[Deepin-Kernel-SIG] [linux 6.6-y] [Upstream] [Alibaba] Support Root Port PMU for Yitian710 （回合upstream社区rootport pmu 驱动到6.6内核）

Documentation/admin-guide/perf/dwc_pcie_pmu.rst

@@ -0,0 +1,94 @@
+======================================================================
+Synopsys DesignWare Cores (DWC) PCIe Performance Monitoring Unit (PMU)
+======================================================================
+
+DesignWare Cores (DWC) PCIe PMU
+===============================
+
+The PMU is a PCIe configuration space register block provided by each PCIe Root
+Port in a Vendor-Specific Extended Capability named RAS D.E.S (Debug, Error
+injection, and Statistics).
+
+As the name indicates, the RAS DES capability supports system level
+debugging, AER error injection, and collection of statistics. To facilitate
+collection of statistics, Synopsys DesignWare Cores PCIe controller
+provides the following two features:
+
+- one 64-bit counter for Time Based Analysis (RX/TX data throughput and
+  time spent in each low-power LTSSM state) and
+- one 32-bit counter for Event Counting (error and non-error events for
+  a specified lane)
+
+Note: There is no interrupt for counter overflow.
+
+Time Based Analysis
+-------------------
+
+Using this feature you can obtain information regarding RX/TX data
+throughput and time spent in each low-power LTSSM state by the controller.
+The PMU measures data in two categories:
+
+- Group#0: Percentage of time the controller stays in LTSSM states.
+- Group#1: Amount of data processed (Units of 16 bytes).
+
+Lane Event counters
+-------------------
+
+Using this feature you can obtain Error and Non-Error information in
+specific lane by the controller. The PMU event is selected by all of:
+
+- Group i
+- Event j within the Group i
+- Lane k
+
+Some of the events only exist for specific configurations.
+
+DesignWare Cores (DWC) PCIe PMU Driver
+=======================================
+
+This driver adds PMU devices for each PCIe Root Port named based on the BDF of
+the Root Port. For example,
+
+    30:03.0 PCI bridge: Device 1ded:8000 (rev 01)
+
+the PMU device name for this Root Port is dwc_rootport_3018.
+
+The DWC PCIe PMU driver registers a perf PMU driver, which provides
+description of available events and configuration options in sysfs, see
+/sys/bus/event_source/devices/dwc_rootport_{bdf}.
+
+The "format" directory describes format of the config fields of the
+perf_event_attr structure. The "events" directory provides configuration
+templates for all documented events.  For example,
+"Rx_PCIe_TLP_Data_Payload" is an equivalent of "eventid=0x22,type=0x1".
+
+The "perf list" command shall list the available events from sysfs, e.g.::
+
+    $# perf list | grep dwc_rootport
+    <...>
+    dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/        [Kernel PMU event]
+    <...>
+    dwc_rootport_3018/rx_memory_read,lane=?/               [Kernel PMU event]
+
+Time Based Analysis Event Usage
+-------------------------------
+
+Example usage of counting PCIe RX TLP data payload (Units of bytes)::
+
+    $# perf stat -a -e dwc_rootport_3018/Rx_PCIe_TLP_Data_Payload/
+
+The average RX/TX bandwidth can be calculated using the following formula:
+
+    PCIe RX Bandwidth = Rx_PCIe_TLP_Data_Payload / Measure_Time_Window
+    PCIe TX Bandwidth = Tx_PCIe_TLP_Data_Payload / Measure_Time_Window
+
+Lane Event Usage
+-------------------------------
+
+Each lane has the same event set and to avoid generating a list of hundreds
+of events, the user need to specify the lane ID explicitly, e.g.::
+
+    $# perf stat -a -e dwc_rootport_3018/rx_memory_read,lane=4/
+
+The driver does not support sampling, therefore "perf record" will not
+work. Per-task (without "-a") perf sessions are not supported.

Documentation/admin-guide/perf/index.rst

@@ -19,6 +19,7 @@ Performance monitor support
    arm_dsu_pmu
    thunderx2-pmu
    alibaba_pmu
+   dwc_pcie_pmu
    nvidia-pmu
    meson-ddr-pmu
    cxl

drivers/infiniband/hw/erdma/erdma_hw.h

@@ -11,8 +11,6 @@
 #include <linux/types.h>
 
 /* PCIe device related definition. */
-#define PCI_VENDOR_ID_ALIBABA 0x1ded
-
 #define ERDMA_PCI_WIDTH 64
 #define ERDMA_FUNC_BAR 0
 #define ERDMA_MISX_BAR 2

drivers/pci/access.c

@@ -598,3 +598,15 @@ int pci_write_config_dword(const struct pci_dev *dev, int where,
 	return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val);
 }
 EXPORT_SYMBOL(pci_write_config_dword);
+
+void pci_clear_and_set_config_dword(const struct pci_dev *dev, int pos,
+				    u32 clear, u32 set)
+{
+	u32 val;
+
+	pci_read_config_dword(dev, pos, &val);
+	val &= ~clear;
+	val |= set;
+	pci_write_config_dword(dev, pos, val);
+}
+EXPORT_SYMBOL(pci_clear_and_set_config_dword);

drivers/pci/pcie/aspm.c

@@ -423,17 +423,6 @@ static void pcie_aspm_check_latency(struct pci_dev *endpoint)
 	}
 }
 
-static void pci_clear_and_set_dword(struct pci_dev *pdev, int pos,
-				    u32 clear, u32 set)
-{
-	u32 val;
-
-	pci_read_config_dword(pdev, pos, &val);
-	val &= ~clear;
-	val |= set;
-	pci_write_config_dword(pdev, pos, val);
-}
-
 /* Calculate L1.2 PM substate timing parameters */
 static void aspm_calc_l12_info(struct pcie_link_state *link,
 				u32 parent_l1ss_cap, u32 child_l1ss_cap)
@@ -494,33 +483,39 @@ static void aspm_calc_l12_info(struct pcie_link_state *link,
 	cl1_2_enables = cctl1 & PCI_L1SS_CTL1_L1_2_MASK;
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-					PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1,
+					       PCI_L1SS_CTL1_L1_2_MASK, 0);
 	}
 
 	/* Program T_POWER_ON times in both ports */
 	pci_write_config_dword(parent, parent->l1ss + PCI_L1SS_CTL2, ctl2);
 	pci_write_config_dword(child, child->l1ss + PCI_L1SS_CTL2, ctl2);
 
 	/* Program Common_Mode_Restore_Time in upstream device */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_CM_RESTORE_TIME, ctl1);
 
 	/* Program LTR_L1.2_THRESHOLD time in both ports */
-	pci_clear_and_set_dword(parent,	parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
-				PCI_L1SS_CTL1_LTR_L12_TH_SCALE, ctl1);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_LTR_L12_TH_VALUE |
+				       PCI_L1SS_CTL1_LTR_L12_TH_SCALE,
+				       ctl1);
 
 	if (pl1_2_enables || cl1_2_enables) {
-		pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1, 0,
-					pl1_2_enables);
-		pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1, 0,
-					cl1_2_enables);
+		pci_clear_and_set_config_dword(parent,
+					       parent->l1ss + PCI_L1SS_CTL1, 0,
+					       pl1_2_enables);
+		pci_clear_and_set_config_dword(child,
+					       child->l1ss + PCI_L1SS_CTL1, 0,
+					       cl1_2_enables);
 	}
 }
 
@@ -680,10 +675,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 	 */
 
 	/* Disable all L1 substates */
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, 0);
 	/*
 	 * If needed, disable L1, and it gets enabled later
 	 * in pcie_config_aspm_link().
@@ -706,10 +701,10 @@ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state)
 		val |= PCI_L1SS_CTL1_PCIPM_L1_2;
 
 	/* Enable what we need to enable */
-	pci_clear_and_set_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
-	pci_clear_and_set_dword(child, child->l1ss + PCI_L1SS_CTL1,
-				PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(parent, parent->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
+	pci_clear_and_set_config_dword(child, child->l1ss + PCI_L1SS_CTL1,
+				       PCI_L1SS_CTL1_L1SS_MASK, val);
 }
 
 static void pcie_config_aspm_dev(struct pci_dev *pdev, u32 val)

drivers/perf/Kconfig

@@ -217,6 +217,13 @@ config MARVELL_CN10K_DDR_PMU
 	  Enable perf support for Marvell DDR Performance monitoring
 	  event on CN10K platform.
 
+config DWC_PCIE_PMU
+	tristate "Synopsys DesignWare PCIe PMU"
+	depends on PCI
+	help
+	  Enable perf support for Synopsys DesignWare PCIe PMU Performance
+	  monitoring event on platform including the Alibaba Yitian 710.
+
 source "drivers/perf/arm_cspmu/Kconfig"
 
 source "drivers/perf/amlogic/Kconfig"

drivers/perf/Makefile

@@ -23,6 +23,7 @@ obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
 obj-$(CONFIG_APPLE_M1_CPU_PMU) += apple_m1_cpu_pmu.o
 obj-$(CONFIG_ALIBABA_UNCORE_DRW_PMU) += alibaba_uncore_drw_pmu.o
+obj-$(CONFIG_DWC_PCIE_PMU) += dwc_pcie_pmu.o
 obj-$(CONFIG_ARM_CORESIGHT_PMU_ARCH_SYSTEM_PMU) += arm_cspmu/
 obj-$(CONFIG_MESON_DDR_PMU) += amlogic/
 obj-$(CONFIG_CXL_PMU) += cxl_pmu.o