The existing mechanism to assign Trace ID values to sources is limited and does not scale for larger multicore / multi trace source systems.

The API introduces functions that reserve IDs based on availabilty represented by a coresight_trace_id_map structure. This records the used and free IDs in a bitmap.

CPU bound sources such as ETMs use the coresight_trace_id_get_cpu_id coresight_trace_id_put_cpu_id pair of functions. The API will record the ID associated with the CPU. This ensures that the same ID will be re-used while perf events are active on the CPU. The put_cpu_id function will pend release of the ID until all perf cs_etm sessions are complete.

For backward compatibility the functions will attempt to use the same CPU IDs as the legacy system would have used if these are still available.

Non-cpu sources, such as the STM can use coresight_trace_id_get_system_id / coresight_trace_id_put_system_id.

Signed-off-by: Mike Leach mike.leach@linaro.org --- drivers/hwtracing/coresight/Makefile | 2 +- .../hwtracing/coresight/coresight-trace-id.c | 265 ++++++++++++++++++ .../hwtracing/coresight/coresight-trace-id.h | 156 +++++++++++ include/linux/coresight-pmu.h | 10 + 4 files changed, 432 insertions(+), 1 deletion(-) create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.c create mode 100644 drivers/hwtracing/coresight/coresight-trace-id.h

diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index b6c4a48140ec..329a0c704b87 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_CORESIGHT) += coresight.o coresight-y := coresight-core.o coresight-etm-perf.o coresight-platform.o \ coresight-sysfs.o coresight-syscfg.o coresight-config.o \ coresight-cfg-preload.o coresight-cfg-afdo.o \ - coresight-syscfg-configfs.o + coresight-syscfg-configfs.o coresight-trace-id.o obj-$(CONFIG_CORESIGHT_LINK_AND_SINK_TMC) += coresight-tmc.o coresight-tmc-y := coresight-tmc-core.o coresight-tmc-etf.o \ coresight-tmc-etr.o diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c new file mode 100644 index 000000000000..9b85c376cb12 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022, Linaro Limited, All rights reserved. + * Author: Mike Leach mike.leach@linaro.org + */ +#include <linux/coresight-pmu.h> +#include <linux/cpumask.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/types.h> + +#include "coresight-trace-id.h" + +/* Default trace ID map. Used on systems that don't require per sink mappings */ +static struct coresight_trace_id_map id_map_default; + +/* maintain a record of the mapping of IDs and pending releases per cpu */ +static DEFINE_PER_CPU(atomic_t, cpu_id) = ATOMIC_INIT(0); +static cpumask_t cpu_id_release_pending; + +/* perf session active counter */ +static atomic_t perf_cs_etm_session_active = ATOMIC_INIT(0); + +/* lock to protect id_map and cpu data */ +static DEFINE_SPINLOCK(id_map_lock); + +/* unlocked read of current trace ID value for given CPU */ +static int _coresight_trace_id_read_cpu_id(int cpu) +{ + return atomic_read(&per_cpu(cpu_id, cpu)); +} + +/* look for next available odd ID, return 0 if none found */ +static int coresight_trace_id_find_odd_id(struct coresight_trace_id_map *id_map) +{ + int found_id = 0, bit = 1, next_id; + + while ((bit < CORESIGHT_TRACE_ID_RES_TOP) && !found_id) { + /* + * bitmap length of CORESIGHT_TRACE_ID_RES_TOP, + * search from offset `bit`. + */ + next_id = find_next_zero_bit(id_map->used_ids, + CORESIGHT_TRACE_ID_RES_TOP, bit); + if ((next_id < CORESIGHT_TRACE_ID_RES_TOP) && (next_id & 0x1)) + found_id = next_id; + else + bit = next_id + 1; + } + return found_id; +} + +/* + * Allocate new ID and set in use + * + * if @preferred_id is a valid id then try to use that value if available. + * if @preferred_id is not valid and @prefer_odd_id is true, try for odd id. + * + * Otherwise allocate next available ID. + */ +static int coresight_trace_id_alloc_new_id(struct coresight_trace_id_map *id_map, + int preferred_id, bool prefer_odd_id) +{ + int id = 0; + + /* for backwards compatibility, cpu IDs may use preferred value */ + if (IS_VALID_CS_TRACE_ID(preferred_id) && + !test_bit(preferred_id, id_map->used_ids)) { + id = preferred_id; + goto trace_id_allocated; + } else if (prefer_odd_id) { + /* may use odd ids to avoid preferred legacy cpu IDs */ + id = coresight_trace_id_find_odd_id(id_map); + if (id) + goto trace_id_allocated; + } + + /* + * skip reserved bit 0, look at bitmap length of + * CORESIGHT_TRACE_ID_RES_TOP from offset of bit 1. + */ + id = find_next_zero_bit(id_map->used_ids, CORESIGHT_TRACE_ID_RES_TOP, 1); + if (id >= CORESIGHT_TRACE_ID_RES_TOP) + return -EINVAL; + + /* mark as used */ +trace_id_allocated: + set_bit(id, id_map->used_ids); + return id; +} + +static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + if (WARN(!test_bit(id, id_map->used_ids), "Freeing unused ID %d\n", id)) + return; + clear_bit(id, id_map->used_ids); +} + +static void coresight_trace_id_set_pend_rel(int id, struct coresight_trace_id_map *id_map) +{ + if (WARN(!IS_VALID_CS_TRACE_ID(id), "Invalid Trace ID %d\n", id)) + return; + set_bit(id, id_map->pend_rel_ids); +} + +/* + * release all pending IDs for all current maps & clear CPU associations + * + * This currently operates on the default id map, but may be extended to + * operate on all registered id maps if per sink id maps are used. + */ +static void coresight_trace_id_release_all_pending(void) +{ + struct coresight_trace_id_map *id_map = &id_map_default; + unsigned long flags; + int cpu, bit; + + spin_lock_irqsave(&id_map_lock, flags); + for_each_set_bit(bit, id_map->pend_rel_ids, CORESIGHT_TRACE_ID_RES_TOP) { + clear_bit(bit, id_map->used_ids); + clear_bit(bit, id_map->pend_rel_ids); + } + for_each_cpu(cpu, &cpu_id_release_pending) { + atomic_set(&per_cpu(cpu_id, cpu), 0); + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + } + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (id) + goto get_cpu_id_clr_pend; + + /* + * Find a new ID. + * + * Use legacy values where possible in the dynamic trace ID allocator to + * allow older tools to continue working if they are not upgraded at the + * same time as the kernel drivers. + * + * If the generated legacy ID is invalid, or not available then the next + * available dynamic ID will be used. + */ + id = coresight_trace_id_alloc_new_id(id_map, + CORESIGHT_LEGACY_CPU_TRACE_ID(cpu), + false); + if (!IS_VALID_CS_TRACE_ID(id)) + goto get_cpu_id_out_unlock; + + /* allocate the new id to the cpu */ + atomic_set(&per_cpu(cpu_id, cpu), id); + +get_cpu_id_clr_pend: + /* we are (re)using this ID - so ensure it is not marked for release */ + cpumask_clear_cpu(cpu, &cpu_id_release_pending); + clear_bit(id, id_map->pend_rel_ids); + +get_cpu_id_out_unlock: + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + /* check for existing allocation for this CPU */ + id = _coresight_trace_id_read_cpu_id(cpu); + if (!id) + return; + + spin_lock_irqsave(&id_map_lock, flags); + + if (atomic_read(&perf_cs_etm_session_active)) { + /* set release at pending if perf still active */ + coresight_trace_id_set_pend_rel(id, id_map); + cpumask_set_cpu(cpu, &cpu_id_release_pending); + } else { + /* otherwise clear id */ + coresight_trace_id_free(id, id_map); + atomic_set(&per_cpu(cpu_id, cpu), 0); + } + + spin_unlock_irqrestore(&id_map_lock, flags); +} + +static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map) +{ + unsigned long flags; + int id; + + spin_lock_irqsave(&id_map_lock, flags); + /* prefer odd IDs for system components to avoid legacy CPU IDS */ + id = coresight_trace_id_alloc_new_id(id_map, 0, true); + spin_unlock_irqrestore(&id_map_lock, flags); + + return id; +} + +static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map *id_map, int id) +{ + unsigned long flags; + + spin_lock_irqsave(&id_map_lock, flags); + coresight_trace_id_free(id, id_map); + spin_unlock_irqrestore(&id_map_lock, flags); +} + +/* API functions */ + +int coresight_trace_id_get_cpu_id(int cpu) +{ + return coresight_trace_id_map_get_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id); + +void coresight_trace_id_put_cpu_id(int cpu) +{ + coresight_trace_id_map_put_cpu_id(cpu, &id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id); + +int coresight_trace_id_read_cpu_id(int cpu) +{ + return _coresight_trace_id_read_cpu_id(cpu); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id); + +int coresight_trace_id_get_system_id(void) +{ + return coresight_trace_id_map_get_system_id(&id_map_default); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_system_id); + +void coresight_trace_id_put_system_id(int id) +{ + coresight_trace_id_map_put_system_id(&id_map_default, id); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); + +void coresight_trace_id_perf_start(void) +{ + atomic_inc(&perf_cs_etm_session_active); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); + +void coresight_trace_id_perf_stop(void) +{ + if (!atomic_dec_return(&perf_cs_etm_session_active)) + coresight_trace_id_release_all_pending(); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); + diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h new file mode 100644 index 000000000000..3797777d367e --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(C) 2022 Linaro Limited. All rights reserved. + * Author: Mike Leach mike.leach@linaro.org + */ + +#ifndef _CORESIGHT_TRACE_ID_H +#define _CORESIGHT_TRACE_ID_H + +/* + * Coresight trace ID allocation API + * + * With multi cpu systems, and more additional trace sources a scalable + * trace ID reservation system is required. + * + * The system will allocate Ids on a demand basis, and allow them to be + * released when done. + * + * In order to ensure that a consistent cpu / ID matching is maintained + * throughout a perf cs_etm event session - a session in progress flag will + * be maintained, and released IDs not cleared until the perf session is + * complete. This allows the same CPU to be re-allocated its prior ID. + * + * + * Trace ID maps will be created and initialised to prevent architecturally + * reserved IDs from being allocated. + * + * API permits multiple maps to be maintained - for large systems where + * different sets of cpus trace into different independent sinks. + */ + +#include <linux/bitops.h> +#include <linux/types.h> + + +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/* ID 0 is reserved */ +#define CORESIGHT_TRACE_ID_RES_0 0 + +/* ID 0x70 onwards are reserved */ +#define CORESIGHT_TRACE_ID_RES_TOP 0x70 + +/* check an ID is in the valid range */ +#define IS_VALID_CS_TRACE_ID(id) \ + ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) + +/** + * Trace ID map. + * + * @used_ids: Bitmap to register available (bit = 0) and in use (bit = 1) IDs. + * Initialised so that the reserved IDs are permanently marked as + * in use. + * @pend_rel_ids: CPU IDs that have been released by the trace source but not + * yet marked as available, to allow re-allocation to the same + * CPU during a perf session. + */ +struct coresight_trace_id_map { + DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); + DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); +}; + +/* Allocate and release IDs for a single default trace ID map */ + +/** + * Read and optionally allocate a CoreSight trace ID and associate with a CPU. + * + * Function will read the current trace ID for the associated CPU, + * allocating an new ID if one is not currently allocated. + * + * Numeric ID values allocated use legacy allocation algorithm if possible, + * otherwise any available ID is used. + * + * @cpu: The CPU index to allocate for. + * + * return: CoreSight trace ID or -EINVAL if allocation impossible. + */ +int coresight_trace_id_get_cpu_id(int cpu); + +/** + * Release an allocated trace ID associated with the CPU. + * + * This will release the CoreSight trace ID associated with the CPU, + * unless a perf session is in operation. + * + * If a perf session is in operation then the ID will be marked as pending + * release. + * + * @cpu: The CPU index to release the associated trace ID. + */ +void coresight_trace_id_put_cpu_id(int cpu); + +/** + * Read the current allocated CoreSight Trace ID value for the CPU. + * + * Fast read of the current value that does not allocate if no ID allocated + * for the CPU. + * + * Used in perf context where it is known that the value for the CPU will not + * be changing, when perf starts and event on a core and outputs the Trace ID + * for the CPU as a packet in the data file. IDs cannot change during a perf + * session. + * + * This function does not take the lock protecting the ID lists, avoiding + * locking dependency issues with perf locks. + * + * @cpu: The CPU index to read. + * + * return: current value, will be 0 if unallocated. + */ +int coresight_trace_id_read_cpu_id(int cpu); + +/** + * Allocate a CoreSight trace ID for a system component. + * + * Unconditionally allocates a Trace ID, without associating the ID with a CPU. + * + * Used to allocate IDs for system trace sources such as STM. + * + * return: Trace ID or -EINVAL if allocation is impossible. + */ +int coresight_trace_id_get_system_id(void); + +/** + * Release an allocated system trace ID. + * + * Unconditionally release a trace ID allocated to a system component. + * + * @id: value of trace ID allocated. + */ +void coresight_trace_id_put_system_id(int id); + +/* notifiers for perf session start and stop */ + +/** + * Notify the Trace ID allocator that a perf session is starting. + * + * Increase the perf session reference count - called by perf when setting up + * a trace event. + * + * This reference count is used by the ID allocator to ensure that trace IDs + * associated with a CPU cannot change or be released during a perf session. + */ +void coresight_trace_id_perf_start(void); + +/** + * Notify the ID allocator that a perf session is stopping. + * + * Decrease the perf session reference count. + * if this causes the count to go to zero, then all Trace IDs marked as pending + * release, will be released. + */ +void coresight_trace_id_perf_stop(void); + +#endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 6c2fd6cc5a98..ffff4e6277e5 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -10,6 +10,16 @@ #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10

+/* + * The legacy Trace ID system based on fixed calculation from the cpu + * number. This has been replaced by drivers using a dynamic allocation + * system - but need to retain the legacy algorithm for backward comparibility + * in certain situations:- + * a) new perf running on older systems that generate the legacy mapping + * b) older tools that may not update at the same time as the kernel. + */ +#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) (0x10 + (cpu * 2)) + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions.

Adds in calls to allocate and release Trace ID for the CPUs in use by the perf session.

Adds in notifier calls to the trace ID allocator that perf events are starting and stopping.

This ensures that Trace IDs associated with CPUs remain the same throughout the perf session, and are only released when all perf sessions are complete.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com --- drivers/hwtracing/coresight/coresight-etm-perf.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 43bbd5dc3d3b..bdb9ab86173a 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -22,6 +22,7 @@ #include "coresight-etm-perf.h" #include "coresight-priv.h" #include "coresight-syscfg.h" +#include "coresight-trace-id.h"

static struct pmu etm_pmu; static bool etm_perf_up; @@ -228,8 +229,12 @@ static void free_event_data(struct work_struct *work) if (!(IS_ERR_OR_NULL(*ppath))) coresight_release_path(*ppath); *ppath = NULL; + coresight_trace_id_put_cpu_id(cpu); }

+ /* mark perf event as done for trace id allocator */ + coresight_trace_id_perf_stop(); + free_percpu(event_data->path); kfree(event_data); } @@ -300,6 +305,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, { u32 id, cfg_hash; int cpu = event->cpu; + int trace_id; cpumask_t *mask; struct coresight_device *sink = NULL; struct coresight_device *user_sink = NULL, *last_sink = NULL; @@ -316,6 +322,9 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, sink = user_sink = coresight_get_sink_by_id(id); }

+ /* tell the trace ID allocator that a perf event is starting up */ + coresight_trace_id_perf_start(); + /* check if user wants a coresight configuration selected */ cfg_hash = (u32)((event->attr.config2 & GENMASK_ULL(63, 32)) >> 32); if (cfg_hash) { @@ -388,6 +397,13 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, continue; }

+ /* ensure we can allocate a trace ID for this CPU */ + trace_id = coresight_trace_id_get_cpu_id(cpu); + if (!IS_VALID_CS_TRACE_ID(trace_id)) { + cpumask_clear_cpu(cpu, mask); + continue; + } + *etm_event_cpu_path_ptr(event_data, cpu) = path; }

The trace ID API is now used to allocate trace IDs for ETM4.x / ETE devices.

For perf sessions, these will be allocated on enable, and released on disable.

For sysfs sessions, these will be allocated on enable, but only released on reset. This allows the sysfs session to interrogate the Trace ID used after the session is over - maintaining functional consistency with the previous allocation scheme.

The trace ID will also be allocated on read of the mgmt/trctraceid file. This ensures that if perf or sysfs read this before enabling trace, the value will be the one used for the trace session.

Trace ID initialisation is removed from the _probe() function.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com --- .../coresight/coresight-etm4x-core.c | 73 +++++++++++++++++-- .../coresight/coresight-etm4x-sysfs.c | 27 ++++++- drivers/hwtracing/coresight/coresight-etm4x.h | 3 + 3 files changed, 93 insertions(+), 10 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 9dc0d7f57565..0656577d7e30 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -42,6 +42,7 @@ #include "coresight-etm4x-cfg.h" #include "coresight-self-hosted-trace.h" #include "coresight-syscfg.h" +#include "coresight-trace-id.h"

static int boot_enable; module_param(boot_enable, int, 0444); @@ -237,6 +238,30 @@ static int etm4_trace_id(struct coresight_device *csdev) return drvdata->trcid; }

+int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata) +{ + int trace_id; + + /* + * This will allocate a trace ID to the cpu, + * or return the one currently allocated. + * The trace id function has its own lock + */ + trace_id = coresight_trace_id_get_cpu_id(drvdata->cpu); + if (IS_VALID_CS_TRACE_ID(trace_id)) + drvdata->trcid = (u8)trace_id; + else + dev_err(&drvdata->csdev->dev, + "Failed to allocate trace ID for %s on CPU%d\n", + dev_name(&drvdata->csdev->dev), drvdata->cpu); + return trace_id; +} + +void etm4_release_trace_id(struct etmv4_drvdata *drvdata) +{ + coresight_trace_id_put_cpu_id(drvdata->cpu); +} + struct etm4_enable_arg { struct etmv4_drvdata *drvdata; int rc; @@ -720,7 +745,7 @@ static int etm4_parse_event_config(struct coresight_device *csdev, static int etm4_enable_perf(struct coresight_device *csdev, struct perf_event *event) { - int ret = 0; + int ret = 0, trace_id; struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent);

if (WARN_ON_ONCE(drvdata->cpu != smp_processor_id())) { @@ -732,6 +757,24 @@ static int etm4_enable_perf(struct coresight_device *csdev, ret = etm4_parse_event_config(csdev, event); if (ret) goto out; + + /* + * perf allocates cpu ids as part of _setup_aux() - device needs to use + * the allocated ID. This reads the current version without allocation. + * + * This does not use the trace id lock to prevent lock_dep issues + * with perf locks - we know the ID cannot change until perf shuts down + * the session + */ + trace_id = coresight_trace_id_read_cpu_id(drvdata->cpu); + if (!IS_VALID_CS_TRACE_ID(trace_id)) { + dev_err(&drvdata->csdev->dev, "Failed to set trace ID for %s on CPU%d\n", + dev_name(&drvdata->csdev->dev), drvdata->cpu); + ret = -EINVAL; + goto out; + } + drvdata->trcid = (u8)trace_id; + /* And enable it */ ret = etm4_enable_hw(drvdata);

@@ -756,6 +799,11 @@ static int etm4_enable_sysfs(struct coresight_device *csdev)

spin_lock(&drvdata->spinlock);

+ /* sysfs needs to read and allocate a trace ID */ + ret = etm4_read_alloc_trace_id(drvdata); + if (ret < 0) + goto unlock_sysfs_enable; + /* * Executing etm4_enable_hw on the cpu whose ETM is being enabled * ensures that register writes occur when cpu is powered. @@ -767,6 +815,11 @@ static int etm4_enable_sysfs(struct coresight_device *csdev) ret = arg.rc; if (!ret) drvdata->sticky_enable = true; + + if (ret) + etm4_release_trace_id(drvdata); + +unlock_sysfs_enable: spin_unlock(&drvdata->spinlock);

if (!ret) @@ -898,6 +951,11 @@ static int etm4_disable_perf(struct coresight_device *csdev, /* TRCVICTLR::SSSTATUS, bit[9] */ filters->ssstatus = (control & BIT(9));

+ /* + * perf will release trace ids when _free_aux() is + * called at the end of the session. + */ + return 0; }

@@ -923,6 +981,13 @@ static void etm4_disable_sysfs(struct coresight_device *csdev) spin_unlock(&drvdata->spinlock); cpus_read_unlock();

+ /* + * we only release trace IDs when resetting sysfs. + * This permits sysfs users to read the trace ID after the trace + * session has completed. This maintains operational behaviour with + * prior trace id allocation method + */ + dev_dbg(&csdev->dev, "ETM tracing disabled\n"); }

@@ -1565,11 +1630,6 @@ static int etm4_dying_cpu(unsigned int cpu) 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; @@ -1946,7 +2006,6 @@ static int etm4_add_coresight_dev(struct etm4_init_arg *init_arg) if (!desc.name) return -ENOMEM;

- etm4_init_trace_id(drvdata); etm4_set_default(&drvdata->config);

pdata = coresight_get_platform_data(dev); diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index 9cac848cffaf..5e62aa40ecd0 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -266,10 +266,11 @@ static ssize_t reset_store(struct device *dev, config->vmid_mask0 = 0x0; config->vmid_mask1 = 0x0;

- drvdata->trcid = drvdata->cpu + 1; - spin_unlock(&drvdata->spinlock);

+ /* for sysfs - only release trace id when resetting */ + etm4_release_trace_id(drvdata); + cscfg_csdev_reset_feats(to_coresight_device(dev));

return size; @@ -2392,6 +2393,26 @@ static struct attribute *coresight_etmv4_attrs[] = { NULL, };

+/* + * Trace ID allocated dynamically on enable - but also allocate on read + * in case sysfs or perf read before enable to ensure consistent metadata + * information for trace decode + */ +static ssize_t trctraceid_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int trace_id; + struct etmv4_drvdata *drvdata = dev_get_drvdata(dev->parent); + + trace_id = etm4_read_alloc_trace_id(drvdata); + if (trace_id < 0) + return trace_id; + + return sysfs_emit(buf, "0x%x\n", trace_id); +} +static DEVICE_ATTR_RO(trctraceid); + struct etmv4_reg { struct coresight_device *csdev; u32 offset; @@ -2528,7 +2549,7 @@ static struct attribute *coresight_etmv4_mgmt_attrs[] = { coresight_etm4x_reg(trcpidr3, TRCPIDR3), coresight_etm4x_reg(trcoslsr, TRCOSLSR), coresight_etm4x_reg(trcconfig, TRCCONFIGR), - coresight_etm4x_reg(trctraceid, TRCTRACEIDR), + &dev_attr_trctraceid.attr, coresight_etm4x_reg(trcdevarch, TRCDEVARCH), NULL, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 4b21bb79f168..434f4e95ee17 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -1095,4 +1095,7 @@ static inline bool etm4x_is_ete(struct etmv4_drvdata *drvdata) { return drvdata->arch >= ETM_ARCH_ETE; } + +int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata); +void etm4_release_trace_id(struct etmv4_drvdata *drvdata); #endif

CoreSight sources provide a callback (.trace_id) in the standard source ops which returns the ID to the core code. This was used to check that sources all had a unique Trace ID.

Uniqueness is now gauranteed by the Trace ID allocation system, and the check code has been removed from the core.

This patch removes the unneeded and unused .trace_id source ops from the ops structure and implementations in etm3x, etm4x and stm.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com --- drivers/hwtracing/coresight/coresight-etm.h | 1 - .../coresight/coresight-etm3x-core.c | 37 ------------------- .../coresight/coresight-etm4x-core.c | 8 ---- drivers/hwtracing/coresight/coresight-stm.c | 8 ---- include/linux/coresight.h | 3 -- 5 files changed, 57 deletions(-)

diff --git a/drivers/hwtracing/coresight/coresight-etm.h b/drivers/hwtracing/coresight/coresight-etm.h index 3667428d38b6..9a0d08b092ae 100644 --- a/drivers/hwtracing/coresight/coresight-etm.h +++ b/drivers/hwtracing/coresight/coresight-etm.h @@ -283,7 +283,6 @@ static inline unsigned int etm_readl(struct etm_drvdata *drvdata, u32 off) }

extern const struct attribute_group *coresight_etm_groups[]; -int etm_get_trace_id(struct etm_drvdata *drvdata); void etm_set_default(struct etm_config *config); void etm_config_trace_mode(struct etm_config *config); struct etm_config *get_etm_config(struct etm_drvdata *drvdata); diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 090b6fbf6305..afc57195ee52 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -455,42 +455,6 @@ static int etm_cpu_id(struct coresight_device *csdev) return drvdata->cpu; }

-int etm_get_trace_id(struct etm_drvdata *drvdata) -{ - unsigned long flags; - int trace_id = -1; - struct device *etm_dev; - - if (!drvdata) - goto out; - - etm_dev = drvdata->csdev->dev.parent; - if (!local_read(&drvdata->mode)) - return drvdata->traceid; - - pm_runtime_get_sync(etm_dev); - - spin_lock_irqsave(&drvdata->spinlock, flags); - - CS_UNLOCK(drvdata->base); - trace_id = (etm_readl(drvdata, ETMTRACEIDR) & ETM_TRACEID_MASK); - CS_LOCK(drvdata->base); - - spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(etm_dev); - -out: - return trace_id; - -} - -static int etm_trace_id(struct coresight_device *csdev) -{ - struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return etm_get_trace_id(drvdata); -} - int etm_read_alloc_trace_id(struct etm_drvdata *drvdata) { int trace_id; @@ -737,7 +701,6 @@ static void etm_disable(struct coresight_device *csdev,

static const struct coresight_ops_source etm_source_ops = { .cpu_id = etm_cpu_id, - .trace_id = etm_trace_id, .enable = etm_enable, .disable = etm_disable, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 0656577d7e30..bc576e254b8f 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -231,13 +231,6 @@ static int etm4_cpu_id(struct coresight_device *csdev) 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; -} - int etm4_read_alloc_trace_id(struct etmv4_drvdata *drvdata) { int trace_id; @@ -1021,7 +1014,6 @@ static void etm4_disable(struct coresight_device *csdev,

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, }; diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 6af1b996af6f..66a614c5492c 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -281,15 +281,7 @@ static void stm_disable(struct coresight_device *csdev, } }

-static int stm_trace_id(struct coresight_device *csdev) -{ - struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - return drvdata->traceid; -} - static const struct coresight_ops_source stm_source_ops = { - .trace_id = stm_trace_id, .enable = stm_enable, .disable = stm_disable, }; diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 1554021231f9..e241eb88dfb9 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -314,14 +314,11 @@ struct coresight_ops_link { * Operations available for sources. * @cpu_id: returns the value of the CPU number this component * is associated to. - * @trace_id: returns the value of the component's trace ID as known - * to the HW. * @enable: enables tracing for a source. * @disable: disables tracing for a source. */ struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); - int (*trace_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, u32 mode); void (*disable)(struct coresight_device *csdev,

The information to associate Trace ID and CPU will be changing.

Drivers will start outputting this as a hardware ID packet in the data file which if present will be used in preference to the AUXINFO values.

To prepare for this we provide a helper functions to do the individual ID mapping, and one to extract the IDs from the completed metadata blocks.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: James Clark james.clark@arm.com Acked-by: Suzuki K Poulose suzuki.poulose@arm.com --- tools/include/linux/coresight-pmu.h | 5 ++ tools/perf/util/cs-etm.c | 92 +++++++++++++++++++---------- tools/perf/util/cs-etm.h | 14 ++++- 3 files changed, 77 insertions(+), 34 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 6c2fd6cc5a98..db9c7c0abb6a 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -7,9 +7,14 @@ #ifndef _LINUX_CORESIGHT_PMU_H #define _LINUX_CORESIGHT_PMU_H

+#include <linux/bits.h> + #define CORESIGHT_ETM_PMU_NAME "cs_etm" #define CORESIGHT_ETM_PMU_SEED 0x10

+/* CoreSight trace ID is currently the bottom 7 bits of the value */ +#define CORESIGHT_TRACE_ID_VAL_MASK GENMASK(6, 0) + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 16db965ac995..11026c9694a4 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -193,6 +193,30 @@ int cs_etm__get_pid_fmt(u8 trace_chan_id, u64 *pid_fmt) return 0; }

+static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata) +{ + struct int_node *inode; + + /* Get an RB node for this CPU */ + inode = intlist__findnew(traceid_list, trace_chan_id); + + /* Something went wrong, no need to continue */ + if (!inode) + return -ENOMEM; + + /* + * The node for that CPU should not be taken. + * Back out if that's the case. + */ + if (inode->priv) + return -EINVAL; + + /* All good, associate the traceID with the metadata pointer */ + inode->priv = cpu_metadata; + + return 0; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { @@ -2881,18 +2905,47 @@ static int cs_etm__queue_aux_records(struct perf_session *session) return 0; }

+/* map trace ids to correct metadata block, from information in metadata */ +static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) +{ + u64 cs_etm_magic; + u8 trace_chan_id; + int i, err; + + for (i = 0; i < num_cpu; i++) { + cs_etm_magic = metadata[i][CS_ETM_MAGIC]; + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + default: + /* unknown magic number */ + return -EINVAL; + } + err = cs_etm__map_trace_id(trace_chan_id, metadata[i]); + if (err) + return err; + } + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; struct cs_etm_auxtrace *etm = NULL; - struct int_node *inode; unsigned int pmu_type; int event_header_size = sizeof(struct perf_event_header); int info_header_size; int total_size = auxtrace_info->header.size; int priv_size = 0; - int num_cpu, trcidr_idx; + int num_cpu; int err = 0; int i, j; u64 *ptr, *hdr = NULL; @@ -2962,23 +3015,13 @@ int cs_etm__process_auxtrace_info(union perf_event *event, cs_etm__create_meta_blk(ptr, &i, CS_ETM_PRIV_MAX, CS_ETM_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETM_ETMTRACEIDR; - } else if (ptr[i] == __perf_cs_etmv4_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETMV4_PRIV_MAX, CS_ETMV4_NR_TRC_PARAMS_V0); - - /* The traceID is our handle */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else if (ptr[i] == __perf_cs_ete_magic) { metadata[j] = cs_etm__create_meta_blk(ptr, &i, CS_ETE_PRIV_MAX, -1); - - /* ETE shares first part of metadata with ETMv4 */ - trcidr_idx = CS_ETMV4_TRCTRACEIDR; } else { ui__error("CS ETM Trace: Unrecognised magic number %#"PRIx64". File could be from a newer version of perf.\n", ptr[i]); @@ -2990,26 +3033,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, err = -ENOMEM; goto err_free_metadata; } - - /* Get an RB node for this CPU */ - inode = intlist__findnew(traceid_list, metadata[j][trcidr_idx]); - - /* Something went wrong, no need to continue */ - if (!inode) { - err = -ENOMEM; - goto err_free_metadata; - } - - /* - * The node for that CPU should not be taken. - * Back out if that's the case. - */ - if (inode->priv) { - err = -EINVAL; - goto err_free_metadata; - } - /* All good, associate the traceID with the metadata pointer */ - inode->priv = metadata[j]; }

/* @@ -3090,6 +3113,11 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread;

+ /* before aux records are queued, need to map metadata to trace IDs */ + err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + if (err) + goto err_delete_thread; + err = cs_etm__queue_aux_records(session); if (err) goto err_delete_thread; diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 90c83f932d9a..712a6f855f0e 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -28,13 +28,17 @@ enum { /* * Update the version for new format. * - * New version 1 format adds a param count to the per cpu metadata. + * Version 1: format adds a param count to the per cpu metadata. * This allows easy adding of new metadata parameters. * Requires that new params always added after current ones. * Also allows client reader to handle file versions that are different by * checking the number of params in the file vs the number expected. + * + * Version 2: Drivers will use PERF_RECORD_AUX_OUTPUT_HW_ID to output + * CoreSight Trace ID. ...TRACEIDR metadata will be set to unused ID. */ -#define CS_HEADER_CURRENT_VERSION 1 +#define CS_HEADER_CURRENT_VERSION 2 +#define CS_AUX_HW_ID_VERSION_MIN 2

/* Beginning of header common to both ETMv3 and V4 */ enum { @@ -85,6 +89,12 @@ enum { CS_ETE_PRIV_MAX };

+/* + * Check for valid CoreSight trace ID. If an invalid value is present in the metadata, + * then IDs are present in the hardware ID packet in the data file. + */ +#define CS_IS_VALID_TRACE_ID(id) ((id > 0) && (id < 0x70)) + /* * ETMv3 exception encoding number: * See Embedded Trace Macrocell specification (ARM IHI 0014Q)

CoreSight trace being updated to use the perf_report_aux_output_id() in a similar way to intel-pt.

This function in needs export visibility to allow it to be called from kernel loadable modules, which CoreSight may configured to be built as.

Signed-off-by: Mike Leach mike.leach@linaro.org Acked-by: Suzuki K Poulose suzuki.poulose@arm.com --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c index 4ec3717003d5..ad388552f1d5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9231,6 +9231,7 @@ void perf_report_aux_output_id(struct perf_event *event, u64 hw_id)

perf_output_end(&handle); } +EXPORT_SYMBOL_GPL(perf_report_aux_output_id);

static int __perf_event_account_interrupt(struct perf_event *event, int throttle)

When using dynamically assigned CoreSight trace IDs the drivers can output the ID / CPU association as a PERF_RECORD_AUX_OUTPUT_HW_ID packet.

Update cs-etm decoder to handle this packet by setting the CPU/Trace ID mapping.

Signed-off-by: Mike Leach mike.leach@linaro.org Reviewed-by: James Clark james.clark@arm.com Acked-by: Suzuki K Poulose suzuki.poulose@arm.com --- tools/include/linux/coresight-pmu.h | 15 ++ .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 7 + tools/perf/util/cs-etm.c | 248 ++++++++++++++++-- 3 files changed, 251 insertions(+), 19 deletions(-)

diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index 307f357defe9..57ba1abf1224 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -32,6 +32,9 @@ */ #define CORESIGHT_TRACE_ID_UNUSED_FLAG BIT(31)

+/* Value to set for unused trace ID values */ +#define CORESIGHT_TRACE_ID_UNUSED_VAL 0x7F + /* * Below are the definition of bit offsets for perf option, and works as * arbitrary values for all ETM versions. @@ -56,4 +59,16 @@ #define ETM4_CFG_BIT_RETSTK 12 #define ETM4_CFG_BIT_VMID_OPT 15

+/* + * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload. + * Used to associate a CPU with the CoreSight Trace ID. + * [07:00] - Trace ID - uses 8 bits to make value easy to read in file. + * [59:08] - Unused (SBZ) + * [63:60] - Version + */ +#define CS_AUX_HW_ID_TRACE_ID_MASK GENMASK_ULL(7, 0) +#define CS_AUX_HW_ID_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_CURR_VERSION 0 + #endif diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c index 31fa3b45134a..fa3aa9c0fb2e 100644 --- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c +++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c @@ -625,6 +625,7 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, switch (t_params->protocol) { case CS_ETM_PROTO_ETMV3: case CS_ETM_PROTO_PTM: + csid = (t_params->etmv3.reg_idr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_etmv3_config(t_params, &config_etmv3); decoder->decoder_name = (t_params->protocol == CS_ETM_PROTO_ETMV3) ? OCSD_BUILTIN_DCD_ETMV3 : @@ -632,11 +633,13 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, trace_config = &config_etmv3; break; case CS_ETM_PROTO_ETMV4i: + csid = (t_params->etmv4.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_etmv4_config(t_params, &trace_config_etmv4); decoder->decoder_name = OCSD_BUILTIN_DCD_ETMV4I; trace_config = &trace_config_etmv4; break; case CS_ETM_PROTO_ETE: + csid = (t_params->ete.reg_traceidr & CORESIGHT_TRACE_ID_VAL_MASK); cs_etm_decoder__gen_ete_config(t_params, &trace_config_ete); decoder->decoder_name = OCSD_BUILTIN_DCD_ETE; trace_config = &trace_config_ete; @@ -645,6 +648,10 @@ cs_etm_decoder__create_etm_decoder(struct cs_etm_decoder_params *d_params, return -1; }

+ /* if the CPU has no trace ID associated, no decoder needed */ + if (csid == CORESIGHT_TRACE_ID_UNUSED_VAL) + return 0; + if (d_params->operation == CS_ETM_OPERATION_DECODE) { if (ocsd_dt_create_decoder(decoder->dcd_tree, decoder->decoder_name, diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 11026c9694a4..f9f7d16a55d1 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -217,6 +217,143 @@ static int cs_etm__map_trace_id(u8 trace_chan_id, u64 *cpu_metadata) return 0; }

+static int cs_etm__metadata_get_trace_id(u8 *trace_chan_id, u64 *cpu_metadata) +{ + u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC]; + + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + *trace_chan_id = (u8)(cpu_metadata[CS_ETM_ETMTRACEIDR] & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + *trace_chan_id = (u8)(cpu_metadata[CS_ETMV4_TRCTRACEIDR] & + CORESIGHT_TRACE_ID_VAL_MASK); + break; + default: + return -EINVAL; + } + return 0; +} + +/* + * update metadata trace ID from the value found in the AUX_HW_INFO packet. + * This will also clear the CORESIGHT_TRACE_ID_UNUSED_FLAG flag if present. + */ +static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata) +{ + u64 cs_etm_magic = cpu_metadata[CS_ETM_MAGIC]; + + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + cpu_metadata[CS_ETM_ETMTRACEIDR] = trace_chan_id; + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + cpu_metadata[CS_ETMV4_TRCTRACEIDR] = trace_chan_id; + break; + + default: + return -EINVAL; + } + return 0; +} + +/* + * FIELD_GET (linux/bitfield.h) not available outside kernel code, + * and the header contains too many dependencies to just copy over, + * so roll our own based on the original + */ +#define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define FIELD_GET(_mask, _reg) \ + ({ \ + (typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask)); \ + }) + +/* + * Handle the PERF_RECORD_AUX_OUTPUT_HW_ID event. + * + * The payload associates the Trace ID and the CPU. + * The routine is tolerant of seeing multiple packets with the same association, + * but a CPU / Trace ID association changing during a session is an error. + */ +static int cs_etm__process_aux_output_hw_id(struct perf_session *session, + union perf_event *event) +{ + struct cs_etm_auxtrace *etm; + struct perf_sample sample; + struct int_node *inode; + struct evsel *evsel; + u64 *cpu_data; + u64 hw_id; + int cpu, version, err; + u8 trace_chan_id, curr_chan_id; + + /* extract and parse the HW ID */ + hw_id = event->aux_output_hw_id.hw_id; + version = FIELD_GET(CS_AUX_HW_ID_VERSION_MASK, hw_id); + trace_chan_id = FIELD_GET(CS_AUX_HW_ID_TRACE_ID_MASK, hw_id); + + /* check that we can handle this version */ + if (version > CS_AUX_HW_ID_CURR_VERSION) + return -EINVAL; + + /* get access to the etm metadata */ + etm = container_of(session->auxtrace, struct cs_etm_auxtrace, auxtrace); + if (!etm || !etm->metadata) + return -EINVAL; + + /* parse the sample to get the CPU */ + evsel = evlist__event2evsel(session->evlist, event); + if (!evsel) + return -EINVAL; + err = evsel__parse_sample(evsel, event, &sample); + if (err) + return err; + cpu = sample.cpu; + if (cpu == -1) { + /* no CPU in the sample - possibly recorded with an old version of perf */ + pr_err("CS_ETM: no CPU AUX_OUTPUT_HW_ID sample. Use compatible perf to record."); + return -EINVAL; + } + + /* See if the ID is mapped to a CPU, and it matches the current CPU */ + inode = intlist__find(traceid_list, trace_chan_id); + if (inode) { + cpu_data = inode->priv; + if ((int)cpu_data[CS_ETM_CPU] != cpu) { + pr_err("CS_ETM: map mismatch between HW_ID packet CPU and Trace ID\n"); + return -EINVAL; + } + + /* check that the mapped ID matches */ + err = cs_etm__metadata_get_trace_id(&curr_chan_id, cpu_data); + if (err) + return err; + if (curr_chan_id != trace_chan_id) { + pr_err("CS_ETM: mismatch between CPU trace ID and HW_ID packet ID\n"); + return -EINVAL; + } + + /* mapped and matched - return OK */ + return 0; + } + + /* not one we've seen before - lets map it */ + cpu_data = etm->metadata[cpu]; + err = cs_etm__map_trace_id(trace_chan_id, cpu_data); + if (err) + return err; + + /* + * if we are picking up the association from the packet, need to plug + * the correct trace ID into the metadata for setting up decoders later. + */ + err = cs_etm__metadata_set_trace_id(trace_chan_id, cpu_data); + return err; +} + void cs_etm__etmq_set_traceid_queue_timestamp(struct cs_etm_queue *etmq, u8 trace_chan_id) { @@ -2662,7 +2799,7 @@ static void cs_etm__print_auxtrace_info(__u64 *val, int num) for (i = CS_HEADER_VERSION_MAX; cpu < num; cpu++) { if (version == 0) err = cs_etm__print_cpu_metadata_v0(val, &i); - else if (version == 1) + else if (version == 1 || version == 2) err = cs_etm__print_cpu_metadata_v1(val, &i); if (err) return; @@ -2774,11 +2911,16 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o }

/* - * In per-thread mode, CPU is set to -1, but TID will be set instead. See - * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match. + * In per-thread mode, auxtrace CPU is set to -1, but TID will be set instead. See + * auxtrace_mmap_params__set_idx(). However, the sample AUX event will contain a + * CPU as we set this always for the AUX_OUTPUT_HW_ID event. + * So now compare only TIDs if auxtrace CPU is -1, and CPUs if auxtrace CPU is not -1. + * Return 'not found' if mismatch. */ - if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) || - auxtrace_event->cpu != sample->cpu) + if (auxtrace_event->cpu == (__u32) -1) { + if (auxtrace_event->tid != sample->tid) + return 1; + } else if (auxtrace_event->cpu != sample->cpu) return 1;

if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) { @@ -2827,6 +2969,17 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o return 1; }

+static int cs_etm__process_aux_hw_id_cb(struct perf_session *session, union perf_event *event, + u64 offset __maybe_unused, void *data __maybe_unused) +{ + /* look to handle PERF_RECORD_AUX_OUTPUT_HW_ID early to ensure decoders can be set up */ + if (event->header.type == PERF_RECORD_AUX_OUTPUT_HW_ID) { + (*(int *)data)++; /* increment found count */ + return cs_etm__process_aux_output_hw_id(session, event); + } + return 0; +} + static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event, u64 offset __maybe_unused, void *data __maybe_unused) { @@ -2916,13 +3069,13 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) cs_etm_magic = metadata[i][CS_ETM_MAGIC]; switch (cs_etm_magic) { case __perf_cs_etmv3_magic: - trace_chan_id = (u8)((metadata[i][CS_ETM_ETMTRACEIDR]) & - CORESIGHT_TRACE_ID_VAL_MASK); + metadata[i][CS_ETM_ETMTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK; + trace_chan_id = (u8)(metadata[i][CS_ETM_ETMTRACEIDR]); break; case __perf_cs_etmv4_magic: case __perf_cs_ete_magic: - trace_chan_id = (u8)((metadata[i][CS_ETMV4_TRCTRACEIDR]) & - CORESIGHT_TRACE_ID_VAL_MASK); + metadata[i][CS_ETMV4_TRCTRACEIDR] &= CORESIGHT_TRACE_ID_VAL_MASK; + trace_chan_id = (u8)(metadata[i][CS_ETMV4_TRCTRACEIDR]); break; default: /* unknown magic number */ @@ -2935,6 +3088,35 @@ static int cs_etm__map_trace_ids_metadata(int num_cpu, u64 **metadata) return 0; }

+/* + * If we found AUX_HW_ID packets, then set any metadata marked as unused to the + * unused value to reduce the number of unneeded decoders created. + */ +static int cs_etm__clear_unused_trace_ids_metadata(int num_cpu, u64 **metadata) +{ + u64 cs_etm_magic; + int i; + + for (i = 0; i < num_cpu; i++) { + cs_etm_magic = metadata[i][CS_ETM_MAGIC]; + switch (cs_etm_magic) { + case __perf_cs_etmv3_magic: + if (metadata[i][CS_ETM_ETMTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG) + metadata[i][CS_ETM_ETMTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL; + break; + case __perf_cs_etmv4_magic: + case __perf_cs_ete_magic: + if (metadata[i][CS_ETMV4_TRCTRACEIDR] & CORESIGHT_TRACE_ID_UNUSED_FLAG) + metadata[i][CS_ETMV4_TRCTRACEIDR] = CORESIGHT_TRACE_ID_UNUSED_VAL; + break; + default: + /* unknown magic number */ + return -EINVAL; + } + } + return 0; +} + int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session) { @@ -2947,6 +3129,7 @@ int cs_etm__process_auxtrace_info(union perf_event *event, int priv_size = 0; int num_cpu; int err = 0; + int aux_hw_id_found; int i, j; u64 *ptr, *hdr = NULL; u64 **metadata = NULL; @@ -3113,8 +3296,43 @@ int cs_etm__process_auxtrace_info(union perf_event *event, if (err) goto err_delete_thread;

- /* before aux records are queued, need to map metadata to trace IDs */ - err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + /* + * Map Trace ID values to CPU metadata. + * + * Trace metadata will always contain Trace ID values from the legacy algorithm. If the + * files has been recorded by a "new" perf updated to handle AUX_HW_ID then the metadata + * ID value will also have the CORESIGHT_TRACE_ID_UNUSED_FLAG set. + * + * The updated kernel drivers that use AUX_HW_ID to sent Trace IDs will attempt to use + * the same IDs as the old algorithm as far as is possible, unless there are clashes + * in which case a different value will be used. This means an older perf may still + * be able to record and read files generate on a newer system. + * + * For a perf able to interpret AUX_HW_ID packets we first check for the presence of + * those packets. If they are there then the values will be mapped and plugged into + * the metadata. We then set any remaining metadata values with the used flag to a + * value CORESIGHT_TRACE_ID_UNUSED_VAL - which indicates no decoder is required. + * + * If no AUX_HW_ID packets are present - which means a file recorded on an old kernel + * then we map Trace ID values to CPU directly from the metadata - clearing any unused + * flags if present. + */ + + /* first scan for AUX_OUTPUT_HW_ID records to map trace ID values to CPU metadata */ + aux_hw_id_found = 0; + err = perf_session__peek_events(session, session->header.data_offset, + session->header.data_size, + cs_etm__process_aux_hw_id_cb, &aux_hw_id_found); + if (err) + goto err_delete_thread; + + /* if HW ID found then clear any unused metadata ID values */ + if (aux_hw_id_found) + err = cs_etm__clear_unused_trace_ids_metadata(num_cpu, metadata); + /* otherwise, this is a file with metadata values only, map from metadata */ + else + err = cs_etm__map_trace_ids_metadata(num_cpu, metadata); + if (err) goto err_delete_thread;

@@ -3123,14 +3341,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event, goto err_delete_thread;

etm->data_queued = etm->queues.populated; - /* - * Print warning in pipe mode, see cs_etm__process_auxtrace_event() and - * cs_etm__queue_aux_fragment() for details relating to limitations. - */ - if (!etm->data_queued) - pr_warning("CS ETM warning: Coresight decode and TRBE support requires random file access.\n" - "Continuing with best effort decoding in piped mode.\n\n"); - return 0;

err_delete_thread:

Adds in a number of pr_debug macros to allow the debugging and test of the trace ID allocation system.

Signed-off-by: Mike Leach mike.leach@linaro.org --- .../hwtracing/coresight/coresight-trace-id.c | 33 +++++++++++++++++++ 1 file changed, 33 insertions(+)

diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 9b85c376cb12..367bbfb4c213 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -24,6 +24,27 @@ static atomic_t perf_cs_etm_session_active = ATOMIC_INIT(0); /* lock to protect id_map and cpu data */ static DEFINE_SPINLOCK(id_map_lock);

+/* #define TRACE_ID_DEBUG 1 */ +#if defined(TRACE_ID_DEBUG) || defined(CONFIG_COMPILE_TEST) + +static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, + const char *func_name) +{ + pr_debug("%s id_map::\n", func_name); + pr_debug("Used = %*pb\n", CORESIGHT_TRACE_IDS_MAX, id_map->used_ids); + pr_debug("Pend = %*pb\n", CORESIGHT_TRACE_IDS_MAX, id_map->pend_rel_ids); +} +#define DUMP_ID_MAP(map) coresight_trace_id_dump_table(map, __func__) +#define DUMP_ID_CPU(cpu, id) pr_debug("%s called; cpu=%d, id=%d\n", __func__, cpu, id) +#define DUMP_ID(id) pr_debug("%s called; id=%d\n", __func__, id) +#define PERF_SESSION(n) pr_debug("%s perf count %d\n", __func__, n) +#else +#define DUMP_ID_MAP(map) +#define DUMP_ID(id) +#define DUMP_ID_CPU(cpu, id) +#define PERF_SESSION(n) +#endif + /* unlocked read of current trace ID value for given CPU */ static int _coresight_trace_id_read_cpu_id(int cpu) { @@ -127,6 +148,7 @@ static void coresight_trace_id_release_all_pending(void) cpumask_clear_cpu(cpu, &cpu_id_release_pending); } spin_unlock_irqrestore(&id_map_lock, flags); + DUMP_ID_MAP(id_map); }

static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) @@ -168,6 +190,8 @@ static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_ get_cpu_id_out_unlock: spin_unlock_irqrestore(&id_map_lock, flags);

+ DUMP_ID_CPU(cpu, id); + DUMP_ID_MAP(id_map); return id; }

@@ -194,6 +218,8 @@ static void coresight_trace_id_map_put_cpu_id(int cpu, struct coresight_trace_id }

spin_unlock_irqrestore(&id_map_lock, flags); + DUMP_ID_CPU(cpu, id); + DUMP_ID_MAP(id_map); }

static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *id_map) @@ -206,6 +232,8 @@ static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *i id = coresight_trace_id_alloc_new_id(id_map, 0, true); spin_unlock_irqrestore(&id_map_lock, flags);

+ DUMP_ID(id); + DUMP_ID_MAP(id_map); return id; }

@@ -216,6 +244,9 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * spin_lock_irqsave(&id_map_lock, flags); coresight_trace_id_free(id, id_map); spin_unlock_irqrestore(&id_map_lock, flags); + + DUMP_ID(id); + DUMP_ID_MAP(id_map); }

/* API functions */ @@ -253,6 +284,7 @@ EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); void coresight_trace_id_perf_start(void) { atomic_inc(&perf_cs_etm_session_active); + PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start);

@@ -260,6 +292,7 @@ void coresight_trace_id_perf_stop(void) { if (!atomic_dec_return(&perf_cs_etm_session_active)) coresight_trace_id_release_all_pending(); + PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop);