diff options
20 files changed, 905 insertions, 154 deletions
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index d410a47ffa57..5342e895fb60 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -92,12 +92,24 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #2119858 | ARM64_ERRATUM_2119858 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #2054223 | ARM64_ERRATUM_2054223 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #2139208 | ARM64_ERRATUM_2139208 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #2067961 | ARM64_ERRATUM_2067961 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt index 7f9c1ca87487..c68d93a35b6c 100644 --- a/Documentation/devicetree/bindings/arm/coresight.txt +++ b/Documentation/devicetree/bindings/arm/coresight.txt @@ -127,6 +127,11 @@ its hardware characteristcs. * arm,scatter-gather: boolean. Indicates that the TMC-ETR can safely use the SG mode on this system. + * arm,max-burst-size: The maximum burst size initiated by TMC on the + AXI master interface. The burst size can be in the range [0..15], + the setting supports one data transfer per burst up to a maximum of + 16 data transfers per burst. + * Optional property for CATU : * interrupts : Exactly one SPI may be listed for reporting the address error diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fee914c716aa..ebb77b894630 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -666,6 +666,117 @@ config ARM64_ERRATUM_1508412 If unsure, say Y. +config ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE + bool + +config ARM64_ERRATUM_2119858 + bool "Cortex-A710: 2119858: workaround TRBE overwriting trace data in FILL mode" + default y + depends on CORESIGHT_TRBE + select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE + help + This option adds the workaround for ARM Cortex-A710 erratum 2119858. + + Affected Cortex-A710 cores could overwrite up to 3 cache lines of trace + data at the base of the buffer (pointed to by TRBASER_EL1) in FILL mode in + the event of a WRAP event. + + Work around the issue by always making sure we move the TRBPTR_EL1 by + 256 bytes before enabling the buffer and filling the first 256 bytes of + the buffer with ETM ignore packets upon disabling. + + If unsure, say Y. + +config ARM64_ERRATUM_2139208 + bool "Neoverse-N2: 2139208: workaround TRBE overwriting trace data in FILL mode" + default y + depends on CORESIGHT_TRBE + select ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE + help + This option adds the workaround for ARM Neoverse-N2 erratum 2139208. + + Affected Neoverse-N2 cores could overwrite up to 3 cache lines of trace + data at the base of the buffer (pointed to by TRBASER_EL1) in FILL mode in + the event of a WRAP event. + + Work around the issue by always making sure we move the TRBPTR_EL1 by + 256 bytes before enabling the buffer and filling the first 256 bytes of + the buffer with ETM ignore packets upon disabling. + + If unsure, say Y. + +config ARM64_WORKAROUND_TSB_FLUSH_FAILURE + bool + +config ARM64_ERRATUM_2054223 + bool "Cortex-A710: 2054223: workaround TSB instruction failing to flush trace" + default y + select ARM64_WORKAROUND_TSB_FLUSH_FAILURE + help + Enable workaround for ARM Cortex-A710 erratum 2054223 + + Affected cores may fail to flush the trace data on a TSB instruction, when + the PE is in trace prohibited state. This will cause losing a few bytes + of the trace cached. + + Workaround is to issue two TSB consecutively on affected cores. + + If unsure, say Y. + +config ARM64_ERRATUM_2067961 + bool "Neoverse-N2: 2067961: workaround TSB instruction failing to flush trace" + default y + select ARM64_WORKAROUND_TSB_FLUSH_FAILURE + help + Enable workaround for ARM Neoverse-N2 erratum 2067961 + + Affected cores may fail to flush the trace data on a TSB instruction, when + the PE is in trace prohibited state. This will cause losing a few bytes + of the trace cached. + + Workaround is to issue two TSB consecutively on affected cores. + + If unsure, say Y. + +config ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE + bool + +config ARM64_ERRATUM_2253138 + bool "Neoverse-N2: 2253138: workaround TRBE writing to address out-of-range" + depends on CORESIGHT_TRBE + default y + select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE + help + This option adds the workaround for ARM Neoverse-N2 erratum 2253138. + + Affected Neoverse-N2 cores might write to an out-of-range address, not reserved + for TRBE. Under some conditions, the TRBE might generate a write to the next + virtually addressed page following the last page of the TRBE address space + (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base. + + Work around this in the driver by always making sure that there is a + page beyond the TRBLIMITR_EL1.LIMIT, within the space allowed for the TRBE. + + If unsure, say Y. + +config ARM64_ERRATUM_2224489 + bool "Cortex-A710: 2224489: workaround TRBE writing to address out-of-range" + depends on CORESIGHT_TRBE + default y + select ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE + help + This option adds the workaround for ARM Cortex-A710 erratum 2224489. + + Affected Cortex-A710 cores might write to an out-of-range address, not reserved + for TRBE. Under some conditions, the TRBE might generate a write to the next + virtually addressed page following the last page of the TRBE address space + (i.e., the TRBLIMITR_EL1.LIMIT), instead of wrapping around to the base. + + Work around this in the driver by always making sure that there is a + page beyond the TRBLIMITR_EL1.LIMIT, within the space allowed for the TRBE. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 451e11e5fd23..1c5a00598458 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -23,7 +23,7 @@ #define dsb(opt) asm volatile("dsb " #opt : : : "memory") #define psb_csync() asm volatile("hint #17" : : : "memory") -#define tsb_csync() asm volatile("hint #18" : : : "memory") +#define __tsb_csync() asm volatile("hint #18" : : : "memory") #define csdb() asm volatile("hint #20" : : : "memory") #ifdef CONFIG_ARM64_PSEUDO_NMI @@ -46,6 +46,20 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) + +#define tsb_csync() \ + do { \ + /* \ + * CPUs affected by Arm Erratum 2054223 or 2067961 needs \ + * another TSB to ensure the trace is flushed. The barriers \ + * don't have to be strictly back to back, as long as the \ + * CPU is in trace prohibited state. \ + */ \ + if (cpus_have_final_cap(ARM64_WORKAROUND_TSB_FLUSH_FAILURE)) \ + __tsb_csync(); \ + __tsb_csync(); \ + } while (0) + /* * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz * and 0 otherwise. diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 6231e1f0abe7..19b8441aa8f2 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -73,6 +73,8 @@ #define ARM_CPU_PART_CORTEX_A76 0xD0B #define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define APM_CPU_PART_POTENZA 0x000 @@ -113,6 +115,8 @@ #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e2c20c036442..9e1c1aef9ebd 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -340,6 +340,42 @@ static const struct midr_range erratum_1463225[] = { }; #endif +#ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE +static const struct midr_range trbe_overwrite_fill_mode_cpus[] = { +#ifdef CONFIG_ARM64_ERRATUM_2139208 + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), +#endif +#ifdef CONFIG_ARM64_ERRATUM_2119858 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), +#endif + {}, +}; +#endif /* CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE */ + +#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE +static const struct midr_range tsb_flush_fail_cpus[] = { +#ifdef CONFIG_ARM64_ERRATUM_2067961 + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), +#endif +#ifdef CONFIG_ARM64_ERRATUM_2054223 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), +#endif + {}, +}; +#endif /* CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE */ + +#ifdef CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE +static struct midr_range trbe_write_out_of_range_cpus[] = { +#ifdef CONFIG_ARM64_ERRATUM_2253138 + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), +#endif +#ifdef CONFIG_ARM64_ERRATUM_2224489 + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), +#endif + {}, +}; +#endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */ + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -534,6 +570,34 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), }, #endif +#ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE + { + /* + * The erratum work around is handled within the TRBE + * driver and can be applied per-cpu. So, we can allow + * a late CPU to come online with this erratum. + */ + .desc = "ARM erratum 2119858 or 2139208", + .capability = ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + CAP_MIDR_RANGE_LIST(trbe_overwrite_fill_mode_cpus), + }, +#endif +#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE + { + .desc = "ARM erratum 2067961 or 2054223", + .capability = ARM64_WORKAROUND_TSB_FLUSH_FAILURE, + ERRATA_MIDR_RANGE_LIST(tsb_flush_fail_cpus), + }, +#endif +#ifdef CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE + { + .desc = "ARM erratum 2253138 or 2224489", + .capability = ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE, + .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, + CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), + }, +#endif { } }; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 49305c2e6dfd..90628638e0f9 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -53,6 +53,9 @@ WORKAROUND_1418040 WORKAROUND_1463225 WORKAROUND_1508412 WORKAROUND_1542419 +WORKAROUND_TRBE_OVERWRITE_FILL_MODE +WORKAROUND_TSB_FLUSH_FAILURE +WORKAROUND_TRBE_WRITE_OUT_OF_RANGE WORKAROUND_CAVIUM_23154 WORKAROUND_CAVIUM_27456 WORKAROUND_CAVIUM_30115 diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index f026e5c0e777..514a9b8086e3 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -150,6 +150,19 @@ config CORESIGHT_CPU_DEBUG To compile this driver as a module, choose M here: the module will be called coresight-cpu-debug. +config CORESIGHT_CPU_DEBUG_DEFAULT_ON + bool "Enable CoreSight CPU Debug by default" + depends on CORESIGHT_CPU_DEBUG + help + Say Y here to enable the CoreSight Debug panic-debug by default. This + can also be enabled via debugfs, but this ensures the debug feature + is enabled as early as possible. + + Has the same effect as setting coresight_cpu_debug.enable=1 on the + kernel command line. + + Say N if unsure. + config CORESIGHT_CTI tristate "CoreSight Cross Trigger Interface (CTI) driver" depends on ARM || ARM64 diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 00de46565bc4..8845ec4b4402 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -105,7 +105,7 @@ static DEFINE_PER_CPU(struct debug_drvdata *, debug_drvdata); static int debug_count; static struct dentry *debug_debugfs_dir; -static bool debug_enable; +static bool debug_enable = IS_ENABLED(CONFIG_CORESIGHT_CPU_DEBUG_DEFAULT_ON); module_param_named(enable, debug_enable, bool, 0600); MODULE_PARM_DESC(enable, "Control to enable coresight CPU debug functionality"); diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c index e2a3620cbf48..8988b2ed2ea6 100644 --- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -175,7 +175,7 @@ static int cti_disable_hw(struct cti_drvdata *drvdata) coresight_disclaim_device_unlocked(csdev); CS_LOCK(drvdata->base); spin_unlock(&drvdata->spinlock); - pm_runtime_put(dev); + pm_runtime_put(dev->parent); return 0; /* not disabled this call */ diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index f775cbee12b8..efa39820acec 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -557,9 +557,8 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, /* * In snapshot mode we simply increment the head by the number of byte - * that were written. User space function cs_etm_find_snapshot() will - * figure out how many bytes to get from the AUX buffer based on the - * position of the head. + * that were written. User space will figure out how many bytes to get + * from the AUX buffer based on the position of the head. */ if (buf->snapshot) handle->head += to_read; diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 8ebd728d3a80..c039b6ae206f 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -452,9 +452,14 @@ static void etm_event_start(struct perf_event *event, int flags) * sink from this ETM. We can't do much in this case if * the sink was specified or hinted to the driver. For * now, simply don't record anything on this ETM. + * + * As such we pretend that everything is fine, and let + * it continue without actually tracing. The event could + * continue tracing when it moves to a CPU where it is + * reachable to a sink. */ if (!cpumask_test_cpu(cpu, &event_data->mask)) - goto fail_end_stop; + goto out; path = etm_event_cpu_path(event_data, cpu); /* We need a sink, no need to continue without one */ @@ -466,26 +471,32 @@ static void etm_event_start(struct perf_event *event, int flags) if (coresight_enable_path(path, CS_MODE_PERF, handle)) goto fail_end_stop; - /* Tell the perf core the event is alive */ - event->hw.state = 0; - /* Finally enable the tracer */ if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) goto fail_disable_path; +out: + /* Tell the perf core the event is alive */ + event->hw.state = 0; /* Save the event_data for this ETM */ ctxt->event_data = event_data; -out: return; fail_disable_path: coresight_disable_path(path); fail_end_stop: - perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); - perf_aux_output_end(handle, 0); + /* + * Check if the handle is still associated with the event, + * to handle cases where if the sink failed to start the + * trace and TRUNCATED the handle already. + */ + if (READ_ONCE(handle->event)) { + perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); + perf_aux_output_end(handle, 0); + } fail: event->hw.state = PERF_HES_STOPPED; - goto out; + return; } static void etm_event_stop(struct perf_event *event, int mode) @@ -517,6 +528,19 @@ static void etm_event_stop(struct perf_event *event, int mode) if (WARN_ON(!event_data)) return; + /* + * Check if this ETM was allowed to trace, as decided at + * etm_setup_aux(). If it wasn't allowed to trace, then + * nothing needs to be torn down other than outputting a + * zero sized record. + */ + if (handle->event && (mode & PERF_EF_UPDATE) && + !cpumask_test_cpu(cpu, &event_data->mask)) { + event->hw.state = PERF_HES_STOPPED; + perf_aux_output_end(handle, 0); + return; + } + if (!csdev) return; @@ -550,7 +574,21 @@ static void etm_event_stop(struct perf_event *event, int mode) size = sink_ops(sink)->update_buffer(sink, handle, event_data->snk_config); - perf_aux_output_end(handle, size); + /* + * Make sure the handle is still valid as the + * sink could have closed it from an IRQ. + * The sink driver must handle the race with + * update_buffer() and IRQ. Thus either we + * should get a valid handle and valid size + * (which may be 0). + * + * But we should never get a non-zero size with + * an invalid handle. + */ + if (READ_ONCE(handle->event)) + perf_aux_output_end(handle, size); + else + WARN_ON(size); } /* Disabling the path make its elements available to other sessions */ diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index e24252eaf8e4..86a313857b58 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -40,6 +40,7 @@ #include "coresight-etm4x.h" #include "coresight-etm-perf.h" #include "coresight-etm4x-cfg.h" +#include "coresight-self-hosted-trace.h" #include "coresight-syscfg.h" static int boot_enable; @@ -238,6 +239,45 @@ struct etm4_enable_arg { int rc; }; +/* + * etm4x_prohibit_trace - Prohibit the CPU from tracing at all ELs. + * When the CPU supports FEAT_TRF, we could move the ETM to a trace + * prohibited state by filtering the Exception levels via TRFCR_EL1. + */ +static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) +{ + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!drvdata->trfcr) + return; + cpu_prohibit_trace(); +} + +/* + * etm4x_allow_trace - Allow CPU tracing in the respective ELs, + * as configured by the drvdata->config.mode for the current + * session. Even though we have TRCVICTLR bits to filter the + * trace in the ELs, it doesn't prevent the ETM from generating + * a packet (e.g, TraceInfo) that might contain the addresses from + * the excluded levels. Thus we use the additional controls provided + * via the Trace Filtering controls (FEAT_TRF) to make sure no trace + * is generated for the excluded ELs. + */ +static void etm4x_allow_trace(struct etmv4_drvdata *drvdata) +{ + u64 trfcr = drvdata->trfcr; + + /* If the CPU doesn't support FEAT_TRF, nothing to do */ + if (!trfcr) + return; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_ELx_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_ELx_E0TRE; + + write_trfcr(trfcr); +} + #ifdef CONFIG_ETM4X_IMPDEF_FEATURE #define HISI_HIP08_AMBA_ID 0x000b6d01 @@ -442,6 +482,7 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) if (etm4x_is_ete(drvdata)) etm4x_relaxed_write32(csa, TRCRSR_TA, TRCRSR); + etm4x_allow_trace(drvdata); /* Enable the trace unit */ etm4x_relaxed_write32(csa, 1, TRCPRGCTLR); @@ -737,7 +778,6 @@ static int etm4_enable(struct coresight_device *csdev, static void etm4_disable_hw(void *info) { u32 control; - u64 trfcr; struct etmv4_drvdata *drvdata = info; struct etmv4_config *config = &drvdata->config; struct coresight_device *csdev = drvdata->csdev; @@ -764,12 +804,7 @@ static void etm4_disable_hw(void *info) * If the CPU supports v8.4 Trace filter Control, * set the ETM to trace prohibited region. */ - if (drvdata->trfc) { - trfcr = read_sysreg_s(SYS_TRFCR_EL1); - write_sysreg_s(trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE), - SYS_TRFCR_EL1); - isb(); - } + etm4x_prohibit_trace(drvdata); /* * Make sure everything completes before disabling, as recommended * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register, @@ -785,9 +820,6 @@ static void etm4_disable_hw(void *info) if (coresight_timeout(csa, TRCSTATR, TRCSTATR_PMSTABLE_BIT, 1)) dev_err(etm_dev, "timeout while waiting for PM stable Trace Status\n"); - if (drvdata->trfc) - write_sysreg_s(trfcr, SYS_TRFCR_EL1); - /* read the status of the single shot comparators */ for (i = 0; i < drvdata->nr_ss_cmp; i++) { config->ss_status[i] = @@ -989,15 +1021,15 @@ static bool etm4_init_csdev_access(struct etmv4_drvdata *drvdata, return false; } -static void cpu_enable_tracing(struct etmv4_drvdata *drvdata) +static void cpu_detect_trace_filtering(struct etmv4_drvdata *drvdata) { u64 dfr0 = read_sysreg(id_aa64dfr0_el1); u64 trfcr; + drvdata->trfcr = 0; if (!cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_TRACE_FILT_SHIFT)) return; - drvdata->trfc = true; /* * If the CPU supports v8.4 SelfHosted Tracing, enable * tracing at the kernel EL and EL0, forcing to use the @@ -1011,7 +1043,7 @@ static void cpu_enable_tracing(struct etmv4_drvdata *drvdata) if (is_kernel_in_hyp_mode()) trfcr |= TRFCR_EL2_CX; - write_sysreg_s(trfcr, SYS_TRFCR_EL1); + drvdata->trfcr = trfcr; } static void etm4_init_arch_data(void *info) @@ -1202,7 +1234,7 @@ static void etm4_init_arch_data(void *info) /* NUMCNTR, bits[30:28] number of counters available for tracing */ drvdata->nr_cntr = BMVAL(etmidr5, 28, 30); etm4_cs_lock(drvdata, csa); - cpu_enable_tracing(drvdata); + cpu_detect_trace_filtering(drvdata); } static inline u32 etm4_get_victlr_access_type(struct etmv4_config *config) @@ -1554,7 +1586,7 @@ 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) +static int __etm4_cpu_save(struct etmv4_drvdata *drvdata) { int i, ret = 0; struct etmv4_save_state *state; @@ -1693,7 +1725,23 @@ out: return ret; } -static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) +static int etm4_cpu_save(struct etmv4_drvdata *drvdata) +{ + int ret = 0; + + /* Save the TRFCR irrespective of whether the ETM is ON */ + if (drvdata->trfcr) + drvdata->save_trfcr = read_trfcr(); + /* + * Save and restore the ETM Trace registers only if + * the ETM is active. + */ + if (local_read(&drvdata->mode) && drvdata->save_state) + ret = __etm4_cpu_save(drvdata); + return ret; +} + +static void __etm4_cpu_restore(struct etmv4_drvdata *drvdata) { int i; struct etmv4_save_state *state = drvdata->save_state; @@ -1789,6 +1837,14 @@ static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) etm4_cs_lock(drvdata, csa); } +static void etm4_cpu_restore(struct etmv4_drvdata *drvdata) +{ + if (drvdata->trfcr) + write_trfcr(drvdata->save_trfcr); + if (drvdata->state_needs_restore) + __etm4_cpu_restore(drvdata); +} + static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, void *v) { @@ -1800,23 +1856,17 @@ static int etm4_cpu_pm_notify(struct notifier_block *nb, unsigned long cmd, drvdata = etmdrvdata[cpu]; - if (!drvdata->save_state) - return NOTIFY_OK; - if (WARN_ON_ONCE(drvdata->cpu != cpu)) return NOTIFY_BAD; switch (cmd) { case CPU_PM_ENTER: - /* save the state if self-hosted coresight is in use */ - if (local_read(&drvdata->mode)) - if (etm4_cpu_save(drvdata)) - return NOTIFY_BAD; + if (etm4_cpu_save(drvdata)) + return NOTIFY_BAD; break; case CPU_PM_EXIT: case CPU_PM_ENTER_FAILED: - if (drvdata->state_needs_restore) - etm4_cpu_restore(drvdata); + etm4_cpu_restore(drvdata); break; default: return NOTIFY_DONE; @@ -2099,6 +2149,7 @@ static const struct amba_id etm4_ids[] = { CS_AMBA_UCI_ID(0x000bb803, uci_id_etm4),/* Qualcomm Kryo 385 Cortex-A75 */ CS_AMBA_UCI_ID(0x000bb805, uci_id_etm4),/* Qualcomm Kryo 4XX Cortex-A55 */ CS_AMBA_UCI_ID(0x000bb804, uci_id_etm4),/* Qualcomm Kryo 4XX Cortex-A76 */ + CS_AMBA_UCI_ID(0x000bbd0d, uci_id_etm4),/* Qualcomm Kryo 5XX Cortex-A77 */ CS_AMBA_UCI_ID(0x000cc0af, uci_id_etm4),/* Marvell ThunderX2 */ CS_AMBA_UCI_ID(0x000b6d01, uci_id_etm4),/* HiSilicon-Hip08 */ CS_AMBA_UCI_ID(0x000b6d02, uci_id_etm4),/* HiSilicon-Hip09 */ diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index e5b79bdb9851..3c4d69b096ca 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -919,8 +919,12 @@ struct etmv4_save_state { * @nooverflow: Indicate if overflow prevention is supported. * @atbtrig: If the implementation can support ATB triggers * @lpoverride: If the implementation can support low-power state over. - * @trfc: If the implementation supports Arm v8.4 trace filter controls. + * @trfcr: If the CPU supports FEAT_TRF, value of the TRFCR_ELx that + * allows tracing at all ELs. We don't want to compute this + * at runtime, due to the additional setting of TRFCR_CX when + * in EL2. Otherwise, 0. * @config: structure holding configuration parameters. + * @save_trfcr: Saved TRFCR_EL1 register during a CPU PM event. * @save_state: State to be preserved across power loss * @state_needs_restore: True when there is context to restore after PM exit * @skip_power_up: Indicates if an implementation can skip powering up @@ -971,8 +975,9 @@ struct etmv4_drvdata { bool nooverflow; bool atbtrig; bool lpoverride; - bool trfc; + u64 trfcr; struct etmv4_config config; + u64 save_trfcr; struct etmv4_save_state *save_state; bool state_needs_restore; bool skip_power_up; diff --git a/drivers/hwtracing/coresight/coresight-self-hosted-trace.h b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h new file mode 100644 index 000000000000..53840a2c41f2 --- /dev/null +++ b/drivers/hwtracing/coresight/coresight-self-hosted-trace.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Arm v8 Self-Hosted trace support. + * + * Copyright (C) 2021 ARM Ltd. + */ + +#ifndef __CORESIGHT_SELF_HOSTED_TRACE_H +#define __CORESIGHT_SELF_HOSTED_TRACE_H + +#include <asm/sysreg.h> + +static inline u64 read_trfcr(void) +{ + return read_sysreg_s(SYS_TRFCR_EL1); +} + +static inline void write_trfcr(u64 val) +{ + write_sysreg_s(val, SYS_TRFCR_EL1); + isb(); +} + +static inline u64 cpu_prohibit_trace(void) +{ + u64 trfcr = read_trfcr(); + + /* Prohibit tracing at EL0 & the kernel EL */ + write_trfcr(trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE)); + /* Return the original value of the TRFCR */ + return trfcr; +} +#endif /* __CORESIGHT_SELF_HOSTED_TRACE_H */ diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c index 74c6323d4d6a..d0276af82494 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-core.c +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c @@ -432,6 +432,21 @@ static u32 tmc_etr_get_default_buffer_size(struct device *dev) return size; } +static u32 tmc_etr_get_max_burst_size(struct device *dev) +{ + u32 burst_size; + + if (fwnode_property_read_u32(dev->fwnode, "arm,max-burst-size", + &burst_size)) + return TMC_AXICTL_WR_BURST_16; + + /* Only permissible values are 0 to 15 */ + if (burst_size > 0xF) + burst_size = TMC_AXICTL_WR_BURST_16; + + return burst_size; +} + static int tmc_probe(struct amba_device *adev, const struct amba_id *id) { int ret = 0; @@ -469,10 +484,12 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) /* This device is not associated with a session */ drvdata->pid = -1; - if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) + if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { drvdata->size = tmc_etr_get_default_buffer_size(dev); - else + drvdata->max_burst_size = tmc_etr_get_max_burst_size(dev); + } else { drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; + } desc.dev = dev; desc.groups = core |