From daca644d0c9e06752c80e10411d89e087fa9a24e Mon Sep 17 00:00:00 2001 From: Javier Carrasco Date: Thu, 8 Aug 2024 17:12:37 +0200 Subject: [PATCH 01/13] coresight: cti: use device_* to iterate over device child nodes Drop the manual access to the fwnode of the device to iterate over its child nodes. `device_for_each_child_node` macro provides direct access to the child nodes, and given that they are only required within the loop, the scoped variant of the macro can be used. Use the `device_for_each_child_node_scoped` macro to iterate over the direct child nodes of the device. Signed-off-by: Javier Carrasco Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240808-device_child_node_access-v2-1-fc757cc76650@gmail.com --- drivers/hwtracing/coresight/coresight-cti-platform.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-cti-platform.c b/drivers/hwtracing/coresight/coresight-cti-platform.c index ccef04f27f12..d0ae10bf6128 100644 --- a/drivers/hwtracing/coresight/coresight-cti-platform.c +++ b/drivers/hwtracing/coresight/coresight-cti-platform.c @@ -416,20 +416,16 @@ 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)) + if (IS_ERR_OR_NULL(dev_fwnode(dev))) return -EINVAL; - fwnode_for_each_child_node(fwnode, child) { + device_for_each_child_node_scoped(dev, child) { if (cti_plat_node_name_eq(child, CTI_DT_CONNS)) - rc = cti_plat_create_connection(dev, drvdata, - child); + rc = cti_plat_create_connection(dev, drvdata, child); if (rc != 0) break; } - fwnode_handle_put(child); return rc; } From 14f5fa9b5fcbe2b3d5098893aba6ad62254d2ef6 Mon Sep 17 00:00:00 2001 From: Jie Gan Date: Mon, 12 Aug 2024 12:30:43 +0800 Subject: [PATCH 02/13] Coresight: Set correct cs_mode for TPDM to fix disable issue The coresight_disable_source_sysfs function should verify the mode of the coresight device before disabling the source. However, the mode for the TPDM device is always set to CS_MODE_DISABLED, resulting in the check consistently failing. As a result, TPDM cannot be properly disabled. Configure CS_MODE_SYSFS/CS_MODE_PERF during the enablement. Configure CS_MODE_DISABLED during the disablement. Fixes: b3c71626a933 ("Coresight: Add coresight TPDM source driver") Signed-off-by: Jie Gan Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240812043043.2890694-1-quic_jiegan@quicinc.com --- drivers/hwtracing/coresight/coresight-tpdm.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c index 0726f8842552..5c5a4b3fe687 100644 --- a/drivers/hwtracing/coresight/coresight-tpdm.c +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -449,6 +449,11 @@ static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event, return -EBUSY; } + if (!coresight_take_mode(csdev, mode)) { + spin_unlock(&drvdata->spinlock); + return -EBUSY; + } + __tpdm_enable(drvdata); drvdata->enable = true; spin_unlock(&drvdata->spinlock); @@ -506,6 +511,7 @@ static void tpdm_disable(struct coresight_device *csdev, } __tpdm_disable(drvdata); + coresight_set_mode(csdev, CS_MODE_DISABLED); drvdata->enable = false; spin_unlock(&drvdata->spinlock); From e6b64cda393efd84709ab3df2e42d36d36d7553e Mon Sep 17 00:00:00 2001 From: Jie Gan Date: Mon, 12 Aug 2024 12:28:44 +0800 Subject: [PATCH 03/13] Coresight: Set correct cs_mode for dummy source to fix disable issue The coresight_disable_source_sysfs function should verify the mode of the coresight device before disabling the source. However, the mode for the dummy source device is always set to CS_MODE_DISABLED, resulting in the check consistently failing. As a result, dummy source cannot be properly disabled. Configure CS_MODE_SYSFS/CS_MODE_PERF during the enablement. Configure CS_MODE_DISABLED during the disablement. Fixes: 9d3ba0b6c056 ("Coresight: Add coresight dummy driver") Signed-off-by: Jie Gan Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240812042844.2890115-1-quic_jiegan@quicinc.com --- drivers/hwtracing/coresight/coresight-dummy.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c index ac70c0b491be..dab389a5507c 100644 --- a/drivers/hwtracing/coresight/coresight-dummy.c +++ b/drivers/hwtracing/coresight/coresight-dummy.c @@ -23,6 +23,9 @@ DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink"); static int dummy_source_enable(struct coresight_device *csdev, struct perf_event *event, enum cs_mode mode) { + if (!coresight_take_mode(csdev, mode)) + return -EBUSY; + dev_dbg(csdev->dev.parent, "Dummy source enabled\n"); return 0; @@ -31,6 +34,7 @@ static int dummy_source_enable(struct coresight_device *csdev, static void dummy_source_disable(struct coresight_device *csdev, struct perf_event *event) { + coresight_set_mode(csdev, CS_MODE_DISABLED); dev_dbg(csdev->dev.parent, "Dummy source disabled\n"); } From c58dc5a1f886f2fcc1133746d0cbaa1fe7fd44ff Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Tue, 2 Jul 2024 14:28:46 +0100 Subject: [PATCH 04/13] coresight: tmc: sg: Do not leak sg_table Running perf with cs_etm on Juno triggers the following kmemleak warning ! :~# cat /sys/kernel/debug/kmemleak unreferenced object 0xffffff8806b6d720 (size 96): comm "perf", pid 562, jiffies 4297810960 hex dump (first 32 bytes): 38 d8 13 07 88 ff ff ff 00 d0 9e 85 c0 ff ff ff 8............... 00 10 00 88 c0 ff ff ff 00 f0 ff f7 ff 00 00 00 ................ backtrace (crc 1dbf6e00): [] kmemleak_alloc+0xbc/0xd8 [] kmalloc_trace_noprof+0x220/0x2e8 [] tmc_alloc_sg_table+0x48/0x208 [coresight_tmc] [] tmc_etr_alloc_sg_buf+0xac/0x240 [coresight_tmc] [] tmc_alloc_etr_buf.constprop.0+0x1f0/0x260 [coresight_tmc] [] alloc_etr_buf.constprop.0.isra.0+0x74/0xa8 [coresight_tmc] [] tmc_alloc_etr_buffer+0x110/0x260 [coresight_tmc] [] etm_setup_aux+0x204/0x3b0 [coresight] [] rb_alloc_aux+0x20c/0x318 [] perf_mmap+0x2e4/0x7a0 [] mmap_region+0x3b0/0xa08 [] do_mmap+0x3a0/0x500 [] vm_mmap_pgoff+0x100/0x1d0 [] ksys_mmap_pgoff+0xb8/0x110 [] __arm64_sys_mmap+0x38/0x58 [] invoke_syscall.constprop.0+0x58/0x100 This due to the fact that we do not free the "sg_table" itself while freeing up the SG table and data pages. Fix this by freeing the sg_table in tmc_free_sg_table(). Fixes: 99443ea19e8b ("coresight: Add generic TMC sg table framework") Cc: Mike Leach Cc: James Clark Signed-off-by: Suzuki K Poulose Reviewed-by: Anshuman Khandual Link: https://lore.kernel.org/r/20240702132846.1677261-1-suzuki.poulose@arm.com --- drivers/hwtracing/coresight/coresight-tmc-etr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index e75428fa1592..610ad51cda65 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -261,6 +261,7 @@ void tmc_free_sg_table(struct tmc_sg_table *sg_table) { tmc_free_table_pages(sg_table); tmc_free_data_pages(sg_table); + kfree(sg_table); } EXPORT_SYMBOL_GPL(tmc_free_sg_table); @@ -342,7 +343,6 @@ struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev, rc = tmc_alloc_table_pages(sg_table); if (rc) { tmc_free_sg_table(sg_table); - kfree(sg_table); return ERR_PTR(rc); } From 34172002bdac28dabbb846f191a86454bb226c7a Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:51 +0100 Subject: [PATCH 05/13] coresight: Remove unused ETM Perf stubs This file is never included anywhere if CONFIG_CORESIGHT is not set so they are unused and aren't currently compile tested with any config so remove them. Reviewed-by: Anshuman Khandual Reviewed-by: Mike Leach Signed-off-by: James Clark Tested-by: Leo Yan Tested-by: Ganapatrao Kulkarni Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-10-james.clark@linaro.org --- .../hwtracing/coresight/coresight-etm-perf.h | 18 ------------------ 1 file changed, 18 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.h b/drivers/hwtracing/coresight/coresight-etm-perf.h index bebbadee2ceb..744531158d6b 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.h +++ b/drivers/hwtracing/coresight/coresight-etm-perf.h @@ -62,7 +62,6 @@ struct etm_event_data { struct list_head * __percpu *path; }; -#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); @@ -77,23 +76,6 @@ static inline void *etm_perf_sink_config(struct perf_output_handle *handle) 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; } -int etm_perf_add_symlink_sink(struct coresight_device *csdev) -{ return -EINVAL; } -void etm_perf_del_symlink_sink(struct coresight_device *csdev) {} -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); From eda1d11979c03f0104ca59ec4a0478cd52fa20de Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:52 +0100 Subject: [PATCH 06/13] coresight: Clarify comments around the PID of the sink owner "Process being monitored" and "pid of the process to monitor" imply that this would be the same PID if there were two sessions targeting the same process. But this is actually the PID of the process that did the Perf event open call, rather than the target of the session. So update the comments to make this clearer. Reviewed-by: Anshuman Khandual Reviewed-by: Mike Leach Signed-off-by: James Clark Tested-by: Leo Yan Tested-by: Ganapatrao Kulkarni Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-11-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++-- drivers/hwtracing/coresight/coresight-tmc.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 610ad51cda65..a48bb85d0e7f 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -36,7 +36,8 @@ struct etr_buf_hw { * etr_perf_buffer - Perf buffer used for ETR * @drvdata - The ETR drvdaga this buffer has been allocated for. * @etr_buf - Actual buffer used by the ETR - * @pid - The PID this etr_perf_buffer belongs to. + * @pid - The PID of the session owner that etr_perf_buffer + * belongs to. * @snaphost - Perf session mode * @nr_pages - Number of pages in the ring buffer. * @pages - Array of Pages in the ring buffer. @@ -1662,7 +1663,7 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) goto unlock_out; } - /* Get a handle on the pid of the process to monitor */ + /* Get a handle on the pid of the session owner */ pid = etr_perf->pid; /* Do not proceed if this device is associated with another session */ diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index c77763b49de0..2671926be62a 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -171,8 +171,9 @@ struct etr_buf { * @csdev: component vitals needed by the framework. * @miscdev: specifics to handle "/dev/xyz.tmc" entry. * @spinlock: only one at a time pls. - * @pid: Process ID of the process being monitored by the session - * that is using this component. + * @pid: Process ID of the process that owns the session that is using + * this component. For example this would be the pid of the Perf + * process. * @buf: Snapshot of the trace data for ETF/ETB. * @etr_buf: details of buffer used in TMC-ETR * @len: size of the available trace for ETF/ETB. From acb0184fe9bca3bb7103dadc76ba9d38c969ca86 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:53 +0100 Subject: [PATCH 07/13] coresight: Move struct coresight_trace_id_map to common header The trace ID maps will need to be created and stored by the core and Perf code so move the definition up to the common header. Reviewed-by: Anshuman Khandual Reviewed-by: Mike Leach Signed-off-by: James Clark Tested-by: Leo Yan Tested-by: Ganapatrao Kulkarni Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-12-james.clark@linaro.org --- .../hwtracing/coresight/coresight-trace-id.c | 1 + .../hwtracing/coresight/coresight-trace-id.h | 19 ------------------- include/linux/coresight.h | 18 ++++++++++++++++++ 3 files changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index af5b4ef59cea..19005b5b4dc4 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -3,6 +3,7 @@ * Copyright (c) 2022, Linaro Limited, All rights reserved. * Author: Mike Leach */ +#include #include #include #include diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 3797777d367e..49438a96fcc6 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -32,10 +32,6 @@ #include #include - -/* 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 @@ -46,21 +42,6 @@ #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 */ /** diff --git a/include/linux/coresight.h b/include/linux/coresight.h index f09ace92176e..c16c61a8411d 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -218,6 +218,24 @@ struct coresight_sysfs_link { const char *target_name; }; +/* architecturally we have 128 IDs some of which are reserved */ +#define CORESIGHT_TRACE_IDS_MAX 128 + +/** + * 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); +}; + /** * struct coresight_device - representation of a device as used by the framework * @pdata: Platform data with device connections associated to this device. From 7e52877868ae2546ead8ba07cdf1d3e4c9e931f7 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:54 +0100 Subject: [PATCH 08/13] coresight: Expose map arguments in trace ID API The trace ID API is currently hard coded to always use the global map. Add public versions that allow the map to be passed in so that Perf mode can use per-sink maps. Keep the non-map versions so that sysfs mode can continue to use the default global map. System ID functions are unchanged because they will always use the default map. Signed-off-by: James Clark Reviewed-by: Mike Leach Tested-by: Leo Yan Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-13-james.clark@linaro.org --- .../hwtracing/coresight/coresight-trace-id.c | 36 ++++++++++++++----- .../hwtracing/coresight/coresight-trace-id.h | 20 +++++++++-- 2 files changed, 45 insertions(+), 11 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 19005b5b4dc4..5561989a03fa 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -12,7 +12,7 @@ #include "coresight-trace-id.h" -/* Default trace ID map. Used on systems that don't require per sink mappings */ +/* Default trace ID map. Used in sysfs mode and for system sources */ static struct coresight_trace_id_map id_map_default; /* maintain a record of the mapping of IDs and pending releases per cpu */ @@ -47,7 +47,7 @@ static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, #endif /* unlocked read of current trace ID value for given CPU */ -static int _coresight_trace_id_read_cpu_id(int cpu) +static int _coresight_trace_id_read_cpu_id(int cpu, struct coresight_trace_id_map *id_map) { return atomic_read(&per_cpu(cpu_id, cpu)); } @@ -152,7 +152,7 @@ static void coresight_trace_id_release_all_pending(void) DUMP_ID_MAP(id_map); } -static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map *id_map) { unsigned long flags; int id; @@ -160,7 +160,7 @@ static int coresight_trace_id_map_get_cpu_id(int cpu, struct coresight_trace_id_ spin_lock_irqsave(&id_map_lock, flags); /* check for existing allocation for this CPU */ - id = _coresight_trace_id_read_cpu_id(cpu); + id = _coresight_trace_id_read_cpu_id(cpu, id_map); if (id) goto get_cpu_id_clr_pend; @@ -196,13 +196,13 @@ get_cpu_id_out_unlock: return id; } -static void coresight_trace_id_map_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) +static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_map *id_map) { unsigned long flags; int id; /* check for existing allocation for this CPU */ - id = _coresight_trace_id_read_cpu_id(cpu); + id = _coresight_trace_id_read_cpu_id(cpu, id_map); if (!id) return; @@ -254,22 +254,40 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * int coresight_trace_id_get_cpu_id(int cpu) { - return coresight_trace_id_map_get_cpu_id(cpu, &id_map_default); + return _coresight_trace_id_get_cpu_id(cpu, &id_map_default); } EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id); +int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + return _coresight_trace_id_get_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_get_cpu_id_map); + void coresight_trace_id_put_cpu_id(int cpu) { - coresight_trace_id_map_put_cpu_id(cpu, &id_map_default); + _coresight_trace_id_put_cpu_id(cpu, &id_map_default); } EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id); +void coresight_trace_id_put_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + _coresight_trace_id_put_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_put_cpu_id_map); + int coresight_trace_id_read_cpu_id(int cpu) { - return _coresight_trace_id_read_cpu_id(cpu); + return _coresight_trace_id_read_cpu_id(cpu, &id_map_default); } EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id); +int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map) +{ + return _coresight_trace_id_read_cpu_id(cpu, id_map); +} +EXPORT_SYMBOL_GPL(coresight_trace_id_read_cpu_id_map); + int coresight_trace_id_get_system_id(void) { return coresight_trace_id_map_get_system_id(&id_map_default); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 49438a96fcc6..840babdd0794 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -42,8 +42,6 @@ #define IS_VALID_CS_TRACE_ID(id) \ ((id > CORESIGHT_TRACE_ID_RES_0) && (id < CORESIGHT_TRACE_ID_RES_TOP)) -/* Allocate and release IDs for a single default trace ID map */ - /** * Read and optionally allocate a CoreSight trace ID and associate with a CPU. * @@ -59,6 +57,12 @@ */ int coresight_trace_id_get_cpu_id(int cpu); +/** + * Version of coresight_trace_id_get_cpu_id() that allows the ID map to operate + * on to be provided. + */ +int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + /** * Release an allocated trace ID associated with the CPU. * @@ -72,6 +76,12 @@ int coresight_trace_id_get_cpu_id(int cpu); */ void coresight_trace_id_put_cpu_id(int cpu); +/** + * Version of coresight_trace_id_put_cpu_id() that allows the ID map to operate + * on to be provided. + */ +void coresight_trace_id_put_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + /** * Read the current allocated CoreSight Trace ID value for the CPU. * @@ -92,6 +102,12 @@ void coresight_trace_id_put_cpu_id(int cpu); */ int coresight_trace_id_read_cpu_id(int cpu); +/** + * Version of coresight_trace_id_read_cpu_id() that allows the ID map to operate + * on to be provided. + */ +int coresight_trace_id_read_cpu_id_map(int cpu, struct coresight_trace_id_map *id_map); + /** * Allocate a CoreSight trace ID for a system component. * From d53c8253c7822fbc524adcd950e7c6de6a229c99 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:55 +0100 Subject: [PATCH 09/13] coresight: Make CPU id map a property of a trace ID map The global CPU ID mappings won't work for per-sink ID maps so move it to the ID map struct. coresight_trace_id_release_all_pending() is hard coded to operate on the default map, but once Perf sessions use their own maps the pending release mechanism will be deleted. So it doesn't need to be extended to accept a trace ID map argument at this point. Signed-off-by: James Clark Reviewed-by: Mike Leach Tested-by: Leo Yan Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-14-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-trace-id.c | 16 +++++++++------- include/linux/coresight.h | 1 + 2 files changed, 10 insertions(+), 7 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 5561989a03fa..8a777c0af6ea 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -13,10 +13,12 @@ #include "coresight-trace-id.h" /* Default trace ID map. Used in sysfs mode and for system sources */ -static struct coresight_trace_id_map id_map_default; +static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); +static struct coresight_trace_id_map id_map_default = { + .cpu_map = &id_map_default_cpu_ids +}; -/* maintain a record of the mapping of IDs and pending releases per cpu */ -static DEFINE_PER_CPU(atomic_t, cpu_id) = ATOMIC_INIT(0); +/* maintain a record of the pending releases per cpu */ static cpumask_t cpu_id_release_pending; /* perf session active counter */ @@ -49,7 +51,7 @@ static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, /* unlocked read of current trace ID value for given CPU */ static int _coresight_trace_id_read_cpu_id(int cpu, struct coresight_trace_id_map *id_map) { - return atomic_read(&per_cpu(cpu_id, cpu)); + return atomic_read(per_cpu_ptr(id_map->cpu_map, cpu)); } /* look for next available odd ID, return 0 if none found */ @@ -145,7 +147,7 @@ static void coresight_trace_id_release_all_pending(void) clear_bit(bit, id_map->pend_rel_ids); } for_each_cpu(cpu, &cpu_id_release_pending) { - atomic_set(&per_cpu(cpu_id, cpu), 0); + atomic_set(per_cpu_ptr(id_map_default.cpu_map, cpu), 0); cpumask_clear_cpu(cpu, &cpu_id_release_pending); } spin_unlock_irqrestore(&id_map_lock, flags); @@ -181,7 +183,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map goto get_cpu_id_out_unlock; /* allocate the new id to the cpu */ - atomic_set(&per_cpu(cpu_id, cpu), id); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); get_cpu_id_clr_pend: /* we are (re)using this ID - so ensure it is not marked for release */ @@ -215,7 +217,7 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma } else { /* otherwise clear id */ coresight_trace_id_free(id, id_map); - atomic_set(&per_cpu(cpu_id, cpu), 0); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); } spin_unlock_irqrestore(&id_map_lock, flags); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index c16c61a8411d..7d62b88bfb5c 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -234,6 +234,7 @@ struct coresight_sysfs_link { struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); + atomic_t __percpu *cpu_map; }; /** From 5ad628a7617607baac53745f8025638b967470a2 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:56 +0100 Subject: [PATCH 10/13] coresight: Use per-sink trace ID maps for Perf sessions This will allow sessions with more than CORESIGHT_TRACE_IDS_MAX ETMs as long as there are fewer than that many ETMs connected to each sink. Each sink owns its own trace ID map, and any Perf session connecting to that sink will allocate from it, even if the sink is currently in use by other users. This is similar to the existing behavior where the dynamic trace IDs are constant as long as there is any concurrent Perf session active. It's not completely optimal because slightly more IDs will be used than necessary, but the optimal solution involves tracking the PIDs of each session and allocating ID maps based on the session owner. This is difficult to do with the combination of per-thread and per-cpu modes and some scheduling issues. The complexity of this isn't likely to worth it because even with multiple users they'd just see a difference in the ordering of ID allocations rather than hitting any limits (unless the hardware does have too many ETMs connected to one sink). Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-15-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 10 ++++++++++ drivers/hwtracing/coresight/coresight-dummy.c | 3 ++- drivers/hwtracing/coresight/coresight-etm-perf.c | 15 ++++++++++----- .../hwtracing/coresight/coresight-etm3x-core.c | 9 +++++---- .../hwtracing/coresight/coresight-etm4x-core.c | 9 +++++---- drivers/hwtracing/coresight/coresight-stm.c | 3 ++- drivers/hwtracing/coresight/coresight-sysfs.c | 3 ++- drivers/hwtracing/coresight/coresight-tpdm.c | 3 ++- include/linux/coresight.h | 3 ++- 9 files changed, 40 insertions(+), 18 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index 9fc6f6b863e0..faf560ba8d64 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -902,6 +902,7 @@ static void coresight_device_release(struct device *dev) struct coresight_device *csdev = to_coresight_device(dev); fwnode_handle_put(csdev->dev.fwnode); + free_percpu(csdev->perf_sink_id_map.cpu_map); kfree(csdev); } @@ -1159,6 +1160,15 @@ 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); + if (csdev->type == CORESIGHT_DEV_TYPE_SINK || + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); + if (!csdev->perf_sink_id_map.cpu_map) { + kfree(csdev); + ret = -ENOMEM; + goto err_out; + } + } /* * Make sure the device registration and the connection fixup * are synchronised, so that we don't see uninitialised devices diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c index dab389a5507c..bb85fa663ffc 100644 --- a/drivers/hwtracing/coresight/coresight-dummy.c +++ b/drivers/hwtracing/coresight/coresight-dummy.c @@ -21,7 +21,8 @@ DEFINE_CORESIGHT_DEVLIST(source_devs, "dummy_source"); DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink"); static int dummy_source_enable(struct coresight_device *csdev, - struct perf_event *event, enum cs_mode mode) + struct perf_event *event, enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *id_map) { if (!coresight_take_mode(csdev, mode)) return -EBUSY; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index c0c60e6a1703..7fb55dafb639 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -229,10 +229,13 @@ static void free_event_data(struct work_struct *work) struct list_head **ppath; ppath = etm_event_cpu_path_ptr(event_data, cpu); - if (!(IS_ERR_OR_NULL(*ppath))) + if (!(IS_ERR_OR_NULL(*ppath))) { + struct coresight_device *sink = coresight_get_sink(*ppath); + + coresight_trace_id_put_cpu_id_map(cpu, &sink->perf_sink_id_map); coresight_release_path(*ppath); + } *ppath = NULL; - coresight_trace_id_put_cpu_id(cpu); } /* mark perf event as done for trace id allocator */ @@ -401,7 +404,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, } /* ensure we can allocate a trace ID for this CPU */ - trace_id = coresight_trace_id_get_cpu_id(cpu); + trace_id = coresight_trace_id_get_cpu_id_map(cpu, &sink->perf_sink_id_map); if (!IS_VALID_CS_TRACE_ID(trace_id)) { cpumask_clear_cpu(cpu, mask); coresight_release_path(path); @@ -495,7 +498,8 @@ static void etm_event_start(struct perf_event *event, int flags) goto fail_end_stop; /* Finally enable the tracer */ - if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) + if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF, + &sink->perf_sink_id_map)) goto fail_disable_path; /* @@ -507,7 +511,8 @@ static void etm_event_start(struct perf_event *event, int flags) hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, CS_AUX_HW_ID_CURR_VERSION); hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, - coresight_trace_id_read_cpu_id(cpu)); + coresight_trace_id_read_cpu_id_map(cpu, + &sink->perf_sink_id_map)); perf_report_aux_output_id(event, hw_id); } diff --git a/drivers/hwtracing/coresight/coresight-etm3x-core.c b/drivers/hwtracing/coresight/coresight-etm3x-core.c index 8b362605d242..c103f4c70f5d 100644 --- a/drivers/hwtracing/coresight/coresight-etm3x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm3x-core.c @@ -481,7 +481,8 @@ void etm_release_trace_id(struct etm_drvdata *drvdata) } static int etm_enable_perf(struct coresight_device *csdev, - struct perf_event *event) + struct perf_event *event, + struct coresight_trace_id_map *id_map) { struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); int trace_id; @@ -500,7 +501,7 @@ static int etm_enable_perf(struct coresight_device *csdev, * 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); + trace_id = coresight_trace_id_read_cpu_id_map(drvdata->cpu, id_map); 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); @@ -553,7 +554,7 @@ unlock_enable_sysfs: } static int etm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, struct coresight_trace_id_map *id_map) { int ret; struct etm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -568,7 +569,7 @@ static int etm_enable(struct coresight_device *csdev, struct perf_event *event, ret = etm_enable_sysfs(csdev); break; case CS_MODE_PERF: - ret = etm_enable_perf(csdev, event); + ret = etm_enable_perf(csdev, event, id_map); break; default: ret = -EINVAL; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index bf01f01964cf..66d44a404ad0 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -752,7 +752,8 @@ out: } static int etm4_enable_perf(struct coresight_device *csdev, - struct perf_event *event) + struct perf_event *event, + struct coresight_trace_id_map *id_map) { int ret = 0, trace_id; struct etmv4_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -775,7 +776,7 @@ static int etm4_enable_perf(struct coresight_device *csdev, * 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); + trace_id = coresight_trace_id_read_cpu_id_map(drvdata->cpu, id_map); 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); @@ -837,7 +838,7 @@ unlock_sysfs_enable: } static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, struct coresight_trace_id_map *id_map) { int ret; @@ -851,7 +852,7 @@ static int etm4_enable(struct coresight_device *csdev, struct perf_event *event, ret = etm4_enable_sysfs(csdev); break; case CS_MODE_PERF: - ret = etm4_enable_perf(csdev, event); + ret = etm4_enable_perf(csdev, event, id_map); break; default: ret = -EINVAL; diff --git a/drivers/hwtracing/coresight/coresight-stm.c b/drivers/hwtracing/coresight/coresight-stm.c index 117dbb484543..cb3e04755c99 100644 --- a/drivers/hwtracing/coresight/coresight-stm.c +++ b/drivers/hwtracing/coresight/coresight-stm.c @@ -194,7 +194,8 @@ static void stm_enable_hw(struct stm_drvdata *drvdata) } static int stm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *trace_id) { struct stm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); diff --git a/drivers/hwtracing/coresight/coresight-sysfs.c b/drivers/hwtracing/coresight/coresight-sysfs.c index 1e67cc7758d7..a01c9e54e2ed 100644 --- a/drivers/hwtracing/coresight/coresight-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-sysfs.c @@ -9,6 +9,7 @@ #include #include "coresight-priv.h" +#include "coresight-trace-id.h" /* * Use IDR to map the hash of the source's device name @@ -63,7 +64,7 @@ static int coresight_enable_source_sysfs(struct coresight_device *csdev, */ lockdep_assert_held(&coresight_mutex); if (coresight_get_mode(csdev) != CS_MODE_SYSFS) { - ret = source_ops(csdev)->enable(csdev, data, mode); + ret = source_ops(csdev)->enable(csdev, data, mode, NULL); if (ret) return ret; } diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c index 5c5a4b3fe687..b7d99e91ab84 100644 --- a/drivers/hwtracing/coresight/coresight-tpdm.c +++ b/drivers/hwtracing/coresight/coresight-tpdm.c @@ -439,7 +439,8 @@ static void __tpdm_enable(struct tpdm_drvdata *drvdata) } static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode) + enum cs_mode mode, + __maybe_unused struct coresight_trace_id_map *id_map) { struct tpdm_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7d62b88bfb5c..9c3067e2e38b 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -290,6 +290,7 @@ struct coresight_device { bool sysfs_sink_activated; struct dev_ext_attribute *ea; struct coresight_device *def_sink; + struct coresight_trace_id_map perf_sink_id_map; /* sysfs links between components */ int nr_links; bool has_conns_grp; @@ -384,7 +385,7 @@ struct coresight_ops_link { struct coresight_ops_source { int (*cpu_id)(struct coresight_device *csdev); int (*enable)(struct coresight_device *csdev, struct perf_event *event, - enum cs_mode mode); + enum cs_mode mode, struct coresight_trace_id_map *id_map); void (*disable)(struct coresight_device *csdev, struct perf_event *event); }; From de0029fdde86092c75472c92e56a962f4edee0f6 Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:57 +0100 Subject: [PATCH 11/13] coresight: Remove pending trace ID release mechanism Pending the release of IDs was a way of managing concurrent sysfs and Perf sessions in a single global ID map. Perf may have finished while sysfs hadn't, and Perf shouldn't release the IDs in use by sysfs and vice versa. Now that Perf uses its own exclusive ID maps, pending release doesn't result in any different behavior than just releasing all IDs when the last Perf session finishes. As part of the per-sink trace ID change, we would have still had to make the pending mechanism work on a per-sink basis, due to the overlapping ID allocations, so instead of making that more complicated, just remove it. Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-16-james.clark@linaro.org --- .../hwtracing/coresight/coresight-etm-perf.c | 18 +++-- .../hwtracing/coresight/coresight-trace-id.c | 67 +++++-------------- .../hwtracing/coresight/coresight-trace-id.h | 31 ++++----- include/linux/coresight.h | 6 +- 4 files changed, 43 insertions(+), 79 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 7fb55dafb639..70c99f0409b2 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -232,15 +232,21 @@ static void free_event_data(struct work_struct *work) if (!(IS_ERR_OR_NULL(*ppath))) { struct coresight_device *sink = coresight_get_sink(*ppath); - coresight_trace_id_put_cpu_id_map(cpu, &sink->perf_sink_id_map); + /* + * Mark perf event as done for trace id allocator, but don't call + * coresight_trace_id_put_cpu_id_map() on individual IDs. Perf sessions + * never free trace IDs to ensure that the ID associated with a CPU + * cannot change during their and other's concurrent sessions. Instead, + * a refcount is used so that the last event to call + * coresight_trace_id_perf_stop() frees all IDs. + */ + coresight_trace_id_perf_stop(&sink->perf_sink_id_map); + coresight_release_path(*ppath); } *ppath = NULL; } - /* mark perf event as done for trace id allocator */ - coresight_trace_id_perf_stop(); - free_percpu(event_data->path); kfree(event_data); } @@ -328,9 +334,6 @@ 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) { @@ -411,6 +414,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, continue; } + coresight_trace_id_perf_start(&sink->perf_sink_id_map); *etm_event_cpu_path_ptr(event_data, cpu) = path; } diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index 8a777c0af6ea..bddaed3e5cf8 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -18,12 +18,6 @@ static struct coresight_trace_id_map id_map_default = { .cpu_map = &id_map_default_cpu_ids }; -/* maintain a record of the pending releases per cpu */ -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); @@ -35,7 +29,6 @@ static void coresight_trace_id_dump_table(struct coresight_trace_id_map *id_map, { 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) @@ -122,34 +115,18 @@ static void coresight_trace_id_free(int id, struct coresight_trace_id_map *id_ma 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. + * Release all IDs and clear CPU associations. */ -static void coresight_trace_id_release_all_pending(void) +static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map) { - struct coresight_trace_id_map *id_map = &id_map_default; unsigned long flags; - int cpu, bit; + int cpu; 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_ptr(id_map_default.cpu_map, cpu), 0); - cpumask_clear_cpu(cpu, &cpu_id_release_pending); - } + bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); + for_each_possible_cpu(cpu) + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); spin_unlock_irqrestore(&id_map_lock, flags); DUMP_ID_MAP(id_map); } @@ -164,7 +141,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map /* check for existing allocation for this CPU */ id = _coresight_trace_id_read_cpu_id(cpu, id_map); if (id) - goto get_cpu_id_clr_pend; + goto get_cpu_id_out_unlock; /* * Find a new ID. @@ -185,11 +162,6 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map /* allocate the new id to the cpu */ atomic_set(per_cpu_ptr(id_map->cpu_map, 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); @@ -210,15 +182,8 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma 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_ptr(id_map->cpu_map, cpu), 0); - } + coresight_trace_id_free(id, id_map); + atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); spin_unlock_irqrestore(&id_map_lock, flags); DUMP_ID_CPU(cpu, id); @@ -302,17 +267,17 @@ void coresight_trace_id_put_system_id(int id) } EXPORT_SYMBOL_GPL(coresight_trace_id_put_system_id); -void coresight_trace_id_perf_start(void) +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map) { - atomic_inc(&perf_cs_etm_session_active); - PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); + atomic_inc(&id_map->perf_cs_etm_session_active); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_start); -void coresight_trace_id_perf_stop(void) +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map) { - if (!atomic_dec_return(&perf_cs_etm_session_active)) - coresight_trace_id_release_all_pending(); - PERF_SESSION(atomic_read(&perf_cs_etm_session_active)); + if (!atomic_dec_return(&id_map->perf_cs_etm_session_active)) + coresight_trace_id_release_all(id_map); + PERF_SESSION(atomic_read(&id_map->perf_cs_etm_session_active)); } EXPORT_SYMBOL_GPL(coresight_trace_id_perf_stop); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.h b/drivers/hwtracing/coresight/coresight-trace-id.h index 840babdd0794..9aae50a553ca 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.h +++ b/drivers/hwtracing/coresight/coresight-trace-id.h @@ -17,9 +17,10 @@ * 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. + * throughout a perf cs_etm event session - a session in progress flag will be + * maintained for each sink, and IDs are cleared when all the perf sessions + * complete. This allows the same CPU to be re-allocated its prior ID when + * events are scheduled in and out. * * * Trace ID maps will be created and initialised to prevent architecturally @@ -66,11 +67,7 @@ int coresight_trace_id_get_cpu_id_map(int cpu, struct coresight_trace_id_map *id /** * 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. + * This will release the CoreSight trace ID associated with the CPU. * * @cpu: The CPU index to release the associated trace ID. */ @@ -133,21 +130,21 @@ void coresight_trace_id_put_system_id(int id); /** * 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. + * 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. + * Perf sessions never free trace IDs to ensure that the ID associated with a + * CPU cannot change during their and other's concurrent sessions. Instead, + * this refcount is used so that the last event to finish always frees all IDs. */ -void coresight_trace_id_perf_start(void); +void coresight_trace_id_perf_start(struct coresight_trace_id_map *id_map); /** * Notify the ID allocator that a perf session is stopping. * - * Decrease the perf session reference count. - * if this causes the count to go to zero, then all Trace IDs marked as pending - * release, will be released. + * Decrease the perf session reference count. If this causes the count to go to + * zero, then all Trace IDs will be released. */ -void coresight_trace_id_perf_stop(void); +void coresight_trace_id_perf_stop(struct coresight_trace_id_map *id_map); #endif /* _CORESIGHT_TRACE_ID_H */ diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 9c3067e2e38b..197949fd2c35 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -227,14 +227,12 @@ struct coresight_sysfs_link { * @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. + * @perf_cs_etm_session_active: Number of Perf sessions using this ID map. */ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); - DECLARE_BITMAP(pend_rel_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; + atomic_t perf_cs_etm_session_active; }; /** From 487eec8da80aef16229d30429f1b26090b1bf0eb Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:58 +0100 Subject: [PATCH 12/13] coresight: Emit sink ID in the HW_ID packets For Perf to be able to decode when per-sink trace IDs are used, emit the sink that's being written to for each ETM. Perf currently errors out if it sees a newer packet version so instead of bumping it, add a new minor version field. This can be used to signify new versions that have backwards compatible fields. Considering this change is only for high core count machines, it doesn't make sense to make a breaking change for everyone. Signed-off-by: James Clark Tested-by: Leo Yan Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-17-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 26 ++++++++++--------- .../hwtracing/coresight/coresight-etm-perf.c | 16 ++++++++---- drivers/hwtracing/coresight/coresight-priv.h | 1 + include/linux/coresight-pmu.h | 17 +++++++++--- 4 files changed, 39 insertions(+), 21 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index faf560ba8d64..c427e9344a84 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -487,23 +487,25 @@ struct coresight_device *coresight_get_sink(struct list_head *path) return csdev; } +u32 coresight_get_sink_id(struct coresight_device *csdev) +{ + if (!csdev->ea) + return 0; + + /* + * See function etm_perf_add_symlink_sink() to know where + * this comes from. + */ + return (u32) (unsigned long) csdev->ea->var; +} + static int coresight_sink_by_id(struct device *dev, const void *data) { struct coresight_device *csdev = to_coresight_device(dev); - unsigned long hash; if (csdev->type == CORESIGHT_DEV_TYPE_SINK || - csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { - - if (!csdev->ea) - return 0; - /* - * See function etm_perf_add_symlink_sink() to know where - * this comes from. - */ - hash = (unsigned long)csdev->ea->var; - - if ((u32)hash == *(u32 *)data) + csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + if (coresight_get_sink_id(csdev) == *(u32 *)data) return 1; } diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 70c99f0409b2..ad6a8f4b70b6 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -460,6 +460,7 @@ static void etm_event_start(struct perf_event *event, int flags) struct coresight_device *sink, *csdev = per_cpu(csdev_src, cpu); struct list_head *path; u64 hw_id; + u8 trace_id; if (!csdev) goto fail; @@ -512,11 +513,16 @@ static void etm_event_start(struct perf_event *event, int flags) */ if (!cpumask_test_cpu(cpu, &event_data->aux_hwid_done)) { cpumask_set_cpu(cpu, &event_data->aux_hwid_done); - hw_id = FIELD_PREP(CS_AUX_HW_ID_VERSION_MASK, - CS_AUX_HW_ID_CURR_VERSION); - hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, - coresight_trace_id_read_cpu_id_map(cpu, - &sink->perf_sink_id_map)); + + trace_id = coresight_trace_id_read_cpu_id_map(cpu, &sink->perf_sink_id_map); + + hw_id = FIELD_PREP(CS_AUX_HW_ID_MAJOR_VERSION_MASK, + CS_AUX_HW_ID_MAJOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_MINOR_VERSION_MASK, + CS_AUX_HW_ID_MINOR_VERSION); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_TRACE_ID_MASK, trace_id); + hw_id |= FIELD_PREP(CS_AUX_HW_ID_SINK_ID_MASK, coresight_get_sink_id(sink)); + perf_report_aux_output_id(event, hw_id); } diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 61a46d3bdcc8..05f891ca6b5c 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -148,6 +148,7 @@ int coresight_make_links(struct coresight_device *orig, struct coresight_device *target); void coresight_remove_links(struct coresight_device *orig, struct coresight_connection *conn); +u32 coresight_get_sink_id(struct coresight_device *csdev); #if IS_ENABLED(CONFIG_CORESIGHT_SOURCE_ETM3X) extern int etm_readl_cp14(u32 off, unsigned int *val); diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 51ac441a37c3..89b0ac0014b0 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -49,12 +49,21 @@ * 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 + * [39:08] - Sink ID - as reported in /sys/bus/event_source/devices/cs_etm/sinks/ + * Added in minor version 1. + * [55:40] - Unused (SBZ) + * [59:56] - Minor Version - previously existing fields are compatible with + * all minor versions. + * [63:60] - Major Version - previously existing fields mean different things + * in new major versions. */ #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_SINK_ID_MASK GENMASK_ULL(39, 8) -#define CS_AUX_HW_ID_CURR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION_MASK GENMASK_ULL(59, 56) +#define CS_AUX_HW_ID_MAJOR_VERSION_MASK GENMASK_ULL(63, 60) + +#define CS_AUX_HW_ID_MAJOR_VERSION 0 +#define CS_AUX_HW_ID_MINOR_VERSION 1 #endif From 988d40a4d4e7d671305bea501562a5d1a1d479fa Mon Sep 17 00:00:00 2001 From: James Clark Date: Mon, 22 Jul 2024 11:11:59 +0100 Subject: [PATCH 13/13] coresight: Make trace ID map spinlock local to the map Reduce contention on the lock by replacing the global lock with one for each map. Signed-off-by: James Clark Reviewed-by: Mike Leach Signed-off-by: James Clark Signed-off-by: Suzuki K Poulose Link: https://lore.kernel.org/r/20240722101202.26915-18-james.clark@linaro.org --- drivers/hwtracing/coresight/coresight-core.c | 1 + .../hwtracing/coresight/coresight-trace-id.c | 26 +++++++++---------- include/linux/coresight.h | 1 + 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c index c427e9344a84..ea38ecf26fcb 100644 --- a/drivers/hwtracing/coresight/coresight-core.c +++ b/drivers/hwtracing/coresight/coresight-core.c @@ -1164,6 +1164,7 @@ struct coresight_device *coresight_register(struct coresight_desc *desc) if (csdev->type == CORESIGHT_DEV_TYPE_SINK || csdev->type == CORESIGHT_DEV_TYPE_LINKSINK) { + spin_lock_init(&csdev->perf_sink_id_map.lock); csdev->perf_sink_id_map.cpu_map = alloc_percpu(atomic_t); if (!csdev->perf_sink_id_map.cpu_map) { kfree(csdev); diff --git a/drivers/hwtracing/coresight/coresight-trace-id.c b/drivers/hwtracing/coresight/coresight-trace-id.c index bddaed3e5cf8..d98e12cb30ec 100644 --- a/drivers/hwtracing/coresight/coresight-trace-id.c +++ b/drivers/hwtracing/coresight/coresight-trace-id.c @@ -15,12 +15,10 @@ /* Default trace ID map. Used in sysfs mode and for system sources */ static DEFINE_PER_CPU(atomic_t, id_map_default_cpu_ids) = ATOMIC_INIT(0); static struct coresight_trace_id_map id_map_default = { - .cpu_map = &id_map_default_cpu_ids + .cpu_map = &id_map_default_cpu_ids, + .lock = __SPIN_LOCK_UNLOCKED(id_map_default.lock) }; -/* 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) @@ -123,11 +121,11 @@ static void coresight_trace_id_release_all(struct coresight_trace_id_map *id_map unsigned long flags; int cpu; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); bitmap_zero(id_map->used_ids, CORESIGHT_TRACE_IDS_MAX); for_each_possible_cpu(cpu) atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_MAP(id_map); } @@ -136,7 +134,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); /* check for existing allocation for this CPU */ id = _coresight_trace_id_read_cpu_id(cpu, id_map); @@ -163,7 +161,7 @@ static int _coresight_trace_id_get_cpu_id(int cpu, struct coresight_trace_id_map atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), id); get_cpu_id_out_unlock: - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); @@ -180,12 +178,12 @@ static void _coresight_trace_id_put_cpu_id(int cpu, struct coresight_trace_id_ma if (!id) return; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); atomic_set(per_cpu_ptr(id_map->cpu_map, cpu), 0); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID_CPU(cpu, id); DUMP_ID_MAP(id_map); } @@ -195,10 +193,10 @@ static int coresight_trace_id_map_get_system_id(struct coresight_trace_id_map *i unsigned long flags; int id; - spin_lock_irqsave(&id_map_lock, flags); + 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); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); @@ -209,9 +207,9 @@ static void coresight_trace_id_map_put_system_id(struct coresight_trace_id_map * { unsigned long flags; - spin_lock_irqsave(&id_map_lock, flags); + spin_lock_irqsave(&id_map->lock, flags); coresight_trace_id_free(id, id_map); - spin_unlock_irqrestore(&id_map_lock, flags); + spin_unlock_irqrestore(&id_map->lock, flags); DUMP_ID(id); DUMP_ID_MAP(id_map); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 197949fd2c35..c13342594278 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -233,6 +233,7 @@ struct coresight_trace_id_map { DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX); atomic_t __percpu *cpu_map; atomic_t perf_cs_etm_session_active; + spinlock_t lock; }; /**