diff --git a/Documentation/admin-guide/perf/hisi-pcie-pmu.rst b/Documentation/admin-guide/perf/hisi-pcie-pmu.rst index 7e863662e2d425c4d4dbba831b42648a0cf298ad..82a8c2429dd66f96aa4eb3bcfcf255ba47c4e541 100644 --- a/Documentation/admin-guide/perf/hisi-pcie-pmu.rst +++ b/Documentation/admin-guide/perf/hisi-pcie-pmu.rst @@ -28,7 +28,9 @@ The "identifier" sysfs file allows users to identify the version of the PMU hardware device. The "bus" sysfs file allows users to get the bus number of Root Ports -monitored by PMU. +monitored by PMU. Furthermore users can get the Root Ports range in +[bdf_min, bdf_max] from "bdf_min" and "bdf_max" sysfs attributes +respectively. Example usage of perf:: diff --git a/Documentation/admin-guide/perf/hisi-pmu.rst b/Documentation/admin-guide/perf/hisi-pmu.rst index e0174d20809a18470ab5809c4bd7336247826b15..2a38da0094d2e9a951b17a6e6d6b8a2d7d270393 100644 --- a/Documentation/admin-guide/perf/hisi-pmu.rst +++ b/Documentation/admin-guide/perf/hisi-pmu.rst @@ -18,10 +18,13 @@ HiSilicon SoC uncore PMU driver Each device PMU has separate registers for event counting, control and interrupt, and the PMU driver shall register perf PMU drivers like L3C, HHA and DDRC etc. The available events and configuration options shall -be described in the sysfs, see: +be described in the sysfs, see:: -/sys/devices/hisi_sccl{X}_/, or -/sys/bus/event_source/devices/hisi_sccl{X}_. +/sys/bus/event_source/devices/hisi_sccl{X}_ + +or:: + +/sys/devices/hisi_sccl{X}_ The "perf list" command shall list the available events from sysfs. Each L3C, HHA and DDRC is registered as a separate PMU with perf. The PMU @@ -36,7 +39,10 @@ e.g. hisi_sccl1_hha0/rx_operations is RX_OPERATIONS event of HHA index #0 in SCCL ID #1. The driver also provides a "cpumask" sysfs attribute, which shows the CPU core -ID used to count the uncore PMU event. +ID used to count the uncore PMU event. An "associated_cpus" sysfs attribute is +also provided to show the CPUs associated with this PMU. The "cpumask" indicates +the CPUs to open the events, usually as a hint for userspaces tools like perf. +It only contains one associated CPU from the "associated_cpus". Example usage of perf:: @@ -110,6 +116,50 @@ uring channel. It is 2 bits. Some important codes are as follows: - 2'b00: default value, count the events which sent to the both uring and uring_ext channel; +6. ch: NoC PMU supports filtering the event counts of certain transaction +channel with this option. The current supported channels are as follows: + +- 3'b010: Request channel +- 3'b100: Snoop channel +- 3'b110: Response channel +- 3'b111: Data channel + +7. tt_en: NoC PMU supports counting only transactions that have tracetag set +if this option is set. See the 2nd list for more information about tracetag. + +For HiSilicon uncore PMU v3 whose identifier is 0x40, some uncore PMUs are +further divided into parts for finer granularity of tracing, each part has its +own dedicated PMU, and all such PMUs together cover the monitoring job of events +on particular uncore device. Such PMUs are described in sysfs with name format +slightly changed:: + +/sys/bus/event_source/devices/hisi_sccl{X}_ + +Z is the sub-id, indicating different PMUs for part of hardware device. + +Usage of most PMUs with different sub-ids are identical. Specially, L3C PMU +provides ``ext`` operand to allow exploration of even finer granual statistics +of L3C PMU. L3C PMU driver uses that as hint of termination when delivering +perf command to hardware: + +- ext=0: Default, could be used with event names. +- ext=1 and ext=2: Must be used with event codes, event names are not supported. + +An example of perf command could be:: + + $# perf stat -a -e hisi_sccl0_l3c1_0/rd_spipe/ sleep 5 + +or:: + + $# perf stat -a -e hisi_sccl0_l3c1_0/event=0x1,ext=1/ sleep 5 + +As above, ``hisi_sccl0_l3c1_0`` locates PMU of Super CPU CLuster 0, L3 cache 1 +pipe0. + +First command locates the first part of L3C since ``ext=0`` is implied by +default. Second command issues the counting on another part of L3C with the +event ``0x1``. + Users could configure IDs to count data come from specific CCL/ICL, by setting srcid_cmd & srcid_msk, and data desitined for specific CCL/ICL by setting tgtid_cmd & tgtid_msk. A set bit in srcid_msk/tgtid_msk means the PMU will not diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 48dcc8381ea75dcff819ca29dc45ce58fd4c4531..186be3d02238b1989ca1edeff51c941c1d9fc3ca 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \ hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \ - hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o hisi_uncore_uc_pmu.o + hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o hisi_uncore_uc_pmu.o \ + hisi_uncore_noc_pmu.o hisi_uncore_mn_pmu.o obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o obj-$(CONFIG_HNS3_PMU) += hns3_pmu.o diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c index 4a902da5c1d495d45213ea0f5718dd323bad2bee..cb9024314a911b1fb1be889aaa326d5a896b87e8 100644 --- a/drivers/perf/hisilicon/hisi_pcie_pmu.c +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -152,6 +152,22 @@ static ssize_t bus_show(struct device *dev, struct device_attribute *attr, char } static DEVICE_ATTR_RO(bus); +static ssize_t bdf_min_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#04x\n", pcie_pmu->bdf_min); +} +static DEVICE_ATTR_RO(bdf_min); + +static ssize_t bdf_max_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#04x\n", pcie_pmu->bdf_max); +} +static DEVICE_ATTR_RO(bdf_max); + static struct hisi_pcie_reg_pair hisi_pcie_parse_reg_value(struct hisi_pcie_pmu *pcie_pmu, u32 reg_off) { @@ -771,6 +787,8 @@ static const struct attribute_group hisi_pcie_pmu_format_group = { static struct attribute *hisi_pcie_pmu_bus_attrs[] = { &dev_attr_bus.attr, + &dev_attr_bdf_max.attr, + &dev_attr_bdf_min.attr, NULL }; diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c index 40f1bc9f9b9136df89f2af54ad76fcaafb57b99f..cfc3ed2a79af5d076c6f3051f30972494bc0fc74 100644 --- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c @@ -180,20 +180,18 @@ MODULE_DEVICE_TABLE(acpi, hisi_cpa_pmu_acpi_match); static int hisi_cpa_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *cpa_pmu) { - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &cpa_pmu->sicl_id)) { + hisi_uncore_pmu_init_topology(cpa_pmu, &pdev->dev); + + if (cpa_pmu->topo.sicl_id < 0) { dev_err(&pdev->dev, "Can not read sicl-id\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &cpa_pmu->index_id)) { + if (cpa_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id\n"); return -EINVAL; } - cpa_pmu->ccl_id = -1; - cpa_pmu->sccl_id = -1; cpa_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(cpa_pmu->base)) return PTR_ERR(cpa_pmu->base); @@ -204,7 +202,7 @@ static int hisi_cpa_pmu_init_data(struct platform_device *pdev, } static struct attribute *hisi_cpa_pmu_format_attr[] = { - HISI_PMU_FORMAT_ATTR(event, "config:0-15"), + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), NULL }; @@ -227,34 +225,11 @@ static const struct attribute_group hisi_cpa_pmu_events_group = { .attrs = hisi_cpa_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_cpa_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL -}; - -static const struct attribute_group hisi_cpa_pmu_cpumask_attr_group = { - .attrs = hisi_cpa_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_cpa_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_cpa_pmu_identifier_attrs[] = { - &hisi_cpa_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_cpa_pmu_identifier_group = { - .attrs = hisi_cpa_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_cpa_pmu_attr_groups[] = { &hisi_cpa_pmu_format_group, &hisi_cpa_pmu_events_group, - &hisi_cpa_pmu_cpumask_attr_group, - &hisi_cpa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -311,8 +286,8 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%u", - cpa_pmu->sicl_id, cpa_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_cpa%d", + cpa_pmu->topo.sicl_id, cpa_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -390,6 +365,7 @@ static void __exit hisi_cpa_pmu_module_exit(void) } module_exit(hisi_cpa_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SoC CPA PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Qi Liu "); diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index ffb039d05d07b2a03e07c5a99c0bc8a0c7e9c0a8..b52891d48f05da55fa9098157985666604754584 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -43,12 +43,21 @@ #define DDRC_V2_EVENT_TYPE 0xe74 #define DDRC_V2_PERF_CTRL 0xeA0 +/* DDRC interrupt registers definition in v3 */ +#define DDRC_V3_INT_MASK 0x534 +#define DDRC_V3_INT_STATUS 0x538 +#define DDRC_V3_INT_CLEAR 0x53C + /* DDRC has 8-counters */ #define DDRC_NR_COUNTERS 0x8 #define DDRC_V1_PERF_CTRL_EN 0x2 #define DDRC_V2_PERF_CTRL_EN 0x1 #define DDRC_V1_NR_EVENTS 0x7 -#define DDRC_V2_NR_EVENTS 0x90 +#define DDRC_V2_NR_EVENTS 0xFF + +#define DDRC_EVENT_CNTn(base, n) ((base) + (n) * 8) +#define DDRC_EVENT_TYPEn(base, n) ((base) + (n) * 4) +#define DDRC_UNIMPLEMENTED_REG GENMASK(31, 0) /* * For PMU v1, there are eight-events and every event has been mapped @@ -63,47 +72,37 @@ static const u32 ddrc_reg_off[] = { DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_RNK_CHG, DDRC_RW_CHG }; -/* - * Select the counter register offset using the counter index. - * In PMU v1, there are no programmable counter, the count - * is read form the statistics counter register itself. - */ -static u32 hisi_ddrc_pmu_v1_get_counter_offset(int cntr_idx) -{ - return ddrc_reg_off[cntr_idx]; -} - -static u32 hisi_ddrc_pmu_v2_get_counter_offset(int cntr_idx) -{ - return DDRC_V2_EVENT_CNT + cntr_idx * 8; -} +struct hisi_ddrc_pmu_regs { + u32 event_cnt; + u32 event_ctrl; + u32 event_type; + u32 perf_ctrl; + u32 perf_ctrl_en; + u32 int_mask; + u32 int_clear; + u32 int_status; +}; -static u64 hisi_ddrc_pmu_v1_read_counter(struct hisi_pmu *ddrc_pmu, +static u64 hisi_ddrc_pmu_read_counter(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { - return readl(ddrc_pmu->base + - hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx)); -} + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; -static void hisi_ddrc_pmu_v1_write_counter(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc, u64 val) -{ - writel((u32)val, - ddrc_pmu->base + hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx)); -} + if (regs->event_cnt == DDRC_UNIMPLEMENTED_REG) + return readl(ddrc_pmu->base + ddrc_reg_off[hwc->idx]); -static u64 hisi_ddrc_pmu_v2_read_counter(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) -{ - return readq(ddrc_pmu->base + - hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx)); + return readq(ddrc_pmu->base + DDRC_EVENT_CNTn(regs->event_cnt, hwc->idx)); } -static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc, u64 val) +static void hisi_ddrc_pmu_write_counter(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc, u64 val) { - writeq(val, - ddrc_pmu->base + hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx)); + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; + + if (regs->event_cnt == DDRC_UNIMPLEMENTED_REG) + writel((u32)val, ddrc_pmu->base + ddrc_reg_off[hwc->idx]); + else + writeq(val, ddrc_pmu->base + DDRC_EVENT_CNTn(regs->event_cnt, hwc->idx)); } /* @@ -111,57 +110,15 @@ static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu, * so there is no need to write event type, while it is programmable counter in * PMU v2. */ -static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx, +static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *ddrc_pmu, int idx, u32 type) { - u32 offset; - - if (hha_pmu->identifier >= HISI_PMU_V2) { - offset = DDRC_V2_EVENT_TYPE + 4 * idx; - writel(type, hha_pmu->base + offset); - } -} - -static void hisi_ddrc_pmu_v1_start_counters(struct hisi_pmu *ddrc_pmu) -{ - u32 val; - - /* Set perf_enable in DDRC_PERF_CTRL to start event counting */ - val = readl(ddrc_pmu->base + DDRC_PERF_CTRL); - val |= DDRC_V1_PERF_CTRL_EN; - writel(val, ddrc_pmu->base + DDRC_PERF_CTRL); -} - -static void hisi_ddrc_pmu_v1_stop_counters(struct hisi_pmu *ddrc_pmu) -{ - u32 val; + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; - /* Clear perf_enable in DDRC_PERF_CTRL to stop event counting */ - val = readl(ddrc_pmu->base + DDRC_PERF_CTRL); - val &= ~DDRC_V1_PERF_CTRL_EN; - writel(val, ddrc_pmu->base + DDRC_PERF_CTRL); -} + if (regs->event_type == DDRC_UNIMPLEMENTED_REG) + return; -static void hisi_ddrc_pmu_v1_enable_counter(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) -{ - u32 val; - - /* Set counter index(event code) in DDRC_EVENT_CTRL register */ - val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL); - val |= (1 << GET_DDRC_EVENTID(hwc)); - writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL); -} - -static void hisi_ddrc_pmu_v1_disable_counter(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) -{ - u32 val; - - /* Clear counter index(event code) in DDRC_EVENT_CTRL register */ - val = readl(ddrc_pmu->base + DDRC_EVENT_CTRL); - val &= ~(1 << GET_DDRC_EVENTID(hwc)); - writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL); + writel(type, ddrc_pmu->base + DDRC_EVENT_TYPEn(regs->event_type, idx)); } static int hisi_ddrc_pmu_v1_get_event_idx(struct perf_event *event) @@ -180,140 +137,121 @@ static int hisi_ddrc_pmu_v1_get_event_idx(struct perf_event *event) return idx; } -static int hisi_ddrc_pmu_v2_get_event_idx(struct perf_event *event) +static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event) { + struct hisi_pmu *ddrc_pmu = to_hisi_pmu(event->pmu); + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; + + if (regs->event_type == DDRC_UNIMPLEMENTED_REG) + return hisi_ddrc_pmu_v1_get_event_idx(event); + return hisi_uncore_pmu_get_event_idx(event); } -static void hisi_ddrc_pmu_v2_start_counters(struct hisi_pmu *ddrc_pmu) +static void hisi_ddrc_pmu_start_counters(struct hisi_pmu *ddrc_pmu) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL); - val |= DDRC_V2_PERF_CTRL_EN; - writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL); + val = readl(ddrc_pmu->base + regs->perf_ctrl); + val |= regs->perf_ctrl_en; + writel(val, ddrc_pmu->base + regs->perf_ctrl); } -static void hisi_ddrc_pmu_v2_stop_counters(struct hisi_pmu *ddrc_pmu) +static void hisi_ddrc_pmu_stop_counters(struct hisi_pmu *ddrc_pmu) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL); - val &= ~DDRC_V2_PERF_CTRL_EN; - writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL); + val = readl(ddrc_pmu->base + regs->perf_ctrl); + val &= ~regs->perf_ctrl_en; + writel(val, ddrc_pmu->base + regs->perf_ctrl); } -static void hisi_ddrc_pmu_v2_enable_counter(struct hisi_pmu *ddrc_pmu, +static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL); - val |= 1 << hwc->idx; - writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL); + val = readl(ddrc_pmu->base + regs->event_ctrl); + val |= BIT_ULL(hwc->idx); + writel(val, ddrc_pmu->base + regs->event_ctrl); } -static void hisi_ddrc_pmu_v2_disable_counter(struct hisi_pmu *ddrc_pmu, +static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL); - val &= ~(1 << hwc->idx); - writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL); -} - -static void hisi_ddrc_pmu_v1_enable_counter_int(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) -{ - u32 val; - /* Write 0 to enable interrupt */ - val = readl(ddrc_pmu->base + DDRC_INT_MASK); - val &= ~(1 << hwc->idx); - writel(val, ddrc_pmu->base + DDRC_INT_MASK); + val = readl(ddrc_pmu->base + regs->event_ctrl); + val &= ~BIT_ULL(hwc->idx); + writel(val, ddrc_pmu->base + regs->event_ctrl); } -static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) +static void hisi_ddrc_pmu_enable_counter_int(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - /* Write 1 to mask interrupt */ - val = readl(ddrc_pmu->base + DDRC_INT_MASK); - val |= 1 << hwc->idx; - writel(val, ddrc_pmu->base + DDRC_INT_MASK); + val = readl(ddrc_pmu->base + regs->int_mask); + val &= ~BIT_ULL(hwc->idx); + writel(val, ddrc_pmu->base + regs->int_mask); } -static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) +static void hisi_ddrc_pmu_disable_counter_int(struct hisi_pmu *ddrc_pmu, + struct hw_perf_event *hwc) { + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); - val &= ~(1 << hwc->idx); - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); -} -static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu, - struct hw_perf_event *hwc) -{ - u32 val; - - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); - val |= 1 << hwc->idx; - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); + val = readl(ddrc_pmu->base + regs->int_mask); + val |= BIT_ULL(hwc->idx); + writel(val, ddrc_pmu->base + regs->int_mask); } -static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu) +static u32 hisi_ddrc_pmu_get_int_status(struct hisi_pmu *ddrc_pmu) { - return readl(ddrc_pmu->base + DDRC_INT_STATUS); -} + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; -static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu, - int idx) -{ - writel(1 << idx, ddrc_pmu->base + DDRC_INT_CLEAR); + return readl(ddrc_pmu->base + regs->int_status); } -static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu) +static void hisi_ddrc_pmu_clear_int_status(struct hisi_pmu *ddrc_pmu, + int idx) { - return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS); -} + struct hisi_ddrc_pmu_regs *regs = ddrc_pmu->dev_info->private; -static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu, - int idx) -{ - writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR); + writel(1 << idx, ddrc_pmu->base + regs->int_clear); } -static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = { - { "HISI0233", }, - { "HISI0234", }, - {} -}; -MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match); - static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *ddrc_pmu) { + hisi_uncore_pmu_init_topology(ddrc_pmu, &pdev->dev); + /* * Use the SCCL_ID and DDRC channel ID to identify the * DDRC PMU, while SCCL_ID is in MPIDR[aff2]. */ if (device_property_read_u32(&pdev->dev, "hisilicon,ch-id", - &ddrc_pmu->index_id)) { + &ddrc_pmu->topo.index_id)) { dev_err(&pdev->dev, "Can not read ddrc channel-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &ddrc_pmu->sccl_id)) { + if (ddrc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read ddrc sccl-id!\n"); return -EINVAL; } - /* DDRC PMUs only share the same SCCL */ - ddrc_pmu->ccl_id = -1; + + ddrc_pmu->dev_info = device_get_match_data(&pdev->dev); + if (!ddrc_pmu->dev_info) + return -ENODEV; ddrc_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ddrc_pmu->base)) { @@ -323,8 +261,7 @@ static int hisi_ddrc_pmu_init_data(struct platform_device *pdev, ddrc_pmu->identifier = readl(ddrc_pmu->base + DDRC_VERSION); if (ddrc_pmu->identifier >= HISI_PMU_V2) { - if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id", - &ddrc_pmu->sub_id)) { + if (ddrc_pmu->topo.sub_id < 0) { dev_err(&pdev->dev, "Can not read sub-id!\n"); return -EINVAL; } @@ -382,73 +319,35 @@ static const struct attribute_group hisi_ddrc_pmu_v2_events_group = { .attrs = hisi_ddrc_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_ddrc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_ddrc_pmu_cpumask_attr_group = { - .attrs = hisi_ddrc_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_ddrc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_ddrc_pmu_identifier_attrs[] = { - &hisi_ddrc_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_ddrc_pmu_identifier_group = { - .attrs = hisi_ddrc_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_ddrc_pmu_v1_attr_groups[] = { &hisi_ddrc_pmu_v1_format_group, &hisi_ddrc_pmu_v1_events_group, - &hisi_ddrc_pmu_cpumask_attr_group, - &hisi_ddrc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_ddrc_pmu_v2_attr_groups[] = { &hisi_ddrc_pmu_v2_format_group, &hisi_ddrc_pmu_v2_events_group, - &hisi_ddrc_pmu_cpumask_attr_group, - &hisi_ddrc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; -static const struct hisi_uncore_ops hisi_uncore_ddrc_v1_ops = { +static const struct hisi_uncore_ops hisi_uncore_ddrc_ops = { .write_evtype = hisi_ddrc_pmu_write_evtype, - .get_event_idx = hisi_ddrc_pmu_v1_get_event_idx, - .start_counters = hisi_ddrc_pmu_v1_start_counters, - .stop_counters = hisi_ddrc_pmu_v1_stop_counters, - .enable_counter = hisi_ddrc_pmu_v1_enable_counter, - .disable_counter = hisi_ddrc_pmu_v1_disable_counter, - .enable_counter_int = hisi_ddrc_pmu_v1_enable_counter_int, - .disable_counter_int = hisi_ddrc_pmu_v1_disable_counter_int, - .write_counter = hisi_ddrc_pmu_v1_write_counter, - .read_counter = hisi_ddrc_pmu_v1_read_counter, - .get_int_status = hisi_ddrc_pmu_v1_get_int_status, - .clear_int_status = hisi_ddrc_pmu_v1_clear_int_status, -}; - -static const struct hisi_uncore_ops hisi_uncore_ddrc_v2_ops = { - .write_evtype = hisi_ddrc_pmu_write_evtype, - .get_event_idx = hisi_ddrc_pmu_v2_get_event_idx, - .start_counters = hisi_ddrc_pmu_v2_start_counters, - .stop_counters = hisi_ddrc_pmu_v2_stop_counters, - .enable_counter = hisi_ddrc_pmu_v2_enable_counter, - .disable_counter = hisi_ddrc_pmu_v2_disable_counter, - .enable_counter_int = hisi_ddrc_pmu_v2_enable_counter_int, - .disable_counter_int = hisi_ddrc_pmu_v2_disable_counter_int, - .write_counter = hisi_ddrc_pmu_v2_write_counter, - .read_counter = hisi_ddrc_pmu_v2_read_counter, - .get_int_status = hisi_ddrc_pmu_v2_get_int_status, - .clear_int_status = hisi_ddrc_pmu_v2_clear_int_status, + .get_event_idx = hisi_ddrc_pmu_get_event_idx, + .start_counters = hisi_ddrc_pmu_start_counters, + .stop_counters = hisi_ddrc_pmu_stop_counters, + .enable_counter = hisi_ddrc_pmu_enable_counter, + .disable_counter = hisi_ddrc_pmu_disable_counter, + .enable_counter_int = hisi_ddrc_pmu_enable_counter_int, + .disable_counter_int = hisi_ddrc_pmu_disable_counter_int, + .write_counter = hisi_ddrc_pmu_write_counter, + .read_counter = hisi_ddrc_pmu_read_counter, + .get_int_status = hisi_ddrc_pmu_get_int_status, + .clear_int_status = hisi_ddrc_pmu_clear_int_status, }; static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev, @@ -464,19 +363,11 @@ static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev, if (ret) return ret; - if (ddrc_pmu->identifier >= HISI_PMU_V2) { - ddrc_pmu->counter_bits = 48; - ddrc_pmu->check_event = DDRC_V2_NR_EVENTS; - ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v2_attr_groups; - ddrc_pmu->ops = &hisi_uncore_ddrc_v2_ops; - } else { - ddrc_pmu->counter_bits = 32; - ddrc_pmu->check_event = DDRC_V1_NR_EVENTS; - ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v1_attr_groups; - ddrc_pmu->ops = &hisi_uncore_ddrc_v1_ops; - } - + ddrc_pmu->pmu_events.attr_groups = ddrc_pmu->dev_info->attr_groups; + ddrc_pmu->counter_bits = ddrc_pmu->dev_info->counter_bits; + ddrc_pmu->check_event = ddrc_pmu->dev_info->check_event; ddrc_pmu->num_counters = DDRC_NR_COUNTERS; + ddrc_pmu->ops = &hisi_uncore_ddrc_ops; ddrc_pmu->dev = &pdev->dev; ddrc_pmu->on_cpu = -1; @@ -501,13 +392,13 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev) if (ddrc_pmu->identifier >= HISI_PMU_V2) name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "hisi_sccl%u_ddrc%u_%u", - ddrc_pmu->sccl_id, ddrc_pmu->index_id, - ddrc_pmu->sub_id); + "hisi_sccl%d_ddrc%d_%d", + ddrc_pmu->topo.sccl_id, ddrc_pmu->topo.index_id, + ddrc_pmu->topo.sub_id); else name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id, - ddrc_pmu->index_id); + "hisi_sccl%d_ddrc%d", ddrc_pmu->topo.sccl_id, + ddrc_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -541,6 +432,68 @@ static int hisi_ddrc_pmu_remove(struct platform_device *pdev) return 0; } +static struct hisi_ddrc_pmu_regs hisi_ddrc_v1_pmu_regs = { + .event_cnt = DDRC_UNIMPLEMENTED_REG, + .event_ctrl = DDRC_EVENT_CTRL, + .event_type = DDRC_UNIMPLEMENTED_REG, + .perf_ctrl = DDRC_PERF_CTRL, + .perf_ctrl_en = DDRC_V1_PERF_CTRL_EN, + .int_mask = DDRC_INT_MASK, + .int_clear = DDRC_INT_CLEAR, + .int_status = DDRC_INT_STATUS, +}; + +static const struct hisi_pmu_dev_info hisi_ddrc_v1 = { + .counter_bits = 32, + .check_event = DDRC_V1_NR_EVENTS, + .attr_groups = hisi_ddrc_pmu_v1_attr_groups, + .private = &hisi_ddrc_v1_pmu_regs, +}; + +static struct hisi_ddrc_pmu_regs hisi_ddrc_v2_pmu_regs = { + .event_cnt = DDRC_V2_EVENT_CNT, + .event_ctrl = DDRC_V2_EVENT_CTRL, + .event_type = DDRC_V2_EVENT_TYPE, + .perf_ctrl = DDRC_V2_PERF_CTRL, + .perf_ctrl_en = DDRC_V2_PERF_CTRL_EN, + .int_mask = DDRC_V2_INT_MASK, + .int_clear = DDRC_V2_INT_CLEAR, + .int_status = DDRC_V2_INT_STATUS, +}; + +static const struct hisi_pmu_dev_info hisi_ddrc_v2 = { + .counter_bits = 48, + .check_event = DDRC_V2_NR_EVENTS, + .attr_groups = hisi_ddrc_pmu_v2_attr_groups, + .private = &hisi_ddrc_v2_pmu_regs, +}; + +static struct hisi_ddrc_pmu_regs hisi_ddrc_v3_pmu_regs = { + .event_cnt = DDRC_V2_EVENT_CNT, + .event_ctrl = DDRC_V2_EVENT_CTRL, + .event_type = DDRC_V2_EVENT_TYPE, + .perf_ctrl = DDRC_V2_PERF_CTRL, + .perf_ctrl_en = DDRC_V2_PERF_CTRL_EN, + .int_mask = DDRC_V3_INT_MASK, + .int_clear = DDRC_V3_INT_CLEAR, + .int_status = DDRC_V3_INT_STATUS, +}; + +static const struct hisi_pmu_dev_info hisi_ddrc_v3 = { + .counter_bits = 48, + .check_event = DDRC_V2_NR_EVENTS, + .attr_groups = hisi_ddrc_pmu_v2_attr_groups, + .private = &hisi_ddrc_v3_pmu_regs, +}; + +static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = { + { "HISI0233", (kernel_ulong_t)&hisi_ddrc_v1}, + { "HISI0234", (kernel_ulong_t)&hisi_ddrc_v2}, + { "HISI0235", (kernel_ulong_t)&hisi_ddrc_v3 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match); + static struct platform_driver hisi_ddrc_pmu_driver = { .driver = { .name = "hisi_ddrc_pmu", @@ -576,10 +529,10 @@ static void __exit hisi_ddrc_pmu_module_exit(void) { platform_driver_unregister(&hisi_ddrc_pmu_driver); cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE); - } module_exit(hisi_ddrc_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SoC DDRC uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index 15caf99e1eefe22f2cd6399258eeb73702bee790..a0a467cc2f49e9b7b703067c987a4f257cd06163 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -47,9 +47,9 @@ #define HHA_SRCID_CMD GENMASK(16, 6) #define HHA_SRCID_MSK GENMASK(30, 20) #define HHA_DATSRC_SKT_EN BIT(23) -#define HHA_EVTYPE_NONE 0xff +#define HHA_EVTYPE_MASK GENMASK(7, 0) #define HHA_V1_NR_EVENT 0x65 -#define HHA_V2_NR_EVENT 0xCE +#define HHA_V2_NR_EVENT 0xFF HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 10, 0); HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 21, 11); @@ -197,7 +197,7 @@ static void hisi_hha_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx, /* Write event code to HHA_EVENT_TYPEx register */ val = readl(hha_pmu->base + reg); - val &= ~(HHA_EVTYPE_NONE << shift); + val &= ~(HHA_EVTYPE_MASK << shift); val |= (type << shift); writel(val, hha_pmu->base + reg); } @@ -295,12 +295,13 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, unsigned long long id; acpi_status status; + hisi_uncore_pmu_init_topology(hha_pmu, &pdev->dev); + /* * Use SCCL_ID and UID to identify the HHA PMU, while * SCCL_ID is in MPIDR[aff2]. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &hha_pmu->sccl_id)) { + if (hha_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read hha sccl-id!\n"); return -EINVAL; } @@ -309,8 +310,7 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, * Early versions of BIOS support _UID by mistake, so we support * both "hisilicon, idx-id" as preference, if available. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &hha_pmu->index_id)) { + if (hha_pmu->topo.index_id < 0) { status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), "_UID", NULL, &id); if (ACPI_FAILURE(status)) { @@ -318,10 +318,8 @@ static int hisi_hha_pmu_init_data(struct platform_device *pdev, return -EINVAL; } - hha_pmu->index_id = id; + hha_pmu->topo.index_id = id; } - /* HHA PMUs only share the same SCCL */ - hha_pmu->ccl_id = -1; hha_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hha_pmu->base)) { @@ -407,42 +405,19 @@ static const struct attribute_group hisi_hha_pmu_v2_events_group = { .attrs = hisi_hha_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_hha_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_hha_pmu_cpumask_attr_group = { - .attrs = hisi_hha_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_hha_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_hha_pmu_identifier_attrs[] = { - &hisi_hha_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_hha_pmu_identifier_group = { - .attrs = hisi_hha_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_hha_pmu_v1_attr_groups[] = { &hisi_hha_pmu_v1_format_group, &hisi_hha_pmu_v1_events_group, - &hisi_hha_pmu_cpumask_attr_group, - &hisi_hha_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_hha_pmu_v2_attr_groups[] = { &hisi_hha_pmu_v2_format_group, &hisi_hha_pmu_v2_events_group, - &hisi_hha_pmu_cpumask_attr_group, - &hisi_hha_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -510,8 +485,8 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u", - hha_pmu->sccl_id, hha_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_hha%d", + hha_pmu->topo.sccl_id, hha_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -582,6 +557,7 @@ static void __exit hisi_hha_pmu_module_exit(void) } module_exit(hisi_hha_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SoC HHA uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 794dbcd19b7a7146b97c0f7f1b55e6b0e5f92ffd..d0ddab874d3d5e7d05e18923937eea6c52c031ec 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -46,6 +47,7 @@ #define L3C_TRACETAG_MARK_EN BIT(0) #define L3C_TRACETAG_REQ_EN (L3C_TRACETAG_MARK_EN | BIT(2)) #define L3C_TRACETAG_CORE_EN (L3C_TRACETAG_MARK_EN | BIT(3)) +#define L3C_TRACETAG_CACHEABLE_EN BIT(12) #define L3C_CORE_EN BIT(20) #define L3C_COER_NONE 0x0 #define L3C_DATSRC_MASK 0xFF @@ -55,59 +57,165 @@ #define L3C_V1_NR_EVENTS 0x59 #define L3C_V2_NR_EVENTS 0xFF -HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_core, config1, 7, 0); +HISI_PMU_EVENT_ATTR_EXTRACTOR(ext, config, 16, 16); + +#define L3C_PG_INFO_MASK(x) GENMASK_ULL((x) - 1, 0) +#define L3C_MAX_CPU 64 + +#define SMT_PER_CORE (cpu_smt_possible() ? 2 : 1) +#define PORT_PER_CORE 2 + HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_req, config1, 10, 8); HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_cfg, config1, 15, 11); HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_skt, config1, 16, 16); +HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_cacheable, config1, 17, 17); +HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_core, config2, 15, 0); + +struct hisi_l3c_pmu { + struct hisi_pmu l3c_pmu; + unsigned long feature; +#define L3C_PMU_FEAT_EXT 0x1 + + /* MMIO and IRQ resources for extension events */ + void __iomem *ext_base; + int ext_irq; + int core_config[L3C_MAX_CPU]; +}; -static void hisi_l3c_pmu_config_req_tracetag(struct perf_event *event) +enum hisi_l3c_cpu_substitute { + ROLL_OVER = 0, + LAST_UP = 1, +}; + +#define to_hisi_l3c_pmu(_l3c_pmu) \ + container_of(_l3c_pmu, struct hisi_l3c_pmu, l3c_pmu) + +/* + * The hardware counter idx used in counter enable/disable, + * interrupt enable/disable and status check, etc. + */ +#define L3C_HW_IDX(_idx) ((_idx) % L3C_NR_COUNTERS) + +static int hisi_l3c_pmu_get_event_idx(struct perf_event *event) { struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + unsigned long *used_mask = l3c_pmu->pmu_events.used_mask; + u32 num_counters = l3c_pmu->num_counters; + struct hisi_l3c_pmu *hisi_l3c_pmu; + int idx; + + hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + + /* + * For an L3C PMU that supports extension events, we can monitor + * maximum 2 * num_counters events. Thus use bit [0, num_counters - 1] + * for normal events and bit [num_counters, 2 * num_counters - 1] for + * extension events. The idx allocation will keep unchanged for normal + * events and we can also use the idx to distinguish whether it's an + * extension event or not. + * + * Since normal events and extension events locates on the different + * address space, save the base address to the event->hw.event_base. + */ + if (hisi_get_ext(event)) { + if (!(hisi_l3c_pmu->feature & L3C_PMU_FEAT_EXT)) + return -EOPNOTSUPP; + + event->hw.event_base = (unsigned long)hisi_l3c_pmu->ext_base; + idx = find_next_zero_bit(used_mask, num_counters, L3C_NR_COUNTERS); + } else { + event->hw.event_base = (unsigned long)l3c_pmu->base; + idx = find_next_zero_bit(used_mask, L3C_NR_COUNTERS, 0); + if (idx == L3C_NR_COUNTERS) + idx = num_counters; + } + + if (idx == num_counters) + return -EAGAIN; + + set_bit(idx, used_mask); + + WARN_ON(hisi_get_ext(event) && idx < L3C_NR_COUNTERS); + WARN_ON(!hisi_get_ext(event) && idx >= L3C_NR_COUNTERS); + + return idx; +} + +static u32 hisi_l3c_pmu_event_readl(struct hw_perf_event *hwc, u32 reg) +{ + return readl((void __iomem *)hwc->event_base + reg); +} + +static void hisi_l3c_pmu_event_writel(struct hw_perf_event *hwc, u32 reg, u32 val) +{ + writel(val, (void __iomem *)hwc->event_base + reg); +} + +static u64 hisi_l3c_pmu_event_readq(struct hw_perf_event *hwc, u32 reg) +{ + return readq((void __iomem *)hwc->event_base + reg); +} + +static void hisi_l3c_pmu_event_writeq(struct hw_perf_event *hwc, u32 reg, u64 val) +{ + writeq(val, (void __iomem *)hwc->event_base + reg); +} + +static void hisi_l3c_pmu_config_req_tracetag(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; u32 tt_req = hisi_get_tt_req(event); if (tt_req) { u32 val; /* Set request-type for tracetag */ - val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_TRACETAG_CTRL); val |= tt_req << L3C_TRACETAG_REQ_SHIFT; val |= L3C_TRACETAG_REQ_EN; - writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL); + + if (hisi_get_tt_cacheable(event)) + val |= L3C_TRACETAG_CACHEABLE_EN; + + hisi_l3c_pmu_event_writel(hwc, L3C_TRACETAG_CTRL, val); /* Enable request-tracetag statistics */ - val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_PERF_CTRL); val |= L3C_TRACETAG_EN; - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_PERF_CTRL, val); } } static void hisi_l3c_pmu_clear_req_tracetag(struct perf_event *event) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; u32 tt_req = hisi_get_tt_req(event); if (tt_req) { u32 val; /* Clear request-type */ - val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_TRACETAG_CTRL); val &= ~(tt_req << L3C_TRACETAG_REQ_SHIFT); val &= ~L3C_TRACETAG_REQ_EN; - writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL); + + if (hisi_get_tt_cacheable(event)) + val &= ~L3C_TRACETAG_CACHEABLE_EN; + + hisi_l3c_pmu_event_writel(hwc, L3C_TRACETAG_CTRL, val); /* Disable request-tracetag statistics */ - val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_PERF_CTRL); val &= ~L3C_TRACETAG_EN; - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_PERF_CTRL, val); } } static void hisi_l3c_pmu_write_ds(struct perf_event *event, u32 ds_cfg) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; u32 reg, reg_idx, shift, val; - int idx = hwc->idx; + int idx = L3C_HW_IDX(hwc->idx); /* * Select the appropriate datasource register(L3C_DATSRC_TYPE0/1). @@ -120,15 +228,15 @@ static void hisi_l3c_pmu_write_ds(struct perf_event *event, u32 ds_cfg) reg_idx = idx % 4; shift = 8 * reg_idx; - val = readl(l3c_pmu->base + reg); + val = hisi_l3c_pmu_event_readl(hwc, reg); val &= ~(L3C_DATSRC_MASK << shift); val |= ds_cfg << shift; - writel(val, l3c_pmu->base + reg); + hisi_l3c_pmu_event_writel(hwc, reg, val); } static void hisi_l3c_pmu_config_ds(struct perf_event *event) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; u32 ds_cfg = hisi_get_datasrc_cfg(event); u32 ds_skt = hisi_get_datasrc_skt(event); @@ -138,15 +246,15 @@ static void hisi_l3c_pmu_config_ds(struct perf_event *event) if (ds_skt) { u32 val; - val = readl(l3c_pmu->base + L3C_DATSRC_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_DATSRC_CTRL); val |= L3C_DATSRC_SKT_EN; - writel(val, l3c_pmu->base + L3C_DATSRC_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_DATSRC_CTRL, val); } } static void hisi_l3c_pmu_clear_ds(struct perf_event *event) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; u32 ds_cfg = hisi_get_datasrc_cfg(event); u32 ds_skt = hisi_get_datasrc_skt(event); @@ -156,57 +264,87 @@ static void hisi_l3c_pmu_clear_ds(struct perf_event *event) if (ds_skt) { u32 val; - val = readl(l3c_pmu->base + L3C_DATSRC_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_DATSRC_CTRL); val &= ~L3C_DATSRC_SKT_EN; - writel(val, l3c_pmu->base + L3C_DATSRC_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_DATSRC_CTRL, val); + } +} + +static u32 hisi_l3c_pmu_cluster_cpu_substitute(struct hisi_l3c_pmu *hisi_l3c_pmu, + u32 core) +{ + int *core_config = hisi_l3c_pmu->core_config; + unsigned long tt_core_config = core; + int bit, offset, pcpu, sub_cpu; + unsigned long tt_core = 0; + + int smt_per_core = SMT_PER_CORE; + + for_each_set_bit(bit, &tt_core_config, BITS_PER_TYPE(u32)) { + offset = bit % smt_per_core; + pcpu = bit / smt_per_core; + sub_cpu = core_config[pcpu] * PORT_PER_CORE + offset; + tt_core |= BIT(sub_cpu); } + + return tt_core; } static void hisi_l3c_pmu_config_core_tracetag(struct perf_event *event) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu); + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(hisi_pmu); + struct hw_perf_event *hwc = &event->hw; u32 core = hisi_get_tt_core(event); + u32 val; - if (core) { - u32 val; + if (!core) + return; - /* Config and enable core information */ - writel(core, l3c_pmu->base + L3C_CORE_CTRL); - val = readl(l3c_pmu->base + L3C_PERF_CTRL); - val |= L3C_CORE_EN; - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + core = hisi_l3c_pmu_cluster_cpu_substitute(hisi_l3c_pmu, core); - /* Enable core-tracetag statistics */ - val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL); - val |= L3C_TRACETAG_CORE_EN; - writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL); - } + /* Config and enable core information */ + hisi_l3c_pmu_event_writel(hwc, L3C_CORE_CTRL, core); + val = hisi_l3c_pmu_event_readl(hwc, L3C_PERF_CTRL); + val |= L3C_CORE_EN; + hisi_l3c_pmu_event_writel(hwc, L3C_PERF_CTRL, val); + + /* Enable core-tracetag statistics */ + val = hisi_l3c_pmu_event_readl(hwc, L3C_TRACETAG_CTRL); + val |= L3C_TRACETAG_CORE_EN; + hisi_l3c_pmu_event_writel(hwc, L3C_TRACETAG_CTRL, val); } static void hisi_l3c_pmu_clear_core_tracetag(struct perf_event *event) { - struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; u32 core = hisi_get_tt_core(event); if (core) { u32 val; /* Clear core information */ - writel(L3C_COER_NONE, l3c_pmu->base + L3C_CORE_CTRL); - val = readl(l3c_pmu->base + L3C_PERF_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_CORE_CTRL, L3C_COER_NONE); + val = hisi_l3c_pmu_event_readl(hwc, L3C_PERF_CTRL); val &= ~L3C_CORE_EN; - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_PERF_CTRL, val); /* Disable core-tracetag statistics */ - val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_TRACETAG_CTRL); val &= ~L3C_TRACETAG_CORE_EN; - writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL); + hisi_l3c_pmu_event_writel(hwc, L3C_TRACETAG_CTRL, val); } } +static bool hisi_l3c_pmu_have_filter(struct perf_event *event) +{ + return hisi_get_tt_req(event) || hisi_get_tt_core(event) || + hisi_get_datasrc_cfg(event) || hisi_get_datasrc_skt(event); +} + static void hisi_l3c_pmu_enable_filter(struct perf_event *event) { - if (event->attr.config1 != 0x0) { + if (hisi_l3c_pmu_have_filter(event)) { hisi_l3c_pmu_config_req_tracetag(event); hisi_l3c_pmu_config_core_tracetag(event); hisi_l3c_pmu_config_ds(event); @@ -215,7 +353,7 @@ static void hisi_l3c_pmu_enable_filter(struct perf_event *event) static void hisi_l3c_pmu_disable_filter(struct perf_event *event) { - if (event->attr.config1 != 0x0) { + if (hisi_l3c_pmu_have_filter(event)) { hisi_l3c_pmu_clear_ds(event); hisi_l3c_pmu_clear_core_tracetag(event); hisi_l3c_pmu_clear_req_tracetag(event); @@ -227,26 +365,29 @@ static void hisi_l3c_pmu_disable_filter(struct perf_event *event) */ static u32 hisi_l3c_pmu_get_counter_offset(int cntr_idx) { - return (L3C_CNTR0_LOWER + (cntr_idx * 8)); + return (L3C_CNTR0_LOWER + (L3C_HW_IDX(cntr_idx) * 8)); } static u64 hisi_l3c_pmu_read_counter(struct hisi_pmu *l3c_pmu, struct hw_perf_event *hwc) { - return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx)); + return hisi_l3c_pmu_event_readq(hwc, hisi_l3c_pmu_get_counter_offset(hwc->idx)); } static void hisi_l3c_pmu_write_counter(struct hisi_pmu *l3c_pmu, struct hw_perf_event *hwc, u64 val) { - writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx)); + hisi_l3c_pmu_event_writeq(hwc, hisi_l3c_pmu_get_counter_offset(hwc->idx), val); } static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx, u32 type) { + struct hw_perf_event *hwc = &l3c_pmu->pmu_events.hw_events[idx]->hw; u32 reg, reg_idx, shift, val; + idx = L3C_HW_IDX(idx); + /* * Select the appropriate event select register(L3C_EVENT_TYPE0/1). * There are 2 event select registers for the 8 hardware counters. @@ -259,36 +400,56 @@ static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx, shift = 8 * reg_idx; /* Write event code to L3C_EVENT_TYPEx Register */ - val = readl(l3c_pmu->base + reg); + val = hisi_l3c_pmu_event_readl(hwc, reg); val &= ~(L3C_EVTYPE_NONE << shift); val |= (type << shift); - writel(val, l3c_pmu->base + reg); + hisi_l3c_pmu_event_writel(hwc, reg, val); } static void hisi_l3c_pmu_start_counters(struct hisi_pmu *l3c_pmu) { + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + unsigned long *used_mask = l3c_pmu->pmu_events.used_mask; u32 val; /* * Set perf_enable bit in L3C_PERF_CTRL register to start counting * for all enabled counters. */ - val = readl(l3c_pmu->base + L3C_PERF_CTRL); - val |= L3C_PERF_CTRL_EN; - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + if (find_first_bit(used_mask, l3c_pmu->num_counters) < L3C_NR_COUNTERS) { + val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val |= L3C_PERF_CTRL_EN; + writel(val, l3c_pmu->base + L3C_PERF_CTRL); + } + + if (find_next_bit(used_mask, l3c_pmu->num_counters, L3C_NR_COUNTERS) != l3c_pmu->num_counters) { + val = readl(hisi_l3c_pmu->ext_base + L3C_PERF_CTRL); + val |= L3C_PERF_CTRL_EN; + writel(val, hisi_l3c_pmu->ext_base + L3C_PERF_CTRL); + } } static void hisi_l3c_pmu_stop_counters(struct hisi_pmu *l3c_pmu) { + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + unsigned long *used_mask = l3c_pmu->pmu_events.used_mask; u32 val; /* * Clear perf_enable bit in L3C_PERF_CTRL register to stop counting * for all enabled counters. */ - val = readl(l3c_pmu->base + L3C_PERF_CTRL); - val &= ~(L3C_PERF_CTRL_EN); - writel(val, l3c_pmu->base + L3C_PERF_CTRL); + if (find_first_bit(used_mask, l3c_pmu->num_counters) < L3C_NR_COUNTERS) { + val = readl(l3c_pmu->base + L3C_PERF_CTRL); + val &= ~(L3C_PERF_CTRL_EN); + writel(val, l3c_pmu->base + L3C_PERF_CTRL); + } + + if (find_next_bit(used_mask, l3c_pmu->num_counters, L3C_NR_COUNTERS) != l3c_pmu->num_counters) { + val = readl(hisi_l3c_pmu->ext_base + L3C_PERF_CTRL); + val &= ~(L3C_PERF_CTRL_EN); + writel(val, hisi_l3c_pmu->ext_base + L3C_PERF_CTRL); + } } static void hisi_l3c_pmu_enable_counter(struct hisi_pmu *l3c_pmu, @@ -297,9 +458,9 @@ static void hisi_l3c_pmu_enable_counter(struct hisi_pmu *l3c_pmu, u32 val; /* Enable counter index in L3C_EVENT_CTRL register */ - val = readl(l3c_pmu->base + L3C_EVENT_CTRL); - val |= (1 << hwc->idx); - writel(val, l3c_pmu->base + L3C_EVENT_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_EVENT_CTRL); + val |= (1 << L3C_HW_IDX(hwc->idx)); + hisi_l3c_pmu_event_writel(hwc, L3C_EVENT_CTRL, val); } static void hisi_l3c_pmu_disable_counter(struct hisi_pmu *l3c_pmu, @@ -308,9 +469,9 @@ static void hisi_l3c_pmu_disable_counter(struct hisi_pmu *l3c_pmu, u32 val; /* Clear counter index in L3C_EVENT_CTRL register */ - val = readl(l3c_pmu->base + L3C_EVENT_CTRL); - val &= ~(1 << hwc->idx); - writel(val, l3c_pmu->base + L3C_EVENT_CTRL); + val = hisi_l3c_pmu_event_readl(hwc, L3C_EVENT_CTRL); + val &= ~(1 << L3C_HW_IDX(hwc->idx)); + hisi_l3c_pmu_event_writel(hwc, L3C_EVENT_CTRL, val); } static void hisi_l3c_pmu_enable_counter_int(struct hisi_pmu *l3c_pmu, @@ -318,10 +479,10 @@ static void hisi_l3c_pmu_enable_counter_int(struct hisi_pmu *l3c_pmu, { u32 val; - val = readl(l3c_pmu->base + L3C_INT_MASK); + val = hisi_l3c_pmu_event_readl(hwc, L3C_INT_MASK); /* Write 0 to enable interrupt */ - val &= ~(1 << hwc->idx); - writel(val, l3c_pmu->base + L3C_INT_MASK); + val &= ~(1 << L3C_HW_IDX(hwc->idx)); + hisi_l3c_pmu_event_writel(hwc, L3C_INT_MASK, val); } static void hisi_l3c_pmu_disable_counter_int(struct hisi_pmu *l3c_pmu, @@ -329,48 +490,54 @@ static void hisi_l3c_pmu_disable_counter_int(struct hisi_pmu *l3c_pmu, { u32 val; - val = readl(l3c_pmu->base + L3C_INT_MASK); + val = hisi_l3c_pmu_event_readl(hwc, L3C_INT_MASK); /* Write 1 to mask interrupt */ - val |= (1 << hwc->idx); - writel(val, l3c_pmu->base + L3C_INT_MASK); + val |= (1 << L3C_HW_IDX(hwc->idx)); + hisi_l3c_pmu_event_writel(hwc, L3C_INT_MASK, val); } static u32 hisi_l3c_pmu_get_int_status(struct hisi_pmu *l3c_pmu) { - return readl(l3c_pmu->base + L3C_INT_STATUS); + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + u32 status, status_ext = 0; + + status = readl(l3c_pmu->base + L3C_INT_STATUS); + if (hisi_l3c_pmu->feature & L3C_PMU_FEAT_EXT) + status_ext = readl(hisi_l3c_pmu->ext_base + L3C_INT_STATUS); + + return status | (status_ext << L3C_NR_COUNTERS); } static void hisi_l3c_pmu_clear_int_status(struct hisi_pmu *l3c_pmu, int idx) { - writel(1 << idx, l3c_pmu->base + L3C_INT_CLEAR); -} + struct hw_perf_event *hwc = &l3c_pmu->pmu_events.hw_events[idx]->hw; -static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = { - { "HISI0213", }, - { "HISI0214", }, - {} -}; -MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match); + hisi_l3c_pmu_event_writel(hwc, L3C_INT_CLEAR, 1 << L3C_HW_IDX(idx)); +} static int hisi_l3c_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *l3c_pmu) { + hisi_uncore_pmu_init_topology(l3c_pmu, &pdev->dev); + /* * Use the SCCL_ID and CCL_ID to identify the L3C PMU, while * SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1]. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &l3c_pmu->sccl_id)) { + if (l3c_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read l3c sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id", - &l3c_pmu->ccl_id)) { + if (l3c_pmu->topo.ccl_id < 0) { dev_err(&pdev->dev, "Can not read l3c ccl-id!\n"); return -EINVAL; } + l3c_pmu->dev_info = device_get_match_data(&pdev->dev); + if (!l3c_pmu->dev_info) + return -ENODEV; + l3c_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(l3c_pmu->base)) { dev_err(&pdev->dev, "ioremap failed for l3c_pmu resource\n"); @@ -382,6 +549,41 @@ static int hisi_l3c_pmu_init_data(struct platform_device *pdev, return 0; } +static int hisi_l3c_pmu_init_ext(struct hisi_pmu *l3c_pmu, struct platform_device *pdev) +{ + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + char *irqname; + int ret, irq; + + hisi_l3c_pmu->ext_base = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(hisi_l3c_pmu->ext_base)) + return PTR_ERR(hisi_l3c_pmu->ext_base); + + irq = platform_get_irq(pdev, 1); + /* + * We may don't need to handle -EPROBDEFER since we should have already + * handle it when probling irq[0]. + */ + if (irq < 0) + return irq; + + irqname = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s ext", dev_name(&pdev->dev)); + if (!irqname) + return -ENOMEM; + + ret = devm_request_irq(&pdev->dev, irq, hisi_uncore_pmu_isr, + IRQF_NOBALANCING | IRQF_NO_THREAD, + irqname, l3c_pmu); + if (ret < 0) { + dev_err(&pdev->dev, + "Fail to request EXT IRQ: %d ret: %d.\n", irq, ret); + return ret; + } + + hisi_l3c_pmu->ext_irq = irq; + return 0; +} + static struct attribute *hisi_l3c_pmu_v1_format_attr[] = { HISI_PMU_FORMAT_ATTR(event, "config:0-7"), NULL, @@ -394,7 +596,7 @@ static const struct attribute_group hisi_l3c_pmu_v1_format_group = { static struct attribute *hisi_l3c_pmu_v2_format_attr[] = { HISI_PMU_FORMAT_ATTR(event, "config:0-7"), - HISI_PMU_FORMAT_ATTR(tt_core, "config1:0-7"), + HISI_PMU_FORMAT_ATTR(tt_core, "config2:0-15"), HISI_PMU_FORMAT_ATTR(tt_req, "config1:8-10"), HISI_PMU_FORMAT_ATTR(datasrc_cfg, "config1:11-15"), HISI_PMU_FORMAT_ATTR(datasrc_skt, "config1:16"), @@ -406,6 +608,20 @@ static const struct attribute_group hisi_l3c_pmu_v2_format_group = { .attrs = hisi_l3c_pmu_v2_format_attr, }; +static struct attribute *hisi_l3c_pmu_v3_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), + HISI_PMU_FORMAT_ATTR(ext, "config:16"), + HISI_PMU_FORMAT_ATTR(tt_req, "config1:8-10"), + HISI_PMU_FORMAT_ATTR(tt_cacheable, "config1:17"), + HISI_PMU_FORMAT_ATTR(tt_core, "config2:0-15"), + NULL +}; + +static const struct attribute_group hisi_l3c_pmu_v3_format_group = { + .name = "format", + .attrs = hisi_l3c_pmu_v3_format_attr, +}; + static struct attribute *hisi_l3c_pmu_v1_events_attr[] = { HISI_PMU_EVENT_ATTR(rd_cpipe, 0x00), HISI_PMU_EVENT_ATTR(wr_cpipe, 0x01), @@ -441,48 +657,147 @@ static const struct attribute_group hisi_l3c_pmu_v2_events_group = { .attrs = hisi_l3c_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_l3c_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, +struct hisi_l3c_pmu_v3_event { + unsigned long event_id; + bool ext; }; -static const struct attribute_group hisi_l3c_pmu_cpumask_attr_group = { - .attrs = hisi_l3c_pmu_cpumask_attrs, -}; +static ssize_t hisi_l3c_pmu_event_show(struct device *dev, + struct device_attribute *attr, char *page) +{ + struct hisi_l3c_pmu_v3_event *event; + struct dev_ext_attribute *eattr; + + eattr = container_of(attr, struct dev_ext_attribute, attr); + event = eattr->var; -static struct device_attribute hisi_l3c_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); + if (!event->ext) + return sysfs_emit(page, "event=0x%lx\n", event->event_id); + else + return sysfs_emit(page, "event=0x%lx,ext=1\n", event->event_id); +} -static struct attribute *hisi_l3c_pmu_identifier_attrs[] = { - &hisi_l3c_pmu_identifier_attr.attr, +#define HISI_L3C_PMU_EVENT_ATTR(_name, _event, _ext) \ +static struct hisi_l3c_pmu_v3_event hisi_l3c_##_name = { _event, _ext }; \ +static struct dev_ext_attribute hisi_l3c_##_name##_attr = \ + { __ATTR(_name, 0444, hisi_l3c_pmu_event_show, NULL), (void *) &hisi_l3c_##_name } + +HISI_L3C_PMU_EVENT_ATTR(rd_cpipe, 0x00, true); +HISI_L3C_PMU_EVENT_ATTR(rd_hit_cpipe, 0x01, true); +HISI_L3C_PMU_EVENT_ATTR(wr_cpipe, 0x02, true); +HISI_L3C_PMU_EVENT_ATTR(wr_hit_cpipe, 0x03, true); +HISI_L3C_PMU_EVENT_ATTR(io_rd_cpipe, 0x04, true); +HISI_L3C_PMU_EVENT_ATTR(io_rd_hit_cpipe, 0x05, true); +HISI_L3C_PMU_EVENT_ATTR(io_wr_cpipe, 0x06, true); +HISI_L3C_PMU_EVENT_ATTR(io_wr_hit_cpipe, 0x07, true); +HISI_L3C_PMU_EVENT_ATTR(victim_num, 0x0c, true); +HISI_L3C_PMU_EVENT_ATTR(rd_spipe, 0x18, false); +HISI_L3C_PMU_EVENT_ATTR(rd_hit_spipe, 0x19, false); +HISI_L3C_PMU_EVENT_ATTR(wr_spipe, 0x1a, false); +HISI_L3C_PMU_EVENT_ATTR(wr_hit_spipe, 0x1b, false); +HISI_L3C_PMU_EVENT_ATTR(io_rd_spipe, 0x1c, false); +HISI_L3C_PMU_EVENT_ATTR(io_rd_hit_spipe, 0x1d, false); +HISI_L3C_PMU_EVENT_ATTR(io_wr_spipe, 0x1e, false); +HISI_L3C_PMU_EVENT_ATTR(io_wr_hit_spipe, 0x1f, false); +HISI_L3C_PMU_EVENT_ATTR(cycles, 0x7f, false); +HISI_L3C_PMU_EVENT_ATTR(l3c_ref, 0xbc, false); +HISI_L3C_PMU_EVENT_ATTR(l3c2ring, 0xbd, true); + +static struct attribute *hisi_l3c_pmu_v3_events_attr[] = { + &hisi_l3c_rd_cpipe_attr.attr.attr, + &hisi_l3c_rd_hit_cpipe_attr.attr.attr, + &hisi_l3c_wr_cpipe_attr.attr.attr, + &hisi_l3c_wr_hit_cpipe_attr.attr.attr, + &hisi_l3c_io_rd_cpipe_attr.attr.attr, + &hisi_l3c_io_rd_hit_cpipe_attr.attr.attr, + &hisi_l3c_io_wr_cpipe_attr.attr.attr, + &hisi_l3c_io_wr_hit_cpipe_attr.attr.attr, + &hisi_l3c_victim_num_attr.attr.attr, + &hisi_l3c_rd_spipe_attr.attr.attr, + &hisi_l3c_rd_hit_spipe_attr.attr.attr, + &hisi_l3c_wr_spipe_attr.attr.attr, + &hisi_l3c_wr_hit_spipe_attr.attr.attr, + &hisi_l3c_io_rd_spipe_attr.attr.attr, + &hisi_l3c_io_rd_hit_spipe_attr.attr.attr, + &hisi_l3c_io_wr_spipe_attr.attr.attr, + &hisi_l3c_io_wr_hit_spipe_attr.attr.attr, + &hisi_l3c_cycles_attr.attr.attr, + &hisi_l3c_l3c_ref_attr.attr.attr, + &hisi_l3c_l3c2ring_attr.attr.attr, NULL }; -static const struct attribute_group hisi_l3c_pmu_identifier_group = { - .attrs = hisi_l3c_pmu_identifier_attrs, +static umode_t hisi_l3c_pmu_v3_events_visible(struct kobject *kobj, + struct attribute *attr, int unused) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + struct hisi_pmu *l3c_pmu = to_hisi_pmu(pmu); + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + struct hisi_l3c_pmu_v3_event *event; + struct dev_ext_attribute *ext_attr; + + ext_attr = container_of(attr, struct dev_ext_attribute, attr.attr); + event = ext_attr->var; + + if (!event->ext || (hisi_l3c_pmu->feature & L3C_PMU_FEAT_EXT)) + return attr->mode; + + return 0; +} + +static const struct attribute_group hisi_l3c_pmu_v3_events_group = { + .name = "events", + .is_visible = hisi_l3c_pmu_v3_events_visible, + .attrs = hisi_l3c_pmu_v3_events_attr, }; static const struct attribute_group *hisi_l3c_pmu_v1_attr_groups[] = { &hisi_l3c_pmu_v1_format_group, &hisi_l3c_pmu_v1_events_group, - &hisi_l3c_pmu_cpumask_attr_group, - &hisi_l3c_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL, }; static const struct attribute_group *hisi_l3c_pmu_v2_attr_groups[] = { &hisi_l3c_pmu_v2_format_group, &hisi_l3c_pmu_v2_events_group, - &hisi_l3c_pmu_cpumask_attr_group, - &hisi_l3c_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, + NULL +}; + +static const struct attribute_group *hisi_l3c_pmu_v3_attr_groups[] = { + &hisi_l3c_pmu_v3_format_group, + &hisi_l3c_pmu_v3_events_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; +static const struct hisi_pmu_dev_info hisi_l3c_pmu_v1 = { + .attr_groups = hisi_l3c_pmu_v1_attr_groups, + .counter_bits = 48, + .check_event = L3C_V1_NR_EVENTS, +}; + +static const struct hisi_pmu_dev_info hisi_l3c_pmu_v2 = { + .attr_groups = hisi_l3c_pmu_v2_attr_groups, + .counter_bits = 64, + .check_event = L3C_V2_NR_EVENTS, +}; + +static const struct hisi_pmu_dev_info hisi_l3c_pmu_v3 = { + .attr_groups = hisi_l3c_pmu_v3_attr_groups, + .counter_bits = 64, + .check_event = L3C_V2_NR_EVENTS, + .private = (void *) L3C_PMU_FEAT_EXT, +}; + static const struct hisi_uncore_ops hisi_uncore_l3c_ops = { .write_evtype = hisi_l3c_pmu_write_evtype, - .get_event_idx = hisi_uncore_pmu_get_event_idx, + .get_event_idx = hisi_l3c_pmu_get_event_idx, .start_counters = hisi_l3c_pmu_start_counters, .stop_counters = hisi_l3c_pmu_stop_counters, .enable_counter = hisi_l3c_pmu_enable_counter, @@ -497,9 +812,75 @@ static const struct hisi_uncore_ops hisi_uncore_l3c_ops = { .disable_filter = hisi_l3c_pmu_disable_filter, }; +static void hisi_l3c_do_roll_over(u64 cpu_mask, u32 cpu_num, + struct hisi_l3c_pmu *hisi_l3c_pmu) +{ + int cpu = 0, bit; + + for_each_set_bit(bit, (unsigned long *)&cpu_mask, cpu_num) { + hisi_l3c_pmu->core_config[cpu] = bit; + cpu++; + } +} + +static void hisi_l3c_do_last_up(u64 cpu_mask, u32 cpu_num, + struct hisi_l3c_pmu *hisi_l3c_pmu) +{ + int sub = 0, bit; + + for_each_set_bit(bit, (unsigned long *)&cpu_mask, cpu_num) { + hisi_l3c_pmu->core_config[bit] = bit; + sub++; + } + + sub = cpu_num - sub; + + for_each_clear_bit(bit, (unsigned long *)&cpu_mask, cpu_num) { + while (sub > 0 && !(cpu_mask & BIT(cpu_num - sub))) + sub--; + + if (sub <= 0) + break; + + hisi_l3c_pmu->core_config[bit] = cpu_num - sub; + sub--; + } +} + +static void hisi_l3c_get_cluster_cpu_info(struct device *dev, + struct hisi_l3c_pmu *hisi_l3c_pmu) +{ + u64 cpu_mask = -1ULL; + u32 cpu_num = 8; + u32 sub = 1; + + /* If the configuration doesn't exist, default to full good. */ + if (device_property_read_u32(dev, "hisilicon,cluster-cpu-num", &cpu_num)) + dev_dbg(dev, "no cluster-cpu-num present\n"); + + if (device_property_read_u64(dev, "hisilicon,cluster-cpu", &cpu_mask)) + dev_dbg(dev, "no cluster-cpu present\n"); + + if (device_property_read_u32(dev, "hisilicon,cpu-substitute", &sub)) + dev_dbg(dev, "no cpu-substitute present\n"); + + cpu_mask &= L3C_PG_INFO_MASK(cpu_num); + + switch (sub) { + case ROLL_OVER: + hisi_l3c_do_roll_over(cpu_mask, cpu_num, hisi_l3c_pmu); + break; + case LAST_UP: + default: + hisi_l3c_do_last_up(cpu_mask, cpu_num, hisi_l3c_pmu); + break; + } +} + static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev, struct hisi_pmu *l3c_pmu) { + struct hisi_l3c_pmu *hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); int ret; ret = hisi_l3c_pmu_init_data(pdev, l3c_pmu); @@ -510,42 +891,60 @@ static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev, if (ret) return ret; - if (l3c_pmu->identifier >= HISI_PMU_V2) { - l3c_pmu->counter_bits = 64; - l3c_pmu->check_event = L3C_V2_NR_EVENTS; - l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v2_attr_groups; - } else { - l3c_pmu->counter_bits = 48; - l3c_pmu->check_event = L3C_V1_NR_EVENTS; - l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v1_attr_groups; - } + hisi_l3c_get_cluster_cpu_info(&pdev->dev, hisi_l3c_pmu); + l3c_pmu->pmu_events.attr_groups = l3c_pmu->dev_info->attr_groups; + l3c_pmu->counter_bits = l3c_pmu->dev_info->counter_bits; + l3c_pmu->check_event = l3c_pmu->dev_info->check_event; l3c_pmu->num_counters = L3C_NR_COUNTERS; l3c_pmu->ops = &hisi_uncore_l3c_ops; l3c_pmu->dev = &pdev->dev; l3c_pmu->on_cpu = -1; + if ((unsigned long)l3c_pmu->dev_info->private & L3C_PMU_FEAT_EXT) { + ret = hisi_l3c_pmu_init_ext(l3c_pmu, pdev); + if (ret) { + dev_warn(&pdev->dev, "ext event is unavailable, ret = %d\n", ret); + } else { + /* + * The extension events have their own counters with the + * same number of the normal events counters. So we can + * have at maximum num_counters * 2 events monitored. + */ + l3c_pmu->num_counters <<= 1; + + hisi_l3c_pmu->feature |= L3C_PMU_FEAT_EXT; + } + } + return 0; } static int hisi_l3c_pmu_probe(struct platform_device *pdev) { + struct hisi_l3c_pmu *hisi_l3c_pmu; struct hisi_pmu *l3c_pmu; char *name; int ret; - l3c_pmu = devm_kzalloc(&pdev->dev, sizeof(*l3c_pmu), GFP_KERNEL); - if (!l3c_pmu) + hisi_l3c_pmu = devm_kzalloc(&pdev->dev, sizeof(*hisi_l3c_pmu), GFP_KERNEL); + if (!hisi_l3c_pmu) return -ENOMEM; + l3c_pmu = &hisi_l3c_pmu->l3c_pmu; platform_set_drvdata(pdev, l3c_pmu); ret = hisi_l3c_pmu_dev_probe(pdev, l3c_pmu); if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u", - l3c_pmu->sccl_id, l3c_pmu->ccl_id); + if (l3c_pmu->topo.sub_id >= 0) + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_l3c%d_%d", + l3c_pmu->topo.sccl_id, l3c_pmu->topo.ccl_id, + l3c_pmu->topo.sub_id); + else + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_l3c%d", + l3c_pmu->topo.sccl_id, l3c_pmu->topo.ccl_id); if (!name) return -ENOMEM; @@ -578,6 +977,14 @@ static int hisi_l3c_pmu_remove(struct platform_device *pdev) return 0; } +static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = { + { "HISI0213", (kernel_ulong_t)&hisi_l3c_pmu_v1 }, + { "HISI0214", (kernel_ulong_t)&hisi_l3c_pmu_v2 }, + { "HISI0215", (kernel_ulong_t)&hisi_l3c_pmu_v3 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match); + static struct platform_driver hisi_l3c_pmu_driver = { .driver = { .name = "hisi_l3c_pmu", @@ -588,14 +995,55 @@ static struct platform_driver hisi_l3c_pmu_driver = { .remove = hisi_l3c_pmu_remove, }; +static int hisi_l3c_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pmu *l3c_pmu = hlist_entry_safe(node, struct hisi_pmu, node); + struct hisi_l3c_pmu *hisi_l3c_pmu; + int ret; + + hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + + /* + * Invoking the framework's online function for doing the core logic + * of CPU, interrupt and perf context migrating. Then return directly + * if we don't support L3C_PMU_FEAT_EXT. Otherwise migrate the ext_irq + * using the migrated CPU. + * + * Same logic for CPU offline. + */ + ret = hisi_uncore_pmu_online_cpu(cpu, node); + if (!(hisi_l3c_pmu->feature & L3C_PMU_FEAT_EXT) || + l3c_pmu->on_cpu >= nr_cpu_ids) + return ret; + + WARN_ON(irq_set_affinity(hisi_l3c_pmu->ext_irq, cpumask_of(l3c_pmu->on_cpu))); + return ret; +} + +static int hisi_l3c_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pmu *l3c_pmu = hlist_entry_safe(node, struct hisi_pmu, node); + struct hisi_l3c_pmu *hisi_l3c_pmu; + int ret; + + hisi_l3c_pmu = to_hisi_l3c_pmu(l3c_pmu); + ret = hisi_uncore_pmu_offline_cpu(cpu, node); + if (!(hisi_l3c_pmu->feature & L3C_PMU_FEAT_EXT) || + l3c_pmu->on_cpu >= nr_cpu_ids) + return ret; + + WARN_ON(irq_set_affinity(hisi_l3c_pmu->ext_irq, cpumask_of(l3c_pmu->on_cpu))); + return ret; +} + static int __init hisi_l3c_pmu_module_init(void) { int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, "AP_PERF_ARM_HISI_L3_ONLINE", - hisi_uncore_pmu_online_cpu, - hisi_uncore_pmu_offline_cpu); + hisi_l3c_pmu_online_cpu, + hisi_l3c_pmu_offline_cpu); if (ret) { pr_err("L3C PMU: Error setup hotplug, ret = %d\n", ret); return ret; @@ -616,6 +1064,7 @@ static void __exit hisi_l3c_pmu_module_exit(void) } module_exit(hisi_l3c_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SoC L3C uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Anurup M "); diff --git a/drivers/perf/hisilicon/hisi_uncore_mn_pmu.c b/drivers/perf/hisilicon/hisi_uncore_mn_pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..38a72c95fb6daa252708b3981fb7a2130b016be5 --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_mn_pmu.c @@ -0,0 +1,411 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * HiSilicon SoC MN uncore Hardware event counters support + * + * Copyright (c) 2025 HiSilicon Technologies Co., Ltd. + */ +#include +#include +#include +#include +#include +#include +#include + +#include "hisi_uncore_pmu.h" + +/* Dynamic CPU hotplug state used by MN PMU */ +static enum cpuhp_state hisi_mn_pmu_online; + +/* MN register definition */ +#define HISI_MN_DYNAMIC_CTRL_REG 0x400 +#define HISI_MN_DYNAMIC_CTRL_EN BIT(0) +#define HISI_MN_PERF_CTRL_REG 0x408 +#define HISI_MN_PERF_CTRL_EN BIT(6) +#define HISI_MN_INT_MASK_REG 0x800 +#define HISI_MN_INT_STATUS_REG 0x808 +#define HISI_MN_INT_CLEAR_REG 0x80C +#define HISI_MN_EVENT_CTRL_REG 0x1C00 +#define HISI_MN_VERSION_REG 0x1C04 +#define HISI_MN_EVTYPE0_REG 0x1d00 +#define HISI_MN_EVTYPE_MASK GENMASK(7, 0) +#define HISI_MN_CNTR0_REG 0x1e00 +#define HISI_MN_EVTYPE_REGn(evtype0, n) ((evtype0) + (n) * 4) +#define HISI_MN_CNTR_REGn(cntr0, n) ((cntr0) + (n) * 8) + +#define HISI_MN_NR_COUNTERS 4 +#define HISI_MN_TIMEOUT_US 500U + +struct hisi_mn_pmu_regs { + u32 version; + u32 dyn_ctrl; + u32 perf_ctrl; + u32 int_mask; + u32 int_clear; + u32 int_status; + u32 event_ctrl; + u32 event_type0; + u32 event_cntr0; +}; + +/* + * Each event request takes a certain amount of time to complete. If + * we counting the latency related event, we need to wait for the all + * requests complete. Otherwise, the value of counter is slightly larger. + */ +static void hisi_mn_pmu_counter_flush(struct hisi_pmu *mn_pmu) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + int ret; + u32 val; + + val = readl(mn_pmu->base + reg_info->dyn_ctrl); + val |= HISI_MN_DYNAMIC_CTRL_EN; + writel(val, mn_pmu->base + reg_info->dyn_ctrl); + + ret = readl_poll_timeout_atomic(mn_pmu->base + reg_info->dyn_ctrl, + val, !(val & HISI_MN_DYNAMIC_CTRL_EN), + 1, HISI_MN_TIMEOUT_US); + if (ret) + dev_warn(mn_pmu->dev, "Counter flush timeout\n"); +} + +static u64 hisi_mn_pmu_read_counter(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + + return readq(mn_pmu->base + HISI_MN_CNTR_REGn(reg_info->event_cntr0, hwc->idx)); +} + +static void hisi_mn_pmu_write_counter(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc, u64 val) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + + writeq(val, mn_pmu->base + HISI_MN_CNTR_REGn(reg_info->event_cntr0, hwc->idx)); +} + +static void hisi_mn_pmu_write_evtype(struct hisi_pmu *mn_pmu, int idx, u32 type) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + /* + * Select the appropriate event select register. + * There are 2 32-bit event select registers for the + * 8 hardware counters, each event code is 8-bit wide. + */ + val = readl(mn_pmu->base + HISI_MN_EVTYPE_REGn(reg_info->event_type0, idx / 4)); + val &= ~(HISI_MN_EVTYPE_MASK << HISI_PMU_EVTYPE_SHIFT(idx)); + val |= (type << HISI_PMU_EVTYPE_SHIFT(idx)); + writel(val, mn_pmu->base + HISI_MN_EVTYPE_REGn(reg_info->event_type0, idx / 4)); +} + +static void hisi_mn_pmu_start_counters(struct hisi_pmu *mn_pmu) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->perf_ctrl); + val |= HISI_MN_PERF_CTRL_EN; + writel(val, mn_pmu->base + reg_info->perf_ctrl); +} + +static void hisi_mn_pmu_stop_counters(struct hisi_pmu *mn_pmu) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->perf_ctrl); + val &= ~HISI_MN_PERF_CTRL_EN; + writel(val, mn_pmu->base + reg_info->perf_ctrl); + + hisi_mn_pmu_counter_flush(mn_pmu); +} + +static void hisi_mn_pmu_enable_counter(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->event_ctrl); + val |= BIT(hwc->idx); + writel(val, mn_pmu->base + reg_info->event_ctrl); +} + +static void hisi_mn_pmu_disable_counter(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->event_ctrl); + val &= ~BIT(hwc->idx); + writel(val, mn_pmu->base + reg_info->event_ctrl); +} + +static void hisi_mn_pmu_enable_counter_int(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->int_mask); + val &= ~BIT(hwc->idx); + writel(val, mn_pmu->base + reg_info->int_mask); +} + +static void hisi_mn_pmu_disable_counter_int(struct hisi_pmu *mn_pmu, + struct hw_perf_event *hwc) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + u32 val; + + val = readl(mn_pmu->base + reg_info->int_mask); + val |= BIT(hwc->idx); + writel(val, mn_pmu->base + reg_info->int_mask); +} + +static u32 hisi_mn_pmu_get_int_status(struct hisi_pmu *mn_pmu) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + + return readl(mn_pmu->base + reg_info->int_status); +} + +static void hisi_mn_pmu_clear_int_status(struct hisi_pmu *mn_pmu, int idx) +{ + struct hisi_mn_pmu_regs *reg_info = mn_pmu->dev_info->private; + + writel(BIT(idx), mn_pmu->base + reg_info->int_clear); +} + +static struct attribute *hisi_mn_pmu_format_attr[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), + NULL +}; + +static const struct attribute_group hisi_mn_pmu_format_group = { + .name = "format", + .attrs = hisi_mn_pmu_format_attr, +}; + +static struct attribute *hisi_mn_pmu_events_attr[] = { + HISI_PMU_EVENT_ATTR(req_eobarrier_num, 0x00), + HISI_PMU_EVENT_ATTR(req_ecbarrier_num, 0x01), + HISI_PMU_EVENT_ATTR(req_dvmop_num, 0x02), + HISI_PMU_EVENT_ATTR(req_dvmsync_num, 0x03), + HISI_PMU_EVENT_ATTR(req_retry_num, 0x04), + HISI_PMU_EVENT_ATTR(req_writenosnp_num, 0x05), + HISI_PMU_EVENT_ATTR(req_readnosnp_num, 0x06), + HISI_PMU_EVENT_ATTR(snp_dvm_num, 0x07), + HISI_PMU_EVENT_ATTR(snp_dvmsync_num, 0x08), + HISI_PMU_EVENT_ATTR(l3t_req_dvm_num, 0x09), + HISI_PMU_EVENT_ATTR(l3t_req_dvmsync_num, 0x0A), + HISI_PMU_EVENT_ATTR(mn_req_dvm_num, 0x0B), + HISI_PMU_EVENT_ATTR(mn_req_dvmsync_num, 0x0C), + HISI_PMU_EVENT_ATTR(pa_req_dvm_num, 0x0D), + HISI_PMU_EVENT_ATTR(pa_req_dvmsync_num, 0x0E), + HISI_PMU_EVENT_ATTR(snp_dvm_latency, 0x80), + HISI_PMU_EVENT_ATTR(snp_dvmsync_latency, 0x81), + HISI_PMU_EVENT_ATTR(l3t_req_dvm_latency, 0x82), + HISI_PMU_EVENT_ATTR(l3t_req_dvmsync_latency, 0x83), + HISI_PMU_EVENT_ATTR(mn_req_dvm_latency, 0x84), + HISI_PMU_EVENT_ATTR(mn_req_dvmsync_latency, 0x85), + HISI_PMU_EVENT_ATTR(pa_req_dvm_latency, 0x86), + HISI_PMU_EVENT_ATTR(pa_req_dvmsync_latency, 0x87), + NULL +}; + +static const struct attribute_group hisi_mn_pmu_events_group = { + .name = "events", + .attrs = hisi_mn_pmu_events_attr, +}; + +static const struct attribute_group *hisi_mn_pmu_attr_groups[] = { + &hisi_mn_pmu_format_group, + &hisi_mn_pmu_events_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, + NULL +}; + +static const struct hisi_uncore_ops hisi_uncore_mn_ops = { + .write_evtype = hisi_mn_pmu_write_evtype, + .get_event_idx = hisi_uncore_pmu_get_event_idx, + .start_counters = hisi_mn_pmu_start_counters, + .stop_counters = hisi_mn_pmu_stop_counters, + .enable_counter = hisi_mn_pmu_enable_counter, + .disable_counter = hisi_mn_pmu_disable_counter, + .enable_counter_int = hisi_mn_pmu_enable_counter_int, + .disable_counter_int = hisi_mn_pmu_disable_counter_int, + .write_counter = hisi_mn_pmu_write_counter, + .read_counter = hisi_mn_pmu_read_counter, + .get_int_status = hisi_mn_pmu_get_int_status, + .clear_int_status = hisi_mn_pmu_clear_int_status, +}; + +static int hisi_mn_pmu_dev_init(struct platform_device *pdev, + struct hisi_pmu *mn_pmu) +{ + struct hisi_mn_pmu_regs *reg_info; + int ret; + + hisi_uncore_pmu_init_topology(mn_pmu, &pdev->dev); + + if (mn_pmu->topo.scl_id < 0) + return dev_err_probe(&pdev->dev, -EINVAL, + "Failed to read MN scl id\n"); + + if (mn_pmu->topo.index_id < 0) + return dev_err_probe(&pdev->dev, -EINVAL, + "Failed to read MN index id\n"); + + mn_pmu->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(mn_pmu->base)) + return dev_err_probe(&pdev->dev, PTR_ERR(mn_pmu->base), + "Failed to ioremap resource\n"); + + ret = hisi_uncore_pmu_init_irq(mn_pmu, pdev); + if (ret) + return ret; + + mn_pmu->dev_info = device_get_match_data(&pdev->dev); + if (!mn_pmu->dev_info) + return -ENODEV; + + mn_pmu->pmu_events.attr_groups = mn_pmu->dev_info->attr_groups; + mn_pmu->counter_bits = mn_pmu->dev_info->counter_bits; + mn_pmu->check_event = mn_pmu->dev_info->check_event; + mn_pmu->num_counters = HISI_MN_NR_COUNTERS; + mn_pmu->ops = &hisi_uncore_mn_ops; + mn_pmu->dev = &pdev->dev; + mn_pmu->on_cpu = -1; + + reg_info = mn_pmu->dev_info->private; + mn_pmu->identifier = readl(mn_pmu->base + reg_info->version); + + return 0; +} + +static void hisi_mn_pmu_remove_cpuhp(void *hotplug_node) +{ + cpuhp_state_remove_instance_nocalls(hisi_mn_pmu_online, hotplug_node); +} + +static void hisi_mn_pmu_unregister(void *pmu) +{ + perf_pmu_unregister(pmu); +} + +static int hisi_mn_pmu_probe(struct platform_device *pdev) +{ + struct hisi_pmu *mn_pmu; + char *name; + int ret; + + mn_pmu = devm_kzalloc(&pdev->dev, sizeof(*mn_pmu), GFP_KERNEL); + if (!mn_pmu) + return -ENOMEM; + + platform_set_drvdata(pdev, mn_pmu); + + ret = hisi_mn_pmu_dev_init(pdev, mn_pmu); + if (ret) + return ret; + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_scl%d_mn%d", + mn_pmu->topo.scl_id, mn_pmu->topo.index_id); + if (!name) + return -ENOMEM; + + ret = cpuhp_state_add_instance(hisi_mn_pmu_online, &mn_pmu->node); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to register cpu hotplug\n"); + + ret = devm_add_action_or_reset(&pdev->dev, hisi_mn_pmu_remove_cpuhp, &mn_pmu->node); + if (ret) + return ret; + + hisi_pmu_init(mn_pmu, THIS_MODULE); + + ret = perf_pmu_register(&mn_pmu->pmu, name, -1); + if (ret) + return dev_err_probe(mn_pmu->dev, ret, "Failed to register MN PMU\n"); + + return devm_add_action_or_reset(&pdev->dev, hisi_mn_pmu_unregister, &mn_pmu->pmu); +} + +static struct hisi_mn_pmu_regs hisi_mn_v1_pmu_regs = { + .version = HISI_MN_VERSION_REG, + .dyn_ctrl = HISI_MN_DYNAMIC_CTRL_REG, + .perf_ctrl = HISI_MN_PERF_CTRL_REG, + .int_mask = HISI_MN_INT_MASK_REG, + .int_clear = HISI_MN_INT_CLEAR_REG, + .int_status = HISI_MN_INT_STATUS_REG, + .event_ctrl = HISI_MN_EVENT_CTRL_REG, + .event_type0 = HISI_MN_EVTYPE0_REG, + .event_cntr0 = HISI_MN_CNTR0_REG, +}; + +static const struct hisi_pmu_dev_info hisi_mn_v1 = { + .attr_groups = hisi_mn_pmu_attr_groups, + .counter_bits = 48, + .check_event = HISI_MN_EVTYPE_MASK, + .private = &hisi_mn_v1_pmu_regs, +}; + +static const struct acpi_device_id hisi_mn_pmu_acpi_match[] = { + { "HISI0222", (kernel_ulong_t) &hisi_mn_v1 }, + { } +}; +MODULE_DEVICE_TABLE(acpi, hisi_mn_pmu_acpi_match); + +static struct platform_driver hisi_mn_pmu_driver = { + .driver = { + .name = "hisi_mn_pmu", + .acpi_match_table = hisi_mn_pmu_acpi_match, + /* + * We have not worked out a safe bind/unbind process, + * Forcefully unbinding during sampling will lead to a + * kernel panic, so this is not supported yet. + */ + .suppress_bind_attrs = true, + }, + .probe = hisi_mn_pmu_probe, +}; + +static int __init hisi_mn_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/hisi/mn:online", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret < 0) { + pr_err("hisi_mn_pmu: Failed to setup MN PMU hotplug: %d\n", ret); + return ret; + } + hisi_mn_pmu_online = ret; + + ret = platform_driver_register(&hisi_mn_pmu_driver); + if (ret) + cpuhp_remove_multi_state(hisi_mn_pmu_online); + + return ret; +} +module_init(hisi_mn_pmu_module_init); + +static void __exit hisi_mn_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_mn_pmu_driver); + cpuhp_remove_multi_state(hisi_mn_pmu_online); +} +module_exit(hisi_mn_pmu_module_exit); + +MODULE_IMPORT_NS(HISI_PMU); +MODULE_DESCRIPTION("HiSilicon SoC MN uncore PMU driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Junhao He "); diff --git a/drivers/perf/hisilicon/hisi_uncore_noc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_noc_pmu.c new file mode 100644 index 0000000000000000000000000000000000000000..bf0a6bce71c436b4d3409b72fe80f0aef2670c53 --- /dev/null +++ b/drivers/perf/hisilicon/hisi_uncore_noc_pmu.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for HiSilicon Uncore NoC (Network on Chip) PMU device + * + * Copyright (c) 2025 HiSilicon Technologies Co., Ltd. + * Author: Yicong Yang + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "hisi_uncore_pmu.h" + +#define NOC_PMU_VERSION 0x1e00 +#define NOC_PMU_GLOBAL_CTRL 0x1e04 +#define NOC_PMU_GLOBAL_CTRL_PMU_EN BIT(0) +#define NOC_PMU_GLOBAL_CTRL_TT_EN BIT(1) +#define NOC_PMU_CNT_INFO 0x1e08 +#define NOC_PMU_CNT_INFO_OVERFLOW(n) BIT(n) +#define NOC_PMU_EVENT_CTRL(n) (0x1e20 + 4 * (n)) +#define NOC_PMU_EVENT_CTRL_TYPE GENMASK(4, 0) +/* + * Note channel of 0x0 will reset the counter value, so don't do it before + * we read out the counter. + */ +#define NOC_PMU_EVENT_CTRL_CHANNEL GENMASK(10, 8) +#define NOC_PMU_EVENT_CTRL_EN BIT(11) +#define NOC_PMU_EVENT_COUNTER(n) (0x1e80 + 8 * (n)) + +#define NOC_PMU_NR_COUNTERS 4 +#define NOC_PMU_COUNTER_BITS 64 + +#define NOC_PMU_CH_DEFAULT 0x7 + +HISI_PMU_EVENT_ATTR_EXTRACTOR(ch, config1, 2, 0); +HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_en, config1, 3, 3); + +/* Dynamic CPU hotplug state used by this PMU driver */ +static enum cpuhp_state hisi_noc_pmu_cpuhp_state; + +/* + * Tracetag filtering is not per event and all the events should keep + * the consistence. Return true if the new comer doesn't match the + * tracetag filtering configuration of the current scheduled events. + */ +static bool hisi_noc_pmu_check_global_filter(struct perf_event *curr, + struct perf_event *new) +{ + return hisi_get_tt_en(curr) == hisi_get_tt_en(new); +} + +static void hisi_noc_pmu_write_evtype(struct hisi_pmu *noc_pmu, int idx, u32 type) +{ + u32 reg; + + reg = readl(noc_pmu->base + NOC_PMU_EVENT_CTRL(idx)); + reg &= ~NOC_PMU_EVENT_CTRL_TYPE; + reg |= FIELD_PREP(NOC_PMU_EVENT_CTRL_TYPE, type); + writel(reg, noc_pmu->base + NOC_PMU_EVENT_CTRL(idx)); +} + +static int hisi_noc_pmu_get_event_idx(struct perf_event *event) +{ + struct hisi_pmu *noc_pmu = to_hisi_pmu(event->pmu); + struct hisi_pmu_hwevents *pmu_events = &noc_pmu->pmu_events; + int cur_idx; + + cur_idx = find_first_bit(pmu_events->used_mask, noc_pmu->num_counters); + if (cur_idx != noc_pmu->num_counters && + !hisi_noc_pmu_check_global_filter(pmu_events->hw_events[cur_idx], event)) + return -EAGAIN; + + return hisi_uncore_pmu_get_event_idx(event); +} + +static u64 hisi_noc_pmu_read_counter(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc) +{ + return readq(noc_pmu->base + NOC_PMU_EVENT_COUNTER(hwc->idx)); +} + +static void hisi_noc_pmu_write_counter(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + writeq(val, noc_pmu->base + NOC_PMU_EVENT_COUNTER(hwc->idx)); +} + +static void hisi_noc_pmu_enable_counter(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc) +{ + u32 reg; + + reg = readl(noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); + reg |= NOC_PMU_EVENT_CTRL_EN; + writel(reg, noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); +} + +static void hisi_noc_pmu_disable_counter(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc) +{ + u32 reg; + + reg = readl(noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); + reg &= ~NOC_PMU_EVENT_CTRL_EN; + writel(reg, noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); +} + +static void hisi_noc_pmu_enable_counter_int(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc) +{ + /* We don't support interrupt, so a stub here. */ +} + +static void hisi_noc_pmu_disable_counter_int(struct hisi_pmu *noc_pmu, + struct hw_perf_event *hwc) +{ +} + +static void hisi_noc_pmu_start_counters(struct hisi_pmu *noc_pmu) +{ + u32 reg; + + reg = readl(noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + reg |= NOC_PMU_GLOBAL_CTRL_PMU_EN; + writel(reg, noc_pmu->base + NOC_PMU_GLOBAL_CTRL); +} + +static void hisi_noc_pmu_stop_counters(struct hisi_pmu *noc_pmu) +{ + u32 reg; + + reg = readl(noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + reg &= ~NOC_PMU_GLOBAL_CTRL_PMU_EN; + writel(reg, noc_pmu->base + NOC_PMU_GLOBAL_CTRL); +} + +static u32 hisi_noc_pmu_get_int_status(struct hisi_pmu *noc_pmu) +{ + return readl(noc_pmu->base + NOC_PMU_CNT_INFO); +} + +static void hisi_noc_pmu_clear_int_status(struct hisi_pmu *noc_pmu, int idx) +{ + writel(~NOC_PMU_CNT_INFO_OVERFLOW(idx), noc_pmu->base + NOC_PMU_CNT_INFO); +} + +static void hisi_noc_pmu_enable_filter(struct perf_event *event) +{ + struct hisi_pmu *noc_pmu = to_hisi_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + u32 tt_en = hisi_get_tt_en(event); + u32 ch = hisi_get_ch(event); + u32 reg; + + if (!ch) + ch = NOC_PMU_CH_DEFAULT; + + reg = readl(noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); + reg &= ~NOC_PMU_EVENT_CTRL_CHANNEL; + reg |= FIELD_PREP(NOC_PMU_EVENT_CTRL_CHANNEL, ch); + writel(reg, noc_pmu->base + NOC_PMU_EVENT_CTRL(hwc->idx)); + + /* + * Since tracetag filter applies to all the counters, don't touch it + * if user doesn't specify it explicitly. + */ + if (tt_en) { + reg = readl(noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + reg |= NOC_PMU_GLOBAL_CTRL_TT_EN; + writel(reg, noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + } +} + +static void hisi_noc_pmu_disable_filter(struct perf_event *event) +{ + struct hisi_pmu *noc_pmu = to_hisi_pmu(event->pmu); + u32 tt_en = hisi_get_tt_en(event); + u32 reg; + + /* + * If we're not the last counter, don't touch the global tracetag + * configuration. + */ + if (bitmap_weight(noc_pmu->pmu_events.used_mask, noc_pmu->num_counters) > 1) + return; + + if (tt_en) { + reg = readl(noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + reg &= ~NOC_PMU_GLOBAL_CTRL_TT_EN; + writel(reg, noc_pmu->base + NOC_PMU_GLOBAL_CTRL); + } +} + +static const struct hisi_uncore_ops hisi_uncore_noc_ops = { + .write_evtype = hisi_noc_pmu_write_evtype, + .get_event_idx = hisi_noc_pmu_get_event_idx, + .read_counter = hisi_noc_pmu_read_counter, + .write_counter = hisi_noc_pmu_write_counter, + .enable_counter = hisi_noc_pmu_enable_counter, + .disable_counter = hisi_noc_pmu_disable_counter, + .enable_counter_int = hisi_noc_pmu_enable_counter_int, + .disable_counter_int = hisi_noc_pmu_disable_counter_int, + .start_counters = hisi_noc_pmu_start_counters, + .stop_counters = hisi_noc_pmu_stop_counters, + .get_int_status = hisi_noc_pmu_get_int_status, + .clear_int_status = hisi_noc_pmu_clear_int_status, + .enable_filter = hisi_noc_pmu_enable_filter, + .disable_filter = hisi_noc_pmu_disable_filter, +}; + +static struct attribute *hisi_noc_pmu_format_attrs[] = { + HISI_PMU_FORMAT_ATTR(event, "config:0-7"), + HISI_PMU_FORMAT_ATTR(ch, "config1:0-2"), + HISI_PMU_FORMAT_ATTR(tt_en, "config1:3"), + NULL +}; + +static const struct attribute_group hisi_noc_pmu_format_group = { + .name = "format", + .attrs = hisi_noc_pmu_format_attrs, +}; + +static struct attribute *hisi_noc_pmu_events_attrs[] = { + HISI_PMU_EVENT_ATTR(cycles, 0x0e), + /* Flux on/off the ring */ + HISI_PMU_EVENT_ATTR(ingress_flow_sum, 0x1a), + HISI_PMU_EVENT_ATTR(egress_flow_sum, 0x17), + /* Buffer full duration on/off the ring */ + HISI_PMU_EVENT_ATTR(ingress_buf_full, 0x19), + HISI_PMU_EVENT_ATTR(egress_buf_full, 0x12), + /* Failure packets count on/off the ring */ + HISI_PMU_EVENT_ATTR(cw_ingress_fail, 0x01), + HISI_PMU_EVENT_ATTR(cc_ingress_fail, 0x09), + HISI_PMU_EVENT_ATTR(cw_egress_fail, 0x03), + HISI_PMU_EVENT_ATTR(cc_egress_fail, 0x0b), + /* Flux of the ring */ + HISI_PMU_EVENT_ATTR(cw_main_flow_sum, 0x05), + HISI_PMU_EVENT_ATTR(cc_main_flow_sum, 0x0d), + NULL +}; + +static const struct attribute_group hisi_noc_pmu_events_group = { + .name = "events", + .attrs = hisi_noc_pmu_events_attrs, +}; + +static const struct attribute_group *hisi_noc_pmu_attr_groups[] = { + &hisi_noc_pmu_format_group, + &hisi_noc_pmu_events_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, + NULL +}; + +static int hisi_noc_pmu_dev_init(struct platform_device *pdev, struct hisi_pmu *noc_pmu) +{ + hisi_uncore_pmu_init_topology(noc_pmu, &pdev->dev); + + if (noc_pmu->topo.scl_id < 0) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get scl-id\n"); + + if (noc_pmu->topo.index_id < 0) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get idx-id\n"); + + if (noc_pmu->topo.sub_id < 0) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get sub-id\n"); + + noc_pmu->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(noc_pmu->base)) + return dev_err_probe(&pdev->dev, PTR_ERR(noc_pmu->base), + "fail to remap io memory\n"); + + noc_pmu->on_cpu = -1; + noc_pmu->dev = &pdev->dev; + noc_pmu->ops = &hisi_uncore_noc_ops; + noc_pmu->pmu_events.attr_groups = hisi_noc_pmu_attr_groups; + noc_pmu->num_counters = NOC_PMU_NR_COUNTERS; + noc_pmu->counter_bits = NOC_PMU_COUNTER_BITS; + noc_pmu->check_event = NOC_PMU_EVENT_CTRL_TYPE; + noc_pmu->identifier = readl(noc_pmu->base + NOC_PMU_VERSION); + return 0; +} + +static void hisi_noc_pmu_remove_cpuhp_instance(void *hotplug_node) +{ + cpuhp_state_remove_instance_nocalls(hisi_noc_pmu_cpuhp_state, hotplug_node); +} + +static void hisi_noc_pmu_unregister_pmu(void *pmu) +{ + perf_pmu_unregister(pmu); +} + +static int hisi_noc_pmu_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct hisi_pmu *noc_pmu; + char *name; + int ret; + + noc_pmu = devm_kzalloc(dev, sizeof(*noc_pmu), GFP_KERNEL); + if (!noc_pmu) + return -ENOMEM; + + /* + * HiSilicon Uncore PMU framework needs to get common hisi_pmu device + * from device's drvdata. + */ + platform_set_drvdata(pdev, noc_pmu); + + ret = hisi_noc_pmu_dev_init(pdev, noc_pmu); + if (ret) + return ret; + + ret = cpuhp_state_add_instance(hisi_noc_pmu_cpuhp_state, &noc_pmu->node); + if (ret) + return dev_err_probe(dev, ret, "Fail to register cpuhp instance\n"); + + ret = devm_add_action_or_reset(dev, hisi_noc_pmu_remove_cpuhp_instance, + &noc_pmu->node); + if (ret) + return ret; + + hisi_pmu_init(noc_pmu, THIS_MODULE); + + name = devm_kasprintf(dev, GFP_KERNEL, "hisi_scl%d_noc%d_%d", + noc_pmu->topo.scl_id, noc_pmu->topo.index_id, + noc_pmu->topo.sub_id); + if (!name) + return -ENOMEM; + + ret = perf_pmu_register(&noc_pmu->pmu, name, -1); + if (ret) + return dev_err_probe(dev, ret, "Fail to register PMU\n"); + + return devm_add_action_or_reset(dev, hisi_noc_pmu_unregister_pmu, + &noc_pmu->pmu); +} + +const struct acpi_device_id hisi_noc_pmu_ids[] = { + { "HISI04E0", }, + { } +}; +MODULE_DEVICE_TABLE(acpi, hisi_noc_pmu_ids); + +static struct platform_driver hisi_noc_pmu_driver = { + .driver = { + .name = "hisi_noc_pmu", + .acpi_match_table = hisi_noc_pmu_ids, + .suppress_bind_attrs = true, + }, + .probe = hisi_noc_pmu_probe, +}; + +static int __init hisi_noc_pmu_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "perf/hisi/noc:online", + hisi_uncore_pmu_online_cpu, + hisi_uncore_pmu_offline_cpu); + if (ret < 0) { + pr_err("hisi_noc_pmu: Fail to setup cpuhp callbacks, ret = %d\n", ret); + return ret; + } + hisi_noc_pmu_cpuhp_state = ret; + + ret = platform_driver_register(&hisi_noc_pmu_driver); + if (ret) + cpuhp_remove_multi_state(hisi_noc_pmu_cpuhp_state); + + return ret; +} +module_init(hisi_noc_pmu_module_init); + +static void __exit hisi_noc_pmu_module_exit(void) +{ + platform_driver_unregister(&hisi_noc_pmu_driver); + cpuhp_remove_multi_state(hisi_noc_pmu_cpuhp_state); +} +module_exit(hisi_noc_pmu_module_exit); + +MODULE_IMPORT_NS(HISI_PMU); +MODULE_DESCRIPTION("HiSilicon SoC Uncore NoC PMU driver"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yicong Yang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index 797cf201996a9646490ee52aee421dfa969dbc61..294746e11e3954ba890fc1ed5497bf201b1bb1b5 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -269,25 +269,22 @@ static void hisi_pa_pmu_clear_int_status(struct hisi_pmu *pa_pmu, int idx) static int hisi_pa_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *pa_pmu) { + hisi_uncore_pmu_init_topology(pa_pmu, &pdev->dev); + /* * As PA PMU is in a SICL, use the SICL_ID and the index ID * to identify the PA PMU. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &pa_pmu->sicl_id)) { + if (pa_pmu->topo.sicl_id < 0) { dev_err(&pdev->dev, "Cannot read sicl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &pa_pmu->index_id)) { + if (pa_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id!\n"); return -EINVAL; } - pa_pmu->ccl_id = -1; - pa_pmu->sccl_id = -1; - pa_pmu->dev_info = device_get_match_data(&pdev->dev); if (!pa_pmu->dev_info) return -ENODEV; @@ -319,9 +316,23 @@ static const struct attribute_group hisi_pa_pmu_v2_format_group = { }; static struct attribute *hisi_pa_pmu_v2_events_attr[] = { - HISI_PMU_EVENT_ATTR(rx_req, 0x40), - HISI_PMU_EVENT_ATTR(tx_req, 0x5c), - HISI_PMU_EVENT_ATTR(cycle, 0x78), + HISI_PMU_EVENT_ATTR(pa_rx_req_link0, 0x40), + HISI_PMU_EVENT_ATTR(pa_rx_req_link1, 0x41), + HISI_PMU_EVENT_ATTR(pa_rx_req_link2, 0x42), + HISI_PMU_EVENT_ATTR(pa_rx_req_link3, 0x43), + HISI_PMU_EVENT_ATTR(pa_rx_data_link0, 0x44), + HISI_PMU_EVENT_ATTR(pa_rx_data_link1, 0x45), + HISI_PMU_EVENT_ATTR(pa_rx_data_link2, 0x46), + HISI_PMU_EVENT_ATTR(pa_rx_data_link3, 0x47), + HISI_PMU_EVENT_ATTR(pa_tx_req_link0, 0x60), + HISI_PMU_EVENT_ATTR(pa_tx_req_link1, 0x61), + HISI_PMU_EVENT_ATTR(pa_tx_req_link2, 0x62), + HISI_PMU_EVENT_ATTR(pa_tx_req_link3, 0x63), + HISI_PMU_EVENT_ATTR(pa_tx_data_link0, 0x64), + HISI_PMU_EVENT_ATTR(pa_tx_data_link1, 0x65), + HISI_PMU_EVENT_ATTR(pa_tx_data_link2, 0x66), + HISI_PMU_EVENT_ATTR(pa_tx_data_link3, 0x67), + HISI_PMU_EVENT_ATTR(pa_cycles, 0x78), NULL }; @@ -356,29 +367,6 @@ static const struct attribute_group hisi_h60pa_pmu_events_group = { .attrs = hisi_h60pa_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_pa_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL -}; - -static const struct attribute_group hisi_pa_pmu_cpumask_attr_group = { - .attrs = hisi_pa_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_pa_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_pa_pmu_identifier_attrs[] = { - &hisi_pa_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_pa_pmu_identifier_group = { - .attrs = hisi_pa_pmu_identifier_attrs, -}; - static struct hisi_pa_pmu_int_regs hisi_pa_pmu_regs = { .mask_offset = PA_INT_MASK, .clear_offset = PA_INT_CLEAR, @@ -388,8 +376,8 @@ static struct hisi_pa_pmu_int_regs hisi_pa_pmu_regs = { static const struct attribute_group *hisi_pa_pmu_v2_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_pa_pmu_v2_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -402,8 +390,8 @@ static const struct hisi_pmu_dev_info hisi_h32pa_v2 = { static const struct attribute_group *hisi_pa_pmu_v3_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_pa_pmu_v3_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -422,8 +410,8 @@ static struct hisi_pa_pmu_int_regs hisi_h60pa_pmu_regs = { static const struct attribute_group *hisi_h60pa_pmu_attr_groups[] = { &hisi_pa_pmu_v2_format_group, &hisi_h60pa_pmu_events_group, - &hisi_pa_pmu_cpumask_attr_group, - &hisi_pa_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -466,7 +454,7 @@ static int hisi_pa_pmu_dev_probe(struct platform_device *pdev, pa_pmu->pmu_events.attr_groups = pa_pmu->dev_info->attr_groups; pa_pmu->num_counters = PA_NR_COUNTERS; pa_pmu->ops = &hisi_uncore_pa_ops; - pa_pmu->check_event = 0xB0; + pa_pmu->check_event = PA_EVTYPE_MASK; pa_pmu->counter_bits = 64; pa_pmu->dev = &pdev->dev; pa_pmu->on_cpu = -1; @@ -488,9 +476,9 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_%s%u", - pa_pmu->sicl_id, pa_pmu->dev_info->name, - pa_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%d_%s%d", + pa_pmu->topo.sicl_id, pa_pmu->dev_info->name, + pa_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -570,6 +558,7 @@ static void __exit hisi_pa_pmu_module_exit(void) } module_exit(hisi_pa_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon Protocol Adapter uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index 04031450d5fecae9c5740deb553f4ce0ea574673..6d5a10d903b3628f52068c0f34172db6be7e0c85 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -34,7 +35,7 @@ ssize_t hisi_format_sysfs_show(struct device *dev, return sysfs_emit(buf, "%s\n", (char *)eattr->var); } -EXPORT_SYMBOL_GPL(hisi_format_sysfs_show); +EXPORT_SYMBOL_NS_GPL(hisi_format_sysfs_show, HISI_PMU); /* * PMU event attributes @@ -48,7 +49,7 @@ ssize_t hisi_event_sysfs_show(struct device *dev, return sysfs_emit(page, "config=0x%lx\n", (unsigned long)eattr->var); } -EXPORT_SYMBOL_GPL(hisi_event_sysfs_show); +EXPORT_SYMBOL_NS_GPL(hisi_event_sysfs_show, HISI_PMU); /* * sysfs cpumask attributes. For uncore PMU, we only have a single CPU to show @@ -60,7 +61,52 @@ ssize_t hisi_cpumask_sysfs_show(struct device *dev, return sysfs_emit(buf, "%d\n", hisi_pmu->on_cpu); } -EXPORT_SYMBOL_GPL(hisi_cpumask_sysfs_show); +EXPORT_SYMBOL_NS_GPL(hisi_cpumask_sysfs_show, HISI_PMU); + +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); + +static ssize_t hisi_associated_cpus_sysfs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, &hisi_pmu->associated_cpus); +} +static DEVICE_ATTR(associated_cpus, 0444, hisi_associated_cpus_sysfs_show, NULL); + +static struct attribute *hisi_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + &dev_attr_associated_cpus.attr, + NULL +}; + +const struct attribute_group hisi_pmu_cpumask_attr_group = { + .attrs = hisi_pmu_cpumask_attrs, +}; +EXPORT_SYMBOL_NS_GPL(hisi_pmu_cpumask_attr_group, HISI_PMU); + +ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier); +} +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_identifier_attr_show, HISI_PMU); + +static struct device_attribute hisi_pmu_identifier_attr = + __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); + +static struct attribute *hisi_pmu_identifier_attrs[] = { + &hisi_pmu_identifier_attr.attr, + NULL +}; + +const struct attribute_group hisi_pmu_identifier_group = { + .attrs = hisi_pmu_identifier_attrs, +}; +EXPORT_SYMBOL_NS_GPL(hisi_pmu_identifier_group, HISI_PMU); static bool hisi_validate_event_group(struct perf_event *event) { @@ -110,24 +156,14 @@ int hisi_uncore_pmu_get_event_idx(struct perf_event *event) return idx; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_get_event_idx); - -ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev)); - - return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier); -} -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_identifier_attr_show); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_get_event_idx, HISI_PMU); static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx) { clear_bit(idx, hisi_pmu->pmu_events.used_mask); } -static irqreturn_t hisi_uncore_pmu_isr(int irq, void *data) +irqreturn_t hisi_uncore_pmu_isr(int irq, void *data) { struct hisi_pmu *hisi_pmu = data; struct perf_event *event; @@ -156,6 +192,7 @@ static irqreturn_t hisi_uncore_pmu_isr(int irq, void *data) return IRQ_HANDLED; } +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_isr, HISI_PMU); int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, struct platform_device *pdev) @@ -179,7 +216,7 @@ int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_init_irq); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_init_irq, HISI_PMU); int hisi_uncore_pmu_event_init(struct perf_event *event) { @@ -212,7 +249,7 @@ int hisi_uncore_pmu_event_init(struct perf_event *event) return -EINVAL; hisi_pmu = to_hisi_pmu(event->pmu); - if (event->attr.config > hisi_pmu->check_event) + if ((event->attr.config & HISI_EVENTID_MASK) > hisi_pmu->check_event) return -EINVAL; if (hisi_pmu->on_cpu == -1) @@ -233,7 +270,7 @@ int hisi_uncore_pmu_event_init(struct perf_event *event) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_init); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_event_init, HISI_PMU); /* * Set the counter to count the event that we're interested in, @@ -287,7 +324,7 @@ void hisi_uncore_pmu_set_event_period(struct perf_event *event) /* Write start value to the hardware event counter */ hisi_pmu->ops->write_counter(hisi_pmu, hwc, val); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_set_event_period); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_set_event_period, HISI_PMU); void hisi_uncore_pmu_event_update(struct perf_event *event) { @@ -308,7 +345,7 @@ void hisi_uncore_pmu_event_update(struct perf_event *event) HISI_MAX_PERIOD(hisi_pmu->counter_bits); local64_add(delta, &event->count); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_event_update); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_event_update, HISI_PMU); void hisi_uncore_pmu_start(struct perf_event *event, int flags) { @@ -331,7 +368,7 @@ void hisi_uncore_pmu_start(struct perf_event *event, int flags) hisi_uncore_pmu_enable_event(event); perf_event_update_userpage(event); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_start); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_start, HISI_PMU); void hisi_uncore_pmu_stop(struct perf_event *event, int flags) { @@ -348,7 +385,7 @@ void hisi_uncore_pmu_stop(struct perf_event *event, int flags) hisi_uncore_pmu_event_update(event); hwc->state |= PERF_HES_UPTODATE; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_stop); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_stop, HISI_PMU); int hisi_uncore_pmu_add(struct perf_event *event, int flags) { @@ -371,7 +408,7 @@ int hisi_uncore_pmu_add(struct perf_event *event, int flags) return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_add); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_add, HISI_PMU); void hisi_uncore_pmu_del(struct perf_event *event, int flags) { @@ -383,14 +420,14 @@ void hisi_uncore_pmu_del(struct perf_event *event, int flags) perf_event_update_userpage(event); hisi_pmu->pmu_events.hw_events[hwc->idx] = NULL; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_del); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_del, HISI_PMU); void hisi_uncore_pmu_read(struct perf_event *event) { /* Read hardware counter and update the perf counter statistics */ hisi_uncore_pmu_event_update(event); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_read); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_read, HISI_PMU); void hisi_uncore_pmu_enable(struct pmu *pmu) { @@ -403,7 +440,7 @@ void hisi_uncore_pmu_enable(struct pmu *pmu) hisi_pmu->ops->start_counters(hisi_pmu); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_enable); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_enable, HISI_PMU); void hisi_uncore_pmu_disable(struct pmu *pmu) { @@ -411,7 +448,7 @@ void hisi_uncore_pmu_disable(struct pmu *pmu) hisi_pmu->ops->stop_counters(hisi_pmu); } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_disable); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_disable, HISI_PMU); /* @@ -458,22 +495,19 @@ static void hisi_read_sccl_and_ccl_id(int *scclp, int *cclp) */ static bool hisi_pmu_cpu_is_associated_pmu(struct hisi_pmu *hisi_pmu) { + struct hisi_pmu_topology *topo = &hisi_pmu->topo; int sccl_id, ccl_id; - /* If SCCL_ID is -1, the PMU is in a SICL and has no CPU affinity */ - if (hisi_pmu->sccl_id == -1) - return true; - - if (hisi_pmu->ccl_id == -1) { + if (topo->ccl_id == -1) { /* If CCL_ID is -1, the PMU only shares the same SCCL */ hisi_read_sccl_and_ccl_id(&sccl_id, NULL); - return sccl_id == hisi_pmu->sccl_id; + return sccl_id == topo->sccl_id; } hisi_read_sccl_and_ccl_id(&sccl_id, &ccl_id); - return sccl_id == hisi_pmu->sccl_id && ccl_id == hisi_pmu->ccl_id; + return sccl_id == topo->sccl_id && ccl_id == topo->ccl_id; } int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) @@ -481,24 +515,39 @@ int hisi_uncore_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu, node); - if (!hisi_pmu_cpu_is_associated_pmu(hisi_pmu)) + /* + * If the CPU is not associated to PMU, initialize the hisi_pmu->on_cpu + * based on the locality if it hasn't been initialized yet. For PMUs + * do have associated CPUs, it'll be updated later. + */ + if (!hisi_pmu_cpu_is_associated_pmu(hisi_pmu)) { + if (hisi_pmu->on_cpu != -1) + return 0; + + hisi_pmu->on_cpu = cpumask_local_spread(0, dev_to_node(hisi_pmu->dev)); + if (hisi_pmu->irq > 0) + WARN_ON(irq_set_affinity(hisi_pmu->irq, + cpumask_of(hisi_pmu->on_cpu))); return 0; + } cpumask_set_cpu(cpu, &hisi_pmu->associated_cpus); - /* If another CPU is already managing this PMU, simply return. */ - if (hisi_pmu->on_cpu != -1) + /* If another associated CPU is already managing this PMU, simply return. */ + if (hisi_pmu->on_cpu != -1 && + cpumask_test_cpu(hisi_pmu->on_cpu, &hisi_pmu->associated_cpus)) return 0; /* Use this CPU in cpumask for event counting */ hisi_pmu->on_cpu = cpu; /* Overflow interrupt also should use the same CPU */ - WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(cpu))); + if (hisi_pmu->irq > 0) + WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(cpu))); return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_online_cpu); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_online_cpu, HISI_PMU); int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) { @@ -507,9 +556,6 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) cpumask_t pmu_online_cpus; unsigned int target; - if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus)) - return 0; - /* Nothing to do if this CPU doesn't own the PMU */ if (hisi_pmu->on_cpu != cpu) return 0; @@ -521,17 +567,52 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) cpumask_and(&pmu_online_cpus, &hisi_pmu->associated_cpus, cpu_online_mask); target = cpumask_any_but(&pmu_online_cpus, cpu); + + if (target >= nr_cpu_ids) + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) return 0; perf_pmu_migrate_context(&hisi_pmu->pmu, cpu, target); /* Use this CPU for event counting */ hisi_pmu->on_cpu = target; - WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(target))); + + if (hisi_pmu->irq > 0) + WARN_ON(irq_set_affinity(hisi_pmu->irq, cpumask_of(target))); return 0; } -EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu); +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_offline_cpu, HISI_PMU); + +/* + * Retrieve the topology information from the firmware for the hisi_pmu device. + * The topology ID will be -1 if we cannot initialize it, it may either due to + * the PMU doesn't locate on this certain topology or the firmware needs to be + * fixed. + */ +void hisi_uncore_pmu_init_topology(struct hisi_pmu *hisi_pmu, struct device *dev) +{ + struct hisi_pmu_topology *topo = &hisi_pmu->topo; + + topo->sccl_id = -1; + topo->ccl_id = -1; + topo->index_id = -1; + topo->sub_id = -1; + + if (device_property_read_u32(dev, "hisilicon,scl-id", &topo->sccl_id)) + dev_dbg(dev, "no scl-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,ccl-id", &topo->ccl_id)) + dev_dbg(dev, "no ccl-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,idx-id", &topo->index_id)) + dev_dbg(dev, "no idx-id present\n"); + + if (device_property_read_u32(dev, "hisilicon,sub-id", &topo->sub_id)) + dev_dbg(dev, "no sub-id present\n"); +} +EXPORT_SYMBOL_NS_GPL(hisi_uncore_pmu_init_topology, HISI_PMU); void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module) { @@ -550,6 +631,6 @@ void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module) pmu->attr_groups = hisi_pmu->pmu_events.attr_groups; pmu->capabilities = PERF_PMU_CAP_NO_EXCLUDE; } -EXPORT_SYMBOL_GPL(hisi_pmu_init); +EXPORT_SYMBOL_NS_GPL(hisi_pmu_init, HISI_PMU); MODULE_LICENSE("GPL v2"); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index 92402aa69d70f5103f41c278d3e3515f14b8e752..31225c2ccdcee1035c26dea9123ccba8052e0fcd 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -43,7 +43,8 @@ return FIELD_GET(GENMASK_ULL(hi, lo), event->attr.config); \ } -#define HISI_GET_EVENTID(ev) (ev->hw.config_base & 0xff) +#define HISI_EVENTID_MASK 0xff +#define HISI_GET_EVENTID(ev) (ev->hw.config_base & HISI_EVENTID_MASK) #define HISI_PMU_EVTYPE_BITS 8 #define HISI_PMU_EVTYPE_SHIFT(idx) ((idx) % 4 * HISI_PMU_EVTYPE_BITS) @@ -72,6 +73,8 @@ struct hisi_uncore_ops { struct hisi_pmu_dev_info { const char *name; const struct attribute_group **attr_groups; + u32 counter_bits; + u32 check_event; void *private; }; @@ -81,27 +84,55 @@ struct hisi_pmu_hwevents { const struct attribute_group **attr_groups; }; +/** + * struct hisi_pmu_topology - Describe the topology hierarchy on which the PMU + * is located. + * @sccl_id: ID of the SCCL on which the PMU locate is located. + * @sicl_id: ID of the SICL on which the PMU locate is located. + * @scl_id: ID used by the core which is unaware of the SCCL/SICL. + * @ccl_id: ID of the CCL (CPU cluster) on which the PMU is located. + * @index_id: the ID of the PMU module if there're several PMUs at a + * particularly location in the topology. + * @sub_id: submodule ID of the PMU. For example we use this for DDRC PMU v2 + * since each DDRC has more than one DMC + * + * The ID will be -1 if the PMU isn't located on a certain topology. + */ +struct hisi_pmu_topology { + /* + * SCCL (Super CPU CLuster) and SICL (Super I/O Cluster) are parallel + * so a PMU cannot locate on a SCCL and a SICL. If the SCCL/SICL + * distinction is not relevant, use scl_id instead. + */ + union { + int sccl_id; + int sicl_id; + int scl_id; + }; + int ccl_id; + int index_id; + int sub_id; +}; + /* Generic pmu struct for different pmu types */ struct hisi_pmu { struct pmu pmu; const struct hisi_uncore_ops *ops; const struct hisi_pmu_dev_info *dev_info; struct hisi_pmu_hwevents pmu_events; - /* associated_cpus: All CPUs associated with the PMU */ + struct hisi_pmu_topology topo; + /* + * CPUs associated to the PMU and are preferred to use for counting. + * Could be empty if PMU has no association (e.g. PMU on SICL), in + * which case any online CPU will be used. + */ cpumask_t associated_cpus; /* CPU used for counting */ int on_cpu; int irq; struct device *dev; struct hlist_node node; - int sccl_id; - int sicl_id; - int ccl_id; void __iomem *base; - /* the ID of the PMU modules */ - u32 index_id; - /* For DDRC PMU v2: each DDRC has more than one DMC */ - u32 sub_id; int num_counters; int counter_bits; /* check event code range */ @@ -109,6 +140,10 @@ struct hisi_pmu { u32 identifier; }; +/* Generic implementation of cpumask/identifier group */ +extern const struct attribute_group hisi_pmu_cpumask_attr_group; +extern const struct attribute_group hisi_pmu_identifier_group; + int hisi_uncore_pmu_get_event_idx(struct perf_event *event); void hisi_uncore_pmu_read(struct perf_event *event); int hisi_uncore_pmu_add(struct perf_event *event, int flags); @@ -132,8 +167,10 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node); ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, struct device_attribute *attr, char *page); +irqreturn_t hisi_uncore_pmu_isr(int irq, void *data); int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, struct platform_device *pdev); +void hisi_uncore_pmu_init_topology(struct hisi_pmu *hisi_pmu, struct device *dev); void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module); #endif /* __HISI_UNCORE_PMU_H__ */ diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c index e706ca5676764b9186a18cd982b29aec907c8231..020bea8c6c7bba054e23dcbeef45c52595327f52 100644 --- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c @@ -28,6 +28,18 @@ #define SLLC_VERSION 0x1cf0 #define SLLC_EVENT_CNT0_L 0x1d00 +/* SLLC registers definition in v3 */ +#define SLLC_V3_INT_MASK 0x6834 +#define SLLC_V3_INT_STATUS 0x6838 +#define SLLC_V3_INT_CLEAR 0x683c +#define SLLC_V3_VERSION 0x6c00 +#define SLLC_V3_PERF_CTRL 0x6d00 +#define SLLC_V3_SRCID_CTRL 0x6d04 +#define SLLC_V3_TGTID_CTRL 0x6d08 +#define SLLC_V3_EVENT_CTRL 0x6d14 +#define SLLC_V3_EVENT_TYPE0 0x6d18 +#define SLLC_V3_EVENT_CNT0_L 0x6e00 + #define SLLC_EVTYPE_MASK 0xff #define SLLC_PERF_CTRL_EN BIT(0) #define SLLC_FILT_EN BIT(1) @@ -40,7 +52,14 @@ #define SLLC_TGTID_MAX_SHIFT 12 #define SLLC_SRCID_CMD_SHIFT 1 #define SLLC_SRCID_MSK_SHIFT 12 -#define SLLC_NR_EVENTS 0x80 + +#define SLLC_V3_TGTID_MIN_SHIFT 1 +#define SLLC_V3_TGTID_MAX_SHIFT 10 +#define SLLC_V3_SRCID_CMD_SHIFT 1 +#define SLLC_V3_SRCID_MSK_SHIFT 10 + +#define SLLC_NR_EVENTS 0xff +#define SLLC_EVENT_CNTn(cnt0, n) ((cnt0) + (n) * 8) HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_min, config1, 10, 0); HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_max, config1, 21, 11); @@ -48,6 +67,23 @@ HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 32, 22); HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 43, 33); HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 44, 44); +struct hisi_sllc_pmu_regs { + u32 int_mask; + u32 int_clear; + u32 int_status; + u32 perf_ctrl; + u32 srcid_ctrl; + u32 srcid_cmd_shift; + u32 srcid_mask_shift; + u32 tgtid_ctrl; + u32 tgtid_min_shift; + u32 tgtid_max_shift; + u32 event_ctrl; + u32 event_type0; + u32 version; + u32 event_cnt0; +}; + static bool tgtid_is_valid(u32 max, u32 min) { return max > 0 && max >= min; @@ -56,96 +92,104 @@ static bool tgtid_is_valid(u32 max, u32 min) static void hisi_sllc_pmu_enable_tracetag(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 tt_en = hisi_get_tracetag_en(event); if (tt_en) { u32 val; - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val |= SLLC_TRACETAG_EN | SLLC_FILT_EN; - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } static void hisi_sllc_pmu_disable_tracetag(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 tt_en = hisi_get_tracetag_en(event); if (tt_en) { u32 val; - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val &= ~(SLLC_TRACETAG_EN | SLLC_FILT_EN); - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } static void hisi_sllc_pmu_config_tgtid(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 min = hisi_get_tgtid_min(event); u32 max = hisi_get_tgtid_max(event); if (tgtid_is_valid(max, min)) { - u32 val = (max << SLLC_TGTID_MAX_SHIFT) | (min << SLLC_TGTID_MIN_SHIFT); + u32 val = (max << regs->tgtid_max_shift) | + (min << regs->tgtid_min_shift); - writel(val, sllc_pmu->base + SLLC_TGTID_CTRL); + writel(val, sllc_pmu->base + regs->tgtid_ctrl); /* Enable the tgtid */ - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val |= SLLC_TGTID_EN | SLLC_FILT_EN; - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } static void hisi_sllc_pmu_clear_tgtid(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 min = hisi_get_tgtid_min(event); u32 max = hisi_get_tgtid_max(event); if (tgtid_is_valid(max, min)) { u32 val; - writel(SLLC_TGTID_NONE, sllc_pmu->base + SLLC_TGTID_CTRL); + writel(SLLC_TGTID_NONE, sllc_pmu->base + regs->tgtid_ctrl); /* Disable the tgtid */ - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val &= ~(SLLC_TGTID_EN | SLLC_FILT_EN); - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } static void hisi_sllc_pmu_config_srcid(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 cmd = hisi_get_srcid_cmd(event); if (cmd) { u32 val, msk; msk = hisi_get_srcid_msk(event); - val = (cmd << SLLC_SRCID_CMD_SHIFT) | (msk << SLLC_SRCID_MSK_SHIFT); - writel(val, sllc_pmu->base + SLLC_SRCID_CTRL); + val = (cmd << regs->srcid_cmd_shift) | + (msk << regs->srcid_mask_shift); + writel(val, sllc_pmu->base + regs->srcid_ctrl); /* Enable the srcid */ - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val |= SLLC_SRCID_EN | SLLC_FILT_EN; - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } static void hisi_sllc_pmu_clear_srcid(struct perf_event *event) { struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 cmd = hisi_get_srcid_cmd(event); if (cmd) { u32 val; - writel(SLLC_SRCID_NONE, sllc_pmu->base + SLLC_SRCID_CTRL); + writel(SLLC_SRCID_NONE, sllc_pmu->base + regs->srcid_ctrl); /* Disable the srcid */ - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val &= ~(SLLC_SRCID_EN | SLLC_FILT_EN); - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } } @@ -167,29 +211,27 @@ static void hisi_sllc_pmu_clear_filter(struct perf_event *event) } } -static u32 hisi_sllc_pmu_get_counter_offset(int idx) -{ - return (SLLC_EVENT_CNT0_L + idx * 8); -} - static u64 hisi_sllc_pmu_read_counter(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc) { - return readq(sllc_pmu->base + - hisi_sllc_pmu_get_counter_offset(hwc->idx)); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; + + return readq(sllc_pmu->base + SLLC_EVENT_CNTn(regs->event_cnt0, hwc->idx)); } static void hisi_sllc_pmu_write_counter(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc, u64 val) { - writeq(val, sllc_pmu->base + - hisi_sllc_pmu_get_counter_offset(hwc->idx)); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; + + writeq(val, sllc_pmu->base + SLLC_EVENT_CNTn(regs->event_cnt0, hwc->idx)); } static void hisi_sllc_pmu_write_evtype(struct hisi_pmu *sllc_pmu, int idx, u32 type) { - u32 reg, reg_idx, shift, val; + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; + u32 reg, val; /* * Select the appropriate event select register(SLLC_EVENT_TYPE0/1). @@ -198,114 +240,117 @@ static void hisi_sllc_pmu_write_evtype(struct hisi_pmu *sllc_pmu, int idx, * SLLC_EVENT_TYPE0 is chosen. For the latter 4 hardware counters, * SLLC_EVENT_TYPE1 is chosen. */ - reg = SLLC_EVENT_TYPE0 + (idx / 4) * 4; - reg_idx = idx % 4; - shift = 8 * reg_idx; + reg = regs->event_type0 + (idx / 4) * 4; /* Write event code to SLLC_EVENT_TYPEx Register */ val = readl(sllc_pmu->base + reg); - val &= ~(SLLC_EVTYPE_MASK << shift); - val |= (type << shift); + val &= ~(SLLC_EVTYPE_MASK << HISI_PMU_EVTYPE_SHIFT(idx)); + val |= (type << HISI_PMU_EVTYPE_SHIFT(idx)); writel(val, sllc_pmu->base + reg); } static void hisi_sllc_pmu_start_counters(struct hisi_pmu *sllc_pmu) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val |= SLLC_PERF_CTRL_EN; - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } static void hisi_sllc_pmu_stop_counters(struct hisi_pmu *sllc_pmu) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_PERF_CTRL); + val = readl(sllc_pmu->base + regs->perf_ctrl); val &= ~(SLLC_PERF_CTRL_EN); - writel(val, sllc_pmu->base + SLLC_PERF_CTRL); + writel(val, sllc_pmu->base + regs->perf_ctrl); } static void hisi_sllc_pmu_enable_counter(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_EVENT_CTRL); - val |= 1 << hwc->idx; - writel(val, sllc_pmu->base + SLLC_EVENT_CTRL); + val = readl(sllc_pmu->base + regs->event_ctrl); + val |= BIT_ULL(hwc->idx); + writel(val, sllc_pmu->base + regs->event_ctrl); } static void hisi_sllc_pmu_disable_counter(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_EVENT_CTRL); - val &= ~(1 << hwc->idx); - writel(val, sllc_pmu->base + SLLC_EVENT_CTRL); + val = readl(sllc_pmu->base + regs->event_ctrl); + val &= ~BIT_ULL(hwc->idx); + writel(val, sllc_pmu->base + regs->event_ctrl); } static void hisi_sllc_pmu_enable_counter_int(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_INT_MASK); - /* Write 0 to enable interrupt */ - val &= ~(1 << hwc->idx); - writel(val, sllc_pmu->base + SLLC_INT_MASK); + val = readl(sllc_pmu->base + regs->int_mask); + val &= ~BIT_ULL(hwc->idx); + writel(val, sllc_pmu->base + regs->int_mask); } static void hisi_sllc_pmu_disable_counter_int(struct hisi_pmu *sllc_pmu, struct hw_perf_event *hwc) { + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; u32 val; - val = readl(sllc_pmu->base + SLLC_INT_MASK); - /* Write 1 to mask interrupt */ - val |= 1 << hwc->idx; - writel(val, sllc_pmu->base + SLLC_INT_MASK); + val = readl(sllc_pmu->base + regs->int_mask); + val |= BIT_ULL(hwc->idx); + writel(val, sllc_pmu->base + regs->int_mask); } static u32 hisi_sllc_pmu_get_int_status(struct hisi_pmu *sllc_pmu) { - return readl(sllc_pmu->base + SLLC_INT_STATUS); + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; + + return readl(sllc_pmu->base + regs->int_status); } static void hisi_sllc_pmu_clear_int_status(struct hisi_pmu *sllc_pmu, int idx) { - writel(1 << idx, sllc_pmu->base + SLLC_INT_CLEAR); -} + struct hisi_sllc_pmu_regs *regs = sllc_pmu->dev_info->private; -static const struct acpi_device_id hisi_sllc_pmu_acpi_match[] = { - { "HISI0263", }, - {} -}; -MODULE_DEVICE_TABLE(acpi, hisi_sllc_pmu_acpi_match); + writel(BIT_ULL(idx), sllc_pmu->base + regs->int_clear); +} static int hisi_sllc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *sllc_pmu) { + struct hisi_sllc_pmu_regs *regs; + + hisi_uncore_pmu_init_topology(sllc_pmu, &pdev->dev); + /* * Use the SCCL_ID and the index ID to identify the SLLC PMU, * while SCCL_ID is from MPIDR_EL1 by CPU. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &sllc_pmu->sccl_id)) { + if (sllc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Cannot read sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id", - &sllc_pmu->index_id)) { + if (sllc_pmu->topo.index_id < 0) { dev_err(&pdev->dev, "Cannot read idx-id!\n"); return -EINVAL; } - /* SLLC PMUs only share the same SCCL */ - sllc_pmu->ccl_id = -1; + sllc_pmu->dev_info = device_get_match_data(&pdev->dev); + if (!sllc_pmu->dev_info) + return -ENODEV; sllc_pmu->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(sllc_pmu->base)) { @@ -313,7 +358,8 @@ static int hisi_sllc_pmu_init_data(struct platform_device *pdev, return PTR_ERR(sllc_pmu->base); } - sllc_pmu->identifier = readl(sllc_pmu->base + SLLC_VERSION); + regs = sllc_pmu->dev_info->private; + sllc_pmu->identifier = readl(sllc_pmu->base + regs->version); return 0; } @@ -347,35 +393,54 @@ static const struct attribute_group hisi_sllc_pmu_v2_events_group = { .attrs = hisi_sllc_pmu_v2_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_sllc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, +static const struct attribute_group *hisi_sllc_pmu_v2_attr_groups[] = { + &hisi_sllc_pmu_v2_format_group, + &hisi_sllc_pmu_v2_events_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; -static const struct attribute_group hisi_sllc_pmu_cpumask_attr_group = { - .attrs = hisi_sllc_pmu_cpumask_attrs, +static struct hisi_sllc_pmu_regs hisi_sllc_v2_pmu_regs = { + .int_mask = SLLC_INT_MASK, + .int_clear = SLLC_INT_CLEAR, + .int_status = SLLC_INT_STATUS, + .perf_ctrl = SLLC_PERF_CTRL, + .srcid_ctrl = SLLC_SRCID_CTRL, + .srcid_cmd_shift = SLLC_SRCID_CMD_SHIFT, + .srcid_mask_shift = SLLC_SRCID_MSK_SHIFT, + .tgtid_ctrl = SLLC_TGTID_CTRL, + .tgtid_min_shift = SLLC_TGTID_MIN_SHIFT, + .tgtid_max_shift = SLLC_TGTID_MAX_SHIFT, + .event_ctrl = SLLC_EVENT_CTRL, + .event_type0 = SLLC_EVENT_TYPE0, + .version = SLLC_VERSION, + .event_cnt0 = SLLC_EVENT_CNT0_L, }; -static struct device_attribute hisi_sllc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_sllc_pmu_identifier_attrs[] = { - &hisi_sllc_pmu_identifier_attr.attr, - NULL +static const struct hisi_pmu_dev_info hisi_sllc_v2 = { + .private = &hisi_sllc_v2_pmu_regs, }; -static const struct attribute_group hisi_sllc_pmu_identifier_group = { - .attrs = hisi_sllc_pmu_identifier_attrs, +static struct hisi_sllc_pmu_regs hisi_sllc_v3_pmu_regs = { + .int_mask = SLLC_V3_INT_MASK, + .int_clear = SLLC_V3_INT_CLEAR, + .int_status = SLLC_V3_INT_STATUS, + .perf_ctrl = SLLC_V3_PERF_CTRL, + .srcid_ctrl = SLLC_V3_SRCID_CTRL, + .srcid_cmd_shift = SLLC_V3_SRCID_CMD_SHIFT, + .srcid_mask_shift = SLLC_V3_SRCID_MSK_SHIFT, + .tgtid_ctrl = SLLC_V3_TGTID_CTRL, + .tgtid_min_shift = SLLC_V3_TGTID_MIN_SHIFT, + .tgtid_max_shift = SLLC_V3_TGTID_MAX_SHIFT, + .event_ctrl = SLLC_V3_EVENT_CTRL, + .event_type0 = SLLC_V3_EVENT_TYPE0, + .version = SLLC_V3_VERSION, + .event_cnt0 = SLLC_V3_EVENT_CNT0_L, }; -static const struct attribute_group *hisi_sllc_pmu_v2_attr_groups[] = { - &hisi_sllc_pmu_v2_format_group, - &hisi_sllc_pmu_v2_events_group, - &hisi_sllc_pmu_cpumask_attr_group, - &hisi_sllc_pmu_identifier_group, - NULL +static const struct hisi_pmu_dev_info hisi_sllc_v3 = { + .private = &hisi_sllc_v3_pmu_regs, }; static const struct hisi_uncore_ops hisi_uncore_sllc_ops = { @@ -433,8 +498,8 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_sllc%u", - sllc_pmu->sccl_id, sllc_pmu->index_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_sllc%d", + sllc_pmu->topo.sccl_id, sllc_pmu->topo.index_id); if (!name) return -ENOMEM; @@ -470,6 +535,13 @@ static int hisi_sllc_pmu_remove(struct platform_device *pdev) return 0; } +static const struct acpi_device_id hisi_sllc_pmu_acpi_match[] = { + { "HISI0263", (kernel_ulong_t)&hisi_sllc_v2 }, + { "HISI0264", (kernel_ulong_t)&hisi_sllc_v3 }, + {} +}; +MODULE_DEVICE_TABLE(acpi, hisi_sllc_pmu_acpi_match); + static struct platform_driver hisi_sllc_pmu_driver = { .driver = { .name = "hisi_sllc_pmu", @@ -508,6 +580,7 @@ static void __exit hisi_sllc_pmu_module_exit(void) } module_exit(hisi_sllc_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SLLC uncore PMU driver"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Shaokun Zhang "); diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 481dcc9e8fbf88e681dd373b8bf6b611fd4f0b5a..f90f752f32dd88c254e56c6fd6e3ef923e92d839 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -11,7 +11,6 @@ #include #include #include -#include #include "hisi_uncore_pmu.h" @@ -366,25 +365,24 @@ static void hisi_uc_pmu_clear_int_status(struct hisi_pmu *uc_pmu, int idx) static int hisi_uc_pmu_init_data(struct platform_device *pdev, struct hisi_pmu *uc_pmu) { + hisi_uncore_pmu_init_topology(uc_pmu, &pdev->dev); + /* * Use SCCL (Super CPU Cluster) ID and CCL (CPU Cluster) ID to * identify the topology information of UC PMU devices in the chip. * They have some CCLs per SCCL and then 4 UC PMU per CCL. */ - if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id", - &uc_pmu->sccl_id)) { + if (uc_pmu->topo.sccl_id < 0) { dev_err(&pdev->dev, "Can not read uc sccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,ccl-id", - &uc_pmu->ccl_id)) { + if (uc_pmu->topo.ccl_id < 0) { dev_err(&pdev->dev, "Can not read uc ccl-id!\n"); return -EINVAL; } - if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id", - &uc_pmu->sub_id)) { + if (uc_pmu->topo.sub_id < 0) { dev_err(&pdev->dev, "Can not read sub-id!\n"); return -EINVAL; } @@ -439,34 +437,11 @@ static const struct attribute_group hisi_uc_pmu_events_group = { .attrs = hisi_uc_pmu_events_attr, }; -static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL); - -static struct attribute *hisi_uc_pmu_cpumask_attrs[] = { - &dev_attr_cpumask.attr, - NULL, -}; - -static const struct attribute_group hisi_uc_pmu_cpumask_attr_group = { - .attrs = hisi_uc_pmu_cpumask_attrs, -}; - -static struct device_attribute hisi_uc_pmu_identifier_attr = - __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL); - -static struct attribute *hisi_uc_pmu_identifier_attrs[] = { - &hisi_uc_pmu_identifier_attr.attr, - NULL -}; - -static const struct attribute_group hisi_uc_pmu_identifier_group = { - .attrs = hisi_uc_pmu_identifier_attrs, -}; - static const struct attribute_group *hisi_uc_pmu_attr_groups[] = { &hisi_uc_pmu_format_group, &hisi_uc_pmu_events_group, - &hisi_uc_pmu_cpumask_attr_group, - &hisi_uc_pmu_identifier_group, + &hisi_pmu_cpumask_attr_group, + &hisi_pmu_identifier_group, NULL }; @@ -538,8 +513,9 @@ static int hisi_uc_pmu_probe(struct platform_device *pdev) if (ret) return ret; - name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_uc%d_%u", - uc_pmu->sccl_id, uc_pmu->ccl_id, uc_pmu->sub_id); + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%d_uc%d_%d", + uc_pmu->topo.sccl_id, uc_pmu->topo.ccl_id, + uc_pmu->topo.sub_id); if (!name) return -ENOMEM; @@ -613,6 +589,7 @@ static void __exit hisi_uc_pmu_module_exit(void) } module_exit(hisi_uc_pmu_module_exit); +MODULE_IMPORT_NS(HISI_PMU); MODULE_DESCRIPTION("HiSilicon SoC UC uncore PMU driver"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Junhao He "); diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build index 78ef7115be3d91a76bf84240e030230bbc3f7521..4e8dabf98b29c26344e4e66a32d84ab4888042c7 100644 --- a/tools/perf/arch/arm64/util/Build +++ b/tools/perf/arch/arm64/util/Build @@ -3,6 +3,7 @@ perf-y += machine.o perf-y += perf_regs.o perf-y += tsc.o perf-y += pmu.o +perf-y += hisi-iostat.o perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o perf-$(CONFIG_DWARF) += dwarf-regs.o perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o diff --git a/tools/perf/arch/arm64/util/hisi-iostat.c b/tools/perf/arch/arm64/util/hisi-iostat.c new file mode 100644 index 0000000000000000000000000000000000000000..fc794ee7d8d46cc9e0b076982480d4506eeaad52 --- /dev/null +++ b/tools/perf/arch/arm64/util/hisi-iostat.c @@ -0,0 +1,451 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * perf iostat support for HiSilicon PCIe PMU. + * Partly derived from tools/perf/arch/x86/util/iostat.c. + * + * Copyright (c) 2024 HiSilicon Technologies Co., Ltd. + * Author: Yicong Yang + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "util/counts.h" +#include "util/cpumap.h" +#include "util/debug.h" +#include "util/iostat.h" +#include "util/pmu.h" + +/* From include/uapi/linux/pci.h */ +#define PCI_SLOT(devfn) (((devfn) >> 3) & 0x1f) +#define PCI_DEVFN(slot, func) ((((slot) & 0x1f) << 3) | ((func) & 0x07)) + +#define PCI_DEFAULT_DOMAIN 0 +#define PCI_DEVICE_NAME_PATTERN "%04x:%02hhx:%02hhx.%hhu" +#define PCI_ROOT_BUS_DEVICES_PATH "bus/pci/devices" + +static const char *hisi_iostat_metrics[] = { + "Inbound MWR(MB)", + "Inbound MRD(MB)", + "Inbound CPL(MB)", + "Outbound MWR(MB)", + "Outbound MRD(MB)", + "Outbound CPL(MB)", +}; + +static const char *hisi_iostat_cmd_template[] = { + /* Inbound Memory Write */ + "hisi_pcie%hu_core%hu/event=0x0104,port=0x%hx/", + /* Inbound Memory Read */ + "hisi_pcie%hu_core%hu/event=0x0804,port=0x%hx/", + /* Inbound Memory Completion */ + "hisi_pcie%hu_core%hu/event=0x2004,port=0x%hx/", + /* Outbound Memory Write */ + "hisi_pcie%hu_core%hu/event=0x0105,port=0x%hx/", + /* Outbound Memory Read */ + "hisi_pcie%hu_core%hu/event=0x0405,port=0x%hx/", + /* Outbound Memory Completion */ + "hisi_pcie%hu_core%hu/event=0x1005,port=0x%hx/", +}; + +struct hisi_pcie_root_port { + struct list_head list; + /* Is this Root Port selected for monitoring */ + bool selected; + /* IDs to locate the PMU */ + u16 sicl_id; + u16 core_id; + /* Filter mask for this Root Port */ + u16 mask; + /* PCIe Root Port's ::. */ + u32 domain; + u8 bus; + u8 dev; + u8 fn; +}; + +LIST_HEAD(hisi_pcie_root_ports_list); +static int hisi_pcie_root_ports_num; + +static void hisi_pcie_init_root_port_mask(struct hisi_pcie_root_port *rp, u16 devbase) +{ + rp->mask = BIT((rp->dev - devbase) << 1); +} + +/* + * Select specific Root Port to monitor. Return 0 if successfully find the + * Root Port, Otherwise -EINVAL. + */ +static int hisi_pcie_root_ports_select_one(u32 domain, u8 bus, u8 dev, u8 fn) +{ + struct hisi_pcie_root_port *rp; + + list_for_each_entry(rp, &hisi_pcie_root_ports_list, list) + if (domain == rp->domain && bus == rp->bus && + dev == rp->dev && fn == rp->fn) { + rp->selected = true; + return 0; + } + + return -EINVAL; +} + +static void hisi_pcie_root_ports_select_all(void) +{ + struct hisi_pcie_root_port *rp; + + list_for_each_entry(rp, &hisi_pcie_root_ports_list, list) + rp->selected = true; +} + +static void hisi_pcie_root_ports_add(u16 sicl_id, u16 core_id, u8 target_bus, + u16 bdf_min, u16 bdf_max) +{ + const char *sysfs = sysfs__mountpoint(); + struct hisi_pcie_root_port *rp; + struct dirent *dent; + char path[PATH_MAX]; + u8 bus, dev, fn; + u32 domain; + DIR *dir; + u16 bdf; + int ret; + + snprintf(path, PATH_MAX, "%s/%s", sysfs, PCI_ROOT_BUS_DEVICES_PATH); + dir = opendir(path); + if (!dir) + return; + + /* Scan the PCI root bus to find the match root port on @target_bus */ + while ((dent = readdir(dir))) { + ret = sscanf(dent->d_name, PCI_DEVICE_NAME_PATTERN, + &domain, &bus, &dev, &fn); + if (ret != 4 || bus != target_bus) + continue; + + bdf = (bus << 8) | PCI_DEVFN(dev, fn); + if (bdf < bdf_min || bdf > bdf_max) + continue; + + rp = zalloc(sizeof(*rp)); + if (!rp) + continue; + + rp->selected = false; + rp->sicl_id = sicl_id; + rp->core_id = core_id; + rp->domain = domain; + rp->bus = bus; + rp->dev = dev; + rp->fn = fn; + + hisi_pcie_init_root_port_mask(rp, PCI_SLOT(bdf_min)); + + list_add(&rp->list, &hisi_pcie_root_ports_list); + hisi_pcie_root_ports_num++; + + pr_debug3("Found root port %s\n", dent->d_name); + } + + closedir(dir); +} + +/* Scan the PMUs and build the mapping of the Root Ports to the PMU */ +static int hisi_pcie_root_ports_init(void) +{ + char event_source[PATH_MAX], bus_path[PATH_MAX]; + unsigned long long bus, bdf_max, bdf_min; + u16 sicl_id, core_id; + struct dirent *dent; + DIR *dir; + + perf_pmu__event_source_devices_scnprintf(event_source, sizeof(event_source)); + dir = opendir(event_source); + if (!dir) + return -ENOENT; + + while ((dent = readdir(dir))) { + /* + * This HiSilicon PCIe PMU will be named as: + * hisi_pcie_core + */ + if ((sscanf(dent->d_name, "hisi_pcie%hu_core%hu", &sicl_id, &core_id)) != 2) + continue; + + /* + * Driver will export the root port it can monitor through + * the "bus" sysfs attribute. + */ + scnprintf(bus_path, sizeof(bus_path), "%s/hisi_pcie%hu_core%hu/bus", + event_source, sicl_id, core_id); + + /* + * Per PCIe spec the bus should be 8bit, use unsigned long long + * for the convience of the library function. + */ + if (filename__read_ull(bus_path, &bus)) + continue; + + scnprintf(bus_path, sizeof(bus_path), "%s/hisi_pcie%hu_core%hu/bdf_max", + event_source, sicl_id, core_id); + if (filename__read_xll(bus_path, &bdf_max)) + bdf_max = -1; + + scnprintf(bus_path, sizeof(bus_path), "%s/hisi_pcie%hu_core%hu/bdf_min", + event_source, sicl_id, core_id); + if (filename__read_xll(bus_path, &bdf_min)) + bdf_min = 0; + + pr_debug3("Found pmu %s bus 0x%llx\n", dent->d_name, bus); + + hisi_pcie_root_ports_add(sicl_id, core_id, (u8)bus, (u16)bdf_min, (u16)bdf_max); + } + + closedir(dir); + return hisi_pcie_root_ports_num > 0 ? 0 : -ENOENT; +} + +static void hisi_pcie_root_ports_free(void) +{ + struct hisi_pcie_root_port *rp, *tmp; + + if (hisi_pcie_root_ports_num == 0) + return; + + list_for_each_entry_safe(rp, tmp, &hisi_pcie_root_ports_list, list) { + list_del(&rp->list); + zfree(&rp); + hisi_pcie_root_ports_num--; + } +} + +static int hisi_iostat_add_events(struct evlist *evl) +{ + struct hisi_pcie_root_port *rp; + struct evsel *evsel; + unsigned int i, j; + char *iostat_cmd; + int pos = 0; + int ret; + + if (!hisi_pcie_root_ports_num) + return -ENOENT; + + iostat_cmd = zalloc(PATH_MAX); + if (!iostat_cmd) + return -ENOMEM; + + list_for_each_entry(rp, &hisi_pcie_root_ports_list, list) { + if (!rp->selected) + continue; + + iostat_cmd[pos++] = '{'; + for (j = 0; j < ARRAY_SIZE(hisi_iostat_cmd_template); j++) { + pos += snprintf(iostat_cmd + pos, ARG_MAX - pos - 1, + hisi_iostat_cmd_template[j], + rp->sicl_id, rp->core_id, rp->mask); + + if (j == ARRAY_SIZE(hisi_iostat_cmd_template) - 1) + iostat_cmd[pos++] = '}'; + else + iostat_cmd[pos++] = ','; + } + + ret = parse_event(evl, iostat_cmd); + if (ret) + break; + + i = 0; + evlist__for_each_entry_reverse(evl, evsel) { + if (i == ARRAY_SIZE(hisi_iostat_cmd_template)) + break; + + evsel->priv = rp; + i++; + } + + memset(iostat_cmd, 0, PATH_MAX); + pos = 0; + } + + zfree(&iostat_cmd); + return ret; +} + +int iostat_prepare(struct evlist *evlist, + struct perf_stat_config *config) +{ + if (evlist->core.nr_entries > 0) { + pr_warning("The -e and -M options are not supported." + "All chosen events/metrics will be dropped\n"); + evlist__delete(evlist); + evlist = evlist__new(); + if (!evlist) + return -ENOMEM; + } + + config->metric_only = true; + config->aggr_mode = AGGR_GLOBAL; + + return hisi_iostat_add_events(evlist); +} + +static int hisi_pcie_root_ports_list_filter(const char *str) +{ + char *tok, *tmp, *copy = NULL; + u8 bus, dev, fn; + u32 domain; + int ret; + + copy = strdup(str); + if (!copy) + return -ENOMEM; + + for (tok = strtok_r(copy, ",", &tmp); tok; tok = strtok_r(NULL, ",", &tmp)) { + ret = sscanf(tok, PCI_DEVICE_NAME_PATTERN, &domain, &bus, &dev, &fn); + if (ret != 4) { + ret = -EINVAL; + break; + } + + ret = hisi_pcie_root_ports_select_one(domain, bus, dev, fn); + if (ret) + break; + } + + zfree(©); + return ret; +} + +int iostat_parse(const struct option *opt, const char *str, int unset __maybe_unused) +{ + struct perf_stat_config *config = (struct perf_stat_config *)opt->data; + int ret; + + ret = hisi_pcie_root_ports_init(); + if (!ret) { + config->iostat_run = true; + + if (!str) { + iostat_mode = IOSTAT_RUN; + hisi_pcie_root_ports_select_all(); + } else if (!strcmp(str, "list")) { + iostat_mode = IOSTAT_LIST; + hisi_pcie_root_ports_select_all(); + } else { + iostat_mode = IOSTAT_RUN; + ret = hisi_pcie_root_ports_list_filter(str); + } + } + + return ret; +} + +static void hisi_pcie_root_port_show(FILE *output, + const struct hisi_pcie_root_port * const rp) +{ + if (output && rp) + fprintf(output, "hisi_pcie%hu_core%hu<" PCI_DEVICE_NAME_PATTERN ">\n", + rp->sicl_id, rp->core_id, rp->domain, rp->bus, rp->dev, rp->fn); +} + +void iostat_list(struct evlist *evlist __maybe_unused, struct perf_stat_config *config) +{ + struct hisi_pcie_root_port *rp = NULL; + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) { + if (rp != evsel->priv) { + hisi_pcie_root_port_show(config->output, evsel->priv); + rp = evsel->priv; + } + } +} + +void iostat_release(struct evlist *evlist) +{ + struct evsel *evsel; + + evlist__for_each_entry(evlist, evsel) + evsel->priv = NULL; + + hisi_pcie_root_ports_free(); +} + +void iostat_print_header_prefix(struct perf_stat_config *config) +{ + if (config->csv_output) + fputs("port,", config->output); + else if (config->interval) + fprintf(config->output, "# time port "); + else + fprintf(config->output, " port "); +} + +void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel, + struct perf_stat_output_ctx *out) +{ + const char *iostat_metric = hisi_iostat_metrics[evsel->core.idx % ARRAY_SIZE(hisi_iostat_metrics)]; + struct perf_counts_values *count; + double iostat_value; + + /* We're using AGGR_GLOBAL so there's only one aggr counts aggr[0]. */ + count = &evsel->stats->aggr[0].counts; + + /* The counts has been scaled, we can use it directly. */ + iostat_value = (double)count->val; + + /* + * Display two digits after decimal point for better accuracy if the + * value is non-zero. + */ + out->print_metric(config, out->ctx, NULL, + iostat_value > 0 ? "%8.2f" : "%8.0f", + iostat_metric, iostat_value / (256 * 1024)); +} + +void iostat_prefix(struct evlist *evlist, struct perf_stat_config *config, + char *prefix, struct timespec *ts) +{ + struct hisi_pcie_root_port *rp = evlist->selected->priv; + + if (rp) { + if (ts) + sprintf(prefix, "%6lu.%09lu%s" PCI_DEVICE_NAME_PATTERN "%s", + ts->tv_sec, ts->tv_nsec, config->csv_sep, + rp->domain, rp->bus, rp->dev, rp->fn, + config->csv_sep); + else + sprintf(prefix, PCI_DEVICE_NAME_PATTERN "%s", + rp->domain, rp->bus, rp->dev, rp->fn, + config->csv_sep); + } +} + +void iostat_print_counters(struct evlist *evlist, struct perf_stat_config *config, + struct timespec *ts, char *prefix, + iostat_print_counter_t print_cnt_cb, void *arg) +{ + struct evsel *counter = evlist__first(evlist); + void *perf_device; + + evlist__set_selected(evlist, counter); + iostat_prefix(evlist, config, prefix, ts); + fprintf(config->output, "%s", prefix); + evlist__for_each_entry(evlist, counter) { + perf_device = evlist->selected->priv; + if (perf_device && perf_device != counter->priv) { + evlist__set_selected(evlist, counter); + iostat_prefix(evlist, config, prefix, ts); + fprintf(config->output, "\n%s", prefix); + } + print_cnt_cb(config, counter, arg); + } + fputc('\n', config->output); +}