Merge branch 'for-next/perf' into for-next/core

* for-next/perf:
  drivers/perf: arm_spe: Fix consistency of SYS_PMSCR_EL1.CX
  perf: RISC-V: Add of_node_put() when breaking out of for_each_of_cpu_node()
  docs: perf: Include hns3-pmu.rst in toctree to fix 'htmldocs' WARNING
  drivers/perf: hisi: add driver for HNS3 PMU
  drivers/perf: hisi: Add description for HNS3 PMU driver
  drivers/perf: riscv_pmu_sbi: perf format
  perf/arm-cci: Use the bitmap API to allocate bitmaps
  drivers/perf: riscv_pmu: Add riscv pmu pm notifier
  perf: hisi: Extract hisi_pmu_init
  perf/marvell_cn10k: Fix TAD PMU register offset
  perf/marvell_cn10k: Remove useless license text when SPDX-License-Identifier is already used
  arm64: cpufeature: Allow different PMU versions in ID_DFR0_EL1
  perf/arm-cci: fix typo in comment
  drivers/perf:Directly use ida_alloc()/free()
  drivers/perf: Directly use ida_alloc()/free()

Author: willdeacon

Documentation/admin-guide/perf/hns3-pmu.rst

@@ -0,0 +1,136 @@
+======================================
+HNS3 Performance Monitoring Unit (PMU)
+======================================
+
+HNS3(HiSilicon network system 3) Performance Monitoring Unit (PMU) is an
+End Point device to collect performance statistics of HiSilicon SoC NIC.
+On Hip09, each SICL(Super I/O cluster) has one PMU device.
+
+HNS3 PMU supports collection of performance statistics such as bandwidth,
+latency, packet rate and interrupt rate.
+
+Each HNS3 PMU supports 8 hardware events.
+
+HNS3 PMU driver
+===============
+
+The HNS3 PMU driver registers a perf PMU with the name of its sicl id.::
+
+  /sys/devices/hns3_pmu_sicl_<sicl_id>
+
+PMU driver provides description of available events, filter modes, format,
+identifier and cpumask in sysfs.
+
+The "events" directory describes the event code of all supported events
+shown in perf list.
+
+The "filtermode" directory describes the supported filter modes of each
+event.
+
+The "format" directory describes all formats of the config (events) and
+config1 (filter options) fields of the perf_event_attr structure.
+
+The "identifier" file shows version of PMU hardware device.
+
+The "bdf_min" and "bdf_max" files show the supported bdf range of each
+pmu device.
+
+The "hw_clk_freq" file shows the hardware clock frequency of each pmu
+device.
+
+Example usage of checking event code and subevent code::
+
+  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_time
+  config=0x00204
+  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_packet_num
+  config=0x10204
+
+Each performance statistic has a pair of events to get two values to
+calculate real performance data in userspace.
+
+The bits 0~15 of config (here 0x0204) are the true hardware event code. If
+two events have same value of bits 0~15 of config, that means they are
+event pair. And the bit 16 of config indicates getting counter 0 or
+counter 1 of hardware event.
+
+After getting two values of event pair in usersapce, the formula of
+computation to calculate real performance data is:::
+
+  counter 0 / counter 1
+
+Example usage of checking supported filter mode::
+
+  $# cat /sys/devices/hns3_pmu_sicl_0/filtermode/bw_ssu_rpu_byte_num
+  filter mode supported: global/port/port-tc/func/func-queue/
+
+Example usage of perf::
+
+  $# perf list
+  hns3_pmu_sicl_0/bw_ssu_rpu_byte_num/ [kernel PMU event]
+  hns3_pmu_sicl_0/bw_ssu_rpu_time/     [kernel PMU event]
+  ------------------------------------------
+
+  $# perf stat -g -e hns3_pmu_sicl_0/bw_ssu_rpu_byte_num,global=1/ -e hns3_pmu_sicl_0/bw_ssu_rpu_time,global=1/ -I 1000
+  or
+  $# perf stat -g -e hns3_pmu_sicl_0/config=0x00002,global=1/ -e hns3_pmu_sicl_0/config=0x10002,global=1/ -I 1000
+
+
+Filter modes
+--------------
+
+1. global mode
+PMU collect performance statistics for all HNS3 PCIe functions of IO DIE.
+Set the "global" filter option to 1 will enable this mode.
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x1020F,global=1/ -I 1000
+
+2. port mode
+PMU collect performance statistic of one whole physical port. The port id
+is same as mac id. The "tc" filter option must be set to 0xF in this mode,
+here tc stands for traffic class.
+
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x1020F,port=0,tc=0xF/ -I 1000
+
+3. port-tc mode
+PMU collect performance statistic of one tc of physical port. The port id
+is same as mac id. The "tc" filter option must be set to 0 ~ 7 in this
+mode.
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x1020F,port=0,tc=0/ -I 1000
+
+4. func mode
+PMU collect performance statistic of one PF/VF. The function id is BDF of
+PF/VF, its conversion formula::
+
+  func = (bus << 8) + (device << 3) + (function)
+
+for example:
+  BDF         func
+  35:00.0    0x3500
+  35:00.1    0x3501
+  35:01.0    0x3508
+
+In this mode, the "queue" filter option must be set to 0xFFFF.
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x1020F,bdf=0x3500,queue=0xFFFF/ -I 1000
+
+5. func-queue mode
+PMU collect performance statistic of one queue of PF/VF. The function id
+is BDF of PF/VF, the "queue" filter option must be set to the exact queue
+id of function.
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x1020F,bdf=0x3500,queue=0/ -I 1000
+
+6. func-intr mode
+PMU collect performance statistic of one interrupt of PF/VF. The function
+id is BDF of PF/VF, the "intr" filter option must be set to the exact
+interrupt id of function.
+Example usage of perf::
+
+  $# perf stat -a -e hns3_pmu_sicl_0/config=0x00301,bdf=0x3500,intr=0/ -I 1000

Documentation/admin-guide/perf/index.rst

@@ -9,6 +9,7 @@ Performance monitor support
 
    hisi-pmu
    hisi-pcie-pmu
+   hns3-pmu
    imx-ddr
    qcom_l2_pmu
    qcom_l3_pmu

MAINTAINERS

@@ -8944,6 +8944,12 @@ F:	Documentation/admin-guide/perf/hisi-pcie-pmu.rst
 F:	Documentation/admin-guide/perf/hisi-pmu.rst
 F:	drivers/perf/hisilicon
 
+HISILICON HNS3 PMU DRIVER
+M:	Guangbin Huang <[email protected]>
+S:	Supported
+F:	Documentation/admin-guide/perf/hns3-pmu.rst
+F:	drivers/perf/hisilicon/hns3_pmu.c
+
 HISILICON QM AND ZIP Controller DRIVER
 M:	Zhou Wang <[email protected]>
 L:	[email protected]

arch/arm64/kernel/cpufeature.c

@@ -562,7 +562,7 @@ static const struct arm64_ftr_bits ftr_id_pfr2[] = {
 
 static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	/* [31:28] TraceFilt */
-	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_PERFMON_SHIFT, 4, 0xf),
+	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_PERFMON_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0),

drivers/perf/arm-cci.c

@@ -1139,7 +1139,7 @@ static void cci_pmu_start(struct perf_event *event, int pmu_flags)
 
 	/*
 	 * To handle interrupt latency, we always reprogram the period
-	 * regardlesss of PERF_EF_RELOAD.
+	 * regardless of PERF_EF_RELOAD.
 	 */
 	if (pmu_flags & PERF_EF_RELOAD)
 		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
@@ -1261,7 +1261,7 @@ static int validate_group(struct perf_event *event)
 		 */
 		.used_mask = mask,
 	};
-	memset(mask, 0, BITS_TO_LONGS(cci_pmu->num_cntrs) * sizeof(unsigned long));
+	bitmap_zero(mask, cci_pmu->num_cntrs);
 
 	if (!validate_event(event->pmu, &fake_pmu, leader))
 		return -EINVAL;
@@ -1629,10 +1629,9 @@ static struct cci_pmu *cci_pmu_alloc(struct device *dev)
 					     GFP_KERNEL);
 	if (!cci_pmu->hw_events.events)
 		return ERR_PTR(-ENOMEM);
-	cci_pmu->hw_events.used_mask = devm_kcalloc(dev,
-						BITS_TO_LONGS(CCI_PMU_MAX_HW_CNTRS(model)),
-						sizeof(*cci_pmu->hw_events.used_mask),
-						GFP_KERNEL);
+	cci_pmu->hw_events.used_mask = devm_bitmap_zalloc(dev,
+							  CCI_PMU_MAX_HW_CNTRS(model),
+							  GFP_KERNEL);
 	if (!cci_pmu->hw_events.used_mask)
 		return ERR_PTR(-ENOMEM);
 

drivers/perf/arm-ccn.c

@@ -1250,7 +1250,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	ccn->dt.cmp_mask[CCN_IDX_MASK_OPCODE].h = ~(0x1f << 9);
 
 	/* Get a convenient /sys/event_source/devices/ name */
-	ccn->dt.id = ida_simple_get(&arm_ccn_pmu_ida, 0, 0, GFP_KERNEL);
+	ccn->dt.id = ida_alloc(&arm_ccn_pmu_ida, GFP_KERNEL);
 	if (ccn->dt.id == 0) {
 		name = "ccn";
 	} else {
@@ -1312,7 +1312,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 					    &ccn->dt.node);
 error_set_affinity:
 error_choose_name:
-	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
+	ida_free(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)
 		writel(0, ccn->xp[i].base + CCN_XP_DT_CONTROL);
 	writel(0, ccn->dt.base + CCN_DT_PMCR);
@@ -1329,7 +1329,7 @@ static void arm_ccn_pmu_cleanup(struct arm_ccn *ccn)
 		writel(0, ccn->xp[i].base + CCN_XP_DT_CONTROL);
 	writel(0, ccn->dt.base + CCN_DT_PMCR);
 	perf_pmu_unregister(&ccn->dt.pmu);
-	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
+	ida_free(&arm_ccn_pmu_ida, ccn->dt.id);
 }
 
 static int arm_ccn_for_each_valid_region(struct arm_ccn *ccn,

drivers/perf/arm_spe_pmu.c

@@ -39,6 +39,24 @@
 #include <asm/mmu.h>
 #include <asm/sysreg.h>
 
+/*
+ * Cache if the event is allowed to trace Context information.
+ * This allows us to perform the check, i.e, perfmon_capable(),
+ * in the context of the event owner, once, during the event_init().
+ */
+#define SPE_PMU_HW_FLAGS_CX			BIT(0)
+
+static void set_spe_event_has_cx(struct perf_event *event)
+{
+	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
+		event->hw.flags |= SPE_PMU_HW_FLAGS_CX;
+}
+
+static bool get_spe_event_has_cx(struct perf_event *event)
+{
+	return !!(event->hw.flags & SPE_PMU_HW_FLAGS_CX);
+}
+
 #define ARM_SPE_BUF_PAD_BYTE			0
 
 struct arm_spe_pmu_buf {
@@ -272,7 +290,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event)
 	if (!attr->exclude_kernel)
 		reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT);
 
-	if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable())
+	if (get_spe_event_has_cx(event))
 		reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT);
 
 	return reg;
@@ -709,10 +727,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event)
 	    !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT))
 		return -EOPNOTSUPP;
 
+	set_spe_event_has_cx(event);
 	reg = arm_spe_event_to_pmscr(event);
 	if (!perfmon_capable() &&
 	    (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) |
-		    BIT(SYS_PMSCR_EL1_CX_SHIFT) |
 		    BIT(SYS_PMSCR_EL1_PCT_SHIFT))))
 		return -EACCES;
 

drivers/perf/fsl_imx8_ddr_perf.c

@@ -611,7 +611,7 @@ static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
 		.dev = dev,
 	};
 
-	pmu->id = ida_simple_get(&ddr_ida, 0, 0, GFP_KERNEL);
+	pmu->id = ida_alloc(&ddr_ida, GFP_KERNEL);
 	return pmu->id;
 }
 
@@ -765,7 +765,7 @@ static int ddr_perf_probe(struct platform_device *pdev)
 cpuhp_instance_err:
 	cpuhp_remove_multi_state(pmu->cpuhp_state);
 cpuhp_state_err:
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 	dev_warn(&pdev->dev, "i.MX8 DDR Perf PMU failed (%d), disabled\n", ret);
 	return ret;
 }
@@ -779,7 +779,7 @@ static int ddr_perf_remove(struct platform_device *pdev)
 
 	perf_pmu_unregister(&pmu->pmu);
 
-	ida_simple_remove(&ddr_ida, pmu->id);
+	ida_free(&ddr_ida, pmu->id);
 	return 0;
 }
 

drivers/perf/hisilicon/Kconfig

@@ -14,3 +14,13 @@ config HISI_PCIE_PMU
 	  RCiEP devices.
 	  Adds the PCIe PMU into perf events system for monitoring latency,
 	  bandwidth etc.
+
+config HNS3_PMU
+	tristate "HNS3 PERF PMU"
+	depends on ARM64 || COMPILE_TEST
+	depends on PCI
+	help
+	  Provide support for HNS3 performance monitoring unit (PMU) RCiEP
+	  devices.
+	  Adds the HNS3 PMU into perf events system for monitoring latency,
+	  bandwidth etc.

drivers/perf/hisilicon/Makefile

@@ -4,3 +4,4 @@ obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
 			  hisi_uncore_pa_pmu.o hisi_uncore_cpa_pmu.o
 
 obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o
+obj-$(CONFIG_HNS3_PMU) += hns3_pmu.o