diff options
Diffstat (limited to 'drivers/hwtracing')
63 files changed, 14421 insertions, 2484 deletions
diff --git a/drivers/hwtracing/Kconfig b/drivers/hwtracing/Kconfig index 13085835a636..911ee977103c 100644 --- a/drivers/hwtracing/Kconfig +++ b/drivers/hwtracing/Kconfig @@ -5,4 +5,6 @@ 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 6ff30e25af55..45c1eb5dfcb7 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -3,11 +3,12 @@ # 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 @@ -15,17 +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. @@ -34,8 +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). @@ -45,8 +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, @@ -56,16 +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 @@ -74,19 +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. + + 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 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 @@ -96,6 +130,9 @@ 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_CPU_DEBUG tristate "CoreSight CPU Debug driver" depends on ARM || ARM64 @@ -107,7 +144,61 @@ 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.rst + 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. endif diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index 3c0ac421e211..b6c4a48140ec 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -2,18 +2,28 @@ # # Makefile for CoreSight drivers. # -obj-$(CONFIG_CORESIGHT) += coresight.o coresight-etm-perf.o coresight-platform.o -obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o \ - coresight-tmc-etf.o \ - coresight-tmc-etr.o +obj-$(CONFIG_CORESIGHT) += coresight.o +coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \ + coresight-sysfs.o coresight-syscfg.o coresight-config.o \ + coresight-cfg-preload.o coresight-cfg-afdo.o \ + coresight-syscfg-configfs.o +obj-$(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_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 +coresight-cti-y := coresight-cti-core.o coresight-cti-platform.o \ + coresight-cti-sysfs.o diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index 16ebf38a9f66..bc90a03f478f 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -358,33 +358,22 @@ 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, }; @@ -401,8 +390,9 @@ static const struct attribute_group *catu_groups[] = { static inline 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) @@ -411,6 +401,7 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) u32 control, mode; struct etr_buf *etr_buf = data; struct device *dev = &drvdata->csdev->dev; + struct coresight_device *csdev = drvdata->csdev; if (catu_wait_for_ready(drvdata)) dev_warn(dev, "Timeout while waiting for READY\n"); @@ -421,7 +412,7 @@ static int catu_enable_hw(struct catu_drvdata *drvdata, void *data) return -EBUSY; } - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) return rc; @@ -465,9 +456,10 @@ 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(dev, "Timeout while waiting for READY\n"); rc = -EAGAIN; @@ -551,6 +543,7 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id) dev->platform_data = pdata; drvdata->base = base; + catu_desc.access = CSDEV_ACCESS_IOMEM(base); catu_desc.pdata = pdata; catu_desc.dev = dev; catu_desc.groups = catu_groups; @@ -567,14 +560,20 @@ out: return ret; } +static void catu_remove(struct amba_device *adev) +{ + struct catu_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_unregister(drvdata->csdev); +} + static struct amba_id catu_ids[] = { - { - .id = 0x000bb9ee, - .mask = 0x000fffff, - }, + CS_AMBA_ID(0x000bb9ee), {}, }; +MODULE_DEVICE_TABLE(amba, catu_ids); + static struct amba_driver catu_driver = { .drv = { .name = "coresight-catu", @@ -582,7 +581,30 @@ static struct amba_driver catu_driver = { .suppress_bind_attrs = true, }, .probe = catu_probe, + .remove = catu_remove, .id_table = catu_ids, }; -builtin_amba_driver(catu_driver); +static int __init catu_init(void) +{ + int ret; + + ret = amba_driver_register(&catu_driver); + if (ret) + pr_info("Error registering catu driver\n"); + tmc_etr_set_catu_ops(&etr_catu_buf_ops); + return ret; +} + +static void __exit catu_exit(void) +{ + tmc_etr_remove_catu_ops(); + amba_driver_unregister(&catu_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 80ceee3c739c..442e034bbfba 100644 --- a/drivers/hwtracing/coresight/coresight-catu.h +++ b/drivers/hwtracing/coresight/coresight-catu.h @@ -70,24 +70,24 @@ struct catu_drvdata { 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); @@ -108,6 +108,4 @@ static inline bool coresight_is_catu_device(struct coresight_device *csdev) return true; } -extern const struct etr_buf_operations etr_catu_buf_ops; - #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..84b31184252b --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-afdo.c @@ -0,0 +1,153 @@ +// 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" + +/* 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..e237a4edfa09 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-preload.c @@ -0,0 +1,36 @@ +// 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, +#endif + NULL +}; + +static struct cscfg_config_desc *preload_cfgs[] = { +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM4X) + &afdo_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..21299e175477 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cfg-preload.h @@ -0,0 +1,13 @@ +/* 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; +#endif diff --git a/drivers/hwtracing/coresight/coresight-config.c b/drivers/hwtracing/coresight/coresight-config.c new file mode 100644 index 000000000000..4723bf7402a2 --- /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; + + 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]); + 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; + + 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]); + 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..6ba013975741 --- /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; + 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 { + const 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.c b/drivers/hwtracing/coresight/coresight-core.c index ef20f74c85fa..f3068175ca9d 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -21,8 +21,10 @@ #include "coresight-etm-perf.h" #include "coresight-priv.h" +#include "coresight-syscfg.h" static DEFINE_MUTEX(coresight_mutex); +static DEFINE_PER_CPU(struct coresight_device *, csdev_sink); /** * struct coresight_node - elements of a path, from source to sink @@ -53,7 +55,62 @@ static struct list_head *stm_path; * 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}; +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; + +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); + +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 int coresight_id_match(struct device *dev, void *data) { @@ -71,7 +128,7 @@ static int coresight_id_match(struct device *dev, void *data) i_csdev->type != CORESIGHT_DEV_TYPE_SOURCE) return 0; - /* Get the source ID for both compoment */ + /* Get the source ID for both components */ trace_id = source_ops(csdev)->trace_id(csdev); i_trace_id = source_ops(i_csdev)->trace_id(i_csdev); @@ -130,30 +187,32 @@ static int coresight_find_link_outport(struct coresight_device *csdev, return -ENODEV; } -static inline u32 coresight_read_claim_tags(void __iomem *base) +static inline u32 coresight_read_claim_tags(struct coresight_device *csdev) { - return readl_relaxed(base + CORESIGHT_CLAIMCLR); + return csdev_access_relaxed_read32(&csdev->access, CORESIGHT_CLAIMCLR); } -static inline bool coresight_is_claimed_self_hosted(void __iomem *base) +static inline bool coresight_is_claimed_self_hosted(struct coresight_device *csdev) { - return coresight_read_claim_tags(base) == CORESIGHT_CLAIM_SELF_HOSTED; + return coresight_read_claim_tags(csdev) == CORESIGHT_CLAIM_SELF_HOSTED; } -static inline bool coresight_is_claimed_any(void __iomem *base) +static inline bool coresight_is_claimed_any(struct coresight_device *csdev) { - return coresight_read_claim_tags(base) != 0; + return coresight_read_claim_tags(csdev) != 0; } -static inline void coresight_set_claim_tags(void __iomem *base) +static inline void coresight_set_claim_tags(struct coresight_device *csdev) { - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMSET); + csdev_access_relaxed_write32(&csdev->access, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMSET); isb(); } -static inline void coresight_clear_claim_tags(void __iomem *base) +static inline void coresight_clear_claim_tags(struct coresight_device *csdev) { - writel_relaxed(CORESIGHT_CLAIM_SELF_HOSTED, base + CORESIGHT_CLAIMCLR); + csdev_access_relaxed_write32(&csdev->access, CORESIGHT_CLAIM_SELF_HOSTED, + CORESIGHT_CLAIMCLR); isb(); } @@ -167,39 +226,50 @@ static inline void coresight_clear_claim_tags(void __iomem *base) * Called with CS_UNLOCKed for the component. * Returns : 0 on success */ -int coresight_claim_device_unlocked(void __iomem *base) +int coresight_claim_device_unlocked(struct coresight_device *csdev) { - if (coresight_is_claimed_any(base)) + if (WARN_ON(!csdev)) + return -EINVAL; + + if (coresight_is_claimed_any(csdev)) return -EBUSY; - coresight_set_claim_tags(base); - if (coresight_is_claimed_self_hosted(base)) + coresight_set_claim_tags(csdev); + if (coresight_is_claimed_self_hosted(csdev)) return 0; /* There was a race setting the tags, clean up and fail */ - coresight_clear_claim_tags(base); + coresight_clear_claim_tags(csdev); return -EBUSY; } +EXPORT_SYMBOL_GPL(coresight_claim_device_unlocked); -int coresight_claim_device(void __iomem *base) +int coresight_claim_device(struct coresight_device *csdev) { int rc; - CS_UNLOCK(base); - rc = coresight_claim_device_unlocked(base); - CS_LOCK(base); + 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 tags for the device. * Called with CS_UNLOCKed for the component. */ -void coresight_disclaim_device_unlocked(void __iomem *base) +void coresight_disclaim_device_unlocked(struct coresight_device *csdev) { - if (coresight_is_claimed_self_hosted(base)) - coresight_clear_claim_tags(base); + if (WARN_ON(!csdev)) + return; + + if (coresight_is_claimed_self_hosted(csdev)) + coresight_clear_claim_tags(csdev); else /* * The external agent may have not honoured our claim @@ -208,13 +278,73 @@ void coresight_disclaim_device_unlocked(void __iomem *base) */ WARN_ON_ONCE(1); } +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); + +/* enable or disable an associated CTI device of the supplied CS device */ +static int +coresight_control_assoc_ectdev(struct coresight_device *csdev, bool enable) +{ + int ect_ret = 0; + struct coresight_device *ect_csdev = csdev->ect_dev; + struct module *mod; + + if (!ect_csdev) + return 0; + if ((!ect_ops(ect_csdev)->enable) || (!ect_ops(ect_csdev)->disable)) + return 0; + + mod = ect_csdev->dev.parent->driver->owner; + if (enable) { + if (try_module_get(mod)) { + ect_ret = ect_ops(ect_csdev)->enable(ect_csdev); + if (ect_ret) { + module_put(mod); + } else { + get_device(ect_csdev->dev.parent); + csdev->ect_enabled = true; + } + } else + ect_ret = -ENODEV; + } else { + if (csdev->ect_enabled) { + ect_ret = ect_ops(ect_csdev)->disable(ect_csdev); + put_device(ect_csdev->dev.parent); + module_put(mod); + csdev->ect_enabled = false; + } + } + + /* output warning if ECT enable is preventing trace operation */ + if (ect_ret) + dev_info(&csdev->dev, "Associated ECT device (%s) %s failed\n", + dev_name(&ect_csdev->dev), + enable ? "enable" : "disable"); + return ect_ret; +} -void coresight_disclaim_device(void __iomem *base) +/* + * Set the associated ect / cti device while holding the coresight_mutex + * to avoid a race with coresight_enable that may try to use this value. + */ +void coresight_set_assoc_ectdev_mutex(struct coresight_device *csdev, + struct coresight_device *ect_csdev) { - CS_UNLOCK(base); - coresight_disclaim_device_unlocked(base); - CS_LOCK(base); + mutex_lock(&coresight_mutex); + csdev->ect_dev = ect_csdev; + mutex_unlock(&coresight_mutex); } +EXPORT_SYMBOL_GPL(coresight_set_assoc_ectdev_mutex); static int coresight_enable_sink(struct coresight_device *csdev, u32 mode, void *data) @@ -228,9 +358,14 @@ static int coresight_enable_sink(struct coresight_device *csdev, if (!sink_ops(csdev)->enable) return -EINVAL; - ret = sink_ops(csdev)->enable(csdev, mode, data); + ret = coresight_control_assoc_ectdev(csdev, true); if (ret) return ret; + ret = sink_ops(csdev)->enable(csdev, mode, data); + if (ret) { + coresight_control_assoc_ectdev(csdev, false); + return ret; + } csdev->enable = true; return 0; @@ -246,6 +381,7 @@ static void coresight_disable_sink(struct coresight_device *csdev) ret = sink_ops(csdev)->disable(csdev); if (ret) return; + coresight_control_assoc_ectdev(csdev, false); csdev->enable = false; } @@ -269,8 +405,15 @@ static int coresight_enable_link(struct coresight_device *csdev, if (link_subtype == CORESIGHT_DEV_SUBTYPE_LINK_SPLIT && outport < 0) return outport; - if (link_ops(csdev)->enable) - ret = link_ops(csdev)->enable(csdev, inport, outport); + if (link_ops(csdev)->enable) { + ret = coresight_control_assoc_ectdev(csdev, true); + if (!ret) { + ret = link_ops(csdev)->enable(csdev, inport, outport); + if (ret) + coresight_control_assoc_ectdev(csdev, false); + } + } + if (!ret) csdev->enable = true; @@ -300,8 +443,10 @@ static void coresight_disable_link(struct coresight_device *csdev, nr_conns = 1; } - if (link_ops(csdev)->disable) + if (link_ops(csdev)->disable) { link_ops(csdev)->disable(csdev, inport, outport); + coresight_control_assoc_ectdev(csdev, false); + } for (i = 0; i < nr_conns; i++) if (atomic_read(&csdev->refcnt[i]) != 0) @@ -322,9 +467,14 @@ static int coresight_enable_source(struct coresight_device *csdev, u32 mode) if (!csdev->enable) { if (source_ops(csdev)->enable) { - ret = source_ops(csdev)->enable(csdev, NULL, mode); + ret = coresight_control_assoc_ectdev(csdev, true); if (ret) return ret; + ret = source_ops(csdev)->enable(csdev, NULL, mode); + if (ret) { + coresight_control_assoc_ectdev(csdev, false); + return ret; + } } csdev->enable = true; } @@ -338,7 +488,7 @@ static int coresight_enable_source(struct coresight_device *csdev, u32 mode) * 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 + * @csdev: The coresight device to disable * * Returns true if the device has been disabled. */ @@ -347,6 +497,7 @@ 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); + coresight_control_assoc_ectdev(csdev, false); csdev->enable = false; } return !csdev->enable; @@ -408,6 +559,7 @@ void coresight_disable_path(struct list_head *path) { coresight_disable_path_from(path, NULL); } +EXPORT_SYMBOL_GPL(coresight_disable_path); int coresight_enable_path(struct list_head *path, u32 mode, void *sink_data) { @@ -481,50 +633,46 @@ struct coresight_device *coresight_get_sink(struct list_head *path) return csdev; } -static int coresight_enabled_sink(struct device *dev, const void *data) +static struct coresight_device * +coresight_find_enabled_sink(struct coresight_device *csdev) { - const bool *reset = data; - struct coresight_device *csdev = to_coresight_device(dev); + int i; + struct coresight_device *sink = NULL; 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; + csdev->activated) + return csdev; - return 1; + /* + * Recursively explore each port found on this element. + */ + for (i = 0; i < csdev->pdata->nr_outport; i++) { + struct coresight_device *child_dev; + + child_dev = csdev->pdata->conns[i].child_dev; + if (child_dev) + sink = coresight_find_enabled_sink(child_dev); + if (sink) + return sink; } - return 0; + return NULL; } /** - * coresight_get_enabled_sink - returns the first enabled sink found on the bus - * @deactivate: Whether the 'enable_sink' flag should be reset + * coresight_get_enabled_sink - returns the first enabled sink using + * connection based search starting from the source reference * - * 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. + * @source: Coresight source device reference */ -struct coresight_device *coresight_get_enabled_sink(bool deactivate) +struct coresight_device * +coresight_get_enabled_sink(struct coresight_device *source) { - struct device *dev = NULL; - - dev = bus_find_device(&coresight_bustype, NULL, &deactivate, - coresight_enabled_sink); + if (!source) + return NULL; - return dev ? to_coresight_device(dev) : NULL; + return coresight_find_enabled_sink(source); } static int coresight_sink_by_id(struct device *dev, const void *data) @@ -568,13 +716,50 @@ struct coresight_device *coresight_get_sink_by_id(u32 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 inline 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 inline 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 - * the master device. + * master device. */ -static void coresight_grab_device(struct coresight_device *csdev) +static int coresight_grab_device(struct coresight_device *csdev) { int i; @@ -583,9 +768,20 @@ static void coresight_grab_device(struct coresight_device *csdev) child = csdev->pdata->conns[i].child_dev; if (child && child->type == CORESIGHT_DEV_TYPE_HELPER) - pm_runtime_get_sync(child->dev.parent); + if (!coresight_get_ref(child)) + goto err; } - pm_runtime_get_sync(csdev->dev.parent); + if (coresight_get_ref(csdev)) + return 0; +err: + for (i--; i >= 0; i--) { + struct coresight_device *child; + + child = csdev->pdata->conns[i].child_dev; + if (child && child->type == CORESIGHT_DEV_TYPE_HELPER) + coresight_put_ref(child); + } + return -ENODEV; } /* @@ -596,19 +792,20 @@ static void coresight_drop_device(struct coresight_device *csdev) { int i; - pm_runtime_put(csdev->dev.parent); + coresight_put_ref(csdev); for (i = 0; i < csdev->pdata->nr_outport; i++) { struct coresight_device *child; child = csdev->pdata->conns[i].child_dev; if (child && child->type == CORESIGHT_DEV_TYPE_HELPER) - pm_runtime_put(child->dev.parent); + coresight_put_ref(child); } } /** * _coresight_build_path - recursively build a path from a @csdev to a sink. * @csdev: The device to start from. + * @sink: The final sink we want in this path. * @path: The list to add devices to. * * The tree of Coresight device is traversed until an activated sink is @@ -621,7 +818,7 @@ static int _coresight_build_path(struct coresight_device *csdev, struct coresight_device *sink, struct list_head *path) { - int i; + int i, ret; bool found = false; struct coresight_node *node; @@ -629,6 +826,14 @@ static int _coresight_build_path(struct coresight_device *csdev, 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, 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_outport; i++) { struct coresight_device *child_dev; @@ -651,11 +856,14 @@ out: * 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; - coresight_grab_device(csdev); node->csdev = csdev; list_add(&node->link, path); @@ -707,7 +915,175 @@ void coresight_release_path(struct list_head *path) } kfree(path); - path = NULL; +} + +/* return true if the device is a suitable type for a default sink */ +static inline 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_outport; i++) { + struct coresight_device *child_dev, *sink = NULL; + int child_depth = curr_depth; + + child_dev = csdev->pdata->conns[i].child_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; +} + +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); + } } /** coresight_validate_source - make sure a source has the right credentials @@ -764,11 +1140,7 @@ int coresight_enable(struct coresight_device *csdev) 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); + sink = coresight_get_enabled_sink(csdev); if (!sink) { ret = -EINVAL; goto out; @@ -935,9 +1307,6 @@ ATTRIBUTE_GROUPS(coresight_source); static struct device_type coresight_dev_type[] = { { - .name = "none", - }, - { .name = "sink", .groups = coresight_sink_groups, }, @@ -955,6 +1324,9 @@ static struct device_type coresight_dev_type[] = { { .name = "helper", }, + { + .name = "ect", + }, }; static void coresight_device_release(struct device *dev) @@ -968,7 +1340,7 @@ static void coresight_device_release(struct device *dev) static int coresight_orphan_match(struct device *dev, void *data) { - int i; + int i, ret = 0; bool still_orphan = false; struct coresight_device *csdev, *i_csdev; struct coresight_connection *conn; @@ -990,55 +1362,62 @@ static int coresight_orphan_match(struct device *dev, void *data) for (i = 0; i < i_csdev->pdata->nr_outport; i++) { conn = &i_csdev->pdata->conns[i]; + /* Skip the port if FW doesn't describe it */ + if (!conn->child_fwnode) + continue; /* We have found at least one orphan connection */ if (conn->child_dev == NULL) { /* Does it match this newly added device? */ - if (conn->child_fwnode == csdev->dev.fwnode) - conn->child_dev = csdev; - else + if (conn->child_fwnode == csdev->dev.fwnode) { + ret = coresight_make_links(i_csdev, + conn, csdev); + if (ret) + return ret; + } 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. + * Returning '0' in case we didn't encounter any error, + * ensures that all known component on the bus will be checked. */ return 0; } -static void coresight_fixup_orphan_conns(struct coresight_device *csdev) +static int 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, + return bus_for_each_dev(&coresight_bustype, NULL, csdev, coresight_orphan_match); } -static void coresight_fixup_device_conns(struct coresight_device *csdev) +static int coresight_fixup_device_conns(struct coresight_device *csdev) { - int i; + int i, ret = 0; for (i = 0; i < csdev->pdata->nr_outport; i++) { struct coresight_connection *conn = &csdev->pdata->conns[i]; - struct device *dev = NULL; - dev = bus_find_device_by_fwnode(&coresight_bustype, conn->child_fwnode); - if (dev) { - conn->child_dev = to_coresight_device(dev); - /* and put reference from 'bus_find_device()' */ - put_device(dev); + if (!conn->child_fwnode) + continue; + conn->child_dev = + coresight_find_csdev_by_fwnode(conn->child_fwnode); + if (conn->child_dev && conn->child_dev->has_conns_grp) { + ret = coresight_make_links(csdev, conn, + conn->child_dev); + if (ret) + break; } else { csdev->orphan = true; - conn->child_dev = NULL; } } + + return ret; } static int coresight_remove_match(struct device *dev, void *data) @@ -1061,18 +1440,19 @@ static int coresight_remove_match(struct device *dev, void *data) for (i = 0; i < iterator->pdata->nr_outport; i++) { conn = &iterator->pdata->conns[i]; - if (conn->child_dev == NULL) + if (conn->child_dev == NULL || conn->child_fwnode == NULL) continue; if (csdev->dev.fwnode == conn->child_fwnode) { iterator->orphan = true; - conn->child_dev = NULL; + coresight_remove_links(iterator, conn); /* * Drop the reference to the handle for the remote * device acquired in parsing the connections from * platform data. */ fwnode_handle_put(conn->child_fwnode); + conn->child_fwnode = NULL; /* No need to continue */ break; } @@ -1103,23 +1483,24 @@ static void coresight_remove_conns(struct coresight_device *csdev) } /** - * 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. + * coresight_timeout - loop until a bit has changed to a specific register + * state. + * @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. * * 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 coresight_timeout(struct csdev_access *csa, u32 offset, + int position, int value) { int i; u32 val; for (i = TIMEOUT_US; i > 0; i--) { - val = __raw_readl(addr + offset); + val = csdev_access_read32(csa, offset); /* waiting on the bit to go from 0 to 1 */ if (value) { if (val & BIT(position)) @@ -1141,31 +1522,75 @@ int coresight_timeout(void __iomem *addr, u32 offset, int position, int value) return -EAGAIN; } +EXPORT_SYMBOL_GPL(coresight_timeout); -struct bus_type coresight_bustype = { - .name = "coresight", -}; +u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset) +{ + return csdev_access_relaxed_read32(&csdev->access, offset); +} -static int __init coresight_init(void) +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 bus_register(&coresight_bustype); + 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); } -postcore_initcall(coresight_init); /* * coresight_release_platform_data: Release references to the devices connected * to the output port of this device. */ -void coresight_release_platform_data(struct coresight_platform_data *pdata) +void coresight_release_platform_data(struct coresight_device *csdev, + struct coresight_platform_data *pdata) { int i; + struct coresight_connection *conns = pdata->conns; for (i = 0; i < pdata->nr_outport; i++) { - if (pdata->conns[i].child_fwnode) { - fwnode_handle_put(pdata->conns[i].child_fwnode); + /* If we have made the links, remove them now */ + if (csdev && conns[i].child_dev) + coresight_remove_links(csdev, &conns[i]); + /* + * Drop the refcount and clear the handle as this device + * is going away + */ + if (conns[i].child_fwnode) { + fwnode_handle_put(conns[i].child_fwnode); pdata->conns[i].child_fwnode = NULL; } } + if (csdev) + coresight_remove_conns_sysfs_group(csdev); } struct coresight_device *coresight_register(struct coresight_desc *desc) @@ -1175,6 +1600,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) int nr_refcnts = 1; atomic_t *refcnts = NULL; struct coresight_device *csdev; + bool registered = false; csdev = kzalloc(sizeof(*csdev), GFP_KERNEL); if (!csdev) { @@ -1195,7 +1621,8 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) refcnts = kcalloc(nr_refcnts, sizeof(*refcnts), GFP_KERNEL); if (!refcnts) { ret = -ENOMEM; - goto err_free_csdev; + kfree(csdev); + goto err_out; } csdev->refcnt = refcnts; @@ -1205,6 +1632,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) csdev->type = desc->type; csdev->subtype = desc->subtype; csdev->ops = desc->ops; + csdev->access = desc->access; csdev->orphan = false; csdev->dev.type = &coresight_dev_type[desc->type]; @@ -1219,6 +1647,13 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) csdev->dev.fwnode = fwnode_handle_get(dev_fwnode(desc->dev)); dev_set_name(&csdev->dev, "%s", desc->name); + /* + * 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); @@ -1226,7 +1661,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) * All resources are free'd explicitly via * coresight_device_release(), triggered from put_device(). */ - goto err_out; + goto out_unlock; } if (csdev->type == CORESIGHT_DEV_TYPE_SINK || @@ -1241,24 +1676,36 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) * from put_device(), which is in turn called from * function device_unregister(). */ - goto err_out; + goto out_unlock; } } + /* Device is now registered */ + registered = true; - mutex_lock(&coresight_mutex); - - coresight_fixup_device_conns(csdev); - coresight_fixup_orphan_conns(csdev); + ret = coresight_create_conns_sysfs_group(csdev); + if (!ret) + ret = coresight_fixup_device_conns(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; + } - return csdev; + /* Unregister the device if needed */ + if (registered) { + coresight_unregister(csdev); + return ERR_PTR(ret); + } -err_free_csdev: - kfree(csdev); err_out: /* Cleanup the connection information */ - coresight_release_platform_data(desc->pdata); + coresight_release_platform_data(NULL, desc->pdata); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(coresight_register); @@ -1267,8 +1714,11 @@ 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_release_platform_data(csdev->pdata); + coresight_clear_default_sink(csdev); + coresight_release_platform_data(csdev, csdev->pdata); device_unregister(&csdev->dev); } EXPORT_SYMBOL_GPL(coresight_unregister); @@ -1296,6 +1746,7 @@ 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 @@ -1317,9 +1768,9 @@ char *coresight_alloc_device_name(struct coresight_dev_list *dict, if (idx < 0) { /* Make space for the new entry */ idx = dict->nr_idx; - list = krealloc(dict->fwnode_list, - (idx + 1) * sizeof(*dict->fwnode_list), - GFP_KERNEL); + list = krealloc_array(dict->fwnode_list, + idx + 1, sizeof(*dict->fwnode_list), + GFP_KERNEL); if (ZERO_OR_NULL_PTR(list)) { idx = -ENOMEM; goto done; @@ -1336,3 +1787,45 @@ done: return name; } EXPORT_SYMBOL_GPL(coresight_alloc_device_name); + +struct bus_type coresight_bustype = { + .name = "coresight", +}; + +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; + + /* initialise the coresight syscfg API */ + ret = cscfg_init(); + if (!ret) + return 0; + + etm_perf_exit(); +exit_bus_unregister: + bus_unregister(&coresight_bustype); + return ret; +} + +static void __exit coresight_exit(void) +{ + cscfg_exit(); + etm_perf_exit(); + bus_unregister(&coresight_bustype); +} + +module_init(coresight_init); +module_exit(coresight_exit); + +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 96544b348c27..1874df7c6a73 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/panic_notifier.h> #include <linux/pm_qos.h> #include <linux/slab.h> #include <linux/smp.h> @@ -104,7 +105,7 @@ 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 +347,10 @@ 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 +380,10 @@ 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 +402,7 @@ 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 = { @@ -587,11 +589,11 @@ static int debug_probe(struct amba_device *adev, const struct amba_id *id) 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); @@ -627,7 +629,7 @@ err: return ret; } -static int debug_remove(struct amba_device *adev) +static void debug_remove(struct amba_device *adev) { struct device *dev = &adev->dev; struct debug_drvdata *drvdata = amba_get_drvdata(adev); @@ -642,8 +644,6 @@ static int debug_remove(struct amba_device *adev) if (!--debug_count) debug_func_exit(); - - return 0; } static const struct amba_cs_uci_id uci_id_debug[] = { @@ -665,6 +665,8 @@ static const struct amba_id debug_ids[] = { {}, }; +MODULE_DEVICE_TABLE(amba, debug_ids); + static struct amba_driver debug_driver = { .drv = { .name = "coresight-cpu-debug", diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c new file mode 100644 index 000000000000..c6e8c6542f24 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -0,0 +1,1004 @@ +// 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; + + 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; + atomic_inc(&drvdata->config.enable_req_count); + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return rc; + +cti_state_unchanged: + atomic_inc(&drvdata->config.enable_req_count); + + /* cannot enable due to error */ +cti_err_not_enabled: + 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; + + spin_lock(&drvdata->spinlock); + config->hw_powered = true; + + /* no need to do anything if no enable request */ + if (!atomic_read(&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; + spin_unlock(&drvdata->spinlock); + return; + + /* did not re-enable due to no claim / no request */ +cti_hp_not_enabled: + 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; + + spin_lock(&drvdata->spinlock); + + /* check refcount - disable on 0 */ + if (atomic_dec_return(&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); + spin_unlock(&drvdata->spinlock); + return 0; + + /* not disabled this call */ +cti_not_disabled: + spin_unlock(&drvdata->spinlock); + return 0; +} + +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; + + spin_lock(&drvdata->spinlock); + /* write if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIINTACK, ackval); + 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); + atomic_set(&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)); + + 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); + 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); + + 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); + } + 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); + + 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); + 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_ECT) || 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_set_assoc_ectdev_mutex(csdev->ect_dev, + ect_item->csdev); + break; + } + } +cti_add_done: + mutex_unlock(&ect_mutex); +} + +/* + * Removing the associated devices is easier. + * A CTI will not have a value for csdev->ect_dev. + */ +static void cti_remove_assoc_from_csdev(struct coresight_device *csdev) +{ + struct cti_drvdata *ctidrv; + struct cti_trig_con *tc; + struct cti_device *ctidev; + + mutex_lock(&ect_mutex); + if (csdev->ect_dev) { + ctidrv = csdev_to_cti_drvdata(csdev->ect_dev); + 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; + } + } + csdev->ect_dev = NULL; + } + 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_set_assoc_ectdev_mutex(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) { + coresight_set_assoc_ectdev_mutex(tc->con_dev, + NULL); + 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; + + 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 (atomic_read(&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: + 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; + + spin_lock(&drvdata->spinlock); + drvdata->config.hw_powered = false; + if (drvdata->config.hw_enabled) + coresight_disclaim_device(drvdata->csdev); + 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) +{ + struct cti_drvdata *drvdata = csdev_to_cti_drvdata(csdev); + + return cti_enable_hw(drvdata); +} + +int cti_disable(struct coresight_device *csdev) +{ + struct cti_drvdata *drvdata = csdev_to_cti_drvdata(csdev); + + return cti_disable_hw(drvdata); +} + +static const struct coresight_ops_ect cti_ops_ect = { + .enable = cti_enable, + .disable = cti_disable, +}; + +static const struct coresight_ops cti_ops = { + .ect_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); + + 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_ECT; + cti_desc.subtype.ect_subtype = CORESIGHT_DEV_SUBTYPE_ECT_CTI; + cti_desc.ops = &cti_ops; + cti_desc.groups = drvdata->ctidev.con_groups; + cti_desc.dev = dev; + 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}, +}; + +MODULE_DEVICE_TABLE(amba, cti_ids); + +static struct amba_driver cti_driver = { + .drv = { + .name = "coresight-cti", + .owner = THIS_MODULE, + .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..ccef04f27f12 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-platform.c @@ -0,0 +1,490 @@ +// 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; + struct fwnode_handle *fwnode = dev_fwnode(dev); + struct fwnode_handle *child = NULL; + + if (IS_ERR_OR_NULL(fwnode)) + return -EINVAL; + + fwnode_for_each_child_node(fwnode, child) { + if (cti_plat_node_name_eq(child, CTI_DT_CONNS)) + rc = cti_plat_create_connection(dev, drvdata, + child); + if (rc != 0) + break; + } + fwnode_handle_put(child); + + 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..6d59c815ecf5 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti-sysfs.c @@ -0,0 +1,1178 @@ +// 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); + + enable_req = atomic_read(&drvdata->config.enable_req_count); + spin_lock(&drvdata->spinlock); + powered = drvdata->config.hw_powered; + enabled = drvdata->config.hw_enabled; + 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 = cti_enable(drvdata->csdev); + else + ret = cti_disable(drvdata->csdev); + 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); + + spin_lock(&drvdata->spinlock); + powered = drvdata->config.hw_powered; + 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); + spin_lock(&drvdata->spinlock); + if (drvdata->config.hw_powered) + val = readl_relaxed(drvdata->base + cti_attr->off); + 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); + spin_lock(&drvdata->spinlock); + if (drvdata->config.hw_powered) + cti_write_single_reg(drvdata, cti_attr->off, val); + 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; + + 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; + } + 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; + + 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); + 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; + + spin_lock(&drvdata->spinlock); + drvdata->config.ctiinout_sel = val; + 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); + + spin_lock(&drvdata->spinlock); + index = drvdata->config.ctiinout_sel; + val = drvdata->config.ctiinen[index]; + 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; + + 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); + 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); + + spin_lock(&drvdata->spinlock); + index = drvdata->config.ctiinout_sel; + val = drvdata->config.ctiouten[index]; + 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; + + 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); + 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; + + 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); + 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; + + spin_lock(&drvdata->spinlock); + + /* write through if enabled */ + if (cti_active(config)) + cti_write_single_reg(drvdata, CTIAPPPULSE, val); + 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); + + spin_lock(&drvdata->spinlock); + val = drvdata->config.trig_filter_enable; + 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; + + spin_lock(&drvdata->spinlock); + drvdata->config.trig_filter_enable = !!val; + 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; + + 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); + + 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; + + spin_lock(&drvdata->spinlock); + drvdata->config.xtrig_rchan_sel = val; + 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); + + spin_lock(&drvdata->spinlock); + val = drvdata->config.xtrig_rchan_sel; + 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. */ + spin_lock(&drvdata->spinlock); + for (i = 0; i < config->nr_trig_max; i++) { + inuse_bits |= config->ctiinen[i]; + inuse_bits |= config->ctiouten[i]; + } + 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..acf7b545e6b9 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-cti.h @@ -0,0 +1,241 @@ +/* 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/fwnode.h> +#include <linux/list.h> +#include <linux/spinlock.h> +#include <linux/sysfs.h> +#include <linux/types.h> + +#include "coresight-priv.h" + +/* + * 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 */ + atomic_t 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; + 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); +int cti_disable(struct coresight_device *csdev); +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-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 3810290e6d07..8aa6e4f83e42 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -132,7 +132,7 @@ 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; @@ -176,6 +176,7 @@ static int etb_enable_perf(struct coresight_device *csdev, void *data) unsigned long flags; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct perf_output_handle *handle = data; + struct cs_buffers *buf = etm_perf_sink_config(handle); spin_lock_irqsave(&drvdata->spinlock, flags); @@ -186,7 +187,7 @@ static int etb_enable_perf(struct coresight_device *csdev, void *data) } /* Get a handle on the pid of the process to monitor */ - pid = task_pid_nr(handle->event->owner); + pid = buf->pid; if (drvdata->pid != -1 && drvdata->pid != pid) { ret = -EBUSY; @@ -251,6 +252,7 @@ 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); @@ -262,7 +264,7 @@ 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)) { + if (coresight_timeout(csa, ETB_FFCR, ETB_FFCR_BIT, 0)) { dev_err(dev, "timeout while waiting for completion of Manual Flush\n"); } @@ -270,7 +272,7 @@ static void __etb_disable_hw(struct etb_drvdata *drvdata) /* disable trace capture */ writel_relaxed(0x0, drvdata->base + ETB_CTL_REG); - if (coresight_timeout(drvdata->base, ETB_FFSR, ETB_FFSR_BIT, 1)) { + if (coresight_timeout(csa, ETB_FFSR, ETB_FFSR_BIT, 1)) { dev_err(dev, "timeout while waiting for Formatter to Stop\n"); } @@ -343,7 +345,7 @@ 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 int etb_disable(struct coresight_device *csdev) @@ -383,6 +385,7 @@ static void *etb_alloc_buffer(struct coresight_device *csdev, if (!buf) return NULL; + buf->pid = task_pid_nr(event->owner); buf->snapshot = overwrite; buf->nr_pages = nr_pages; buf->data_pages = pages; @@ -525,7 +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; @@ -554,9 +557,8 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, /* * In snapshot mode we simply increment the head by the number of byte - * that were written. User space function cs_etm_find_snapshot() will - * figure out how many bytes to get from the AUX buffer based on the - * position of the head. + * 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; @@ -653,27 +655,15 @@ static const struct file_operations etb_fops = { .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, }; @@ -717,7 +707,7 @@ 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, @@ -755,6 +745,7 @@ 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); @@ -801,6 +792,19 @@ 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) { @@ -835,6 +839,8 @@ static const struct amba_id etb_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, etb_ids); + static struct amba_driver etb_driver = { .drv = { .name = "coresight-etb10", @@ -844,6 +850,13 @@ static struct amba_driver etb_driver = { }, .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 84f1dcb69827..43bbd5dc3d3b 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -18,29 +18,87 @@ #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" 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)); -PMU_FORMAT_ATTR(contextid, "config:" __stringify(ETM_OPT_CTXTID)); +/* 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"); + + +/* + * 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, NULL, }; @@ -58,9 +116,19 @@ static const struct attribute_group etm_pmu_sinks_group = { .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, }; @@ -126,10 +194,10 @@ static void free_sink_buffer(struct etm_event_data *event_data) cpumask_t *mask = &event_data->mask; struct coresight_device *sink; - if (WARN_ON(cpumask_empty(mask))) + if (!event_data->snk_config) return; - if (!event_data->snk_config) + if (WARN_ON(cpumask_empty(mask))) return; cpu = cpumask_first(mask); @@ -149,6 +217,10 @@ static void free_event_data(struct work_struct *work) /* Free the sink buffers, if there are any */ 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; @@ -204,13 +276,33 @@ static void etm_free_aux(void *data) schedule_work(&event_data->work); } +/* + * 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) { - u32 id; + 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(cpu); @@ -219,15 +311,18 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, INIT_WORK(&event_data->work, free_event_data); /* First get the selected sink from user space. */ - if (event->attr.config2) { + if (event->attr.config2 & GENMASK_ULL(31, 0)) { id = (u32)event->attr.config2; - sink = coresight_get_sink_by_id(id); - } else { - sink = coresight_get_enabled_sink(true); + sink = user_sink = coresight_get_sink_by_id(id); } - if (!sink) - goto err; + /* 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; @@ -254,6 +349,35 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, } /* + * 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. @@ -267,6 +391,10 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, *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) @@ -275,7 +403,12 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, if (!sink_ops(sink)->alloc_buffer || !sink_ops(sink)->free_buffer) goto err; - /* Allocate the sink buffer for this session */ + /* + * 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, event, pages, nr_pages, overwrite); @@ -295,13 +428,18 @@ 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; if (!csdev) goto fail; + /* 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. @@ -310,6 +448,21 @@ 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); /* We need a sink, no need to continue without one */ sink = coresight_get_sink(path); @@ -320,24 +473,32 @@ static void etm_event_start(struct perf_event *event, int flags) if (coresight_enable_path(path, CS_MODE_PERF, handle)) 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)) goto fail_disable_path; 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_stop(struct perf_event *event, int mode) @@ -345,13 +506,43 @@ 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 etm_ctxt *ctxt = this_cpu_ptr(&etm_ctxt); + struct perf_output_handle *handle = &ctxt->handle; + struct etm_event_data *event_data; struct list_head *path; + /* + * 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; @@ -369,7 +560,13 @@ static void etm_event_stop(struct perf_event *event, int mode) /* 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; @@ -379,7 +576,21 @@ 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 */ @@ -506,6 +717,7 @@ 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, @@ -517,69 +729,128 @@ static ssize_t etm_perf_sink_name_show(struct device *dev, return scnprintf(buf, PAGE_SIZE, "0x%lx\n", (unsigned long)(ea->var)); } -int etm_perf_add_symlink_sink(struct coresight_device *csdev) +static struct dev_ext_attribute * +etm_perf_add_symlink_group(struct device *dev, const char *name, const char *group_name) { - int ret; + struct dev_ext_attribute *ea; unsigned long hash; - const char *name; + int ret; struct device *pmu_dev = etm_pmu.dev; - struct device *dev = &csdev->dev; - struct dev_ext_attribute *ea; - - if (csdev->type != CORESIGHT_DEV_TYPE_SINK && - csdev->type != CORESIGHT_DEV_TYPE_LINKSINK) - return -EINVAL; - - if (csdev->ea != NULL) - return -EINVAL; if (!etm_perf_up) - return -EPROBE_DEFER; + return ERR_PTR(-EPROBE_DEFER); ea = devm_kzalloc(dev, sizeof(*ea), GFP_KERNEL); if (!ea) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - name = dev_name(dev); - /* See function coresight_get_sink_by_id() to know where this is used */ + /* + * 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 -ENOMEM; + return ERR_PTR(-ENOMEM); ea->attr.attr.mode = 0444; - ea->attr.show = etm_perf_sink_name_show; ea->var = (unsigned long *)hash; ret = sysfs_add_file_to_group(&pmu_dev->kobj, - &ea->attr.attr, "sinks"); + &ea->attr.attr, group_name); - if (!ret) - csdev->ea = ea; + return ret ? ERR_PTR(ret) : ea; +} - return ret; +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; } -void etm_perf_del_symlink_sink(struct coresight_device *csdev) +static void etm_perf_del_symlink_group(struct dev_ext_attribute *ea, const char *group_name) { struct device *pmu_dev = etm_pmu.dev; - struct dev_ext_attribute *ea = csdev->ea; + 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 (!ea) + if (!csdev->ea) return; - sysfs_remove_file_from_group(&pmu_dev->kobj, - &ea->attr.attr, "sinks"); + etm_perf_del_symlink_group(csdev->ea, "sinks"); csdev->ea = NULL; } -static int __init etm_perf_init(void) +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%lx\n", (unsigned long)(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; @@ -606,4 +877,8 @@ 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 015213abe00a..468f7799ab4f 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 @@ -48,16 +49,18 @@ struct etm_filters { * @work: Handle to free allocated memory outside IRQ context. * @mask: Hold the CPU(s) this event was set for. * @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; void *snk_config; + u32 cfg_hash; struct list_head * __percpu *path; }; -#ifdef CONFIG_CORESIGHT +#if IS_ENABLED(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); @@ -69,6 +72,9 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle) return data->snk_config; return NULL; } +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); #else static inline int etm_perf_symlink(struct coresight_device *csdev, bool link) { return -EINVAL; } @@ -79,7 +85,14 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle) { return NULL; } +int etm_perf_add_symlink_cscfg(struct device *dev, + struct cscfg_config_desc *config_desc) +{ return -EINVAL; } +void etm_perf_del_symlink_cscfg(struct cscfg_config_desc *config_desc) {} #endif /* CONFIG_CORESIGHT */ +int __init etm_perf_init(void); +void etm_perf_exit(void); + #endif diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index e2cb6873c3f2..d0ab9933472b 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -40,8 +40,6 @@ 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; @@ -206,7 +204,7 @@ 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 +340,10 @@ 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 +362,11 @@ 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); - rc = coresight_claim_device_unlocked(drvdata->base); + rc = coresight_claim_device_unlocked(csdev); if (rc) goto done; @@ -504,7 +507,7 @@ static int etm_enable_perf(struct coresight_device *csdev, static int etm_enable_sysfs(struct coresight_device *csdev) { 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); @@ -568,6 +571,7 @@ static void etm_disable_hw(void *info) int i; struct etm_drvdata *drvdata = info; struct etm_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); etm_set_prog(drvdata); @@ -579,7 +583,7 @@ 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); @@ -604,7 +608,7 @@ 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->base); } @@ -782,6 +786,42 @@ static void etm_init_trace_id(struct etm_drvdata *drvdata) drvdata->traceid = coresight_get_trace_id(drvdata->cpu); } +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_hp_clear(void) +{ + 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) { int ret; @@ -805,6 +845,7 @@ static int etm_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); @@ -823,39 +864,20 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) if (!desc.name) return -ENOMEM; - cpus_read_lock(); - etmdrvdata[drvdata->cpu] = drvdata; - 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)) { - ret = PTR_ERR(pdata); - goto err_arch_supported; - } + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + adev->dev.platform_data = pdata; desc.type = CORESIGHT_DEV_TYPE_SOURCE; @@ -865,17 +887,17 @@ 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(&drvdata->csdev->dev, "%s initialized\n", (char *)coresight_get_uci_data(id)); @@ -885,14 +907,38 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id) } 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 @@ -937,6 +983,8 @@ static const struct amba_id etm_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, etm_ids); + static struct amba_driver etm_driver = { .drv = { .name = "coresight-etm3x", @@ -945,6 +993,39 @@ static struct amba_driver etm_driver = { .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 e8c7649f123e..fd81eca3ec18 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-sysfs.c @@ -474,7 +474,7 @@ 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; @@ -1252,31 +1252,17 @@ 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..d2ea903231b2 --- /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: 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: 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..80fefaba58ee --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -0,0 +1,2210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2014, The Linux Foundation. All rights reserved. + */ + +#include <linux/bitops.h> +#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/cpu_pm.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/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/property.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" + +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 { + unsigned int pid; + struct etmv4_drvdata *drvdata; + struct csdev_access *csa; +}; + +/* + * 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 inline 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 inline 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; +} + +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; +}; + +/* + * 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) +{ + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!drvdata->trfcr) + return; + cpu_prohibit_trace(); +} + +/* + * 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 = drvdata->trfcr; + + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!trfcr) + return; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_ELx_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_ELx_E0TRE; + + write_trfcr(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, + unsigned int id) +{ + if (etm4_hisi_match_pid(id)) + 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, + unsigned int id) +{ +} +#endif /* CONFIG_ETM4X_IMPDEF_FEATURE */ + +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 (coresight_timeout(csa, TRCSTATR, 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)); + etm4x_relaxed_write32(csa, config->seq_rst, TRCSEQRSTEVR); + etm4x_relaxed_write32(csa, config->seq_state, TRCSEQSTR); + 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; 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); + } + + /* + * 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); + /* Enable the trace unit */ + etm4x_relaxed_write32(csa, 1, TRCPRGCTLR); + + /* Synchronize the register updates for sysreg access */ + if (!csa->io_mem) + isb(); + + /* wait for TRCSTATR.IDLE to go back down to '0' */ + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 0)) + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + + /* + * As recommended by section 4.3.7 ("Synchronization when using the + * memory-mapped interface") of ARM IHI 0064D + */ + dsb(sy); + isb(); + +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_hw_smp_call(void *info) +{ + struct etm4_enable_arg *arg = info; + + if (WARN_ON(!arg)) + return; + arg->rc = etm4_enable_hw(arg->drvdata); +} + +/* + * 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; + + /* 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 |= TRCCONFIGR_CCI; + /* TRM: Must program this for cycacc to work */ + config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT; + } + 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) +{ + 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(csdev, 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 = { }; + 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; + } + + 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(&csdev->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; + struct etmv4_config *config = &drvdata->config; + struct coresight_device *csdev = drvdata->csdev; + struct device *etm_dev = &csdev->dev; + 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); + } + + 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); + /* + * Make sure everything completes before disabling, as recommended + * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register, + * SSTATUS") of ARM IHI 0064D + */ + dsb(sy); + isb(); + /* Trace synchronization barrier, is a nop if not supported */ + tsb_csync(); + etm4x_relaxed_write32(csa, control, TRCPRGCTLR); + + /* wait for TRCSTATR.PMSTABLE to go to '1' */ + if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) + dev_err(etm_dev, + "timeout while waiting for PM stable Trace Status\n"); + /* 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 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)); + + 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(&csdev->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 inline 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 etm4_init_iomem_access(struct etmv4_drvdata *drvdata, + struct csdev_access *csa) +{ + u32 devarch = readl_relaxed(drvdata->base + TRCDEVARCH); + u32 idr1 = readl_relaxed(drvdata->base + TRCIDR1); + + /* + * All ETMs must implement TRCDEVARCH to indicate that + * the component is an ETMv4. To support any broken + * implementations we fall back to TRCIDR1 check, which + * is not really reliable. + */ + if ((devarch & ETM_DEVARCH_ID_MASK) == ETM_DEVARCH_ETMv4x_ARCH) { + drvdata->arch = etm_devarch_to_arch(devarch); + } else { + pr_warn("CPU%d: ETM4x incompatible TRCDEVARCH: %x, falling back to TRCIDR1\n", + smp_processor_id(), devarch); + + if (ETM_TRCIDR1_ARCH_MAJOR(idr1) != ETM_TRCIDR1_ARCH_ETMv4) + return false; + drvdata->arch = etm_trcidr_to_arch(idr1); + } + + *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 = (TRFCR_ELx_TS_VIRTUAL | + TRFCR_ELx_ExTRE | + TRFCR_ELx_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; +} + +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; + int i; + + drvdata = init_arg->drvdata; + 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; + + /* 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, init_arg->pid); + + /* 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); + /* 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); + /* 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); + /* 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); + etm4_cs_lock(drvdata, csa); + cpu_detect_trace_filtering(drvdata); +} + +static inline 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 + * 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 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]); + + 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_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 (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for PM Stable Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + state = drvdata->save_state; + + state->trcprgctlr = etm4x_read32(csa, TRCPRGCTLR); + 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); + 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); + state->trcvdctlr = etm4x_read32(csa, TRCVDCTLR); + state->trcvdsacctlr = etm4x_read32(csa, TRCVDSACCTLR); + state->trcvdarcctlr = etm4x_read32(csa, TRCVDARCCTLR); + + for (i = 0; i < drvdata->nrseqstate - 1; i++) + state->trcseqevr[i] = etm4x_read32(csa, TRCSEQEVRn(i)); + + state->trcseqrstevr = etm4x_read32(csa, TRCSEQRSTEVR); + state->trcseqstr = etm4x_read32(csa, TRCSEQSTR); + 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)); + } + + for (i = 0; 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 (coresight_timeout(csa, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) { + dev_err(etm_dev, + "timeout while waiting for Idle Trace Status\n"); + etm4_os_unlock(drvdata); + ret = -EBUSY; + goto out; + } + + drvdata->state_needs_restore = true; + + /* + * 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; + + /* Save the TRFCR irrespective of whether the ETM is ON */ + if (drvdata->trfcr) + drvdata->save_trfcr = read_trfcr(); + /* + * Save and restore the ETM Trace registers only if + * the ETM is active. + */ + if (local_read(&drvdata->mode) && drvdata->save_state) + 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 tmp_csa = CSDEV_ACCESS_IOMEM(drvdata->base); + struct csdev_access *csa = &tmp_csa; + + etm4_cs_unlock(drvdata, csa); + etm4x_relaxed_write32(csa, state->trcclaimset, TRCCLAIMSET); + + etm4x_relaxed_write32(csa, state->trcprgctlr, TRCPRGCTLR); + 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); + 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); + etm4x_relaxed_write32(csa, state->trcvdctlr, TRCVDCTLR); + etm4x_relaxed_write32(csa, state->trcvdsacctlr, TRCVDSACCTLR); + etm4x_relaxed_write32(csa, state->trcvdarcctlr, TRCVDARCCTLR); + + for (i = 0; i < drvdata->nrseqstate - 1; i++) + etm4x_relaxed_write32(csa, state->trcseqevr[i], TRCSEQEVRn(i)); + + etm4x_relaxed_write32(csa, state->trcseqrstevr, TRCSEQRSTEVR); + etm4x_relaxed_write32(csa, state->trcseqstr, TRCSEQSTR); + 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)); + } + + for (i = 0; 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); + + drvdata->state_needs_restore = false; + + /* + * 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); + etm4_cs_lock(drvdata, csa); +} + +static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) +{ + if (drvdata->trfcr) + write_trfcr(drvdata->save_trfcr); + if (drvdata->state_needs_restore) + __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_probe(struct device *dev, void __iomem *base, u32 etm_pid) +{ + int ret; + struct coresight_platform_data *pdata = NULL; + struct etmv4_drvdata *drvdata; + struct coresight_desc desc = { 0 }; + struct etm4_init_arg init_arg = { 0 }; + u8 major, minor; + char *type_name; + + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); + if (!drvdata) + return -ENOMEM; + + dev_set_drvdata(dev, drvdata); + + 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; + } + + drvdata->base = base; + + spin_lock_init(&drvdata->spinlock); + + drvdata->cpu = coresight_get_cpu(dev); + if (drvdata->cpu < 0) + return drvdata->cpu; + + init_arg.drvdata = drvdata; + init_arg.csa = &desc.access; + init_arg.pid = etm_pid; + + if (smp_call_function_single(drvdata->cpu, + etm4_init_arch_data, &init_arg, 1)) + dev_err(dev, "ETM arch init failed\n"); + + if (!drvdata->arch) + return -EINVAL; + + /* TRCPDCR is not accessible with system instructions. */ + if (!desc.access.io_mem || + fwnode_property_present(dev_fwnode(dev), "qcom,skip-power-up")) + drvdata->skip_power_up = true; + + 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_init_trace_id(drvdata); + 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(drvdata->csdev); + drvdata->boot_enable = true; + } + + return 0; +} + +static int etm4_probe_amba(struct amba_device *adev, const struct amba_id *id) +{ + 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); + + ret = etm4_probe(dev, base, id->id); + if (!ret) + pm_runtime_put(&adev->dev); + + return ret; +} + +static int etm4_probe_platform_dev(struct platform_device *pdev) +{ + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + /* + * System register based devices could match the + * HW by reading appropriate registers on the HW + * and thus we could skip the PID. + */ + ret = etm4_probe(&pdev->dev, NULL, 0); + + pm_runtime_put(&pdev->dev); + return ret; +} + +static struct amba_cs_uci_id uci_id_etm4[] = { + { + /* ETMv4 UCI data */ + .devarch = ETM_DEVARCH_ETMv4x_ARCH, + .devarch_mask = ETM_DEVARCH_ID_MASK, + .devtype = 0x00000013, + } +}; + +static void clear_etmdrvdata(void *info) +{ + int cpu = *(int *)info; + + etmdrvdata[cpu] = NULL; +} + +static int __exit etm4_remove_dev(struct etmv4_drvdata *drvdata) +{ + etm_perf_symlink(drvdata->csdev, false); + /* + * Taking hotplug lock here to avoid racing between etm4_remove_dev() + * 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(); + + cscfg_unregister_csdev(drvdata->csdev); + coresight_unregister(drvdata->csdev); + + return 0; +} + +static void __exit etm4_remove_amba(struct amba_device *adev) +{ + struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + if (drvdata) + etm4_remove_dev(drvdata); +} + +static int __exit etm4_remove_platform_dev(struct platform_device *pdev) +{ + int ret = 0; + struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev); + + if (drvdata) + ret = etm4_remove_dev(drvdata); + pm_runtime_disable(&pdev->dev); + return ret; +} + +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 */ + {}, +}; + +MODULE_DEVICE_TABLE(amba, etm4_ids); + +static struct amba_driver etm4x_amba_driver = { + .drv = { + .name = "coresight-etm4x", + .owner = THIS_MODULE, + .suppress_bind_attrs = true, + }, + .probe = etm4_probe_amba, + .remove = etm4_remove_amba, + .id_table = etm4_ids, +}; + +static const struct of_device_id etm4_sysreg_match[] = { + { .compatible = "arm,coresight-etm4x-sysreg" }, + { .compatible = "arm,embedded-trace-extension" }, + {} +}; + +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, + .suppress_bind_attrs = true, + }, +}; + +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 ce41482431f9..9cac848cffaf 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -9,6 +9,7 @@ #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 +22,7 @@ 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; @@ -179,12 +180,12 @@ static ssize_t reset_store(struct device *dev, /* 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 +206,11 @@ 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 */ @@ -236,7 +237,7 @@ 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; @@ -269,6 +270,8 @@ static ssize_t reset_store(struct device *dev, spin_unlock(&drvdata->spinlock); + cscfg_csdev_reset_feats(to_coresight_device(dev)); + return size; } static DEVICE_ATTR_WO(reset); @@ -301,130 +304,134 @@ static ssize_t mode_store(struct device *dev, 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); @@ -527,7 +534,7 @@ 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); } @@ -544,23 +551,28 @@ static ssize_t event_instren_store(struct device *dev, 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; @@ -695,10 +707,10 @@ static ssize_t bb_ctrl_store(struct device *dev, * individual range comparators. If include then at least 1 * range must be selected. */ - if ((val & BIT(8)) && (BMVAL(val, 0, 7) == 0)) + if ((val & TRCBBCTLR_MODE) && (FIELD_GET(TRCBBCTLR_RANGE_MASK, val) == 0)) return -EINVAL; - config->bb_ctrl = val & GENMASK(8, 0); + config->bb_ctrl = val & (TRCBBCTLR_MODE | TRCBBCTLR_RANGE_MASK); return size; } static DEVICE_ATTR_RW(bb_ctrl); @@ -711,7 +723,7 @@ 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); } @@ -727,9 +739,9 @@ static ssize_t event_vinst_store(struct device *dev, return -EINVAL; spin_lock(&drvdata->spinlock); - val &= ETMv4_EVENT_MASK; - config->vinst_ctrl &= ~ETMv4_EVENT_MASK; - config->vinst_ctrl |= val; + val &= TRCVICTLR_EVENT_MASK >> __bf_shf(TRCVICTLR_EVENT_MASK); + config->vinst_ctrl &= ~TRCVICTLR_EVENT_MASK; + config->vinst_ctrl |= FIELD_PREP(TRCVICTLR_EVENT_MASK, val); spin_unlock(&drvdata->spinlock); return size; } @@ -743,7 +755,7 @@ 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 = (config->vinst_ctrl & ETM_EXLEVEL_S_VICTLR_MASK) >> 16; + val = FIELD_GET(TRCVICTLR_EXLEVEL_S_MASK, config->vinst_ctrl); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -760,10 +772,10 @@ static ssize_t s_exlevel_vinst_store(struct device *dev, spin_lock(&drvdata->spinlock); /* clear all EXLEVEL_S bits */ - config->vinst_ctrl &= ~(ETM_EXLEVEL_S_VICTLR_MASK); + config->vinst_ctrl &= ~TRCVICTLR_EXLEVEL_S_MASK; /* enable instruction tracing for corresponding exception level */ val &= drvdata->s_ex_level; - config->vinst_ctrl |= (val << 16); + config->vinst_ctrl |= val << __bf_shf(TRCVICTLR_EXLEVEL_S_MASK); spin_unlock(&drvdata->spinlock); return size; } @@ -778,7 +790,7 @@ static ssize_t ns_exlevel_vinst_show(struct device *dev, struct etmv4_config *config = &drvdata->config; /* EXLEVEL_NS, bits[23:20] */ - val = (config->vinst_ctrl & ETM_EXLEVEL_NS_VICTLR_MASK) >> 20; + val = FIELD_GET(TRCVICTLR_EXLEVEL_NS_MASK, config->vinst_ctrl); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -795,10 +807,10 @@ static ssize_t ns_exlevel_vinst_store(struct device *dev, spin_lock(&drvdata->spinlock); /* clear EXLEVEL_NS bits */ - config->vinst_ctrl &= ~(ETM_EXLEVEL_NS_VICTLR_MASK); + config->vinst_ctrl &= ~TRCVICTLR_EXLEVEL_NS_MASK; /* enable instruction tracing for corresponding exception level */ val &= drvdata->ns_ex_level; - config->vinst_ctrl |= (val << 20); + config->vinst_ctrl |= val << __bf_shf(TRCVICTLR_EXLEVEL_NS_MASK); spin_unlock(&drvdata->spinlock); return size; } @@ -851,11 +863,11 @@ static ssize_t addr_instdatatype_show(struct device *dev, 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); return len; @@ -879,7 +891,7 @@ static ssize_t addr_instdatatype_store(struct device *dev, 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); return size; @@ -1137,7 +1149,7 @@ static ssize_t addr_ctxtype_show(struct device *dev, 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"))); @@ -1163,18 +1175,18 @@ static ssize_t addr_ctxtype_store(struct device *dev, 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")) { /* @@ -1182,9 +1194,9 @@ 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); return size; @@ -1203,7 +1215,7 @@ static ssize_t addr_context_show(struct device *dev, spin_lock(&drvdata->spinlock); idx = config->addr_idx; /* context ID comparator bits[6:4] */ - val = BMVAL(config->addr_acc[idx], 4, 6); + val = FIELD_GET(TRCACATRn_CONTEXT_MASK, config->addr_acc[idx]); spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1228,8 +1240,8 @@ static ssize_t addr_context_store(struct device *dev, 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); + config->addr_acc[idx] &= ~TRCACATRn_CONTEXT_MASK; + config->addr_acc[idx] |= val << __bf_shf(TRCACATRn_CONTEXT_MASK); spin_unlock(&drvdata->spinlock); return size; } @@ -1246,7 +1258,7 @@ static ssize_t addr_exlevel_s_ns_show(struct device *dev, spin_lock(&drvdata->spinlock); idx = config->addr_idx; - val = BMVAL(config->addr_acc[idx], 8, 14); + val = FIELD_GET(TRCACATRn_EXLEVEL_MASK, config->addr_acc[idx]); spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -1263,14 +1275,14 @@ static ssize_t addr_exlevel_s_ns_store(struct device *dev, if (kstrtoul(buf, 0, &val)) return -EINVAL; - if (val & ~((GENMASK(14, 8) >> 8))) + if (val & ~(TRCACATRn_EXLEVEL_MASK >> __bf_shf(TRCACATRn_EXLEVEL_MASK))) return -EINVAL; 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] &= ~(GENMASK(14, 8)); - config->addr_acc[idx] |= (val << 8); + config->addr_acc[idx] &= ~TRCACATRn_EXLEVEL_MASK; + config->addr_acc[idx] |= val << __bf_shf(TRCACATRn_EXLEVEL_MASK); spin_unlock(&drvdata->spinlock); return size; } @@ -1663,8 +1675,11 @@ 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; /* @@ -1711,8 +1726,11 @@ static ssize_t res_ctrl_store(struct device *dev, /* For odd idx pair inversal bit is RES0 */ if (idx % 2 != 0) /* PAIRINV, bit[21] */ - val &= ~BIT(21); - config->res_ctrl[idx] = val & GENMASK(21, 0); + val &= ~TRCRSCTLRn_PAIRINV; + config->res_ctrl[idx] = val & (TRCRSCTLRn_PAIRINV | + TRCRSCTLRn_INV | + TRCRSCTLRn_GROUP_MASK | + TRCRSCTLRn_SELECT_MASK); spin_unlock(&drvdata->spinlock); return size; } @@ -1777,9 +1795,9 @@ static ssize_t sshot_ctrl_store(struct device *dev, spin_lock(&drvdata->spinlock); idx = config->ss_idx; - config->ss_ctrl[idx] = val & GENMASK(24, 0); + 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] &= ~BIT(31); + config->ss_status[idx] &= ~TRCSSCSRn_STATUS; spin_unlock(&drvdata->spinlock); return size; } @@ -1827,9 +1845,9 @@ static ssize_t sshot_pe_ctrl_store(struct device *dev, spin_lock(&drvdata->spinlock); idx = config->ss_idx; - config->ss_pe_cmp[idx] = val & GENMASK(7, 0); + 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] &= ~BIT(31); + config->ss_status[idx] &= ~TRCSSCSRn_STATUS; spin_unlock(&drvdata->spinlock); return size; } @@ -2105,7 +2123,16 @@ 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; + + spin_lock(&drvdata->spinlock); val = (unsigned long)config->vmid_val[config->vmid_idx]; + spin_unlock(&drvdata->spinlock); return scnprintf(buf, PAGE_SIZE, "%#lx\n", val); } @@ -2118,6 +2145,13 @@ 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 */ @@ -2140,6 +2174,13 @@ static ssize_t vmid_masks_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; + spin_lock(&drvdata->spinlock); val1 = config->vmid_mask0; val2 = config->vmid_mask1; @@ -2158,6 +2199,13 @@ static ssize_t vmid_masks_store(struct device *dev, 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 * vmid comparator is implemented and at least 8 bit vmid size */ @@ -2258,6 +2306,34 @@ 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; + } + + switch (drvdata->trfcr & TRFCR_ELx_TS_MASK) { + case TRFCR_ELx_TS_VIRTUAL: + case TRFCR_ELx_TS_GUEST_PHYSICAL: + case TRFCR_ELx_TS_PHYSICAL: + val = FIELD_GET(TRFCR_ELx_TS_MASK, drvdata->trfcr); + 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, @@ -2312,11 +2388,13 @@ 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, }; struct etmv4_reg { - void __iomem *addr; + struct coresight_device *csdev; + u32 offset; u32 data; }; @@ -2324,15 +2402,16 @@ 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 @@ -2341,72 +2420,133 @@ 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 inline u32 coresight_etm4x_attr_to_offset(struct device_attribute *attr) +{ + struct dev_ext_attribute *eattr; + + eattr = container_of(attr, struct dev_ext_attribute, attr); + return (u32)(unsigned long)eattr->var; +} + +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 inline 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; -#define coresight_etm4x_cross_read(name, offset) \ - coresight_simple_func(struct etmv4_drvdata, etmv4_cross_read, \ - name, offset) + d_attr = container_of(attr, struct device_attribute, attr); + offset = coresight_etm4x_attr_to_offset(d_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_cross_read(trcoslsr, TRCOSLSR); -coresight_etm4x_cross_read(trcconfig, TRCCONFIGR); -coresight_etm4x_cross_read(trctraceid, TRCTRACEIDR); + if (etm4x_register_implemented(drvdata, offset)) + return attr->mode; + return 0; +} + +#define coresight_etm4x_reg(name, offset) \ + &((struct dev_ext_attribute[]) { \ + { \ + __ATTR(name, 0444, coresight_etm4x_reg_show, NULL), \ + (void *)(unsigned long)offset \ + } \ + })[0].attr.attr 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(trctraceid, TRCTRACEIDR), + 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, }; @@ -2415,6 +2555,7 @@ 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 a90d757f7043..000000000000 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ /dev/null @@ -1,1571 +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/cpu_pm.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 <linux/property.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(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"); - -/* 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 0 to TRCOSLAR unlocks the trace registers */ - writel_relaxed(0x0, drvdata->base + TRCOSLAR); - drvdata->os_unlock = true; - isb(); -} - -static void etm4_os_lock(struct etmv4_drvdata *drvdata) -{ - /* Writing 0x1 to TRCOSLAR locks the trace registers */ - writel_relaxed(0x1, drvdata->base + TRCOSLAR); - drvdata->os_unlock = false; - isb(); -} - -static bool etm4_arch_supported(u8 arch) -{ - /* Mask out the minor version number */ - switch (arch & 0xf0) { - 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; - struct device *etm_dev = &drvdata->csdev->dev; - - 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(etm_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. As - * such start at 2. - */ - for (i = 2; 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++) { - /* always clear status bit on restart if using single-shot */ - if (config->ss_ctrl[i] || config->ss_pe_cmp[i]) - config->ss_status[i] &= ~BIT(31); - 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(etm_dev, - "timeout while waiting for Idle Trace Status\n"); - - /* - * As recommended by section 4.3.7 ("Synchronization when using the - * memory-mapped interface") of ARM IHI 0064D - */ - dsb(sy); - isb(); - -done: - CS_LOCK(drvdata->base); - - dev_dbg(etm_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); -} - -/* - * 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 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)) { - /* - * 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 |= BIT(11); - } - - if (attr->config & BIT(ETM_OPT_CTXTID)) - /* bit[6], Context ID tracing bit */ - config->cfg |= BIT(ETM4_CFG_BIT_CTXTID); - - /* 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(&csdev->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; - struct etmv4_config *config = &drvdata->config; - struct device *etm_dev = &drvdata->csdev->dev; - int i; - - 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, as recommended - * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register, - * SSTATUS") of ARM IHI 0064D - */ - dsb(sy); - isb(); - writel_relaxed(control, drvdata->base + TRCPRGCTLR); - - /* wait for TRCSTATR.PMSTABLE to go to '1' */ - if (coresight_timeout(drvdata->base, TRCSTATR, - TRCSTATR_PMSTABLE_BIT, 1)) - dev_err(etm_dev, - "timeout while waiting for PM stable Trace Status\n"); - - /* read the status of the single shot comparators */ - for (i = 0; i < drvdata->nr_ss_cmp; i++) { - config->ss_status[i] = - readl_relaxed(drvdata->base + TRCSSCSRn(i)); - } - - coresight_disclaim_device_unlocked(drvdata->base); - - CS_LOCK(drvdata->base); - - dev_dbg(&drvdata->csdev->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(&csdev->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; - int i; - - /* 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); - drvdata->config.arch = drvdata->arch; - - /* 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. Read any status regs as these - * also contain RO capability data. - */ - drvdata->nr_ss_cmp = BMVAL(etmidr4, 20, 23); - for (i = 0; i < drvdata->nr_ss_cmp; i++) { - drvdata->config.ss_status[i] = - readl_relaxed(drvdata->base + TRCSSCSRn(i)); - } - /* 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); - u64 s_hyp = (config->arch & 0x0f) >= 0x4 ? ETM_EXLEVEL_S_HYP : 0; - - /* - * EXLEVEL_S, bits[11:8], don't trace anything happening - * in secure state. - */ - access_type |= (ETM_EXLEVEL_S_APP | - ETM_EXLEVEL_S_OS | - s_hyp | - ETM_EXLEVEL_S_MON); - - 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); - 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 - * - * 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]); - - 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_cpu_save(struct etmv4_drvdata *drvdata) -{ - int i, ret = 0; - struct etmv4_save_state *state; - struct device *etm_dev = &drvdata->csdev->dev; - - /* - * As recommended by 3.4.1 ("The procedure when powering down the PE") - * of ARM IHI 0064D - */ - dsb(sy); - isb(); - - CS_UNLOCK(drvdata->base); - - /* Lock the OS lock to disable trace and external debugger access */ - etm4_os_lock(drvdata); - - /* wait for TRCSTATR.PMSTABLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, - TRCSTATR_PMSTABLE_BIT, 1)) { - dev_err(etm_dev, - "timeout while waiting for PM Stable Status\n"); - etm4_os_unlock(drvdata); - ret = -EBUSY; - goto out; - } - - state = drvdata->save_state; - - state->trcprgctlr = readl(drvdata->base + TRCPRGCTLR); - state->trcprocselr = readl(drvdata->base + TRCPROCSELR); - state->trcconfigr = readl(drvdata->base + TRCCONFIGR); - state->trcauxctlr = readl(drvdata->base + TRCAUXCTLR); - state->trceventctl0r = readl(drvdata->base + TRCEVENTCTL0R); - state->trceventctl1r = readl(drvdata->base + TRCEVENTCTL1R); - state->trcstallctlr = readl(drvdata->base + TRCSTALLCTLR); - state->trctsctlr = readl(drvdata->base + TRCTSCTLR); - state->trcsyncpr = readl(drvdata->base + TRCSYNCPR); - state->trcccctlr = readl(drvdata->base + TRCCCCTLR); - state->trcbbctlr = readl(drvdata->base + TRCBBCTLR); - state->trctraceidr = readl(drvdata->base + TRCTRACEIDR); - state->trcqctlr = readl(drvdata->base + TRCQCTLR); - - state->trcvictlr = readl(drvdata->base + TRCVICTLR); - state->trcviiectlr = readl(drvdata->base + TRCVIIECTLR); - state->trcvissctlr = readl(drvdata->base + TRCVISSCTLR); - state->trcvipcssctlr = readl(drvdata->base + TRCVIPCSSCTLR); - state->trcvdctlr = readl(drvdata->base + TRCVDCTLR); - state->trcvdsacctlr = readl(drvdata->base + TRCVDSACCTLR); - state->trcvdarcctlr = readl(drvdata->base + TRCVDARCCTLR); - - for (i = 0; i < drvdata->nrseqstate; i++) - state->trcseqevr[i] = readl(drvdata->base + TRCSEQEVRn(i)); - - state->trcseqrstevr = readl(drvdata->base + TRCSEQRSTEVR); - state->trcseqstr = readl(drvdata->base + TRCSEQSTR); - state->trcextinselr = readl(drvdata->base + TRCEXTINSELR); - - for (i = 0; i < drvdata->nr_cntr; i++) { - state->trccntrldvr[i] = readl(drvdata->base + TRCCNTRLDVRn(i)); - state->trccntctlr[i] = readl(drvdata->base + TRCCNTCTLRn(i)); - state->trccntvr[i] = readl(drvdata->base + TRCCNTVRn(i)); - } - - for (i = 0; i < drvdata->nr_resource * 2; i++) - state->trcrsctlr[i] = readl(drvdata->base + TRCRSCTLRn(i)); - - for (i = 0; i < drvdata->nr_ss_cmp; i++) { - state->trcssccr[i] = readl(drvdata->base + TRCSSCCRn(i)); - state->trcsscsr[i] = readl(drvdata->base + TRCSSCSRn(i)); - state->trcsspcicr[i] = readl(drvdata->base + TRCSSPCICRn(i)); - } - - for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { - state->trcacvr[i] = readl(drvdata->base + TRCACVRn(i)); - state->trcacatr[i] = readl(drvdata->base + 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] = readl(drvdata->base + TRCCIDCVRn(i)); - - for (i = 0; i < drvdata->numvmidc; i++) - state->trcvmidcvr[i] = readl(drvdata->base + TRCVMIDCVRn(i)); - - state->trccidcctlr0 = readl(drvdata->base + TRCCIDCCTLR0); - state->trccidcctlr1 = readl(drvdata->base + TRCCIDCCTLR1); - - state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR0); - state->trcvmidcctlr0 = readl(drvdata->base + TRCVMIDCCTLR1); - - state->trcclaimset = readl(drvdata->base + TRCCLAIMCLR); - - state->trcpdcr = readl(drvdata->base + TRCPDCR); - - /* wait for TRCSTATR.IDLE to go up */ - if (coresight_timeout(drvdata->base, TRCSTATR, TRCSTATR_IDLE_BIT, 1)) { - dev_err(etm_dev, - "timeout while waiting for Idle Trace Status\n"); - etm4_os_unlock(drvdata); - ret = -EBUSY; - goto out; - } - - drvdata->state_needs_restore = true; - - /* - * 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. - */ - writel_relaxed((state->trcpdcr & ~TRCPDCR_PU), - drvdata->base + TRCPDCR); - -out: - CS_LOCK(drvdata->base); - return ret; -} - -static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) -{ - int i; - struct etmv4_save_state *state = drvdata->save_state; - - CS_UNLOCK(drvdata->base); - - writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET); - - writel_relaxed(state->trcprgctlr, drvdata->base + TRCPRGCTLR); - writel_relaxed(state->trcprocselr, drvdata->base + TRCPROCSELR); - writel_relaxed(state->trcconfigr, drvdata->base + TRCCONFIGR); - writel_relaxed(state->trcauxctlr, drvdata->base + TRCAUXCTLR); - writel_relaxed(state->trceventctl0r, drvdata->base + TRCEVENTCTL0R); - writel_relaxed(state->trceventctl1r, drvdata->base + TRCEVENTCTL1R); - writel_relaxed(state->trcstallctlr, drvdata->base + TRCSTALLCTLR); - writel_relaxed(state->trctsctlr, drvdata->base + TRCTSCTLR); - writel_relaxed(state->trcsyncpr, drvdata->base + TRCSYNCPR); - writel_relaxed(state->trcccctlr, drvdata->base + TRCCCCTLR); - writel_relaxed(state->trcbbctlr, drvdata->base + TRCBBCTLR); - writel_relaxed(state->trctraceidr, drvdata->base + TRCTRACEIDR); - writel_relaxed(state->trcqctlr, drvdata->base + TRCQCTLR); - - writel_relaxed(state->trcvictlr, drvdata->base + TRCVICTLR); - writel_relaxed(state->trcviiectlr, drvdata->base + TRCVIIECTLR); - writel_relaxed(state->trcvissctlr, drvdata->base + TRCVISSCTLR); - writel_relaxed(state->trcvipcssctlr, drvdata->base + TRCVIPCSSCTLR); - writel_relaxed(state->trcvdctlr, drvdata->base + TRCVDCTLR); - writel_relaxed(state->trcvdsacctlr, drvdata->base + TRCVDSACCTLR); - writel_relaxed(state->trcvdarcctlr, drvdata->base + TRCVDARCCTLR); - - for (i = 0; i < drvdata->nrseqstate; i++) - writel_relaxed(state->trcseqevr[i], - drvdata->base + TRCSEQEVRn(i)); - - writel_relaxed(state->trcseqrstevr, drvdata->base + TRCSEQRSTEVR); - writel_relaxed(state->trcseqstr, drvdata->base + TRCSEQSTR); - writel_relaxed(state->trcextinselr, drvdata->base + TRCEXTINSELR); - - for (i = 0; i < drvdata->nr_cntr; i++) { - writel_relaxed(state->trccntrldvr[i], - drvdata->base + TRCCNTRLDVRn(i)); - writel_relaxed(state->trccntctlr[i], - drvdata->base + TRCCNTCTLRn(i)); - writel_relaxed(state->trccntvr[i], - drvdata->base + TRCCNTVRn(i)); - } - - for (i = 0; i < drvdata->nr_resource * 2; i++) - writel_relaxed(state->trcrsctlr[i], - drvdata->base + TRCRSCTLRn(i)); - - for (i = 0; i < drvdata->nr_ss_cmp; i++) { - writel_relaxed(state->trcssccr[i], - drvdata->base + TRCSSCCRn(i)); - writel_relaxed(state->trcsscsr[i], - drvdata->base + TRCSSCSRn(i)); - writel_relaxed(state->trcsspcicr[i], - drvdata->base + TRCSSPCICRn(i)); - } - - for (i = 0; i < drvdata->nr_addr_cmp * 2; i++) { - writel_relaxed(state->trcacvr[i], - drvdata->base + TRCACVRn(i)); - writel_relaxed(state->trcacatr[i], - drvdata->base + TRCACATRn(i)); - } - - for (i = 0; i < drvdata->numcidc; i++) - writel_relaxed(state->trccidcvr[i], - drvdata->base + TRCCIDCVRn(i)); - - for (i = 0; i < drvdata->numvmidc; i++) - writel_relaxed(state->trcvmidcvr[i], - drvdata->base + TRCVMIDCVRn(i)); - - writel_relaxed(state->trccidcctlr0, drvdata->base + TRCCIDCCTLR0); - writel_relaxed(state->trccidcctlr1, drvdata->base + TRCCIDCCTLR1); - - writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR0); - writel_relaxed(state->trcvmidcctlr0, drvdata->base + TRCVMIDCCTLR1); - - writel_relaxed(state->trcclaimset, drvdata->base + TRCCLAIMSET); - - writel_relaxed(state->trcpdcr, drvdata->base + TRCPDCR); - - drvdata->state_needs_restore = false; - - /* - * 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); - CS_LOCK(drvdata->base); -} - -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 (!drvdata->save_state) - return NOTIFY_OK; - - if (WARN_ON_ONCE(drvdata->cpu != cpu)) - return NOTIFY_BAD; - - switch (cmd) { - case CPU_PM_ENTER: - /* save the state if self-hosted coresight is in use */ - if (local_read(&drvdata->mode)) - if (etm4_cpu_save(drvdata)) - return NOTIFY_BAD; - break; - case CPU_PM_EXIT: - /* fallthrough */ - case CPU_PM_ENTER_FAILED: - if (drvdata->state_needs_restore) - 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, -}; - -static int etm4_cpu_pm_register(void) -{ - if (IS_ENABLED(CONFIG_CPU_PM)) - return cpu_pm_register_notifier(&etm4_cpu_pm_nb); - - return 0; -} - -static void etm4_cpu_pm_unregister(void) -{ - if (IS_ENABLED(CONFIG_CPU_PM)) - cpu_pm_unregister_notifier(&etm4_cpu_pm_nb); -} - -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 }; - - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - - dev_set_drvdata(dev, drvdata); - - 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; - } - - /* 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 = coresight_get_cpu(dev); - if (drvdata->cpu < 0) - return drvdata->cpu; - - desc.name = devm_kasprintf(dev, GFP_KERNEL, "etm%d", drvdata->cpu); - if (!desc.name) - return -ENOMEM; - - 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; - - ret = etm4_cpu_pm_register(); - if (ret) - goto err_arch_supported; - } - - 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); - - pdata = coresight_get_platform_data(dev); - if (IS_ERR(pdata)) { - ret = PTR_ERR(pdata); - goto err_arch_supported; - } - adev->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)) { - 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(&drvdata->csdev->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) { - etm4_cpu_pm_unregister(); - - cpuhp_remove_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING); - if (hp_online) - cpuhp_remove_state_nocalls(hp_online); - } - return ret; -} - -static struct amba_cs_uci_id uci_id_etm4[] = { - { - /* ETMv4 UCI data */ - .devarch = 0x47704a13, - .devarch_mask = 0xfff0ffff, - .devtype = 0x00000013, - } -}; - -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(0x000f0205, uci_id_etm4),/* Qualcomm Kryo */ - CS_AMBA_UCI_ID(0x000f0211, uci_id_etm4),/* Qualcomm Kryo */ - CS_AMBA_ID(0x000bb802), /* Qualcomm Kryo 385 Cortex-A55 */ - CS_AMBA_ID(0x000bb803), /* Qualcomm Kryo 385 Cortex-A75 */ - CS_AMBA_UCI_ID(0x000cc0af, uci_id_etm4),/* Marvell ThunderX2 */ - {}, -}; - -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 4a695bf90582..4b21bb79f168 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 @@ -44,13 +47,14 @@ #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 +63,7 @@ #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 +72,12 @@ #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 +87,13 @@ #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)) +/* Data Value Comparator Value registers, n = 0-7 */ #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 +129,466 @@ #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_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_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), TRCVDCTLR) \ + CASE_##op((val), TRCVDSACCTLR) \ + CASE_##op((val), TRCVDARCCTLR) \ + 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), TRCDVCVRn(0)) \ + CASE_##op((val), TRCDVCVRn(1)) \ + CASE_##op((val), TRCDVCVRn(2)) \ + CASE_##op((val), TRCDVCVRn(3)) \ + CASE_##op((val), TRCDVCVRn(4)) \ + CASE_##op((val), TRCDVCVRn(5)) \ + CASE_##op((val), TRCDVCVRn(6)) \ + CASE_##op((val), TRCDVCVRn(7)) \ + CASE_##op((val), TRCDVCMRn(0)) \ + CASE_##op((val), TRCDVCMRn(1)) \ + CASE_##op((val), TRCDVCMRn(2)) \ + CASE_##op((val), TRCDVCMRn(3)) \ + CASE_##op((val), TRCDVCMRn(4)) \ + CASE_##op((val), TRCDVCMRn(5)) \ + CASE_##op((val), TRCDVCMRn(6)) \ + CASE_##op((val), TRCDVCMRn(7)) \ + 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 +602,9 @@ #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 @@ -174,28 +642,160 @@ 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 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 - TRCACATRn */ -#define ETM_EXLEVEL_S_APP BIT(8) -#define ETM_EXLEVEL_S_OS BIT(9) -#define ETM_EXLEVEL_S_HYP BIT(10) -#define ETM_EXLEVEL_S_MON BIT(11) -/* non-secure state access levels - TRCACATRn */ -#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) - -/* secure / non secure masks - TRCVICTLR, IDR3 */ -#define ETM_EXLEVEL_S_VICTLR_MASK GENMASK(19, 16) -/* NS MON (EL3) mode never implemented */ -#define ETM_EXLEVEL_NS_VICTLR_MASK GENMASK(22, 20) +#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 + * TRCIDR1 - ETM architected register + * - Bits[11:8] - Major version + * - Bits[7:4] - Minor version + * We must rely on TRCDEVARCH for the version information, + * however we don't want to break the support for potential + * old implementations which might not implement it. Thus + * we fall back to TRCIDR1 if TRCDEVARCH is not implemented + * for memory mapped components. + * 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)); +} + +static inline u8 etm_trcidr_to_arch(u32 trcidr1) +{ + return ETM_ARCH_VERSION(ETM_TRCIDR1_ARCH_MAJOR(trcidr1), + ETM_TRCIDR1_ARCH_MINOR(trcidr1)); +} + +enum etm_impdef_type { + ETM4_IMPDEF_HISI_CORE_COMMIT, + ETM4_IMPDEF_FEATURE_MAX, +}; /** * struct etmv4_config - configuration information related to an ETMv4 @@ -244,7 +844,7 @@ * @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. - * @arch: ETM architecture version (for arch dependent config). + * @s_ex_level: Secure ELs where tracing is supported. */ struct etmv4_config { u32 mode; @@ -288,7 +888,7 @@ struct etmv4_config { u32 vmid_mask0; u32 vmid_mask1; u32 ext_inp; - u8 arch; + u8 s_ex_level; }; /** @@ -325,7 +925,7 @@ struct etmv4_save_state { u32 trccntctlr[ETMv4_MAX_CNTR]; u32 trccntvr[ETMv4_MAX_CNTR]; - u32 trcrsctlr[ETM_MAX_RES_SEL * 2]; + u32 trcrsctlr[ETM_MAX_RES_SEL]; u32 trcssccr[ETM_MAX_SS_CMP]; u32 trcsscsr[ETM_MAX_SS_CMP]; @@ -334,7 +934,7 @@ struct etmv4_save_state { u64 trcacvr[ETM_MAX_SINGLE_ADDR_CMP]; u64 trcacatr[ETM_MAX_SINGLE_ADDR_CMP]; u64 trccidcvr[ETMv4_MAX_CTXID_CMP]; - u32 trcvmidcvr[ETM_MAX_VMID_CMP]; + u64 trcvmidcvr[ETM_MAX_VMID_CMP]; u32 trccidcctlr0; u32 trccidcctlr1; u32 trcvmidcctlr0; @@ -357,7 +957,7 @@ struct etmv4_save_state { * @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. @@ -404,9 +1004,17 @@ struct etmv4_save_state { * @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_trfcr: Saved TRFCR_EL1 register during a CPU PM event. * @save_state: State to be preserved across power loss * @state_needs_restore: True when there is context to restore after PM exit + * @skip_power_up: Indicates if an implementation can skip powering up + * the trace unit. + * @arch_features: Bitmap of arch features of etmv4 devices. */ struct etmv4_drvdata { void __iomem *base; @@ -436,6 +1044,7 @@ struct etmv4_drvdata { u8 s_ex_level; u8 ns_ex_level; u8 q_support; + u8 os_lock_model; bool sticky_enable; bool boot_enable; bool os_unlock; @@ -451,17 +1060,21 @@ struct etmv4_drvdata { bool nooverflow; bool atbtrig; bool lpoverride; + u64 trfcr; struct etmv4_config config; + u64 save_trfcr; struct etmv4_save_state *save_state; bool state_needs_restore; + bool skip_power_up; + 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 */ @@ -474,4 +1087,12 @@ 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; +} #endif diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 900690a9f7f0..b363dd6bc510 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -52,13 +52,14 @@ 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; } @@ -101,6 +102,7 @@ static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) { u32 functl; + struct coresight_device *csdev = drvdata->csdev; CS_UNLOCK(drvdata->base); @@ -110,7 +112,7 @@ static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, /* 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); } @@ -242,6 +244,7 @@ static int funnel_probe(struct device *dev, struct resource *res) } drvdata->base = base; desc.groups = coresight_funnel_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); } dev_set_drvdata(dev, drvdata); @@ -274,6 +277,15 @@ out_disable_clk: return ret; } +static int funnel_remove(struct device *dev) +{ + struct funnel_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); + + return 0; +} + #ifdef CONFIG_PM static int funnel_runtime_suspend(struct device *dev) { @@ -319,29 +331,41 @@ static int static_funnel_probe(struct platform_device *pdev) return ret; } +static int static_funnel_remove(struct platform_device *pdev) +{ + funnel_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; +} + static const struct of_device_id static_funnel_match[] = { {.compatible = "arm,coresight-static-funnel"}, {} }; +MODULE_DEVICE_TABLE(of, static_funnel_match); + #ifdef CONFIG_ACPI static const struct acpi_device_id static_funnel_ids[] = { {"ARMHC9FE", 0}, {}, }; + +MODULE_DEVICE_TABLE(acpi, static_funnel_ids); #endif static struct platform_driver static_funnel_driver = { .probe = static_funnel_probe, + .remove = static_funnel_remove, .driver = { .name = "coresight-static-funnel", + /* THIS_MODULE is taken care of by platform_driver_register() */ .of_match_table = static_funnel_match, .acpi_match_table = ACPI_PTR(static_funnel_ids), .pm = &funnel_dev_pm_ops, .suppress_bind_attrs = true, }, }; -builtin_platform_driver(static_funnel_driver); static int dynamic_funnel_probe(struct amba_device *adev, const struct amba_id *id) @@ -349,6 +373,11 @@ static int dynamic_funnel_probe(struct amba_device *adev, return funnel_probe(&adev->dev, &adev->res); } +static void dynamic_funnel_remove(struct amba_device *adev) +{ + funnel_remove(&adev->dev); +} + static const struct amba_id dynamic_funnel_ids[] = { { .id = 0x000bb908, @@ -362,6 +391,8 @@ static const struct amba_id dynamic_funnel_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, dynamic_funnel_ids); + static struct amba_driver dynamic_funnel_driver = { .drv = { .name = "coresight-dynamic-funnel", @@ -370,6 +401,39 @@ static struct amba_driver dynamic_funnel_driver = { .suppress_bind_attrs = true, }, .probe = dynamic_funnel_probe, + .remove = dynamic_funnel_remove, .id_table = dynamic_funnel_ids, }; -builtin_amba_driver(dynamic_funnel_driver); + +static int __init funnel_init(void) +{ + int ret; + + ret = platform_driver_register(&static_funnel_driver); + if (ret) { + pr_info("Error registering platform driver\n"); + return ret; + } + + ret = amba_driver_register(&dynamic_funnel_driver); + if (ret) { + pr_info("Error registering amba driver\n"); + platform_driver_unregister(&static_funnel_driver); + } + + return ret; +} + +static void __exit funnel_exit(void) +{ + platform_driver_unregister(&static_funnel_driver); + amba_driver_unregister(&dynamic_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-platform.c b/drivers/hwtracing/coresight/coresight-platform.c index 3c5bee429105..475899714104 100644 --- a/drivers/hwtracing/coresight/coresight-platform.c +++ b/drivers/hwtracing/coresight/coresight-platform.c @@ -27,9 +27,8 @@ static int coresight_alloc_conns(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); + pdata->conns = devm_kcalloc(dev, pdata->nr_outport, + sizeof(*pdata->conns), GFP_KERNEL); if (!pdata->conns) return -ENOMEM; } @@ -57,6 +56,27 @@ coresight_find_device_by_fwnode(struct fwnode_handle *fwnode) 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 inline bool of_coresight_legacy_ep_is_input(struct device_node *ep) { @@ -67,17 +87,30 @@ static void of_coresight_get_ports_legacy(const struct device_node *node, int *nr_inport, int *nr_outport) { struct device_node *ep = NULL; + struct of_endpoint endpoint; int in = 0, out = 0; + /* + * Avoid warnings in of_graph_get_next_endpoint() + * if the device doesn't have any graph connections + */ + if (!of_graph_is_present(node)) + return; do { ep = of_graph_get_next_endpoint(node, ep); if (!ep) break; - if (of_coresight_legacy_ep_is_input(ep)) - in++; - else - out++; + if (of_graph_parse_endpoint(ep, &endpoint)) + continue; + + if (of_coresight_legacy_ep_is_input(ep)) { + in = (endpoint.port + 1 > in) ? + endpoint.port + 1 : in; + } else { + out = (endpoint.port + 1) > out ? + endpoint.port + 1 : out; + } } while (ep); @@ -117,9 +150,16 @@ of_coresight_count_ports(struct device_node *port_parent) { int i = 0; struct device_node *ep = NULL; + struct of_endpoint endpoint; + + while ((ep = of_graph_get_next_endpoint(port_parent, ep))) { + /* Defer error handling to parsing */ + if (of_graph_parse_endpoint(ep, &endpoint)) + continue; + if (endpoint.port + 1 > i) + i = endpoint.port + 1; + } - while ((ep = of_graph_get_next_endpoint(port_parent, ep))) - i++; return i; } @@ -171,14 +211,12 @@ static int of_coresight_get_cpu(struct device *dev) * 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) + struct coresight_platform_data *pdata) { int ret = 0; struct of_endpoint endpoint, rendpoint; @@ -186,6 +224,7 @@ static int of_coresight_parse_endpoint(struct device *dev, struct device_node *rep = NULL; struct device *rdev = NULL; struct fwnode_handle *rdev_fwnode; + struct coresight_connection *conn; do { /* Parse the local port details */ @@ -212,6 +251,13 @@ static int of_coresight_parse_endpoint(struct device *dev, break; } + conn = &pdata->conns[endpoint.port]; + if (conn->child_fwnode) { + dev_warn(dev, "Duplicate output port %d\n", + endpoint.port); + ret = -EINVAL; + break; + } conn->outport = endpoint.port; /* * Hold the refcount to the target device. This could be @@ -224,7 +270,6 @@ static int of_coresight_parse_endpoint(struct device *dev, conn->child_fwnode = fwnode_handle_get(rdev_fwnode); conn->child_port = rendpoint.port; /* Connection record updated */ - ret = 1; } while (0); of_node_put(rparent); @@ -238,7 +283,6 @@ static int of_get_coresight_platform_data(struct device *dev, struct coresight_platform_data *pdata) { int ret = 0; - struct coresight_connection *conn; struct device_node *ep = NULL; const struct device_node *parent = NULL; bool legacy_binding = false; @@ -267,8 +311,6 @@ static int of_get_coresight_platform_data(struct device *dev, 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))) { /* @@ -280,15 +322,9 @@ static int of_get_coresight_platform_data(struct device *dev, 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: + ret = of_coresight_parse_endpoint(dev, ep, pdata); + if (ret) return ret; - } } return 0; @@ -481,7 +517,7 @@ static inline bool acpi_validate_dsd_graph(const union acpi_object *graph) } /* acpi_get_dsd_graph - Find the _DSD Graph property for the given device. */ -const union acpi_object * +static const union acpi_object * acpi_get_dsd_graph(struct acpi_device *adev) { int i; @@ -544,7 +580,7 @@ acpi_validate_coresight_graph(const union acpi_object *cs_graph) * Returns the pointer to the CoreSight Graph Package when found. Otherwise * returns NULL. */ -const union acpi_object * +static const union acpi_object * acpi_get_coresight_graph(struct acpi_device *adev) { const union acpi_object *graph_list, *graph; @@ -590,7 +626,7 @@ static int acpi_coresight_parse_link(struct acpi_device *adev, const union acpi_object *link, struct coresight_connection *conn) { - int rc, dir; + int dir; const union acpi_object *fields; struct acpi_device *r_adev; struct device *rdev; @@ -607,9 +643,9 @@ static int acpi_coresight_parse_link(struct acpi_device *adev, fields[3].type != ACPI_TYPE_INTEGER) return -EINVAL; - rc = acpi_bus_get_device(fields[2].reference.handle, &r_adev); - if (rc) - return rc; + 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) { @@ -627,6 +663,16 @@ static int acpi_coresight_parse_link(struct acpi_device *adev, * coresight_remove_match(). */ conn->child_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->child_port = fields[0].integer.value; + } else { + /* Invalid direction */ + return -EINVAL; } return dir; @@ -672,10 +718,20 @@ static int acpi_coresight_parse_graph(struct acpi_device *adev, return dir; if (dir == ACPI_CORESIGHT_LINK_MASTER) { - pdata->nr_outport++; + if (ptr->outport >= pdata->nr_outport) + pdata->nr_outport = ptr->outport + 1; ptr++; } else { - pdata->nr_inport++; + WARN_ON(pdata->nr_inport == ptr->child_port + 1); + /* + * We do not track input port connections for a device. + * However we need the highest port number described, + * which can be recorded now and reuse this connection + * record for an output connection. Hence, do not move + * the ptr for input connections + */ + if (ptr->child_port >= pdata->nr_inport) + pdata->nr_inport = ptr->child_port + 1; } } @@ -684,8 +740,13 @@ static int acpi_coresight_parse_graph(struct acpi_device *adev, return rc; /* Copy the connection information to the final location */ - for (i = 0; i < pdata->nr_outport; i++) - pdata->conns[i] = conns[i]; + for (i = 0; conns + i < ptr; i++) { + int port = conns[i].outport; + + /* Duplicate output port */ + WARN_ON(pdata->conns[port].child_fwnode); + pdata->conns[port] = conns[i]; + } devm_kfree(&adev->dev, conns); return 0; @@ -802,7 +863,7 @@ coresight_get_platform_data(struct device *dev) error: if (!IS_ERR_OR_NULL(pdata)) /* Cleanup the connection information */ - coresight_release_platform_data(pdata); + coresight_release_platform_data(NULL, 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 82e563cdc879..595ce5862056 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -22,6 +22,7 @@ #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 @@ -38,35 +39,40 @@ #define ETM_MODE_EXCL_KERN BIT(30) #define ETM_MODE_EXCL_USER BIT(31) +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)) +extern ssize_t coresight_simple_show32(struct device *_dev, + struct device_attribute *attr, char *buf); +extern 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, @@ -86,6 +92,7 @@ enum cs_mode { * 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 @@ -94,6 +101,7 @@ 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; @@ -103,10 +111,9 @@ 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 { @@ -125,35 +132,28 @@ 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) -{ - u64 val; - - val = readl_relaxed(addr + lo_offset); - val |= (hi_offset < 0) ? 0 : - (u64)readl_relaxed(addr + hi_offset) << 32; - return val; -} - -static inline void coresight_write_reg_pair(void __iomem *addr, u64 val, - s32 lo_offset, s32 hi_offset) -{ - writel_relaxed((u32)val, addr + lo_offset); - if (hi_offset >= 0) - writel_relaxed((u32)(val >> 32), addr + hi_offset); -} - 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 coresight_device * +coresight_get_enabled_sink(struct coresight_device *source); struct coresight_device *coresight_get_sink_by_id(u32 id); +struct coresight_device * +coresight_find_default_sink(struct coresight_device *csdev); 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 +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); + +#if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X) extern int etm_readl_cp14(u32 off, unsigned int *val); extern int etm_writel_cp14(u32 off, u32 val); #else @@ -161,6 +161,14 @@ 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); +}; + +extern void coresight_set_cti_ops(const struct cti_assoc_op *cti_op); +extern 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. @@ -195,11 +203,22 @@ static inline int etm_writel_cp14(u32 off, u32 val) { return 0; } /* extract the data value from a UCI structure given amba_id pointer. */ static inline void *coresight_get_uci_data(const struct amba_id *id) { - if (id->data) - return ((struct amba_cs_uci_id *)(id->data))->data; - return 0; + struct amba_cs_uci_id *uci_id = id->data; + + if (!uci_id) + return NULL; + + return uci_id->data; } -void coresight_release_platform_data(struct coresight_platform_data *pdata); +void coresight_release_platform_data(struct coresight_device *csdev, + struct coresight_platform_data *pdata); +struct coresight_device * +coresight_find_csdev_by_fwnode(struct fwnode_handle *r_fwnode); +void coresight_set_assoc_ectdev_mutex(struct coresight_device *csdev, + struct coresight_device *ect_csdev); + +void coresight_set_percpu_sink(int cpu, struct coresight_device *csdev); +struct coresight_device *coresight_get_percpu_sink(int cpu); #endif diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index e7dc1c31d20d..4dd50546d7e4 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -14,6 +14,7 @@ #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> @@ -32,22 +33,26 @@ DEFINE_CORESIGHT_DEVLIST(replicator_devs, "replicator"); * @atclk: optional clock for the core parts of the replicator. * @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 { void __iomem *base; struct clk *atclk; struct coresight_device *csdev; spinlock_t spinlock; + bool check_idfilter_val; }; static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) { + struct coresight_device *csdev = drvdata->csdev; + CS_UNLOCK(drvdata->base); - if (!coresight_claim_device_unlocked(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(drvdata->base); + coresight_disclaim_device_unlocked(csdev); } CS_LOCK(drvdata->base); @@ -66,29 +71,44 @@ static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, int inport, int outport) { int rc = 0; - u32 reg; - - switch (outport) { - case 0: - reg = REPLICATOR_IDFILTER0; - break; - case 1: - reg = REPLICATOR_IDFILTER1; - break; - default: - WARN_ON(1); - return -EINVAL; - } + u32 id0val, id1val; + struct coresight_device *csdev = drvdata->csdev; 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); + 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(0x00, drvdata->base + reg); + if (!rc) { + writel_relaxed(id0val, drvdata->base + REPLICATOR_IDFILTER0); + writel_relaxed(id1val, drvdata->base + REPLICATOR_IDFILTER1); + } + CS_LOCK(drvdata->base); return rc; @@ -123,6 +143,7 @@ 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: @@ -143,7 +164,7 @@ static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - coresight_disclaim_device_unlocked(drvdata->base); + coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); } @@ -175,15 +196,9 @@ static const struct coresight_ops replicator_cs_ops = { .link_ops = &replicator_link_ops, }; -#define coresight_replicator_reg(name, offset) \ - coresight_simple_reg32(struct replicator_drvdata, 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, + coresight_simple_reg32(idfilter0, REPLICATOR_IDFILTER0), + coresight_simple_reg32(idfilter1, REPLICATOR_IDFILTER1), NULL, }; @@ -237,8 +252,13 @@ static int replicator_probe(struct device *dev, struct resource *res) } drvdata->base = base; desc.groups = replicator_groups; + desc.access = CSDEV_ACCESS_IOMEM(base); } + 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); @@ -270,6 +290,14 @@ out_disable_clk: return ret; } +static int replicator_remove(struct device *dev) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(dev); + + coresight_unregister(drvdata->csdev); + return 0; +} + static int static_replicator_probe(struct platform_device *pdev) { int ret; @@ -289,6 +317,13 @@ static int static_replicator_probe(struct platform_device *pdev) return ret; } +static int static_replicator_remove(struct platform_device *pdev) +{ + replicator_remove(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return 0; +} + #ifdef CONFIG_PM static int replicator_runtime_suspend(struct device *dev) { @@ -322,24 +357,29 @@ static const struct of_device_id static_replicator_match[] = { {} }; +MODULE_DEVICE_TABLE(of, static_replicator_match); + #ifdef CONFIG_ACPI static const struct acpi_device_id static_replicator_acpi_ids[] = { {"ARMHC985", 0}, /* ARM CoreSight Static Replicator */ {} }; + +MODULE_DEVICE_TABLE(acpi, static_replicator_acpi_ids); #endif static struct platform_driver static_replicator_driver = { .probe = static_replicator_probe, + .remove = static_replicator_remove, .driver = { .name = "coresight-static-replicator", + /* THIS_MODULE is taken care of by platform_driver_register() */ .of_match_table = of_match_ptr(static_replicator_match), .acpi_match_table = ACPI_PTR(static_replicator_acpi_ids), .pm = &replicator_dev_pm_ops, .suppress_bind_attrs = true, }, }; -builtin_platform_driver(static_replicator_driver); static int dynamic_replicator_probe(struct amba_device *adev, const struct amba_id *id) @@ -347,26 +387,60 @@ static int dynamic_replicator_probe(struct amba_device *adev, return replicator_probe(&adev->dev, &adev->res); } +static void dynamic_replicator_remove(struct amba_device *adev) +{ + replicator_remove(&adev->dev); +} + static const struct amba_id dynamic_replicator_ids[] = { - { - .id = 0x000bb909, - .mask = 0x000fffff, - }, - { - /* Coresight SoC-600 */ - .id = 0x000bb9ec, - .mask = 0x000fffff, - }, - { 0, 0 }, + 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, + .owner = THIS_MODULE, .suppress_bind_attrs = true, }, .probe = dynamic_replicator_probe, + .remove = dynamic_replicator_remove, .id_table = dynamic_replicator_ids, }; -builtin_amba_driver(dynamic_replicator_driver); + +static int __init replicator_init(void) +{ + int ret; + + ret = platform_driver_register(&static_replicator_driver); + if (ret) { + pr_info("Error registering platform driver\n"); + return ret; + } + + ret = amba_driver_register(&dynamic_replicator_driver); + if (ret) { + pr_info("Error registering amba driver\n"); + platform_driver_unregister(&static_replicator_driver); + } + + return ret; +} + +static void __exit replicator_exit(void) +{ + platform_driver_unregister(&static_replicator_driver); + amba_driver_unregister(&dynamic_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..53840a2c41f2 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h @@ -0,0 +1,33 @@ +/* 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(); +} + +static inline u64 cpu_prohibit_trace(void) +{ + u64 trfcr = read_trfcr(); + + /* Prohibit tracing at EL0 & the kernel EL */ + write_trfcr(trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE)); + /* Return the original value of the TRFCR */ + return trfcr; +} +#endif /* __CORESIGHT_SELF_HOSTED_TRACE_H */ diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index b908ca104645..463f449cfb79 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -96,7 +96,7 @@ 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. @@ -258,6 +258,7 @@ 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 @@ -270,7 +271,7 @@ static void stm_disable(struct coresight_device *csdev, 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(csdev->dev.parent); @@ -412,6 +413,7 @@ 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))) return -EACCES; @@ -421,8 +423,9 @@ 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) @@ -432,7 +435,7 @@ 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. @@ -444,7 +447,8 @@ 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; @@ -630,22 +634,6 @@ static ssize_t traceid_store(struct device *dev, } 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 struct attribute *coresight_stm_attrs[] = { &dev_attr_hwevent_enable.attr, &dev_attr_hwevent_select.attr, @@ -656,18 +644,18 @@ 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, }; @@ -727,8 +715,6 @@ static int acpi_stm_get_stimulus_area(struct device *dev, struct resource *res) struct acpi_device *adev = ACPI_COMPANION(dev); - if (!adev) - return -ENODEV; rc = acpi_dev_get_resources(adev, &res_list, NULL, NULL); if (rc < 0) return rc; @@ -854,13 +840,11 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) { int ret; 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 bitmap_size; struct coresight_desc desc = { 0 }; desc.name = coresight_alloc_device_name(&stm_devs, dev); @@ -883,6 +867,7 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) if (IS_ERR(base)) return PTR_ERR(base); drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); ret = stm_get_stimulus_area(dev, &ch_res); if (ret) @@ -901,12 +886,10 @@ static int stm_probe(struct amba_device *adev, const struct amba_id *id) else drvdata->numsp = stm_num_stimulus_port(drvdata); - 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); @@ -950,6 +933,15 @@ stm_unregister: return ret; } +static void stm_remove(struct amba_device *adev) +{ + struct stm_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_unregister(drvdata->csdev); + + stm_unregister_device(&drvdata->stm); +} + #ifdef CONFIG_PM static int stm_runtime_suspend(struct device *dev) { @@ -982,6 +974,8 @@ static const struct amba_id stm_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, stm_ids); + static struct amba_driver stm_driver = { .drv = { .name = "coresight-stm", @@ -990,7 +984,12 @@ static struct amba_driver stm_driver = { .suppress_bind_attrs = true, }, .probe = stm_probe, + .remove = stm_remove, .id_table = stm_ids, }; -builtin_amba_driver(stm_driver); +module_amba_driver(stm_driver); + +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..433ede94dd63 --- /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 inline 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 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 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 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 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 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 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..11138a9762b0 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-syscfg.c @@ -0,0 +1,1298 @@ +// 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) { + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&config_csdev->node, &csdev->config_csdev_list); + 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); + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + list_add(&feat_csdev->node, &csdev->feature_csdev_list); + 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; + + 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); + 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; + + 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: + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); +} +EXPORT_SYMBOL_GPL(cscfg_csdev_reset_feats); + +/* + * 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; + + /* must ensure that config cannot be unloaded in use */ + err = cscfg_owner_get(config_desc->load_owner); + if (err) + break; + /* + * increment the global active count - control changes to + * active configurations + */ + atomic_inc(&cscfg_mgr->sys_active_cnt); + + /* + * mark the descriptor as active so enable config on a + * device instance will use it + */ + atomic_inc(&config_desc->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(&config_desc->active_cnt); + atomic_dec(&cscfg_mgr->sys_active_cnt); + cscfg_owner_put(config_desc->load_owner); + 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; + const 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. + */ + 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 ((atomic_read(&config_desc->active_cnt)) && + ((unsigned long)config_desc->event_ea->var == cfg_hash)) { + config_csdev_active = config_csdev_item; + csdev->active_cscfg_ctxt = (void *)config_csdev_active; + break; + } + } + 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. + */ + spin_lock_irqsave(&csdev->cscfg_csdev_lock, flags); + if (csdev->active_cscfg_ctxt) + config_csdev_active->enabled = true; + else + err = -EBUSY; + spin_unlock_irqrestore(&csdev->cscfg_csdev_lock, flags); + } + } + 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. + */ + 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; + 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); +} +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..34d2a2d31d00 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-sysfs.c @@ -0,0 +1,206 @@ +// 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/kernel.h> + +#include "coresight-priv.h" + +/* + * 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; + + do { + outs = devm_kasprintf(&orig->dev, GFP_KERNEL, + "out:%d", conn->outport); + if (!outs) + break; + ins = devm_kasprintf(&target->dev, GFP_KERNEL, + "in:%d", conn->child_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; + + /* + * Install the device connection. This also indicates that + * the links are operational on both ends. + */ + conn->child_dev = target; + 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->child_dev->dev, conn->link->target_name); + devm_kfree(&orig->dev, conn->link->orig_name); + devm_kfree(&orig->dev, conn->link); + conn->link = NULL; + conn->child_dev = NULL; +} diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index 1cf82fa58289..07abf28ad725 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -33,16 +33,20 @@ DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr"); void 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(drvdata->base, - TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { - dev_err(&drvdata->csdev->dev, + if (coresight_timeout(csa, TMC_STS, TMC_STS_TMCREADY_BIT, 1)) { + dev_err(&csdev->dev, "timeout while waiting for TMC to be Ready\n"); } } 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); @@ -51,9 +55,8 @@ void tmc_flush_and_stop(struct tmc_drvdata *drvdata) 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->csdev->dev, + if (coresight_timeout(csa, TMC_FFCR, TMC_FFCR_FLUSHMAN_BIT, 0)) { + dev_err(&csdev->dev, "timeout while waiting for completion of Manual Flush\n"); } @@ -84,9 +87,7 @@ u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata) */ switch (drvdata->memwidth) { case TMC_MEM_INTF_WIDTH_32BITS: - /* fallthrough */ case TMC_MEM_INTF_WIDTH_64BITS: - /* fallthrough */ case TMC_MEM_INTF_WIDTH_128BITS: mask = GENMASK(31, 4); break; @@ -250,41 +251,21 @@ static enum tmc_mem_intf_width tmc_get_memwidth(u32 devid) 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(authstatus, TMC_AUTHSTATUS); -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, - &dev_attr_authstatus.attr, + 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, }; @@ -361,7 +342,7 @@ static const struct attribute_group coresight_tmc_mgmt_group = { .name = "mgmt", }; -const struct attribute_group *coresight_tmc_groups[] = { +static const struct attribute_group *coresight_tmc_groups[] = { &coresight_tmc_group, &coresight_tmc_mgmt_group, NULL, @@ -431,6 +412,21 @@ static u32 tmc_etr_get_default_buffer_size(struct device *dev) 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 int tmc_probe(struct amba_device *adev, const struct amba_id *id) { int ret = 0; @@ -458,6 +454,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) } drvdata->base = base; + desc.access = CSDEV_ACCESS_IOMEM(base); spin_lock_init(&drvdata->spinlock); @@ -467,10 +464,12 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) /* This device is not associated with a session */ drvdata->pid = -1; - if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { drvdata->size = tmc_etr_get_default_buffer_size(dev); - else + drvdata->max_burst_size = tmc_etr_get_max_burst_size(dev); + } else { drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; + } desc.dev = dev; desc.groups = coresight_tmc_groups; @@ -484,7 +483,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) break; case TMC_CONFIG_TYPE_ETR: desc.type = CORESIGHT_DEV_TYPE_SINK; - desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM; desc.ops = &tmc_etr_cs_ops; ret = tmc_etr_setup_caps(dev, devid, coresight_get_uci_data(id)); @@ -496,6 +495,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) break; case TMC_CONFIG_TYPE_ETF: 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; @@ -538,6 +538,41 @@ out: return ret; } +static void tmc_shutdown(struct amba_device *adev) +{ + unsigned long flags; + struct tmc_drvdata *drvdata = amba_get_drvdata(adev); + + spin_lock_irqsave(&drvdata->spinlock, flags); + + if (drvdata->mode == 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: + spin_unlock_irqrestore(&drvdata->spinlock, flags); +} + +static void tmc_remove(struct amba_device *adev) +{ + struct tmc_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); +} + static const struct amba_id tmc_ids[] = { CS_AMBA_ID(0x000bb961), /* Coresight SoC 600 TMC-ETR/ETS */ @@ -549,6 +584,8 @@ static const struct amba_id tmc_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, tmc_ids); + static struct amba_driver tmc_driver = { .drv = { .name = "coresight-tmc", @@ -556,6 +593,13 @@ static struct amba_driver tmc_driver = { .suppress_bind_attrs = true, }, .probe = tmc_probe, + .shutdown = tmc_shutdown, + .remove = tmc_remove, .id_table = tmc_ids, }; -builtin_amba_driver(tmc_driver); + +module_amba_driver(tmc_driver); + +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 d0cc3985b72a..4c4cbd1f7258 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -37,7 +37,7 @@ static void __tmc_etb_enable_hw(struct tmc_drvdata *drvdata) 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; @@ -88,7 +88,7 @@ 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) @@ -109,7 +109,7 @@ static void __tmc_etf_enable_hw(struct tmc_drvdata *drvdata) 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; @@ -120,11 +120,13 @@ static int tmc_etf_enable_hw(struct tmc_drvdata *drvdata) 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); } @@ -227,6 +229,7 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct perf_output_handle *handle = data; + struct cs_buffers *buf = etm_perf_sink_config(handle); spin_lock_irqsave(&drvdata->spinlock, flags); do { @@ -243,7 +246,7 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) } /* Get a handle on the pid of the process to monitor */ - pid = task_pid_nr(handle->event->owner); + pid = buf->pid; if (drvdata->pid != -1 && drvdata->pid != pid) { ret = -EBUSY; @@ -399,6 +402,7 @@ static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, if (!buf) return NULL; + buf->pid = task_pid_nr(event->owner); buf->snapshot = overwrite; buf->nr_pages = nr_pages; buf->data_pages = pages; @@ -519,14 +523,14 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, 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++; } @@ -542,13 +546,17 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, /* * In snapshot mode we simply increment the head by the number of byte - * that were written. User space function cs_etm_find_snapshot() will - * figure out how many bytes to get from the AUX buffer based on the - * position of the head. + * 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); out: spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -596,13 +604,6 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata) 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) { ret = -EINVAL; @@ -616,8 +617,15 @@ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata) } /* Disable the TMC if need be */ - if (drvdata->mode == CS_MODE_SYSFS) + if (drvdata->mode == 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: @@ -639,15 +647,14 @@ int tmc_read_unprepare_etb(struct tmc_drvdata *drvdata) 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; - } - /* Re-enable the TMC if need be */ if (drvdata->mode == 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) { + 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 diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 625882bc8b08..867ad8bb9b0c 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -32,7 +32,6 @@ struct etr_flat_buf { * @etr_buf - Actual buffer used by the ETR * @pid - The PID this 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. */ @@ -41,7 +40,6 @@ struct etr_perf_buffer { struct etr_buf *etr_buf; pid_t pid; bool snapshot; - unsigned long head; int nr_pages; void **pages; }; @@ -217,6 +215,8 @@ 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(real_dev, page, 0, PAGE_SIZE, dir); if (dma_mapping_error(real_dev, paddr)) @@ -255,6 +255,7 @@ void tmc_free_sg_table(struct tmc_sg_table *sg_table) tmc_free_table_pages(sg_table); tmc_free_data_pages(sg_table); } +EXPORT_SYMBOL_GPL(tmc_free_sg_table); /* * Alloc pages for the table. Since this will be used by the device, @@ -340,6 +341,7 @@ struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev, return sg_table; } +EXPORT_SYMBOL_GPL(tmc_alloc_sg_table); /* * tmc_sg_table_sync_data_range: Sync the data buffer written @@ -360,6 +362,7 @@ void tmc_sg_table_sync_data_range(struct tmc_sg_table *table, 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) @@ -372,6 +375,7 @@ void tmc_sg_table_sync_table(struct tmc_sg_table *sg_table) 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 @@ -401,6 +405,7 @@ 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 */ @@ -602,8 +607,9 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, if (!flat_buf) return -ENOMEM; - flat_buf->vaddr = dma_alloc_coherent(real_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); if (!flat_buf->vaddr) { kfree(flat_buf); return -ENOMEM; @@ -624,14 +630,18 @@ static void tmc_etr_free_flat_buf(struct etr_buf *etr_buf) if (flat_buf && flat_buf->daddr) { struct device *real_dev = flat_buf->dev->parent; - dma_free_coherent(real_dev, flat_buf->size, - flat_buf->vaddr, flat_buf->daddr); + 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. @@ -641,6 +651,19 @@ 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, @@ -766,6 +789,7 @@ tmc_etr_get_catu_device(struct tmc_drvdata *drvdata) return NULL; } +EXPORT_SYMBOL_GPL(tmc_etr_get_catu_device); static inline int tmc_etr_enable_catu(struct tmc_drvdata *drvdata, struct etr_buf *etr_buf) @@ -788,10 +812,21 @@ static inline void tmc_etr_disable_catu(struct tmc_drvdata *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] = IS_ENABLED(CONFIG_CORESIGHT_CATU) - ? &etr_catu_buf_ops : NULL, + [ETR_MODE_CATU] = NULL, }; +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); + +void tmc_etr_remove_catu_ops(void) +{ + etr_buf_ops[ETR_MODE_CATU] = NULL; +} +EXPORT_SYMBOL_GPL(tmc_etr_remove_catu_ops); + static inline int tmc_etr_mode_alloc_buf(int mode, struct tmc_drvdata *drvdata, struct etr_buf *etr_buf, int node, @@ -937,11 +972,11 @@ static void tmc_sync_etr_buf(struct tmc_drvdata *drvdata) dev_dbg(&drvdata->csdev->dev, "tmc memory error detected, truncating buffer\n"); etr_buf->len = 0; - etr_buf->full = 0; + etr_buf->full = false; return; } - etr_buf->full = status & TMC_STS_FULL; + etr_buf->full = !!(status & TMC_STS_FULL); WARN_ON(!etr_buf->ops || !etr_buf->ops->sync); @@ -963,7 +998,8 @@ static void __tmc_etr_enable_hw(struct tmc_drvdata *drvdata) 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)) { @@ -1021,7 +1057,7 @@ static int tmc_etr_enable_hw(struct tmc_drvdata *drvdata, 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); @@ -1110,12 +1146,12 @@ 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; } @@ -1418,16 +1454,16 @@ free_etr_perf_buffer: * buffer to the perf ring buffer. */ 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; long pg_idx, pg_offset; - unsigned long head = etr_perf->head; 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; @@ -1533,17 +1569,24 @@ tmc_update_etr_buffer(struct coresight_device *csdev, /* Insert barrier packets at the beginning, if there was an overflow */ if (lost) - tmc_etr_buf_insert_barrier_packet(etr_buf, etr_buf->offset); - tmc_etr_sync_perf_buffer(etr_perf, offset, size); + 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 function cs_etm_find_snapshot() will - * figure out how many bytes to get from the AUX buffer based on the - * position of the head. + * 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(); + out: /* * Don't set the TRUNCATED flag in snapshot mode because 1) the @@ -1586,8 +1629,6 @@ 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); - /* * No HW configuration is needed if the sink is already in * use for this session. diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index 71de978575f3..66959557cf39 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -70,7 +70,8 @@ #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) @@ -174,6 +175,8 @@ struct etr_buf { * @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). + * @max_burst_size: The maximum burst size that can be initiated by + * TMC-ETR on AXI bus. * @mode: how this TMC is being used. * @config_type: TMC variant, must be of type @tmc_config_type. * @memwidth: width of the memory interface databus, in bytes. @@ -198,6 +201,7 @@ struct tmc_drvdata { }; u32 len; u32 size; + u32 max_burst_size; u32 mode; enum tmc_config_type config_type; enum tmc_mem_intf_width memwidth; @@ -268,6 +272,7 @@ 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); @@ -277,12 +282,12 @@ 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) @@ -325,4 +330,7 @@ tmc_sg_table_buf_size(struct tmc_sg_table *sg_table) 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); + #endif diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index f8583e4032a6..34d37abd2c8d 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -49,7 +49,7 @@ DEFINE_CORESIGHT_DEVLIST(tpiu_devs, "tpiu"); -/** +/* * @base: memory mapped base address for this component. * @atclk: optional clock for the core parts of the TPIU. * @csdev: component vitals needed by the framework. @@ -60,49 +60,45 @@ struct tpiu_drvdata { struct coresight_device *csdev; }; -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) { - struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - tpiu_enable_hw(drvdata); + tpiu_enable_hw(&csdev->access); atomic_inc(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 int tpiu_disable(struct coresight_device *csdev) { - struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - if (atomic_dec_return(csdev->refcnt)) return -EBUSY; - tpiu_disable_hw(drvdata); + tpiu_disable_hw(&csdev->access); dev_dbg(&csdev->dev, "TPIU disabled\n"); return 0; @@ -149,9 +145,10 @@ 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); pdata = coresight_get_platform_data(dev); if (IS_ERR(pdata)) @@ -173,6 +170,13 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) return PTR_ERR(drvdata->csdev); } +static void tpiu_remove(struct amba_device *adev) +{ + struct tpiu_drvdata *drvdata = dev_get_drvdata(&adev->dev); + + coresight_unregister(drvdata->csdev); +} + #ifdef CONFIG_PM static int tpiu_runtime_suspend(struct device *dev) { @@ -216,6 +220,8 @@ static const struct amba_id tpiu_ids[] = { { 0, 0}, }; +MODULE_DEVICE_TABLE(amba, tpiu_ids); + static struct amba_driver tpiu_driver = { .drv = { .name = "coresight-tpiu", @@ -224,6 +230,13 @@ static struct amba_driver tpiu_driver = { .suppress_bind_attrs = true, }, .probe = tpiu_probe, + .remove = tpiu_remove, .id_table = tpiu_ids, }; -builtin_amba_driver(tpiu_driver); + +module_amba_driver(tpiu_driver); + +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-trbe.c b/drivers/hwtracing/coresight/coresight-trbe.c new file mode 100644 index 000000000000..2b386bb848f8 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trbe.c @@ -0,0 +1,1568 @@ +// 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 "coresight-self-hosted-trace.h" +#include "coresight-trbe.h" + +#define PERF_IDX2OFF(idx, buf) ((idx) % ((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 inline bool trbe_has_erratum(struct trbe_cpudata *cpudata, int i) +{ + return (i < TRBE_ERRATA_MAX) && test_bit(i, cpudata->errata); +} + +static inline bool trbe_may_overwrite_in_fill_mode(struct trbe_cpudata *cpudata) +{ + return trbe_has_erratum(cpudata, TRBE_WORKAROUND_OVERWRITE_FILL_MODE); +} + +static inline bool trbe_may_write_out_of_range(struct trbe_cpudata *cpudata) +{ + return trbe_has_erratum(cpudata, TRBE_WORKAROUND_WRITE_OUT_OF_RANGE); +} + +static inline 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 inline 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 inline 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 inline void trbe_drain_buffer(void) +{ + tsb_csync(); + dsb(nsh); +} + +static inline 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_ENABLE; + write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + + /* Synchronize the TRBE enable event */ + isb(); + + if (trbe_needs_ctxt_sync_after_enable(cpudata)) + isb(); +} + +static inline 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_ENABLE; + write_sysreg_s(trblimitr, SYS_TRBLIMITR_EL1); + + 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) +{ + trbe_drain_and_disable_local(cpudata); + write_sysreg_s(0, SYS_TRBLIMITR_EL1); + 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_IRQ; + trbsr &= ~TRBSR_TRG; + trbsr &= ~TRBSR_WRAP; + trbsr &= ~(TRBSR_EC_MASK << TRBSR_EC_SHIFT); + trbsr &= ~(TRBSR_BSC_MASK << TRBSR_BSC_SHIFT); + trbsr &= ~TRBSR_STOP; + 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_LIMIT_SHIFT))); + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + + trblimitr &= ~TRBLIMITR_NVM; + trblimitr &= ~(TRBLIMITR_FILL_MODE_MASK << TRBLIMITR_FILL_MODE_SHIFT); + trblimitr &= ~(TRBLIMITR_TRIG_MODE_MASK << TRBLIMITR_TRIG_MODE_SHIFT); + trblimitr &= ~(TRBLIMITR_LIMIT_MASK << TRBLIMITR_LIMIT_SHIFT); + + /* + * 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 |= (TRBE_FILL_MODE_FILL & TRBLIMITR_FILL_MODE_MASK) << TRBLIMITR_FILL_MODE_SHIFT; + + /* + * Trigger mode is not used here while configuring the TRBE for + * the trace capture. Hence just keep this in the ignore mode. + */ + trblimitr |= (TRBE_TRIG_MODE_IGNORE & TRBLIMITR_TRIG_MODE_MASK) << + TRBLIMITR_TRIG_MODE_SHIFT; + 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 ERR_PTR(-ENOMEM); + + pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL); + if (!pglist) { + kfree(buf); + return ERR_PTR(-ENOMEM); + } + + 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 ERR_PTR(-ENOMEM); + } + 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, u32 mode, void *data) +{ + struct trbe_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct trbe_cpudata *cpudata = dev_get_drvdata(&csdev->dev); + struct perf_output_handle *handle = data; + 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 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_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; + + desc.type = CORESIGHT_DEV_TYPE_SINK; + desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM; + desc.ops = &arm_trbe_cs_ops; + desc.pdata = dev_get_platdata(dev); + 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(void *info) +{ + int cpu = smp_processor_id(); + struct trbe_drvdata *drvdata = info; + struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); + struct coresight_device *trbe_csdev = coresight_get_percpu_sink(cpu); + + disable_percpu_irq(drvdata->irq); + trbe_reset_local(cpudata); + if (trbe_csdev) { + coresight_unregister(trbe_csdev); + cpudata->drvdata = NULL; + 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_remove_coresight_cpu, drvdata, 1); + 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)) { + struct trbe_cpudata *cpudata = per_cpu_ptr(drvdata->cpudata, cpu); + + disable_percpu_irq(drvdata->irq); + trbe_reset_local(cpudata); + } + 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_remove_multi_state(drvdata->trbe_online); +} + +static int arm_trbe_probe_irq(struct platform_device *pdev, + struct trbe_drvdata *drvdata) +{ + int ret; + + drvdata->irq = platform_get_irq(pdev, 0); + 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; + } + + if (irq_get_percpu_devid_partition(drvdata->irq, &drvdata->supported_cpus)) + return -EINVAL; + + drvdata->handle = alloc_percpu(struct perf_output_handle *); + if (!drvdata->handle) + return -ENOMEM; + + ret = request_percpu_irq(drvdata->irq, arm_trbe_irq_handler, DRVNAME, 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 coresight_platform_data *pdata; + 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; + + pdata = coresight_get_platform_data(dev); + if (IS_ERR(pdata)) + return PTR_ERR(pdata); + + dev_set_drvdata(dev, drvdata); + dev->platform_data = pdata; + 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 int 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); + return 0; +} + +static const struct of_device_id arm_trbe_of_match[] = { + { .compatible = "arm,trace-buffer-extension"}, + {}, +}; +MODULE_DEVICE_TABLE(of, arm_trbe_of_match); + +static struct platform_driver arm_trbe_driver = { + .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..98ff1b17ad07 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trbe.h @@ -0,0 +1,145 @@ +/* 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/coresight.h> +#include <linux/device.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/of.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 >= 0b0001; +} + +static inline bool is_trbe_enabled(void) +{ + u64 trblimitr = read_sysreg_s(SYS_TRBLIMITR_EL1); + + return trblimitr & TRBLIMITR_ENABLE; +} + +#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_EC_SHIFT) & TRBSR_EC_MASK; +} + +#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_BSC_SHIFT) & TRBSR_BSC_MASK; +} + +static inline void clr_trbe_irq(void) +{ + u64 trbsr = read_sysreg_s(SYS_TRBSR_EL1); + + trbsr &= ~TRBSR_IRQ; + write_sysreg_s(trbsr, SYS_TRBSR_EL1); +} + +static inline bool is_trbe_irq(u64 trbsr) +{ + return trbsr & TRBSR_IRQ; +} + +static inline bool is_trbe_trg(u64 trbsr) +{ + return trbsr & TRBSR_TRG; +} + +static inline bool is_trbe_wrap(u64 trbsr) +{ + return trbsr & TRBSR_WRAP; +} + +static inline bool is_trbe_abort(u64 trbsr) +{ + return trbsr & TRBSR_ABORT; +} + +static inline bool is_trbe_running(u64 trbsr) +{ + return !(trbsr & TRBSR_STOP); +} + +#define TRBE_TRIG_MODE_STOP 0 +#define TRBE_TRIG_MODE_IRQ 1 +#define TRBE_TRIG_MODE_IGNORE 3 + +#define TRBE_FILL_MODE_FILL 0 +#define TRBE_FILL_MODE_WRAP 1 +#define TRBE_FILL_MODE_CIRCULAR_BUFFER 3 + +static inline bool get_trbe_flag_update(u64 trbidr) +{ + return trbidr & TRBIDR_FLAG; +} + +static inline bool is_trbe_programmable(u64 trbidr) +{ + return !(trbidr & TRBIDR_PROG); +} + +static inline int get_trbe_address_align(u64 trbidr) +{ + return (trbidr >> TRBIDR_ALIGN_SHIFT) & TRBIDR_ALIGN_MASK; +} + +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_LIMIT_MASK << TRBLIMITR_LIMIT_SHIFT); + + 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_BASE_MASK << TRBBASER_BASE_SHIFT); + + 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_BASE_SHIFT))); + WARN_ON(!IS_ALIGNED(addr, PAGE_SIZE)); + write_sysreg_s(addr, SYS_TRBBASER_EL1); +} diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index ca232ec565e8..7e753a75d23b 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -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 @@ -162,8 +164,6 @@ 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 = { @@ -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 @@ -844,7 +861,7 @@ static irqreturn_t intel_th_irq(int irq, void *data) * @irq: irq number */ struct intel_th * -intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, +intel_th_alloc(struct device *dev, const struct intel_th_drvdata *drvdata, struct resource *devres, unsigned int ndevres) { int err, r, nr_mmios = 0; @@ -1021,15 +1038,30 @@ 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; + } + + ret = hubdrv->set_output(hub, master); - return 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 f72803a02391..b3308934a687 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -543,7 +543,7 @@ 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); @@ -564,6 +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 @@ -697,7 +712,7 @@ 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; master++) + for (master = 0; master < TH_CONFIGURABLE_MASTERS + 1; master++) if (gth->master[master] == port) gth->master[master] = -1; spin_unlock(>h->gth_lock); @@ -815,6 +830,7 @@ 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, diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 6f4f5486fe6d..0ffb42990175 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -47,11 +47,13 @@ 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; }; @@ -72,7 +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; @@ -141,6 +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 @@ -162,6 +165,8 @@ 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, @@ -176,7 +181,7 @@ struct intel_th_driver { /* 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, @@ -222,7 +227,7 @@ 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, +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); @@ -270,7 +275,7 @@ 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[TH_MMIO_END]; int (*activate)(struct intel_th *); diff --git a/drivers/hwtracing/intel_th/msu-sink.c b/drivers/hwtracing/intel_th/msu-sink.c index 2c7f5116be12..891b28ea25fe 100644 --- a/drivers/hwtracing/intel_th/msu-sink.c +++ b/drivers/hwtracing/intel_th/msu-sink.c @@ -71,6 +71,9 @@ static int msu_sink_alloc_window(void *data, struct sg_table **sgt, size_t size) 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); } diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 255f8f41c8ff..6c8215a47a60 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -138,6 +138,7 @@ struct msc { 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; @@ -154,10 +155,13 @@ struct msc { struct list_head iter_list; + bool stop_on_full; + /* config */ unsigned int enabled : 1, wrap : 1, - do_irq : 1; + do_irq : 1, + multi_is_broken : 1; unsigned int mode; unsigned int burst_len; unsigned int index; @@ -654,13 +658,11 @@ static void msc_buffer_clear_hw_header(struct msc *msc) 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_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); } } } @@ -1020,35 +1022,61 @@ err_nomem: } #ifdef CONFIG_X86 -static void msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs) +static void msc_buffer_set_uc(struct msc *msc) { struct scatterlist *sg_ptr; + struct msc_window *win; int i; - for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) { - /* Set the page as uncached */ - set_memory_uc((unsigned long)sg_virt(sg_ptr), - PFN_DOWN(sg_ptr->length)); + 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_window *win) +static void msc_buffer_set_wb(struct msc *msc) { struct scatterlist *sg_ptr; + struct msc_window *win; int i; - 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)); + 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_window *win, unsigned int nr_segs) {} -static inline void msc_buffer_set_wb(struct msc_window *win) {} +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 @@ -1093,8 +1121,6 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) if (ret <= 0) goto err_nomem; - msc_buffer_set_uc(win, ret); - win->nr_segs = ret; win->nr_blocks = nr_blocks; @@ -1121,7 +1147,7 @@ static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win) int i; for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) { - struct page *page = sg_page(sg); + struct page *page = msc_sg_page(sg); page->mapping = NULL; dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, @@ -1148,8 +1174,6 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) msc->base_addr = 0; } - msc_buffer_set_wb(win); - if (msc->mbuf && msc->mbuf->free_window) msc->mbuf->free_window(msc->mbuf_priv, win->sgt); else @@ -1256,6 +1280,8 @@ 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) @@ -1299,6 +1325,8 @@ static int msc_buffer_alloc(struct msc *msc, unsigned long *nr_pages, } if (!ret) { + msc_buffer_set_uc(msc); + /* allocation should be visible before the counter goes to 0 */ smp_mb__before_atomic(); @@ -1383,7 +1411,7 @@ found: pgoff -= win->pgoff; for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { - struct page *page = sg_page(sg); + struct page *page = msc_sg_page(sg); size_t pgsz = PFN_DOWN(sg->length); if (pgoff < pgsz) @@ -1665,7 +1693,7 @@ 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); @@ -1717,6 +1745,10 @@ void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt) 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); @@ -1757,7 +1789,11 @@ static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) /* next window: if READY, proceed, if LOCKED, stop the trace */ if (msc_win_set_lockout(next_win, WIN_READY, WIN_INUSE)) { - schedule_work(&msc->work); + if (msc->stop_on_full) + schedule_work(&msc->work); + else + msc->switch_on_unlock = next_win; + return IRQ_HANDLED; } @@ -1877,6 +1913,9 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, return -EINVAL; found: + if (i == MSC_MODE_MULTI && msc->multi_is_broken) + return -EOPNOTSUPP; + mutex_lock(&msc->buf_mutex); ret = 0; @@ -1987,7 +2026,7 @@ 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; @@ -2047,15 +2086,40 @@ win_switch_store(struct device *dev, struct device_attribute *attr, 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, }; @@ -2083,6 +2147,9 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) 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; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 86aa6a46bcba..147d338c191e 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -71,7 +71,7 @@ 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], @@ -100,8 +100,10 @@ static int intel_th_pci_probe(struct pci_dev *pdev, } th = intel_th_alloc(&pdev->dev, drvdata, resource, r); - if (IS_ERR(th)) - return PTR_ERR(th); + if (IS_ERR(th)) { + err = PTR_ERR(th); + goto err_free_irq; + } th->activate = intel_th_pci_activate; th->deactivate = intel_th_pci_deactivate; @@ -109,6 +111,10 @@ 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) @@ -120,6 +126,10 @@ static void intel_th_pci_remove(struct pci_dev *pdev) 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, @@ -152,7 +162,7 @@ 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 */ @@ -207,7 +217,7 @@ static const struct pci_device_id intel_th_pci_id_table[] = { { /* Comet Lake PCH-V */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa3a6), - .driver_data = (kernel_ulong_t)&intel_th_2x, + .driver_data = (kernel_ulong_t)&intel_th_1x_multi_is_broken, }, { /* Ice Lake NNPI */ @@ -230,11 +240,21 @@ static const struct pci_device_id intel_th_pci_id_table[] = { .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, @@ -244,6 +264,51 @@ static const struct pci_device_id intel_th_pci_id_table[] = { 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, + }, + { + /* 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, + }, + { + /* 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 0da6b787f553..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, }; @@ -295,7 +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/sth.c b/drivers/hwtracing/intel_th/sth.c index 3a1f4e650378..9ca8c4e045f8 100644 --- a/drivers/hwtracing/intel_th/sth.c +++ b/drivers/hwtracing/intel_th/sth.c @@ -84,11 +84,11 @@ 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; - /* fall through */ + fallthrough; case STP_PACKET_XSYNC: reg += 8; - /* fall through */ + fallthrough; case STP_PACKET_TRIG: if (flags & STP_PACKET_TIMESTAMPED) @@ -161,9 +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..5d5526aa60c4 --- /dev/null +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -0,0 +1,1046 @@ +// 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); + 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; + + /* + * Just commit the traced data if we're going to stop. Otherwise if the + * resident AUX buffer cannot contain the data of next trace buffer, + * apply a new one. + */ + if (stop) { + perf_aux_output_end(handle, buf->pos); + } else if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) { + perf_aux_output_end(handle, buf->pos); + + 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; + + ret = devm_request_threaded_irq(&pdev->dev, + pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ), + NULL, hisi_ptt_isr, 0, + DRV_NAME, hisi_ptt); + if (ret) { + pci_err(pdev, "failed to request irq %d, ret = %d\n", + pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ), ret); + return ret; + } + + return 0; +} + +static int hisi_ptt_init_filters(struct pci_dev *pdev, void *data) +{ + struct hisi_ptt_filter_desc *filter; + struct hisi_ptt *hisi_ptt = data; + + /* + * 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 = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) { + pci_err(hisi_ptt->pdev, "failed to add filter %s\n", pci_name(pdev)); + return -ENOMEM; + } + + filter->devid = PCI_DEVID(pdev->bus->number, pdev->devfn); + + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) { + filter->is_port = true; + 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 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) { + list_del(&filter->list); + kfree(filter); + } + + list_for_each_entry_safe(filter, tmp, &hisi_ptt->port_filters, list) { + list_del(&filter->list); + kfree(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_LIST_HEAD(&hisi_ptt->port_filters); + INIT_LIST_HEAD(&hisi_ptt->req_filters); + + 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 const struct attribute_group *hisi_ptt_pmu_groups[] = { + &hisi_ptt_cpumask_attr_group, + &hisi_ptt_pmu_format_group, + &hisi_ptt_tune_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; + + 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. + */ + 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)) + return 0; + } + } else if (bitmap_subset(&val, &port_mask, BITS_PER_LONG)) { + return 0; + } + + return -EINVAL; +} + +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->cpu < 0) { + dev_dbg(event->pmu->dev, "Per-task mode not supported\n"); + return -EOPNOTSUPP; + } + + if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type) + return -ENOENT; + + 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(pci_irq_vector(hisi_ptt->pdev, HISI_PTT_TRACE_DMA_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_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, + .capabilities = PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE, + .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, + }; + + 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); +} + +/* + * 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_pmu(hisi_ptt); + if (ret) { + pci_err(pdev, "failed to register PMU device, 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(pci_irq_vector(hisi_ptt->pdev, HISI_PTT_TRACE_DMA_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..5beb1648c93a --- /dev/null +++ b/drivers/hwtracing/ptt/hisi_ptt.h @@ -0,0 +1,200 @@ +/* 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/list.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/perf_event.h> +#include <linux/spinlock.h> +#include <linux/types.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_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 + +#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; +}; + +/** + * struct hisi_ptt_filter_desc - Descriptor of the PTT trace filter + * @list: entry of this descriptor in the filter list + * @is_port: the PCI device of the filter is a Root Port or not + * @devid: the PCI device's devid of the filter + */ +struct hisi_ptt_filter_desc { + struct list_head list; + bool is_port; + 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 + * @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 + * @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 + * @port_mask: port mask of the managed root ports + */ +struct hisi_ptt { + struct hisi_ptt_trace_ctrl trace_ctrl; + 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; + 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; + u16 port_mask; +}; + +#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 d0e92a8a045c..aad594fe79cc 100644 --- a/drivers/hwtracing/stm/Kconfig +++ b/drivers/hwtracing/stm/Kconfig @@ -71,7 +71,7 @@ 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/ftrace.c b/drivers/hwtracing/stm/ftrace.c index ce868e095410..3bb606dfa634 100644 --- a/drivers/hwtracing/stm/ftrace.c +++ b/drivers/hwtracing/stm/ftrace.c @@ -37,8 +37,10 @@ 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 +48,8 @@ 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 +65,7 @@ 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..81d7b21d31ec 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; @@ -72,8 +72,10 @@ 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.link = stm_heartbeat_link; diff --git a/drivers/hwtracing/stm/p_sys-t.c b/drivers/hwtracing/stm/p_sys-t.c index 360b5c03df95..8254971c02e7 100644 --- a/drivers/hwtracing/stm/p_sys-t.c +++ b/drivers/hwtracing/stm/p_sys-t.c @@ -92,7 +92,7 @@ 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) @@ -292,6 +292,7 @@ static ssize_t sys_t_write(struct stm_data *data, struct stm_output *output, unsigned int m = output->master; const unsigned char nil = 0; u32 header = DATA_HEADER; + u8 uuid[UUID_SIZE]; ssize_t sz; /* We require an existing policy node to proceed */ @@ -322,7 +323,8 @@ 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; diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c index 4f932a419752..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 ? diff --git a/drivers/hwtracing/stm/stm.h b/drivers/hwtracing/stm/stm.h index 3569439d53bb..a9be49fc7a6b 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) \ |