos += to_copy; + smb_update_read_ptr(drvdata, to_copy); + if (!sdb->data_size) + smb_reset_buffer(drvdata); + + dev_dbg(dev, "%zu bytes copied\n", to_copy); + return to_copy; +} + +static int smb_release(struct inode *inode, struct file *file) +{ + struct smb_drv_data *drvdata = container_of(file->private_data, + struct smb_drv_data, miscdev); + + guard(raw_spinlock)(&drvdata->spinlock); + drvdata->reading = false; + + return 0; +} + +static const struct file_operations smb_fops = { + .owner = THIS_MODULE, + .open = smb_open, + .read = smb_read, + .release = smb_release, +}; + +static ssize_t buf_size_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(dev->parent); + + return sysfs_emit(buf, "0x%lx\n", drvdata->sdb.buf_size); +} +static DEVICE_ATTR_RO(buf_size); + +static struct attribute *smb_sink_attrs[] = { + coresight_simple_reg32(read_pos, SMB_LB_RD_ADDR_REG), + coresight_simple_reg32(write_pos, SMB_LB_WR_ADDR_REG), + coresight_simple_reg32(buf_status, SMB_LB_INT_STS_REG), + &dev_attr_buf_size.attr, + NULL +}; + +static const struct attribute_group smb_sink_group = { + .attrs = smb_sink_attrs, + .name = "mgmt", +}; + +static const struct attribute_group *smb_sink_groups[] = { + &smb_sink_group, + NULL +}; + +static void smb_enable_hw(struct smb_drv_data *drvdata) +{ + writel(SMB_GLB_EN_HW_ENABLE, drvdata->base + SMB_GLB_EN_REG); +} + +static void smb_disable_hw(struct smb_drv_data *drvdata) +{ + writel(0x0, drvdata->base + SMB_GLB_EN_REG); +} + +static void smb_enable_sysfs(struct coresight_device *csdev) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); + + if (coresight_get_mode(csdev) != CS_MODE_DISABLED) + return; + + smb_enable_hw(drvdata); + coresight_set_mode(csdev, CS_MODE_SYSFS); +} + +static int smb_enable_perf(struct coresight_device *csdev, + struct coresight_path *path) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_output_handle *handle = path->handle; + struct cs_buffers *buf = etm_perf_sink_config(handle); + pid_t pid; + + if (!buf) + return -EINVAL; + + /* Get a handle on the pid of the target process */ + pid = buf->pid; + + /* Device is already in used by other session */ + if (drvdata->pid != -1 && drvdata->pid != pid) + return -EBUSY; + + if (drvdata->pid == -1) { + smb_enable_hw(drvdata); + drvdata->pid = pid; + coresight_set_mode(csdev, CS_MODE_PERF); + } + + return 0; +} + +static int smb_enable(struct coresight_device *csdev, enum cs_mode mode, + struct coresight_path *path) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); + int ret = 0; + + guard(raw_spinlock)(&drvdata->spinlock); + + /* Do nothing, the trace data is reading by other interface now */ + if (drvdata->reading) + return -EBUSY; + + /* Do nothing, the SMB is already enabled as other mode */ + if (coresight_get_mode(csdev) != CS_MODE_DISABLED && + coresight_get_mode(csdev) != mode) + return -EBUSY; + + switch (mode) { + case CS_MODE_SYSFS: + smb_enable_sysfs(csdev); + break; + case CS_MODE_PERF: + ret = smb_enable_perf(csdev, path); + break; + default: + ret = -EINVAL; + } + + if (ret) + return ret; + + csdev->refcnt++; + dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n"); + + return ret; +} + +static int smb_disable(struct coresight_device *csdev) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); + + guard(raw_spinlock)(&drvdata->spinlock); + + if (drvdata->reading) + return -EBUSY; + + csdev->refcnt--; + if (csdev->refcnt) + return -EBUSY; + + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(coresight_get_mode(csdev) == CS_MODE_DISABLED); + + smb_disable_hw(drvdata); + + /* Dissociate from the target process. */ + drvdata->pid = -1; + coresight_set_mode(csdev, CS_MODE_DISABLED); + dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n"); + + return 0; +} + +static void *smb_alloc_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite) +{ + struct cs_buffers *buf; + int node; + + node = (event->cpu == -1) ? NUMA_NO_NODE : cpu_to_node(event->cpu); + buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->snapshot = overwrite; + buf->nr_pages = nr_pages; + buf->data_pages = pages; + buf->pid = task_pid_nr(event->owner); + + return buf; +} + +static void smb_free_buffer(void *config) +{ + struct cs_buffers *buf = config; + + kfree(buf); +} + +static void smb_sync_perf_buffer(struct smb_drv_data *drvdata, + struct cs_buffers *buf, + unsigned long head) +{ + struct smb_data_buffer *sdb = &drvdata->sdb; + char **dst_pages = (char **)buf->data_pages; + unsigned long to_copy; + long pg_idx, pg_offset; + + pg_idx = head >> PAGE_SHIFT; + pg_offset = head & (PAGE_SIZE - 1); + + while (sdb->data_size) { + unsigned long pg_space = PAGE_SIZE - pg_offset; + + to_copy = min(sdb->data_size, pg_space); + + /* Copy parts of trace data when read pointer wrap around */ + if (sdb->buf_rdptr + to_copy > sdb->buf_size) + to_copy = sdb->buf_size - sdb->buf_rdptr; + + memcpy(dst_pages[pg_idx] + pg_offset, + sdb->buf_base + sdb->buf_rdptr, to_copy); + + pg_offset += to_copy; + if (pg_offset >= PAGE_SIZE) { + pg_offset = 0; + pg_idx++; + pg_idx %= buf->nr_pages; + } + smb_update_read_ptr(drvdata, to_copy); + } + + smb_reset_buffer(drvdata); +} + +static unsigned long smb_update_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config) +{ + struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); + struct smb_data_buffer *sdb = &drvdata->sdb; + struct cs_buffers *buf = sink_config; + unsigned long data_size; + bool lost = false; + + if (!buf) + return 0; + + guard(raw_spinlock)(&drvdata->spinlock); + + /* Don't do anything if another tracer is using this sink. */ + if (csdev->refcnt != 1) + return 0; + + smb_disable_hw(drvdata); + smb_update_data_size(drvdata); + + /* + * The SMB buffer may be bigger than the space available in the + * perf ring buffer (handle->size). If so advance the offset so + * that we get the latest trace data. + */ + if (sdb->data_size > handle->size) { + smb_update_read_ptr(drvdata, sdb->data_size - handle->size); + lost = true; + } + + data_size = sdb->data_size; + smb_sync_perf_buffer(drvdata, buf, handle->head); + if (!buf->snapshot && lost) + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); + + return data_size; +} + +static const struct coresight_ops_sink smb_cs_ops = { + .enable = smb_enable, + .disable = smb_disable, + .alloc_buffer = smb_alloc_buffer, + .free_buffer = smb_free_buffer, + .update_buffer = smb_update_buffer, +}; + +static const struct coresight_ops cs_ops = { + .sink_ops = &smb_cs_ops, +}; + +static int smb_init_data_buffer(struct platform_device *pdev, + struct smb_data_buffer *sdb) +{ + struct resource *res; + void *base; + + res = platform_get_resource(pdev, IORESOURCE_MEM, SMB_BUF_ADDR_RES); + if (!res) { + dev_err(&pdev->dev, "SMB device failed to get resource\n"); + return -EINVAL; + } + + sdb->buf_rdptr = 0; + sdb->buf_hw_base = FIELD_GET(SMB_BUF_ADDR_LO_MSK, res->start); + sdb->buf_size = resource_size(res); + if (sdb->buf_size == 0) + return -EINVAL; + + /* + * This is a chunk of memory, use classic mapping with better + * performance. + */ + base = devm_memremap(&pdev->dev, sdb->buf_hw_base, sdb->buf_size, + MEMREMAP_WB); + if (IS_ERR(base)) + return PTR_ERR(base); + + sdb->buf_base = base; + + return 0; +} + +static void smb_init_hw(struct smb_drv_data *drvdata) +{ + smb_disable_hw(drvdata); + + writel(SMB_LB_CFG_LO_DEFAULT, drvdata->base + SMB_LB_CFG_LO_REG); + writel(SMB_LB_CFG_HI_DEFAULT, drvdata->base + SMB_LB_CFG_HI_REG); + writel(SMB_GLB_CFG_DEFAULT, drvdata->base + SMB_GLB_CFG_REG); + writel(SMB_GLB_INT_CFG, drvdata->base + SMB_GLB_INT_REG); + writel(SMB_LB_INT_CTRL_CFG, drvdata->base + SMB_LB_INT_CTRL_REG); +} + +static int smb_register_sink(struct platform_device *pdev, + struct smb_drv_data *drvdata) +{ + struct coresight_platform_data *pdata = NULL; + struct coresight_desc desc = { 0 }; + int ret; + + pdata = coresight_get_platform_data(&pdev->dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + desc.ops = &cs_ops; + desc.pdata = pdata; + desc.dev = &pdev->dev; + desc.groups = smb_sink_groups; + desc.name = coresight_alloc_device_name(&sink_devs, &pdev->dev); + if (!desc.name) { + dev_err(&pdev->dev, "Failed to alloc coresight device name"); + return -ENOMEM; + } + desc.access = CSDEV_ACCESS_IOMEM(drvdata->base); + + drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) + return PTR_ERR(drvdata->csdev); + + drvdata->miscdev.name = desc.name; + drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; + drvdata->miscdev.fops = &smb_fops; + ret = misc_register(&drvdata->miscdev); + if (ret) { + coresight_unregister(drvdata->csdev); + dev_err(&pdev->dev, "Failed to register misc, ret=%d\n", ret); + } + + return ret; +} + +static void smb_unregister_sink(struct smb_drv_data *drvdata) +{ + misc_deregister(&drvdata->miscdev); + coresight_unregister(drvdata->csdev); +} + +static int smb_config_inport(struct device *dev, bool enable) +{ + u64 func = enable ? 1 : 0; + union acpi_object *obj; + guid_t guid; + u64 rev = 0; + + /* + * Using DSM calls to enable/disable ultrasoc hardwares on + * tracing path, to prevent ultrasoc packet format being exposed. + */ + if (guid_parse(ULTRASOC_SMB_DSM_UUID, &guid)) { + dev_err(dev, "Get GUID failed\n"); + return -EINVAL; + } + + obj = acpi_evaluate_dsm(ACPI_HANDLE(dev), &guid, rev, func, NULL); + if (!obj) { + dev_err(dev, "ACPI handle failed\n"); + return -ENODEV; + } + + ACPI_FREE(obj); + + return 0; +} + +static int smb_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct smb_drv_data *drvdata; + int ret; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + drvdata->base = devm_platform_ioremap_resource(pdev, SMB_REG_ADDR_RES); + if (IS_ERR(drvdata->base)) { + dev_err(dev, "Failed to ioremap resource\n"); + return PTR_ERR(drvdata->base); + } + + smb_init_hw(drvdata); + + ret = smb_init_data_buffer(pdev, &drvdata->sdb); + if (ret) { + dev_err(dev, "Failed to init buffer, ret = %d\n", ret); + return ret; + } + + ret = smb_config_inport(dev, true); + if (ret) + return ret; + + smb_reset_buffer(drvdata); + platform_set_drvdata(pdev, drvdata); + raw_spin_lock_init(&drvdata->spinlock); + drvdata->pid = -1; + + ret = smb_register_sink(pdev, drvdata); + if (ret) { + smb_config_inport(&pdev->dev, false); + dev_err(dev, "Failed to register SMB sink\n"); + return ret; + } + + return 0; +} + +static void smb_remove(struct platform_device *pdev) +{ + struct smb_drv_data *drvdata = platform_get_drvdata(pdev); + + smb_unregister_sink(drvdata); + + smb_config_inport(&pdev->dev, false); +} + +#ifdef CONFIG_ACPI +static const struct acpi_device_id ultrasoc_smb_acpi_match[] = { + {"HISI03A1", 0, 0, 0}, + {} +}; +MODULE_DEVICE_TABLE(acpi, ultrasoc_smb_acpi_match); +#endif + +static struct platform_driver smb_driver = { + .driver = { + .name = "ultrasoc-smb", + .acpi_match_table = ACPI_PTR(ultrasoc_smb_acpi_match), + .suppress_bind_attrs = true, + }, + .probe = smb_probe, + .remove = smb_remove, +}; +module_platform_driver(smb_driver); + +MODULE_DESCRIPTION("UltraSoc SMB CoreSight driver"); +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_AUTHOR("Jonathan Zhou <jonathan.zhouwen@huawei.com>"); +MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>"); diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.h b/drivers/hwtracing/coresight/ultrasoc-smb.h new file mode 100644 index 000000000000..323f0ccb6878 --- /dev/null +++ b/drivers/hwtracing/coresight/ultrasoc-smb.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Siemens System Memory Buffer driver. + * Copyright(c) 2022, HiSilicon Limited. + */ + +#ifndef _ULTRASOC_SMB_H +#define _ULTRASOC_SMB_H + +#include <linux/bitfield.h> +#include <linux/miscdevice.h> +#include <linux/spinlock.h> + +/* Offset of SMB global registers */ +#define SMB_GLB_CFG_REG 0x00 +#define SMB_GLB_EN_REG 0x04 +#define SMB_GLB_INT_REG 0x08 + +/* Offset of SMB logical buffer registers */ +#define SMB_LB_CFG_LO_REG 0x40 +#define SMB_LB_CFG_HI_REG 0x44 +#define SMB_LB_INT_CTRL_REG 0x48 +#define SMB_LB_INT_STS_REG 0x4c +#define SMB_LB_RD_ADDR_REG 0x5c +#define SMB_LB_WR_ADDR_REG 0x60 +#define SMB_LB_PURGE_REG 0x64 + +/* Set global config register */ +#define SMB_GLB_CFG_BURST_LEN_MSK GENMASK(11, 4) +#define SMB_GLB_CFG_IDLE_PRD_MSK GENMASK(15, 12) +#define SMB_GLB_CFG_MEM_WR_MSK GENMASK(21, 16) +#define SMB_GLB_CFG_MEM_RD_MSK GENMASK(27, 22) +#define SMB_GLB_CFG_DEFAULT (FIELD_PREP(SMB_GLB_CFG_BURST_LEN_MSK, 0xf) | \ + FIELD_PREP(SMB_GLB_CFG_IDLE_PRD_MSK, 0xf) | \ + FIELD_PREP(SMB_GLB_CFG_MEM_WR_MSK, 0x3) | \ + FIELD_PREP(SMB_GLB_CFG_MEM_RD_MSK, 0x1b)) + +#define SMB_GLB_EN_HW_ENABLE BIT(0) + +/* Set global interrupt control register */ +#define SMB_GLB_INT_EN BIT(0) +#define SMB_GLB_INT_PULSE BIT(1) /* Interrupt type: 1 - Pulse */ +#define SMB_GLB_INT_ACT_H BIT(2) /* Interrupt polarity: 1 - Active high */ +#define SMB_GLB_INT_CFG (SMB_GLB_INT_EN | SMB_GLB_INT_PULSE | \ + SMB_GLB_INT_ACT_H) + +/* Set logical buffer config register lower 32 bits */ +#define SMB_LB_CFG_LO_EN BIT(0) +#define SMB_LB_CFG_LO_SINGLE_END BIT(1) +#define SMB_LB_CFG_LO_INIT BIT(8) +#define SMB_LB_CFG_LO_CONT BIT(11) +#define SMB_LB_CFG_LO_FLOW_MSK GENMASK(19, 16) +#define SMB_LB_CFG_LO_DEFAULT (SMB_LB_CFG_LO_EN | SMB_LB_CFG_LO_SINGLE_END | \ + SMB_LB_CFG_LO_INIT | SMB_LB_CFG_LO_CONT | \ + FIELD_PREP(SMB_LB_CFG_LO_FLOW_MSK, 0xf)) + +/* Set logical buffer config register upper 32 bits */ +#define SMB_LB_CFG_HI_RANGE_UP_MSK GENMASK(15, 8) +#define SMB_LB_CFG_HI_DEFAULT FIELD_PREP(SMB_LB_CFG_HI_RANGE_UP_MSK, 0xff) + +/* + * Set logical buffer interrupt control register. + * The register control the validity of both real-time events and + * interrupts. When logical buffer status changes causes to issue + * an interrupt at the same time as it issues a real-time event. + * Real-time events are used in SMB driver, which needs to get the buffer + * status. Interrupts are used in debugger mode. + * SMB_LB_INT_CTRL_BUF_NOTE_MASK control which events flags or interrupts + * are valid. + */ +#define SMB_LB_INT_CTRL_EN BIT(0) +#define SMB_LB_INT_CTRL_BUF_NOTE_MSK GENMASK(11, 8) +#define SMB_LB_INT_CTRL_CFG (SMB_LB_INT_CTRL_EN | \ + FIELD_PREP(SMB_LB_INT_CTRL_BUF_NOTE_MSK, 0xf)) + +/* Set logical buffer interrupt status register */ +#define SMB_LB_INT_STS_NOT_EMPTY_MSK BIT(0) +#define SMB_LB_INT_STS_BUF_RESET_MSK GENMASK(3, 0) +#define SMB_LB_INT_STS_RESET FIELD_PREP(SMB_LB_INT_STS_BUF_RESET_MSK, 0xf) + +#define SMB_LB_PURGE_PURGED BIT(0) + +#define SMB_REG_ADDR_RES 0 +#define SMB_BUF_ADDR_RES 1 +#define SMB_BUF_ADDR_LO_MSK GENMASK(31, 0) + +/** + * struct smb_data_buffer - Details of the buffer used by SMB + * @buf_base: Memory mapped base address of SMB. + * @buf_hw_base: SMB buffer start Physical base address, only used 32bits. + * @buf_size: Size of the buffer. + * @data_size: Size of the available trace data for SMB. + * @buf_rdptr: Current read position (index) within the buffer. + */ +struct smb_data_buffer { + void *buf_base; + u32 buf_hw_base; + unsigned long buf_size; + unsigned long data_size; + unsigned long buf_rdptr; +}; + +/** + * struct smb_drv_data - specifics associated to an SMB component + * @base: Memory mapped base address for SMB component. + * @csdev: Component vitals needed by the framework. + * @sdb: Data buffer for SMB. + * @miscdev: Specifics to handle "/dev/xyz.smb" entry. + * @spinlock: Control data access to one at a time. + * @reading: Synchronise user space access to SMB buffer. + * @pid: Process ID of the process being monitored by the + * session that is using this component. + */ +struct smb_drv_data { + void __iomem *base; + struct coresight_device *csdev; + struct smb_data_buffer sdb; + struct miscdevice miscdev; + raw_spinlock_t spinlock; + bool reading; + pid_t pid; +}; + +#endif diff --git a/drivers/hwtracing/intel_th/Kconfig b/drivers/hwtracing/intel_th/Kconfig index ca0527d588e9..4f7d2b6d79e2 100644 --- a/drivers/hwtracing/intel_th/Kconfig +++ b/drivers/hwtracing/intel_th/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config INTEL_TH tristate "Intel(R) Trace Hub controller" depends on HAS_DMA && HAS_IOMEM @@ -59,6 +60,7 @@ config INTEL_TH_STH config INTEL_TH_MSU tristate "Intel(R) Trace Hub Memory Storage Unit" + depends on MMU help Memory Storage Unit (MSU) trace output device enables storing STP traces to system memory. It supports single diff --git a/drivers/hwtracing/intel_th/Makefile b/drivers/hwtracing/intel_th/Makefile index d9252fa8d9ca..b63eb8f309ad 100644 --- a/drivers/hwtracing/intel_th/Makefile +++ b/drivers/hwtracing/intel_th/Makefile @@ -20,3 +20,6 @@ intel_th_msu-y := msu.o obj-$(CONFIG_INTEL_TH_PTI) += intel_th_pti.o intel_th_pti-y := pti.o + +obj-$(CONFIG_INTEL_TH_MSU) += intel_th_msu_sink.o +intel_th_msu_sink-y := msu-sink.o diff --git a/drivers/hwtracing/intel_th/acpi.c b/drivers/hwtracing/intel_th/acpi.c index 87bc3744755f..d229324978bd 100644 --- a/drivers/hwtracing/intel_th/acpi.c +++ b/drivers/hwtracing/intel_th/acpi.c @@ -37,15 +37,21 @@ MODULE_DEVICE_TABLE(acpi, intel_th_acpi_ids); static int intel_th_acpi_probe(struct platform_device *pdev) { struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); + struct resource resource[TH_MMIO_END]; const struct acpi_device_id *id; struct intel_th *th; + int i, r; id = acpi_match_device(intel_th_acpi_ids, &pdev->dev); if (!id) return -ENODEV; - th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, - pdev->resource, pdev->num_resources, -1); + for (i = 0, r = 0; i < pdev->num_resources && r < TH_MMIO_END; i++) + if (pdev->resource[i].flags & + (IORESOURCE_IRQ | IORESOURCE_MEM)) + resource[r++] = pdev->resource[i]; + + th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, resource, r); if (IS_ERR(th)) return PTR_ERR(th); @@ -54,13 +60,11 @@ static int intel_th_acpi_probe(struct platform_device *pdev) return 0; } -static int intel_th_acpi_remove(struct platform_device *pdev) +static void intel_th_acpi_remove(struct platform_device *pdev) { struct intel_th *th = platform_get_drvdata(pdev); intel_th_free(th); - - return 0; } static struct platform_driver intel_th_acpi_driver = { diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index fc6b7f8b62fb..591b7c12aae5 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -26,9 +26,9 @@ module_param(host_mode, bool, 0444); static DEFINE_IDA(intel_th_ida); -static int intel_th_match(struct device *dev, struct device_driver *driver) +static int intel_th_match(struct device *dev, const struct device_driver *driver) { - struct intel_th_driver *thdrv = to_intel_th_driver(driver); + const struct intel_th_driver *thdrv = to_intel_th_driver(driver); struct intel_th_device *thdev = to_intel_th_device(dev); if (thdev->type == INTEL_TH_SWITCH && @@ -95,21 +95,23 @@ out_pm: static void intel_th_device_remove(struct intel_th_device *thdev); -static int intel_th_remove(struct device *dev) +static void intel_th_remove(struct device *dev) { struct intel_th_driver *thdrv = to_intel_th_driver(dev->driver); struct intel_th_device *thdev = to_intel_th_device(dev); struct intel_th_device *hub = to_intel_th_hub(thdev); - int err; if (thdev->type == INTEL_TH_SWITCH) { struct intel_th *th = to_intel_th(hub); int i, lowest; - /* disconnect outputs */ - err = device_for_each_child(dev, thdev, intel_th_child_remove); - if (err) - return err; + /* + * disconnect outputs + * + * intel_th_child_remove returns 0 unconditionally, so there is + * no need to check the return value of device_for_each_child. + */ + device_for_each_child(dev, thdev, intel_th_child_remove); /* * Remove outputs, that is, hub's children: they are created @@ -162,11 +164,9 @@ static int intel_th_remove(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); - - return 0; } -static struct bus_type intel_th_bus = { +static const struct bus_type intel_th_bus = { .name = "intel_th", .match = intel_th_match, .probe = intel_th_probe, @@ -180,16 +180,16 @@ static void intel_th_device_release(struct device *dev) intel_th_device_free(to_intel_th_device(dev)); } -static struct device_type intel_th_source_device_type = { +static const struct device_type intel_th_source_device_type = { .name = "intel_th_source_device", .release = intel_th_device_release, }; -static char *intel_th_output_devnode(struct device *dev, umode_t *mode, +static char *intel_th_output_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid) { - struct intel_th_device *thdev = to_intel_th_device(dev); - struct intel_th *th = to_intel_th(thdev); + const struct intel_th_device *thdev = to_intel_th_device(dev); + const struct intel_th *th = to_intel_th(thdev); char *node; if (thdev->id >= 0) @@ -215,6 +215,22 @@ static ssize_t port_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(port); +static void intel_th_trace_prepare(struct intel_th_device *thdev) +{ + struct intel_th_device *hub = to_intel_th_hub(thdev); + struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver); + + if (hub->type != INTEL_TH_SWITCH) + return; + + if (thdev->type != INTEL_TH_OUTPUT) + return; + + pm_runtime_get_sync(&thdev->dev); + hubdrv->prepare(hub, &thdev->output); + pm_runtime_put(&thdev->dev); +} + static int intel_th_output_activate(struct intel_th_device *thdev) { struct intel_th_driver *thdrv = @@ -235,6 +251,7 @@ static int intel_th_output_activate(struct intel_th_device *thdev) if (ret) goto fail_put; + intel_th_trace_prepare(thdev); if (thdrv->activate) ret = thdrv->activate(thdev); else @@ -316,19 +333,19 @@ static struct attribute *intel_th_output_attrs[] = { ATTRIBUTE_GROUPS(intel_th_output); -static struct device_type intel_th_output_device_type = { +static const struct device_type intel_th_output_device_type = { .name = "intel_th_output_device", .groups = intel_th_output_groups, .release = intel_th_device_release, .devnode = intel_th_output_devnode, }; -static struct device_type intel_th_switch_device_type = { +static const struct device_type intel_th_switch_device_type = { .name = "intel_th_switch_device", .release = intel_th_device_release, }; -static struct device_type *intel_th_device_type[] = { +static const struct device_type *intel_th_device_type[] = { [INTEL_TH_SOURCE] = &intel_th_source_device_type, [INTEL_TH_OUTPUT] = &intel_th_output_device_type, [INTEL_TH_SWITCH] = &intel_th_switch_device_type, @@ -422,6 +439,7 @@ static const struct intel_th_subdevice { unsigned nres; unsigned type; unsigned otype; + bool mknode; unsigned scrpd; int id; } intel_th_subdevices[] = { @@ -429,9 +447,9 @@ static const struct intel_th_subdevice { .nres = 1, .res = { { - /* Handle TSCU from GTH driver */ + /* Handle TSCU and CTS from GTH driver */ .start = REG_GTH_OFFSET, - .end = REG_TSCU_OFFSET + REG_TSCU_LENGTH - 1, + .end = REG_CTS_OFFSET + REG_CTS_LENGTH - 1, .flags = IORESOURCE_MEM, }, }, @@ -456,6 +474,7 @@ static const struct intel_th_subdevice { .name = "msc", .id = 0, .type = INTEL_TH_OUTPUT, + .mknode = true, .otype = GTH_MSU, .scrpd = SCRPD_MEM_IS_PRIM_DEST | SCRPD_MSC0_IS_ENABLED, }, @@ -476,6 +495,7 @@ static const struct intel_th_subdevice { .name = "msc", .id = 1, .type = INTEL_TH_OUTPUT, + .mknode = true, .otype = GTH_MSU, .scrpd = SCRPD_MEM_IS_PRIM_DEST | SCRPD_MSC1_IS_ENABLED, }, @@ -488,7 +508,7 @@ static const struct intel_th_subdevice { .flags = IORESOURCE_MEM, }, { - .start = 1, /* use resource[1] */ + .start = TH_MMIO_SW, .end = 0, .flags = IORESOURCE_MEM, }, @@ -498,6 +518,24 @@ static const struct intel_th_subdevice { .type = INTEL_TH_SOURCE, }, { + .nres = 2, + .res = { + { + .start = REG_STH_OFFSET, + .end = REG_STH_OFFSET + REG_STH_LENGTH - 1, + .flags = IORESOURCE_MEM, + }, + { + .start = TH_MMIO_RTIT, + .end = 0, + .flags = IORESOURCE_MEM, + }, + }, + .id = -1, + .name = "rtit", + .type = INTEL_TH_SOURCE, + }, + { .nres = 1, .res = { { @@ -581,7 +619,6 @@ intel_th_subdevice_alloc(struct intel_th *th, struct intel_th_device *thdev; struct resource res[3]; unsigned int req = 0; - bool is64bit = false; int r, err; thdev = intel_th_device_alloc(th, subdev->type, subdev->name, @@ -591,18 +628,12 @@ intel_th_subdevice_alloc(struct intel_th *th, thdev->drvdata = th->drvdata; - for (r = 0; r < th->num_resources; r++) - if (th->resource[r].flags & IORESOURCE_MEM_64) { - is64bit = true; - break; - } - memcpy(res, subdev->res, sizeof(struct resource) * subdev->nres); for (r = 0; r < subdev->nres; r++) { struct resource *devres = th->resource; - int bar = 0; /* cut subdevices' MMIO from resource[0] */ + int bar = TH_MMIO_CONFIG; /* * Take .end == 0 to mean 'take the whole bar', @@ -611,8 +642,9 @@ intel_th_subdevice_alloc(struct intel_th *th, */ if (!res[r].end && res[r].flags == IORESOURCE_MEM) { bar = res[r].start; - if (is64bit) - bar *= 2; + err = -ENODEV; + if (bar >= th->num_resources) + goto fail_put_device; res[r].start = 0; res[r].end = resource_size(&devres[bar]) - 1; } @@ -624,18 +656,22 @@ intel_th_subdevice_alloc(struct intel_th *th, dev_dbg(th->dev, "%s:%d @ %pR\n", subdev->name, r, &res[r]); } else if (res[r].flags & IORESOURCE_IRQ) { - res[r].start = th->irq; + /* + * Only pass on the IRQ if we have useful interrupts: + * the ones that can be configured via MINTCTL. + */ + if (INTEL_TH_CAP(th, has_mintctl) && th->irq != -1) + res[r].start = th->irq; } } err = intel_th_device_add_resources(thdev, res, subdev->nres); - if (err) { - put_device(&thdev->dev); + if (err) goto fail_put_device; - } if (subdev->type == INTEL_TH_OUTPUT) { - thdev->dev.devt = MKDEV(th->major, th->num_thdevs); + if (subdev->mknode) + thdev->dev.devt = MKDEV(th->major, th->num_thdevs); thdev->output.type = subdev->otype; thdev->output.port = -1; thdev->output.scratchpad = subdev->scrpd; @@ -646,10 +682,8 @@ intel_th_subdevice_alloc(struct intel_th *th, } err = device_add(&thdev->dev); - if (err) { - put_device(&thdev->dev); + if (err) goto fail_free_res; - } /* need switch driver to be loaded to enumerate the rest */ if (subdev->type == INTEL_TH_SWITCH && !req) { @@ -754,8 +788,13 @@ static int intel_th_populate(struct intel_th *th) thdev = intel_th_subdevice_alloc(th, subdev); /* note: caller should free subdevices from th::thdev[] */ - if (IS_ERR(thdev)) + if (IS_ERR(thdev)) { + /* ENODEV for individual subdevices is allowed */ + if (PTR_ERR(thdev) == -ENODEV) + continue; + return PTR_ERR(thdev); + } th->thdev[th->num_thdevs++] = thdev; } @@ -763,13 +802,6 @@ static int intel_th_populate(struct intel_th *th) return 0; } -static int match_devt(struct device *dev, void *data) -{ - dev_t devt = (dev_t)(unsigned long)data; - - return dev->devt == devt; -} - static int intel_th_output_open(struct inode *inode, struct file *file) { const struct file_operations *fops; @@ -777,16 +809,18 @@ static int intel_th_output_open(struct inode *inode, struct file *file) struct device *dev; int err; - dev = bus_find_device(&intel_th_bus, NULL, - (void *)(unsigned long)inode->i_rdev, - match_devt); - if (!dev || !dev->driver) - return -ENODEV; + dev = bus_find_device_by_devt(&intel_th_bus, inode->i_rdev); + if (!dev || !dev->driver) { + err = -ENODEV; + goto out_no_device; + } thdrv = to_intel_th_driver(dev->driver); fops = fops_get(thdrv->fops); - if (!fops) - return -ENODEV; + if (!fops) { + err = -ENODEV; + goto out_put_device; + } replace_fops(file, fops); @@ -794,10 +828,16 @@ static int intel_th_output_open(struct inode *inode, struct file *file) if (file->f_op->open) { err = file->f_op->open(inode, file); - return err; + if (err) + goto out_put_device; } return 0; + +out_put_device: + put_device(dev); +out_no_device: + return err; } static const struct file_operations intel_th_output_fops = { @@ -805,32 +845,44 @@ static const struct file_operations intel_th_output_fops = { .llseek = noop_llseek, }; +static irqreturn_t intel_th_irq(int irq, void *data) +{ + struct intel_th *th = data; + irqreturn_t ret = IRQ_NONE; + struct intel_th_driver *d; + int i; + + for (i = 0; i < th->num_thdevs; i++) { + if (th->thdev[i]->type != INTEL_TH_OUTPUT) + continue; + + d = to_intel_th_driver(th->thdev[i]->dev.driver); + if (d && d->irq) + ret |= d->irq(th->thdev[i]); + } + + return ret; +} + /** * intel_th_alloc() - allocate a new Intel TH device and its subdevices * @dev: parent device - * @devres: parent's resources - * @ndevres: number of resources - * @irq: irq number + * @drvdata: data private to the driver + * @devres: resources indexed by th_mmio_idx + * @ndevres: number of entries in the @devres resources */ struct intel_th * -intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, - struct resource *devres, unsigned int ndevres, int irq) +intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata, + struct resource *devres, unsigned int ndevres) { + int err, r, nr_mmios = 0; struct intel_th *th; - int err, r; - - if (irq == -1) - for (r = 0; r < ndevres; r++) - if (devres[r].flags & IORESOURCE_IRQ) { - irq = devres[r].start; - break; - } th = kzalloc(sizeof(*th), GFP_KERNEL); if (!th) return ERR_PTR(-ENOMEM); - th->id = ida_simple_get(&intel_th_ida, 0, 0, GFP_KERNEL); + th->id = ida_alloc(&intel_th_ida, GFP_KERNEL); if (th->id < 0) { err = th->id; goto err_alloc; @@ -842,12 +894,33 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, err = th->major; goto err_ida; } + th->irq = -1; th->dev = dev; th->drvdata = drvdata; - th->resource = devres; - th->num_resources = ndevres; - th->irq = irq; + for (r = 0; r < ndevres; r++) + switch (devres[r].flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_MEM: + th->resource[nr_mmios++] = devres[r]; + break; + case IORESOURCE_IRQ: + err = devm_request_irq(dev, devres[r].start, + intel_th_irq, IRQF_SHARED, + dev_name(dev), th); + if (err) + goto err_chrdev; + + if (th->irq == -1) + th->irq = devres[r].start; + th->num_irqs++; + break; + default: + dev_warn(dev, "Unknown resource type %lx\n", + devres[r].flags); + break; + } + + th->num_resources = nr_mmios; dev_set_drvdata(dev, th); @@ -864,8 +937,12 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, return th; +err_chrdev: + __unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS, + "intel_th/output"); + err_ida: - ida_simple_remove(&intel_th_ida, th->id); + ida_free(&intel_th_ida, th->id); err_alloc: kfree(th); @@ -889,13 +966,16 @@ void intel_th_free(struct intel_th *th) th->num_thdevs = 0; + for (i = 0; i < th->num_irqs; i++) + devm_free_irq(th->dev, th->irq + i, th); + pm_runtime_get_sync(th->dev); pm_runtime_forbid(th->dev); __unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS, "intel_th/output"); - ida_simple_remove(&intel_th_ida, th->id); + ida_free(&intel_th_ida, th->id); kfree(th); } @@ -924,6 +1004,27 @@ int intel_th_trace_enable(struct intel_th_device *thdev) EXPORT_SYMBOL_GPL(intel_th_trace_enable); /** + * intel_th_trace_switch() - execute a switch sequence + * @thdev: output device that requests tracing switch + */ +int intel_th_trace_switch(struct intel_th_device *thdev) +{ + struct intel_th_device *hub = to_intel_th_device(thdev->dev.parent); + struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver); + + if (WARN_ON_ONCE(hub->type != INTEL_TH_SWITCH)) + return -EINVAL; + + if (WARN_ON_ONCE(thdev->type != INTEL_TH_OUTPUT)) + return -EINVAL; + + hubdrv->trig_switch(hub, &thdev->output); + + return 0; +} +EXPORT_SYMBOL_GPL(intel_th_trace_switch); + +/** * intel_th_trace_disable() - disable tracing for an output device * @thdev: output device that requests tracing be disabled */ @@ -948,15 +1049,30 @@ int intel_th_set_output(struct intel_th_device *thdev, { struct intel_th_device *hub = to_intel_th_hub(thdev); struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver); + int ret; /* In host mode, this is up to the external debugger, do nothing. */ if (hub->host_mode) return 0; - if (!hubdrv->set_output) - return -ENOTSUPP; + /* + * hub is instantiated together with the source device that + * calls here, so guaranteed to be present. + */ + hubdrv = to_intel_th_driver(hub->dev.driver); + if (!hubdrv || !try_module_get(hubdrv->driver.owner)) + return -EINVAL; + + if (!hubdrv->set_output) { + ret = -ENOTSUPP; + goto out; + } - return hubdrv->set_output(hub, master); + ret = hubdrv->set_output(hub, master); + +out: + module_put(hubdrv->driver.owner); + return ret; } EXPORT_SYMBOL_GPL(intel_th_set_output); diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index 8426b7970c14..3883f99fd5d5 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -154,9 +154,9 @@ static ssize_t master_attr_show(struct device *dev, spin_unlock(>h->gth_lock); if (port >= 0) - count = snprintf(buf, PAGE_SIZE, "%x\n", port); + count = sysfs_emit(buf, "%x\n", port); else - count = snprintf(buf, PAGE_SIZE, "disabled\n"); + count = sysfs_emit(buf, "disabled\n"); return count; } @@ -308,6 +308,11 @@ static int intel_th_gth_reset(struct gth_device *gth) iowrite32(0, gth->base + REG_GTH_SCR); iowrite32(0xfc, gth->base + REG_GTH_SCR2); + /* setup CTS for single trigger */ + iowrite32(CTS_EVENT_ENABLE_IF_ANYTHING, gth->base + REG_CTS_C0S0_EN); + iowrite32(CTS_ACTION_CONTROL_SET_STATE(CTS_STATE_IDLE) | + CTS_ACTION_CONTROL_TRIGGER, gth->base + REG_CTS_C0S0_ACT); + return 0; } @@ -327,8 +332,8 @@ static ssize_t output_attr_show(struct device *dev, pm_runtime_get_sync(dev); spin_lock(>h->gth_lock); - count = snprintf(buf, PAGE_SIZE, "%x\n", - gth_output_parm_get(gth, oa->port, oa->parm)); + count = sysfs_emit(buf, "%x\n", + gth_output_parm_get(gth, oa->port, oa->parm)); spin_unlock(>h->gth_lock); pm_runtime_put(dev); @@ -457,6 +462,68 @@ static int intel_th_output_attributes(struct gth_device *gth) } /** + * intel_th_gth_stop() - stop tracing to an output device + * @gth: GTH device + * @output: output device's descriptor + * @capture_done: set when no more traces will be captured + * + * This will stop tracing using force storeEn off signal and wait for the + * pipelines to be empty for the corresponding output port. + */ +static void intel_th_gth_stop(struct gth_device *gth, + struct intel_th_output *output, + bool capture_done) +{ + struct intel_th_device *outdev = + container_of(output, struct intel_th_device, output); + struct intel_th_driver *outdrv = + to_intel_th_driver(outdev->dev.driver); + unsigned long count; + u32 reg; + u32 scr2 = 0xfc | (capture_done ? 1 : 0); + + iowrite32(0, gth->base + REG_GTH_SCR); + iowrite32(scr2, gth->base + REG_GTH_SCR2); + + /* wait on pipeline empty for the given port */ + for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH; + count && !(reg & BIT(output->port)); count--) { + reg = ioread32(gth->base + REG_GTH_STAT); + cpu_relax(); + } + + if (!count) + dev_dbg(gth->dev, "timeout waiting for GTH[%d] PLE\n", + output->port); + + /* wait on output piepline empty */ + if (outdrv->wait_empty) + outdrv->wait_empty(outdev); + + /* clear force capture done for next captures */ + iowrite32(0xfc, gth->base + REG_GTH_SCR2); +} + +/** + * intel_th_gth_start() - start tracing to an output device + * @gth: GTH device + * @output: output device's descriptor + * + * This will start tracing using force storeEn signal. + */ +static void intel_th_gth_start(struct gth_device *gth, + struct intel_th_output *output) +{ + u32 scr = 0xfc0000; + + if (output->multiblock) + scr |= 0xff; + + iowrite32(scr, gth->base + REG_GTH_SCR); + iowrite32(0, gth->base + REG_GTH_SCR2); +} + +/** * intel_th_gth_disable() - disable tracing to an output device * @thdev: GTH device * @output: output device's descriptor @@ -469,7 +536,6 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, struct intel_th_output *output) { struct gth_device *gth = dev_get_drvdata(&thdev->dev); - unsigned long count; int master; u32 reg; @@ -477,27 +543,12 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, output->active = false; for_each_set_bit(master, gth->output[output->port].master, - TH_CONFIGURABLE_MASTERS) { + TH_CONFIGURABLE_MASTERS + 1) { gth_master_set(gth, master, -1); } spin_unlock(>h->gth_lock); - iowrite32(0, gth->base + REG_GTH_SCR); - iowrite32(0xfd, gth->base + REG_GTH_SCR2); - - /* wait on pipeline empty for the given port */ - for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH; - count && !(reg & BIT(output->port)); count--) { - reg = ioread32(gth->base + REG_GTH_STAT); - cpu_relax(); - } - - /* clear force capture done for next captures */ - iowrite32(0xfc, gth->base + REG_GTH_SCR2); - - if (!count) - dev_dbg(&thdev->dev, "timeout waiting for GTH[%d] PLE\n", - output->port); + intel_th_gth_stop(gth, output, true); reg = ioread32(gth->base + REG_GTH_SCRPD0); reg &= ~output->scratchpad; @@ -513,6 +564,21 @@ static void gth_tscu_resync(struct gth_device *gth) iowrite32(reg, gth->base + REG_TSCU_TSUCTRL); } +static void intel_th_gth_prepare(struct intel_th_device *thdev, + struct intel_th_output *output) +{ + struct gth_device *gth = dev_get_drvdata(&thdev->dev); + int count; + + /* + * Wait until the output port is in reset before we start + * programming it. + */ + for (count = GTH_PLE_WAITLOOP_DEPTH; + count && !(gth_output_get(gth, output->port) & BIT(5)); count--) + cpu_relax(); +} + /** * intel_th_gth_enable() - enable tracing to an output device * @thdev: GTH device @@ -526,8 +592,8 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, { struct gth_device *gth = dev_get_drvdata(&thdev->dev); struct intel_th *th = to_intel_th(thdev); - u32 scr = 0xfc0000, scrpd; int master; + u32 scrpd; spin_lock(>h->gth_lock); for_each_set_bit(master, gth->output[output->port].master, @@ -535,9 +601,6 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, gth_master_set(gth, master, output->port); } - if (output->multiblock) - scr |= 0xff; - output->active = true; spin_unlock(>h->gth_lock); @@ -548,8 +611,41 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, scrpd |= output->scratchpad; iowrite32(scrpd, gth->base + REG_GTH_SCRPD0); - iowrite32(scr, gth->base + REG_GTH_SCR); - iowrite32(0, gth->base + REG_GTH_SCR2); + intel_th_gth_start(gth, output); +} + +/** + * intel_th_gth_switch() - execute a switch sequence + * @thdev: GTH device + * @output: output device's descriptor + * + * This will execute a switch sequence that will trigger a switch window + * when tracing to MSC in multi-block mode. + */ +static void intel_th_gth_switch(struct intel_th_device *thdev, + struct intel_th_output *output) +{ + struct gth_device *gth = dev_get_drvdata(&thdev->dev); + unsigned long count; + u32 reg; + + /* trigger */ + iowrite32(0, gth->base + REG_CTS_CTL); + iowrite32(CTS_CTL_SEQUENCER_ENABLE, gth->base + REG_CTS_CTL); + /* wait on trigger status */ + for (reg = 0, count = CTS_TRIG_WAITLOOP_DEPTH; + count && !(reg & BIT(4)); count--) { + reg = ioread32(gth->base + REG_CTS_STAT); + cpu_relax(); + } + if (!count) + dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n"); + + /* De-assert the trigger */ + iowrite32(0, gth->base + REG_CTS_CTL); + + intel_th_gth_stop(gth, output, false); + intel_th_gth_start(gth, output); } /** @@ -607,6 +703,7 @@ static void intel_th_gth_unassign(struct intel_th_device *thdev, { struct gth_device *gth = dev_get_drvdata(&thdev->dev); int port = othdev->output.port; + int master; if (thdev->host_mode) return; @@ -615,6 +712,9 @@ static void intel_th_gth_unassign(struct intel_th_device *thdev, othdev->output.port = -1; othdev->output.active = false; gth->output[port].output = NULL; + for (master = 0; master < TH_CONFIGURABLE_MASTERS + 1; master++) + if (gth->master[master] == port) + gth->master[master] = -1; spin_unlock(>h->gth_lock); } @@ -730,7 +830,9 @@ static struct intel_th_driver intel_th_gth_driver = { .assign = intel_th_gth_assign, .unassign = intel_th_gth_unassign, .set_output = intel_th_gth_set_output, + .prepare = intel_th_gth_prepare, .enable = intel_th_gth_enable, + .trig_switch = intel_th_gth_switch, .disable = intel_th_gth_disable, .driver = { .name = "gth", diff --git a/drivers/hwtracing/intel_th/gth.h b/drivers/hwtracing/intel_th/gth.h index 6f2b0b930875..bfcc0fd01177 100644 --- a/drivers/hwtracing/intel_th/gth.h +++ b/drivers/hwtracing/intel_th/gth.h @@ -49,6 +49,12 @@ enum { REG_GTH_SCRPD3 = 0xec, /* ScratchPad[3] */ REG_TSCU_TSUCTRL = 0x2000, /* TSCU control register */ REG_TSCU_TSCUSTAT = 0x2004, /* TSCU status register */ + + /* Common Capture Sequencer (CTS) registers */ + REG_CTS_C0S0_EN = 0x30c0, /* clause_event_enable_c0s0 */ + REG_CTS_C0S0_ACT = 0x3180, /* clause_action_control_c0s0 */ + REG_CTS_STAT = 0x32a0, /* cts_status */ + REG_CTS_CTL = 0x32a4, /* cts_control */ }; /* waiting for Pipeline Empty bit(s) to assert for GTH */ @@ -57,4 +63,17 @@ enum { #define TSUCTRL_CTCRESYNC BIT(0) #define TSCUSTAT_CTCSYNCING BIT(1) +/* waiting for Trigger status to assert for CTS */ +#define CTS_TRIG_WAITLOOP_DEPTH 10000 + +#define CTS_EVENT_ENABLE_IF_ANYTHING BIT(31) +#define CTS_ACTION_CONTROL_STATE_OFF 27 +#define CTS_ACTION_CONTROL_SET_STATE(x) \ + (((x) & 0x1f) << CTS_ACTION_CONTROL_STATE_OFF) +#define CTS_ACTION_CONTROL_TRIGGER BIT(4) + +#define CTS_STATE_IDLE 0x10u + +#define CTS_CTL_SEQUENCER_ENABLE BIT(0) + #endif /* __INTEL_TH_GTH_H__ */ diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 780206dc9012..3b87cd542c1b 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -8,6 +8,8 @@ #ifndef __INTEL_TH_H__ #define __INTEL_TH_H__ +#include <linux/irqreturn.h> + /* intel_th_device device types */ enum { /* Devices that generate trace data */ @@ -18,6 +20,8 @@ enum { INTEL_TH_SWITCH, }; +struct intel_th_device; + /** * struct intel_th_output - descriptor INTEL_TH_OUTPUT type devices * @port: output port number, assigned by the switch @@ -25,6 +29,7 @@ enum { * @scratchpad: scratchpad bits to flag when this output is enabled * @multiblock: true for multiblock output configuration * @active: true when this output is enabled + * @wait_empty: wait for device pipeline to be empty * * Output port descriptor, used by switch driver to tell which output * port this output device corresponds to. Filled in at output device's @@ -42,10 +47,14 @@ struct intel_th_output { /** * struct intel_th_drvdata - describes hardware capabilities and quirks * @tscu_enable: device needs SW to enable time stamping unit + * @multi_is_broken: device has multiblock mode is broken + * @has_mintctl: device has interrupt control (MINTCTL) register * @host_mode_only: device can only operate in 'host debugger' mode */ struct intel_th_drvdata { unsigned int tscu_enable : 1, + multi_is_broken : 1, + has_mintctl : 1, host_mode_only : 1; }; @@ -65,7 +74,7 @@ struct intel_th_drvdata { */ struct intel_th_device { struct device dev; - struct intel_th_drvdata *drvdata; + const struct intel_th_drvdata *drvdata; struct resource *resource; unsigned int num_resources; unsigned int type; @@ -134,6 +143,7 @@ intel_th_output_assigned(struct intel_th_device *thdev) * @remove: remove method * @assign: match a given output type device against available outputs * @unassign: deassociate an output type device from an output port + * @prepare: prepare output port for tracing * @enable: enable tracing for a given output device * @disable: disable tracing for a given output device * @irq: interrupt callback @@ -155,18 +165,23 @@ struct intel_th_driver { struct intel_th_device *othdev); void (*unassign)(struct intel_th_device *thdev, struct intel_th_device *othdev); + void (*prepare)(struct intel_th_device *thdev, + struct intel_th_output *output); void (*enable)(struct intel_th_device *thdev, struct intel_th_output *output); + void (*trig_switch)(struct intel_th_device *thdev, + struct intel_th_output *output); void (*disable)(struct intel_th_device *thdev, struct intel_th_output *output); /* output ops */ - void (*irq)(struct intel_th_device *thdev); + irqreturn_t (*irq)(struct intel_th_device *thdev); + void (*wait_empty)(struct intel_th_device *thdev); int (*activate)(struct intel_th_device *thdev); void (*deactivate)(struct intel_th_device *thdev); /* file_operations for those who want a device node */ const struct file_operations *fops; /* optional attributes */ - struct attribute_group *attr_group; + const struct attribute_group *attr_group; /* source ops */ int (*set_output)(struct intel_th_device *thdev, @@ -174,7 +189,7 @@ struct intel_th_driver { }; #define to_intel_th_driver(_d) \ - container_of((_d), struct intel_th_driver, driver) + container_of_const((_d), struct intel_th_driver, driver) #define to_intel_th_driver_or_null(_d) \ ((_d) ? to_intel_th_driver(_d) : NULL) @@ -190,7 +205,7 @@ struct intel_th_driver { * INTEL_TH_SWITCH and INTEL_TH_SOURCE are children of the intel_th device. */ static inline struct intel_th_device * -to_intel_th_parent(struct intel_th_device *thdev) +to_intel_th_parent(const struct intel_th_device *thdev) { struct device *parent = thdev->dev.parent; @@ -200,7 +215,7 @@ to_intel_th_parent(struct intel_th_device *thdev) return to_intel_th_device(parent); } -static inline struct intel_th *to_intel_th(struct intel_th_device *thdev) +static inline struct intel_th *to_intel_th(const struct intel_th_device *thdev) { if (thdev->type == INTEL_TH_OUTPUT) thdev = to_intel_th_parent(thdev); @@ -212,22 +227,24 @@ static inline struct intel_th *to_intel_th(struct intel_th_device *thdev) } struct intel_th * -intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, - struct resource *devres, unsigned int ndevres, int irq); +intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata, + struct resource *devres, unsigned int ndevres); void intel_th_free(struct intel_th *th); int intel_th_driver_register(struct intel_th_driver *thdrv); void intel_th_driver_unregister(struct intel_th_driver *thdrv); int intel_th_trace_enable(struct intel_th_device *thdev); +int intel_th_trace_switch(struct intel_th_device *thdev); int intel_th_trace_disable(struct intel_th_device *thdev); int intel_th_set_output(struct intel_th_device *thdev, unsigned int master); int intel_th_output_enable(struct intel_th *th, unsigned int otype); -enum { +enum th_mmio_idx { TH_MMIO_CONFIG = 0, - TH_MMIO_SW = 2, + TH_MMIO_SW = 1, + TH_MMIO_RTIT = 2, TH_MMIO_END, }; @@ -237,6 +254,9 @@ enum { #define TH_CONFIGURABLE_MASTERS 256 #define TH_MSC_MAX 2 +/* Maximum IRQ vectors */ +#define TH_NVEC_MAX 8 + /** * struct intel_th - Intel TH controller * @dev: driver core's device @@ -244,8 +264,9 @@ enum { * @hub: "switch" subdevice (GTH) * @resource: resources of the entire controller * @num_thdevs: number of devices in the @thdev array - * @num_resources: number or resources in the @resource array + * @num_resources: number of resources in the @resource array * @irq: irq number + * @num_irqs: number of IRQs is use * @id: this Intel TH controller's device ID in the system * @major: device node major for output devices */ @@ -254,14 +275,15 @@ struct intel_th { struct intel_th_device *thdev[TH_SUBDEVICE_MAX]; struct intel_th_device *hub; - struct intel_th_drvdata *drvdata; + const struct intel_th_drvdata *drvdata; - struct resource *resource; + struct resource resource[TH_MMIO_END]; int (*activate)(struct intel_th *); void (*deactivate)(struct intel_th *); unsigned int num_thdevs; unsigned int num_resources; int irq; + int num_irqs; int id; int major; @@ -296,6 +318,9 @@ enum { REG_TSCU_OFFSET = 0x2000, REG_TSCU_LENGTH = 0x1000, + REG_CTS_OFFSET = 0x3000, + REG_CTS_LENGTH = 0x1000, + /* Software Trace Hub (STH) [0x4000..0x4fff] */ REG_STH_OFFSET = 0x4000, REG_STH_LENGTH = 0x2000, diff --git a/drivers/hwtracing/intel_th/msu-sink.c b/drivers/hwtracing/intel_th/msu-sink.c new file mode 100644 index 000000000000..256ce3260ad9 --- /dev/null +++ b/drivers/hwtracing/intel_th/msu-sink.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * An example software sink buffer for Intel TH MSU. + * + * Copyright (C) 2019 Intel Corporation. + */ + +#include <linux/intel_th.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> + +#define MAX_SGTS 16 + +struct msu_sink_private { + struct device *dev; + struct sg_table **sgts; + unsigned int nr_sgts; +}; + +static void *msu_sink_assign(struct device *dev, int *mode) +{ + struct msu_sink_private *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return NULL; + + priv->sgts = kcalloc(MAX_SGTS, sizeof(void *), GFP_KERNEL); + if (!priv->sgts) { + kfree(priv); + return NULL; + } + + priv->dev = dev; + *mode = MSC_MODE_MULTI; + + return priv; +} + +static void msu_sink_unassign(void *data) +{ + struct msu_sink_private *priv = data; + + kfree(priv->sgts); + kfree(priv); +} + +/* See also: msc.c: __msc_buffer_win_alloc() */ +static int msu_sink_alloc_window(void *data, struct sg_table **sgt, size_t size) +{ + struct msu_sink_private *priv = data; + unsigned int nents; + struct scatterlist *sg_ptr; + void *block; + int ret, i; + + if (priv->nr_sgts == MAX_SGTS) + return -ENOMEM; + + nents = DIV_ROUND_UP(size, PAGE_SIZE); + + ret = sg_alloc_table(*sgt, nents, GFP_KERNEL); + if (ret) + return -ENOMEM; + + priv->sgts[priv->nr_sgts++] = *sgt; + + for_each_sg((*sgt)->sgl, sg_ptr, nents, i) { + block = dma_alloc_coherent(priv->dev->parent->parent, + PAGE_SIZE, &sg_dma_address(sg_ptr), + GFP_KERNEL); + if (!block) + return -ENOMEM; + + sg_set_buf(sg_ptr, block, PAGE_SIZE); + } + + return nents; +} + +/* See also: msc.c: __msc_buffer_win_free() */ +static void msu_sink_free_window(void *data, struct sg_table *sgt) +{ + struct msu_sink_private *priv = data; + struct scatterlist *sg_ptr; + int i; + + for_each_sg(sgt->sgl, sg_ptr, sgt->nents, i) { + dma_free_coherent(priv->dev->parent->parent, PAGE_SIZE, + sg_virt(sg_ptr), sg_dma_address(sg_ptr)); + } + + sg_free_table(sgt); + priv->nr_sgts--; +} + +static int msu_sink_ready(void *data, struct sg_table *sgt, size_t bytes) +{ + struct msu_sink_private *priv = data; + + intel_th_msc_window_unlock(priv->dev, sgt); + + return 0; +} + +static const struct msu_buffer sink_mbuf = { + .name = "sink", + .assign = msu_sink_assign, + .unassign = msu_sink_unassign, + .alloc_window = msu_sink_alloc_window, + .free_window = msu_sink_free_window, + .ready = msu_sink_ready, +}; + +module_intel_th_msu_buffer(sink_mbuf); + +MODULE_DESCRIPTION("example software sink buffer for Intel TH MSU"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index ba7aaf421f36..f3a13b300835 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -17,40 +17,64 @@ #include <linux/mm.h> #include <linux/fs.h> #include <linux/io.h> +#include <linux/workqueue.h> #include <linux/dma-mapping.h> #ifdef CONFIG_X86 #include <asm/set_memory.h> #endif +#include <linux/intel_th.h> #include "intel_th.h" #include "msu.h" #define msc_dev(x) (&(x)->thdev->dev) -/** - * struct msc_block - multiblock mode block descriptor - * @bdesc: pointer to hardware descriptor (beginning of the block) - * @addr: physical address of the block +/* + * Lockout state transitions: + * READY -> INUSE -+-> LOCKED -+-> READY -> etc. + * \-----------/ + * WIN_READY: window can be used by HW + * WIN_INUSE: window is in use + * WIN_LOCKED: window is filled up and is being processed by the buffer + * handling code + * + * All state transitions happen automatically, except for the LOCKED->READY, + * which needs to be signalled by the buffer code by calling + * intel_th_msc_window_unlock(). + * + * When the interrupt handler has to switch to the next window, it checks + * whether it's READY, and if it is, it performs the switch and tracing + * continues. If it's LOCKED, it stops the trace. */ -struct msc_block { - struct msc_block_desc *bdesc; - dma_addr_t addr; +enum lockout_state { + WIN_READY = 0, + WIN_INUSE, + WIN_LOCKED }; /** * struct msc_window - multiblock mode window descriptor * @entry: window list linkage (msc::win_list) * @pgoff: page offset into the buffer that this window starts at + * @lockout: lockout state, see comment below + * @lo_lock: lockout state serialization * @nr_blocks: number of blocks (pages) in this window - * @block: array of block descriptors + * @nr_segs: number of segments in this window (<= @nr_blocks) + * @msc: pointer to the MSC device + * @_sgt: array of block descriptors + * @sgt: array of block descriptors */ struct msc_window { struct list_head entry; unsigned long pgoff; + enum lockout_state lockout; + spinlock_t lo_lock; unsigned int nr_blocks; + unsigned int nr_segs; struct msc *msc; - struct msc_block block[0]; + struct sg_table _sgt; + struct sg_table *sgt; }; /** @@ -72,8 +96,8 @@ struct msc_iter { struct msc_window *start_win; struct msc_window *win; unsigned long offset; - int start_block; - int block; + struct scatterlist *start_block; + struct scatterlist *block; unsigned int block_off; unsigned int wrap_count; unsigned int eof; @@ -81,34 +105,56 @@ struct msc_iter { /** * struct msc - MSC device representation - * @reg_base: register window base address + * @reg_base: register window base address for the entire MSU + * @msu_base: register window base address for this MSC * @thdev: intel_th_device pointer + * @mbuf: MSU buffer, if assigned + * @mbuf_priv: MSU buffer's private data, if @mbuf + * @work: a work to stop the trace when the buffer is full * @win_list: list of windows in multiblock mode + * @single_sgt: single mode buffer + * @cur_win: current window + * @switch_on_unlock: window to switch to when it becomes available * @nr_pages: total number of pages allocated for this buffer * @single_sz: amount of data in single mode * @single_wrap: single mode wrap occurred * @base: buffer's base pointer * @base_addr: buffer's base address + * @orig_addr: MSC0 buffer's base address + * @orig_sz: MSC0 buffer's size * @user_count: number of users of the buffer * @mmap_count: number of mappings * @buf_mutex: mutex to serialize access to buffer-related bits - + * @iter_list: list of open file descriptor iterators + * @stop_on_full: stop the trace if the current window is full * @enabled: MSC is enabled * @wrap: wrapping is enabled + * @do_irq: IRQ resource is available, handle interrupts + * @multi_is_broken: multiblock mode enabled (not disabled by PCI drvdata) * @mode: MSC operating mode * @burst_len: write burst length * @index: number of this MSC in the MSU */ struct msc { void __iomem *reg_base; + void __iomem *msu_base; struct intel_th_device *thdev; + const struct msu_buffer *mbuf; + void *mbuf_priv; + + struct work_struct work; struct list_head win_list; + struct sg_table single_sgt; + struct msc_window *cur_win; + struct msc_window *switch_on_unlock; unsigned long nr_pages; unsigned long single_sz; unsigned int single_wrap : 1; void *base; dma_addr_t base_addr; + u32 orig_addr; + u32 orig_sz; /* <0: no buffer, 0: no users, >0: active users */ atomic_t user_count; @@ -118,14 +164,113 @@ struct msc { struct list_head iter_list; + bool stop_on_full; + /* config */ unsigned int enabled : 1, - wrap : 1; + wrap : 1, + do_irq : 1, + multi_is_broken : 1; unsigned int mode; unsigned int burst_len; unsigned int index; }; +static LIST_HEAD(msu_buffer_list); +static DEFINE_MUTEX(msu_buffer_mutex); + +/** + * struct msu_buffer_entry - internal MSU buffer bookkeeping + * @entry: link to msu_buffer_list + * @mbuf: MSU buffer object + * @owner: module that provides this MSU buffer + */ +struct msu_buffer_entry { + struct list_head entry; + const struct msu_buffer *mbuf; + struct module *owner; +}; + +static struct msu_buffer_entry *__msu_buffer_entry_find(const char *name) +{ + struct msu_buffer_entry *mbe; + + lockdep_assert_held(&msu_buffer_mutex); + + list_for_each_entry(mbe, &msu_buffer_list, entry) { + if (!strcmp(mbe->mbuf->name, name)) + return mbe; + } + + return NULL; +} + +static const struct msu_buffer * +msu_buffer_get(const char *name) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(name); + if (mbe && !try_module_get(mbe->owner)) + mbe = NULL; + mutex_unlock(&msu_buffer_mutex); + + return mbe ? mbe->mbuf : NULL; +} + +static void msu_buffer_put(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) + module_put(mbe->owner); + mutex_unlock(&msu_buffer_mutex); +} + +int intel_th_msu_buffer_register(const struct msu_buffer *mbuf, + struct module *owner) +{ + struct msu_buffer_entry *mbe; + int ret = 0; + + mbe = kzalloc(sizeof(*mbe), GFP_KERNEL); + if (!mbe) + return -ENOMEM; + + mutex_lock(&msu_buffer_mutex); + if (__msu_buffer_entry_find(mbuf->name)) { + ret = -EEXIST; + kfree(mbe); + goto unlock; + } + + mbe->mbuf = mbuf; + mbe->owner = owner; + list_add_tail(&mbe->entry, &msu_buffer_list); +unlock: + mutex_unlock(&msu_buffer_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_register); + +void intel_th_msu_buffer_unregister(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) { + list_del(&mbe->entry); + kfree(mbe); + } + mutex_unlock(&msu_buffer_mutex); +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_unregister); + static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) { /* header hasn't been written */ @@ -139,20 +284,85 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) return false; } +static inline struct scatterlist *msc_win_base_sg(struct msc_window *win) +{ + return win->sgt->sgl; +} + +static inline struct msc_block_desc *msc_win_base(struct msc_window *win) +{ + return sg_virt(msc_win_base_sg(win)); +} + +static inline dma_addr_t msc_win_base_dma(struct msc_window *win) +{ + return sg_dma_address(msc_win_base_sg(win)); +} + +static inline unsigned long +msc_win_base_pfn(struct msc_window *win) +{ + return PFN_DOWN(msc_win_base_dma(win)); +} + /** - * msc_oldest_window() - locate the window with oldest data - * @msc: MSC device + * msc_is_last_win() - check if a window is the last one for a given MSC + * @win: window + * Return: true if @win is the last window in MSC's multiblock buffer + */ +static inline bool msc_is_last_win(struct msc_window *win) +{ + return win->entry.next == &win->msc->win_list; +} + +/** + * msc_next_window() - return next window in the multiblock buffer + * @win: current window * - * This should only be used in multiblock mode. Caller should hold the - * msc::user_count reference. + * Return: window following the current one + */ +static struct msc_window *msc_next_window(struct msc_window *win) +{ + if (msc_is_last_win(win)) + return list_first_entry(&win->msc->win_list, struct msc_window, + entry); + + return list_next_entry(win, entry); +} + +static size_t msc_win_total_sz(struct msc_window *win) +{ + struct scatterlist *sg; + unsigned int blk; + size_t size = 0; + + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); + + if (msc_block_wrapped(bdesc)) + return (size_t)win->nr_blocks << PAGE_SHIFT; + + size += msc_total_sz(bdesc); + if (msc_block_last_written(bdesc)) + break; + } + + return size; +} + +/** + * msc_find_window() - find a window matching a given sg_table + * @msc: MSC device + * @sgt: SG table of the window + * @nonempty: skip over empty windows * - * Return: the oldest window with valid data + * Return: MSC window structure pointer or NULL if the window + * could not be found. */ -static struct msc_window *msc_oldest_window(struct msc *msc) +static struct msc_window * +msc_find_window(struct msc *msc, struct sg_table *sgt, bool nonempty) { struct msc_window *win; - u32 reg = ioread32(msc->reg_base + REG_MSU_MSC0NWSA); - unsigned long win_addr = (unsigned long)reg << PAGE_SHIFT; unsigned int found = 0; if (list_empty(&msc->win_list)) @@ -164,84 +374,76 @@ static struct msc_window *msc_oldest_window(struct msc *msc) * something like 2, in which case we're good */ list_for_each_entry(win, &msc->win_list, entry) { - if (win->block[0].addr == win_addr) + if (win->sgt == sgt) found++; /* skip the empty ones */ - if (msc_block_is_empty(win->block[0].bdesc)) + if (nonempty && msc_block_is_empty(msc_win_base(win))) continue; if (found) return win; } - return list_entry(msc->win_list.next, struct msc_window, entry); + return NULL; } /** - * msc_win_oldest_block() - locate the oldest block in a given window + * msc_oldest_window() - locate the window with oldest data + * @msc: MSC device + * + * This should only be used in multiblock mode. Caller should hold the + * msc::user_count reference. + * + * Return: the oldest window with valid data + */ +static struct msc_window *msc_oldest_window(struct msc *msc) +{ + struct msc_window *win; + + if (list_empty(&msc->win_list)) + return NULL; + + win = msc_find_window(msc, msc_next_window(msc->cur_win)->sgt, true); + if (win) + return win; + + return list_first_entry(&msc->win_list, struct msc_window, entry); +} + +/** + * msc_win_oldest_sg() - locate the oldest block in a given window * @win: window to look at * * Return: index of the block with the oldest data */ -static unsigned int msc_win_oldest_block(struct msc_window *win) +static struct scatterlist *msc_win_oldest_sg(struct msc_window *win) { unsigned int blk; - struct msc_block_desc *bdesc = win->block[0].bdesc; + struct scatterlist *sg; + struct msc_block_desc *bdesc = msc_win_base(win); /* without wrapping, first block is the oldest */ if (!msc_block_wrapped(bdesc)) - return 0; + return msc_win_base_sg(win); /* * with wrapping, last written block contains both the newest and the * oldest data for this window. */ - for (blk = 0; blk < win->nr_blocks; blk++) { - bdesc = win->block[blk].bdesc; + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); if (msc_block_last_written(bdesc)) - return blk; + return sg; } - return 0; -} - -/** - * msc_is_last_win() - check if a window is the last one for a given MSC - * @win: window - * Return: true if @win is the last window in MSC's multiblock buffer - */ -static inline bool msc_is_last_win(struct msc_window *win) -{ - return win->entry.next == &win->msc->win_list; -} - -/** - * msc_next_window() - return next window in the multiblock buffer - * @win: current window - * - * Return: window following the current one - */ -static struct msc_window *msc_next_window(struct msc_window *win) -{ - if (msc_is_last_win(win)) - return list_entry(win->msc->win_list.next, struct msc_window, - entry); - - return list_entry(win->entry.next, struct msc_window, entry); + return msc_win_base_sg(win); } static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter) { - return iter->win->block[iter->block].bdesc; -} - -static void msc_iter_init(struct msc_iter *iter) -{ - memset(iter, 0, sizeof(*iter)); - iter->start_block = -1; - iter->block = -1; + return sg_virt(iter->block); } static struct msc_iter *msc_iter_install(struct msc *msc) @@ -266,7 +468,6 @@ static struct msc_iter *msc_iter_install(struct msc *msc) goto unlock; } - msc_iter_init(iter); iter->msc = msc; list_add_tail(&iter->entry, &msc->iter_list); @@ -287,10 +488,10 @@ static void msc_iter_remove(struct msc_iter *iter, struct msc *msc) static void msc_iter_block_start(struct msc_iter *iter) { - if (iter->start_block != -1) + if (iter->start_block) return; - iter->start_block = msc_win_oldest_block(iter->win); + iter->start_block = msc_win_oldest_sg(iter->win); iter->block = iter->start_block; iter->wrap_count = 0; @@ -314,7 +515,7 @@ static int msc_iter_win_start(struct msc_iter *iter, struct msc *msc) return -EINVAL; iter->win = iter->start_win; - iter->start_block = -1; + iter->start_block = NULL; msc_iter_block_start(iter); @@ -324,7 +525,7 @@ static int msc_iter_win_start(struct msc_iter *iter, struct msc *msc) static int msc_iter_win_advance(struct msc_iter *iter) { iter->win = msc_next_window(iter->win); - iter->start_block = -1; + iter->start_block = NULL; if (iter->win == iter->start_win) { iter->eof++; @@ -354,8 +555,10 @@ static int msc_iter_block_advance(struct msc_iter *iter) return msc_iter_win_advance(iter); /* block advance */ - if (++iter->block == iter->win->nr_blocks) - iter->block = 0; + if (sg_is_last(iter->block)) + iter->block = msc_win_base_sg(iter->win); + else + iter->block = sg_next(iter->block); /* no wrapping, sanity check in case there is no last written block */ if (!iter->wrap_count && iter->block == iter->start_block) @@ -460,20 +663,100 @@ next_block: static void msc_buffer_clear_hw_header(struct msc *msc) { struct msc_window *win; + struct scatterlist *sg; list_for_each_entry(win, &msc->win_list, entry) { unsigned int blk; - size_t hw_sz = sizeof(struct msc_block_desc) - - offsetof(struct msc_block_desc, hw_tag); - for (blk = 0; blk < win->nr_blocks; blk++) { - struct msc_block_desc *bdesc = win->block[blk].bdesc; + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); - memset(&bdesc->hw_tag, 0, hw_sz); + memset_startat(bdesc, 0, hw_tag); } } } +static int intel_th_msu_init(struct msc *msc) +{ + u32 mintctl, msusts; + + if (!msc->do_irq) + return 0; + + if (!msc->mbuf) + return 0; + + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); + mintctl |= msc->index ? M1BLIE : M0BLIE; + iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); + if (mintctl != ioread32(msc->msu_base + REG_MSU_MINTCTL)) { + dev_info(msc_dev(msc), "MINTCTL ignores writes: no usable interrupts\n"); + msc->do_irq = 0; + return 0; + } + + msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); + iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS); + + return 0; +} + +static void intel_th_msu_deinit(struct msc *msc) +{ + u32 mintctl; + + if (!msc->do_irq) + return; + + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); + mintctl &= msc->index ? ~M1BLIE : ~M0BLIE; + iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); +} + +static int msc_win_set_lockout(struct msc_window *win, + enum lockout_state expect, + enum lockout_state new) +{ + enum lockout_state old; + unsigned long flags; + int ret = 0; + + if (!win->msc->mbuf) + return 0; + + spin_lock_irqsave(&win->lo_lock, flags); + old = win->lockout; + + if (old != expect) { + ret = -EINVAL; + goto unlock; + } + + win->lockout = new; + + if (old == expect && new == WIN_LOCKED) + atomic_inc(&win->msc->user_count); + else if (old == expect && old == WIN_LOCKED) + atomic_dec(&win->msc->user_count); + +unlock: + spin_unlock_irqrestore(&win->lo_lock, flags); + + if (ret) { + if (expect == WIN_READY && old == WIN_LOCKED) + return -EBUSY; + + /* from intel_th_msc_window_unlock(), don't warn if not locked */ + if (expect == WIN_LOCKED && old == new) + return 0; + + dev_warn_ratelimited(msc_dev(win->msc), + "expected lockout state %d, got %d\n", + expect, old); + } + + return ret; +} /** * msc_configure() - set up MSC hardware * @msc: the MSC device to configure @@ -481,6 +764,8 @@ static void msc_buffer_clear_hw_header(struct msc *msc) * Program storage mode, wrapping, burst length and trace buffer address * into a given MSC. Then, enable tracing and set msc::enabled. * The latter is serialized on msc::buf_mutex, so make sure to hold it. + * + * Return: %0 for success or a negative error code otherwise. */ static int msc_configure(struct msc *msc) { @@ -489,10 +774,17 @@ static int msc_configure(struct msc *msc) lockdep_assert_held(&msc->buf_mutex); if (msc->mode > MSC_MODE_MULTI) - return -ENOTSUPP; + return -EINVAL; + + if (msc->mode == MSC_MODE_MULTI) { + if (msc_win_set_lockout(msc->cur_win, WIN_READY, WIN_INUSE)) + return -EBUSY; - if (msc->mode == MSC_MODE_MULTI) msc_buffer_clear_hw_header(msc); + } + + msc->orig_addr = ioread32(msc->reg_base + REG_MSU_MSC0BAR); + msc->orig_sz = ioread32(msc->reg_base + REG_MSU_MSC0SIZE); reg = msc->base_addr >> PAGE_SHIFT; iowrite32(reg, msc->reg_base + REG_MSU_MSC0BAR); @@ -514,10 +806,14 @@ static int msc_configure(struct msc *msc) iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + intel_th_msu_init(msc); + msc->thdev->output.multiblock = msc->mode == MSC_MODE_MULTI; intel_th_trace_enable(msc->thdev); msc->enabled = 1; + if (msc->mbuf && msc->mbuf->activate) + msc->mbuf->activate(msc->mbuf_priv); return 0; } @@ -531,23 +827,21 @@ static int msc_configure(struct msc *msc) */ static void msc_disable(struct msc *msc) { - unsigned long count; + struct msc_window *win = msc->cur_win; u32 reg; lockdep_assert_held(&msc->buf_mutex); - intel_th_trace_disable(msc->thdev); - - for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH; - count && !(reg & MSCSTS_PLE); count--) { - reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); - cpu_relax(); - } + if (msc->mode == MSC_MODE_MULTI) + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); - if (!count) - dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n"); + if (msc->mbuf && msc->mbuf->deactivate) + msc->mbuf->deactivate(msc->mbuf_priv); + intel_th_msu_deinit(msc); + intel_th_trace_disable(msc->thdev); if (msc->mode == MSC_MODE_SINGLE) { + reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); msc->single_wrap = !!(reg & MSCSTS_WRAPSTAT); reg = ioread32(msc->reg_base + REG_MSU_MSC0MWP); @@ -559,16 +853,25 @@ static void msc_disable(struct msc *msc) reg = ioread32(msc->reg_base + REG_MSU_MSC0CTL); reg &= ~MSC_EN; iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + msc->enabled = 0; - iowrite32(0, msc->reg_base + REG_MSU_MSC0BAR); - iowrite32(0, msc->reg_base + REG_MSU_MSC0SIZE); + iowrite32(msc->orig_addr, msc->reg_base + REG_MSU_MSC0BAR); + iowrite32(msc->orig_sz, msc->reg_base + REG_MSU_MSC0SIZE); dev_dbg(msc_dev(msc), "MSCnNWSA: %08x\n", ioread32(msc->reg_base + REG_MSU_MSC0NWSA)); reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); dev_dbg(msc_dev(msc), "MSCnSTS: %08x\n", reg); + + reg = ioread32(msc->reg_base + REG_MSU_MSUSTS); + reg &= msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + iowrite32(reg, msc->reg_base + REG_MSU_MSUSTS); } static int intel_th_msc_activate(struct intel_th_device *thdev) @@ -617,22 +920,45 @@ static void intel_th_msc_deactivate(struct intel_th_device *thdev) */ static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size) { + unsigned long nr_pages = size >> PAGE_SHIFT; unsigned int order = get_order(size); struct page *page; + int ret; if (!size) return 0; - page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); + ret = sg_alloc_table(&msc->single_sgt, 1, GFP_KERNEL); + if (ret) + goto err_out; + + ret = -ENOMEM; + page = alloc_pages(GFP_KERNEL | __GFP_ZERO | GFP_DMA32, order); if (!page) - return -ENOMEM; + goto err_free_sgt; split_page(page, order); - msc->nr_pages = size >> PAGE_SHIFT; + sg_set_buf(msc->single_sgt.sgl, page_address(page), size); + + ret = dma_map_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, 1, + DMA_FROM_DEVICE); + if (ret < 0) + goto err_free_pages; + + msc->nr_pages = nr_pages; msc->base = page_address(page); - msc->base_addr = page_to_phys(page); + msc->base_addr = sg_dma_address(msc->single_sgt.sgl); return 0; + +err_free_pages: + __free_pages(page, order); + +err_free_sgt: + sg_free_table(&msc->single_sgt); + +err_out: + return ret; } /** @@ -643,10 +969,13 @@ static void msc_buffer_contig_free(struct msc *msc) { unsigned long off; + dma_unmap_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, + 1, DMA_FROM_DEVICE); + sg_free_table(&msc->single_sgt); + for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) { struct page *page = virt_to_page(msc->base + off); - page->mapping = NULL; __free_page(page); } @@ -669,6 +998,95 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc, return virt_to_page(msc->base + (pgoff << PAGE_SHIFT)); } +static int __msc_buffer_win_alloc(struct msc_window *win, + unsigned int nr_segs) +{ + struct scatterlist *sg_ptr; + void *block; + int i, ret; + + ret = sg_alloc_table(win->sgt, nr_segs, GFP_KERNEL); + if (ret) + return -ENOMEM; + + for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) { + block = dma_alloc_coherent(msc_dev(win->msc)->parent->parent, + PAGE_SIZE, &sg_dma_address(sg_ptr), + GFP_KERNEL); + if (!block) + goto err_nomem; + + sg_set_buf(sg_ptr, block, PAGE_SIZE); + } + + return nr_segs; + +err_nomem: + for_each_sg(win->sgt->sgl, sg_ptr, i, ret) + dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, + sg_virt(sg_ptr), sg_dma_address(sg_ptr)); + + sg_free_table(win->sgt); + + return -ENOMEM; +} + +#ifdef CONFIG_X86 +static void msc_buffer_set_uc(struct msc *msc) +{ + struct scatterlist *sg_ptr; + struct msc_window *win; + int i; + + if (msc->mode == MSC_MODE_SINGLE) { + set_memory_uc((unsigned long)msc->base, msc->nr_pages); + return; + } + + list_for_each_entry(win, &msc->win_list, entry) { + for_each_sg(win->sgt->sgl, sg_ptr, win->nr_segs, i) { + /* Set the page as uncached */ + set_memory_uc((unsigned long)sg_virt(sg_ptr), + PFN_DOWN(sg_ptr->length)); + } + } +} + +static void msc_buffer_set_wb(struct msc *msc) +{ + struct scatterlist *sg_ptr; + struct msc_window *win; + int i; + + if (msc->mode == MSC_MODE_SINGLE) { + set_memory_wb((unsigned long)msc->base, msc->nr_pages); + return; + } + + list_for_each_entry(win, &msc->win_list, entry) { + for_each_sg(win->sgt->sgl, sg_ptr, win->nr_segs, i) { + /* Reset the page to write-back */ + set_memory_wb((unsigned long)sg_virt(sg_ptr), + PFN_DOWN(sg_ptr->length)); + } + } +} +#else /* !X86 */ +static inline void +msc_buffer_set_uc(struct msc *msc) {} +static inline void msc_buffer_set_wb(struct msc *msc) {} +#endif /* CONFIG_X86 */ + +static struct page *msc_sg_page(struct scatterlist *sg) +{ + void *addr = sg_virt(sg); + + if (is_vmalloc_addr(addr)) + return vmalloc_to_page(addr); + + return sg_page(sg); +} + /** * msc_buffer_win_alloc() - alloc a window for a multiblock mode * @msc: MSC device @@ -682,44 +1100,44 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc, static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) { struct msc_window *win; - unsigned long size = PAGE_SIZE; - int i, ret = -ENOMEM; + int ret = -ENOMEM; if (!nr_blocks) return 0; - win = kzalloc(offsetof(struct msc_window, block[nr_blocks]), - GFP_KERNEL); + win = kzalloc(sizeof(*win), GFP_KERNEL); if (!win) return -ENOMEM; + win->msc = msc; + win->sgt = &win->_sgt; + win->lockout = WIN_READY; + spin_lock_init(&win->lo_lock); + if (!list_empty(&msc->win_list)) { - struct msc_window *prev = list_entry(msc->win_list.prev, - struct msc_window, entry); + struct msc_window *prev = list_last_entry(&msc->win_list, + struct msc_window, + entry); win->pgoff = prev->pgoff + prev->nr_blocks; } - for (i = 0; i < nr_blocks; i++) { - win->block[i].bdesc = - dma_alloc_coherent(msc_dev(msc)->parent->parent, size, - &win->block[i].addr, GFP_KERNEL); - - if (!win->block[i].bdesc) - goto err_nomem; + if (msc->mbuf && msc->mbuf->alloc_window) + ret = msc->mbuf->alloc_window(msc->mbuf_priv, &win->sgt, + nr_blocks << PAGE_SHIFT); + else + ret = __msc_buffer_win_alloc(win, nr_blocks); -#ifdef CONFIG_X86 - /* Set the page as uncached */ - set_memory_uc((unsigned long)win->block[i].bdesc, 1); -#endif - } + if (ret <= 0) + goto err_nomem; - win->msc = msc; + win->nr_segs = ret; win->nr_blocks = nr_blocks; if (list_empty(&msc->win_list)) { - msc->base = win->block[0].bdesc; - msc->base_addr = win->block[0].addr; + msc->base = msc_win_base(win); + msc->base_addr = msc_win_base_dma(win); + msc->cur_win = win; } list_add_tail(&win->entry, &msc->win_list); @@ -728,19 +1146,23 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) return 0; err_nomem: - for (i--; i >= 0; i--) { -#ifdef CONFIG_X86 - /* Reset the page to write-back before releasing */ - set_memory_wb((unsigned long)win->block[i].bdesc, 1); -#endif - dma_free_coherent(msc_dev(msc)->parent->parent, size, - win->block[i].bdesc, win->block[i].addr); - } kfree(win); return ret; } +static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win) +{ + struct scatterlist *sg; + int i; + + for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) { + dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, + sg_virt(sg), sg_dma_address(sg)); + } + sg_free_table(win->sgt); +} + /** * msc_buffer_win_free() - free a window from MSC's window list * @msc: MSC device @@ -751,8 +1173,6 @@ err_nomem: */ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) { - int i; - msc->nr_pages -= win->nr_blocks; list_del(&win->entry); @@ -761,17 +1181,10 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) msc->base_addr = 0; } - for (i = 0; i < win->nr_blocks; i++) { - struct page *page = virt_to_page(win->block[i].bdesc); - - page->mapping = NULL; -#ifdef CONFIG_X86 - /* Reset the page to write-back before releasing */ - set_memory_wb((unsigned long)win->block[i].bdesc, 1); -#endif - dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, - win->block[i].bdesc, win->block[i].addr); - } + if (msc->mbuf && msc->mbuf->free_window) + msc->mbuf->free_window(msc->mbuf_priv, win->sgt); + else + __msc_buffer_win_free(msc, win); kfree(win); } @@ -789,6 +1202,7 @@ static void msc_buffer_relink(struct msc *msc) /* call with msc::mutex locked */ list_for_each_entry(win, &msc->win_list, entry) { + struct scatterlist *sg; unsigned int blk; u32 sw_tag = 0; @@ -798,35 +1212,34 @@ static void msc_buffer_relink(struct msc *msc) */ if (msc_is_last_win(win)) { sw_tag |= MSC_SW_TAG_LASTWIN; - next_win = list_entry(msc->win_list.next, - struct msc_window, entry); + next_win = list_first_entry(&msc->win_list, + struct msc_window, entry); } else { - next_win = list_entry(win->entry.next, - struct msc_window, entry); + next_win = list_next_entry(win, entry); } - for (blk = 0; blk < win->nr_blocks; blk++) { - struct msc_block_desc *bdesc = win->block[blk].bdesc; + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); memset(bdesc, 0, sizeof(*bdesc)); - bdesc->next_win = next_win->block[0].addr >> PAGE_SHIFT; + bdesc->next_win = msc_win_base_pfn(next_win); /* * Similarly to last window, last block should point * to the first one. */ - if (blk == win->nr_blocks - 1) { + if (blk == win->nr_segs - 1) { sw_tag |= MSC_SW_TAG_LASTBLK; - bdesc->next_blk = - win->block[0].addr >> PAGE_SHIFT; + bdesc->next_blk = msc_win_base_pfn(win); } else { - bdesc->next_blk = - win->block[blk + 1].addr >> PAGE_SHIFT; + dma_addr_t addr = sg_dma_address(sg_next(sg)); + + bdesc->next_blk = PFN_DOWN(addr); } bdesc->sw_tag = sw_tag; - bdesc->block_sz = PAGE_SIZE / 64; + bdesc->block_sz = sg->length / 64; } } @@ -874,6 +1287,8 @@ static int msc_buffer_multi_alloc(struct msc *msc, unsigned long *nr_pages, */ static void msc_buffer_free(struct msc *msc) { + msc_buffer_set_wb(msc); + if (msc->mode == MSC_MODE_SINGLE) msc_buffer_contig_free(msc); else if (msc->mode == MSC_MODE_MULTI) @@ -883,7 +1298,8 @@ static void msc_buffer_free(struct msc *msc) /** * msc_buffer_alloc() - allocate a buffer for MSC * @msc: MSC device - * @size: allocation size in bytes + * @nr_pages: number of pages for each window + * @nr_wins: number of windows * * Allocate a storage buffer for MSC, depending on the msc::mode, it will be * either done via msc_buffer_contig_alloc() for SINGLE operation mode or @@ -913,10 +1329,12 @@ static int msc_buffer_alloc(struct msc *msc, unsigned long *nr_pages, } else if (msc->mode == MSC_MODE_MULTI) { ret = msc_buffer_multi_alloc(msc, nr_pages, nr_wins); } else { - ret = -ENOTSUPP; + ret = -EINVAL; } if (!ret) { + msc_buffer_set_uc(msc); + /* allocation should be visible before the counter goes to 0 */ smp_mb__before_atomic(); @@ -960,6 +1378,9 @@ static int msc_buffer_unlocked_free_unless_used(struct msc *msc) * @msc: MSC device * * This is a locked version of msc_buffer_unlocked_free_unless_used(). + * + * Return: 0 on successful deallocation or if there was no buffer to + * deallocate, -EBUSY if there are active users. */ static int msc_buffer_free_unless_used(struct msc *msc) { @@ -985,6 +1406,8 @@ static int msc_buffer_free_unless_used(struct msc *msc) static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff) { struct msc_window *win; + struct scatterlist *sg; + unsigned int blk; if (msc->mode == MSC_MODE_SINGLE) return msc_buffer_contig_get_page(msc, pgoff); @@ -997,7 +1420,18 @@ static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff) found: pgoff -= win->pgoff; - return virt_to_page(win->block[pgoff].bdesc); + + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct page *page = msc_sg_page(sg); + size_t pgsz = PFN_DOWN(sg->length); + + if (pgoff < pgsz) + return page + pgoff; + + pgoff -= pgsz; + } + + return NULL; } /** @@ -1015,6 +1449,8 @@ struct msc_win_to_user_struct { * @data: callback's private data * @src: source buffer * @len: amount of data to copy from the source buffer + * + * Return: >= %0 for success or -errno for error. */ static unsigned long msc_win_to_user(void *data, void *src, size_t len) { @@ -1136,7 +1572,7 @@ static ssize_t intel_th_msc_read(struct file *file, char __user *buf, if (ret >= 0) *ppos = iter->offset; } else { - ret = -ENOTSUPP; + ret = -EINVAL; } put_count: @@ -1161,22 +1597,10 @@ static void msc_mmap_close(struct vm_area_struct *vma) { struct msc_iter *iter = vma->vm_file->private_data; struct msc *msc = iter->msc; - unsigned long pg; if (!atomic_dec_and_mutex_lock(&msc->mmap_count, &msc->buf_mutex)) return; - /* drop page _refcounts */ - for (pg = 0; pg < msc->nr_pages; pg++) { - struct page *page = msc_buffer_get_page(msc, pg); - - if (WARN_ON_ONCE(!page)) - continue; - - if (page->mapping) - page->mapping = NULL; - } - /* last mapping -- drop user_count */ atomic_dec(&msc->user_count); mutex_unlock(&msc->buf_mutex); @@ -1186,16 +1610,14 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf) { struct msc_iter *iter = vmf->vma->vm_file->private_data; struct msc *msc = iter->msc; + struct page *page; - vmf->page = msc_buffer_get_page(msc, vmf->pgoff); - if (!vmf->page) + page = msc_buffer_get_page(msc, vmf->pgoff); + if (!page) return VM_FAULT_SIGBUS; - get_page(vmf->page); - vmf->page->mapping = vmf->vma->vm_file->f_mapping; - vmf->page->index = vmf->pgoff; - - return 0; + get_page(page); + return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn(page)); } static const struct vm_operations_struct msc_mmap_ops = { @@ -1236,7 +1658,7 @@ out: atomic_dec(&msc->user_count); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTCOPY; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTCOPY | VM_MIXEDMAP); vma->vm_ops = &msc_mmap_ops; return ret; } @@ -1246,15 +1668,30 @@ static const struct file_operations intel_th_msc_fops = { .release = intel_th_msc_release, .read = intel_th_msc_read, .mmap = intel_th_msc_mmap, - .llseek = no_llseek, .owner = THIS_MODULE, }; +static void intel_th_msc_wait_empty(struct intel_th_device *thdev) +{ + struct msc *msc = dev_get_drvdata(&thdev->dev); + unsigned long count; + u32 reg; + + for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH; + count && !(reg & MSCSTS_PLE); count--) { + reg = __raw_readl(msc->reg_base + REG_MSU_MSC0STS); + cpu_relax(); + } + + if (!count) + dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n"); +} + static int intel_th_msc_init(struct msc *msc) { atomic_set(&msc->user_count, -1); - msc->mode = MSC_MODE_MULTI; + msc->mode = msc->multi_is_broken ? MSC_MODE_SINGLE : MSC_MODE_MULTI; mutex_init(&msc->buf_mutex); INIT_LIST_HEAD(&msc->win_list); INIT_LIST_HEAD(&msc->iter_list); @@ -1266,6 +1703,110 @@ static int intel_th_msc_init(struct msc *msc) return 0; } +static int msc_win_switch(struct msc *msc) +{ + struct msc_window *first; + + if (list_empty(&msc->win_list)) + return -EINVAL; + + first = list_first_entry(&msc->win_list, struct msc_window, entry); + + if (msc_is_last_win(msc->cur_win)) + msc->cur_win = first; + else + msc->cur_win = list_next_entry(msc->cur_win, entry); + + msc->base = msc_win_base(msc->cur_win); + msc->base_addr = msc_win_base_dma(msc->cur_win); + + intel_th_trace_switch(msc->thdev); + + return 0; +} + +/** + * intel_th_msc_window_unlock - put the window back in rotation + * @dev: MSC device to which this relates + * @sgt: buffer's sg_table for the window, does nothing if NULL + */ +void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt) +{ + struct msc *msc = dev_get_drvdata(dev); + struct msc_window *win; + + if (!sgt) + return; + + win = msc_find_window(msc, sgt, false); + if (!win) + return; + + msc_win_set_lockout(win, WIN_LOCKED, WIN_READY); + if (msc->switch_on_unlock == win) { + msc->switch_on_unlock = NULL; + msc_win_switch(msc); + } +} +EXPORT_SYMBOL_GPL(intel_th_msc_window_unlock); + +static void msc_work(struct work_struct *work) +{ + struct msc *msc = container_of(work, struct msc, work); + + intel_th_msc_deactivate(msc->thdev); +} + +static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) +{ + struct msc *msc = dev_get_drvdata(&thdev->dev); + u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); + u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + struct msc_window *win, *next_win; + + if (!msc->do_irq || !msc->mbuf) + return IRQ_NONE; + + msusts &= mask; + + if (!msusts) + return msc->enabled ? IRQ_HANDLED : IRQ_NONE; + + iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS); + + if (!msc->enabled) + return IRQ_NONE; + + /* grab the window before we do the switch */ + win = msc->cur_win; + if (!win) + return IRQ_HANDLED; + next_win = msc_next_window(win); + if (!next_win) + return IRQ_HANDLED; + + /* next window: if READY, proceed, if LOCKED, stop the trace */ + if (msc_win_set_lockout(next_win, WIN_READY, WIN_INUSE)) { + if (msc->stop_on_full) + schedule_work(&msc->work); + else + msc->switch_on_unlock = next_win; + + return IRQ_HANDLED; + } + + /* current window: INUSE -> LOCKED */ + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); + + msc_win_switch(msc); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + + return IRQ_HANDLED; +} + static const char * const msc_mode[] = { [MSC_MODE_SINGLE] = "single", [MSC_MODE_MULTI] = "multi", @@ -1300,21 +1841,43 @@ wrap_store(struct device *dev, struct device_attribute *attr, const char *buf, static DEVICE_ATTR_RW(wrap); +static void msc_buffer_unassign(struct msc *msc) +{ + lockdep_assert_held(&msc->buf_mutex); + + if (!msc->mbuf) + return; + + msc->mbuf->unassign(msc->mbuf_priv); + msu_buffer_put(msc->mbuf); + msc->mbuf_priv = NULL; + msc->mbuf = NULL; +} + static ssize_t mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct msc *msc = dev_get_drvdata(dev); + const char *mode = msc_mode[msc->mode]; + ssize_t ret; + + mutex_lock(&msc->buf_mutex); + if (msc->mbuf) + mode = msc->mbuf->name; + ret = scnprintf(buf, PAGE_SIZE, "%s\n", mode); + mutex_unlock(&msc->buf_mutex); - return scnprintf(buf, PAGE_SIZE, "%s\n", msc_mode[msc->mode]); + return ret; } static ssize_t mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + const struct msu_buffer *mbuf = NULL; struct msc *msc = dev_get_drvdata(dev); size_t len = size; - char *cp; + char *cp, *mode; int i, ret; if (!capable(CAP_SYS_RAWIO)) @@ -1324,17 +1887,67 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, if (cp) len = cp - buf; - for (i = 0; i < ARRAY_SIZE(msc_mode); i++) - if (!strncmp(msc_mode[i], buf, len)) - goto found; + mode = kstrndup(buf, len, GFP_KERNEL); + if (!mode) + return -ENOMEM; + + i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode); + if (i >= 0) { + kfree(mode); + goto found; + } + + /* Buffer sinks only work with a usable IRQ */ + if (!msc->do_irq) { + kfree(mode); + return -EINVAL; + } + + mbuf = msu_buffer_get(mode); + kfree(mode); + if (mbuf) + goto found; return -EINVAL; found: + if (i == MSC_MODE_MULTI && msc->multi_is_broken) + return -EOPNOTSUPP; + mutex_lock(&msc->buf_mutex); + ret = 0; + + /* Same buffer: do nothing */ + if (mbuf && mbuf == msc->mbuf) { + /* put the extra reference we just got */ + msu_buffer_put(mbuf); + goto unlock; + } + ret = msc_buffer_unlocked_free_unless_used(msc); - if (!ret) - msc->mode = i; + if (ret) + goto unlock; + + if (mbuf) { + void *mbuf_priv = mbuf->assign(dev, &i); + + if (!mbuf_priv) { + ret = -ENOMEM; + goto unlock; + } + + msc_buffer_unassign(msc); + msc->mbuf_priv = mbuf_priv; + msc->mbuf = mbuf; + } else { + msc_buffer_unassign(msc); + } + + msc->mode = i; + +unlock: + if (ret && mbuf) + msu_buffer_put(mbuf); mutex_unlock(&msc->buf_mutex); return ret ? ret : size; @@ -1411,7 +2024,7 @@ nr_pages_store(struct device *dev, struct device_attribute *attr, } nr_wins++; - rewin = krealloc(win, sizeof(*win) * nr_wins, GFP_KERNEL); + rewin = krealloc_array(win, nr_wins, sizeof(*win), GFP_KERNEL); if (!rewin) { kfree(win); return -ENOMEM; @@ -1440,14 +2053,71 @@ free_win: static DEVICE_ATTR_RW(nr_pages); +static ssize_t +win_switch_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t size) +{ + struct msc *msc = dev_get_drvdata(dev); + unsigned long val; + int ret; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val != 1) + return -EINVAL; + + ret = -EINVAL; + mutex_lock(&msc->buf_mutex); + /* + * Window switch can only happen in the "multi" mode. + * If a external buffer is engaged, they have the full + * control over window switching. + */ + if (msc->mode == MSC_MODE_MULTI && !msc->mbuf) + ret = msc_win_switch(msc); + mutex_unlock(&msc->buf_mutex); + + return ret ? ret : size; +} + +static DEVICE_ATTR_WO(win_switch); + +static ssize_t stop_on_full_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct msc *msc = dev_get_drvdata(dev); + + return sprintf(buf, "%d\n", msc->stop_on_full); +} + +static ssize_t stop_on_full_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t size) +{ + struct msc *msc = dev_get_drvdata(dev); + int ret; + + ret = kstrtobool(buf, &msc->stop_on_full); + if (ret) + return ret; + + return size; +} + +static DEVICE_ATTR_RW(stop_on_full); + static struct attribute *msc_output_attrs[] = { &dev_attr_wrap.attr, &dev_attr_mode.attr, &dev_attr_nr_pages.attr, + &dev_attr_win_switch.attr, + &dev_attr_stop_on_full.attr, NULL, }; -static struct attribute_group msc_output_group = { +static const struct attribute_group msc_output_group = { .attrs = msc_output_attrs, }; @@ -1471,11 +2141,20 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) if (!msc) return -ENOMEM; + res = intel_th_device_get_resource(thdev, IORESOURCE_IRQ, 1); + if (!res) + msc->do_irq = 1; + + if (INTEL_TH_CAP(to_intel_th(thdev), multi_is_broken)) + msc->multi_is_broken = 1; + msc->index = thdev->id; msc->thdev = thdev; msc->reg_base = base + msc->index * 0x100; + msc->msu_base = base; + INIT_WORK(&msc->work, msc_work); err = intel_th_msc_init(msc); if (err) return err; @@ -1504,6 +2183,8 @@ static void intel_th_msc_remove(struct intel_th_device *thdev) static struct intel_th_driver intel_th_msc_driver = { .probe = intel_th_msc_probe, .remove = intel_th_msc_remove, + .irq = intel_th_msc_interrupt, + .wait_empty = intel_th_msc_wait_empty, .activate = intel_th_msc_activate, .deactivate = intel_th_msc_deactivate, .fops = &intel_th_msc_fops, diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index 9cc8aced6116..e771f509bd02 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel(R) Trace Hub Memory Storage Unit (MSU) data structures * @@ -11,6 +11,7 @@ enum { REG_MSU_MSUPARAMS = 0x0000, REG_MSU_MSUSTS = 0x0008, + REG_MSU_MINTCTL = 0x0004, /* MSU-global interrupt control */ REG_MSU_MSC0CTL = 0x0100, /* MSC0 control */ REG_MSU_MSC0STS = 0x0104, /* MSC0 status */ REG_MSU_MSC0BAR = 0x0108, /* MSC0 output base address */ @@ -28,6 +29,8 @@ enum { /* MSUSTS bits */ #define MSUSTS_MSU_INT BIT(0) +#define MSUSTS_MSC0BLAST BIT(16) +#define MSUSTS_MSC1BLAST BIT(24) /* MSCnCTL bits */ #define MSC_EN BIT(0) @@ -36,13 +39,10 @@ enum { #define MSC_MODE (BIT(4) | BIT(5)) #define MSC_LEN (BIT(8) | BIT(9) | BIT(10)) -/* MSC operating modes (MSC_MODE) */ -enum { - MSC_MODE_SINGLE = 0, - MSC_MODE_MULTI, - MSC_MODE_EXI, - MSC_MODE_DEBUG, -}; +/* MINTCTL bits */ +#define MICDE BIT(0) +#define M0BLIE BIT(16) +#define M1BLIE BIT(24) /* MSCnSTS bits */ #define MSCSTS_WRAPSTAT BIT(1) /* Wrap occurred */ @@ -85,9 +85,19 @@ static inline unsigned long msc_data_sz(struct msc_block_desc *bdesc) return bdesc->valid_dw * 4 - MSC_BDESC; } +static inline unsigned long msc_total_sz(struct msc_block_desc *bdesc) +{ + return bdesc->valid_dw * 4; +} + +static inline unsigned long msc_block_sz(struct msc_block_desc *bdesc) +{ + return bdesc->block_sz * 64 - MSC_BDESC; +} + static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) { - if (bdesc->hw_tag & MSC_HW_TAG_BLOCKWRAP) + if (bdesc->hw_tag & (MSC_HW_TAG_BLOCKWRAP | MSC_HW_TAG_WINWRAP)) return true; return false; @@ -96,7 +106,7 @@ static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) static inline bool msc_block_last_written(struct msc_block_desc *bdesc) { if ((bdesc->hw_tag & MSC_HW_TAG_ENDBIT) || - (msc_data_sz(bdesc) != DATA_IN_PAGE)) + (msc_data_sz(bdesc) != msc_block_sz(bdesc))) return true; return false; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 1cf6290d6435..e3def163d5cf 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -17,7 +17,12 @@ #define DRIVER_NAME "intel_th_pci" -#define BAR_MASK (BIT(TH_MMIO_CONFIG) | BIT(TH_MMIO_SW)) +enum { + TH_PCI_CONFIG_BAR = 0, + TH_PCI_STH_SW_BAR = 2, + TH_PCI_RTIT_BAR = 4, +}; + #define PCI_REG_NPKDSC 0x80 #define NPKDSC_TSACT BIT(5) @@ -65,22 +70,45 @@ static void intel_th_pci_deactivate(struct intel_th *th) static int intel_th_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - struct intel_th_drvdata *drvdata = (void *)id->driver_data; + const struct intel_th_drvdata *drvdata = (void *)id->driver_data; + struct resource resource[TH_MMIO_END + TH_NVEC_MAX] = { + [TH_MMIO_CONFIG] = pdev->resource[TH_PCI_CONFIG_BAR], + [TH_MMIO_SW] = pdev->resource[TH_PCI_STH_SW_BAR], + }; + int err, r = TH_MMIO_SW + 1, i; struct intel_th *th; - int err; err = pcim_enable_device(pdev); if (err) return err; - err = pcim_iomap_regions_request_all(pdev, BAR_MASK, DRIVER_NAME); + err = pcim_request_all_regions(pdev, DRIVER_NAME); if (err) return err; - th = intel_th_alloc(&pdev->dev, drvdata, pdev->resource, - DEVICE_COUNT_RESOURCE, pdev->irq); - if (IS_ERR(th)) - return PTR_ERR(th); + if (!pcim_iomap(pdev, TH_PCI_CONFIG_BAR, 0)) + return -ENOMEM; + + if (!pcim_iomap(pdev, TH_PCI_STH_SW_BAR, 0)) + return -ENOMEM; + + if (pdev->resource[TH_PCI_RTIT_BAR].start) { + resource[TH_MMIO_RTIT] = pdev->resource[TH_PCI_RTIT_BAR]; + r++; + } + + err = pci_alloc_irq_vectors(pdev, 1, 8, PCI_IRQ_ALL_TYPES); + if (err > 0) + for (i = 0; i < err; i++, r++) { + resource[r].flags = IORESOURCE_IRQ; + resource[r].start = pci_irq_vector(pdev, i); + } + + th = intel_th_alloc(&pdev->dev, drvdata, resource, r); + if (IS_ERR(th)) { + err = PTR_ERR(th); + goto err_free_irq; + } th->activate = intel_th_pci_activate; th->deactivate = intel_th_pci_deactivate; @@ -88,6 +116,10 @@ static int intel_th_pci_probe(struct pci_dev *pdev, pci_set_master(pdev); return 0; + +err_free_irq: + pci_free_irq_vectors(pdev); + return err; } static void intel_th_pci_remove(struct pci_dev *pdev) @@ -95,10 +127,17 @@ static void intel_th_pci_remove(struct pci_dev *pdev) struct intel_th *th = pci_get_drvdata(pdev); intel_th_free(th); + + pci_free_irq_vectors(pdev); } +static const struct intel_th_drvdata intel_th_1x_multi_is_broken = { + .multi_is_broken = 1, +}; + static const struct intel_th_drvdata intel_th_2x = { .tscu_enable = 1, + .has_mintctl = 1, }; static const struct pci_device_id intel_th_pci_id_table[] = { @@ -128,7 +167,7 @@ static const struct pci_device_id intel_th_pci_id_table[] = { { /* Kaby Lake PCH-H */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa2a6), - .driver_data = (kernel_ulong_t)0, + .driver_data = (kernel_ulong_t)&intel_th_1x_multi_is_broken, }, { /* Denverton */ @@ -141,6 +180,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .driver_data = (kernel_ulong_t)0, }, { + /* Lewisburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa226), + .driver_data = (kernel_ulong_t)0, + }, + { /* Gemini Lake */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e), .driver_data = (kernel_ulong_t)&intel_th_2x, @@ -165,6 +209,156 @@ static const struct pci_device_id intel_th_pci_id_table[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x34a6), .driver_data = (kernel_ulong_t)&intel_th_2x, }, + { + /* Comet Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x02a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Comet Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Comet Lake PCH-V */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa3a6), + .driver_data = (kernel_ulong_t)&intel_th_1x_multi_is_broken, + }, + { + /* Ice Lake NNPI */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Ice Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x8a29), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Tiger Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x9a33), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Tiger Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Tiger Lake PCH-H */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x43a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Jasper Lake PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Jasper Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4e29), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Elkhart Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4529), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Elkhart Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4b26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Emmitsburg PCH */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x1bcc), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Alder Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7aa6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Alder Lake-P */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x51a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Alder Lake-M */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x54a6), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Meteor Lake-P */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7e24), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Meteor Lake-S */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7f26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Meteor Lake-S CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xae24), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Raptor Lake-S */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7a26), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Raptor Lake-S CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa76f), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Granite Rapids */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0963), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Granite Rapids SOC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3256), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Sapphire Rapids SOC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3456), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Lunar Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa824), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Arrow Lake */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Panther Lake-H */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Panther Lake-P/U */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe424), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Alder Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, + { + /* Rocket Lake CPU */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c19), + .driver_data = (kernel_ulong_t)&intel_th_2x, + }, { 0 }, }; diff --git a/drivers/hwtracing/intel_th/pti.c b/drivers/hwtracing/intel_th/pti.c index 56694339cb06..09132ab8bc23 100644 --- a/drivers/hwtracing/intel_th/pti.c +++ b/drivers/hwtracing/intel_th/pti.c @@ -142,7 +142,7 @@ static struct attribute *pti_output_attrs[] = { NULL, }; -static struct attribute_group pti_output_group = { +static const struct attribute_group pti_output_group = { .attrs = pti_output_attrs, }; @@ -272,19 +272,17 @@ static ssize_t lpp_dest_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { struct pti_device *pti = dev_get_drvdata(dev); - ssize_t ret = -EINVAL; int i; - for (i = 0; i < ARRAY_SIZE(lpp_dest_str); i++) - if (sysfs_streq(buf, lpp_dest_str[i])) - break; + i = sysfs_match_string(lpp_dest_str, buf); + if (i < 0) + return i; - if (i < ARRAY_SIZE(lpp_dest_str) && pti->lpp_dest_mask & BIT(i)) { - pti->lpp_dest = i; - ret = size; - } + if (!(pti->lpp_dest_mask & BIT(i))) + return -EINVAL; - return ret; + pti->lpp_dest = i; + return size; } static DEVICE_ATTR_RW(lpp_dest); @@ -297,7 +295,7 @@ static struct attribute *lpp_output_attrs[] = { NULL, }; -static struct attribute_group lpp_output_group = { +static const struct attribute_group lpp_output_group = { .attrs = lpp_output_attrs, }; diff --git a/drivers/hwtracing/intel_th/pti.h b/drivers/hwtracing/intel_th/pti.h index e9381babc84c..7dfc0431333b 100644 --- a/drivers/hwtracing/intel_th/pti.h +++ b/drivers/hwtracing/intel_th/pti.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ /* * Intel(R) Trace Hub PTI output data structures * diff --git a/drivers/hwtracing/intel_th/sth.c b/drivers/hwtracing/intel_th/sth.c index 4b7ae47789d2..428f595a28a0 100644 --- a/drivers/hwtracing/intel_th/sth.c +++ b/drivers/hwtracing/intel_th/sth.c @@ -70,8 +70,8 @@ static ssize_t notrace sth_stm_packet(struct stm_data *stm_data, struct sth_device *sth = container_of(stm_data, struct sth_device, stm); struct intel_th_channel __iomem *out = sth_channel(sth, master, channel); - u64 __iomem *outp = &out->Dn; unsigned long reg = REG_STH_TRIG; + u64 __iomem *outp; #ifndef CONFIG_64BIT if (size > 4) @@ -84,8 +84,12 @@ static ssize_t notrace sth_stm_packet(struct stm_data *stm_data, /* Global packets (GERR, XSYNC, TRIG) are sent with register writes */ case STP_PACKET_GERR: reg += 4; + fallthrough; + case STP_PACKET_XSYNC: reg += 8; + fallthrough; + case STP_PACKET_TRIG: if (flags & STP_PACKET_TIMESTAMPED) reg += 4; @@ -157,9 +161,7 @@ static int sth_stm_link(struct stm_data *stm_data, unsigned int master, { struct sth_device *sth = container_of(stm_data, struct sth_device, stm); - intel_th_set_output(to_intel_th_device(sth->dev), master); - - return 0; + return intel_th_set_output(to_intel_th_device(sth->dev), master); } static int intel_th_sw_init(struct sth_device *sth) diff --git a/drivers/hwtracing/ptt/Kconfig b/drivers/hwtracing/ptt/Kconfig new file mode 100644 index 000000000000..6d46a09ffeb9 --- /dev/null +++ b/drivers/hwtracing/ptt/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +config HISI_PTT + tristate "HiSilicon PCIe Tune and Trace Device" + depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on PCI && HAS_DMA && HAS_IOMEM && PERF_EVENTS + help + HiSilicon PCIe Tune and Trace device exists as a PCIe RCiEP + device, and it provides support for PCIe traffic tuning and + tracing TLP headers to the memory. + + This driver can also be built as a module. If so, the module + will be called hisi_ptt. diff --git a/drivers/hwtracing/ptt/Makefile b/drivers/hwtracing/ptt/Makefile new file mode 100644 index 000000000000..908c09a98161 --- /dev/null +++ b/drivers/hwtracing/ptt/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_HISI_PTT) += hisi_ptt.o diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c new file mode 100644 index 000000000000..3090479a2979 --- /dev/null +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -0,0 +1,1442 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for HiSilicon PCIe tune and trace device + * + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + * Author: Yicong Yang <yangyicong@hisilicon.com> + */ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/cpuhotplug.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iommu.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/sysfs.h> +#include <linux/vmalloc.h> + +#include "hisi_ptt.h" + +/* Dynamic CPU hotplug state used by PTT */ +static enum cpuhp_state hisi_ptt_pmu_online; + +static bool hisi_ptt_wait_tuning_finish(struct hisi_ptt *hisi_ptt) +{ + u32 val; + + return !readl_poll_timeout(hisi_ptt->iobase + HISI_PTT_TUNING_INT_STAT, + val, !(val & HISI_PTT_TUNING_INT_STAT_MASK), + HISI_PTT_WAIT_POLL_INTERVAL_US, + HISI_PTT_WAIT_TUNE_TIMEOUT_US); +} + +static ssize_t hisi_ptt_tune_attr_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev)); + struct dev_ext_attribute *ext_attr; + struct hisi_ptt_tune_desc *desc; + u32 reg; + u16 val; + + ext_attr = container_of(attr, struct dev_ext_attribute, attr); + desc = ext_attr->var; + + mutex_lock(&hisi_ptt->tune_lock); + + reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_CTRL); + reg &= ~(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB); + reg |= FIELD_PREP(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB, + desc->event_code); + writel(reg, hisi_ptt->iobase + HISI_PTT_TUNING_CTRL); + + /* Write all 1 to indicates it's the read process */ + writel(~0U, hisi_ptt->iobase + HISI_PTT_TUNING_DATA); + + if (!hisi_ptt_wait_tuning_finish(hisi_ptt)) { + mutex_unlock(&hisi_ptt->tune_lock); + return -ETIMEDOUT; + } + + reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_DATA); + reg &= HISI_PTT_TUNING_DATA_VAL_MASK; + val = FIELD_GET(HISI_PTT_TUNING_DATA_VAL_MASK, reg); + + mutex_unlock(&hisi_ptt->tune_lock); + return sysfs_emit(buf, "%u\n", val); +} + +static ssize_t hisi_ptt_tune_attr_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev)); + struct dev_ext_attribute *ext_attr; + struct hisi_ptt_tune_desc *desc; + u32 reg; + u16 val; + + ext_attr = container_of(attr, struct dev_ext_attribute, attr); + desc = ext_attr->var; + + if (kstrtou16(buf, 10, &val)) + return -EINVAL; + + mutex_lock(&hisi_ptt->tune_lock); + + reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_CTRL); + reg &= ~(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB); + reg |= FIELD_PREP(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB, + desc->event_code); + writel(reg, hisi_ptt->iobase + HISI_PTT_TUNING_CTRL); + writel(FIELD_PREP(HISI_PTT_TUNING_DATA_VAL_MASK, val), + hisi_ptt->iobase + HISI_PTT_TUNING_DATA); + + if (!hisi_ptt_wait_tuning_finish(hisi_ptt)) { + mutex_unlock(&hisi_ptt->tune_lock); + return -ETIMEDOUT; + } + + mutex_unlock(&hisi_ptt->tune_lock); + return count; +} + +#define HISI_PTT_TUNE_ATTR(_name, _val, _show, _store) \ + static struct hisi_ptt_tune_desc _name##_desc = { \ + .name = #_name, \ + .event_code = (_val), \ + }; \ + static struct dev_ext_attribute hisi_ptt_##_name##_attr = { \ + .attr = __ATTR(_name, 0600, _show, _store), \ + .var = &_name##_desc, \ + } + +#define HISI_PTT_TUNE_ATTR_COMMON(_name, _val) \ + HISI_PTT_TUNE_ATTR(_name, _val, \ + hisi_ptt_tune_attr_show, \ + hisi_ptt_tune_attr_store) + +/* + * The value of the tuning event are composed of two parts: main event code + * in BIT[0,15] and subevent code in BIT[16,23]. For example, qox_tx_cpl is + * a subevent of 'Tx path QoS control' which for tuning the weight of Tx + * completion TLPs. See hisi_ptt.rst documentation for more information. + */ +#define HISI_PTT_TUNE_QOS_TX_CPL (0x4 | (3 << 16)) +#define HISI_PTT_TUNE_QOS_TX_NP (0x4 | (4 << 16)) +#define HISI_PTT_TUNE_QOS_TX_P (0x4 | (5 << 16)) +#define HISI_PTT_TUNE_RX_ALLOC_BUF_LEVEL (0x5 | (6 << 16)) +#define HISI_PTT_TUNE_TX_ALLOC_BUF_LEVEL (0x5 | (7 << 16)) + +HISI_PTT_TUNE_ATTR_COMMON(qos_tx_cpl, HISI_PTT_TUNE_QOS_TX_CPL); +HISI_PTT_TUNE_ATTR_COMMON(qos_tx_np, HISI_PTT_TUNE_QOS_TX_NP); +HISI_PTT_TUNE_ATTR_COMMON(qos_tx_p, HISI_PTT_TUNE_QOS_TX_P); +HISI_PTT_TUNE_ATTR_COMMON(rx_alloc_buf_level, HISI_PTT_TUNE_RX_ALLOC_BUF_LEVEL); +HISI_PTT_TUNE_ATTR_COMMON(tx_alloc_buf_level, HISI_PTT_TUNE_TX_ALLOC_BUF_LEVEL); + +static struct attribute *hisi_ptt_tune_attrs[] = { + &hisi_ptt_qos_tx_cpl_attr.attr.attr, + &hisi_ptt_qos_tx_np_attr.attr.attr, + &hisi_ptt_qos_tx_p_attr.attr.attr, + &hisi_ptt_rx_alloc_buf_level_attr.attr.attr, + &hisi_ptt_tx_alloc_buf_level_attr.attr.attr, + NULL, +}; + +static struct attribute_group hisi_ptt_tune_group = { + .name = "tune", + .attrs = hisi_ptt_tune_attrs, +}; + +static u16 hisi_ptt_get_filter_val(u16 devid, bool is_port) +{ + if (is_port) + return BIT(HISI_PCIE_CORE_PORT_ID(devid & 0xff)); + + return devid; +} + +static bool hisi_ptt_wait_trace_hw_idle(struct hisi_ptt *hisi_ptt) +{ + u32 val; + + return !readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_STS, + val, val & HISI_PTT_TRACE_IDLE, + HISI_PTT_WAIT_POLL_INTERVAL_US, + HISI_PTT_WAIT_TRACE_TIMEOUT_US); +} + +static void hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt) +{ + u32 val; + + readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS, + val, !val, HISI_PTT_RESET_POLL_INTERVAL_US, + HISI_PTT_RESET_TIMEOUT_US); +} + +static void hisi_ptt_trace_end(struct hisi_ptt *hisi_ptt) +{ + writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + + /* Mask the interrupt on the end */ + writel(HISI_PTT_TRACE_INT_MASK_ALL, hisi_ptt->iobase + HISI_PTT_TRACE_INT_MASK); + + hisi_ptt->trace_ctrl.started = false; +} + +static int hisi_ptt_trace_start(struct hisi_ptt *hisi_ptt) +{ + struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl; + u32 val; + int i; + + /* Check device idle before start trace */ + if (!hisi_ptt_wait_trace_hw_idle(hisi_ptt)) { + pci_err(hisi_ptt->pdev, "Failed to start trace, the device is still busy\n"); + return -EBUSY; + } + + ctrl->started = true; + + /* Reset the DMA before start tracing */ + val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + val |= HISI_PTT_TRACE_CTRL_RST; + writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + + hisi_ptt_wait_dma_reset_done(hisi_ptt); + + val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + val &= ~HISI_PTT_TRACE_CTRL_RST; + writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + + /* Reset the index of current buffer */ + hisi_ptt->trace_ctrl.buf_index = 0; + + /* Zero the trace buffers */ + for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; i++) + memset(ctrl->trace_buf[i].addr, 0, HISI_PTT_TRACE_BUF_SIZE); + + /* Clear the interrupt status */ + writel(HISI_PTT_TRACE_INT_STAT_MASK, hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT); + writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_INT_MASK); + + /* Set the trace control register */ + val = FIELD_PREP(HISI_PTT_TRACE_CTRL_TYPE_SEL, ctrl->type); + val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_RXTX_SEL, ctrl->direction); + val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_DATA_FORMAT, ctrl->format); + val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_TARGET_SEL, hisi_ptt->trace_ctrl.filter); + if (!hisi_ptt->trace_ctrl.is_port) + val |= HISI_PTT_TRACE_CTRL_FILTER_MODE; + + /* Start the Trace */ + val |= HISI_PTT_TRACE_CTRL_EN; + writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL); + + return 0; +} + +static int hisi_ptt_update_aux(struct hisi_ptt *hisi_ptt, int index, bool stop) +{ + struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl; + struct perf_output_handle *handle = &ctrl->handle; + struct perf_event *event = handle->event; + struct hisi_ptt_pmu_buf *buf; + size_t size; + void *addr; + + buf = perf_get_aux(handle); + if (!buf || !handle->size) + return -EINVAL; + + addr = ctrl->trace_buf[ctrl->buf_index].addr; + + /* + * If we're going to stop, read the size of already traced data from + * HISI_PTT_TRACE_WR_STS. Otherwise we're coming from the interrupt, + * the data size is always HISI_PTT_TRACE_BUF_SIZE. + */ + if (stop) { + u32 reg; + + reg = readl(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS); + size = FIELD_GET(HISI_PTT_TRACE_WR_STS_WRITE, reg); + } else { + size = HISI_PTT_TRACE_BUF_SIZE; + } + + memcpy(buf->base + buf->pos, addr, size); + buf->pos += size; + + /* + * Always commit the data to the AUX buffer in time to make sure + * userspace got enough time to consume the data. + * + * If we're not going to stop, apply a new one and check whether + * there's enough room for the next trace. + */ + perf_aux_output_end(handle, size); + if (!stop) { + buf = perf_aux_output_begin(handle, event); + if (!buf) + return -EINVAL; + + buf->pos = handle->head % buf->length; + if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) { + perf_aux_output_end(handle, 0); + return -EINVAL; + } + } + + return 0; +} + +static irqreturn_t hisi_ptt_isr(int irq, void *context) +{ + struct hisi_ptt *hisi_ptt = context; + u32 status, buf_idx; + + status = readl(hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT); + if (!(status & HISI_PTT_TRACE_INT_STAT_MASK)) + return IRQ_NONE; + + buf_idx = ffs(status) - 1; + + /* Clear the interrupt status of buffer @buf_idx */ + writel(status, hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT); + + /* + * Update the AUX buffer and cache the current buffer index, + * as we need to know this and save the data when the trace + * is ended out of the interrupt handler. End the trace + * if the updating fails. + */ + if (hisi_ptt_update_aux(hisi_ptt, buf_idx, false)) + hisi_ptt_trace_end(hisi_ptt); + else + hisi_ptt->trace_ctrl.buf_index = (buf_idx + 1) % HISI_PTT_TRACE_BUF_CNT; + + return IRQ_HANDLED; +} + +static void hisi_ptt_irq_free_vectors(void *pdev) +{ + pci_free_irq_vectors(pdev); +} + +static int hisi_ptt_register_irq(struct hisi_ptt *hisi_ptt) +{ + struct pci_dev *pdev = hisi_ptt->pdev; + int ret; + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + pci_err(pdev, "failed to allocate irq vector, ret = %d\n", ret); + return ret; + } + + ret = devm_add_action_or_reset(&pdev->dev, hisi_ptt_irq_free_vectors, pdev); + if (ret < 0) + return ret; + + hisi_ptt->trace_irq = pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ); + ret = devm_request_irq(&pdev->dev, hisi_ptt->trace_irq, hisi_ptt_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME, + hisi_ptt); + if (ret) { + pci_err(pdev, "failed to request irq %d, ret = %d\n", + hisi_ptt->trace_irq, ret); + return ret; + } + + return 0; +} + +static void hisi_ptt_del_free_filter(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + if (filter->is_port) + hisi_ptt->port_mask &= ~hisi_ptt_get_filter_val(filter->devid, true); + + list_del(&filter->list); + kfree(filter->name); + kfree(filter); +} + +static struct hisi_ptt_filter_desc * +hisi_ptt_alloc_add_filter(struct hisi_ptt *hisi_ptt, u16 devid, bool is_port) +{ + struct hisi_ptt_filter_desc *filter; + u8 devfn = devid & 0xff; + char *filter_name; + + filter_name = kasprintf(GFP_KERNEL, "%04x:%02x:%02x.%d", pci_domain_nr(hisi_ptt->pdev->bus), + PCI_BUS_NUM(devid), PCI_SLOT(devfn), PCI_FUNC(devfn)); + if (!filter_name) { + pci_err(hisi_ptt->pdev, "failed to allocate name for filter %04x:%02x:%02x.%d\n", + pci_domain_nr(hisi_ptt->pdev->bus), PCI_BUS_NUM(devid), + PCI_SLOT(devfn), PCI_FUNC(devfn)); + return NULL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) { + pci_err(hisi_ptt->pdev, "failed to add filter for %s\n", + filter_name); + kfree(filter_name); + return NULL; + } + + filter->name = filter_name; + filter->is_port = is_port; + filter->devid = devid; + + if (filter->is_port) { + list_add_tail(&filter->list, &hisi_ptt->port_filters); + + /* Update the available port mask */ + hisi_ptt->port_mask |= hisi_ptt_get_filter_val(filter->devid, true); + } else { + list_add_tail(&filter->list, &hisi_ptt->req_filters); + } + + return filter; +} + +static ssize_t hisi_ptt_filter_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hisi_ptt_filter_desc *filter; + unsigned long filter_val; + + filter = container_of(attr, struct hisi_ptt_filter_desc, attr); + filter_val = hisi_ptt_get_filter_val(filter->devid, filter->is_port) | + (filter->is_port ? HISI_PTT_PMU_FILTER_IS_PORT : 0); + + return sysfs_emit(buf, "0x%05lx\n", filter_val); +} + +static int hisi_ptt_create_rp_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + struct kobject *kobj = &hisi_ptt->hisi_ptt_pmu.dev->kobj; + + sysfs_attr_init(&filter->attr.attr); + filter->attr.attr.name = filter->name; + filter->attr.attr.mode = 0400; /* DEVICE_ATTR_ADMIN_RO */ + filter->attr.show = hisi_ptt_filter_show; + + return sysfs_add_file_to_group(kobj, &filter->attr.attr, + HISI_PTT_RP_FILTERS_GRP_NAME); +} + +static void hisi_ptt_remove_rp_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + struct kobject *kobj = &hisi_ptt->hisi_ptt_pmu.dev->kobj; + + sysfs_remove_file_from_group(kobj, &filter->attr.attr, + HISI_PTT_RP_FILTERS_GRP_NAME); +} + +static int hisi_ptt_create_req_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + struct kobject *kobj = &hisi_ptt->hisi_ptt_pmu.dev->kobj; + + sysfs_attr_init(&filter->attr.attr); + filter->attr.attr.name = filter->name; + filter->attr.attr.mode = 0400; /* DEVICE_ATTR_ADMIN_RO */ + filter->attr.show = hisi_ptt_filter_show; + + return sysfs_add_file_to_group(kobj, &filter->attr.attr, + HISI_PTT_REQ_FILTERS_GRP_NAME); +} + +static void hisi_ptt_remove_req_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + struct kobject *kobj = &hisi_ptt->hisi_ptt_pmu.dev->kobj; + + sysfs_remove_file_from_group(kobj, &filter->attr.attr, + HISI_PTT_REQ_FILTERS_GRP_NAME); +} + +static int hisi_ptt_create_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + int ret; + + if (filter->is_port) + ret = hisi_ptt_create_rp_filter_attr(hisi_ptt, filter); + else + ret = hisi_ptt_create_req_filter_attr(hisi_ptt, filter); + + if (ret) + pci_err(hisi_ptt->pdev, "failed to create sysfs attribute for filter %s\n", + filter->name); + + return ret; +} + +static void hisi_ptt_remove_filter_attr(struct hisi_ptt *hisi_ptt, + struct hisi_ptt_filter_desc *filter) +{ + if (filter->is_port) + hisi_ptt_remove_rp_filter_attr(hisi_ptt, filter); + else + hisi_ptt_remove_req_filter_attr(hisi_ptt, filter); +} + +static void hisi_ptt_remove_all_filter_attributes(void *data) +{ + struct hisi_ptt_filter_desc *filter; + struct hisi_ptt *hisi_ptt = data; + + mutex_lock(&hisi_ptt->filter_lock); + + list_for_each_entry(filter, &hisi_ptt->req_filters, list) + hisi_ptt_remove_filter_attr(hisi_ptt, filter); + + list_for_each_entry(filter, &hisi_ptt->port_filters, list) + hisi_ptt_remove_filter_attr(hisi_ptt, filter); + + hisi_ptt->sysfs_inited = false; + mutex_unlock(&hisi_ptt->filter_lock); +} + +static int hisi_ptt_init_filter_attributes(struct hisi_ptt *hisi_ptt) +{ + struct hisi_ptt_filter_desc *filter; + int ret; + + mutex_lock(&hisi_ptt->filter_lock); + + /* + * Register the reset callback in the first stage. In reset we traverse + * the filters list to remove the sysfs attributes so the callback can + * be called safely even without below filter attributes creation. + */ + ret = devm_add_action(&hisi_ptt->pdev->dev, + hisi_ptt_remove_all_filter_attributes, + hisi_ptt); + if (ret) + goto out; + + list_for_each_entry(filter, &hisi_ptt->port_filters, list) { + ret = hisi_ptt_create_filter_attr(hisi_ptt, filter); + if (ret) + goto out; + } + + list_for_each_entry(filter, &hisi_ptt->req_filters, list) { + ret = hisi_ptt_create_filter_attr(hisi_ptt, filter); + if (ret) + goto out; + } + + hisi_ptt->sysfs_inited = true; +out: + mutex_unlock(&hisi_ptt->filter_lock); + return ret; +} + +static void hisi_ptt_update_filters(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct hisi_ptt_filter_update_info info; + struct hisi_ptt_filter_desc *filter; + struct hisi_ptt *hisi_ptt; + + hisi_ptt = container_of(delayed_work, struct hisi_ptt, work); + + if (!mutex_trylock(&hisi_ptt->filter_lock)) { + schedule_delayed_work(&hisi_ptt->work, HISI_PTT_WORK_DELAY_MS); + return; + } + + while (kfifo_get(&hisi_ptt->filter_update_kfifo, &info)) { + if (info.is_add) { + /* + * Notify the users if failed to add this filter, others + * still work and available. See the comments in + * hisi_ptt_init_filters(). + */ + filter = hisi_ptt_alloc_add_filter(hisi_ptt, info.devid, info.is_port); + if (!filter) + continue; + + /* + * If filters' sysfs entries hasn't been initialized, + * then we're still at probe stage. Add the filters to + * the list and later hisi_ptt_init_filter_attributes() + * will create sysfs attributes for all the filters. + */ + if (hisi_ptt->sysfs_inited && + hisi_ptt_create_filter_attr(hisi_ptt, filter)) { + hisi_ptt_del_free_filter(hisi_ptt, filter); + continue; + } + } else { + struct hisi_ptt_filter_desc *tmp; + struct list_head *target_list; + + target_list = info.is_port ? &hisi_ptt->port_filters : + &hisi_ptt->req_filters; + + list_for_each_entry_safe(filter, tmp, target_list, list) + if (filter->devid == info.devid) { + if (hisi_ptt->sysfs_inited) + hisi_ptt_remove_filter_attr(hisi_ptt, filter); + + hisi_ptt_del_free_filter(hisi_ptt, filter); + break; + } + } + } + + mutex_unlock(&hisi_ptt->filter_lock); +} + +/* + * A PCI bus notifier is used here for dynamically updating the filter + * list. + */ +static int hisi_ptt_notifier_call(struct notifier_block *nb, unsigned long action, + void *data) +{ + struct hisi_ptt *hisi_ptt = container_of(nb, struct hisi_ptt, hisi_ptt_nb); + struct hisi_ptt_filter_update_info info; + struct pci_dev *pdev, *root_port; + struct device *dev = data; + u32 port_devid; + + pdev = to_pci_dev(dev); + root_port = pcie_find_root_port(pdev); + if (!root_port) + return 0; + + port_devid = pci_dev_id(root_port); + if (port_devid < hisi_ptt->lower_bdf || + port_devid > hisi_ptt->upper_bdf) + return 0; + + info.is_port = pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT; + info.devid = pci_dev_id(pdev); + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + info.is_add = true; + break; + case BUS_NOTIFY_DEL_DEVICE: + info.is_add = false; + break; + default: + return 0; + } + + /* + * The FIFO size is 16 which is sufficient for almost all the cases, + * since each PCIe core will have most 8 Root Ports (typically only + * 1~4 Root Ports). On failure log the failed filter and let user + * handle it. + */ + if (kfifo_in_spinlocked(&hisi_ptt->filter_update_kfifo, &info, 1, + &hisi_ptt->filter_update_lock)) + schedule_delayed_work(&hisi_ptt->work, 0); + else + pci_warn(hisi_ptt->pdev, + "filter update fifo overflow for target %s\n", + pci_name(pdev)); + + return 0; +} + +static int hisi_ptt_init_filters(struct pci_dev *pdev, void *data) +{ + struct pci_dev *root_port = pcie_find_root_port(pdev); + struct hisi_ptt_filter_desc *filter; + struct hisi_ptt *hisi_ptt = data; + u32 port_devid; + + if (!root_port) + return 0; + + port_devid = pci_dev_id(root_port); + if (port_devid < hisi_ptt->lower_bdf || + port_devid > hisi_ptt->upper_bdf) + return 0; + + /* + * We won't fail the probe if filter allocation failed here. The filters + * should be partial initialized and users would know which filter fails + * through the log. Other functions of PTT device are still available. + */ + filter = hisi_ptt_alloc_add_filter(hisi_ptt, pci_dev_id(pdev), + pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT); + if (!filter) + return -ENOMEM; + + return 0; +} + +static void hisi_ptt_release_filters(void *data) +{ + struct hisi_ptt_filter_desc *filter, *tmp; + struct hisi_ptt *hisi_ptt = data; + + list_for_each_entry_safe(filter, tmp, &hisi_ptt->req_filters, list) + hisi_ptt_del_free_filter(hisi_ptt, filter); + + list_for_each_entry_safe(filter, tmp, &hisi_ptt->port_filters, list) + hisi_ptt_del_free_filter(hisi_ptt, filter); +} + +static int hisi_ptt_config_trace_buf(struct hisi_ptt *hisi_ptt) +{ + struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl; + struct device *dev = &hisi_ptt->pdev->dev; + int i; + + ctrl->trace_buf = devm_kcalloc(dev, HISI_PTT_TRACE_BUF_CNT, + sizeof(*ctrl->trace_buf), GFP_KERNEL); + if (!ctrl->trace_buf) + return -ENOMEM; + + for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; ++i) { + ctrl->trace_buf[i].addr = dmam_alloc_coherent(dev, HISI_PTT_TRACE_BUF_SIZE, + &ctrl->trace_buf[i].dma, + GFP_KERNEL); + if (!ctrl->trace_buf[i].addr) + return -ENOMEM; + } + + /* Configure the trace DMA buffer */ + for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; i++) { + writel(lower_32_bits(ctrl->trace_buf[i].dma), + hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_BASE_LO_0 + + i * HISI_PTT_TRACE_ADDR_STRIDE); + writel(upper_32_bits(ctrl->trace_buf[i].dma), + hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_BASE_HI_0 + + i * HISI_PTT_TRACE_ADDR_STRIDE); + } + writel(HISI_PTT_TRACE_BUF_SIZE, hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_SIZE); + + return 0; +} + +static int hisi_ptt_init_ctrls(struct hisi_ptt *hisi_ptt) +{ + struct pci_dev *pdev = hisi_ptt->pdev; + struct pci_bus *bus; + int ret; + u32 reg; + + INIT_DELAYED_WORK(&hisi_ptt->work, hisi_ptt_update_filters); + INIT_KFIFO(hisi_ptt->filter_update_kfifo); + spin_lock_init(&hisi_ptt->filter_update_lock); + + INIT_LIST_HEAD(&hisi_ptt->port_filters); + INIT_LIST_HEAD(&hisi_ptt->req_filters); + mutex_init(&hisi_ptt->filter_lock); + + ret = hisi_ptt_config_trace_buf(hisi_ptt); + if (ret) + return ret; + + /* + * The device range register provides the information about the root + * ports which the RCiEP can control and trace. The RCiEP and the root + * ports which it supports are on the same PCIe core, with same domain + * number but maybe different bus number. The device range register + * will tell us which root ports we can support, Bit[31:16] indicates + * the upper BDF numbers of the root port, while Bit[15:0] indicates + * the lower. + */ + reg = readl(hisi_ptt->iobase + HISI_PTT_DEVICE_RANGE); + hisi_ptt->upper_bdf = FIELD_GET(HISI_PTT_DEVICE_RANGE_UPPER, reg); + hisi_ptt->lower_bdf = FIELD_GET(HISI_PTT_DEVICE_RANGE_LOWER, reg); + + bus = pci_find_bus(pci_domain_nr(pdev->bus), PCI_BUS_NUM(hisi_ptt->upper_bdf)); + if (bus) + pci_walk_bus(bus, hisi_ptt_init_filters, hisi_ptt); + + ret = devm_add_action_or_reset(&pdev->dev, hisi_ptt_release_filters, hisi_ptt); + if (ret) + return ret; + + hisi_ptt->trace_ctrl.on_cpu = -1; + return 0; +} + +static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev)); + const cpumask_t *cpumask = cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev)); + + return cpumap_print_to_pagebuf(true, buf, cpumask); +} +static DEVICE_ATTR_RO(cpumask); + +static struct attribute *hisi_ptt_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static const struct attribute_group hisi_ptt_cpumask_attr_group = { + .attrs = hisi_ptt_cpumask_attrs, +}; + +/* + * Bit 19 indicates the filter type, 1 for Root Port filter and 0 for Requester + * filter. Bit[15:0] indicates the filter value, for Root Port filter it's + * a bit mask of desired ports and for Requester filter it's the Requester ID + * of the desired PCIe function. Bit[18:16] is reserved for extension. + * + * See hisi_ptt.rst documentation for detailed information. + */ +PMU_FORMAT_ATTR(filter, "config:0-19"); +PMU_FORMAT_ATTR(direction, "config:20-23"); +PMU_FORMAT_ATTR(type, "config:24-31"); +PMU_FORMAT_ATTR(format, "config:32-35"); + +static struct attribute *hisi_ptt_pmu_format_attrs[] = { + &format_attr_filter.attr, + &format_attr_direction.attr, + &format_attr_type.attr, + &format_attr_format.attr, + NULL +}; + +static struct attribute_group hisi_ptt_pmu_format_group = { + .name = "format", + .attrs = hisi_ptt_pmu_format_attrs, +}; + +static ssize_t hisi_ptt_filter_multiselect_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ext_attr; + + ext_attr = container_of(attr, struct dev_ext_attribute, attr); + return sysfs_emit(buf, "%s\n", (char *)ext_attr->var); +} + +static struct dev_ext_attribute root_port_filters_multiselect = { + .attr = { + .attr = { .name = "multiselect", .mode = 0400 }, + .show = hisi_ptt_filter_multiselect_show, + }, + .var = "1", +}; + +static struct attribute *hisi_ptt_pmu_root_ports_attrs[] = { + &root_port_filters_multiselect.attr.attr, + NULL +}; + +static struct attribute_group hisi_ptt_pmu_root_ports_group = { + .name = HISI_PTT_RP_FILTERS_GRP_NAME, + .attrs = hisi_ptt_pmu_root_ports_attrs, +}; + +static struct dev_ext_attribute requester_filters_multiselect = { + .attr = { + .attr = { .name = "multiselect", .mode = 0400 }, + .show = hisi_ptt_filter_multiselect_show, + }, + .var = "0", +}; + +static struct attribute *hisi_ptt_pmu_requesters_attrs[] = { + &requester_filters_multiselect.attr.attr, + NULL +}; + +static struct attribute_group hisi_ptt_pmu_requesters_group = { + .name = HISI_PTT_REQ_FILTERS_GRP_NAME, + .attrs = hisi_ptt_pmu_requesters_attrs, +}; + +static const struct attribute_group *hisi_ptt_pmu_groups[] = { + &hisi_ptt_cpumask_attr_group, + &hisi_ptt_pmu_format_group, + &hisi_ptt_tune_group, + &hisi_ptt_pmu_root_ports_group, + &hisi_ptt_pmu_requesters_group, + NULL +}; + +static int hisi_ptt_trace_valid_direction(u32 val) +{ + /* + * The direction values have different effects according to the data + * format (specified in the parentheses). TLP set A/B means different + * set of TLP types. See hisi_ptt.rst documentation for more details. + */ + static const u32 hisi_ptt_trace_available_direction[] = { + 0, /* inbound(4DW) or reserved(8DW) */ + 1, /* outbound(4DW) */ + 2, /* {in, out}bound(4DW) or inbound(8DW), TLP set A */ + 3, /* {in, out}bound(4DW) or inbound(8DW), TLP set B */ + }; + int i; + + for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_available_direction); i++) { + if (val == hisi_ptt_trace_available_direction[i]) + return 0; + } + + return -EINVAL; +} + +static int hisi_ptt_trace_valid_type(u32 val) +{ + /* Different types can be set simultaneously */ + static const u32 hisi_ptt_trace_available_type[] = { + 1, /* posted_request */ + 2, /* non-posted_request */ + 4, /* completion */ + }; + int i; + + if (!val) + return -EINVAL; + + /* + * Walk the available list and clear the valid bits of + * the config. If there is any resident bit after the + * walk then the config is invalid. + */ + for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_available_type); i++) + val &= ~hisi_ptt_trace_available_type[i]; + + if (val) + return -EINVAL; + + return 0; +} + +static int hisi_ptt_trace_valid_format(u32 val) +{ + static const u32 hisi_ptt_trace_availble_format[] = { + 0, /* 4DW */ + 1, /* 8DW */ + }; + int i; + + for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_availble_format); i++) { + if (val == hisi_ptt_trace_availble_format[i]) + return 0; + } + + return -EINVAL; +} + +static int hisi_ptt_trace_valid_filter(struct hisi_ptt *hisi_ptt, u64 config) +{ + unsigned long val, port_mask = hisi_ptt->port_mask; + struct hisi_ptt_filter_desc *filter; + int ret = 0; + + hisi_ptt->trace_ctrl.is_port = FIELD_GET(HISI_PTT_PMU_FILTER_IS_PORT, config); + val = FIELD_GET(HISI_PTT_PMU_FILTER_VAL_MASK, config); + + /* + * Port filters are defined as bit mask. For port filters, check + * the bits in the @val are within the range of hisi_ptt->port_mask + * and whether it's empty or not, otherwise user has specified + * some unsupported root ports. + * + * For Requester ID filters, walk the available filter list to see + * whether we have one matched. + */ + mutex_lock(&hisi_ptt->filter_lock); + if (!hisi_ptt->trace_ctrl.is_port) { + list_for_each_entry(filter, &hisi_ptt->req_filters, list) { + if (val == hisi_ptt_get_filter_val(filter->devid, filter->is_port)) + goto out; + } + } else if (bitmap_subset(&val, &port_mask, BITS_PER_LONG)) { + goto out; + } + + ret = -EINVAL; +out: + mutex_unlock(&hisi_ptt->filter_lock); + return ret; +} + +static void hisi_ptt_pmu_init_configs(struct hisi_ptt *hisi_ptt, struct perf_event *event) +{ + struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl; + u32 val; + + val = FIELD_GET(HISI_PTT_PMU_FILTER_VAL_MASK, event->attr.config); + hisi_ptt->trace_ctrl.filter = val; + + val = FIELD_GET(HISI_PTT_PMU_DIRECTION_MASK, event->attr.config); + ctrl->direction = val; + + val = FIELD_GET(HISI_PTT_PMU_TYPE_MASK, event->attr.config); + ctrl->type = val; + + val = FIELD_GET(HISI_PTT_PMU_FORMAT_MASK, event->attr.config); + ctrl->format = val; +} + +static int hisi_ptt_pmu_event_init(struct perf_event *event) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu); + int ret; + u32 val; + + if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) + return -ENOENT; + + if (event->cpu < 0) { + dev_dbg(event->pmu->dev, "Per-task mode not supported\n"); + return -EOPNOTSUPP; + } + + if (event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + + ret = hisi_ptt_trace_valid_filter(hisi_ptt, event->attr.config); + if (ret < 0) + return ret; + + val = FIELD_GET(HISI_PTT_PMU_DIRECTION_MASK, event->attr.config); + ret = hisi_ptt_trace_valid_direction(val); + if (ret < 0) + return ret; + + val = FIELD_GET(HISI_PTT_PMU_TYPE_MASK, event->attr.config); + ret = hisi_ptt_trace_valid_type(val); + if (ret < 0) + return ret; + + val = FIELD_GET(HISI_PTT_PMU_FORMAT_MASK, event->attr.config); + return hisi_ptt_trace_valid_format(val); +} + +static void *hisi_ptt_pmu_setup_aux(struct perf_event *event, void **pages, + int nr_pages, bool overwrite) +{ + struct hisi_ptt_pmu_buf *buf; + struct page **pagelist; + int i; + + if (overwrite) { + dev_warn(event->pmu->dev, "Overwrite mode is not supported\n"); + return NULL; + } + + /* If the pages size less than buffers, we cannot start trace */ + if (nr_pages < HISI_PTT_TRACE_TOTAL_BUF_SIZE / PAGE_SIZE) + return NULL; + + buf = kzalloc(sizeof(*buf), GFP_KERNEL); + if (!buf) + return NULL; + + pagelist = kcalloc(nr_pages, sizeof(*pagelist), GFP_KERNEL); + if (!pagelist) + goto err; + + for (i = 0; i < nr_pages; i++) + pagelist[i] = virt_to_page(pages[i]); + + buf->base = vmap(pagelist, nr_pages, VM_MAP, PAGE_KERNEL); + if (!buf->base) { + kfree(pagelist); + goto err; + } + + buf->nr_pages = nr_pages; + buf->length = nr_pages * PAGE_SIZE; + buf->pos = 0; + + kfree(pagelist); + return buf; +err: + kfree(buf); + return NULL; +} + +static void hisi_ptt_pmu_free_aux(void *aux) +{ + struct hisi_ptt_pmu_buf *buf = aux; + + vunmap(buf->base); + kfree(buf); +} + +static void hisi_ptt_pmu_start(struct perf_event *event, int flags) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu); + struct perf_output_handle *handle = &hisi_ptt->trace_ctrl.handle; + struct hw_perf_event *hwc = &event->hw; + struct device *dev = event->pmu->dev; + struct hisi_ptt_pmu_buf *buf; + int cpu = event->cpu; + int ret; + + hwc->state = 0; + + /* Serialize the perf process if user specified several CPUs */ + spin_lock(&hisi_ptt->pmu_lock); + if (hisi_ptt->trace_ctrl.started) { + dev_dbg(dev, "trace has already started\n"); + goto stop; + } + + /* + * Handle the interrupt on the same cpu which starts the trace to avoid + * context mismatch. Otherwise we'll trigger the WARN from the perf + * core in event_function_local(). If CPU passed is offline we'll fail + * here, just log it since we can do nothing here. + */ + ret = irq_set_affinity(hisi_ptt->trace_irq, cpumask_of(cpu)); + if (ret) + dev_warn(dev, "failed to set the affinity of trace interrupt\n"); + + hisi_ptt->trace_ctrl.on_cpu = cpu; + + buf = perf_aux_output_begin(handle, event); + if (!buf) { + dev_dbg(dev, "aux output begin failed\n"); + goto stop; + } + + buf->pos = handle->head % buf->length; + + hisi_ptt_pmu_init_configs(hisi_ptt, event); + + ret = hisi_ptt_trace_start(hisi_ptt); + if (ret) { + dev_dbg(dev, "trace start failed, ret = %d\n", ret); + perf_aux_output_end(handle, 0); + goto stop; + } + + spin_unlock(&hisi_ptt->pmu_lock); + return; +stop: + event->hw.state |= PERF_HES_STOPPED; + spin_unlock(&hisi_ptt->pmu_lock); +} + +static void hisi_ptt_pmu_stop(struct perf_event *event, int flags) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + if (hwc->state & PERF_HES_STOPPED) + return; + + spin_lock(&hisi_ptt->pmu_lock); + if (hisi_ptt->trace_ctrl.started) { + hisi_ptt_trace_end(hisi_ptt); + + if (!hisi_ptt_wait_trace_hw_idle(hisi_ptt)) + dev_warn(event->pmu->dev, "Device is still busy\n"); + + hisi_ptt_update_aux(hisi_ptt, hisi_ptt->trace_ctrl.buf_index, true); + } + spin_unlock(&hisi_ptt->pmu_lock); + + hwc->state |= PERF_HES_STOPPED; + perf_event_update_userpage(event); + hwc->state |= PERF_HES_UPTODATE; +} + +static int hisi_ptt_pmu_add(struct perf_event *event, int flags) +{ + struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int cpu = event->cpu; + + /* Only allow the cpus on the device's node to add the event */ + if (!cpumask_test_cpu(cpu, cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev)))) + return 0; + + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + + if (flags & PERF_EF_START) { + hisi_ptt_pmu_start(event, PERF_EF_RELOAD); + if (hwc->state & PERF_HES_STOPPED) + return -EINVAL; + } + + return 0; +} + +static void hisi_ptt_pmu_del(struct perf_event *event, int flags) +{ + hisi_ptt_pmu_stop(event, PERF_EF_UPDATE); +} + +static void hisi_ptt_pmu_read(struct perf_event *event) +{ +} + +static void hisi_ptt_remove_cpuhp_instance(void *hotplug_node) +{ + cpuhp_state_remove_instance_nocalls(hisi_ptt_pmu_online, hotplug_node); +} + +static void hisi_ptt_unregister_pmu(void *pmu) +{ + perf_pmu_unregister(pmu); +} + +static int hisi_ptt_register_pmu(struct hisi_ptt *hisi_ptt) +{ + u16 core_id, sicl_id; + char *pmu_name; + u32 reg; + int ret; + + ret = cpuhp_state_add_instance_nocalls(hisi_ptt_pmu_online, + &hisi_ptt->hotplug_node); + if (ret) + return ret; + + ret = devm_add_action_or_reset(&hisi_ptt->pdev->dev, + hisi_ptt_remove_cpuhp_instance, + &hisi_ptt->hotplug_node); + if (ret) + return ret; + + mutex_init(&hisi_ptt->tune_lock); + spin_lock_init(&hisi_ptt->pmu_lock); + + hisi_ptt->hisi_ptt_pmu = (struct pmu) { + .module = THIS_MODULE, + .parent = &hisi_ptt->pdev->dev, + .capabilities = PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_NO_EXCLUDE, + .task_ctx_nr = perf_sw_context, + .attr_groups = hisi_ptt_pmu_groups, + .event_init = hisi_ptt_pmu_event_init, + .setup_aux = hisi_ptt_pmu_setup_aux, + .free_aux = hisi_ptt_pmu_free_aux, + .start = hisi_ptt_pmu_start, + .stop = hisi_ptt_pmu_stop, + .add = hisi_ptt_pmu_add, + .del = hisi_ptt_pmu_del, + .read = hisi_ptt_pmu_read, + }; + + reg = readl(hisi_ptt->iobase + HISI_PTT_LOCATION); + core_id = FIELD_GET(HISI_PTT_CORE_ID, reg); + sicl_id = FIELD_GET(HISI_PTT_SICL_ID, reg); + + pmu_name = devm_kasprintf(&hisi_ptt->pdev->dev, GFP_KERNEL, "hisi_ptt%u_%u", + sicl_id, core_id); + if (!pmu_name) + return -ENOMEM; + + ret = perf_pmu_register(&hisi_ptt->hisi_ptt_pmu, pmu_name, -1); + if (ret) + return ret; + + return devm_add_action_or_reset(&hisi_ptt->pdev->dev, + hisi_ptt_unregister_pmu, + &hisi_ptt->hisi_ptt_pmu); +} + +static void hisi_ptt_unregister_filter_update_notifier(void *data) +{ + struct hisi_ptt *hisi_ptt = data; + + bus_unregister_notifier(&pci_bus_type, &hisi_ptt->hisi_ptt_nb); + + /* Cancel any work that has been queued */ + cancel_delayed_work_sync(&hisi_ptt->work); +} + +/* Register the bus notifier for dynamically updating the filter list */ +static int hisi_ptt_register_filter_update_notifier(struct hisi_ptt *hisi_ptt) +{ + int ret; + + hisi_ptt->hisi_ptt_nb.notifier_call = hisi_ptt_notifier_call; + ret = bus_register_notifier(&pci_bus_type, &hisi_ptt->hisi_ptt_nb); + if (ret) + return ret; + + return devm_add_action_or_reset(&hisi_ptt->pdev->dev, + hisi_ptt_unregister_filter_update_notifier, + hisi_ptt); +} + +/* + * The DMA of PTT trace can only use direct mappings due to some + * hardware restriction. Check whether there is no IOMMU or the + * policy of the IOMMU domain is passthrough, otherwise the trace + * cannot work. + * + * The PTT device is supposed to behind an ARM SMMUv3, which + * should have passthrough the device by a quirk. + */ +static int hisi_ptt_check_iommu_mapping(struct pci_dev *pdev) +{ + struct iommu_domain *iommu_domain; + + iommu_domain = iommu_get_domain_for_dev(&pdev->dev); + if (!iommu_domain || iommu_domain->type == IOMMU_DOMAIN_IDENTITY) + return 0; + + return -EOPNOTSUPP; +} + +static int hisi_ptt_probe(struct pci_dev *pdev, + const struct pci_device_id *id) +{ + struct hisi_ptt *hisi_ptt; + int ret; + + ret = hisi_ptt_check_iommu_mapping(pdev); + if (ret) { + pci_err(pdev, "requires direct DMA mappings\n"); + return ret; + } + + hisi_ptt = devm_kzalloc(&pdev->dev, sizeof(*hisi_ptt), GFP_KERNEL); + if (!hisi_ptt) + return -ENOMEM; + + hisi_ptt->pdev = pdev; + pci_set_drvdata(pdev, hisi_ptt); + + ret = pcim_enable_device(pdev); + if (ret) { + pci_err(pdev, "failed to enable device, ret = %d\n", ret); + return ret; + } + + ret = pcim_iomap_regions(pdev, BIT(2), DRV_NAME); + if (ret) { + pci_err(pdev, "failed to remap io memory, ret = %d\n", ret); + return ret; + } + + hisi_ptt->iobase = pcim_iomap_table(pdev)[2]; + + ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); + if (ret) { + pci_err(pdev, "failed to set 64 bit dma mask, ret = %d\n", ret); + return ret; + } + + pci_set_master(pdev); + + ret = hisi_ptt_register_irq(hisi_ptt); + if (ret) + return ret; + + ret = hisi_ptt_init_ctrls(hisi_ptt); + if (ret) { + pci_err(pdev, "failed to init controls, ret = %d\n", ret); + return ret; + } + + ret = hisi_ptt_register_filter_update_notifier(hisi_ptt); + if (ret) + pci_warn(pdev, "failed to register filter update notifier, ret = %d", ret); + + ret = hisi_ptt_register_pmu(hisi_ptt); + if (ret) { + pci_err(pdev, "failed to register PMU device, ret = %d", ret); + return ret; + } + + ret = hisi_ptt_init_filter_attributes(hisi_ptt); + if (ret) { + pci_err(pdev, "failed to init sysfs filter attributes, ret = %d", ret); + return ret; + } + + return 0; +} + +static const struct pci_device_id hisi_ptt_id_tbl[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa12e) }, + { } +}; +MODULE_DEVICE_TABLE(pci, hisi_ptt_id_tbl); + +static struct pci_driver hisi_ptt_driver = { + .name = DRV_NAME, + .id_table = hisi_ptt_id_tbl, + .probe = hisi_ptt_probe, +}; + +static int hisi_ptt_cpu_teardown(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_ptt *hisi_ptt; + struct device *dev; + int target, src; + + hisi_ptt = hlist_entry_safe(node, struct hisi_ptt, hotplug_node); + src = hisi_ptt->trace_ctrl.on_cpu; + dev = hisi_ptt->hisi_ptt_pmu.dev; + + if (!hisi_ptt->trace_ctrl.started || src != cpu) + return 0; + + target = cpumask_any_but(cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev)), cpu); + if (target >= nr_cpu_ids) { + dev_err(dev, "no available cpu for perf context migration\n"); + return 0; + } + + perf_pmu_migrate_context(&hisi_ptt->hisi_ptt_pmu, src, target); + + /* + * Also make sure the interrupt bind to the migrated CPU as well. Warn + * the user on failure here. + */ + if (irq_set_affinity(hisi_ptt->trace_irq, cpumask_of(target))) + dev_warn(dev, "failed to set the affinity of trace interrupt\n"); + + hisi_ptt->trace_ctrl.on_cpu = target; + return 0; +} + +static int __init hisi_ptt_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DRV_NAME, NULL, + hisi_ptt_cpu_teardown); + if (ret < 0) + return ret; + hisi_ptt_pmu_online = ret; + + ret = pci_register_driver(&hisi_ptt_driver); + if (ret) + cpuhp_remove_multi_state(hisi_ptt_pmu_online); + + return ret; +} +module_init(hisi_ptt_init); + +static void __exit hisi_ptt_exit(void) +{ + pci_unregister_driver(&hisi_ptt_driver); + cpuhp_remove_multi_state(hisi_ptt_pmu_online); +} +module_exit(hisi_ptt_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yicong Yang <yangyicong@hisilicon.com>"); +MODULE_DESCRIPTION("Driver for HiSilicon PCIe tune and trace device"); diff --git a/drivers/hwtracing/ptt/hisi_ptt.h b/drivers/hwtracing/ptt/hisi_ptt.h new file mode 100644 index 000000000000..46030aa88081 --- /dev/null +++ b/drivers/hwtracing/ptt/hisi_ptt.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Driver for HiSilicon PCIe tune and trace device + * + * Copyright (c) 2022 HiSilicon Technologies Co., Ltd. + * Author: Yicong Yang <yangyicong@hisilicon.com> + */ + +#ifndef _HISI_PTT_H +#define _HISI_PTT_H + +#include <linux/bits.h> +#include <linux/cpumask.h> +#include <linux/device.h> +#include <linux/kfifo.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/notifier.h> +#include <linux/pci.h> +#include <linux/perf_event.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/workqueue.h> + +#define DRV_NAME "hisi_ptt" + +/* + * The definition of the device registers and register fields. + */ +#define HISI_PTT_TUNING_CTRL 0x0000 +#define HISI_PTT_TUNING_CTRL_CODE GENMASK(15, 0) +#define HISI_PTT_TUNING_CTRL_SUB GENMASK(23, 16) +#define HISI_PTT_TUNING_DATA 0x0004 +#define HISI_PTT_TUNING_DATA_VAL_MASK GENMASK(15, 0) +#define HISI_PTT_TRACE_ADDR_SIZE 0x0800 +#define HISI_PTT_TRACE_ADDR_BASE_LO_0 0x0810 +#define HISI_PTT_TRACE_ADDR_BASE_HI_0 0x0814 +#define HISI_PTT_TRACE_ADDR_STRIDE 0x8 +#define HISI_PTT_TRACE_CTRL 0x0850 +#define HISI_PTT_TRACE_CTRL_EN BIT(0) +#define HISI_PTT_TRACE_CTRL_RST BIT(1) +#define HISI_PTT_TRACE_CTRL_RXTX_SEL GENMASK(3, 2) +#define HISI_PTT_TRACE_CTRL_TYPE_SEL GENMASK(7, 4) +#define HISI_PTT_TRACE_CTRL_DATA_FORMAT BIT(14) +#define HISI_PTT_TRACE_CTRL_FILTER_MODE BIT(15) +#define HISI_PTT_TRACE_CTRL_TARGET_SEL GENMASK(31, 16) +#define HISI_PTT_TRACE_INT_STAT 0x0890 +#define HISI_PTT_TRACE_INT_STAT_MASK GENMASK(3, 0) +#define HISI_PTT_TRACE_INT_MASK 0x0894 +#define HISI_PTT_TRACE_INT_MASK_ALL GENMASK(3, 0) +#define HISI_PTT_TUNING_INT_STAT 0x0898 +#define HISI_PTT_TUNING_INT_STAT_MASK BIT(0) +#define HISI_PTT_TRACE_WR_STS 0x08a0 +#define HISI_PTT_TRACE_WR_STS_WRITE GENMASK(27, 0) +#define HISI_PTT_TRACE_WR_STS_BUFFER GENMASK(29, 28) +#define HISI_PTT_TRACE_STS 0x08b0 +#define HISI_PTT_TRACE_IDLE BIT(0) +#define HISI_PTT_DEVICE_RANGE 0x0fe0 +#define HISI_PTT_DEVICE_RANGE_UPPER GENMASK(31, 16) +#define HISI_PTT_DEVICE_RANGE_LOWER GENMASK(15, 0) +#define HISI_PTT_LOCATION 0x0fe8 +#define HISI_PTT_CORE_ID GENMASK(15, 0) +#define HISI_PTT_SICL_ID GENMASK(31, 16) + +/* Parameters of PTT trace DMA part. */ +#define HISI_PTT_TRACE_DMA_IRQ 0 +#define HISI_PTT_TRACE_BUF_CNT 4 +#define HISI_PTT_TRACE_BUF_SIZE SZ_4M +#define HISI_PTT_TRACE_TOTAL_BUF_SIZE (HISI_PTT_TRACE_BUF_SIZE * \ + HISI_PTT_TRACE_BUF_CNT) +/* Wait time for hardware DMA to reset */ +#define HISI_PTT_RESET_TIMEOUT_US 10UL +#define HISI_PTT_RESET_POLL_INTERVAL_US 1UL +/* Poll timeout and interval for waiting hardware work to finish */ +#define HISI_PTT_WAIT_TUNE_TIMEOUT_US 1000000UL +#define HISI_PTT_WAIT_TRACE_TIMEOUT_US 100UL +#define HISI_PTT_WAIT_POLL_INTERVAL_US 10UL + +/* FIFO size for dynamically updating the PTT trace filter list. */ +#define HISI_PTT_FILTER_UPDATE_FIFO_SIZE 16 +/* Delay time for filter updating work */ +#define HISI_PTT_WORK_DELAY_MS 100UL + +#define HISI_PCIE_CORE_PORT_ID(devfn) ((PCI_SLOT(devfn) & 0x7) << 1) + +/* Definition of the PMU configs */ +#define HISI_PTT_PMU_FILTER_IS_PORT BIT(19) +#define HISI_PTT_PMU_FILTER_VAL_MASK GENMASK(15, 0) +#define HISI_PTT_PMU_DIRECTION_MASK GENMASK(23, 20) +#define HISI_PTT_PMU_TYPE_MASK GENMASK(31, 24) +#define HISI_PTT_PMU_FORMAT_MASK GENMASK(35, 32) + +/** + * struct hisi_ptt_tune_desc - Describe tune event for PTT tune + * @hisi_ptt: PTT device this tune event belongs to + * @name: name of this event + * @event_code: code of the event + */ +struct hisi_ptt_tune_desc { + struct hisi_ptt *hisi_ptt; + const char *name; + u32 event_code; +}; + +/** + * struct hisi_ptt_dma_buffer - Describe a single trace buffer of PTT trace. + * The detail of the data format is described + * in the documentation of PTT device. + * @dma: DMA address of this buffer visible to the device + * @addr: virtual address of this buffer visible to the cpu + */ +struct hisi_ptt_dma_buffer { + dma_addr_t dma; + void *addr; +}; + +/** + * struct hisi_ptt_trace_ctrl - Control and status of PTT trace + * @trace_buf: array of the trace buffers for holding the trace data. + * the length will be HISI_PTT_TRACE_BUF_CNT. + * @handle: perf output handle of current trace session + * @buf_index: the index of current using trace buffer + * @on_cpu: current tracing cpu + * @started: current trace status, true for started + * @is_port: whether we're tracing root port or not + * @direction: direction of the TLP headers to trace + * @filter: filter value for tracing the TLP headers + * @format: format of the TLP headers to trace + * @type: type of the TLP headers to trace + */ +struct hisi_ptt_trace_ctrl { + struct hisi_ptt_dma_buffer *trace_buf; + struct perf_output_handle handle; + u32 buf_index; + int on_cpu; + bool started; + bool is_port; + u32 direction:2; + u32 filter:16; + u32 format:1; + u32 type:4; +}; + +/* + * sysfs attribute group name for root port filters and requester filters: + * /sys/devices/hisi_ptt<sicl_id>_<core_id>/root_port_filters + * and + * /sys/devices/hisi_ptt<sicl_id>_<core_id>/requester_filters + */ +#define HISI_PTT_RP_FILTERS_GRP_NAME "root_port_filters" +#define HISI_PTT_REQ_FILTERS_GRP_NAME "requester_filters" + +/** + * struct hisi_ptt_filter_desc - Descriptor of the PTT trace filter + * @attr: sysfs attribute of this filter + * @list: entry of this descriptor in the filter list + * @is_port: the PCI device of the filter is a Root Port or not + * @name: name of this filter, same as the name of the related PCI device + * @devid: the PCI device's devid of the filter + */ +struct hisi_ptt_filter_desc { + struct device_attribute attr; + struct list_head list; + bool is_port; + char *name; + u16 devid; +}; + +/** + * struct hisi_ptt_filter_update_info - Information for PTT filter updating + * @is_port: the PCI device to update is a Root Port or not + * @is_add: adding to the filter or not + * @devid: the PCI device's devid of the filter + */ +struct hisi_ptt_filter_update_info { + bool is_port; + bool is_add; + u16 devid; +}; + +/** + * struct hisi_ptt_pmu_buf - Descriptor of the AUX buffer of PTT trace + * @length: size of the AUX buffer + * @nr_pages: number of pages of the AUX buffer + * @base: start address of AUX buffer + * @pos: position in the AUX buffer to commit traced data + */ +struct hisi_ptt_pmu_buf { + size_t length; + int nr_pages; + void *base; + long pos; +}; + +/** + * struct hisi_ptt - Per PTT device data + * @trace_ctrl: the control information of PTT trace + * @hisi_ptt_nb: dynamic filter update notifier + * @hotplug_node: node for register cpu hotplug event + * @hisi_ptt_pmu: the pum device of trace + * @iobase: base IO address of the device + * @pdev: pci_dev of this PTT device + * @tune_lock: lock to serialize the tune process + * @pmu_lock: lock to serialize the perf process + * @trace_irq: interrupt number used by trace + * @upper_bdf: the upper BDF range of the PCI devices managed by this PTT device + * @lower_bdf: the lower BDF range of the PCI devices managed by this PTT device + * @port_filters: the filter list of root ports + * @req_filters: the filter list of requester ID + * @filter_lock: lock to protect the filters + * @sysfs_inited: whether the filters' sysfs entries has been initialized + * @port_mask: port mask of the managed root ports + * @work: delayed work for filter updating + * @filter_update_lock: spinlock to protect the filter update fifo + * @filter_update_fifo: fifo of the filters waiting to update the filter list + */ +struct hisi_ptt { + struct hisi_ptt_trace_ctrl trace_ctrl; + struct notifier_block hisi_ptt_nb; + struct hlist_node hotplug_node; + struct pmu hisi_ptt_pmu; + void __iomem *iobase; + struct pci_dev *pdev; + struct mutex tune_lock; + spinlock_t pmu_lock; + int trace_irq; + u32 upper_bdf; + u32 lower_bdf; + + /* + * The trace TLP headers can either be filtered by certain + * root port, or by the requester ID. Organize the filters + * by @port_filters and @req_filters here. The mask of all + * the valid ports is also cached for doing sanity check + * of user input. + */ + struct list_head port_filters; + struct list_head req_filters; + struct mutex filter_lock; + bool sysfs_inited; + u16 port_mask; + + /* + * We use a delayed work here to avoid indefinitely waiting for + * the hisi_ptt->mutex which protecting the filter list. The + * work will be delayed only if the mutex can not be held, + * otherwise no delay will be applied. + */ + struct delayed_work work; + spinlock_t filter_update_lock; + DECLARE_KFIFO(filter_update_kfifo, struct hisi_ptt_filter_update_info, + HISI_PTT_FILTER_UPDATE_FIFO_SIZE); +}; + +#define to_hisi_ptt(pmu) container_of(pmu, struct hisi_ptt, hisi_ptt_pmu) + +#endif /* _HISI_PTT_H */ diff --git a/drivers/hwtracing/stm/Kconfig b/drivers/hwtracing/stm/Kconfig index 752dd66742bf..eda6b11d40a1 100644 --- a/drivers/hwtracing/stm/Kconfig +++ b/drivers/hwtracing/stm/Kconfig @@ -1,7 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only config STM tristate "System Trace Module devices" select CONFIGFS_FS - select SRCU help A System Trace Module (STM) is a device exporting data in System Trace Protocol (STP) format as defined by MIPI STP standards. @@ -70,7 +70,7 @@ config STM_SOURCE_HEARTBEAT config STM_SOURCE_FTRACE tristate "Copy the output from kernel Ftrace to STM engine" - depends on FUNCTION_TRACER + depends on TRACING help This option can be used to copy the output from kernel Ftrace to STM engine. Enabling this option will introduce a slight diff --git a/drivers/hwtracing/stm/console.c b/drivers/hwtracing/stm/console.c index a00f65e21747..097a00ac43a7 100644 --- a/drivers/hwtracing/stm/console.c +++ b/drivers/hwtracing/stm/console.c @@ -22,6 +22,7 @@ static struct stm_console { .data = { .name = "console", .nr_chans = 1, + .type = STM_USER, .link = stm_console_link, .unlink = stm_console_unlink, }, diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c index 93ce3aa740a9..cdba4e875b28 100644 --- a/drivers/hwtracing/stm/core.c +++ b/drivers/hwtracing/stm/core.c @@ -89,13 +89,6 @@ static struct class stm_class = { .dev_groups = stm_groups, }; -static int stm_dev_match(struct device *dev, const void *data) -{ - const char *name = data; - - return sysfs_streq(name, dev_name(dev)); -} - /** * stm_find_device() - find stm device by name * @buf: character buffer containing the name @@ -116,7 +109,7 @@ struct stm_device *stm_find_device(const char *buf) if (!stm_core_up) return NULL; - dev = class_find_device(&stm_class, NULL, buf, stm_dev_match); + dev = class_find_device_by_name(&stm_class, buf); if (!dev) return NULL; @@ -166,11 +159,10 @@ stm_master(struct stm_device *stm, unsigned int idx) static int stp_master_alloc(struct stm_device *stm, unsigned int idx) { struct stp_master *master; - size_t size; - size = ALIGN(stm->data->sw_nchannels, 8) / 8; - size += sizeof(struct stp_master); - master = kzalloc(size, GFP_ATOMIC); + master = kzalloc(struct_size(master, chan_map, + BITS_TO_LONGS(stm->data->sw_nchannels)), + GFP_ATOMIC); if (!master) return -ENOMEM; @@ -218,8 +210,8 @@ stm_output_disclaim(struct stm_device *stm, struct stm_output *output) bitmap_release_region(&master->chan_map[0], output->channel, ilog2(output->nr_chans)); - output->nr_chans = 0; master->nr_free += output->nr_chans; + output->nr_chans = 0; } /* @@ -244,6 +236,9 @@ static int find_free_channels(unsigned long *bitmap, unsigned int start, ; if (i == width) return pos; + + /* step over [pos..pos+i) to continue search */ + pos += i; } return -1; @@ -605,7 +600,7 @@ EXPORT_SYMBOL_GPL(stm_data_write); static ssize_t notrace stm_write(struct stm_device *stm, struct stm_output *output, - unsigned int chan, const char *buf, size_t count) + unsigned int chan, const char *buf, size_t count, struct stm_source_data *source) { int err; @@ -613,7 +608,7 @@ stm_write(struct stm_device *stm, struct stm_output *output, if (!stm->pdrv) return -ENODEV; - err = stm->pdrv->write(stm->data, output, chan, buf, count); + err = stm->pdrv->write(stm->data, output, chan, buf, count, source); if (err < 0) return err; @@ -662,7 +657,7 @@ static ssize_t stm_char_write(struct file *file, const char __user *buf, pm_runtime_get_sync(&stm->dev); - count = stm_write(stm, &stmf->output, 0, kbuf, count); + count = stm_write(stm, &stmf->output, 0, kbuf, count, NULL); pm_runtime_mark_last_busy(&stm->dev); pm_runtime_put_autosuspend(&stm->dev); @@ -720,7 +715,7 @@ static int stm_char_mmap(struct file *file, struct vm_area_struct *vma) pm_runtime_get_sync(&stm->dev); vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &stm_mmap_vmops; vm_iomap_memory(vma, phys, size); @@ -732,7 +727,7 @@ static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg) struct stm_device *stm = stmf->stm; struct stp_policy_id *id; char *ids[] = { NULL, NULL }; - int ret = -EINVAL; + int ret = -EINVAL, wlimit = 1; u32 size; if (stmf->output.nr_chans) @@ -760,8 +755,10 @@ static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg) if (id->__reserved_0 || id->__reserved_1) goto err_free; - if (id->width < 1 || - id->width > PAGE_SIZE / stm->data->sw_mmiosz) + if (stm->data->sw_mmiosz) + wlimit = PAGE_SIZE / stm->data->sw_mmiosz; + + if (id->width < 1 || id->width > wlimit) goto err_free; ids[0] = id->id; @@ -835,24 +832,13 @@ stm_char_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; } -#ifdef CONFIG_COMPAT -static long -stm_char_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - return stm_char_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); -} -#else -#define stm_char_compat_ioctl NULL -#endif - static const struct file_operations stm_fops = { .open = stm_char_open, .release = stm_char_release, .write = stm_char_write, .mmap = stm_char_mmap, .unlocked_ioctl = stm_char_ioctl, - .compat_ioctl = stm_char_compat_ioctl, - .llseek = no_llseek, + .compat_ioctl = compat_ptr_ioctl, }; static void stm_device_release(struct device *dev) @@ -881,8 +867,11 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data, return -ENOMEM; stm->major = register_chrdev(0, stm_data->name, &stm_fops); - if (stm->major < 0) - goto err_free; + if (stm->major < 0) { + err = stm->major; + vfree(stm); + return err; + } device_initialize(&stm->dev); stm->dev.devt = MKDEV(stm->major, 0); @@ -926,10 +915,8 @@ int stm_register_device(struct device *parent, struct stm_data *stm_data, err_device: unregister_chrdev(stm->major, stm_data->name); - /* matches device_initialize() above */ + /* calls stm_device_release() */ put_device(&stm->dev); -err_free: - vfree(stm); return err; } @@ -1272,7 +1259,6 @@ int stm_source_register_device(struct device *parent, err: put_device(&src->dev); - kfree(src); return err; } @@ -1312,7 +1298,7 @@ int notrace stm_source_write(struct stm_source_data *data, stm = srcu_dereference(src->link, &stm_source_srcu); if (stm) - count = stm_write(stm, &src->output, chan, buf, count); + count = stm_write(stm, &src->output, chan, buf, count, data); else count = -ENODEV; diff --git a/drivers/hwtracing/stm/ftrace.c b/drivers/hwtracing/stm/ftrace.c index ce868e095410..a7cea7ea0163 100644 --- a/drivers/hwtracing/stm/ftrace.c +++ b/drivers/hwtracing/stm/ftrace.c @@ -23,6 +23,7 @@ static struct stm_ftrace { .data = { .name = "ftrace", .nr_chans = STM_FTRACE_NR_CHANNELS, + .type = STM_FTRACE, .link = stm_ftrace_link, .unlink = stm_ftrace_unlink, }, @@ -37,8 +38,10 @@ static void notrace stm_ftrace_write(struct trace_export *export, const void *buf, unsigned int len) { struct stm_ftrace *stm = container_of(export, struct stm_ftrace, ftrace); + /* This is called from trace system with preemption disabled */ + unsigned int cpu = smp_processor_id(); - stm_source_write(&stm->data, STM_FTRACE_CHAN, buf, len); + stm_source_write(&stm->data, STM_FTRACE_CHAN + cpu, buf, len); } static int stm_ftrace_link(struct stm_source_data *data) @@ -46,6 +49,8 @@ static int stm_ftrace_link(struct stm_source_data *data) struct stm_ftrace *sf = container_of(data, struct stm_ftrace, data); sf->ftrace.write = stm_ftrace_write; + sf->ftrace.flags = TRACE_EXPORT_FUNCTION | TRACE_EXPORT_EVENT + | TRACE_EXPORT_MARKER; return register_ftrace_export(&sf->ftrace); } @@ -61,6 +66,7 @@ static int __init stm_ftrace_init(void) { int ret; + stm_ftrace.data.nr_chans = roundup_pow_of_two(num_possible_cpus()); ret = stm_source_register_device(NULL, &stm_ftrace.data); if (ret) pr_err("Failed to register stm_source - ftrace.\n"); diff --git a/drivers/hwtracing/stm/heartbeat.c b/drivers/hwtracing/stm/heartbeat.c index 3e7df1c0477f..495eb1dc8ac5 100644 --- a/drivers/hwtracing/stm/heartbeat.c +++ b/drivers/hwtracing/stm/heartbeat.c @@ -64,7 +64,7 @@ static void stm_heartbeat_unlink(struct stm_source_data *data) static int stm_heartbeat_init(void) { - int i, ret = -ENOMEM; + int i, ret; if (nr_devs < 0 || nr_devs > STM_HEARTBEAT_MAX) return -EINVAL; @@ -72,16 +72,17 @@ static int stm_heartbeat_init(void) for (i = 0; i < nr_devs; i++) { stm_heartbeat[i].data.name = kasprintf(GFP_KERNEL, "heartbeat.%d", i); - if (!stm_heartbeat[i].data.name) + if (!stm_heartbeat[i].data.name) { + ret = -ENOMEM; goto fail_unregister; + } stm_heartbeat[i].data.nr_chans = 1; + stm_heartbeat[i].data.type = STM_USER; stm_heartbeat[i].data.link = stm_heartbeat_link; stm_heartbeat[i].data.unlink = stm_heartbeat_unlink; - hrtimer_init(&stm_heartbeat[i].hrtimer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); - stm_heartbeat[i].hrtimer.function = - stm_heartbeat_hrtimer_handler; + hrtimer_setup(&stm_heartbeat[i].hrtimer, stm_heartbeat_hrtimer_handler, + CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ret = stm_source_register_device(NULL, &stm_heartbeat[i].data); if (ret) diff --git a/drivers/hwtracing/stm/p_basic.c b/drivers/hwtracing/stm/p_basic.c index 8980a6a5fd6c..5525c975cc6f 100644 --- a/drivers/hwtracing/stm/p_basic.c +++ b/drivers/hwtracing/stm/p_basic.c @@ -10,7 +10,8 @@ #include "stm.h" static ssize_t basic_write(struct stm_data *data, struct stm_output *output, - unsigned int chan, const char *buf, size_t count) + unsigned int chan, const char *buf, size_t count, + struct stm_source_data *source) { unsigned int c = output->channel + chan; unsigned int m = output->master; diff --git a/drivers/hwtracing/stm/p_sys-t.c b/drivers/hwtracing/stm/p_sys-t.c index b178a5495b67..1e75aa0025a3 100644 --- a/drivers/hwtracing/stm/p_sys-t.c +++ b/drivers/hwtracing/stm/p_sys-t.c @@ -20,6 +20,7 @@ enum sys_t_message_type { MIPI_SYST_TYPE_RAW = 6, MIPI_SYST_TYPE_SHORT64, MIPI_SYST_TYPE_CLOCK, + MIPI_SYST_TYPE_SBD, }; enum sys_t_message_severity { @@ -53,6 +54,19 @@ enum sys_t_message_string_subtype { MIPI_SYST_STRING_PRINTF_64 = 12, }; +/** + * enum sys_t_message_sbd_subtype - SyS-T SBD message subtypes + * @MIPI_SYST_SBD_ID32: SBD message with 32-bit message ID + * @MIPI_SYST_SBD_ID64: SBD message with 64-bit message ID + * + * Structured Binary Data messages can send information of arbitrary length, + * together with ID's that describe BLOB's content and layout. + */ +enum sys_t_message_sbd_subtype { + MIPI_SYST_SBD_ID32 = 0, + MIPI_SYST_SBD_ID64 = 1, +}; + #define MIPI_SYST_TYPE(t) ((u32)(MIPI_SYST_TYPE_ ## t)) #define MIPI_SYST_SEVERITY(s) ((u32)(MIPI_SYST_SEVERITY_ ## s) << 4) #define MIPI_SYST_OPT_LOC BIT(8) @@ -75,6 +89,20 @@ enum sys_t_message_string_subtype { #define CLOCK_SYNC_HEADER (MIPI_SYST_TYPES(CLOCK, TRANSPORT_SYNC) | \ MIPI_SYST_SEVERITY(MAX)) +/* + * SyS-T and ftrace headers are compatible to an extent that ftrace event ID + * and args can be treated as SyS-T SBD message with 64-bit ID and arguments + * BLOB right behind the header without modification. Bits [16:63] coming + * together with message ID from ftrace aren't used by SBD and must be zeroed. + * + * 0 15 16 23 24 31 32 39 40 63 + * ftrace: <event_id> <flags> <preempt> <-pid-> <----> <args> + * SBD: <------- msg_id ------------------------------> <BLOB> + */ +#define SBD_HEADER (MIPI_SYST_TYPES(SBD, ID64) | \ + MIPI_SYST_SEVERITY(INFO) | \ + MIPI_SYST_OPT_GUID) + struct sys_t_policy_node { uuid_t uuid; bool do_len; @@ -92,7 +120,7 @@ static void sys_t_policy_node_init(void *priv) { struct sys_t_policy_node *pn = priv; - generate_random_uuid(pn->uuid.b); + uuid_gen(&pn->uuid); } static int sys_t_output_open(void *priv, struct stm_output *output) @@ -238,7 +266,7 @@ static struct configfs_attribute *sys_t_policy_attrs[] = { static inline bool sys_t_need_ts(struct sys_t_output *op) { if (op->node.ts_interval && - time_after(op->ts_jiffies + op->node.ts_interval, jiffies)) { + time_after(jiffies, op->ts_jiffies + op->node.ts_interval)) { op->ts_jiffies = jiffies; return true; @@ -250,8 +278,8 @@ static inline bool sys_t_need_ts(struct sys_t_output *op) static bool sys_t_need_clock_sync(struct sys_t_output *op) { if (op->node.clocksync_interval && - time_after(op->clocksync_jiffies + op->node.clocksync_interval, - jiffies)) { + time_after(jiffies, + op->clocksync_jiffies + op->node.clocksync_interval)) { op->clocksync_jiffies = jiffies; return true; @@ -284,14 +312,68 @@ sys_t_clock_sync(struct stm_data *data, unsigned int m, unsigned int c) return sizeof(header) + sizeof(payload); } +static inline u32 sys_t_header(struct stm_source_data *source) +{ + if (source && source->type == STM_FTRACE) + return SBD_HEADER; + return DATA_HEADER; +} + +static ssize_t sys_t_write_data(struct stm_data *data, + struct stm_source_data *source, + unsigned int master, unsigned int channel, + bool ts_first, const void *buf, size_t count) +{ + ssize_t sz; + const unsigned char nil = 0; + + /* + * Ftrace is zero-copy compatible with SyS-T SBD, but requires + * special handling of first 64 bits. Trim and send them separately + * to avoid damage on original ftrace buffer. + */ + if (source && source->type == STM_FTRACE) { + u64 compat_ftrace_header; + ssize_t header_sz; + ssize_t buf_sz; + + if (count < sizeof(compat_ftrace_header)) + return -EINVAL; + + /* SBD only makes use of low 16 bits (event ID) from ftrace event */ + compat_ftrace_header = *(u64 *)buf & 0xffff; + header_sz = stm_data_write(data, master, channel, false, + &compat_ftrace_header, + sizeof(compat_ftrace_header)); + if (header_sz != sizeof(compat_ftrace_header)) + return header_sz; + + buf_sz = stm_data_write(data, master, channel, false, + buf + header_sz, count - header_sz); + if (buf_sz != count - header_sz) + return buf_sz; + sz = header_sz + buf_sz; + } else { + sz = stm_data_write(data, master, channel, false, buf, count); + } + + if (sz <= 0) + return sz; + + data->packet(data, master, channel, STP_PACKET_FLAG, 0, 0, &nil); + + return sz; +} + static ssize_t sys_t_write(struct stm_data *data, struct stm_output *output, - unsigned int chan, const char *buf, size_t count) + unsigned int chan, const char *buf, size_t count, + struct stm_source_data *source) { struct sys_t_output *op = output->pdrv_private; unsigned int c = output->channel + chan; unsigned int m = output->master; - const unsigned char nil = 0; - u32 header = DATA_HEADER; + u32 header = sys_t_header(source); + u8 uuid[UUID_SIZE]; ssize_t sz; /* We require an existing policy node to proceed */ @@ -322,7 +404,8 @@ static ssize_t sys_t_write(struct stm_data *data, struct stm_output *output, return sz; /* GUID */ - sz = stm_data_write(data, m, c, false, op->node.uuid.b, UUID_SIZE); + export_uuid(uuid, &op->node.uuid); + sz = stm_data_write(data, m, c, false, uuid, sizeof(op->node.uuid)); if (sz <= 0) return sz; @@ -346,11 +429,7 @@ static ssize_t sys_t_write(struct stm_data *data, struct stm_output *output, } /* DATA */ - sz = stm_data_write(data, m, c, false, buf, count); - if (sz > 0) - data->packet(data, m, c, STP_PACKET_FLAG, 0, 0, &nil); - - return sz; + return sys_t_write_data(data, source, m, c, false, buf, count); } static const struct stm_protocol_driver sys_t_pdrv = { diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c index 4b9e44b227d8..42103c3a177f 100644 --- a/drivers/hwtracing/stm/policy.c +++ b/drivers/hwtracing/stm/policy.c @@ -34,7 +34,7 @@ struct stp_policy_node { unsigned int first_channel; unsigned int last_channel; /* this is the one that's exposed to the attributes */ - unsigned char priv[0]; + unsigned char priv[]; }; void *stp_policy_node_priv(struct stp_policy_node *pn) @@ -57,11 +57,6 @@ void stp_policy_node_get_ranges(struct stp_policy_node *policy_node, *cend = policy_node->last_channel; } -static inline char *stp_policy_node_name(struct stp_policy_node *policy_node) -{ - return policy_node->group.cg_item.ci_name ? : "<none>"; -} - static inline struct stp_policy *to_stp_policy(struct config_item *item) { return item ? @@ -345,7 +340,11 @@ void stp_policy_unbind(struct stp_policy *policy) stm->policy = NULL; policy->stm = NULL; + /* + * Drop the reference on the protocol driver and lose the link. + */ stm_put_protocol(stm->pdrv); + stm->pdrv = NULL; stm_put_device(stm); } diff --git a/drivers/hwtracing/stm/stm.h b/drivers/hwtracing/stm/stm.h index 3569439d53bb..85dda6e0d10c 100644 --- a/drivers/hwtracing/stm/stm.h +++ b/drivers/hwtracing/stm/stm.h @@ -23,7 +23,7 @@ void *stp_policy_node_priv(struct stp_policy_node *pn); struct stp_master { unsigned int nr_free; - unsigned long chan_map[0]; + unsigned long chan_map[]; }; struct stm_device { @@ -42,7 +42,7 @@ struct stm_device { const struct config_item_type *pdrv_node_type; /* master allocation */ spinlock_t mc_lock; - struct stp_master *masters[0]; + struct stp_master *masters[]; }; #define to_stm_device(_d) \ @@ -96,7 +96,7 @@ struct stm_protocol_driver { const char *name; ssize_t (*write)(struct stm_data *data, struct stm_output *output, unsigned int chan, - const char *buf, size_t count); + const char *buf, size_t count, struct stm_source_data *source); void (*policy_node_init)(void *arg); int (*output_open)(void *priv, struct stm_output *output); void (*output_close)(struct stm_output *output); |