* [dpdk-dev] [PATCH v2 1/1] virt2phys: virtual to physical address translator for Windows
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-13 5:32 ` Ranjit Menon
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 02/10] eal/windows: do not expose private EAL facilities Dmitry Kozlyuk
` (10 subsequent siblings)
11 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk
This driver supports Windows EAL memory management by translating
current process virtual addresses to physical addresses (IOVA).
Standalone virt2phys allows using DPDK without PMD and provides a
reference implementation.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
Note: this patch is for dpdk-kmods tree.
windows/README.rst | 92 ++++++++
windows/virt2phys/virt2phys.c | 129 +++++++++++
windows/virt2phys/virt2phys.h | 34 +++
windows/virt2phys/virt2phys.inf | 64 ++++++
windows/virt2phys/virt2phys.sln | 27 +++
windows/virt2phys/virt2phys.vcxproj | 228 ++++++++++++++++++++
windows/virt2phys/virt2phys.vcxproj.filters | 36 ++++
7 files changed, 610 insertions(+)
create mode 100644 windows/README.rst
create mode 100755 windows/virt2phys/virt2phys.c
create mode 100755 windows/virt2phys/virt2phys.h
create mode 100755 windows/virt2phys/virt2phys.inf
create mode 100755 windows/virt2phys/virt2phys.sln
create mode 100755 windows/virt2phys/virt2phys.vcxproj
create mode 100755 windows/virt2phys/virt2phys.vcxproj.filters
diff --git a/windows/README.rst b/windows/README.rst
new file mode 100644
index 0000000..e30d4dc
--- /dev/null
+++ b/windows/README.rst
@@ -0,0 +1,92 @@
+Developing Windows Drivers
+==========================
+
+Prerequisites
+-------------
+
+Building Windows Drivers is only possible on Windows.
+
+1. Visual Studio 2019 Community or Professional Edition
+2. Windows Driver Kit (WDK) for Windows 10, version 1903
+
+Follow the official instructions to obtain all of the above:
+https://docs.microsoft.com/en-us/windows-hardware/drivers/download-the-wdk
+
+
+Build the Drivers
+-----------------
+
+Build from Visual Studio
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Open a solution (``*.sln``) with Visual Studio and build it (Ctrl+Shift+B).
+
+
+Build from Command-Line
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Run *Developer Command Prompt for VS 2019* from the Start menu.
+
+Navigate to the solution directory (with ``*.sln``), then run:
+
+.. code-block:: console
+
+ msbuild
+
+To build a particular combination of configuration and platform:
+
+.. code-block:: console
+
+ msbuild -p:Configuration=Debug;Platform=x64
+
+
+Install the Drivers
+-------------------
+
+Disable Driver Signature Enforcement
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default Windows prohibits installing and loading drivers without `digital
+signature`_ obtained from Microsoft. For development signature enforcement may
+be disabled as follows.
+
+In Elevated Command Prompt (from this point, sufficient privileges are
+assumed):
+
+.. code-block:: console
+
+ bcdedit -set loadoptions DISABLE_INTEGRITY_CHECKS
+ bcdedit -set TESTSIGNING ON
+ shutdown -r -t 0
+
+Upon reboot, an overlay message should appear on the desktop informing
+that Windows is in test mode, which means it allows loading unsigned drivers.
+
+.. _digital signature: https://docs.microsoft.com/en-us/windows-hardware/drivers/install/driver-signing
+
+
+Install, List, and Remove Drivers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Driver package is by default located in a subdirectory of its source tree,
+e.g. ``x64\Debug\virt2phys\virt2phys`` (note two levels of ``virt2phys``).
+
+To install the driver and bind associated devices to it:
+
+.. code-block:: console
+
+ pnputil /add-driver x64\Debug\virt2phys\virt2phys\virt2phys.inf /install
+
+A graphical confirmation to load an unsigned driver will still appear.
+
+To list installed drivers:
+
+.. code-block:: console
+
+ pnputil /enum-drivers
+
+To remove the driver package and to uninstall its devices:
+
+.. code-block:: console
+
+ pnputil /delete-driver oem2.inf /uninstall
diff --git a/windows/virt2phys/virt2phys.c b/windows/virt2phys/virt2phys.c
new file mode 100755
index 0000000..e157e9c
--- /dev/null
+++ b/windows/virt2phys/virt2phys.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Dmitry Kozlyuk
+ */
+
+#include <ntddk.h>
+#include <wdf.h>
+#include <wdmsec.h>
+#include <initguid.h>
+
+#include "virt2phys.h"
+
+DRIVER_INITIALIZE DriverEntry;
+EVT_WDF_DRIVER_DEVICE_ADD virt2phys_driver_EvtDeviceAdd;
+EVT_WDF_IO_IN_CALLER_CONTEXT virt2phys_device_EvtIoInCallerContext;
+
+NTSTATUS
+DriverEntry(
+ IN PDRIVER_OBJECT driver_object, IN PUNICODE_STRING registry_path)
+{
+ WDF_DRIVER_CONFIG config;
+ WDF_OBJECT_ATTRIBUTES attributes;
+ NTSTATUS status;
+
+ PAGED_CODE();
+
+ WDF_DRIVER_CONFIG_INIT(&config, virt2phys_driver_EvtDeviceAdd);
+ WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
+ status = WdfDriverCreate(
+ driver_object, registry_path,
+ &attributes, &config, WDF_NO_HANDLE);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDriverCreate() failed, status=%08x\n", status));
+ }
+
+ return status;
+}
+
+_Use_decl_annotations_
+NTSTATUS
+virt2phys_driver_EvtDeviceAdd(
+ WDFDRIVER driver, PWDFDEVICE_INIT init)
+{
+ WDF_OBJECT_ATTRIBUTES attributes;
+ WDFDEVICE device;
+ NTSTATUS status;
+
+ UNREFERENCED_PARAMETER(driver);
+
+ PAGED_CODE();
+
+ WdfDeviceInitSetIoType(
+ init, WdfDeviceIoNeither);
+ WdfDeviceInitSetIoInCallerContextCallback(
+ init, virt2phys_device_EvtIoInCallerContext);
+
+ WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
+
+ status = WdfDeviceCreate(&init, &attributes, &device);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDeviceCreate() failed, status=%08x\n", status));
+ return status;
+ }
+
+ status = WdfDeviceCreateDeviceInterface(
+ device, &GUID_DEVINTERFACE_VIRT2PHYS, NULL);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDeviceCreateDeviceInterface() failed, "
+ "status=%08x\n", status));
+ return status;
+ }
+
+ return STATUS_SUCCESS;
+}
+
+_Use_decl_annotations_
+VOID
+virt2phys_device_EvtIoInCallerContext(
+ IN WDFDEVICE device, IN WDFREQUEST request)
+{
+ WDF_REQUEST_PARAMETERS params;
+ ULONG code;
+ PVOID *virt;
+ PHYSICAL_ADDRESS *phys;
+ size_t size;
+ NTSTATUS status;
+
+ UNREFERENCED_PARAMETER(device);
+
+ PAGED_CODE();
+
+ WDF_REQUEST_PARAMETERS_INIT(¶ms);
+ WdfRequestGetParameters(request, ¶ms);
+
+ if (params.Type != WdfRequestTypeDeviceControl) {
+ KdPrint(("bogus request type=%u\n", params.Type));
+ WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
+ return;
+ }
+
+ code = params.Parameters.DeviceIoControl.IoControlCode;
+ if (code != IOCTL_VIRT2PHYS_TRANSLATE) {
+ KdPrint(("bogus IO control code=%lu\n", code));
+ WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
+ return;
+ }
+
+ status = WdfRequestRetrieveInputBuffer(
+ request, sizeof(*virt), (PVOID *)&virt, &size);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfRequestRetrieveInputBuffer() failed, "
+ "status=%08x\n", status));
+ WdfRequestComplete(request, status);
+ return;
+ }
+
+ status = WdfRequestRetrieveOutputBuffer(
+ request, sizeof(*phys), (PVOID *)&phys, &size);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfRequestRetrieveOutputBuffer() failed, "
+ "status=%08x\n", status));
+ WdfRequestComplete(request, status);
+ return;
+ }
+
+ *phys = MmGetPhysicalAddress(*virt);
+
+ WdfRequestCompleteWithInformation(
+ request, STATUS_SUCCESS, sizeof(*phys));
+}
diff --git a/windows/virt2phys/virt2phys.h b/windows/virt2phys/virt2phys.h
new file mode 100755
index 0000000..4bb2b4a
--- /dev/null
+++ b/windows/virt2phys/virt2phys.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file virt2phys driver interface
+ */
+
+/**
+ * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
+ */
+DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
+ 0x539c2135, 0x793a, 0x4926,
+ 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
+
+/**
+ * Driver device type for IO control codes.
+ */
+#define VIRT2PHYS_DEVTYPE 0x8000
+
+/**
+ * Translate a valid non-paged virtual address to a physical address.
+ *
+ * Note: A physical address zero (0) is reported if input address
+ * is paged out or not mapped. However, if input is a valid mapping
+ * of I/O port 0x0000, output is also zero. There is no way
+ * to distinguish between these cases by return value only.
+ *
+ * Input: a non-paged virtual address (PVOID).
+ *
+ * Output: the corresponding physical address (LARGE_INTEGER).
+ */
+#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
+ VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
diff --git a/windows/virt2phys/virt2phys.inf b/windows/virt2phys/virt2phys.inf
new file mode 100755
index 0000000..e35765e
--- /dev/null
+++ b/windows/virt2phys/virt2phys.inf
@@ -0,0 +1,64 @@
+; SPDX-License-Identifier: BSD-3-Clause
+; Copyright (c) 2020 Dmitry Kozlyuk
+
+[Version]
+Signature = "$WINDOWS NT$"
+Class = %ClassName%
+ClassGuid = {78A1C341-4539-11d3-B88D-00C04FAD5171}
+Provider = %ManufacturerName%
+CatalogFile = virt2phys.cat
+DriverVer =
+
+[DestinationDirs]
+DefaultDestDir = 12
+
+; ================= Class section =====================
+
+[ClassInstall32]
+Addreg = virt2phys_ClassReg
+
+[virt2phys_ClassReg]
+HKR,,,0,%ClassName%
+HKR,,Icon,,-5
+
+[SourceDisksNames]
+1 = %DiskName%,,,""
+
+[SourceDisksFiles]
+virt2phys.sys = 1,,
+
+;*****************************************
+; Install Section
+;*****************************************
+
+[Manufacturer]
+%ManufacturerName%=Standard,NT$ARCH$
+
+[Standard.NT$ARCH$]
+%virt2phys.DeviceDesc%=virt2phys_Device, Root\virt2phys
+
+[virt2phys_Device.NT]
+CopyFiles = Drivers_Dir
+
+[Drivers_Dir]
+virt2phys.sys
+
+;-------------- Service installation
+[virt2phys_Device.NT.Services]
+AddService = virt2phys,%SPSVCINST_ASSOCSERVICE%, virt2phys_Service_Inst
+
+; -------------- virt2phys driver install sections
+[virt2phys_Service_Inst]
+DisplayName = %virt2phys.SVCDESC%
+ServiceType = 1 ; SERVICE_KERNEL_DRIVER
+StartType = 3 ; SERVICE_DEMAND_START
+ErrorControl = 1 ; SERVICE_ERROR_NORMAL
+ServiceBinary = %12%\virt2phys.sys
+
+[Strings]
+SPSVCINST_ASSOCSERVICE = 0x00000002
+ManufacturerName = "Dmitry Kozlyuk"
+ClassName = "Kernel bypass"
+DiskName = "virt2phys Installation Disk"
+virt2phys.DeviceDesc = "Virtual to physical address translator"
+virt2phys.SVCDESC = "virt2phys Service"
diff --git a/windows/virt2phys/virt2phys.sln b/windows/virt2phys/virt2phys.sln
new file mode 100755
index 0000000..0f5ecdc
--- /dev/null
+++ b/windows/virt2phys/virt2phys.sln
@@ -0,0 +1,27 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 16
+VisualStudioVersion = 16.0.29613.14
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "virt2phys", "virt2phys.vcxproj", "{0EEF826B-9391-43A8-A722-BDD6F6115137}"
+EndProject
+Global
+ GlobalSection(SolutionConfigurationPlatforms) = preSolution
+ Debug|x64 = Debug|x64
+ Release|x64 = Release|x64
+ EndGlobalSection
+ GlobalSection(ProjectConfigurationPlatforms) = postSolution
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.ActiveCfg = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.Build.0 = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.Deploy.0 = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.ActiveCfg = Release|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.Build.0 = Release|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.Deploy.0 = Release|x64
+ EndGlobalSection
+ GlobalSection(SolutionProperties) = preSolution
+ HideSolutionNode = FALSE
+ EndGlobalSection
+ GlobalSection(ExtensibilityGlobals) = postSolution
+ SolutionGuid = {845012FB-4471-4A12-A1C4-FF7E05C40E8E}
+ EndGlobalSection
+EndGlobal
diff --git a/windows/virt2phys/virt2phys.vcxproj b/windows/virt2phys/virt2phys.vcxproj
new file mode 100755
index 0000000..fa51916
--- /dev/null
+++ b/windows/virt2phys/virt2phys.vcxproj
@@ -0,0 +1,228 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|x64">
+ <Configuration>Debug</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|x64">
+ <Configuration>Release</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|ARM">
+ <Configuration>Debug</Configuration>
+ <Platform>ARM</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|ARM">
+ <Configuration>Release</Configuration>
+ <Platform>ARM</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|ARM64">
+ <Configuration>Debug</Configuration>
+ <Platform>ARM64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|ARM64">
+ <Configuration>Release</Configuration>
+ <Platform>ARM64</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="virt2phys.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="virt2phys.h" />
+ </ItemGroup>
+ <ItemGroup>
+ <Inf Include="virt2phys.inf" />
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <ProjectGuid>{0EEF826B-9391-43A8-A722-BDD6F6115137}</ProjectGuid>
+ <TemplateGuid>{497e31cb-056b-4f31-abb8-447fd55ee5a5}</TemplateGuid>
+ <TargetFrameworkVersion>v4.5</TargetFrameworkVersion>
+ <MinimumVisualStudioVersion>12.0</MinimumVisualStudioVersion>
+ <Configuration>Debug</Configuration>
+ <Platform Condition="'$(Platform)' == ''">Win32</Platform>
+ <RootNamespace>virt2phys</RootNamespace>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+ <ClCompile>
+ <WppEnabled>false</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ <Link>
+ <AdditionalDependencies>$(DDK_LIB_PATH)wdmsec.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ <Inf>
+ <TimeStamp>0.1</TimeStamp>
+ </Inf>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <FilesToPackage Include="$(TargetPath)" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project>
\ No newline at end of file
diff --git a/windows/virt2phys/virt2phys.vcxproj.filters b/windows/virt2phys/virt2phys.vcxproj.filters
new file mode 100755
index 0000000..0fe65fc
--- /dev/null
+++ b/windows/virt2phys/virt2phys.vcxproj.filters
@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
+ <Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl;inc;xsd</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+ <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
+ </Filter>
+ <Filter Include="Driver Files">
+ <UniqueIdentifier>{8E41214B-6785-4CFE-B992-037D68949A14}</UniqueIdentifier>
+ <Extensions>inf;inv;inx;mof;mc;</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <Inf Include="virt2phys.inf">
+ <Filter>Driver Files</Filter>
+ </Inf>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="virt2phys.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="virt2phys.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+</Project>
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 02/10] eal/windows: do not expose private EAL facilities
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 03/10] eal/windows: improve CPU and NUMA node detection Dmitry Kozlyuk
` (9 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon, Anand Rawat, Thomas Monjalon
The goal of rte_os.h is to mitigate OS differences for EAL users.
In Windows EAL, rte_os.h did excessive things:
1. It included platform SDK headers (windows.h, etc). Those files are
huge, require specific inclusion order, and are generally unused by
the code including rte_os.h. Declarations from platform SDK may
break otherwise platform-independent code, e.g. min, max, ERROR.
2. It included pthread.h, which is clearly not always required.
3. It defined functions private to Windows EAL.
Reorganize Windows EAL includes in the following way:
1. Create rte_windows.h to properly import Windows-specific facilities.
Primary users are bus drivers, tests, and external applications.
2. Remove platform SDK includes from rte_os.h to prevent breaking
otherwise portable code by including rte_os.h on Windows.
Copy necessary definitions to avoid including those headers.
3. Remove pthread.h include from rte_os.h.
4. Move declarations private to Windows EAL into eal_windows.h.
Fixes: 428eb983f5f7 ("eal: add OS specific header file")
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/eal.c | 2 +
lib/librte_eal/windows/eal_lcore.c | 2 +
lib/librte_eal/windows/eal_thread.c | 1 +
lib/librte_eal/windows/eal_windows.h | 29 +++++++++++++
lib/librte_eal/windows/include/meson.build | 1 +
lib/librte_eal/windows/include/pthread.h | 2 +
lib/librte_eal/windows/include/rte_os.h | 44 ++++++--------------
lib/librte_eal/windows/include/rte_windows.h | 41 ++++++++++++++++++
8 files changed, 91 insertions(+), 31 deletions(-)
create mode 100644 lib/librte_eal/windows/eal_windows.h
create mode 100644 lib/librte_eal/windows/include/rte_windows.h
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index e4b50df3b..2cf7a04ef 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -18,6 +18,8 @@
#include <eal_options.h>
#include <eal_private.h>
+#include "eal_windows.h"
+
/* Allow the application to print its usage message too if set */
static rte_usage_hook_t rte_application_usage_hook;
diff --git a/lib/librte_eal/windows/eal_lcore.c b/lib/librte_eal/windows/eal_lcore.c
index b3a6c63af..82ee45413 100644
--- a/lib/librte_eal/windows/eal_lcore.c
+++ b/lib/librte_eal/windows/eal_lcore.c
@@ -2,12 +2,14 @@
* Copyright(c) 2019 Intel Corporation
*/
+#include <pthread.h>
#include <stdint.h>
#include <rte_common.h>
#include "eal_private.h"
#include "eal_thread.h"
+#include "eal_windows.h"
/* global data structure that contains the CPU map */
static struct _wcpu_map {
diff --git a/lib/librte_eal/windows/eal_thread.c b/lib/librte_eal/windows/eal_thread.c
index 9e4bbaa08..e149199a6 100644
--- a/lib/librte_eal/windows/eal_thread.c
+++ b/lib/librte_eal/windows/eal_thread.c
@@ -14,6 +14,7 @@
#include <eal_thread.h>
#include "eal_private.h"
+#include "eal_windows.h"
RTE_DEFINE_PER_LCORE(unsigned int, _lcore_id) = LCORE_ID_ANY;
RTE_DEFINE_PER_LCORE(unsigned int, _socket_id) = (unsigned int)SOCKET_ID_ANY;
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
new file mode 100644
index 000000000..fadd676b2
--- /dev/null
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#ifndef _EAL_WINDOWS_H_
+#define _EAL_WINDOWS_H_
+
+/**
+ * @file Facilities private to Windows EAL
+ */
+
+#include <rte_windows.h>
+
+/**
+ * Create a map of processors and cores on the system.
+ */
+void eal_create_cpu_map(void);
+
+/**
+ * Create a thread.
+ *
+ * @param thread
+ * The location to store the thread id if successful.
+ * @return
+ * 0 for success, -1 if the thread is not created.
+ */
+int eal_thread_create(pthread_t *thread);
+
+#endif /* _EAL_WINDOWS_H_ */
diff --git a/lib/librte_eal/windows/include/meson.build b/lib/librte_eal/windows/include/meson.build
index 7d18dd52f..5fb1962ac 100644
--- a/lib/librte_eal/windows/include/meson.build
+++ b/lib/librte_eal/windows/include/meson.build
@@ -5,4 +5,5 @@ includes += include_directories('.')
headers += files(
'rte_os.h',
+ 'rte_windows.h',
)
diff --git a/lib/librte_eal/windows/include/pthread.h b/lib/librte_eal/windows/include/pthread.h
index b9dd18e56..cfd53f0b8 100644
--- a/lib/librte_eal/windows/include/pthread.h
+++ b/lib/librte_eal/windows/include/pthread.h
@@ -5,6 +5,8 @@
#ifndef _PTHREAD_H_
#define _PTHREAD_H_
+#include <stdint.h>
+
/**
* This file is required to support the common code in eal_common_proc.c,
* eal_common_thread.c and common\include\rte_per_lcore.h as Microsoft libc
diff --git a/lib/librte_eal/windows/include/rte_os.h b/lib/librte_eal/windows/include/rte_os.h
index e1e0378e6..510e39e03 100644
--- a/lib/librte_eal/windows/include/rte_os.h
+++ b/lib/librte_eal/windows/include/rte_os.h
@@ -8,20 +8,18 @@
/**
* This is header should contain any function/macro definition
* which are not supported natively or named differently in the
- * Windows OS. Functions will be added in future releases.
+ * Windows OS. It must not include Windows-specific headers.
*/
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
#ifdef __cplusplus
extern "C" {
#endif
-#include <windows.h>
-#include <basetsd.h>
-#include <pthread.h>
-#include <stdio.h>
-
-/* limits.h replacement */
-#include <stdlib.h>
+/* limits.h replacement, value as in <windows.h> */
#ifndef PATH_MAX
#define PATH_MAX _MAX_PATH
#endif
@@ -31,8 +29,6 @@ extern "C" {
/* strdup is deprecated in Microsoft libc and _strdup is preferred */
#define strdup(str) _strdup(str)
-typedef SSIZE_T ssize_t;
-
#define strtok_r(str, delim, saveptr) strtok_s(str, delim, saveptr)
#define index(a, b) strchr(a, b)
@@ -40,22 +36,14 @@ typedef SSIZE_T ssize_t;
#define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
-/**
- * Create a thread.
- * This function is private to EAL.
- *
- * @param thread
- * The location to store the thread id if successful.
- * @return
- * 0 for success, -1 if the thread is not created.
- */
-int eal_thread_create(pthread_t *thread);
+/* cpu_set macros implementation */
+#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
+#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
+#define RTE_CPU_FILL(set) CPU_FILL(set)
+#define RTE_CPU_NOT(dst, src) CPU_NOT(dst, src)
-/**
- * Create a map of processors and cores on the system.
- * This function is private to EAL.
- */
-void eal_create_cpu_map(void);
+/* as in <windows.h> */
+typedef long long ssize_t;
#ifndef RTE_TOOLCHAIN_GCC
static inline int
@@ -86,12 +74,6 @@ asprintf(char **buffer, const char *format, ...)
}
#endif /* RTE_TOOLCHAIN_GCC */
-/* cpu_set macros implementation */
-#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
-#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
-#define RTE_CPU_FILL(set) CPU_FILL(set)
-#define RTE_CPU_NOT(dst, src) CPU_NOT(dst, src)
-
#ifdef __cplusplus
}
#endif
diff --git a/lib/librte_eal/windows/include/rte_windows.h b/lib/librte_eal/windows/include/rte_windows.h
new file mode 100644
index 000000000..ed6e4c148
--- /dev/null
+++ b/lib/librte_eal/windows/include/rte_windows.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#ifndef _RTE_WINDOWS_H_
+#define _RTE_WINDOWS_H_
+
+/**
+ * @file Windows-specific facilities
+ *
+ * This file should be included by DPDK libraries and applications
+ * that need access to Windows API. It includes platform SDK headers
+ * in compatible order with proper options and defines error-handling macros.
+ */
+
+/* Disable excessive libraries. */
+#ifndef WIN32_LEAN_AND_MEAN
+#define WIN32_LEAN_AND_MEAN
+#endif
+
+/* Must come first. */
+#include <windows.h>
+
+#include <basetsd.h>
+#include <psapi.h>
+
+/* Have GUIDs defined. */
+#ifndef INITGUID
+#define INITGUID
+#endif
+#include <initguid.h>
+
+/**
+ * Log GetLastError() with context, usually a Win32 API function and arguments.
+ */
+#define RTE_LOG_WIN32_ERR(...) \
+ RTE_LOG(DEBUG, EAL, RTE_FMT("GetLastError()=%lu: " \
+ RTE_FMT_HEAD(__VA_ARGS__,) "\n", GetLastError(), \
+ RTE_FMT_TAIL(__VA_ARGS__,)))
+
+#endif /* _RTE_WINDOWS_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 03/10] eal/windows: improve CPU and NUMA node detection
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 02/10] eal/windows: do not expose private EAL facilities Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 04/10] eal/windows: initialize hugepage info Dmitry Kozlyuk
` (8 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon, Jeff Shaw, Anand Rawat
1. Map CPU cores to their respective NUMA nodes as reported by system.
2. Support systems with more than 64 cores (multiple processor groups).
3. Fix magic constants, styling issues, and compiler warnings.
4. Add EAL private function to map DPDK socket ID to NUMA node number.
Fixes: 53ffd9f080fc ("eal/windows: add minimum viable code")
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/eal_lcore.c | 185 +++++++++++++++++----------
lib/librte_eal/windows/eal_windows.h | 10 ++
2 files changed, 124 insertions(+), 71 deletions(-)
diff --git a/lib/librte_eal/windows/eal_lcore.c b/lib/librte_eal/windows/eal_lcore.c
index 82ee45413..9d931d50a 100644
--- a/lib/librte_eal/windows/eal_lcore.c
+++ b/lib/librte_eal/windows/eal_lcore.c
@@ -3,103 +3,146 @@
*/
#include <pthread.h>
+#include <stdbool.h>
#include <stdint.h>
#include <rte_common.h>
+#include <rte_debug.h>
+#include <rte_lcore.h>
+#include <rte_os.h>
#include "eal_private.h"
#include "eal_thread.h"
#include "eal_windows.h"
-/* global data structure that contains the CPU map */
-static struct _wcpu_map {
- unsigned int total_procs;
- unsigned int proc_sockets;
- unsigned int proc_cores;
- unsigned int reserved;
- struct _win_lcore_map {
- uint8_t socket_id;
- uint8_t core_id;
- } wlcore_map[RTE_MAX_LCORE];
-} wcpu_map = { 0 };
-
-/*
- * Create a map of all processors and associated cores on the system
- */
+/** Number of logical processors (cores) in a processor group (32 or 64). */
+#define EAL_PROCESSOR_GROUP_SIZE (sizeof(KAFFINITY) * CHAR_BIT)
+
+struct lcore_map {
+ uint8_t socket_id;
+ uint8_t core_id;
+};
+
+struct socket_map {
+ uint16_t node_id;
+};
+
+struct cpu_map {
+ unsigned int socket_count;
+ unsigned int lcore_count;
+ struct lcore_map lcores[RTE_MAX_LCORE];
+ struct socket_map sockets[RTE_MAX_NUMA_NODES];
+};
+
+static struct cpu_map cpu_map = { 0 };
+
void
-eal_create_cpu_map()
+eal_create_cpu_map(void)
{
- wcpu_map.total_procs =
- GetActiveProcessorCount(ALL_PROCESSOR_GROUPS);
-
- LOGICAL_PROCESSOR_RELATIONSHIP lprocRel;
- DWORD lprocInfoSize = 0;
- BOOL ht_enabled = FALSE;
-
- /* First get the processor package information */
- lprocRel = RelationProcessorPackage;
- /* Determine the size of buffer we need (pass NULL) */
- GetLogicalProcessorInformationEx(lprocRel, NULL, &lprocInfoSize);
- wcpu_map.proc_sockets = lprocInfoSize / 48;
-
- lprocInfoSize = 0;
- /* Next get the processor core information */
- lprocRel = RelationProcessorCore;
- GetLogicalProcessorInformationEx(lprocRel, NULL, &lprocInfoSize);
- wcpu_map.proc_cores = lprocInfoSize / 48;
-
- if (wcpu_map.total_procs > wcpu_map.proc_cores)
- ht_enabled = TRUE;
-
- /* Distribute the socket and core ids appropriately
- * across the logical cores. For now, split the cores
- * equally across the sockets.
- */
- unsigned int lcore = 0;
- for (unsigned int socket = 0; socket <
- wcpu_map.proc_sockets; ++socket) {
- for (unsigned int core = 0;
- core < (wcpu_map.proc_cores / wcpu_map.proc_sockets);
- ++core) {
- wcpu_map.wlcore_map[lcore]
- .socket_id = socket;
- wcpu_map.wlcore_map[lcore]
- .core_id = core;
- lcore++;
- if (ht_enabled) {
- wcpu_map.wlcore_map[lcore]
- .socket_id = socket;
- wcpu_map.wlcore_map[lcore]
- .core_id = core;
- lcore++;
+ SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *infos, *info;
+ DWORD infos_size;
+ bool full = false;
+
+ infos_size = 0;
+ if (!GetLogicalProcessorInformationEx(
+ RelationNumaNode, NULL, &infos_size)) {
+ DWORD error = GetLastError();
+ if (error != ERROR_INSUFFICIENT_BUFFER) {
+ rte_panic("cannot get NUMA node info size, error %lu",
+ GetLastError());
+ }
+ }
+
+ infos = malloc(infos_size);
+ if (infos == NULL) {
+ rte_panic("cannot allocate memory for NUMA node information");
+ return;
+ }
+
+ if (!GetLogicalProcessorInformationEx(
+ RelationNumaNode, infos, &infos_size)) {
+ rte_panic("cannot get NUMA node information, error %lu",
+ GetLastError());
+ }
+
+ info = infos;
+ while ((uint8_t *)info - (uint8_t *)infos < infos_size) {
+ unsigned int node_id = info->NumaNode.NodeNumber;
+ GROUP_AFFINITY *cores = &info->NumaNode.GroupMask;
+ struct lcore_map *lcore;
+ unsigned int i, socket_id;
+
+ /* NUMA node may be reported multiple times if it includes
+ * cores from different processor groups, e. g. 80 cores
+ * of a physical processor comprise one NUMA node, but two
+ * processor groups, because group size is limited by 32/64.
+ */
+ for (socket_id = 0; socket_id < cpu_map.socket_count;
+ socket_id++) {
+ if (cpu_map.sockets[socket_id].node_id == node_id)
+ break;
+ }
+
+ if (socket_id == cpu_map.socket_count) {
+ if (socket_id == RTE_DIM(cpu_map.sockets)) {
+ full = true;
+ goto exit;
}
+
+ cpu_map.sockets[socket_id].node_id = node_id;
+ cpu_map.socket_count++;
+ }
+
+ for (i = 0; i < EAL_PROCESSOR_GROUP_SIZE; i++) {
+ if ((cores->Mask & ((KAFFINITY)1 << i)) == 0)
+ continue;
+
+ if (cpu_map.lcore_count == RTE_DIM(cpu_map.lcores)) {
+ full = true;
+ goto exit;
+ }
+
+ lcore = &cpu_map.lcores[cpu_map.lcore_count];
+ lcore->socket_id = socket_id;
+ lcore->core_id =
+ cores->Group * EAL_PROCESSOR_GROUP_SIZE + i;
+ cpu_map.lcore_count++;
}
+
+ info = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)(
+ (uint8_t *)info + info->Size);
+ }
+
+exit:
+ if (full) {
+ /* RTE_LOG() may not be available, but this is important. */
+ fprintf(stderr, "Enumerated maximum of %u NUMA nodes and %u cores\n",
+ cpu_map.socket_count, cpu_map.lcore_count);
}
+
+ free(infos);
}
-/*
- * Check if a cpu is present by the presence of the cpu information for it
- */
int
eal_cpu_detected(unsigned int lcore_id)
{
- return (lcore_id < wcpu_map.total_procs);
+ return lcore_id < cpu_map.lcore_count;
}
-/*
- * Get CPU socket id for a logical core
- */
unsigned
eal_cpu_socket_id(unsigned int lcore_id)
{
- return wcpu_map.wlcore_map[lcore_id].socket_id;
+ return cpu_map.lcores[lcore_id].socket_id;
}
-/*
- * Get CPU socket id (NUMA node) for a logical core
- */
unsigned
eal_cpu_core_id(unsigned int lcore_id)
{
- return wcpu_map.wlcore_map[lcore_id].core_id;
+ return cpu_map.lcores[lcore_id].core_id;
+}
+
+unsigned int
+eal_socket_numa_node(unsigned int socket_id)
+{
+ return cpu_map.sockets[socket_id].node_id;
}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index fadd676b2..390d2fd66 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -26,4 +26,14 @@ void eal_create_cpu_map(void);
*/
int eal_thread_create(pthread_t *thread);
+/**
+ * Get system NUMA node number for a socket ID.
+ *
+ * @param socket_id
+ * Valid EAL socket ID.
+ * @return
+ * NUMA node number to use with Win32 API.
+ */
+unsigned int eal_socket_numa_node(unsigned int socket_id);
+
#endif /* _EAL_WINDOWS_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 04/10] eal/windows: initialize hugepage info
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (2 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 03/10] eal/windows: improve CPU and NUMA node detection Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
` (7 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Harini Ramakrishnan,
Omar Cardona, Pallavi Kadam, Ranjit Menon, John McNamara,
Marko Kovacevic
Add hugepages discovery ("large pages" in Windows terminology)
and update documentation for required privilege setup.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 2 +
doc/guides/windows_gsg/build_dpdk.rst | 20 -----
doc/guides/windows_gsg/index.rst | 1 +
doc/guides/windows_gsg/run_apps.rst | 47 +++++++++++
lib/librte_eal/windows/eal.c | 14 ++++
lib/librte_eal/windows/eal_hugepages.c | 108 +++++++++++++++++++++++++
lib/librte_eal/windows/meson.build | 1 +
7 files changed, 173 insertions(+), 20 deletions(-)
create mode 100644 doc/guides/windows_gsg/run_apps.rst
create mode 100644 lib/librte_eal/windows/eal_hugepages.c
diff --git a/config/meson.build b/config/meson.build
index 58421342b..4607655d9 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -263,6 +263,8 @@ if is_windows
if cc.get_id() == 'gcc'
add_project_arguments('-D__USE_MINGW_ANSI_STDIO', language: 'c')
endif
+
+ add_project_link_arguments('-ladvapi32', language: 'c')
endif
if get_option('b_lto')
diff --git a/doc/guides/windows_gsg/build_dpdk.rst b/doc/guides/windows_gsg/build_dpdk.rst
index d46e84e3f..650483e3b 100644
--- a/doc/guides/windows_gsg/build_dpdk.rst
+++ b/doc/guides/windows_gsg/build_dpdk.rst
@@ -111,23 +111,3 @@ Depending on the distribution, paths in this file may need adjustments.
meson --cross-file config/x86/meson_mingw.txt -Dexamples=helloworld build
ninja -C build
-
-
-Run the helloworld example
-==========================
-
-Navigate to the examples in the build directory and run `dpdk-helloworld.exe`.
-
-.. code-block:: console
-
- cd C:\Users\me\dpdk\build\examples
- dpdk-helloworld.exe
- hello from core 1
- hello from core 3
- hello from core 0
- hello from core 2
-
-Note for MinGW-w64: applications are linked to ``libwinpthread-1.dll``
-by default. To run the example, either add toolchain executables directory
-to the PATH or copy the library to the working directory.
-Alternatively, static linking may be used (mind the LGPLv2.1 license).
diff --git a/doc/guides/windows_gsg/index.rst b/doc/guides/windows_gsg/index.rst
index d9b7990a8..e94593572 100644
--- a/doc/guides/windows_gsg/index.rst
+++ b/doc/guides/windows_gsg/index.rst
@@ -12,3 +12,4 @@ Getting Started Guide for Windows
intro
build_dpdk
+ run_apps
diff --git a/doc/guides/windows_gsg/run_apps.rst b/doc/guides/windows_gsg/run_apps.rst
new file mode 100644
index 000000000..21ac7f6c1
--- /dev/null
+++ b/doc/guides/windows_gsg/run_apps.rst
@@ -0,0 +1,47 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2020 Dmitry Kozlyuk
+
+Running DPDK Applications
+=========================
+
+Grant *Lock pages in memory* Privilege
+--------------------------------------
+
+Use of hugepages ("large pages" in Windows terminolocy) requires
+``SeLockMemoryPrivilege`` for the user running an application.
+
+1. Open *Local Security Policy* snap in, either:
+
+ * Control Panel / Computer Management / Local Security Policy;
+ * or Win+R, type ``secpol``, press Enter.
+
+2. Open *Local Policies / User Rights Assignment / Lock pages in memory.*
+
+3. Add desired users or groups to the list of grantees.
+
+4. Privilege is applied upon next logon. In particular, if privilege has been
+ granted to current user, a logoff is required before it is available.
+
+See `Large-Page Support`_ in MSDN for details.
+
+.. _Large-page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
+
+
+Run the ``helloworld`` Example
+------------------------------
+
+Navigate to the examples in the build directory and run `dpdk-helloworld.exe`.
+
+.. code-block:: console
+
+ cd C:\Users\me\dpdk\build\examples
+ dpdk-helloworld.exe
+ hello from core 1
+ hello from core 3
+ hello from core 0
+ hello from core 2
+
+Note for MinGW-w64: applications are linked to ``libwinpthread-1.dll``
+by default. To run the example, either add toolchain executables directory
+to the PATH or copy the library to the working directory.
+Alternatively, static linking may be used (mind the LGPLv2.1 license).
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 2cf7a04ef..63461f51a 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -18,8 +18,11 @@
#include <eal_options.h>
#include <eal_private.h>
+#include "eal_hugepages.h"
#include "eal_windows.h"
+#define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)
+
/* Allow the application to print its usage message too if set */
static rte_usage_hook_t rte_application_usage_hook;
@@ -242,6 +245,17 @@ rte_eal_init(int argc, char **argv)
if (fctret < 0)
exit(1);
+ if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
+ rte_eal_init_alert("Cannot get hugepage information");
+ rte_errno = EACCES;
+ return -1;
+ }
+
+ if (internal_config.memory == 0 && !internal_config.force_sockets) {
+ if (internal_config.no_hugetlbfs)
+ internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_hugepages.c b/lib/librte_eal/windows/eal_hugepages.c
new file mode 100644
index 000000000..b099d13f9
--- /dev/null
+++ b/lib/librte_eal/windows/eal_hugepages.c
@@ -0,0 +1,108 @@
+#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+#include <rte_memzone.h>
+#include <rte_os.h>
+
+#include "eal_filesystem.h"
+#include "eal_hugepages.h"
+#include "eal_internal_cfg.h"
+#include "eal_windows.h"
+
+static int
+hugepage_claim_privilege(void)
+{
+ static const wchar_t privilege[] = L"SeLockMemoryPrivilege";
+
+ HANDLE token;
+ LUID luid;
+ TOKEN_PRIVILEGES tp;
+ int ret = -1;
+
+ if (!OpenProcessToken(GetCurrentProcess(),
+ TOKEN_ADJUST_PRIVILEGES, &token)) {
+ RTE_LOG_WIN32_ERR("OpenProcessToken()");
+ return -1;
+ }
+
+ if (!LookupPrivilegeValueW(NULL, privilege, &luid)) {
+ RTE_LOG_WIN32_ERR("LookupPrivilegeValue(\"%S\")", privilege);
+ goto exit;
+ }
+
+ tp.PrivilegeCount = 1;
+ tp.Privileges[0].Luid = luid;
+ tp.Privileges[0].Attributes = SE_PRIVILEGE_ENABLED;
+
+ if (!AdjustTokenPrivileges(
+ token, FALSE, &tp, sizeof(tp), NULL, NULL)) {
+ RTE_LOG_WIN32_ERR("AdjustTokenPrivileges()");
+ goto exit;
+ }
+
+ ret = 0;
+
+exit:
+ CloseHandle(token);
+
+ return ret;
+}
+
+static int
+hugepage_info_init(void)
+{
+ struct hugepage_info *hpi;
+ unsigned int socket_id;
+ int ret = 0;
+
+ /* Only one hugepage size available in Windows. */
+ internal_config.num_hugepage_sizes = 1;
+ hpi = &internal_config.hugepage_info[0];
+
+ hpi->hugepage_sz = GetLargePageMinimum();
+ if (hpi->hugepage_sz == 0)
+ return -ENOTSUP;
+
+ /* Assume all memory on each NUMA node available for hugepages,
+ * because Windows neither advertises additional limits,
+ * nor provides an API to query them.
+ */
+ for (socket_id = 0; socket_id < rte_socket_count(); socket_id++) {
+ ULONGLONG bytes;
+ unsigned int numa_node;
+
+ numa_node = eal_socket_numa_node(socket_id);
+ if (!GetNumaAvailableMemoryNodeEx(numa_node, &bytes)) {
+ RTE_LOG_WIN32_ERR("GetNumaAvailableMemoryNodeEx(%u)",
+ numa_node);
+ continue;
+ }
+
+ hpi->num_pages[socket_id] = bytes / hpi->hugepage_sz;
+ RTE_LOG(DEBUG, EAL,
+ "Found %u hugepages of %zu bytes on socket %u\n",
+ hpi->num_pages[socket_id], hpi->hugepage_sz, socket_id);
+ }
+
+ /* No hugepage filesystem in Windows. */
+ hpi->lock_descriptor = -1;
+ memset(hpi->hugedir, 0, sizeof(hpi->hugedir));
+
+ return ret;
+}
+
+int
+eal_hugepage_info_init(void)
+{
+ if (hugepage_claim_privilege() < 0) {
+ RTE_LOG(ERR, EAL, "Cannot claim hugepage privilege\n");
+ return -1;
+ }
+
+ if (hugepage_info_init() < 0) {
+ RTE_LOG(ERR, EAL, "Cannot get hugepage information\n");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 09dd4ab2f..5f118bfe2 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -6,6 +6,7 @@ subdir('include')
sources += files(
'eal.c',
'eal_debug.c',
+ 'eal_hugepages.c',
'eal_lcore.c',
'eal_thread.c',
'getopt.c',
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 05/10] eal: introduce internal wrappers for file operations
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (3 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 04/10] eal/windows: initialize hugepage info Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
` (6 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon
EAL common code uses file locking and truncation. Introduce
OS-independent wrappers in order to support both Linux/FreeBSD
and Windows:
* eal_file_lock: lock or unlock an open file.
* eal_file_truncate: enforce a given size for an open file.
Wrappers follow POSIX semantics, but interface is not POSIX,
so that it can be made more clean, e.g. by not mixing locking
operation and behaviour on conflict.
Implementation for Linux and FreeBSD is placed in "unix" subdirectory,
which is intended for common code between the two. Files should be named
after the ones from which the code is factored in OS subdirectory.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/common/eal_private.h | 45 ++++++++++++++++
lib/librte_eal/meson.build | 4 ++
lib/librte_eal/unix/eal.c | 47 ++++++++++++++++
lib/librte_eal/unix/meson.build | 6 +++
lib/librte_eal/windows/eal.c | 83 +++++++++++++++++++++++++++++
5 files changed, 185 insertions(+)
create mode 100644 lib/librte_eal/unix/eal.c
create mode 100644 lib/librte_eal/unix/meson.build
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index ddcfbe2e4..65d61ff13 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -443,4 +443,49 @@ rte_option_usage(void);
uint64_t
eal_get_baseaddr(void);
+/** File locking operation. */
+enum eal_flock_op {
+ EAL_FLOCK_SHARED, /**< Acquire a shared lock. */
+ EAL_FLOCK_EXCLUSIVE, /**< Acquire an exclusive lock. */
+ EAL_FLOCK_UNLOCK /**< Release a previously taken lock. */
+};
+
+/** Behavior on file locking conflict. */
+enum eal_flock_mode {
+ EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
+ EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
+};
+
+/**
+ * Lock or unlock the file.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX flock(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param op
+ * Operation to perform.
+ * @param mode
+ * Behavior on conflict.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode);
+
+/**
+ * Truncate or extend the file to the specified size.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX ftruncate(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param size
+ * Desired file size.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_truncate(int fd, ssize_t size);
+
#endif /* _EAL_PRIVATE_H_ */
diff --git a/lib/librte_eal/meson.build b/lib/librte_eal/meson.build
index 9d219a0e6..1f89efb88 100644
--- a/lib/librte_eal/meson.build
+++ b/lib/librte_eal/meson.build
@@ -6,6 +6,10 @@ subdir('include')
subdir('common')
+if not is_windows
+ subdir('unix')
+endif
+
dpdk_conf.set('RTE_EXEC_ENV_' + exec_env.to_upper(), 1)
subdir(exec_env)
diff --git a/lib/librte_eal/unix/eal.c b/lib/librte_eal/unix/eal.c
new file mode 100644
index 000000000..a337b59b1
--- /dev/null
+++ b/lib/librte_eal/unix/eal.c
@@ -0,0 +1,47 @@
+#include <sys/file.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <rte_errno.h>
+
+#include "eal_private.h"
+
+int
+eal_file_truncate(int fd, ssize_t size)
+{
+ int ret;
+
+ ret = ftruncate(fd, size);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
+
+int
+eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ int sys_flags = 0;
+ int ret;
+
+ if (mode == EAL_FLOCK_RETURN)
+ sys_flags |= LOCK_NB;
+
+ switch (op) {
+ case EAL_FLOCK_EXCLUSIVE:
+ sys_flags |= LOCK_EX;
+ break;
+ case EAL_FLOCK_SHARED:
+ sys_flags |= LOCK_SH;
+ break;
+ case EAL_FLOCK_UNLOCK:
+ sys_flags |= LOCK_UN;
+ break;
+ }
+
+ ret = flock(fd, sys_flags);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
diff --git a/lib/librte_eal/unix/meson.build b/lib/librte_eal/unix/meson.build
new file mode 100644
index 000000000..13564838e
--- /dev/null
+++ b/lib/librte_eal/unix/meson.build
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2020 Dmitry Kozlyuk
+
+sources += files(
+ 'eal.c',
+)
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 63461f51a..9dba895e7 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -224,6 +224,89 @@ rte_eal_init_alert(const char *msg)
RTE_LOG(ERR, EAL, "%s\n", msg);
}
+int
+eal_file_truncate(int fd, ssize_t size)
+{
+ HANDLE handle;
+ DWORD ret;
+ LONG low = (LONG)((size_t)size);
+ LONG high = (LONG)((size_t)size >> 32);
+
+ handle = (HANDLE)_get_osfhandle(fd);
+ if (handle == INVALID_HANDLE_VALUE) {
+ rte_errno = EBADF;
+ return -1;
+ }
+
+ ret = SetFilePointer(handle, low, &high, FILE_BEGIN);
+ if (ret == INVALID_SET_FILE_POINTER) {
+ RTE_LOG_WIN32_ERR("SetFilePointer()");
+ rte_errno = EINVAL;
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+lock_file(HANDLE handle, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ DWORD sys_flags = 0;
+ OVERLAPPED overlapped;
+
+ if (op == EAL_FLOCK_EXCLUSIVE)
+ sys_flags |= LOCKFILE_EXCLUSIVE_LOCK;
+ if (mode == EAL_FLOCK_RETURN)
+ sys_flags |= LOCKFILE_FAIL_IMMEDIATELY;
+
+ memset(&overlapped, 0, sizeof(overlapped));
+ if (!LockFileEx(handle, sys_flags, 0, 0, 0, &overlapped)) {
+ if ((sys_flags & LOCKFILE_FAIL_IMMEDIATELY) &&
+ (GetLastError() == ERROR_IO_PENDING)) {
+ rte_errno = EWOULDBLOCK;
+ } else {
+ RTE_LOG_WIN32_ERR("LockFileEx()");
+ rte_errno = EINVAL;
+ }
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+unlock_file(HANDLE handle)
+{
+ if (!UnlockFileEx(handle, 0, 0, 0, NULL)) {
+ RTE_LOG_WIN32_ERR("UnlockFileEx()");
+ rte_errno = EINVAL;
+ return -1;
+ }
+ return 0;
+}
+
+int
+eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ HANDLE handle = (HANDLE)_get_osfhandle(fd);
+
+ if (handle == INVALID_HANDLE_VALUE) {
+ rte_errno = EBADF;
+ return -1;
+ }
+
+ switch (op) {
+ case EAL_FLOCK_EXCLUSIVE:
+ case EAL_FLOCK_SHARED:
+ return lock_file(handle, op, mode);
+ case EAL_FLOCK_UNLOCK:
+ return unlock_file(handle);
+ default:
+ rte_errno = EINVAL;
+ return -1;
+ }
+}
+
/* Launch threads, called at application init(). */
int
rte_eal_init(int argc, char **argv)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 06/10] eal: introduce memory management wrappers
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (4 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-13 7:50 ` Tal Shnaiderman
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
` (5 subsequent siblings)
11 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Anatoly Burakov,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
System meory management is implemented differently for POSIX and
Windows. Introduce wrapper functions for operations used across DPDK:
* rte_mem_map()
Create memory mapping for a regular file or a page file (swap).
This supports mapping to a reserved memory region even on Windows.
* rte_mem_unmap()
Remove mapping created with rte_mem_map().
* rte_get_page_size()
Obtain default system page size.
* rte_mem_lock()
Make arbitrary-sized memory region non-swappable.
Wrappers follow POSIX semantics limited to DPDK tasks, but their
signatures deliberately differ from POSIX ones to be more safe and
expressive.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 10 +-
lib/librte_eal/common/eal_private.h | 51 +++-
lib/librte_eal/include/rte_memory.h | 68 +++++
lib/librte_eal/rte_eal_exports.def | 4 +
lib/librte_eal/rte_eal_version.map | 4 +
lib/librte_eal/unix/eal_memory.c | 112 +++++++
lib/librte_eal/unix/meson.build | 1 +
lib/librte_eal/windows/eal.c | 6 +
lib/librte_eal/windows/eal_memory.c | 433 +++++++++++++++++++++++++++
lib/librte_eal/windows/eal_windows.h | 67 +++++
lib/librte_eal/windows/meson.build | 1 +
11 files changed, 753 insertions(+), 4 deletions(-)
create mode 100644 lib/librte_eal/unix/eal_memory.c
create mode 100644 lib/librte_eal/windows/eal_memory.c
diff --git a/config/meson.build b/config/meson.build
index 4607655d9..bceb5ef7b 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -256,14 +256,20 @@ if is_freebsd
endif
if is_windows
- # Minimum supported API is Windows 7.
- add_project_arguments('-D_WIN32_WINNT=0x0601', language: 'c')
+ # VirtualAlloc2() is available since Windows 10 / Server 2016.
+ add_project_arguments('-D_WIN32_WINNT=0x0A00', language: 'c')
# Use MinGW-w64 stdio, because DPDK assumes ANSI-compliant formatting.
if cc.get_id() == 'gcc'
add_project_arguments('-D__USE_MINGW_ANSI_STDIO', language: 'c')
endif
+ # Contrary to docs, VirtualAlloc2() is exported by mincore.lib
+ # in Windows SDK, while MinGW exports it by advapi32.a.
+ if is_ms_linker
+ add_project_link_arguments('-lmincore', language: 'c')
+ endif
+
add_project_link_arguments('-ladvapi32', language: 'c')
endif
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 65d61ff13..1e89338f2 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -11,6 +11,7 @@
#include <rte_dev.h>
#include <rte_lcore.h>
+#include <rte_memory.h>
/**
* Structure storing internal configuration (per-lcore)
@@ -202,6 +203,16 @@ int rte_eal_alarm_init(void);
*/
int rte_eal_check_module(const char *module_name);
+/**
+ * Memory reservation flags.
+ */
+enum eal_mem_reserve_flags {
+ /**< Reserve hugepages (support may be limited or missing). */
+ EAL_RESERVE_HUGEPAGES = 1 << 0,
+ /**< Fail if requested address is not available. */
+ EAL_RESERVE_EXACT_ADDRESS = 1 << 1
+};
+
/**
* Get virtual area of specified size from the OS.
*
@@ -232,8 +243,8 @@ int rte_eal_check_module(const char *module_name);
#define EAL_VIRTUAL_AREA_UNMAP (1 << 2)
/**< immediately unmap reserved virtual area. */
void *
-eal_get_virtual_area(void *requested_addr, size_t *size,
- size_t page_sz, int flags, int mmap_flags);
+eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
+ int flags, int mmap_flags);
/**
* Get cpu core_id.
@@ -488,4 +499,40 @@ int eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode);
*/
int eal_file_truncate(int fd, ssize_t size);
+/**
+ * Reserve a region of virtual memory.
+ *
+ * Use eal_mem_free() to free reserved memory.
+ *
+ * @param requested_addr
+ * A desired reservation address. The system may not respect it.
+ * NULL means the address will be chosen by the system.
+ * @param size
+ * Reservation size. Must be a multiple of system page size.
+ * @param flags
+ * Reservation options.
+ * @returns
+ * Starting address of the reserved area on success, NULL on failure.
+ * Callers must not access this memory until remapping it.
+ */
+void *eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags);
+
+/**
+ * Free memory obtained by eal_mem_reserve() or eal_mem_alloc().
+ *
+ * If @code virt @endcode and @code size @endcode describe a part of the
+ * reserved region, only this part of the region is freed (accurately
+ * up to the system page size). If @code virt @endcode points to allocated
+ * memory, @code size @endcode must match the one specified on allocation.
+ * The behavior is undefined if the memory pointed by @code virt @endcode
+ * is obtained from another source than listed above.
+ *
+ * @param virt
+ * A virtual address in a region previously reserved.
+ * @param size
+ * Number of bytes to unreserve.
+ */
+void eal_mem_free(void *virt, size_t size);
+
#endif /* _EAL_PRIVATE_H_ */
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 3d8d0bd69..1b7c3e5df 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -85,6 +85,74 @@ struct rte_memseg_list {
struct rte_fbarray memseg_arr;
};
+/**
+ * Memory protection flags.
+ */
+enum rte_mem_prot {
+ RTE_PROT_READ = 1 << 0, /**< Read access. */
+ RTE_PROT_WRITE = 1 << 1, /**< Write access. */
+ RTE_PROT_EXECUTE = 1 << 2 /**< Code execution. */
+};
+
+/**
+ * Memory mapping additional flags.
+ *
+ * In Linux and FreeBSD, each flag is semantically equivalent
+ * to OS-specific mmap(3) flag with the same or similar name.
+ * In Windows, POSIX and MAP_ANONYMOUS semantics are followed.
+ */
+enum rte_map_flags {
+ /** Changes of mapped memory are visible to other processes. */
+ RTE_MAP_SHARED = 1 << 0,
+ /** Mapping is not backed by a regular file. */
+ RTE_MAP_ANONYMOUS = 1 << 1,
+ /** Copy-on-write mapping, changes are invisible to other processes. */
+ RTE_MAP_PRIVATE = 1 << 2,
+ /** Fail if requested address cannot be taken. */
+ RTE_MAP_FIXED = 1 << 3
+};
+
+/**
+ * OS-independent implementation of POSIX mmap(3)
+ * with MAP_ANONYMOUS Linux/FreeBSD extension.
+ */
+__rte_experimental
+void *rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset);
+
+/**
+ * OS-independent implementation of POSIX munmap(3).
+ */
+__rte_experimental
+int rte_mem_unmap(void *virt, size_t size);
+
+/**
+ * Get system page size. This function never failes.
+ *
+ * @return
+ * Positive page size in bytes.
+ */
+__rte_experimental
+int rte_get_page_size(void);
+
+/**
+ * Lock region in physical memory and prevent it from swapping.
+ *
+ * @param virt
+ * The virtual address.
+ * @param size
+ * Size of the region.
+ * @return
+ * 0 on success, negative on error.
+ *
+ * @note Implementations may require @p virt and @p size to be multiples
+ * of system page size.
+ * @see rte_get_page_size()
+ * @see rte_mem_lock_page()
+ */
+__rte_experimental
+int rte_mem_lock(const void *virt, size_t size);
+
/**
* Lock page in physical memory and prevent from swapping.
*
diff --git a/lib/librte_eal/rte_eal_exports.def b/lib/librte_eal/rte_eal_exports.def
index 12a6c79d6..bacf9a107 100644
--- a/lib/librte_eal/rte_eal_exports.def
+++ b/lib/librte_eal/rte_eal_exports.def
@@ -5,5 +5,9 @@ EXPORTS
rte_eal_mp_remote_launch
rte_eal_mp_wait_lcore
rte_eal_remote_launch
+ rte_get_page_size
rte_log
+ rte_mem_lock
+ rte_mem_map
+ rte_mem_unmap
rte_vlog
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index f9ede5b41..07128898f 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -337,5 +337,9 @@ EXPERIMENTAL {
rte_thread_is_intr;
# added in 20.05
+ rte_get_page_size;
rte_log_can_log;
+ rte_mem_lock;
+ rte_mem_map;
+ rte_mem_unmap;
};
diff --git a/lib/librte_eal/unix/eal_memory.c b/lib/librte_eal/unix/eal_memory.c
new file mode 100644
index 000000000..312560b49
--- /dev/null
+++ b/lib/librte_eal/unix/eal_memory.c
@@ -0,0 +1,112 @@
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+
+#include "eal_private.h"
+
+static void *
+mem_map(void *requested_addr, size_t size, int prot, int flags,
+ int fd, size_t offset)
+{
+ void *virt = mmap(requested_addr, size, prot, flags, fd, offset);
+ if (virt == MAP_FAILED) {
+ RTE_LOG(ERR, EAL,
+ "Cannot mmap(%p, 0x%zx, 0x%x, 0x%x, %d, 0x%zx): %s\n",
+ requested_addr, size, prot, flags, fd, offset,
+ strerror(errno));
+ rte_errno = errno;
+ }
+ return virt;
+}
+
+static int
+mem_unmap(void *virt, size_t size)
+{
+ int ret = munmap(virt, size);
+ if (ret < 0) {
+ RTE_LOG(ERR, EAL, "Cannot munmap(%p, 0x%zx): %s\n",
+ virt, size, strerror(errno));
+ rte_errno = errno;
+ }
+ return ret;
+}
+
+void *
+eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags)
+{
+ int sys_flags = MAP_PRIVATE | MAP_ANONYMOUS;
+
+#ifdef MAP_HUGETLB
+ if (flags & EAL_RESERVE_HUGEPAGES)
+ sys_flags |= MAP_HUGETLB;
+#endif
+ if (flags & EAL_RESERVE_EXACT_ADDRESS)
+ sys_flags |= MAP_FIXED;
+
+ return mem_map(requested_addr, size, PROT_NONE, sys_flags, -1, 0);
+}
+
+void
+eal_mem_free(void *virt, size_t size)
+{
+ mem_unmap(virt, size);
+}
+
+static int
+mem_rte_to_sys_prot(enum rte_mem_prot prot)
+{
+ int sys_prot = 0;
+
+ if (prot & RTE_PROT_READ)
+ sys_prot |= PROT_READ;
+ if (prot & RTE_PROT_WRITE)
+ sys_prot |= PROT_WRITE;
+ if (prot & RTE_PROT_EXECUTE)
+ sys_prot |= PROT_EXEC;
+
+ return sys_prot;
+}
+
+void *
+rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset)
+{
+ int sys_prot = 0;
+ int sys_flags = 0;
+
+ sys_prot = mem_rte_to_sys_prot(prot);
+
+ if (flags & RTE_MAP_SHARED)
+ sys_flags |= MAP_SHARED;
+ if (flags & RTE_MAP_ANONYMOUS)
+ sys_flags |= MAP_ANONYMOUS;
+ if (flags & RTE_MAP_PRIVATE)
+ sys_flags |= MAP_PRIVATE;
+ if (flags & RTE_MAP_FIXED)
+ sys_flags |= MAP_FIXED;
+
+ return mem_map(requested_addr, size, sys_prot, sys_flags, fd, offset);
+}
+
+int
+rte_mem_unmap(void *virt, size_t size)
+{
+ return mem_unmap(virt, size);
+}
+
+int
+rte_get_page_size(void)
+{
+ return getpagesize();
+}
+
+int
+rte_mem_lock(const void *virt, size_t size)
+{
+ return mlock(virt, size);
+}
diff --git a/lib/librte_eal/unix/meson.build b/lib/librte_eal/unix/meson.build
index 13564838e..50c019a56 100644
--- a/lib/librte_eal/unix/meson.build
+++ b/lib/librte_eal/unix/meson.build
@@ -3,4 +3,5 @@
sources += files(
'eal.c',
+ 'eal_memory.c',
)
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 9dba895e7..cf55b56da 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -339,6 +339,12 @@ rte_eal_init(int argc, char **argv)
internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
}
+ if (eal_mem_win32api_init() < 0) {
+ rte_eal_init_alert("Cannot access Win32 memory management");
+ rte_errno = ENOTSUP;
+ return -1;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
new file mode 100644
index 000000000..59606d84c
--- /dev/null
+++ b/lib/librte_eal/windows/eal_memory.c
@@ -0,0 +1,433 @@
+#include <io.h>
+
+#include <rte_errno.h>
+#include <rte_memory.h>
+
+#include "eal_private.h"
+#include "eal_windows.h"
+
+/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
+ * Provide a copy of definitions and code to load it dynamically.
+ * Note: definitions are copied verbatim from Microsoft documentation
+ * and don't follow DPDK code style.
+ */
+#ifndef MEM_PRESERVE_PLACEHOLDER
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ne-winnt-mem_extended_parameter_type */
+typedef enum MEM_EXTENDED_PARAMETER_TYPE {
+ MemExtendedParameterInvalidType,
+ MemExtendedParameterAddressRequirements,
+ MemExtendedParameterNumaNode,
+ MemExtendedParameterPartitionHandle,
+ MemExtendedParameterMax,
+ MemExtendedParameterUserPhysicalHandle,
+ MemExtendedParameterAttributeFlags
+} *PMEM_EXTENDED_PARAMETER_TYPE;
+
+#define MEM_EXTENDED_PARAMETER_TYPE_BITS 4
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ns-winnt-mem_extended_parameter */
+typedef struct MEM_EXTENDED_PARAMETER {
+ struct {
+ DWORD64 Type : MEM_EXTENDED_PARAMETER_TYPE_BITS;
+ DWORD64 Reserved : 64 - MEM_EXTENDED_PARAMETER_TYPE_BITS;
+ } DUMMYSTRUCTNAME;
+ union {
+ DWORD64 ULong64;
+ PVOID Pointer;
+ SIZE_T Size;
+ HANDLE Handle;
+ DWORD ULong;
+ } DUMMYUNIONNAME;
+} MEM_EXTENDED_PARAMETER, *PMEM_EXTENDED_PARAMETER;
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualalloc2 */
+typedef PVOID (*VirtualAlloc2_type)(
+ HANDLE Process,
+ PVOID BaseAddress,
+ SIZE_T Size,
+ ULONG AllocationType,
+ ULONG PageProtection,
+ MEM_EXTENDED_PARAMETER *ExtendedParameters,
+ ULONG ParameterCount
+);
+
+/* VirtualAlloc2() flags. */
+#define MEM_COALESCE_PLACEHOLDERS 0x00000001
+#define MEM_PRESERVE_PLACEHOLDER 0x00000002
+#define MEM_REPLACE_PLACEHOLDER 0x00004000
+#define MEM_RESERVE_PLACEHOLDER 0x00040000
+
+/* Named exactly as the function, so that user code does not depend
+ * on it being found at compile time or dynamically.
+ */
+static VirtualAlloc2_type VirtualAlloc2;
+
+int
+eal_mem_win32api_init(void)
+{
+ static const char library_name[] = "kernelbase.dll";
+ static const char function[] = "VirtualAlloc2";
+
+ OSVERSIONINFO info;
+ HMODULE library = NULL;
+ int ret = 0;
+
+ /* Already done. */
+ if (VirtualAlloc2 != NULL)
+ return 0;
+
+ /* IsWindows10OrGreater() may also be unavailable. */
+ memset(&info, 0, sizeof(info));
+ info.dwOSVersionInfoSize = sizeof(info);
+ GetVersionEx(&info);
+
+ /* Checking for Windows 10+ will also detect Windows Server 2016+.
+ * Do not abort, because Windows may report false version depending
+ * on executable manifest, compatibility mode, etc.
+ */
+ if (info.dwMajorVersion < 10)
+ RTE_LOG(DEBUG, EAL, "Windows 10+ or Windows Server 2016+ "
+ "is required for advanced memory features\n");
+
+ library = LoadLibraryA(library_name);
+ if (library == NULL) {
+ RTE_LOG_WIN32_ERR("LoadLibraryA(\"%s\")", library_name);
+ return -1;
+ }
+
+ VirtualAlloc2 = (VirtualAlloc2_type)(
+ (void *)GetProcAddress(library, function));
+ if (VirtualAlloc2 == NULL) {
+ RTE_LOG_WIN32_ERR("GetProcAddress(\"%s\", \"%s\")\n",
+ library_name, function);
+ ret = -1;
+ }
+
+ FreeLibrary(library);
+
+ return ret;
+}
+
+#else
+
+/* Stub in case VirtualAlloc2() is provided by the compiler. */
+int
+eal_mem_win32api_init(void)
+{
+ return 0;
+}
+
+#endif /* no VirtualAlloc2() */
+
+/* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
+static int
+win32_alloc_error_to_errno(DWORD code)
+{
+ switch (code) {
+ case ERROR_SUCCESS:
+ return 0;
+
+ case ERROR_INVALID_ADDRESS:
+ /* A valid requested address is not available. */
+ case ERROR_COMMITMENT_LIMIT:
+ /* May occcur when committing regular memory. */
+ case ERROR_NO_SYSTEM_RESOURCES:
+ /* Occurs when the system runs out of hugepages. */
+ return ENOMEM;
+
+ case ERROR_INVALID_PARAMETER:
+ default:
+ return EINVAL;
+ }
+}
+
+void *
+eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags)
+{
+ void *virt;
+
+ /* Windows requires hugepages to be committed. */
+ if (flags & EAL_RESERVE_HUGEPAGES) {
+ RTE_LOG(ERR, EAL, "Hugepage reservation is not supported\n");
+ rte_errno = ENOTSUP;
+ return NULL;
+ }
+
+ virt = VirtualAlloc2(GetCurrentProcess(), requested_addr, size,
+ MEM_RESERVE | MEM_RESERVE_PLACEHOLDER, PAGE_NOACCESS,
+ NULL, 0);
+ if (virt == NULL) {
+ RTE_LOG_WIN32_ERR("VirtualAlloc2()");
+ rte_errno = win32_alloc_error_to_errno(GetLastError());
+ }
+
+ if ((flags & EAL_RESERVE_EXACT_ADDRESS) && (virt != requested_addr)) {
+ if (!VirtualFree(virt, 0, MEM_RELEASE))
+ RTE_LOG_WIN32_ERR("VirtualFree()");
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+
+ return virt;
+}
+
+void *
+eal_mem_alloc(size_t size, enum rte_page_sizes page_size)
+{
+ if (page_size != 0)
+ return eal_mem_alloc_socket(size, SOCKET_ID_ANY);
+
+ return VirtualAlloc(
+ NULL, size, MEM_RESERVE | MEM_COMMIT, PAGE_READWRITE);
+}
+
+void *
+eal_mem_alloc_socket(size_t size, int socket_id)
+{
+ DWORD flags = MEM_RESERVE | MEM_COMMIT;
+ void *addr;
+
+ flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
+ addr = VirtualAllocExNuma(GetCurrentProcess(), NULL, size, flags,
+ PAGE_READWRITE, eal_socket_numa_node(socket_id));
+ if (addr == NULL)
+ rte_errno = ENOMEM;
+ return addr;
+}
+
+void*
+eal_mem_commit(void *requested_addr, size_t size, int socket_id)
+{
+ MEM_EXTENDED_PARAMETER param;
+ DWORD param_count = 0;
+ DWORD flags;
+ void *addr;
+
+ if (requested_addr != NULL) {
+ MEMORY_BASIC_INFORMATION info;
+ if (VirtualQuery(requested_addr, &info, sizeof(info)) == 0) {
+ RTE_LOG_WIN32_ERR("VirtualQuery()");
+ return NULL;
+ }
+
+ /* Split reserved region if only a part is committed. */
+ flags = MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER;
+ if ((info.RegionSize > size) &&
+ !VirtualFree(requested_addr, size, flags)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, "
+ "<split placeholder>)", requested_addr, size);
+ return NULL;
+ }
+ }
+
+ if (socket_id != SOCKET_ID_ANY) {
+ param_count = 1;
+ memset(¶m, 0, sizeof(param));
+ param.Type = MemExtendedParameterNumaNode;
+ param.ULong = eal_socket_numa_node(socket_id);
+ }
+
+ flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
+ if (requested_addr != NULL)
+ flags |= MEM_REPLACE_PLACEHOLDER;
+
+ addr = VirtualAlloc2(GetCurrentProcess(), requested_addr, size,
+ flags, PAGE_READWRITE, ¶m, param_count);
+ if (addr == NULL) {
+ int err = GetLastError();
+ RTE_LOG_WIN32_ERR("VirtualAlloc2(%p, %zu, "
+ "<replace placeholder>)", addr, size);
+ rte_errno = win32_alloc_error_to_errno(err);
+ return NULL;
+ }
+
+ return addr;
+}
+
+int
+eal_mem_decommit(void *addr, size_t size)
+{
+ if (!VirtualFree(addr, size, MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, ...)", addr, size);
+ return -1;
+ }
+ return 0;
+}
+
+/**
+ * Free a reserved memory region in full or in part.
+ *
+ * @param addr
+ * Starting address of the area to free.
+ * @param size
+ * Number of bytes to free. Must be a multiple of page size.
+ * @param reserved
+ * Fail if the region is not in reserved state.
+ * @return
+ * * 0 on successful deallocation;
+ * * 1 if region mut be in reserved state but it is not;
+ * * (-1) on system API failures.
+ */
+static int
+mem_free(void *addr, size_t size, bool reserved)
+{
+ MEMORY_BASIC_INFORMATION info;
+ if (VirtualQuery(addr, &info, sizeof(info)) == 0) {
+ RTE_LOG_WIN32_ERR("VirtualQuery()");
+ return -1;
+ }
+
+ if (reserved && (info.State != MEM_RESERVE))
+ return 1;
+
+ /* Free complete region. */
+ if ((addr == info.AllocationBase) && (size == info.RegionSize)) {
+ if (!VirtualFree(addr, 0, MEM_RELEASE)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, 0, MEM_RELEASE)",
+ addr);
+ }
+ return 0;
+ }
+
+ /* Split the part to be freed and the remaining reservation. */
+ if (!VirtualFree(addr, size, MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, "
+ "MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)", addr, size);
+ return -1;
+ }
+
+ /* Actually free reservation part. */
+ if (!VirtualFree(addr, 0, MEM_RELEASE)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, 0, MEM_RELEASE)", addr);
+ return -1;
+ }
+
+ return 0;
+}
+
+void
+eal_mem_free(void *virt, size_t size)
+{
+ mem_free(virt, size, false);
+}
+
+void *
+rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset)
+{
+ HANDLE file_handle = INVALID_HANDLE_VALUE;
+ HANDLE mapping_handle = INVALID_HANDLE_VALUE;
+ DWORD sys_prot = 0;
+ DWORD sys_access = 0;
+ DWORD size_high = (DWORD)(size >> 32);
+ DWORD size_low = (DWORD)size;
+ DWORD offset_high = (DWORD)(offset >> 32);
+ DWORD offset_low = (DWORD)offset;
+ LPVOID virt = NULL;
+
+ if (prot & RTE_PROT_EXECUTE) {
+ if (prot & RTE_PROT_READ) {
+ sys_prot = PAGE_EXECUTE_READ;
+ sys_access = FILE_MAP_READ | FILE_MAP_EXECUTE;
+ }
+ if (prot & RTE_PROT_WRITE) {
+ sys_prot = PAGE_EXECUTE_READWRITE;
+ sys_access = FILE_MAP_WRITE | FILE_MAP_EXECUTE;
+ }
+ } else {
+ if (prot & RTE_PROT_READ) {
+ sys_prot = PAGE_READONLY;
+ sys_access = FILE_MAP_READ;
+ }
+ if (prot & RTE_PROT_WRITE) {
+ sys_prot = PAGE_READWRITE;
+ sys_access = FILE_MAP_WRITE;
+ }
+ }
+
+ if (flags & RTE_MAP_PRIVATE)
+ sys_access |= FILE_MAP_COPY;
+
+ if ((flags & RTE_MAP_ANONYMOUS) == 0)
+ file_handle = (HANDLE)_get_osfhandle(fd);
+
+ mapping_handle = CreateFileMapping(
+ file_handle, NULL, sys_prot, size_high, size_low, NULL);
+ if (mapping_handle == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("CreateFileMapping()");
+ return NULL;
+ }
+
+ /* TODO: there is a race for the requested_addr between mem_free()
+ * and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
+ * region with a mapping in a single operation, but it does not support
+ * private mappings.
+ */
+ if (requested_addr != NULL) {
+ int ret = mem_free(requested_addr, size, true);
+ if (ret) {
+ if (ret > 0) {
+ RTE_LOG(ERR, EAL, "Cannot map memory "
+ "to a region not reserved\n");
+ rte_errno = EADDRNOTAVAIL;
+ }
+ return NULL;
+ }
+ }
+
+ virt = MapViewOfFileEx(mapping_handle, sys_access,
+ offset_high, offset_low, size, requested_addr);
+ if (!virt) {
+ RTE_LOG_WIN32_ERR("MapViewOfFileEx()");
+ return NULL;
+ }
+
+ if ((flags & RTE_MAP_FIXED) && (virt != requested_addr)) {
+ BOOL ret = UnmapViewOfFile(virt);
+ virt = NULL;
+ if (!ret)
+ RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
+ }
+
+ if (!CloseHandle(mapping_handle))
+ RTE_LOG_WIN32_ERR("CloseHandle()");
+
+ return virt;
+}
+
+int
+rte_mem_unmap(void *virt, size_t size)
+{
+ RTE_SET_USED(size);
+
+ if (!UnmapViewOfFile(virt)) {
+ rte_errno = GetLastError();
+ RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
+ return -1;
+ }
+ return 0;
+}
+
+int
+rte_get_page_size(void)
+{
+ SYSTEM_INFO info;
+ GetSystemInfo(&info);
+ return info.dwPageSize;
+}
+
+int
+rte_mem_lock(const void *virt, size_t size)
+{
+ /* VirtualLock() takes `void*`, work around compiler warning. */
+ void *addr = (void *)((uintptr_t)virt);
+
+ if (!VirtualLock(addr, size)) {
+ RTE_LOG_WIN32_ERR("VirtualLock()");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index 390d2fd66..b202a1aa5 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -36,4 +36,71 @@ int eal_thread_create(pthread_t *thread);
*/
unsigned int eal_socket_numa_node(unsigned int socket_id);
+/**
+ * Locate Win32 memory management routines in system libraries.
+ *
+ * @return 0 on success, (-1) on failure.
+ */
+int eal_mem_win32api_init(void);
+
+/**
+ * Allocate a contiguous chunk of virtual memory.
+ *
+ * Use eal_mem_free() to free allocated memory.
+ *
+ * @param size
+ * Number of bytes to allocate.
+ * @param page_size
+ * If non-zero, means memory must be allocated in hugepages
+ * of the specified size. The @code size @endcode parameter
+ * must then be a multiple of the largest hugepage size requested.
+ * @return
+ * Address of allocated memory or NULL on failure (rte_errno is set).
+ */
+void *eal_mem_alloc(size_t size, enum rte_page_sizes page_size);
+
+/**
+ * Allocate new memory in hugepages on the specified NUMA node.
+ *
+ * @param size
+ * Number of bytes to allocate. Must be a multiple of huge page size.
+ * @param socket_id
+ * Socket ID.
+ * @return
+ * Address of the memory allocated on success or NULL on failure.
+ */
+void *eal_mem_alloc_socket(size_t size, int socket_id);
+
+/**
+ * Commit memory previously reserved with @ref eal_mem_reserve()
+ * or decommitted from hugepages by @ref eal_mem_decommit().
+ *
+ * @param requested_addr
+ * Address within a reserved region. Must not be NULL.
+ * @param size
+ * Number of bytes to commit. Must be a multiple of page size.
+ * @param socket_id
+ * Socket ID to allocate on. Can be SOCKET_ID_ANY.
+ * @return
+ * On success, address of the committed memory, that is, requested_addr.
+ * On failure, NULL and @code rte_errno @endcode is set.
+ */
+void *eal_mem_commit(void *requested_addr, size_t size, int socket_id);
+
+/**
+ * Put allocated or committed memory back into reserved state.
+ *
+ * @param addr
+ * Address of the region to decommit.
+ * @param size
+ * Number of bytes to decommit.
+ *
+ * The @code addr @endcode and @code param @endcode must match
+ * location and size of previously allocated or committed region.
+ *
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_mem_decommit(void *addr, size_t size);
+
#endif /* _EAL_WINDOWS_H_ */
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 5f118bfe2..81d3ee095 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -8,6 +8,7 @@ sources += files(
'eal_debug.c',
'eal_hugepages.c',
'eal_lcore.c',
+ 'eal_memory.c',
'eal_thread.c',
'getopt.c',
)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v2 06/10] eal: introduce memory management wrappers
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
@ 2020-04-13 7:50 ` Tal Shnaiderman
0 siblings, 0 replies; 218+ messages in thread
From: Tal Shnaiderman @ 2020-04-13 7:50 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Thomas Monjalon,
Anatoly Burakov, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon
> Subject: [PATCH v2 06/10] eal: introduce memory management wrappers
>
> System meory management is implemented differently for POSIX and
> Windows. Introduce wrapper functions for operations used across DPDK:
>
> * rte_mem_map()
> Create memory mapping for a regular file or a page file (swap).
> This supports mapping to a reserved memory region even on Windows.
>
> * rte_mem_unmap()
> Remove mapping created with rte_mem_map().
>
> * rte_get_page_size()
> Obtain default system page size.
>
> * rte_mem_lock()
> Make arbitrary-sized memory region non-swappable.
>
> Wrappers follow POSIX semantics limited to DPDK tasks, but their signatures
> deliberately differ from POSIX ones to be more safe and expressive.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
<Snip!>
> +void *
> +rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot
> prot,
> + enum rte_map_flags flags, int fd, size_t offset) {
> + int sys_prot = 0;
> + int sys_flags = 0;
> +
> + sys_prot = mem_rte_to_sys_prot(prot);
> +
> + if (flags & RTE_MAP_SHARED)
> + sys_flags |= MAP_SHARED;
> + if (flags & RTE_MAP_ANONYMOUS)
> + sys_flags |= MAP_ANONYMOUS;
> + if (flags & RTE_MAP_PRIVATE)
> + sys_flags |= MAP_PRIVATE;
> + if (flags & RTE_MAP_FIXED)
> + sys_flags |= MAP_FIXED;
> +
> + return mem_map(requested_addr, size, sys_prot, sys_flags, fd,
> offset);
> +}
Looks like there is a different behavior in the Windows and Unix implementation of rte_mem_map in case of memory mapping failure, in Windows the function returns NULL however in Unix the return value is the MAP_FAILED value of mmap which is ((void *)-1)
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 07/10] eal: extract common code for memseg list initialization
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (5 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 08/10] eal/windows: fix rte_page_sizes with Clang on Windows Dmitry Kozlyuk
` (4 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Anatoly Burakov, Bruce Richardson
All supported OS create memory segment lists (MSL) and reserve VA space
for them in a nearly identical way. Move common code into EAL private
functions to reduce duplication.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/common/eal_common_memory.c | 54 ++++++++++++++++++
lib/librte_eal/common/eal_private.h | 34 ++++++++++++
lib/librte_eal/freebsd/eal_memory.c | 54 +++---------------
lib/librte_eal/linux/eal_memory.c | 68 +++++------------------
4 files changed, 110 insertions(+), 100 deletions(-)
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index cc7d54e0c..d9764681a 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -25,6 +25,7 @@
#include "eal_private.h"
#include "eal_internal_cfg.h"
#include "eal_memcfg.h"
+#include "eal_options.h"
#include "malloc_heap.h"
/*
@@ -182,6 +183,59 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
return aligned_addr;
}
+int
+eal_reserve_memseg_list(struct rte_memseg_list *msl,
+ enum eal_mem_reserve_flags flags)
+{
+ uint64_t page_sz;
+ size_t mem_sz;
+ void *addr;
+
+ page_sz = msl->page_sz;
+ mem_sz = page_sz * msl->memseg_arr.len;
+
+ addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
+ if (addr == NULL) {
+ if (rte_errno == EADDRNOTAVAIL)
+ RTE_LOG(ERR, EAL, "Cannot reserve %llu bytes at [%p] - "
+ "please use '--" OPT_BASE_VIRTADDR "' option\n",
+ (unsigned long long)mem_sz, msl->base_va);
+ else
+ RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
+ return -1;
+ }
+ msl->base_va = addr;
+ msl->len = mem_sz;
+
+ return 0;
+}
+
+int
+eal_alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx, bool heap)
+{
+ char name[RTE_FBARRAY_NAME_LEN];
+
+ snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
+ type_msl_idx);
+ if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
+ sizeof(struct rte_memseg))) {
+ RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
+ rte_strerror(rte_errno));
+ return -1;
+ }
+
+ msl->page_sz = page_sz;
+ msl->socket_id = socket_id;
+ msl->base_va = NULL;
+ msl->heap = heap;
+
+ RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
+ (size_t)page_sz >> 10, socket_id);
+
+ return 0;
+}
+
static struct rte_memseg *
virt2memseg(const void *addr, const struct rte_memseg_list *msl)
{
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 1e89338f2..76938e379 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -246,6 +246,40 @@ void *
eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
int flags, int mmap_flags);
+/**
+ * Reserve VA space for a memory segment list.
+ *
+ * @param msl
+ * Memory segment list with page size defined.
+ * @param flags
+ * Extra memory reservation flags. Can be 0 if unnecessary.
+ * @return
+ * 0 on success, (-1) on failure and rte_errno is set.
+ */
+int
+eal_reserve_memseg_list(struct rte_memseg_list *msl,
+ enum eal_mem_reserve_flags flags);
+
+/**
+ * Initialize a memory segment list with its backing storage.
+ *
+ * @param msl
+ * Memory segment list to be filled.
+ * @param page_sz
+ * Size of segment pages in the MSL.
+ * @param n_segs
+ * Number of segments.
+ * @param socket_id
+ * Socket ID. Must not be SOCKET_ID_ANY.
+ * @param type_msl_idx
+ * Index of the MSL among other MSLs of the same socket and page size.
+ * @param heap
+ * Mark MSL as pointing to a heap.
+ */
+int
+eal_alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx, bool heap);
+
/**
* Get cpu core_id.
*
diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
index a97d8f0f0..5174f9cd0 100644
--- a/lib/librte_eal/freebsd/eal_memory.c
+++ b/lib/librte_eal/freebsd/eal_memory.c
@@ -336,61 +336,23 @@ get_mem_amount(uint64_t page_sz, uint64_t max_mem)
return RTE_ALIGN(area_sz, page_sz);
}
-#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
static int
-alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
int n_segs, int socket_id, int type_msl_idx)
{
- char name[RTE_FBARRAY_NAME_LEN];
-
- snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
- type_msl_idx);
- if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
- sizeof(struct rte_memseg))) {
- RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
- rte_strerror(rte_errno));
- return -1;
- }
-
- msl->page_sz = page_sz;
- msl->socket_id = socket_id;
- msl->base_va = NULL;
-
- RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
- (size_t)page_sz >> 10, socket_id);
-
- return 0;
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, false);
}
static int
-alloc_va_space(struct rte_memseg_list *msl)
+memseg_list_reserve(struct rte_memseg_list *msl)
{
- uint64_t page_sz;
- size_t mem_sz;
- void *addr;
- int flags = 0;
+ enum eal_reserve_flags flags = 0;
#ifdef RTE_ARCH_PPC_64
- flags |= MAP_HUGETLB;
+ flags |= EAL_RESERVE_HUGEPAGES;
#endif
-
- page_sz = msl->page_sz;
- mem_sz = page_sz * msl->memseg_arr.len;
-
- addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
- if (addr == NULL) {
- if (rte_errno == EADDRNOTAVAIL)
- RTE_LOG(ERR, EAL, "Could not mmap %llu bytes at [%p] - "
- "please use '--" OPT_BASE_VIRTADDR "' option\n",
- (unsigned long long)mem_sz, msl->base_va);
- else
- RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
- return -1;
- }
- msl->base_va = addr;
- msl->len = mem_sz;
-
- return 0;
+ return eal_reserve_memseg_list(msl, flags);
}
@@ -479,7 +441,7 @@ memseg_primary_init(void)
cur_max_mem);
n_segs = cur_mem / hugepage_sz;
- if (alloc_memseg_list(msl, hugepage_sz, n_segs,
+ if (memseg_list_alloc(msl, hugepage_sz, n_segs,
0, type_msl_idx))
return -1;
diff --git a/lib/librte_eal/linux/eal_memory.c b/lib/librte_eal/linux/eal_memory.c
index 7a9c97ff8..a01a7ce76 100644
--- a/lib/librte_eal/linux/eal_memory.c
+++ b/lib/librte_eal/linux/eal_memory.c
@@ -802,7 +802,7 @@ get_mem_amount(uint64_t page_sz, uint64_t max_mem)
}
static int
-free_memseg_list(struct rte_memseg_list *msl)
+memseg_list_free(struct rte_memseg_list *msl)
{
if (rte_fbarray_destroy(&msl->memseg_arr)) {
RTE_LOG(ERR, EAL, "Cannot destroy memseg list\n");
@@ -812,58 +812,18 @@ free_memseg_list(struct rte_memseg_list *msl)
return 0;
}
-#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
static int
-alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
int n_segs, int socket_id, int type_msl_idx)
{
- char name[RTE_FBARRAY_NAME_LEN];
-
- snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
- type_msl_idx);
- if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
- sizeof(struct rte_memseg))) {
- RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
- rte_strerror(rte_errno));
- return -1;
- }
-
- msl->page_sz = page_sz;
- msl->socket_id = socket_id;
- msl->base_va = NULL;
- msl->heap = 1; /* mark it as a heap segment */
-
- RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
- (size_t)page_sz >> 10, socket_id);
-
- return 0;
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, true);
}
static int
-alloc_va_space(struct rte_memseg_list *msl)
+memseg_list_reserve(struct rte_memseg_list *msl)
{
- uint64_t page_sz;
- size_t mem_sz;
- void *addr;
- int flags = 0;
-
- page_sz = msl->page_sz;
- mem_sz = page_sz * msl->memseg_arr.len;
-
- addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
- if (addr == NULL) {
- if (rte_errno == EADDRNOTAVAIL)
- RTE_LOG(ERR, EAL, "Could not mmap %llu bytes at [%p] - "
- "please use '--" OPT_BASE_VIRTADDR "' option\n",
- (unsigned long long)mem_sz, msl->base_va);
- else
- RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
- return -1;
- }
- msl->base_va = addr;
- msl->len = mem_sz;
-
- return 0;
+ return eal_reserve_memseg_list(msl, 0);
}
/*
@@ -1009,12 +969,12 @@ prealloc_segments(struct hugepage_file *hugepages, int n_pages)
}
/* now, allocate fbarray itself */
- if (alloc_memseg_list(msl, page_sz, n_segs, socket,
+ if (memseg_list_alloc(msl, page_sz, n_segs, socket,
msl_idx) < 0)
return -1;
/* finally, allocate VA space */
- if (alloc_va_space(msl) < 0)
+ if (memseg_list_reserve(msl) < 0)
return -1;
}
}
@@ -2191,7 +2151,7 @@ memseg_primary_init_32(void)
max_pagesz_mem);
n_segs = cur_mem / hugepage_sz;
- if (alloc_memseg_list(msl, hugepage_sz, n_segs,
+ if (memseg_list_alloc(msl, hugepage_sz, n_segs,
socket_id, type_msl_idx)) {
/* failing to allocate a memseg list is
* a serious error.
@@ -2200,13 +2160,13 @@ memseg_primary_init_32(void)
return -1;
}
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
/* if we couldn't allocate VA space, we
* can try with smaller page sizes.
*/
RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list, retrying with different page size\n");
/* deallocate memseg list */
- if (free_memseg_list(msl))
+ if (memseg_list_free(msl))
return -1;
break;
}
@@ -2395,11 +2355,11 @@ memseg_primary_init(void)
}
msl = &mcfg->memsegs[msl_idx++];
- if (alloc_memseg_list(msl, pagesz, n_segs,
+ if (memseg_list_alloc(msl, pagesz, n_segs,
socket_id, cur_seglist))
goto out;
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
goto out;
}
@@ -2433,7 +2393,7 @@ memseg_secondary_init(void)
}
/* preallocate VA space */
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
RTE_LOG(ERR, EAL, "Cannot preallocate VA space for hugepage memory\n");
return -1;
}
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (6 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD Dmitry Kozlyuk
` (3 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Anatoly Burakov
Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
Enum rte_page_size has members valued above this limit, which get
wrapped to zero, resulting in compilation error (duplicate values in
enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
Define these values outside of the enum for Clang on Windows only.
This does not affect runtime, because Windows doesn't run on machines
with 4GiB and 16GiB hugepages.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/include/rte_memory.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 1b7c3e5df..3ec673f51 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -34,8 +34,14 @@ enum rte_page_sizes {
RTE_PGSIZE_256M = 1ULL << 28,
RTE_PGSIZE_512M = 1ULL << 29,
RTE_PGSIZE_1G = 1ULL << 30,
+/* Work around Clang on Windows being limited to 32-bit underlying type. */
+#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
RTE_PGSIZE_4G = 1ULL << 32,
RTE_PGSIZE_16G = 1ULL << 34,
+#else
+#define RTE_PGSIZE_4G (1ULL << 32)
+#define RTE_PGSIZE_16G (1ULL << 34)
+#endif
};
#define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (7 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 08/10] eal/windows: fix rte_page_sizes with Clang on Windows Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
` (2 subsequent siblings)
11 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon
Limited version imported previously lacks at least SLIST macros.
Import a complete file from FreeBSD, since its license exception is
already approved by Technical Board.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/include/sys/queue.h | 663 +++++++++++++++++++--
1 file changed, 601 insertions(+), 62 deletions(-)
diff --git a/lib/librte_eal/windows/include/sys/queue.h b/lib/librte_eal/windows/include/sys/queue.h
index a65949a78..9756bee6f 100644
--- a/lib/librte_eal/windows/include/sys/queue.h
+++ b/lib/librte_eal/windows/include/sys/queue.h
@@ -8,7 +8,36 @@
#define _SYS_QUEUE_H_
/*
- * This file defines tail queues.
+ * This file defines four types of data structures: singly-linked lists,
+ * singly-linked tail queues, lists and tail queues.
+ *
+ * A singly-linked list is headed by a single forward pointer. The elements
+ * are singly linked for minimum space and pointer manipulation overhead at
+ * the expense of O(n) removal for arbitrary elements. New elements can be
+ * added to the list after an existing element or at the head of the list.
+ * Elements being removed from the head of the list should use the explicit
+ * macro for this purpose for optimum efficiency. A singly-linked list may
+ * only be traversed in the forward direction. Singly-linked lists are ideal
+ * for applications with large datasets and few or no removals or for
+ * implementing a LIFO queue.
+ *
+ * A singly-linked tail queue is headed by a pair of pointers, one to the
+ * head of the list and the other to the tail of the list. The elements are
+ * singly linked for minimum space and pointer manipulation overhead at the
+ * expense of O(n) removal for arbitrary elements. New elements can be added
+ * to the list after an existing element, at the head of the list, or at the
+ * end of the list. Elements being removed from the head of the tail queue
+ * should use the explicit macro for this purpose for optimum efficiency.
+ * A singly-linked tail queue may only be traversed in the forward direction.
+ * Singly-linked tail queues are ideal for applications with large datasets
+ * and few or no removals or for implementing a FIFO queue.
+ *
+ * A list is headed by a single forward pointer (or an array of forward
+ * pointers for a hash table header). The elements are doubly linked
+ * so that an arbitrary element can be removed without a need to
+ * traverse the list. New elements can be added to the list before
+ * or after an existing element or at the head of the list. A list
+ * may be traversed in either direction.
*
* A tail queue is headed by a pair of pointers, one to the head of the
* list and the other to the tail of the list. The elements are doubly
@@ -17,65 +46,93 @@
* after an existing element, at the head of the list, or at the end of
* the list. A tail queue may be traversed in either direction.
*
+ * For details on the use of these macros, see the queue(3) manual page.
+ *
* Below is a summary of implemented functions where:
* + means the macro is available
* - means the macro is not available
* s means the macro is available but is slow (runs in O(n) time)
*
- * TAILQ
- * _HEAD +
- * _CLASS_HEAD +
- * _HEAD_INITIALIZER +
- * _ENTRY +
- * _CLASS_ENTRY +
- * _INIT +
- * _EMPTY +
- * _FIRST +
- * _NEXT +
- * _PREV +
- * _LAST +
- * _LAST_FAST +
- * _FOREACH +
- * _FOREACH_FROM +
- * _FOREACH_SAFE +
- * _FOREACH_FROM_SAFE +
- * _FOREACH_REVERSE +
- * _FOREACH_REVERSE_FROM +
- * _FOREACH_REVERSE_SAFE +
- * _FOREACH_REVERSE_FROM_SAFE +
- * _INSERT_HEAD +
- * _INSERT_BEFORE +
- * _INSERT_AFTER +
- * _INSERT_TAIL +
- * _CONCAT +
- * _REMOVE_AFTER -
- * _REMOVE_HEAD -
- * _REMOVE +
- * _SWAP +
+ * SLIST LIST STAILQ TAILQ
+ * _HEAD + + + +
+ * _CLASS_HEAD + + + +
+ * _HEAD_INITIALIZER + + + +
+ * _ENTRY + + + +
+ * _CLASS_ENTRY + + + +
+ * _INIT + + + +
+ * _EMPTY + + + +
+ * _FIRST + + + +
+ * _NEXT + + + +
+ * _PREV - + - +
+ * _LAST - - + +
+ * _LAST_FAST - - - +
+ * _FOREACH + + + +
+ * _FOREACH_FROM + + + +
+ * _FOREACH_SAFE + + + +
+ * _FOREACH_FROM_SAFE + + + +
+ * _FOREACH_REVERSE - - - +
+ * _FOREACH_REVERSE_FROM - - - +
+ * _FOREACH_REVERSE_SAFE - - - +
+ * _FOREACH_REVERSE_FROM_SAFE - - - +
+ * _INSERT_HEAD + + + +
+ * _INSERT_BEFORE - + - +
+ * _INSERT_AFTER + + + +
+ * _INSERT_TAIL - - + +
+ * _CONCAT s s + +
+ * _REMOVE_AFTER + - + -
+ * _REMOVE_HEAD + - + -
+ * _REMOVE s + s +
+ * _SWAP + + + +
*
*/
-
-#ifdef __cplusplus
-extern "C" {
+#ifdef QUEUE_MACRO_DEBUG
+#warn Use QUEUE_MACRO_DEBUG_TRACE and/or QUEUE_MACRO_DEBUG_TRASH
+#define QUEUE_MACRO_DEBUG_TRACE
+#define QUEUE_MACRO_DEBUG_TRASH
#endif
-/*
- * List definitions.
- */
-#define LIST_HEAD(name, type) \
-struct name { \
- struct type *lh_first; /* first element */ \
-}
+#ifdef QUEUE_MACRO_DEBUG_TRACE
+/* Store the last 2 places the queue element or head was altered */
+struct qm_trace {
+ unsigned long lastline;
+ unsigned long prevline;
+ const char *lastfile;
+ const char *prevfile;
+};
+
+#define TRACEBUF struct qm_trace trace;
+#define TRACEBUF_INITIALIZER { __LINE__, 0, __FILE__, NULL } ,
+
+#define QMD_TRACE_HEAD(head) do { \
+ (head)->trace.prevline = (head)->trace.lastline; \
+ (head)->trace.prevfile = (head)->trace.lastfile; \
+ (head)->trace.lastline = __LINE__; \
+ (head)->trace.lastfile = __FILE__; \
+} while (0)
+#define QMD_TRACE_ELEM(elem) do { \
+ (elem)->trace.prevline = (elem)->trace.lastline; \
+ (elem)->trace.prevfile = (elem)->trace.lastfile; \
+ (elem)->trace.lastline = __LINE__; \
+ (elem)->trace.lastfile = __FILE__; \
+} while (0)
+
+#else /* !QUEUE_MACRO_DEBUG_TRACE */
#define QMD_TRACE_ELEM(elem)
#define QMD_TRACE_HEAD(head)
#define TRACEBUF
#define TRACEBUF_INITIALIZER
+#endif /* QUEUE_MACRO_DEBUG_TRACE */
+#ifdef QUEUE_MACRO_DEBUG_TRASH
+#define QMD_SAVELINK(name, link) void **name = (void *)&(link)
+#define TRASHIT(x) do {(x) = (void *)-1;} while (0)
+#define QMD_IS_TRASHED(x) ((x) == (void *)(intptr_t)-1)
+#else /* !QUEUE_MACRO_DEBUG_TRASH */
+#define QMD_SAVELINK(name, link)
#define TRASHIT(x)
#define QMD_IS_TRASHED(x) 0
-
-#define QMD_SAVELINK(name, link)
+#endif /* QUEUE_MACRO_DEBUG_TRASH */
#ifdef __cplusplus
/*
@@ -86,6 +143,445 @@ struct name { \
#define QUEUE_TYPEOF(type) struct type
#endif
+/*
+ * Singly-linked List declarations.
+ */
+#define SLIST_HEAD(name, type) \
+struct name { \
+ struct type *slh_first; /* first element */ \
+}
+
+#define SLIST_CLASS_HEAD(name, type) \
+struct name { \
+ class type *slh_first; /* first element */ \
+}
+
+#define SLIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define SLIST_ENTRY(type) \
+struct { \
+ struct type *sle_next; /* next element */ \
+}
+
+#define SLIST_CLASS_ENTRY(type) \
+struct { \
+ class type *sle_next; /* next element */ \
+}
+
+/*
+ * Singly-linked List functions.
+ */
+#if (defined(_KERNEL) && defined(INVARIANTS))
+#define QMD_SLIST_CHECK_PREVPTR(prevp, elm) do { \
+ if (*(prevp) != (elm)) \
+ panic("Bad prevptr *(%p) == %p != %p", \
+ (prevp), *(prevp), (elm)); \
+} while (0)
+#else
+#define QMD_SLIST_CHECK_PREVPTR(prevp, elm)
+#endif
+
+#define SLIST_CONCAT(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *curelm = SLIST_FIRST(head1); \
+ if (curelm == NULL) { \
+ if ((SLIST_FIRST(head1) = SLIST_FIRST(head2)) != NULL) \
+ SLIST_INIT(head2); \
+ } else if (SLIST_FIRST(head2) != NULL) { \
+ while (SLIST_NEXT(curelm, field) != NULL) \
+ curelm = SLIST_NEXT(curelm, field); \
+ SLIST_NEXT(curelm, field) = SLIST_FIRST(head2); \
+ SLIST_INIT(head2); \
+ } \
+} while (0)
+
+#define SLIST_EMPTY(head) ((head)->slh_first == NULL)
+
+#define SLIST_FIRST(head) ((head)->slh_first)
+
+#define SLIST_FOREACH(var, head, field) \
+ for ((var) = SLIST_FIRST((head)); \
+ (var); \
+ (var) = SLIST_NEXT((var), field))
+
+#define SLIST_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : SLIST_FIRST((head))); \
+ (var); \
+ (var) = SLIST_NEXT((var), field))
+
+#define SLIST_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = SLIST_FIRST((head)); \
+ (var) && ((tvar) = SLIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define SLIST_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : SLIST_FIRST((head))); \
+ (var) && ((tvar) = SLIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define SLIST_FOREACH_PREVPTR(var, varp, head, field) \
+ for ((varp) = &SLIST_FIRST((head)); \
+ ((var) = *(varp)) != NULL; \
+ (varp) = &SLIST_NEXT((var), field))
+
+#define SLIST_INIT(head) do { \
+ SLIST_FIRST((head)) = NULL; \
+} while (0)
+
+#define SLIST_INSERT_AFTER(slistelm, elm, field) do { \
+ SLIST_NEXT((elm), field) = SLIST_NEXT((slistelm), field); \
+ SLIST_NEXT((slistelm), field) = (elm); \
+} while (0)
+
+#define SLIST_INSERT_HEAD(head, elm, field) do { \
+ SLIST_NEXT((elm), field) = SLIST_FIRST((head)); \
+ SLIST_FIRST((head)) = (elm); \
+} while (0)
+
+#define SLIST_NEXT(elm, field) ((elm)->field.sle_next)
+
+#define SLIST_REMOVE(head, elm, type, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.sle_next); \
+ if (SLIST_FIRST((head)) == (elm)) { \
+ SLIST_REMOVE_HEAD((head), field); \
+ } \
+ else { \
+ QUEUE_TYPEOF(type) *curelm = SLIST_FIRST(head); \
+ while (SLIST_NEXT(curelm, field) != (elm)) \
+ curelm = SLIST_NEXT(curelm, field); \
+ SLIST_REMOVE_AFTER(curelm, field); \
+ } \
+ TRASHIT(*oldnext); \
+} while (0)
+
+#define SLIST_REMOVE_AFTER(elm, field) do { \
+ SLIST_NEXT(elm, field) = \
+ SLIST_NEXT(SLIST_NEXT(elm, field), field); \
+} while (0)
+
+#define SLIST_REMOVE_HEAD(head, field) do { \
+ SLIST_FIRST((head)) = SLIST_NEXT(SLIST_FIRST((head)), field); \
+} while (0)
+
+#define SLIST_REMOVE_PREVPTR(prevp, elm, field) do { \
+ QMD_SLIST_CHECK_PREVPTR(prevp, elm); \
+ *(prevp) = SLIST_NEXT(elm, field); \
+ TRASHIT((elm)->field.sle_next); \
+} while (0)
+
+#define SLIST_SWAP(head1, head2, type) do { \
+ QUEUE_TYPEOF(type) *swap_first = SLIST_FIRST(head1); \
+ SLIST_FIRST(head1) = SLIST_FIRST(head2); \
+ SLIST_FIRST(head2) = swap_first; \
+} while (0)
+
+/*
+ * Singly-linked Tail queue declarations.
+ */
+#define STAILQ_HEAD(name, type) \
+struct name { \
+ struct type *stqh_first;/* first element */ \
+ struct type **stqh_last;/* addr of last next element */ \
+}
+
+#define STAILQ_CLASS_HEAD(name, type) \
+struct name { \
+ class type *stqh_first; /* first element */ \
+ class type **stqh_last; /* addr of last next element */ \
+}
+
+#define STAILQ_HEAD_INITIALIZER(head) \
+ { NULL, &(head).stqh_first }
+
+#define STAILQ_ENTRY(type) \
+struct { \
+ struct type *stqe_next; /* next element */ \
+}
+
+#define STAILQ_CLASS_ENTRY(type) \
+struct { \
+ class type *stqe_next; /* next element */ \
+}
+
+/*
+ * Singly-linked Tail queue functions.
+ */
+#define STAILQ_CONCAT(head1, head2) do { \
+ if (!STAILQ_EMPTY((head2))) { \
+ *(head1)->stqh_last = (head2)->stqh_first; \
+ (head1)->stqh_last = (head2)->stqh_last; \
+ STAILQ_INIT((head2)); \
+ } \
+} while (0)
+
+#define STAILQ_EMPTY(head) ((head)->stqh_first == NULL)
+
+#define STAILQ_FIRST(head) ((head)->stqh_first)
+
+#define STAILQ_FOREACH(var, head, field) \
+ for((var) = STAILQ_FIRST((head)); \
+ (var); \
+ (var) = STAILQ_NEXT((var), field))
+
+#define STAILQ_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : STAILQ_FIRST((head))); \
+ (var); \
+ (var) = STAILQ_NEXT((var), field))
+
+#define STAILQ_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = STAILQ_FIRST((head)); \
+ (var) && ((tvar) = STAILQ_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define STAILQ_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : STAILQ_FIRST((head))); \
+ (var) && ((tvar) = STAILQ_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define STAILQ_INIT(head) do { \
+ STAILQ_FIRST((head)) = NULL; \
+ (head)->stqh_last = &STAILQ_FIRST((head)); \
+} while (0)
+
+#define STAILQ_INSERT_AFTER(head, tqelm, elm, field) do { \
+ if ((STAILQ_NEXT((elm), field) = STAILQ_NEXT((tqelm), field)) == NULL)\
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+ STAILQ_NEXT((tqelm), field) = (elm); \
+} while (0)
+
+#define STAILQ_INSERT_HEAD(head, elm, field) do { \
+ if ((STAILQ_NEXT((elm), field) = STAILQ_FIRST((head))) == NULL) \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+ STAILQ_FIRST((head)) = (elm); \
+} while (0)
+
+#define STAILQ_INSERT_TAIL(head, elm, field) do { \
+ STAILQ_NEXT((elm), field) = NULL; \
+ *(head)->stqh_last = (elm); \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+} while (0)
+
+#define STAILQ_LAST(head, type, field) \
+ (STAILQ_EMPTY((head)) ? NULL : \
+ __containerof((head)->stqh_last, \
+ QUEUE_TYPEOF(type), field.stqe_next))
+
+#define STAILQ_NEXT(elm, field) ((elm)->field.stqe_next)
+
+#define STAILQ_REMOVE(head, elm, type, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.stqe_next); \
+ if (STAILQ_FIRST((head)) == (elm)) { \
+ STAILQ_REMOVE_HEAD((head), field); \
+ } \
+ else { \
+ QUEUE_TYPEOF(type) *curelm = STAILQ_FIRST(head); \
+ while (STAILQ_NEXT(curelm, field) != (elm)) \
+ curelm = STAILQ_NEXT(curelm, field); \
+ STAILQ_REMOVE_AFTER(head, curelm, field); \
+ } \
+ TRASHIT(*oldnext); \
+} while (0)
+
+#define STAILQ_REMOVE_AFTER(head, elm, field) do { \
+ if ((STAILQ_NEXT(elm, field) = \
+ STAILQ_NEXT(STAILQ_NEXT(elm, field), field)) == NULL) \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+} while (0)
+
+#define STAILQ_REMOVE_HEAD(head, field) do { \
+ if ((STAILQ_FIRST((head)) = \
+ STAILQ_NEXT(STAILQ_FIRST((head)), field)) == NULL) \
+ (head)->stqh_last = &STAILQ_FIRST((head)); \
+} while (0)
+
+#define STAILQ_SWAP(head1, head2, type) do { \
+ QUEUE_TYPEOF(type) *swap_first = STAILQ_FIRST(head1); \
+ QUEUE_TYPEOF(type) **swap_last = (head1)->stqh_last; \
+ STAILQ_FIRST(head1) = STAILQ_FIRST(head2); \
+ (head1)->stqh_last = (head2)->stqh_last; \
+ STAILQ_FIRST(head2) = swap_first; \
+ (head2)->stqh_last = swap_last; \
+ if (STAILQ_EMPTY(head1)) \
+ (head1)->stqh_last = &STAILQ_FIRST(head1); \
+ if (STAILQ_EMPTY(head2)) \
+ (head2)->stqh_last = &STAILQ_FIRST(head2); \
+} while (0)
+
+
+/*
+ * List declarations.
+ */
+#define LIST_HEAD(name, type) \
+struct name { \
+ struct type *lh_first; /* first element */ \
+}
+
+#define LIST_CLASS_HEAD(name, type) \
+struct name { \
+ class type *lh_first; /* first element */ \
+}
+
+#define LIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define LIST_ENTRY(type) \
+struct { \
+ struct type *le_next; /* next element */ \
+ struct type **le_prev; /* address of previous next element */ \
+}
+
+#define LIST_CLASS_ENTRY(type) \
+struct { \
+ class type *le_next; /* next element */ \
+ class type **le_prev; /* address of previous next element */ \
+}
+
+/*
+ * List functions.
+ */
+
+#if (defined(_KERNEL) && defined(INVARIANTS))
+/*
+ * QMD_LIST_CHECK_HEAD(LIST_HEAD *head, LIST_ENTRY NAME)
+ *
+ * If the list is non-empty, validates that the first element of the list
+ * points back at 'head.'
+ */
+#define QMD_LIST_CHECK_HEAD(head, field) do { \
+ if (LIST_FIRST((head)) != NULL && \
+ LIST_FIRST((head))->field.le_prev != \
+ &LIST_FIRST((head))) \
+ panic("Bad list head %p first->prev != head", (head)); \
+} while (0)
+
+/*
+ * QMD_LIST_CHECK_NEXT(TYPE *elm, LIST_ENTRY NAME)
+ *
+ * If an element follows 'elm' in the list, validates that the next element
+ * points back at 'elm.'
+ */
+#define QMD_LIST_CHECK_NEXT(elm, field) do { \
+ if (LIST_NEXT((elm), field) != NULL && \
+ LIST_NEXT((elm), field)->field.le_prev != \
+ &((elm)->field.le_next)) \
+ panic("Bad link elm %p next->prev != elm", (elm)); \
+} while (0)
+
+/*
+ * QMD_LIST_CHECK_PREV(TYPE *elm, LIST_ENTRY NAME)
+ *
+ * Validates that the previous element (or head of the list) points to 'elm.'
+ */
+#define QMD_LIST_CHECK_PREV(elm, field) do { \
+ if (*(elm)->field.le_prev != (elm)) \
+ panic("Bad link elm %p prev->next != elm", (elm)); \
+} while (0)
+#else
+#define QMD_LIST_CHECK_HEAD(head, field)
+#define QMD_LIST_CHECK_NEXT(elm, field)
+#define QMD_LIST_CHECK_PREV(elm, field)
+#endif /* (_KERNEL && INVARIANTS) */
+
+#define LIST_CONCAT(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *curelm = LIST_FIRST(head1); \
+ if (curelm == NULL) { \
+ if ((LIST_FIRST(head1) = LIST_FIRST(head2)) != NULL) { \
+ LIST_FIRST(head2)->field.le_prev = \
+ &LIST_FIRST((head1)); \
+ LIST_INIT(head2); \
+ } \
+ } else if (LIST_FIRST(head2) != NULL) { \
+ while (LIST_NEXT(curelm, field) != NULL) \
+ curelm = LIST_NEXT(curelm, field); \
+ LIST_NEXT(curelm, field) = LIST_FIRST(head2); \
+ LIST_FIRST(head2)->field.le_prev = &LIST_NEXT(curelm, field); \
+ LIST_INIT(head2); \
+ } \
+} while (0)
+
+#define LIST_EMPTY(head) ((head)->lh_first == NULL)
+
+#define LIST_FIRST(head) ((head)->lh_first)
+
+#define LIST_FOREACH(var, head, field) \
+ for ((var) = LIST_FIRST((head)); \
+ (var); \
+ (var) = LIST_NEXT((var), field))
+
+#define LIST_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : LIST_FIRST((head))); \
+ (var); \
+ (var) = LIST_NEXT((var), field))
+
+#define LIST_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = LIST_FIRST((head)); \
+ (var) && ((tvar) = LIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define LIST_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : LIST_FIRST((head))); \
+ (var) && ((tvar) = LIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define LIST_INIT(head) do { \
+ LIST_FIRST((head)) = NULL; \
+} while (0)
+
+#define LIST_INSERT_AFTER(listelm, elm, field) do { \
+ QMD_LIST_CHECK_NEXT(listelm, field); \
+ if ((LIST_NEXT((elm), field) = LIST_NEXT((listelm), field)) != NULL)\
+ LIST_NEXT((listelm), field)->field.le_prev = \
+ &LIST_NEXT((elm), field); \
+ LIST_NEXT((listelm), field) = (elm); \
+ (elm)->field.le_prev = &LIST_NEXT((listelm), field); \
+} while (0)
+
+#define LIST_INSERT_BEFORE(listelm, elm, field) do { \
+ QMD_LIST_CHECK_PREV(listelm, field); \
+ (elm)->field.le_prev = (listelm)->field.le_prev; \
+ LIST_NEXT((elm), field) = (listelm); \
+ *(listelm)->field.le_prev = (elm); \
+ (listelm)->field.le_prev = &LIST_NEXT((elm), field); \
+} while (0)
+
+#define LIST_INSERT_HEAD(head, elm, field) do { \
+ QMD_LIST_CHECK_HEAD((head), field); \
+ if ((LIST_NEXT((elm), field) = LIST_FIRST((head))) != NULL) \
+ LIST_FIRST((head))->field.le_prev = &LIST_NEXT((elm), field);\
+ LIST_FIRST((head)) = (elm); \
+ (elm)->field.le_prev = &LIST_FIRST((head)); \
+} while (0)
+
+#define LIST_NEXT(elm, field) ((elm)->field.le_next)
+
+#define LIST_PREV(elm, head, type, field) \
+ ((elm)->field.le_prev == &LIST_FIRST((head)) ? NULL : \
+ __containerof((elm)->field.le_prev, \
+ QUEUE_TYPEOF(type), field.le_next))
+
+#define LIST_REMOVE(elm, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.le_next); \
+ QMD_SAVELINK(oldprev, (elm)->field.le_prev); \
+ QMD_LIST_CHECK_NEXT(elm, field); \
+ QMD_LIST_CHECK_PREV(elm, field); \
+ if (LIST_NEXT((elm), field) != NULL) \
+ LIST_NEXT((elm), field)->field.le_prev = \
+ (elm)->field.le_prev; \
+ *(elm)->field.le_prev = LIST_NEXT((elm), field); \
+ TRASHIT(*oldnext); \
+ TRASHIT(*oldprev); \
+} while (0)
+
+#define LIST_SWAP(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *swap_tmp = LIST_FIRST(head1); \
+ LIST_FIRST((head1)) = LIST_FIRST((head2)); \
+ LIST_FIRST((head2)) = swap_tmp; \
+ if ((swap_tmp = LIST_FIRST((head1))) != NULL) \
+ swap_tmp->field.le_prev = &LIST_FIRST((head1)); \
+ if ((swap_tmp = LIST_FIRST((head2))) != NULL) \
+ swap_tmp->field.le_prev = &LIST_FIRST((head2)); \
+} while (0)
+
/*
* Tail queue declarations.
*/
@@ -123,10 +619,58 @@ struct { \
/*
* Tail queue functions.
*/
+#if (defined(_KERNEL) && defined(INVARIANTS))
+/*
+ * QMD_TAILQ_CHECK_HEAD(TAILQ_HEAD *head, TAILQ_ENTRY NAME)
+ *
+ * If the tailq is non-empty, validates that the first element of the tailq
+ * points back at 'head.'
+ */
+#define QMD_TAILQ_CHECK_HEAD(head, field) do { \
+ if (!TAILQ_EMPTY(head) && \
+ TAILQ_FIRST((head))->field.tqe_prev != \
+ &TAILQ_FIRST((head))) \
+ panic("Bad tailq head %p first->prev != head", (head)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_TAIL(TAILQ_HEAD *head, TAILQ_ENTRY NAME)
+ *
+ * Validates that the tail of the tailq is a pointer to pointer to NULL.
+ */
+#define QMD_TAILQ_CHECK_TAIL(head, field) do { \
+ if (*(head)->tqh_last != NULL) \
+ panic("Bad tailq NEXT(%p->tqh_last) != NULL", (head)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_NEXT(TYPE *elm, TAILQ_ENTRY NAME)
+ *
+ * If an element follows 'elm' in the tailq, validates that the next element
+ * points back at 'elm.'
+ */
+#define QMD_TAILQ_CHECK_NEXT(elm, field) do { \
+ if (TAILQ_NEXT((elm), field) != NULL && \
+ TAILQ_NEXT((elm), field)->field.tqe_prev != \
+ &((elm)->field.tqe_next)) \
+ panic("Bad link elm %p next->prev != elm", (elm)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_PREV(TYPE *elm, TAILQ_ENTRY NAME)
+ *
+ * Validates that the previous element (or head of the tailq) points to 'elm.'
+ */
+#define QMD_TAILQ_CHECK_PREV(elm, field) do { \
+ if (*(elm)->field.tqe_prev != (elm)) \
+ panic("Bad link elm %p prev->next != elm", (elm)); \
+} while (0)
+#else
#define QMD_TAILQ_CHECK_HEAD(head, field)
#define QMD_TAILQ_CHECK_TAIL(head, headname)
#define QMD_TAILQ_CHECK_NEXT(elm, field)
#define QMD_TAILQ_CHECK_PREV(elm, field)
+#endif /* (_KERNEL && INVARIANTS) */
#define TAILQ_CONCAT(head1, head2, field) do { \
if (!TAILQ_EMPTY(head2)) { \
@@ -191,9 +735,8 @@ struct { \
#define TAILQ_INSERT_AFTER(head, listelm, elm, field) do { \
QMD_TAILQ_CHECK_NEXT(listelm, field); \
- TAILQ_NEXT((elm), field) = TAILQ_NEXT((listelm), field); \
- if (TAILQ_NEXT((listelm), field) != NULL) \
- TAILQ_NEXT((elm), field)->field.tqe_prev = \
+ if ((TAILQ_NEXT((elm), field) = TAILQ_NEXT((listelm), field)) != NULL)\
+ TAILQ_NEXT((elm), field)->field.tqe_prev = \
&TAILQ_NEXT((elm), field); \
else { \
(head)->tqh_last = &TAILQ_NEXT((elm), field); \
@@ -217,8 +760,7 @@ struct { \
#define TAILQ_INSERT_HEAD(head, elm, field) do { \
QMD_TAILQ_CHECK_HEAD(head, field); \
- TAILQ_NEXT((elm), field) = TAILQ_FIRST((head)); \
- if (TAILQ_FIRST((head)) != NULL) \
+ if ((TAILQ_NEXT((elm), field) = TAILQ_FIRST((head))) != NULL) \
TAILQ_FIRST((head))->field.tqe_prev = \
&TAILQ_NEXT((elm), field); \
else \
@@ -250,21 +792,24 @@ struct { \
* you may want to prefetch the last data element.
*/
#define TAILQ_LAST_FAST(head, type, field) \
- (TAILQ_EMPTY(head) ? NULL : __containerof((head)->tqh_last, \
- QUEUE_TYPEOF(type), field.tqe_next))
+ (TAILQ_EMPTY(head) ? NULL : __containerof((head)->tqh_last, QUEUE_TYPEOF(type), field.tqe_next))
#define TAILQ_NEXT(elm, field) ((elm)->field.tqe_next)
#define TAILQ_PREV(elm, headname, field) \
(*(((struct headname *)((elm)->field.tqe_prev))->tqh_last))
+#define TAILQ_PREV_FAST(elm, head, type, field) \
+ ((elm)->field.tqe_prev == &(head)->tqh_first ? NULL : \
+ __containerof((elm)->field.tqe_prev, QUEUE_TYPEOF(type), field.tqe_next))
+
#define TAILQ_REMOVE(head, elm, field) do { \
QMD_SAVELINK(oldnext, (elm)->field.tqe_next); \
QMD_SAVELINK(oldprev, (elm)->field.tqe_prev); \
QMD_TAILQ_CHECK_NEXT(elm, field); \
QMD_TAILQ_CHECK_PREV(elm, field); \
if ((TAILQ_NEXT((elm), field)) != NULL) \
- TAILQ_NEXT((elm), field)->field.tqe_prev = \
+ TAILQ_NEXT((elm), field)->field.tqe_prev = \
(elm)->field.tqe_prev; \
else { \
(head)->tqh_last = (elm)->field.tqe_prev; \
@@ -277,26 +822,20 @@ struct { \
} while (0)
#define TAILQ_SWAP(head1, head2, type, field) do { \
- QUEUE_TYPEOF(type) * swap_first = (head1)->tqh_first; \
- QUEUE_TYPEOF(type) * *swap_last = (head1)->tqh_last; \
+ QUEUE_TYPEOF(type) *swap_first = (head1)->tqh_first; \
+ QUEUE_TYPEOF(type) **swap_last = (head1)->tqh_last; \
(head1)->tqh_first = (head2)->tqh_first; \
(head1)->tqh_last = (head2)->tqh_last; \
(head2)->tqh_first = swap_first; \
(head2)->tqh_last = swap_last; \
- swap_first = (head1)->tqh_first; \
- if (swap_first != NULL) \
+ if ((swap_first = (head1)->tqh_first) != NULL) \
swap_first->field.tqe_prev = &(head1)->tqh_first; \
else \
(head1)->tqh_last = &(head1)->tqh_first; \
- swap_first = (head2)->tqh_first; \
- if (swap_first != NULL) \
+ if ((swap_first = (head2)->tqh_first) != NULL) \
swap_first->field.tqe_prev = &(head2)->tqh_first; \
else \
(head2)->tqh_last = &(head2)->tqh_first; \
} while (0)
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* _SYS_QUEUE_H_ */
+#endif /* !_SYS_QUEUE_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (8 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD Dmitry Kozlyuk
@ 2020-04-10 16:43 ` Dmitry Kozlyuk
2020-04-10 22:04 ` Narcisa Ana Maria Vasile
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 0/8] " Dmitry Kozlyuk
11 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-10 16:43 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Harini Ramakrishnan,
Omar Cardona, Pallavi Kadam, Ranjit Menon, John McNamara,
Marko Kovacevic, Anatoly Burakov, Bruce Richardson
Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 2 +-
doc/guides/windows_gsg/run_apps.rst | 30 +
lib/librte_eal/common/eal_common_fbarray.c | 57 +-
lib/librte_eal/common/eal_common_memory.c | 50 +-
lib/librte_eal/common/eal_private.h | 6 +-
lib/librte_eal/common/malloc_heap.c | 1 +
lib/librte_eal/common/meson.build | 9 +
lib/librte_eal/freebsd/eal_memory.c | 1 -
lib/librte_eal/meson.build | 1 +
lib/librte_eal/rte_eal_exports.def | 119 ++-
lib/librte_eal/windows/eal.c | 55 ++
lib/librte_eal/windows/eal_memalloc.c | 423 +++++++++++
lib/librte_eal/windows/eal_memory.c | 702 +++++++++++++++++-
lib/librte_eal/windows/eal_mp.c | 103 +++
lib/librte_eal/windows/eal_windows.h | 23 +
lib/librte_eal/windows/include/meson.build | 1 +
lib/librte_eal/windows/include/rte_os.h | 4 +
.../windows/include/rte_virt2phys.h | 34 +
lib/librte_eal/windows/include/rte_windows.h | 2 +
lib/librte_eal/windows/include/unistd.h | 3 +
lib/librte_eal/windows/meson.build | 2 +
21 files changed, 1561 insertions(+), 67 deletions(-)
create mode 100644 lib/librte_eal/windows/eal_memalloc.c
create mode 100644 lib/librte_eal/windows/eal_mp.c
create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
diff --git a/config/meson.build b/config/meson.build
index bceb5ef7b..7b8baa788 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -270,7 +270,7 @@ if is_windows
add_project_link_arguments('-lmincore', language: 'c')
endif
- add_project_link_arguments('-ladvapi32', language: 'c')
+ add_project_link_arguments('-ladvapi32', '-lsetupapi', language: 'c')
endif
if get_option('b_lto')
diff --git a/doc/guides/windows_gsg/run_apps.rst b/doc/guides/windows_gsg/run_apps.rst
index 21ac7f6c1..e858cf8c1 100644
--- a/doc/guides/windows_gsg/run_apps.rst
+++ b/doc/guides/windows_gsg/run_apps.rst
@@ -27,6 +27,36 @@ See `Large-Page Support`_ in MSDN for details.
.. _Large-page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
+Load virt2phys Driver
+---------------------
+
+Access to physical addresses is provided by a kernel-mode driver, virt2phys.
+It is mandatory at least for using hardware PMDs, but may also be required
+for mempools.
+
+This driver is not signed, so signature checking must be disabled to load it.
+Refer to documentation in ``dpdk-kmods`` repository for details on system
+setup, driver build and installation.
+
+Compiled package, consisting of ``virt2phys.inf``, ``virt2phys.cat``,
+and ``virt2phys.sys``, is installed as follows (from Elevated Command Line):
+
+.. code-block:: console
+
+ pnputil /add-driver virt2phys.inf /install
+
+When loaded successfully, the driver is shown in *Device Manager* as *Virtual
+to physical address translator* device under *Kernel bypass* category.
+
+If DPDK is unable to communicate with the driver, a warning is printed
+on initialization (debug-level logs provide more details):
+
+.. code-block:: text
+
+ EAL: Cannot open virt2phys driver interface
+
+
+
Run the ``helloworld`` Example
------------------------------
diff --git a/lib/librte_eal/common/eal_common_fbarray.c b/lib/librte_eal/common/eal_common_fbarray.c
index 1312f936b..236db9cb7 100644
--- a/lib/librte_eal/common/eal_common_fbarray.c
+++ b/lib/librte_eal/common/eal_common_fbarray.c
@@ -5,15 +5,15 @@
#include <fcntl.h>
#include <inttypes.h>
#include <limits.h>
-#include <sys/mman.h>
#include <stdint.h>
#include <errno.h>
-#include <sys/file.h>
#include <string.h>
+#include <unistd.h>
#include <rte_common.h>
-#include <rte_log.h>
#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
#include <rte_spinlock.h>
#include <rte_tailq.h>
@@ -85,19 +85,16 @@ resize_and_map(int fd, void *addr, size_t len)
char path[PATH_MAX];
void *map_addr;
- if (ftruncate(fd, len)) {
+ if (eal_file_truncate(fd, len)) {
RTE_LOG(ERR, EAL, "Cannot truncate %s\n", path);
/* pass errno up the chain */
rte_errno = errno;
return -1;
}
- map_addr = mmap(addr, len, PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_FIXED, fd, 0);
+ map_addr = rte_mem_map(addr, len, RTE_PROT_READ | RTE_PROT_WRITE,
+ RTE_MAP_SHARED | RTE_MAP_FIXED, fd, 0);
if (map_addr != addr) {
- RTE_LOG(ERR, EAL, "mmap() failed: %s\n", strerror(errno));
- /* pass errno up the chain */
- rte_errno = errno;
return -1;
}
return 0;
@@ -735,7 +732,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
return -1;
}
- page_sz = sysconf(_SC_PAGESIZE);
+ page_sz = rte_get_page_size();
if (page_sz == (size_t)-1) {
free(ma);
return -1;
@@ -756,9 +753,12 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
if (internal_config.no_shconf) {
/* remap virtual area as writable */
- void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, fd, 0);
- if (new_data == MAP_FAILED) {
+ void *new_data = rte_mem_map(
+ data, mmap_len,
+ RTE_PROT_READ | RTE_PROT_WRITE,
+ RTE_MAP_FIXED | RTE_MAP_PRIVATE | RTE_MAP_ANONYMOUS,
+ fd, 0);
+ if (new_data == NULL) {
RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
__func__, strerror(errno));
goto fail;
@@ -778,7 +778,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
__func__, path, strerror(errno));
rte_errno = errno;
goto fail;
- } else if (flock(fd, LOCK_EX | LOCK_NB)) {
+ } else if (eal_file_lock(
+ fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
__func__, path, strerror(errno));
rte_errno = EBUSY;
@@ -789,10 +790,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
* still attach to it, but no other process could reinitialize
* it.
*/
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -824,7 +823,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
return 0;
fail:
if (data)
- munmap(data, mmap_len);
+ rte_mem_unmap(data, mmap_len);
if (fd >= 0)
close(fd);
free(ma);
@@ -862,7 +861,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
return -1;
}
- page_sz = sysconf(_SC_PAGESIZE);
+ page_sz = rte_get_page_size();
if (page_sz == (size_t)-1) {
free(ma);
return -1;
@@ -895,10 +894,8 @@ rte_fbarray_attach(struct rte_fbarray *arr)
}
/* lock the file, to let others know we're using it */
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -916,7 +913,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
return 0;
fail:
if (data)
- munmap(data, mmap_len);
+ rte_mem_unmap(data, mmap_len);
if (fd >= 0)
close(fd);
free(ma);
@@ -944,8 +941,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
* really do anything about it, things will blow up either way.
*/
- size_t page_sz = sysconf(_SC_PAGESIZE);
-
+ size_t page_sz = rte_get_page_size();
if (page_sz == (size_t)-1)
return -1;
@@ -964,7 +960,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
goto out;
}
- munmap(arr->data, mmap_len);
+ rte_mem_unmap(arr->data, mmap_len);
/* area is unmapped, close fd and remove the tailq entry */
if (tmp->fd >= 0)
@@ -999,8 +995,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* really do anything about it, things will blow up either way.
*/
- size_t page_sz = sysconf(_SC_PAGESIZE);
-
+ size_t page_sz = rte_get_page_size();
if (page_sz == (size_t)-1)
return -1;
@@ -1025,7 +1020,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* has been detached by all other processes
*/
fd = tmp->fd;
- if (flock(fd, LOCK_EX | LOCK_NB)) {
+ if (eal_file_lock(fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "Cannot destroy fbarray - another process is using it\n");
rte_errno = EBUSY;
ret = -1;
@@ -1042,14 +1037,14 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* we're still holding an exclusive lock, so drop it to
* shared.
*/
- flock(fd, LOCK_SH | LOCK_NB);
+ eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN);
ret = -1;
goto out;
}
close(fd);
}
- munmap(arr->data, mmap_len);
+ rte_mem_unmap(arr->data, mmap_len);
/* area is unmapped, remove the tailq entry */
TAILQ_REMOVE(&mem_area_tailq, tmp, next);
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index d9764681a..5c3cf1f75 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -11,7 +11,6 @@
#include <string.h>
#include <unistd.h>
#include <inttypes.h>
-#include <sys/mman.h>
#include <sys/queue.h>
#include <rte_fbarray.h>
@@ -44,7 +43,7 @@ static uint64_t system_page_sz;
#define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
void *
eal_get_virtual_area(void *requested_addr, size_t *size,
- size_t page_sz, int flags, int mmap_flags)
+ size_t page_sz, int flags, enum eal_mem_reserve_flags reserve_flags)
{
bool addr_is_hint, allow_shrink, unmap, no_align;
uint64_t map_sz;
@@ -52,9 +51,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
uint8_t try = 0;
if (system_page_sz == 0)
- system_page_sz = sysconf(_SC_PAGESIZE);
-
- mmap_flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+ system_page_sz = rte_get_page_size();
RTE_LOG(DEBUG, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
@@ -98,24 +95,24 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
return NULL;
}
- mapped_addr = mmap(requested_addr, (size_t)map_sz, PROT_NONE,
- mmap_flags, -1, 0);
- if (mapped_addr == MAP_FAILED && allow_shrink)
- *size -= page_sz;
+ mapped_addr = eal_mem_reserve(
+ requested_addr, (size_t)map_sz, reserve_flags);
+ if ((mapped_addr == NULL) && allow_shrink)
+ size -= page_sz;
- if (mapped_addr != MAP_FAILED && addr_is_hint &&
- mapped_addr != requested_addr) {
+ if ((mapped_addr != NULL) && addr_is_hint &&
+ (mapped_addr != requested_addr)) {
try++;
next_baseaddr = RTE_PTR_ADD(next_baseaddr, page_sz);
if (try <= MAX_MMAP_WITH_DEFINED_ADDR_TRIES) {
/* hint was not used. Try with another offset */
- munmap(mapped_addr, map_sz);
- mapped_addr = MAP_FAILED;
+ eal_mem_free(mapped_addr, *size);
+ mapped_addr = NULL;
requested_addr = next_baseaddr;
}
}
} while ((allow_shrink || addr_is_hint) &&
- mapped_addr == MAP_FAILED && *size > 0);
+ (mapped_addr == NULL) && (*size > 0));
/* align resulting address - if map failed, we will ignore the value
* anyway, so no need to add additional checks.
@@ -125,20 +122,17 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
if (*size == 0) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area of any size: %s\n",
- strerror(errno));
- rte_errno = errno;
+ strerror(rte_errno));
return NULL;
- } else if (mapped_addr == MAP_FAILED) {
+ } else if (mapped_addr == NULL) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area: %s\n",
- strerror(errno));
- /* pass errno up the call chain */
- rte_errno = errno;
+ strerror(rte_errno));
return NULL;
} else if (requested_addr != NULL && !addr_is_hint &&
aligned_addr != requested_addr) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area at requested address: %p (got %p)\n",
requested_addr, aligned_addr);
- munmap(mapped_addr, map_sz);
+ eal_mem_free(mapped_addr, map_sz);
rte_errno = EADDRNOTAVAIL;
return NULL;
} else if (requested_addr != NULL && addr_is_hint &&
@@ -154,7 +148,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
aligned_addr, *size);
if (unmap) {
- munmap(mapped_addr, map_sz);
+ eal_mem_free(mapped_addr, map_sz);
} else if (!no_align) {
void *map_end, *aligned_end;
size_t before_len, after_len;
@@ -172,12 +166,12 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
/* unmap space before aligned mmap address */
before_len = RTE_PTR_DIFF(aligned_addr, mapped_addr);
if (before_len > 0)
- munmap(mapped_addr, before_len);
+ eal_mem_free(mapped_addr, before_len);
/* unmap space after aligned end mmap address */
after_len = RTE_PTR_DIFF(map_end, aligned_end);
if (after_len > 0)
- munmap(aligned_end, after_len);
+ eal_mem_free(aligned_end, after_len);
}
return aligned_addr;
@@ -586,10 +580,10 @@ rte_eal_memdevice_init(void)
int
rte_mem_lock_page(const void *virt)
{
- unsigned long virtual = (unsigned long)virt;
- int page_size = getpagesize();
- unsigned long aligned = (virtual & ~(page_size - 1));
- return mlock((void *)aligned, page_size);
+ uintptr_t virtual = (uintptr_t)virt;
+ int page_size = rte_get_page_size();
+ uintptr_t aligned = (virtual & ~(page_size - 1));
+ return rte_mem_lock((void *)aligned, page_size);
}
int
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 76938e379..59ac41916 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -226,8 +226,8 @@ enum eal_mem_reserve_flags {
* Page size on which to align requested virtual area.
* @param flags
* EAL_VIRTUAL_AREA_* flags.
- * @param mmap_flags
- * Extra flags passed directly to mmap().
+ * @param reserve_flags
+ * Extra flags passed directly to rte_mem_reserve().
*
* @return
* Virtual area address if successful.
@@ -244,7 +244,7 @@ enum eal_mem_reserve_flags {
/**< immediately unmap reserved virtual area. */
void *
eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
- int flags, int mmap_flags);
+ int flags, enum eal_mem_reserve_flags reserve_flags);
/**
* Reserve VA space for a memory segment list.
diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
index 842eb9de7..6534c895c 100644
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -729,6 +729,7 @@ malloc_heap_alloc(const char *type, size_t size, int socket_arg,
if (ret != NULL)
return ret;
}
+
return NULL;
}
diff --git a/lib/librte_eal/common/meson.build b/lib/librte_eal/common/meson.build
index 02d9280cc..6dcdcc890 100644
--- a/lib/librte_eal/common/meson.build
+++ b/lib/librte_eal/common/meson.build
@@ -9,11 +9,20 @@ if is_windows
'eal_common_class.c',
'eal_common_devargs.c',
'eal_common_errno.c',
+ 'eal_common_fbarray.c',
'eal_common_launch.c',
'eal_common_lcore.c',
'eal_common_log.c',
+ 'eal_common_mcfg.c',
+ 'eal_common_memalloc.c',
+ 'eal_common_memory.c',
+ 'eal_common_memzone.c',
'eal_common_options.c',
+ 'eal_common_tailqs.c',
'eal_common_thread.c',
+ 'malloc_elem.c',
+ 'malloc_heap.c',
+ 'rte_malloc.c',
'rte_option.c',
)
subdir_done()
diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
index 5174f9cd0..99bf6ec9e 100644
--- a/lib/librte_eal/freebsd/eal_memory.c
+++ b/lib/librte_eal/freebsd/eal_memory.c
@@ -355,7 +355,6 @@ memseg_list_reserve(struct rte_memseg_list *msl)
return eal_reserve_memseg_list(msl, flags);
}
-
static int
memseg_primary_init(void)
{
diff --git a/lib/librte_eal/meson.build b/lib/librte_eal/meson.build
index 1f89efb88..1d750f003 100644
--- a/lib/librte_eal/meson.build
+++ b/lib/librte_eal/meson.build
@@ -11,6 +11,7 @@ if not is_windows
endif
dpdk_conf.set('RTE_EXEC_ENV_' + exec_env.to_upper(), 1)
+dpdk_conf.set10('RTE_EAL_NUMA_AWARE_HUGEPAGES', true)
subdir(exec_env)
subdir(arch_subdir)
diff --git a/lib/librte_eal/rte_eal_exports.def b/lib/librte_eal/rte_eal_exports.def
index bacf9a107..854b83bcd 100644
--- a/lib/librte_eal/rte_eal_exports.def
+++ b/lib/librte_eal/rte_eal_exports.def
@@ -1,13 +1,128 @@
EXPORTS
__rte_panic
+ rte_calloc
+ rte_calloc_socket
rte_eal_get_configuration
+ rte_eal_has_hugepages
rte_eal_init
+ rte_eal_iova_mode
rte_eal_mp_remote_launch
rte_eal_mp_wait_lcore
+ rte_eal_process_type
rte_eal_remote_launch
- rte_get_page_size
+ rte_eal_tailq_lookup
+ rte_eal_tailq_register
+ rte_eal_using_phys_addrs
+ rte_free
rte_log
+ rte_malloc
+ rte_malloc_dump_stats
+ rte_malloc_get_socket_stats
+ rte_malloc_set_limit
+ rte_malloc_socket
+ rte_malloc_validate
+ rte_malloc_virt2iova
+ rte_mcfg_mem_read_lock
+ rte_mcfg_mem_read_unlock
+ rte_mcfg_mem_write_lock
+ rte_mcfg_mem_write_unlock
+ rte_mcfg_mempool_read_lock
+ rte_mcfg_mempool_read_unlock
+ rte_mcfg_mempool_write_lock
+ rte_mcfg_mempool_write_unlock
+ rte_mcfg_tailq_read_lock
+ rte_mcfg_tailq_read_unlock
+ rte_mcfg_tailq_write_lock
+ rte_mcfg_tailq_write_unlock
+ rte_mem_lock_page
+ rte_mem_virt2iova
+ rte_mem_virt2phy
+ rte_memory_get_nchannel
+ rte_memory_get_nrank
+ rte_memzone_dump
+ rte_memzone_free
+ rte_memzone_lookup
+ rte_memzone_reserve
+ rte_memzone_reserve_aligned
+ rte_memzone_reserve_bounded
+ rte_memzone_walk
+ rte_vlog
+ rte_realloc
+ rte_zmalloc
+ rte_zmalloc_socket
+
+ rte_mp_action_register
+ rte_mp_action_unregister
+ rte_mp_reply
+ rte_mp_sendmsg
+
+ rte_fbarray_attach
+ rte_fbarray_destroy
+ rte_fbarray_detach
+ rte_fbarray_dump_metadata
+ rte_fbarray_find_contig_free
+ rte_fbarray_find_contig_used
+ rte_fbarray_find_idx
+ rte_fbarray_find_next_free
+ rte_fbarray_find_next_n_free
+ rte_fbarray_find_next_n_used
+ rte_fbarray_find_next_used
+ rte_fbarray_get
+ rte_fbarray_init
+ rte_fbarray_is_used
+ rte_fbarray_set_free
+ rte_fbarray_set_used
+ rte_malloc_dump_heaps
+ rte_mem_alloc_validator_register
+ rte_mem_alloc_validator_unregister
+ rte_mem_check_dma_mask
+ rte_mem_event_callback_register
+ rte_mem_event_callback_unregister
+ rte_mem_iova2virt
+ rte_mem_virt2memseg
+ rte_mem_virt2memseg_list
+ rte_memseg_contig_walk
+ rte_memseg_list_walk
+ rte_memseg_walk
+ rte_mp_request_async
+ rte_mp_request_sync
+
+ rte_fbarray_find_prev_free
+ rte_fbarray_find_prev_n_free
+ rte_fbarray_find_prev_n_used
+ rte_fbarray_find_prev_used
+ rte_fbarray_find_rev_contig_free
+ rte_fbarray_find_rev_contig_used
+ rte_memseg_contig_walk_thread_unsafe
+ rte_memseg_list_walk_thread_unsafe
+ rte_memseg_walk_thread_unsafe
+
+ rte_malloc_heap_create
+ rte_malloc_heap_destroy
+ rte_malloc_heap_get_socket
+ rte_malloc_heap_memory_add
+ rte_malloc_heap_memory_attach
+ rte_malloc_heap_memory_detach
+ rte_malloc_heap_memory_remove
+ rte_malloc_heap_socket_is_external
+ rte_mem_check_dma_mask_thread_unsafe
+ rte_mem_set_dma_mask
+ rte_memseg_get_fd
+ rte_memseg_get_fd_offset
+ rte_memseg_get_fd_offset_thread_unsafe
+ rte_memseg_get_fd_thread_unsafe
+
+ rte_extmem_attach
+ rte_extmem_detach
+ rte_extmem_register
+ rte_extmem_unregister
+
+ rte_fbarray_find_biggest_free
+ rte_fbarray_find_biggest_used
+ rte_fbarray_find_rev_biggest_free
+ rte_fbarray_find_rev_biggest_used
+
+ rte_get_page_size
rte_mem_lock
rte_mem_map
rte_mem_unmap
- rte_vlog
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index cf55b56da..38f17f09c 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -93,6 +93,24 @@ eal_proc_type_detect(void)
return ptype;
}
+enum rte_proc_type_t
+rte_eal_process_type(void)
+{
+ return rte_config.process_type;
+}
+
+int
+rte_eal_has_hugepages(void)
+{
+ return !internal_config.no_hugetlbfs;
+}
+
+enum rte_iova_mode
+rte_eal_iova_mode(void)
+{
+ return rte_config.iova_mode;
+}
+
/* display usage */
static void
eal_usage(const char *prgname)
@@ -328,6 +346,13 @@ rte_eal_init(int argc, char **argv)
if (fctret < 0)
exit(1);
+ /* Prevent creation of shared memory files. */
+ if (internal_config.no_shconf == 0) {
+ RTE_LOG(WARNING, EAL, "Multi-process support is requested, "
+ "but not available.\n");
+ internal_config.no_shconf = 1;
+ }
+
if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
rte_eal_init_alert("Cannot get hugepage information");
rte_errno = EACCES;
@@ -345,6 +370,36 @@ rte_eal_init(int argc, char **argv)
return -1;
}
+ if (eal_mem_virt2iova_init() < 0) {
+ /* Non-fatal error if physical addresses are not required. */
+ RTE_LOG(WARNING, EAL, "Cannot access virt2phys driver, "
+ "PA will not be available\n");
+ }
+
+ if (rte_eal_memzone_init() < 0) {
+ rte_eal_init_alert("Cannot init memzone");
+ rte_errno = ENODEV;
+ return -1;
+ }
+
+ if (rte_eal_memory_init() < 0) {
+ rte_eal_init_alert("Cannot init memory");
+ rte_errno = ENOMEM;
+ return -1;
+ }
+
+ if (rte_eal_malloc_heap_init() < 0) {
+ rte_eal_init_alert("Cannot init malloc heap");
+ rte_errno = ENODEV;
+ return -1;
+ }
+
+ if (rte_eal_tailqs_init() < 0) {
+ rte_eal_init_alert("Cannot init tail queues for objects");
+ rte_errno = EFAULT;
+ return -1;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_memalloc.c b/lib/librte_eal/windows/eal_memalloc.c
new file mode 100644
index 000000000..c7c3cf8df
--- /dev/null
+++ b/lib/librte_eal/windows/eal_memalloc.c
@@ -0,0 +1,423 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#include <rte_errno.h>
+#include <rte_os.h>
+#include <rte_windows.h>
+
+#include "eal_internal_cfg.h"
+#include "eal_memalloc.h"
+#include "eal_memcfg.h"
+#include "eal_private.h"
+#include "eal_windows.h"
+
+int
+eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
+{
+ /* Hugepages have no assiciated files in Windows. */
+ RTE_SET_USED(list_idx);
+ RTE_SET_USED(seg_idx);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+eal_memalloc_get_seg_fd_offset(int list_idx, int seg_idx, size_t *offset)
+{
+ /* Hugepages have no assiciated files in Windows. */
+ RTE_SET_USED(list_idx);
+ RTE_SET_USED(seg_idx);
+ RTE_SET_USED(offset);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+static int
+alloc_seg(struct rte_memseg *ms, void *requested_addr, int socket_id,
+ struct hugepage_info *hi)
+{
+ HANDLE current_process;
+ unsigned int numa_node;
+ size_t alloc_sz;
+ void *addr;
+ rte_iova_t iova = RTE_BAD_IOVA;
+ PSAPI_WORKING_SET_EX_INFORMATION info;
+ PSAPI_WORKING_SET_EX_BLOCK *page;
+
+ if (ms->len > 0) {
+ /* If a segment is already allocated as needed, return it. */
+ if ((ms->addr == requested_addr) &&
+ (ms->socket_id == socket_id) &&
+ (ms->hugepage_sz == hi->hugepage_sz)) {
+ return 0;
+ }
+
+ /* Bugcheck, should not happen. */
+ RTE_LOG(DEBUG, EAL, "Attempted to reallocate segment %p "
+ "(size %zu) on socket %d", ms->addr,
+ ms->len, ms->socket_id);
+ return -1;
+ }
+
+ current_process = GetCurrentProcess();
+ numa_node = eal_socket_numa_node(socket_id);
+ alloc_sz = hi->hugepage_sz;
+
+ if (requested_addr == NULL) {
+ /* Request a new chunk of memory and enforce address hint. */
+ addr = eal_mem_alloc_socket(alloc_sz, socket_id);
+ if (addr == NULL) {
+ RTE_LOG(DEBUG, EAL, "Cannot allocate %zu bytes "
+ "on socket %d\n", alloc_sz, socket_id);
+ return -1;
+ }
+
+ if (addr != requested_addr) {
+ RTE_LOG(DEBUG, EAL, "Address hint %p not respected, "
+ "got %p\n", requested_addr, addr);
+ goto error;
+ }
+ } else {
+ /* Requested address is already reserved, commit memory. */
+ addr = eal_mem_commit(requested_addr, alloc_sz, socket_id);
+ if (addr == NULL) {
+ RTE_LOG(DEBUG, EAL, "Cannot commit reserved memory %p "
+ "(size %zu)\n", requested_addr, alloc_sz);
+ goto error;
+ }
+ }
+
+ /* Force OS to allocate a physical page and select a NUMA node.
+ * Hugepages are not pageable in Windows, so there's no race
+ * for physical address.
+ */
+ *(volatile int *)addr = *(volatile int *)addr;
+
+ /* Only try to obtain IOVA if it's available, so that applications
+ * that do not need IOVA can use this allocator.
+ */
+ if (rte_eal_using_phys_addrs()) {
+ iova = rte_mem_virt2iova(addr);
+ if (iova == RTE_BAD_IOVA) {
+ RTE_LOG(DEBUG, EAL,
+ "Cannot get IOVA of allocated segment\n");
+ goto error;
+ }
+ }
+
+ /* Only "Ex" function can handle hugepages. */
+ info.VirtualAddress = addr;
+ if (!QueryWorkingSetEx(current_process, &info, sizeof(info))) {
+ RTE_LOG_WIN32_ERR("QueryWorkingSetEx()");
+ goto error;
+ }
+
+ page = &info.VirtualAttributes;
+ if (!page->Valid || !page->LargePage) {
+ RTE_LOG(DEBUG, EAL, "Got regular page instead of hugepage\n");
+ goto error;
+ }
+ if (page->Node != numa_node) {
+ RTE_LOG(DEBUG, EAL,
+ "NUMA node hint %u (socket %d) not respected, got %u\n",
+ numa_node, socket_id, page->Node);
+ goto error;
+ }
+
+ ms->addr = addr;
+ ms->hugepage_sz = hi->hugepage_sz;
+ ms->len = alloc_sz;
+ ms->nchannel = rte_memory_get_nchannel();
+ ms->nrank = rte_memory_get_nrank();
+ ms->iova = iova;
+ ms->socket_id = socket_id;
+
+ return 0;
+
+error:
+ /* Only jump here when `addr` and `alloc_sz` are valid. */
+ eal_mem_decommit(addr, alloc_sz);
+ return -1;
+}
+
+static int
+free_seg(struct rte_memseg *ms)
+{
+ if (eal_mem_decommit(ms->addr, ms->len))
+ return -1;
+
+ /* Must clear the segment, because alloc_seg() inspects it. */
+ memset(ms, 0, sizeof(*ms));
+ return 0;
+}
+
+struct alloc_walk_param {
+ struct hugepage_info *hi;
+ struct rte_memseg **ms;
+ size_t page_sz;
+ unsigned int segs_allocated;
+ unsigned int n_segs;
+ int socket;
+ bool exact;
+};
+
+static int
+alloc_seg_walk(const struct rte_memseg_list *msl, void *arg)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct alloc_walk_param *wa = arg;
+ struct rte_memseg_list *cur_msl;
+ size_t page_sz;
+ int cur_idx, start_idx, j;
+ unsigned int msl_idx, need, i;
+
+ if (msl->page_sz != wa->page_sz)
+ return 0;
+ if (msl->socket_id != wa->socket)
+ return 0;
+
+ page_sz = (size_t)msl->page_sz;
+
+ msl_idx = msl - mcfg->memsegs;
+ cur_msl = &mcfg->memsegs[msl_idx];
+
+ need = wa->n_segs;
+
+ /* try finding space in memseg list */
+ if (wa->exact) {
+ /* if we require exact number of pages in a list, find them */
+ cur_idx = rte_fbarray_find_next_n_free(
+ &cur_msl->memseg_arr, 0, need);
+ if (cur_idx < 0)
+ return 0;
+ start_idx = cur_idx;
+ } else {
+ int cur_len;
+
+ /* we don't require exact number of pages, so we're going to go
+ * for best-effort allocation. that means finding the biggest
+ * unused block, and going with that.
+ */
+ cur_idx = rte_fbarray_find_biggest_free(
+ &cur_msl->memseg_arr, 0);
+ if (cur_idx < 0)
+ return 0;
+ start_idx = cur_idx;
+ /* adjust the size to possibly be smaller than original
+ * request, but do not allow it to be bigger.
+ */
+ cur_len = rte_fbarray_find_contig_free(
+ &cur_msl->memseg_arr, cur_idx);
+ need = RTE_MIN(need, (unsigned int)cur_len);
+ }
+
+ for (i = 0; i < need; i++, cur_idx++) {
+ struct rte_memseg *cur;
+ void *map_addr;
+
+ cur = rte_fbarray_get(&cur_msl->memseg_arr, cur_idx);
+ map_addr = RTE_PTR_ADD(cur_msl->base_va, cur_idx * page_sz);
+
+ if (alloc_seg(cur, map_addr, wa->socket, wa->hi)) {
+ RTE_LOG(DEBUG, EAL, "attempted to allocate %i segments, "
+ "but only %i were allocated\n", need, i);
+
+ /* if exact number wasn't requested, stop */
+ if (!wa->exact)
+ goto out;
+
+ /* clean up */
+ for (j = start_idx; j < cur_idx; j++) {
+ struct rte_memseg *tmp;
+ struct rte_fbarray *arr = &cur_msl->memseg_arr;
+
+ tmp = rte_fbarray_get(arr, j);
+ rte_fbarray_set_free(arr, j);
+
+ if (free_seg(tmp))
+ RTE_LOG(DEBUG, EAL, "Cannot free page\n");
+ }
+ /* clear the list */
+ if (wa->ms)
+ memset(wa->ms, 0, sizeof(*wa->ms) * wa->n_segs);
+
+ return -1;
+ }
+ if (wa->ms)
+ wa->ms[i] = cur;
+
+ rte_fbarray_set_used(&cur_msl->memseg_arr, cur_idx);
+ }
+
+out:
+ wa->segs_allocated = i;
+ if (i > 0)
+ cur_msl->version++;
+
+ /* if we didn't allocate any segments, move on to the next list */
+ return i > 0;
+}
+
+struct free_walk_param {
+ struct hugepage_info *hi;
+ struct rte_memseg *ms;
+};
+static int
+free_seg_walk(const struct rte_memseg_list *msl, void *arg)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct rte_memseg_list *found_msl;
+ struct free_walk_param *wa = arg;
+ uintptr_t start_addr, end_addr;
+ int msl_idx, seg_idx, ret;
+
+ start_addr = (uintptr_t) msl->base_va;
+ end_addr = start_addr + msl->len;
+
+ if ((uintptr_t)wa->ms->addr < start_addr ||
+ (uintptr_t)wa->ms->addr >= end_addr)
+ return 0;
+
+ msl_idx = msl - mcfg->memsegs;
+ seg_idx = RTE_PTR_DIFF(wa->ms->addr, start_addr) / msl->page_sz;
+
+ /* msl is const */
+ found_msl = &mcfg->memsegs[msl_idx];
+ found_msl->version++;
+
+ rte_fbarray_set_free(&found_msl->memseg_arr, seg_idx);
+
+ ret = free_seg(wa->ms);
+
+ return (ret < 0) ? (-1) : 1;
+}
+
+int
+eal_memalloc_alloc_seg_bulk(struct rte_memseg **ms, int n_segs,
+ size_t page_sz, int socket, bool exact)
+{
+ unsigned int i;
+ int ret = -1;
+ struct alloc_walk_param wa;
+ struct hugepage_info *hi = NULL;
+
+ if (internal_config.legacy_mem) {
+ RTE_LOG(ERR, EAL, "dynamic allocation not supported in legacy mode\n");
+ return -ENOTSUP;
+ }
+
+ for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
+ struct hugepage_info *hpi = &internal_config.hugepage_info[i];
+ if (page_sz == hpi->hugepage_sz) {
+ hi = hpi;
+ break;
+ }
+ }
+ if (!hi) {
+ RTE_LOG(ERR, EAL, "cannot find relevant hugepage_info entry\n");
+ return -1;
+ }
+
+ memset(&wa, 0, sizeof(wa));
+ wa.exact = exact;
+ wa.hi = hi;
+ wa.ms = ms;
+ wa.n_segs = n_segs;
+ wa.page_sz = page_sz;
+ wa.socket = socket;
+ wa.segs_allocated = 0;
+
+ /* memalloc is locked, so it's safe to use thread-unsafe version */
+ ret = rte_memseg_list_walk_thread_unsafe(alloc_seg_walk, &wa);
+ if (ret == 0) {
+ RTE_LOG(ERR, EAL, "cannot find suitable memseg_list\n");
+ ret = -1;
+ } else if (ret > 0) {
+ ret = (int)wa.segs_allocated;
+ }
+
+ return ret;
+}
+
+struct rte_memseg *
+eal_memalloc_alloc_seg(size_t page_sz, int socket)
+{
+ struct rte_memseg *ms = NULL;
+ eal_memalloc_alloc_seg_bulk(&ms, 1, page_sz, socket, true);
+ return ms;
+}
+
+int
+eal_memalloc_free_seg_bulk(struct rte_memseg **ms, int n_segs)
+{
+ int seg, ret = 0;
+
+ /* dynamic free not supported in legacy mode */
+ if (internal_config.legacy_mem)
+ return -1;
+
+ for (seg = 0; seg < n_segs; seg++) {
+ struct rte_memseg *cur = ms[seg];
+ struct hugepage_info *hi = NULL;
+ struct free_walk_param wa;
+ size_t i;
+ int walk_res;
+
+ /* if this page is marked as unfreeable, fail */
+ if (cur->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
+ RTE_LOG(DEBUG, EAL, "Page is not allowed to be freed\n");
+ ret = -1;
+ continue;
+ }
+
+ memset(&wa, 0, sizeof(wa));
+
+ for (i = 0; i < RTE_DIM(internal_config.hugepage_info);
+ i++) {
+ hi = &internal_config.hugepage_info[i];
+ if (cur->hugepage_sz == hi->hugepage_sz)
+ break;
+ }
+ if (i == RTE_DIM(internal_config.hugepage_info)) {
+ RTE_LOG(ERR, EAL, "Can't find relevant hugepage_info entry\n");
+ ret = -1;
+ continue;
+ }
+
+ wa.ms = cur;
+ wa.hi = hi;
+
+ /* memalloc is locked, so it's safe to use thread-unsafe version
+ */
+ walk_res = rte_memseg_list_walk_thread_unsafe(free_seg_walk,
+ &wa);
+ if (walk_res == 1)
+ continue;
+ if (walk_res == 0)
+ RTE_LOG(ERR, EAL, "Couldn't find memseg list\n");
+ ret = -1;
+ }
+ return ret;
+}
+
+int
+eal_memalloc_free_seg(struct rte_memseg *ms)
+{
+ return eal_memalloc_free_seg_bulk(&ms, 1);
+}
+
+int
+eal_memalloc_sync_with_primary(void)
+{
+ /* No multi-process support. */
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+eal_memalloc_init(void)
+{
+ /* No action required. */
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
index 59606d84c..a9a35b7dc 100644
--- a/lib/librte_eal/windows/eal_memory.c
+++ b/lib/librte_eal/windows/eal_memory.c
@@ -1,11 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2010-2014 Intel Corporation (functions from Linux EAL)
+ * Copyright (c) 2020 Dmitry Kozlyuk (Windows specifics)
+ */
+
+#include <inttypes.h>
#include <io.h>
#include <rte_errno.h>
#include <rte_memory.h>
+#include "eal_internal_cfg.h"
+#include "eal_memalloc.h"
+#include "eal_memcfg.h"
+#include "eal_options.h"
#include "eal_private.h"
#include "eal_windows.h"
+#include <rte_virt2phys.h>
+
/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
* Provide a copy of definitions and code to load it dynamically.
* Note: definitions are copied verbatim from Microsoft documentation
@@ -120,6 +132,119 @@ eal_mem_win32api_init(void)
#endif /* no VirtualAlloc2() */
+static HANDLE virt2phys_device = INVALID_HANDLE_VALUE;
+
+int
+eal_mem_virt2iova_init(void)
+{
+ HDEVINFO list = INVALID_HANDLE_VALUE;
+ SP_DEVICE_INTERFACE_DATA ifdata;
+ SP_DEVICE_INTERFACE_DETAIL_DATA *detail = NULL;
+ DWORD detail_size;
+ int ret = -1;
+
+ list = SetupDiGetClassDevs(
+ &GUID_DEVINTERFACE_VIRT2PHYS, NULL, NULL,
+ DIGCF_DEVICEINTERFACE | DIGCF_PRESENT);
+ if (list == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("SetupDiGetClassDevs()");
+ goto exit;
+ }
+
+ ifdata.cbSize = sizeof(ifdata);
+ if (!SetupDiEnumDeviceInterfaces(
+ list, NULL, &GUID_DEVINTERFACE_VIRT2PHYS, 0, &ifdata)) {
+ RTE_LOG_WIN32_ERR("SetupDiEnumDeviceInterfaces()");
+ goto exit;
+ }
+
+ if (!SetupDiGetDeviceInterfaceDetail(
+ list, &ifdata, NULL, 0, &detail_size, NULL)) {
+ if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
+ RTE_LOG_WIN32_ERR(
+ "SetupDiGetDeviceInterfaceDetail(probe)");
+ goto exit;
+ }
+ }
+
+ detail = malloc(detail_size);
+ if (detail == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate virt2phys "
+ "device interface detail data\n");
+ goto exit;
+ }
+
+ detail->cbSize = sizeof(*detail);
+ if (!SetupDiGetDeviceInterfaceDetail(
+ list, &ifdata, detail, detail_size, NULL, NULL)) {
+ RTE_LOG_WIN32_ERR("SetupDiGetDeviceInterfaceDetail(read)");
+ goto exit;
+ }
+
+ RTE_LOG(DEBUG, EAL, "Found virt2phys device: %s\n", detail->DevicePath);
+
+ virt2phys_device = CreateFile(
+ detail->DevicePath, 0, 0, NULL, OPEN_EXISTING, 0, NULL);
+ if (virt2phys_device == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("CreateFile()");
+ goto exit;
+ }
+
+ /* Indicate success. */
+ ret = 0;
+
+exit:
+ if (detail != NULL)
+ free(detail);
+ if (list != INVALID_HANDLE_VALUE)
+ SetupDiDestroyDeviceInfoList(list);
+
+ return ret;
+}
+
+phys_addr_t
+rte_mem_virt2phy(const void *virt)
+{
+ LARGE_INTEGER phys;
+ DWORD bytes_returned;
+
+ if (virt2phys_device == INVALID_HANDLE_VALUE)
+ return RTE_BAD_PHYS_ADDR;
+
+ if (!DeviceIoControl(
+ virt2phys_device, IOCTL_VIRT2PHYS_TRANSLATE,
+ &virt, sizeof(virt), &phys, sizeof(phys),
+ &bytes_returned, NULL)) {
+ RTE_LOG_WIN32_ERR("DeviceIoControl(IOCTL_VIRT2PHYS_TRANSLATE)");
+ return RTE_BAD_PHYS_ADDR;
+ }
+
+ return phys.QuadPart;
+}
+
+/* Windows currently only supports IOVA as PA. */
+rte_iova_t
+rte_mem_virt2iova(const void *virt)
+{
+ phys_addr_t phys;
+
+ if (virt2phys_device == INVALID_HANDLE_VALUE)
+ return RTE_BAD_IOVA;
+
+ phys = rte_mem_virt2phy(virt);
+ if (phys == RTE_BAD_PHYS_ADDR)
+ return RTE_BAD_IOVA;
+
+ return (rte_iova_t)phys;
+}
+
+/* Always using physical addresses under Windows if they can be obtained. */
+int
+rte_eal_using_phys_addrs(void)
+{
+ return virt2phys_device != INVALID_HANDLE_VALUE;
+}
+
/* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
static int
win32_alloc_error_to_errno(DWORD code)
@@ -360,7 +485,7 @@ rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
return NULL;
}
- /* TODO: there is a race for the requested_addr between mem_free()
+ /* There is a race for the requested_addr between mem_free()
* and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
* region with a mapping in a single operation, but it does not support
* private mappings.
@@ -410,6 +535,16 @@ rte_mem_unmap(void *virt, size_t size)
return 0;
}
+uint64_t
+eal_get_baseaddr(void)
+{
+ /* Windows strategy for memory allocation is undocumented.
+ * Returning 0 here effectively disables address guessing
+ * unless user provides an address hint.
+ */
+ return 0;
+}
+
int
rte_get_page_size(void)
{
@@ -431,3 +566,568 @@ rte_mem_lock(const void *virt, size_t size)
return 0;
}
+
+static int
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx)
+{
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, true);
+}
+
+static int
+memseg_list_reserve(struct rte_memseg_list *msl)
+{
+ return eal_reserve_memseg_list(msl, 0);
+}
+
+/*
+ * Remaining code in this file largely duplicates Linux EAL.
+ * Although Windows EAL supports only one hugepage size currently,
+ * code structure and comments are preserved so that changes may be
+ * easily ported until duplication is removed.
+ */
+
+static int
+memseg_primary_init(void)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct memtype {
+ uint64_t page_sz;
+ int socket_id;
+ } *memtypes = NULL;
+ int i, hpi_idx, msl_idx, ret = -1; /* fail unless told to succeed */
+ struct rte_memseg_list *msl;
+ uint64_t max_mem, max_mem_per_type;
+ unsigned int max_seglists_per_type;
+ unsigned int n_memtypes, cur_type;
+
+ /* no-huge does not need this at all */
+ if (internal_config.no_hugetlbfs)
+ return 0;
+
+ /*
+ * figuring out amount of memory we're going to have is a long and very
+ * involved process. the basic element we're operating with is a memory
+ * type, defined as a combination of NUMA node ID and page size (so that
+ * e.g. 2 sockets with 2 page sizes yield 4 memory types in total).
+ *
+ * deciding amount of memory going towards each memory type is a
+ * balancing act between maximum segments per type, maximum memory per
+ * type, and number of detected NUMA nodes. the goal is to make sure
+ * each memory type gets at least one memseg list.
+ *
+ * the total amount of memory is limited by RTE_MAX_MEM_MB value.
+ *
+ * the total amount of memory per type is limited by either
+ * RTE_MAX_MEM_MB_PER_TYPE, or by RTE_MAX_MEM_MB divided by the number
+ * of detected NUMA nodes. additionally, maximum number of segments per
+ * type is also limited by RTE_MAX_MEMSEG_PER_TYPE. this is because for
+ * smaller page sizes, it can take hundreds of thousands of segments to
+ * reach the above specified per-type memory limits.
+ *
+ * additionally, each type may have multiple memseg lists associated
+ * with it, each limited by either RTE_MAX_MEM_MB_PER_LIST for bigger
+ * page sizes, or RTE_MAX_MEMSEG_PER_LIST segments for smaller ones.
+ *
+ * the number of memseg lists per type is decided based on the above
+ * limits, and also taking number of detected NUMA nodes, to make sure
+ * that we don't run out of memseg lists before we populate all NUMA
+ * nodes with memory.
+ *
+ * we do this in three stages. first, we collect the number of types.
+ * then, we figure out memory constraints and populate the list of
+ * would-be memseg lists. then, we go ahead and allocate the memseg
+ * lists.
+ */
+
+ /* create space for mem types */
+ n_memtypes = internal_config.num_hugepage_sizes * rte_socket_count();
+ memtypes = calloc(n_memtypes, sizeof(*memtypes));
+ if (memtypes == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate space for memory types\n");
+ return -1;
+ }
+
+ /* populate mem types */
+ cur_type = 0;
+ for (hpi_idx = 0; hpi_idx < (int) internal_config.num_hugepage_sizes;
+ hpi_idx++) {
+ struct hugepage_info *hpi;
+ uint64_t hugepage_sz;
+
+ hpi = &internal_config.hugepage_info[hpi_idx];
+ hugepage_sz = hpi->hugepage_sz;
+
+ for (i = 0; i < (int) rte_socket_count(); i++, cur_type++) {
+ int socket_id = rte_socket_id_by_idx(i);
+
+ memtypes[cur_type].page_sz = hugepage_sz;
+ memtypes[cur_type].socket_id = socket_id;
+
+ RTE_LOG(DEBUG, EAL, "Detected memory type: "
+ "socket_id:%u hugepage_sz:%" PRIu64 "\n",
+ socket_id, hugepage_sz);
+ }
+ }
+ /* number of memtypes could have been lower due to no NUMA support */
+ n_memtypes = cur_type;
+
+ /* set up limits for types */
+ max_mem = (uint64_t)RTE_MAX_MEM_MB << 20;
+ max_mem_per_type = RTE_MIN((uint64_t)RTE_MAX_MEM_MB_PER_TYPE << 20,
+ max_mem / n_memtypes);
+
+ /*
+ * limit maximum number of segment lists per type to ensure there's
+ * space for memseg lists for all NUMA nodes with all page sizes
+ */
+ max_seglists_per_type = RTE_MAX_MEMSEG_LISTS / n_memtypes;
+
+ if (max_seglists_per_type == 0) {
+ RTE_LOG(ERR, EAL, "Cannot accommodate all memory types, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ goto out;
+ }
+
+ /* go through all mem types and create segment lists */
+ msl_idx = 0;
+ for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
+ unsigned int cur_seglist, n_seglists, n_segs;
+ unsigned int max_segs_per_type, max_segs_per_list;
+ struct memtype *type = &memtypes[cur_type];
+ uint64_t max_mem_per_list, pagesz;
+ int socket_id;
+
+ pagesz = type->page_sz;
+ socket_id = type->socket_id;
+
+ /*
+ * we need to create segment lists for this type. we must take
+ * into account the following things:
+ *
+ * 1. total amount of memory we can use for this memory type
+ * 2. total amount of memory per memseg list allowed
+ * 3. number of segments needed to fit the amount of memory
+ * 4. number of segments allowed per type
+ * 5. number of segments allowed per memseg list
+ * 6. number of memseg lists we are allowed to take up
+ */
+
+ /* calculate how much segments we will need in total */
+ max_segs_per_type = max_mem_per_type / pagesz;
+ /* limit number of segments to maximum allowed per type */
+ max_segs_per_type = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_TYPE);
+ /* limit number of segments to maximum allowed per list */
+ max_segs_per_list = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_LIST);
+
+ /* calculate how much memory we can have per segment list */
+ max_mem_per_list = RTE_MIN(max_segs_per_list * pagesz,
+ (uint64_t)RTE_MAX_MEM_MB_PER_LIST << 20);
+
+ /* calculate how many segments each segment list will have */
+ n_segs = RTE_MIN(max_segs_per_list, max_mem_per_list / pagesz);
+
+ /* calculate how many segment lists we can have */
+ n_seglists = RTE_MIN(max_segs_per_type / n_segs,
+ max_mem_per_type / max_mem_per_list);
+
+ /* limit number of segment lists according to our maximum */
+ n_seglists = RTE_MIN(n_seglists, max_seglists_per_type);
+
+ RTE_LOG(DEBUG, EAL, "Creating %i segment lists: "
+ "n_segs:%i socket_id:%i hugepage_sz:%" PRIu64 "\n",
+ n_seglists, n_segs, socket_id, pagesz);
+
+ /* create all segment lists */
+ for (cur_seglist = 0; cur_seglist < n_seglists; cur_seglist++) {
+ if (msl_idx >= RTE_MAX_MEMSEG_LISTS) {
+ RTE_LOG(ERR, EAL,
+ "No more space in memseg lists, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ goto out;
+ }
+ msl = &mcfg->memsegs[msl_idx++];
+
+ if (memseg_list_alloc(msl, pagesz, n_segs,
+ socket_id, cur_seglist))
+ goto out;
+
+ if (memseg_list_reserve(msl)) {
+ RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
+ goto out;
+ }
+ }
+ }
+ /* we're successful */
+ ret = 0;
+out:
+ free(memtypes);
+ return ret;
+}
+
+static int
+memseg_secondary_init(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_eal_memseg_init(void)
+{
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ return memseg_primary_init();
+ return memseg_secondary_init();
+}
+
+static inline uint64_t
+get_socket_mem_size(int socket)
+{
+ uint64_t size = 0;
+ unsigned int i;
+
+ for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
+ struct hugepage_info *hpi = &internal_config.hugepage_info[i];
+ size += hpi->hugepage_sz * hpi->num_pages[socket];
+ }
+
+ return size;
+}
+
+static int
+calc_num_pages_per_socket(uint64_t *memory,
+ struct hugepage_info *hp_info,
+ struct hugepage_info *hp_used,
+ unsigned int num_hp_info)
+{
+ unsigned int socket, j, i = 0;
+ unsigned int requested, available;
+ int total_num_pages = 0;
+ uint64_t remaining_mem, cur_mem;
+ uint64_t total_mem = internal_config.memory;
+
+ if (num_hp_info == 0)
+ return -1;
+
+ /* if specific memory amounts per socket weren't requested */
+ if (internal_config.force_sockets == 0) {
+ size_t total_size;
+ int cpu_per_socket[RTE_MAX_NUMA_NODES];
+ size_t default_size;
+ unsigned int lcore_id;
+
+ /* Compute number of cores per socket */
+ memset(cpu_per_socket, 0, sizeof(cpu_per_socket));
+ RTE_LCORE_FOREACH(lcore_id) {
+ cpu_per_socket[rte_lcore_to_socket_id(lcore_id)]++;
+ }
+
+ /*
+ * Automatically spread requested memory amongst detected
+ * sockets according to number of cores from cpu mask present
+ * on each socket.
+ */
+ total_size = internal_config.memory;
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
+ socket++) {
+
+ /* Set memory amount per socket */
+ default_size = internal_config.memory *
+ cpu_per_socket[socket] / rte_lcore_count();
+
+ /* Limit to maximum available memory on socket */
+ default_size = RTE_MIN(
+ default_size, get_socket_mem_size(socket));
+
+ /* Update sizes */
+ memory[socket] = default_size;
+ total_size -= default_size;
+ }
+
+ /*
+ * If some memory is remaining, try to allocate it by getting
+ * all available memory from sockets, one after the other.
+ */
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
+ socket++) {
+ /* take whatever is available */
+ default_size = RTE_MIN(
+ get_socket_mem_size(socket) - memory[socket],
+ total_size);
+
+ /* Update sizes */
+ memory[socket] += default_size;
+ total_size -= default_size;
+ }
+ }
+
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_mem != 0;
+ socket++) {
+ /* skips if the memory on specific socket wasn't requested */
+ for (i = 0; i < num_hp_info && memory[socket] != 0; i++) {
+ strncpy(hp_used[i].hugedir, hp_info[i].hugedir,
+ sizeof(hp_used[i].hugedir));
+ hp_used[i].num_pages[socket] = RTE_MIN(
+ memory[socket] / hp_info[i].hugepage_sz,
+ hp_info[i].num_pages[socket]);
+
+ cur_mem = hp_used[i].num_pages[socket] *
+ hp_used[i].hugepage_sz;
+
+ memory[socket] -= cur_mem;
+ total_mem -= cur_mem;
+
+ total_num_pages += hp_used[i].num_pages[socket];
+
+ /* check if we have met all memory requests */
+ if (memory[socket] == 0)
+ break;
+
+ /* Check if we have any more pages left at this size,
+ * if so, move on to next size.
+ */
+ if (hp_used[i].num_pages[socket] ==
+ hp_info[i].num_pages[socket])
+ continue;
+
+ /* At this point we know that there are more pages
+ * available that are bigger than the memory we want,
+ * so lets see if we can get enough from other page
+ * sizes.
+ */
+ remaining_mem = 0;
+ for (j = i+1; j < num_hp_info; j++)
+ remaining_mem += hp_info[j].hugepage_sz *
+ hp_info[j].num_pages[socket];
+
+ /* Is there enough other memory?
+ * If not, allocate another page and quit.
+ */
+ if (remaining_mem < memory[socket]) {
+ cur_mem = RTE_MIN(
+ memory[socket], hp_info[i].hugepage_sz);
+ memory[socket] -= cur_mem;
+ total_mem -= cur_mem;
+ hp_used[i].num_pages[socket]++;
+ total_num_pages++;
+ break; /* we are done with this socket*/
+ }
+ }
+ /* if we didn't satisfy all memory requirements per socket */
+ if (memory[socket] > 0 &&
+ internal_config.socket_mem[socket] != 0) {
+ /* to prevent icc errors */
+ requested = (unsigned int)(
+ internal_config.socket_mem[socket] / 0x100000);
+ available = requested -
+ ((unsigned int)(memory[socket] / 0x100000));
+ RTE_LOG(ERR, EAL, "Not enough memory available on "
+ "socket %u! Requested: %uMB, available: %uMB\n",
+ socket, requested, available);
+ return -1;
+ }
+ }
+
+ /* if we didn't satisfy total memory requirements */
+ if (total_mem > 0) {
+ requested = (unsigned int) (internal_config.memory / 0x100000);
+ available = requested - (unsigned int) (total_mem / 0x100000);
+ RTE_LOG(ERR, EAL, "Not enough memory available! "
+ "Requested: %uMB, available: %uMB\n",
+ requested, available);
+ return -1;
+ }
+ return total_num_pages;
+}
+
+/* Limit is checked by validator itself, nothing left to analyze.*/
+static int
+limits_callback(int socket_id, size_t cur_limit, size_t new_len)
+{
+ RTE_SET_USED(socket_id);
+ RTE_SET_USED(cur_limit);
+ RTE_SET_USED(new_len);
+ return -1;
+}
+
+static int
+eal_hugepage_init(void)
+{
+ struct hugepage_info used_hp[MAX_HUGEPAGE_SIZES];
+ uint64_t memory[RTE_MAX_NUMA_NODES];
+ int hp_sz_idx, socket_id;
+
+ memset(used_hp, 0, sizeof(used_hp));
+
+ for (hp_sz_idx = 0;
+ hp_sz_idx < (int) internal_config.num_hugepage_sizes;
+ hp_sz_idx++) {
+ /* also initialize used_hp hugepage sizes in used_hp */
+ struct hugepage_info *hpi;
+ hpi = &internal_config.hugepage_info[hp_sz_idx];
+ used_hp[hp_sz_idx].hugepage_sz = hpi->hugepage_sz;
+ }
+
+ /* make a copy of socket_mem, needed for balanced allocation. */
+ for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES; socket_id++)
+ memory[socket_id] = internal_config.socket_mem[socket_id];
+
+ /* calculate final number of pages */
+ if (calc_num_pages_per_socket(memory,
+ internal_config.hugepage_info, used_hp,
+ internal_config.num_hugepage_sizes) < 0)
+ return -1;
+
+ for (hp_sz_idx = 0;
+ hp_sz_idx < (int)internal_config.num_hugepage_sizes;
+ hp_sz_idx++) {
+ for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES;
+ socket_id++) {
+ struct rte_memseg **pages;
+ struct hugepage_info *hpi = &used_hp[hp_sz_idx];
+ unsigned int num_pages = hpi->num_pages[socket_id];
+ unsigned int num_pages_alloc;
+
+ if (num_pages == 0)
+ continue;
+
+ RTE_LOG(DEBUG, EAL,
+ "Allocating %u pages of size %" PRIu64 "M on socket %i\n",
+ num_pages, hpi->hugepage_sz >> 20, socket_id);
+
+ /* we may not be able to allocate all pages in one go,
+ * because we break up our memory map into multiple
+ * memseg lists. therefore, try allocating multiple
+ * times and see if we can get the desired number of
+ * pages from multiple allocations.
+ */
+
+ num_pages_alloc = 0;
+ do {
+ int i, cur_pages, needed;
+
+ needed = num_pages - num_pages_alloc;
+
+ pages = malloc(sizeof(*pages) * needed);
+
+ /* do not request exact number of pages */
+ cur_pages = eal_memalloc_alloc_seg_bulk(pages,
+ needed, hpi->hugepage_sz,
+ socket_id, false);
+ if (cur_pages <= 0) {
+ free(pages);
+ return -1;
+ }
+
+ /* mark preallocated pages as unfreeable */
+ for (i = 0; i < cur_pages; i++) {
+ struct rte_memseg *ms = pages[i];
+ ms->flags |=
+ RTE_MEMSEG_FLAG_DO_NOT_FREE;
+ }
+ free(pages);
+
+ num_pages_alloc += cur_pages;
+ } while (num_pages_alloc != num_pages);
+ }
+ }
+ /* if socket limits were specified, set them */
+ if (internal_config.force_socket_limits) {
+ unsigned int i;
+ for (i = 0; i < RTE_MAX_NUMA_NODES; i++) {
+ uint64_t limit = internal_config.socket_limit[i];
+ if (limit == 0)
+ continue;
+ if (rte_mem_alloc_validator_register("socket-limit",
+ limits_callback, i, limit))
+ RTE_LOG(ERR, EAL, "Failed to register socket "
+ "limits validator callback\n");
+ }
+ }
+ return 0;
+}
+
+static int
+eal_nohuge_init(void)
+{
+ struct rte_mem_config *mcfg;
+ struct rte_memseg_list *msl;
+ int n_segs, cur_seg;
+ uint64_t page_sz;
+ void *addr;
+ struct rte_fbarray *arr;
+ struct rte_memseg *ms;
+
+ mcfg = rte_eal_get_configuration()->mem_config;
+
+ /* nohuge mode is legacy mode */
+ internal_config.legacy_mem = 1;
+
+ /* create a memseg list */
+ msl = &mcfg->memsegs[0];
+
+ page_sz = RTE_PGSIZE_4K;
+ n_segs = internal_config.memory / page_sz;
+
+ if (rte_fbarray_init(&msl->memseg_arr, "nohugemem", n_segs,
+ sizeof(struct rte_memseg))) {
+ RTE_LOG(ERR, EAL, "Cannot allocate memseg list\n");
+ return -1;
+ }
+
+ addr = eal_mem_alloc(internal_config.memory, 0);
+ if (addr == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate %zu bytes",
+ internal_config.memory);
+ return -1;
+ }
+
+ msl->base_va = addr;
+ msl->page_sz = page_sz;
+ msl->socket_id = 0;
+ msl->len = internal_config.memory;
+ msl->heap = 1;
+
+ /* populate memsegs. each memseg is one page long */
+ for (cur_seg = 0; cur_seg < n_segs; cur_seg++) {
+ arr = &msl->memseg_arr;
+
+ ms = rte_fbarray_get(arr, cur_seg);
+ ms->iova = RTE_BAD_IOVA;
+ ms->addr = addr;
+ ms->hugepage_sz = page_sz;
+ ms->socket_id = 0;
+ ms->len = page_sz;
+
+ rte_fbarray_set_used(arr, cur_seg);
+
+ addr = RTE_PTR_ADD(addr, (size_t)page_sz);
+ }
+
+ if (mcfg->dma_maskbits &&
+ rte_mem_check_dma_mask_thread_unsafe(mcfg->dma_maskbits)) {
+ RTE_LOG(ERR, EAL,
+ "%s(): couldn't allocate memory due to IOVA "
+ "exceeding limits of current DMA mask.\n", __func__);
+ return -1;
+ }
+
+ return 0;
+}
+
+int
+rte_eal_hugepage_init(void)
+{
+ return internal_config.no_hugetlbfs ?
+ eal_nohuge_init() : eal_hugepage_init();
+}
+
+int
+rte_eal_hugepage_attach(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
diff --git a/lib/librte_eal/windows/eal_mp.c b/lib/librte_eal/windows/eal_mp.c
new file mode 100644
index 000000000..16a5e8ba0
--- /dev/null
+++ b/lib/librte_eal/windows/eal_mp.c
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file Multiprocess support stubs
+ *
+ * Stubs must log an error until implemented. If success is required
+ * for non-multiprocess operation, stub must log a warning and a comment
+ * must document what requires success emulation.
+ */
+
+#include <rte_eal.h>
+#include <rte_errno.h>
+
+#include "eal_private.h"
+#include "eal_windows.h"
+#include "malloc_mp.h"
+
+void
+rte_mp_channel_cleanup(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+}
+
+int
+rte_mp_action_register(const char *name, rte_mp_t action)
+{
+ RTE_SET_USED(name);
+ RTE_SET_USED(action);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+void
+rte_mp_action_unregister(const char *name)
+{
+ RTE_SET_USED(name);
+ EAL_LOG_NOT_IMPLEMENTED();
+}
+
+int
+rte_mp_sendmsg(struct rte_mp_msg *msg)
+{
+ RTE_SET_USED(msg);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
+ const struct timespec *ts)
+{
+ RTE_SET_USED(req);
+ RTE_SET_USED(reply);
+ RTE_SET_USED(ts);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
+ rte_mp_async_reply_t clb)
+{
+ RTE_SET_USED(req);
+ RTE_SET_USED(ts);
+ RTE_SET_USED(clb);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
+{
+ RTE_SET_USED(msg);
+ RTE_SET_USED(peer);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+register_mp_requests(void)
+{
+ /* Non-stub function succeeds if multi-process is not supported. */
+ EAL_LOG_STUB();
+ return 0;
+}
+
+int
+request_to_primary(struct malloc_mp_req *req)
+{
+ RTE_SET_USED(req);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+request_sync(void)
+{
+ /* Common memory allocator depends on this function success. */
+ EAL_LOG_STUB();
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index b202a1aa5..083ab8b93 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -9,8 +9,24 @@
* @file Facilities private to Windows EAL
*/
+#include <rte_errno.h>
#include <rte_windows.h>
+/**
+ * Log current function as not implemented and set rte_errno.
+ */
+#define EAL_LOG_NOT_IMPLEMENTED() \
+ do { \
+ RTE_LOG(DEBUG, EAL, "%s() is not implemented\n", __func__); \
+ rte_errno = ENOTSUP; \
+ } while (0)
+
+/**
+ * Log current function as a stub.
+ */
+#define EAL_LOG_STUB() \
+ RTE_LOG(DEBUG, EAL, "Windows: %s() is a stub\n", __func__)
+
/**
* Create a map of processors and cores on the system.
*/
@@ -36,6 +52,13 @@ int eal_thread_create(pthread_t *thread);
*/
unsigned int eal_socket_numa_node(unsigned int socket_id);
+/**
+ * Open virt2phys driver interface device.
+ *
+ * @return 0 on success, (-1) on failure.
+ */
+int eal_mem_virt2iova_init(void);
+
/**
* Locate Win32 memory management routines in system libraries.
*
diff --git a/lib/librte_eal/windows/include/meson.build b/lib/librte_eal/windows/include/meson.build
index 5fb1962ac..b3534b025 100644
--- a/lib/librte_eal/windows/include/meson.build
+++ b/lib/librte_eal/windows/include/meson.build
@@ -5,5 +5,6 @@ includes += include_directories('.')
headers += files(
'rte_os.h',
+ 'rte_virt2phys.h',
'rte_windows.h',
)
diff --git a/lib/librte_eal/windows/include/rte_os.h b/lib/librte_eal/windows/include/rte_os.h
index 510e39e03..62805a307 100644
--- a/lib/librte_eal/windows/include/rte_os.h
+++ b/lib/librte_eal/windows/include/rte_os.h
@@ -36,6 +36,10 @@ extern "C" {
#define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
+#define open _open
+#define close _close
+#define unlink _unlink
+
/* cpu_set macros implementation */
#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
diff --git a/lib/librte_eal/windows/include/rte_virt2phys.h b/lib/librte_eal/windows/include/rte_virt2phys.h
new file mode 100644
index 000000000..4bb2b4aaf
--- /dev/null
+++ b/lib/librte_eal/windows/include/rte_virt2phys.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file virt2phys driver interface
+ */
+
+/**
+ * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
+ */
+DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
+ 0x539c2135, 0x793a, 0x4926,
+ 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
+
+/**
+ * Driver device type for IO control codes.
+ */
+#define VIRT2PHYS_DEVTYPE 0x8000
+
+/**
+ * Translate a valid non-paged virtual address to a physical address.
+ *
+ * Note: A physical address zero (0) is reported if input address
+ * is paged out or not mapped. However, if input is a valid mapping
+ * of I/O port 0x0000, output is also zero. There is no way
+ * to distinguish between these cases by return value only.
+ *
+ * Input: a non-paged virtual address (PVOID).
+ *
+ * Output: the corresponding physical address (LARGE_INTEGER).
+ */
+#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
+ VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
diff --git a/lib/librte_eal/windows/include/rte_windows.h b/lib/librte_eal/windows/include/rte_windows.h
index ed6e4c148..899ed7d87 100644
--- a/lib/librte_eal/windows/include/rte_windows.h
+++ b/lib/librte_eal/windows/include/rte_windows.h
@@ -23,6 +23,8 @@
#include <basetsd.h>
#include <psapi.h>
+#include <setupapi.h>
+#include <winioctl.h>
/* Have GUIDs defined. */
#ifndef INITGUID
diff --git a/lib/librte_eal/windows/include/unistd.h b/lib/librte_eal/windows/include/unistd.h
index 757b7f3c5..6b33005b2 100644
--- a/lib/librte_eal/windows/include/unistd.h
+++ b/lib/librte_eal/windows/include/unistd.h
@@ -9,4 +9,7 @@
* as Microsoft libc does not contain unistd.h. This may be removed
* in future releases.
*/
+
+#include <io.h>
+
#endif /* _UNISTD_H_ */
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 81d3ee095..2f4fa91a9 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -8,7 +8,9 @@ sources += files(
'eal_debug.c',
'eal_hugepages.c',
'eal_lcore.c',
+ 'eal_memalloc.c',
'eal_memory.c',
+ 'eal_mp.c',
'eal_thread.c',
'getopt.c',
)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
@ 2020-04-10 22:04 ` Narcisa Ana Maria Vasile
2020-04-11 1:16 ` Dmitry Kozlyuk
0 siblings, 1 reply; 218+ messages in thread
From: Narcisa Ana Maria Vasile @ 2020-04-10 22:04 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon, John McNamara, Marko Kovacevic,
Anatoly Burakov, Bruce Richardson
On Fri, Apr 10, 2020 at 07:43:42PM +0300, Dmitry Kozlyuk wrote:
> Basic memory management supports core libraries and PMDs operating in
> IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
> IOVAs of hugepages allocated from user-mode.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> config/meson.build | 2 +-
> doc/guides/windows_gsg/run_apps.rst | 30 +
> lib/librte_eal/common/eal_common_fbarray.c | 57 +-
> lib/librte_eal/common/eal_common_memory.c | 50 +-
> lib/librte_eal/common/eal_private.h | 6 +-
> lib/librte_eal/common/malloc_heap.c | 1 +
> lib/librte_eal/common/meson.build | 9 +
> lib/librte_eal/freebsd/eal_memory.c | 1 -
> lib/librte_eal/meson.build | 1 +
> lib/librte_eal/rte_eal_exports.def | 119 ++-
> lib/librte_eal/windows/eal.c | 55 ++
> lib/librte_eal/windows/eal_memalloc.c | 423 +++++++++++
> lib/librte_eal/windows/eal_memory.c | 702 +++++++++++++++++-
> lib/librte_eal/windows/eal_mp.c | 103 +++
> lib/librte_eal/windows/eal_windows.h | 23 +
> lib/librte_eal/windows/include/meson.build | 1 +
> lib/librte_eal/windows/include/rte_os.h | 4 +
> .../windows/include/rte_virt2phys.h | 34 +
> lib/librte_eal/windows/include/rte_windows.h | 2 +
> lib/librte_eal/windows/include/unistd.h | 3 +
> lib/librte_eal/windows/meson.build | 2 +
> 21 files changed, 1561 insertions(+), 67 deletions(-)
> create mode 100644 lib/librte_eal/windows/eal_memalloc.c
> create mode 100644 lib/librte_eal/windows/eal_mp.c
> create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
>
> diff --git a/config/meson.build b/config/meson.build
> index bceb5ef7b..7b8baa788 100644
> --- a/config/meson.build
> +++ b/config/meson.build
> @@ -270,7 +270,7 @@ if is_windows
> add_project_link_arguments('-lmincore', language: 'c')
> endif
>
> - add_project_link_arguments('-ladvapi32', language: 'c')
> + add_project_link_arguments('-ladvapi32', '-lsetupapi', language: 'c')
> endif
>
> if get_option('b_lto')
> diff --git a/doc/guides/windows_gsg/run_apps.rst b/doc/guides/windows_gsg/run_apps.rst
> index 21ac7f6c1..e858cf8c1 100644
> --- a/doc/guides/windows_gsg/run_apps.rst
> +++ b/doc/guides/windows_gsg/run_apps.rst
> @@ -27,6 +27,36 @@ See `Large-Page Support`_ in MSDN for details.
> .. _Large-page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
>
>
> +Load virt2phys Driver
> +---------------------
> +
> +Access to physical addresses is provided by a kernel-mode driver, virt2phys.
> +It is mandatory at least for using hardware PMDs, but may also be required
> +for mempools.
> +
> +This driver is not signed, so signature checking must be disabled to load it.
> +Refer to documentation in ``dpdk-kmods`` repository for details on system
> +setup, driver build and installation.
> +
> +Compiled package, consisting of ``virt2phys.inf``, ``virt2phys.cat``,
> +and ``virt2phys.sys``, is installed as follows (from Elevated Command Line):
> +
> +.. code-block:: console
> +
> + pnputil /add-driver virt2phys.inf /install
> +
> +When loaded successfully, the driver is shown in *Device Manager* as *Virtual
> +to physical address translator* device under *Kernel bypass* category.
> +
> +If DPDK is unable to communicate with the driver, a warning is printed
> +on initialization (debug-level logs provide more details):
> +
> +.. code-block:: text
> +
> + EAL: Cannot open virt2phys driver interface
> +
> +
> +
> Run the ``helloworld`` Example
> ------------------------------
>
> diff --git a/lib/librte_eal/common/eal_common_fbarray.c b/lib/librte_eal/common/eal_common_fbarray.c
> index 1312f936b..236db9cb7 100644
> --- a/lib/librte_eal/common/eal_common_fbarray.c
> +++ b/lib/librte_eal/common/eal_common_fbarray.c
> @@ -5,15 +5,15 @@
> #include <fcntl.h>
> #include <inttypes.h>
> #include <limits.h>
> -#include <sys/mman.h>
> #include <stdint.h>
> #include <errno.h>
> -#include <sys/file.h>
> #include <string.h>
> +#include <unistd.h>
>
> #include <rte_common.h>
> -#include <rte_log.h>
> #include <rte_errno.h>
> +#include <rte_log.h>
> +#include <rte_memory.h>
> #include <rte_spinlock.h>
> #include <rte_tailq.h>
>
> @@ -85,19 +85,16 @@ resize_and_map(int fd, void *addr, size_t len)
> char path[PATH_MAX];
> void *map_addr;
>
> - if (ftruncate(fd, len)) {
> + if (eal_file_truncate(fd, len)) {
> RTE_LOG(ERR, EAL, "Cannot truncate %s\n", path);
> /* pass errno up the chain */
> rte_errno = errno;
> return -1;
> }
>
> - map_addr = mmap(addr, len, PROT_READ | PROT_WRITE,
> - MAP_SHARED | MAP_FIXED, fd, 0);
> + map_addr = rte_mem_map(addr, len, RTE_PROT_READ | RTE_PROT_WRITE,
> + RTE_MAP_SHARED | RTE_MAP_FIXED, fd, 0);
> if (map_addr != addr) {
> - RTE_LOG(ERR, EAL, "mmap() failed: %s\n", strerror(errno));
> - /* pass errno up the chain */
> - rte_errno = errno;
> return -1;
> }
> return 0;
> @@ -735,7 +732,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
> return -1;
> }
>
> - page_sz = sysconf(_SC_PAGESIZE);
> + page_sz = rte_get_page_size();
> if (page_sz == (size_t)-1) {
> free(ma);
> return -1;
> @@ -756,9 +753,12 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
>
> if (internal_config.no_shconf) {
> /* remap virtual area as writable */
> - void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
> - MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, fd, 0);
> - if (new_data == MAP_FAILED) {
> + void *new_data = rte_mem_map(
> + data, mmap_len,
> + RTE_PROT_READ | RTE_PROT_WRITE,
> + RTE_MAP_FIXED | RTE_MAP_PRIVATE | RTE_MAP_ANONYMOUS,
> + fd, 0);
> + if (new_data == NULL) {
> RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
> __func__, strerror(errno));
> goto fail;
> @@ -778,7 +778,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
> __func__, path, strerror(errno));
> rte_errno = errno;
> goto fail;
> - } else if (flock(fd, LOCK_EX | LOCK_NB)) {
> + } else if (eal_file_lock(
> + fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
> RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
> __func__, path, strerror(errno));
> rte_errno = EBUSY;
> @@ -789,10 +790,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
> * still attach to it, but no other process could reinitialize
> * it.
> */
> - if (flock(fd, LOCK_SH | LOCK_NB)) {
> - rte_errno = errno;
> + if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
> goto fail;
> - }
>
> if (resize_and_map(fd, data, mmap_len))
> goto fail;
> @@ -824,7 +823,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
> return 0;
> fail:
> if (data)
> - munmap(data, mmap_len);
> + rte_mem_unmap(data, mmap_len);
> if (fd >= 0)
> close(fd);
> free(ma);
> @@ -862,7 +861,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
> return -1;
> }
>
> - page_sz = sysconf(_SC_PAGESIZE);
> + page_sz = rte_get_page_size();
> if (page_sz == (size_t)-1) {
> free(ma);
> return -1;
> @@ -895,10 +894,8 @@ rte_fbarray_attach(struct rte_fbarray *arr)
> }
>
> /* lock the file, to let others know we're using it */
> - if (flock(fd, LOCK_SH | LOCK_NB)) {
> - rte_errno = errno;
> + if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
> goto fail;
> - }
>
> if (resize_and_map(fd, data, mmap_len))
> goto fail;
> @@ -916,7 +913,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
> return 0;
> fail:
> if (data)
> - munmap(data, mmap_len);
> + rte_mem_unmap(data, mmap_len);
> if (fd >= 0)
> close(fd);
> free(ma);
> @@ -944,8 +941,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
> * really do anything about it, things will blow up either way.
> */
>
> - size_t page_sz = sysconf(_SC_PAGESIZE);
> -
> + size_t page_sz = rte_get_page_size();
> if (page_sz == (size_t)-1)
> return -1;
>
> @@ -964,7 +960,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
> goto out;
> }
>
> - munmap(arr->data, mmap_len);
> + rte_mem_unmap(arr->data, mmap_len);
>
> /* area is unmapped, close fd and remove the tailq entry */
> if (tmp->fd >= 0)
> @@ -999,8 +995,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
> * really do anything about it, things will blow up either way.
> */
>
> - size_t page_sz = sysconf(_SC_PAGESIZE);
> -
> + size_t page_sz = rte_get_page_size();
> if (page_sz == (size_t)-1)
> return -1;
>
> @@ -1025,7 +1020,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
> * has been detached by all other processes
> */
> fd = tmp->fd;
> - if (flock(fd, LOCK_EX | LOCK_NB)) {
> + if (eal_file_lock(fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
> RTE_LOG(DEBUG, EAL, "Cannot destroy fbarray - another process is using it\n");
> rte_errno = EBUSY;
> ret = -1;
> @@ -1042,14 +1037,14 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
> * we're still holding an exclusive lock, so drop it to
> * shared.
> */
> - flock(fd, LOCK_SH | LOCK_NB);
> + eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN);
>
> ret = -1;
> goto out;
> }
> close(fd);
> }
> - munmap(arr->data, mmap_len);
> + rte_mem_unmap(arr->data, mmap_len);
>
> /* area is unmapped, remove the tailq entry */
> TAILQ_REMOVE(&mem_area_tailq, tmp, next);
> diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
> index d9764681a..5c3cf1f75 100644
> --- a/lib/librte_eal/common/eal_common_memory.c
> +++ b/lib/librte_eal/common/eal_common_memory.c
> @@ -11,7 +11,6 @@
> #include <string.h>
> #include <unistd.h>
> #include <inttypes.h>
> -#include <sys/mman.h>
> #include <sys/queue.h>
>
> #include <rte_fbarray.h>
> @@ -44,7 +43,7 @@ static uint64_t system_page_sz;
> #define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
> void *
> eal_get_virtual_area(void *requested_addr, size_t *size,
> - size_t page_sz, int flags, int mmap_flags)
> + size_t page_sz, int flags, enum eal_mem_reserve_flags reserve_flags)
> {
> bool addr_is_hint, allow_shrink, unmap, no_align;
> uint64_t map_sz;
> @@ -52,9 +51,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> uint8_t try = 0;
>
> if (system_page_sz == 0)
> - system_page_sz = sysconf(_SC_PAGESIZE);
> -
> - mmap_flags |= MAP_PRIVATE | MAP_ANONYMOUS;
> + system_page_sz = rte_get_page_size();
>
> RTE_LOG(DEBUG, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
>
> @@ -98,24 +95,24 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> return NULL;
> }
>
> - mapped_addr = mmap(requested_addr, (size_t)map_sz, PROT_NONE,
> - mmap_flags, -1, 0);
> - if (mapped_addr == MAP_FAILED && allow_shrink)
> - *size -= page_sz;
> + mapped_addr = eal_mem_reserve(
> + requested_addr, (size_t)map_sz, reserve_flags);
> + if ((mapped_addr == NULL) && allow_shrink)
> + size -= page_sz;
>
> - if (mapped_addr != MAP_FAILED && addr_is_hint &&
> - mapped_addr != requested_addr) {
> + if ((mapped_addr != NULL) && addr_is_hint &&
> + (mapped_addr != requested_addr)) {
> try++;
> next_baseaddr = RTE_PTR_ADD(next_baseaddr, page_sz);
> if (try <= MAX_MMAP_WITH_DEFINED_ADDR_TRIES) {
> /* hint was not used. Try with another offset */
> - munmap(mapped_addr, map_sz);
> - mapped_addr = MAP_FAILED;
> + eal_mem_free(mapped_addr, *size);
> + mapped_addr = NULL;
> requested_addr = next_baseaddr;
> }
> }
> } while ((allow_shrink || addr_is_hint) &&
> - mapped_addr == MAP_FAILED && *size > 0);
> + (mapped_addr == NULL) && (*size > 0));
>
> /* align resulting address - if map failed, we will ignore the value
> * anyway, so no need to add additional checks.
> @@ -125,20 +122,17 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
>
> if (*size == 0) {
> RTE_LOG(ERR, EAL, "Cannot get a virtual area of any size: %s\n",
> - strerror(errno));
> - rte_errno = errno;
> + strerror(rte_errno));
> return NULL;
> - } else if (mapped_addr == MAP_FAILED) {
> + } else if (mapped_addr == NULL) {
> RTE_LOG(ERR, EAL, "Cannot get a virtual area: %s\n",
> - strerror(errno));
> - /* pass errno up the call chain */
> - rte_errno = errno;
> + strerror(rte_errno));
> return NULL;
> } else if (requested_addr != NULL && !addr_is_hint &&
> aligned_addr != requested_addr) {
> RTE_LOG(ERR, EAL, "Cannot get a virtual area at requested address: %p (got %p)\n",
> requested_addr, aligned_addr);
> - munmap(mapped_addr, map_sz);
> + eal_mem_free(mapped_addr, map_sz);
> rte_errno = EADDRNOTAVAIL;
> return NULL;
> } else if (requested_addr != NULL && addr_is_hint &&
> @@ -154,7 +148,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> aligned_addr, *size);
>
> if (unmap) {
> - munmap(mapped_addr, map_sz);
> + eal_mem_free(mapped_addr, map_sz);
> } else if (!no_align) {
> void *map_end, *aligned_end;
> size_t before_len, after_len;
> @@ -172,12 +166,12 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> /* unmap space before aligned mmap address */
> before_len = RTE_PTR_DIFF(aligned_addr, mapped_addr);
> if (before_len > 0)
> - munmap(mapped_addr, before_len);
> + eal_mem_free(mapped_addr, before_len);
>
> /* unmap space after aligned end mmap address */
> after_len = RTE_PTR_DIFF(map_end, aligned_end);
> if (after_len > 0)
> - munmap(aligned_end, after_len);
> + eal_mem_free(aligned_end, after_len);
> }
>
> return aligned_addr;
> @@ -586,10 +580,10 @@ rte_eal_memdevice_init(void)
> int
> rte_mem_lock_page(const void *virt)
> {
> - unsigned long virtual = (unsigned long)virt;
> - int page_size = getpagesize();
> - unsigned long aligned = (virtual & ~(page_size - 1));
> - return mlock((void *)aligned, page_size);
> + uintptr_t virtual = (uintptr_t)virt;
> + int page_size = rte_get_page_size();
> + uintptr_t aligned = (virtual & ~(page_size - 1));
> + return rte_mem_lock((void *)aligned, page_size);
> }
>
> int
> diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
> index 76938e379..59ac41916 100644
> --- a/lib/librte_eal/common/eal_private.h
> +++ b/lib/librte_eal/common/eal_private.h
> @@ -226,8 +226,8 @@ enum eal_mem_reserve_flags {
> * Page size on which to align requested virtual area.
> * @param flags
> * EAL_VIRTUAL_AREA_* flags.
> - * @param mmap_flags
> - * Extra flags passed directly to mmap().
> + * @param reserve_flags
> + * Extra flags passed directly to rte_mem_reserve().
> *
> * @return
> * Virtual area address if successful.
> @@ -244,7 +244,7 @@ enum eal_mem_reserve_flags {
> /**< immediately unmap reserved virtual area. */
> void *
> eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
> - int flags, int mmap_flags);
> + int flags, enum eal_mem_reserve_flags reserve_flags);
>
> /**
> * Reserve VA space for a memory segment list.
> diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
> index 842eb9de7..6534c895c 100644
> --- a/lib/librte_eal/common/malloc_heap.c
> +++ b/lib/librte_eal/common/malloc_heap.c
> @@ -729,6 +729,7 @@ malloc_heap_alloc(const char *type, size_t size, int socket_arg,
> if (ret != NULL)
> return ret;
> }
> +
> return NULL;
> }
>
> diff --git a/lib/librte_eal/common/meson.build b/lib/librte_eal/common/meson.build
> index 02d9280cc..6dcdcc890 100644
> --- a/lib/librte_eal/common/meson.build
> +++ b/lib/librte_eal/common/meson.build
> @@ -9,11 +9,20 @@ if is_windows
> 'eal_common_class.c',
> 'eal_common_devargs.c',
> 'eal_common_errno.c',
> + 'eal_common_fbarray.c',
> 'eal_common_launch.c',
> 'eal_common_lcore.c',
> 'eal_common_log.c',
> + 'eal_common_mcfg.c',
> + 'eal_common_memalloc.c',
> + 'eal_common_memory.c',
> + 'eal_common_memzone.c',
> 'eal_common_options.c',
> + 'eal_common_tailqs.c',
> 'eal_common_thread.c',
> + 'malloc_elem.c',
> + 'malloc_heap.c',
> + 'rte_malloc.c',
> 'rte_option.c',
> )
> subdir_done()
> diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
> index 5174f9cd0..99bf6ec9e 100644
> --- a/lib/librte_eal/freebsd/eal_memory.c
> +++ b/lib/librte_eal/freebsd/eal_memory.c
> @@ -355,7 +355,6 @@ memseg_list_reserve(struct rte_memseg_list *msl)
> return eal_reserve_memseg_list(msl, flags);
> }
>
> -
> static int
> memseg_primary_init(void)
> {
> diff --git a/lib/librte_eal/meson.build b/lib/librte_eal/meson.build
> index 1f89efb88..1d750f003 100644
> --- a/lib/librte_eal/meson.build
> +++ b/lib/librte_eal/meson.build
> @@ -11,6 +11,7 @@ if not is_windows
> endif
>
> dpdk_conf.set('RTE_EXEC_ENV_' + exec_env.to_upper(), 1)
> +dpdk_conf.set10('RTE_EAL_NUMA_AWARE_HUGEPAGES', true)
> subdir(exec_env)
>
> subdir(arch_subdir)
> diff --git a/lib/librte_eal/rte_eal_exports.def b/lib/librte_eal/rte_eal_exports.def
> index bacf9a107..854b83bcd 100644
> --- a/lib/librte_eal/rte_eal_exports.def
> +++ b/lib/librte_eal/rte_eal_exports.def
> @@ -1,13 +1,128 @@
> EXPORTS
> __rte_panic
> + rte_calloc
> + rte_calloc_socket
> rte_eal_get_configuration
> + rte_eal_has_hugepages
> rte_eal_init
> + rte_eal_iova_mode
> rte_eal_mp_remote_launch
> rte_eal_mp_wait_lcore
> + rte_eal_process_type
> rte_eal_remote_launch
> - rte_get_page_size
> + rte_eal_tailq_lookup
> + rte_eal_tailq_register
> + rte_eal_using_phys_addrs
> + rte_free
> rte_log
> + rte_malloc
> + rte_malloc_dump_stats
> + rte_malloc_get_socket_stats
> + rte_malloc_set_limit
> + rte_malloc_socket
> + rte_malloc_validate
> + rte_malloc_virt2iova
> + rte_mcfg_mem_read_lock
> + rte_mcfg_mem_read_unlock
> + rte_mcfg_mem_write_lock
> + rte_mcfg_mem_write_unlock
> + rte_mcfg_mempool_read_lock
> + rte_mcfg_mempool_read_unlock
> + rte_mcfg_mempool_write_lock
> + rte_mcfg_mempool_write_unlock
> + rte_mcfg_tailq_read_lock
> + rte_mcfg_tailq_read_unlock
> + rte_mcfg_tailq_write_lock
> + rte_mcfg_tailq_write_unlock
> + rte_mem_lock_page
> + rte_mem_virt2iova
> + rte_mem_virt2phy
> + rte_memory_get_nchannel
> + rte_memory_get_nrank
> + rte_memzone_dump
> + rte_memzone_free
> + rte_memzone_lookup
> + rte_memzone_reserve
> + rte_memzone_reserve_aligned
> + rte_memzone_reserve_bounded
> + rte_memzone_walk
> + rte_vlog
> + rte_realloc
> + rte_zmalloc
> + rte_zmalloc_socket
> +
> + rte_mp_action_register
> + rte_mp_action_unregister
> + rte_mp_reply
> + rte_mp_sendmsg
> +
> + rte_fbarray_attach
> + rte_fbarray_destroy
> + rte_fbarray_detach
> + rte_fbarray_dump_metadata
> + rte_fbarray_find_contig_free
> + rte_fbarray_find_contig_used
> + rte_fbarray_find_idx
> + rte_fbarray_find_next_free
> + rte_fbarray_find_next_n_free
> + rte_fbarray_find_next_n_used
> + rte_fbarray_find_next_used
> + rte_fbarray_get
> + rte_fbarray_init
> + rte_fbarray_is_used
> + rte_fbarray_set_free
> + rte_fbarray_set_used
> + rte_malloc_dump_heaps
> + rte_mem_alloc_validator_register
> + rte_mem_alloc_validator_unregister
> + rte_mem_check_dma_mask
> + rte_mem_event_callback_register
> + rte_mem_event_callback_unregister
> + rte_mem_iova2virt
> + rte_mem_virt2memseg
> + rte_mem_virt2memseg_list
> + rte_memseg_contig_walk
> + rte_memseg_list_walk
> + rte_memseg_walk
> + rte_mp_request_async
> + rte_mp_request_sync
> +
> + rte_fbarray_find_prev_free
> + rte_fbarray_find_prev_n_free
> + rte_fbarray_find_prev_n_used
> + rte_fbarray_find_prev_used
> + rte_fbarray_find_rev_contig_free
> + rte_fbarray_find_rev_contig_used
> + rte_memseg_contig_walk_thread_unsafe
> + rte_memseg_list_walk_thread_unsafe
> + rte_memseg_walk_thread_unsafe
> +
> + rte_malloc_heap_create
> + rte_malloc_heap_destroy
> + rte_malloc_heap_get_socket
> + rte_malloc_heap_memory_add
> + rte_malloc_heap_memory_attach
> + rte_malloc_heap_memory_detach
> + rte_malloc_heap_memory_remove
> + rte_malloc_heap_socket_is_external
> + rte_mem_check_dma_mask_thread_unsafe
> + rte_mem_set_dma_mask
> + rte_memseg_get_fd
> + rte_memseg_get_fd_offset
> + rte_memseg_get_fd_offset_thread_unsafe
> + rte_memseg_get_fd_thread_unsafe
> +
> + rte_extmem_attach
> + rte_extmem_detach
> + rte_extmem_register
> + rte_extmem_unregister
> +
> + rte_fbarray_find_biggest_free
> + rte_fbarray_find_biggest_used
> + rte_fbarray_find_rev_biggest_free
> + rte_fbarray_find_rev_biggest_used
> +
> + rte_get_page_size
> rte_mem_lock
> rte_mem_map
> rte_mem_unmap
> - rte_vlog
> diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
> index cf55b56da..38f17f09c 100644
> --- a/lib/librte_eal/windows/eal.c
> +++ b/lib/librte_eal/windows/eal.c
> @@ -93,6 +93,24 @@ eal_proc_type_detect(void)
> return ptype;
> }
>
> +enum rte_proc_type_t
> +rte_eal_process_type(void)
> +{
> + return rte_config.process_type;
> +}
> +
> +int
> +rte_eal_has_hugepages(void)
> +{
> + return !internal_config.no_hugetlbfs;
> +}
> +
> +enum rte_iova_mode
> +rte_eal_iova_mode(void)
> +{
> + return rte_config.iova_mode;
> +}
> +
> /* display usage */
> static void
> eal_usage(const char *prgname)
> @@ -328,6 +346,13 @@ rte_eal_init(int argc, char **argv)
> if (fctret < 0)
> exit(1);
>
> + /* Prevent creation of shared memory files. */
> + if (internal_config.no_shconf == 0) {
> + RTE_LOG(WARNING, EAL, "Multi-process support is requested, "
> + "but not available.\n");
> + internal_config.no_shconf = 1;
> + }
> +
> if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
> rte_eal_init_alert("Cannot get hugepage information");
> rte_errno = EACCES;
> @@ -345,6 +370,36 @@ rte_eal_init(int argc, char **argv)
> return -1;
> }
>
> + if (eal_mem_virt2iova_init() < 0) {
> + /* Non-fatal error if physical addresses are not required. */
> + RTE_LOG(WARNING, EAL, "Cannot access virt2phys driver, "
> + "PA will not be available\n");
> + }
> +
> + if (rte_eal_memzone_init() < 0) {
> + rte_eal_init_alert("Cannot init memzone");
> + rte_errno = ENODEV;
> + return -1;
> + }
> +
> + if (rte_eal_memory_init() < 0) {
> + rte_eal_init_alert("Cannot init memory");
> + rte_errno = ENOMEM;
> + return -1;
> + }
> +
> + if (rte_eal_malloc_heap_init() < 0) {
> + rte_eal_init_alert("Cannot init malloc heap");
> + rte_errno = ENODEV;
> + return -1;
> + }
> +
> + if (rte_eal_tailqs_init() < 0) {
> + rte_eal_init_alert("Cannot init tail queues for objects");
> + rte_errno = EFAULT;
> + return -1;
> + }
> +
> eal_thread_init_master(rte_config.master_lcore);
>
> RTE_LCORE_FOREACH_SLAVE(i) {
> diff --git a/lib/librte_eal/windows/eal_memalloc.c b/lib/librte_eal/windows/eal_memalloc.c
> new file mode 100644
> index 000000000..c7c3cf8df
> --- /dev/null
> +++ b/lib/librte_eal/windows/eal_memalloc.c
> @@ -0,0 +1,423 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2020 Dmitry Kozlyuk
> + */
> +
> +#include <rte_errno.h>
> +#include <rte_os.h>
> +#include <rte_windows.h>
> +
> +#include "eal_internal_cfg.h"
> +#include "eal_memalloc.h"
> +#include "eal_memcfg.h"
> +#include "eal_private.h"
> +#include "eal_windows.h"
> +
> +int
> +eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
> +{
> + /* Hugepages have no assiciated files in Windows. */
> + RTE_SET_USED(list_idx);
> + RTE_SET_USED(seg_idx);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +eal_memalloc_get_seg_fd_offset(int list_idx, int seg_idx, size_t *offset)
> +{
> + /* Hugepages have no assiciated files in Windows. */
> + RTE_SET_USED(list_idx);
> + RTE_SET_USED(seg_idx);
> + RTE_SET_USED(offset);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +static int
> +alloc_seg(struct rte_memseg *ms, void *requested_addr, int socket_id,
> + struct hugepage_info *hi)
> +{
> + HANDLE current_process;
> + unsigned int numa_node;
> + size_t alloc_sz;
> + void *addr;
> + rte_iova_t iova = RTE_BAD_IOVA;
> + PSAPI_WORKING_SET_EX_INFORMATION info;
> + PSAPI_WORKING_SET_EX_BLOCK *page;
> +
> + if (ms->len > 0) {
> + /* If a segment is already allocated as needed, return it. */
> + if ((ms->addr == requested_addr) &&
> + (ms->socket_id == socket_id) &&
> + (ms->hugepage_sz == hi->hugepage_sz)) {
> + return 0;
> + }
> +
> + /* Bugcheck, should not happen. */
> + RTE_LOG(DEBUG, EAL, "Attempted to reallocate segment %p "
> + "(size %zu) on socket %d", ms->addr,
> + ms->len, ms->socket_id);
> + return -1;
> + }
> +
> + current_process = GetCurrentProcess();
> + numa_node = eal_socket_numa_node(socket_id);
> + alloc_sz = hi->hugepage_sz;
> +
> + if (requested_addr == NULL) {
> + /* Request a new chunk of memory and enforce address hint. */
Does requested_addr being NULL means that no hint was provided? It also looks like eal_mem_alloc_socket
ignores the address hint anyway and just calls VirtualAllocExNuma with NULL for lpAddress. Maybe remove
the second part of the comment.
> + addr = eal_mem_alloc_socket(alloc_sz, socket_id);
> + if (addr == NULL) {
> + RTE_LOG(DEBUG, EAL, "Cannot allocate %zu bytes "
> + "on socket %d\n", alloc_sz, socket_id);
> + return -1;
> + }
> +
> + if (addr != requested_addr) {
requested_addr is NULL on this branch and we confirmed with the previous 'if' that addr is not NULL.
Should this branch be removed, since requested_addr is NULL, so there is no hint provided?
> + RTE_LOG(DEBUG, EAL, "Address hint %p not respected, "
> + "got %p\n", requested_addr, addr);
> + goto error;
> + }
> + } else {
> + /* Requested address is already reserved, commit memory. */
> + addr = eal_mem_commit(requested_addr, alloc_sz, socket_id);
> + if (addr == NULL) {
> + RTE_LOG(DEBUG, EAL, "Cannot commit reserved memory %p "
> + "(size %zu)\n", requested_addr, alloc_sz);
> + goto error;
Execution jumps to 'error' with an invalid addr, so it will try to call eal_mem_decommit with NULL as parameter.
Instead of 'goto error', maybe we should return here.
> + }
> + }
> +
> + /* Force OS to allocate a physical page and select a NUMA node.
> + * Hugepages are not pageable in Windows, so there's no race
> + * for physical address.
> + */
> + *(volatile int *)addr = *(volatile int *)addr;
> +
> + /* Only try to obtain IOVA if it's available, so that applications
> + * that do not need IOVA can use this allocator.
> + */
> + if (rte_eal_using_phys_addrs()) {
> + iova = rte_mem_virt2iova(addr);
> + if (iova == RTE_BAD_IOVA) {
> + RTE_LOG(DEBUG, EAL,
> + "Cannot get IOVA of allocated segment\n");
> + goto error;
> + }
> + }
> +
> + /* Only "Ex" function can handle hugepages. */
> + info.VirtualAddress = addr;
> + if (!QueryWorkingSetEx(current_process, &info, sizeof(info))) {
> + RTE_LOG_WIN32_ERR("QueryWorkingSetEx()");
> + goto error;
> + }
> +
> + page = &info.VirtualAttributes;
> + if (!page->Valid || !page->LargePage) {
> + RTE_LOG(DEBUG, EAL, "Got regular page instead of hugepage\n");
> + goto error;
> + }
> + if (page->Node != numa_node) {
> + RTE_LOG(DEBUG, EAL,
> + "NUMA node hint %u (socket %d) not respected, got %u\n",
> + numa_node, socket_id, page->Node);
> + goto error;
> + }
> +
> + ms->addr = addr;
> + ms->hugepage_sz = hi->hugepage_sz;
> + ms->len = alloc_sz;
> + ms->nchannel = rte_memory_get_nchannel();
> + ms->nrank = rte_memory_get_nrank();
> + ms->iova = iova;
> + ms->socket_id = socket_id;
> +
> + return 0;
> +
> +error:
> + /* Only jump here when `addr` and `alloc_sz` are valid. */
> + eal_mem_decommit(addr, alloc_sz);
> + return -1;
> +}
> +
> +static int
> +free_seg(struct rte_memseg *ms)
> +{
> + if (eal_mem_decommit(ms->addr, ms->len))
> + return -1;
> +
> + /* Must clear the segment, because alloc_seg() inspects it. */
> + memset(ms, 0, sizeof(*ms));
> + return 0;
> +}
> +
> +struct alloc_walk_param {
> + struct hugepage_info *hi;
> + struct rte_memseg **ms;
> + size_t page_sz;
> + unsigned int segs_allocated;
> + unsigned int n_segs;
> + int socket;
> + bool exact;
> +};
> +
> +static int
> +alloc_seg_walk(const struct rte_memseg_list *msl, void *arg)
> +{
> + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
> + struct alloc_walk_param *wa = arg;
> + struct rte_memseg_list *cur_msl;
> + size_t page_sz;
> + int cur_idx, start_idx, j;
> + unsigned int msl_idx, need, i;
> +
> + if (msl->page_sz != wa->page_sz)
> + return 0;
> + if (msl->socket_id != wa->socket)
> + return 0;
> +
> + page_sz = (size_t)msl->page_sz;
> +
> + msl_idx = msl - mcfg->memsegs;
> + cur_msl = &mcfg->memsegs[msl_idx];
> +
> + need = wa->n_segs;
> +
> + /* try finding space in memseg list */
> + if (wa->exact) {
> + /* if we require exact number of pages in a list, find them */
> + cur_idx = rte_fbarray_find_next_n_free(
> + &cur_msl->memseg_arr, 0, need);
> + if (cur_idx < 0)
> + return 0;
> + start_idx = cur_idx;
> + } else {
> + int cur_len;
> +
> + /* we don't require exact number of pages, so we're going to go
> + * for best-effort allocation. that means finding the biggest
> + * unused block, and going with that.
> + */
> + cur_idx = rte_fbarray_find_biggest_free(
> + &cur_msl->memseg_arr, 0);
> + if (cur_idx < 0)
> + return 0;
> + start_idx = cur_idx;
> + /* adjust the size to possibly be smaller than original
> + * request, but do not allow it to be bigger.
> + */
> + cur_len = rte_fbarray_find_contig_free(
> + &cur_msl->memseg_arr, cur_idx);
> + need = RTE_MIN(need, (unsigned int)cur_len);
> + }
> +
> + for (i = 0; i < need; i++, cur_idx++) {
> + struct rte_memseg *cur;
> + void *map_addr;
> +
> + cur = rte_fbarray_get(&cur_msl->memseg_arr, cur_idx);
> + map_addr = RTE_PTR_ADD(cur_msl->base_va, cur_idx * page_sz);
> +
> + if (alloc_seg(cur, map_addr, wa->socket, wa->hi)) {
> + RTE_LOG(DEBUG, EAL, "attempted to allocate %i segments, "
> + "but only %i were allocated\n", need, i);
> +
> + /* if exact number wasn't requested, stop */
> + if (!wa->exact)
> + goto out;
> +
> + /* clean up */
> + for (j = start_idx; j < cur_idx; j++) {
> + struct rte_memseg *tmp;
> + struct rte_fbarray *arr = &cur_msl->memseg_arr;
> +
> + tmp = rte_fbarray_get(arr, j);
> + rte_fbarray_set_free(arr, j);
> +
> + if (free_seg(tmp))
> + RTE_LOG(DEBUG, EAL, "Cannot free page\n");
> + }
> + /* clear the list */
> + if (wa->ms)
> + memset(wa->ms, 0, sizeof(*wa->ms) * wa->n_segs);
> +
> + return -1;
> + }
> + if (wa->ms)
> + wa->ms[i] = cur;
> +
> + rte_fbarray_set_used(&cur_msl->memseg_arr, cur_idx);
> + }
> +
> +out:
> + wa->segs_allocated = i;
> + if (i > 0)
> + cur_msl->version++;
> +
> + /* if we didn't allocate any segments, move on to the next list */
> + return i > 0;
> +}
> +
> +struct free_walk_param {
> + struct hugepage_info *hi;
> + struct rte_memseg *ms;
> +};
> +static int
> +free_seg_walk(const struct rte_memseg_list *msl, void *arg)
> +{
> + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
> + struct rte_memseg_list *found_msl;
> + struct free_walk_param *wa = arg;
> + uintptr_t start_addr, end_addr;
> + int msl_idx, seg_idx, ret;
> +
> + start_addr = (uintptr_t) msl->base_va;
> + end_addr = start_addr + msl->len;
> +
> + if ((uintptr_t)wa->ms->addr < start_addr ||
> + (uintptr_t)wa->ms->addr >= end_addr)
> + return 0;
> +
> + msl_idx = msl - mcfg->memsegs;
> + seg_idx = RTE_PTR_DIFF(wa->ms->addr, start_addr) / msl->page_sz;
> +
> + /* msl is const */
> + found_msl = &mcfg->memsegs[msl_idx];
> + found_msl->version++;
> +
> + rte_fbarray_set_free(&found_msl->memseg_arr, seg_idx);
> +
> + ret = free_seg(wa->ms);
> +
> + return (ret < 0) ? (-1) : 1;
> +}
> +
> +int
> +eal_memalloc_alloc_seg_bulk(struct rte_memseg **ms, int n_segs,
> + size_t page_sz, int socket, bool exact)
> +{
> + unsigned int i;
> + int ret = -1;
> + struct alloc_walk_param wa;
> + struct hugepage_info *hi = NULL;
> +
> + if (internal_config.legacy_mem) {
> + RTE_LOG(ERR, EAL, "dynamic allocation not supported in legacy mode\n");
> + return -ENOTSUP;
> + }
> +
> + for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
> + struct hugepage_info *hpi = &internal_config.hugepage_info[i];
> + if (page_sz == hpi->hugepage_sz) {
> + hi = hpi;
> + break;
> + }
> + }
> + if (!hi) {
> + RTE_LOG(ERR, EAL, "cannot find relevant hugepage_info entry\n");
> + return -1;
> + }
> +
> + memset(&wa, 0, sizeof(wa));
> + wa.exact = exact;
> + wa.hi = hi;
> + wa.ms = ms;
> + wa.n_segs = n_segs;
> + wa.page_sz = page_sz;
> + wa.socket = socket;
> + wa.segs_allocated = 0;
> +
> + /* memalloc is locked, so it's safe to use thread-unsafe version */
> + ret = rte_memseg_list_walk_thread_unsafe(alloc_seg_walk, &wa);
> + if (ret == 0) {
> + RTE_LOG(ERR, EAL, "cannot find suitable memseg_list\n");
> + ret = -1;
> + } else if (ret > 0) {
> + ret = (int)wa.segs_allocated;
> + }
> +
> + return ret;
> +}
> +
> +struct rte_memseg *
> +eal_memalloc_alloc_seg(size_t page_sz, int socket)
> +{
> + struct rte_memseg *ms = NULL;
> + eal_memalloc_alloc_seg_bulk(&ms, 1, page_sz, socket, true);
> + return ms;
> +}
> +
> +int
> +eal_memalloc_free_seg_bulk(struct rte_memseg **ms, int n_segs)
> +{
> + int seg, ret = 0;
> +
> + /* dynamic free not supported in legacy mode */
> + if (internal_config.legacy_mem)
> + return -1;
> +
> + for (seg = 0; seg < n_segs; seg++) {
> + struct rte_memseg *cur = ms[seg];
> + struct hugepage_info *hi = NULL;
> + struct free_walk_param wa;
> + size_t i;
> + int walk_res;
> +
> + /* if this page is marked as unfreeable, fail */
> + if (cur->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
> + RTE_LOG(DEBUG, EAL, "Page is not allowed to be freed\n");
> + ret = -1;
> + continue;
> + }
> +
> + memset(&wa, 0, sizeof(wa));
> +
> + for (i = 0; i < RTE_DIM(internal_config.hugepage_info);
> + i++) {
> + hi = &internal_config.hugepage_info[i];
> + if (cur->hugepage_sz == hi->hugepage_sz)
> + break;
> + }
> + if (i == RTE_DIM(internal_config.hugepage_info)) {
> + RTE_LOG(ERR, EAL, "Can't find relevant hugepage_info entry\n");
> + ret = -1;
> + continue;
> + }
> +
> + wa.ms = cur;
> + wa.hi = hi;
> +
> + /* memalloc is locked, so it's safe to use thread-unsafe version
> + */
> + walk_res = rte_memseg_list_walk_thread_unsafe(free_seg_walk,
> + &wa);
> + if (walk_res == 1)
> + continue;
> + if (walk_res == 0)
> + RTE_LOG(ERR, EAL, "Couldn't find memseg list\n");
> + ret = -1;
> + }
> + return ret;
> +}
> +
> +int
> +eal_memalloc_free_seg(struct rte_memseg *ms)
> +{
> + return eal_memalloc_free_seg_bulk(&ms, 1);
> +}
> +
> +int
> +eal_memalloc_sync_with_primary(void)
> +{
> + /* No multi-process support. */
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +eal_memalloc_init(void)
> +{
> + /* No action required. */
> + return 0;
> +}
> diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
> index 59606d84c..a9a35b7dc 100644
> --- a/lib/librte_eal/windows/eal_memory.c
> +++ b/lib/librte_eal/windows/eal_memory.c
> @@ -1,11 +1,23 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2010-2014 Intel Corporation (functions from Linux EAL)
> + * Copyright (c) 2020 Dmitry Kozlyuk (Windows specifics)
> + */
> +
> +#include <inttypes.h>
> #include <io.h>
>
> #include <rte_errno.h>
> #include <rte_memory.h>
>
> +#include "eal_internal_cfg.h"
> +#include "eal_memalloc.h"
> +#include "eal_memcfg.h"
> +#include "eal_options.h"
> #include "eal_private.h"
> #include "eal_windows.h"
>
> +#include <rte_virt2phys.h>
> +
> /* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
> * Provide a copy of definitions and code to load it dynamically.
> * Note: definitions are copied verbatim from Microsoft documentation
> @@ -120,6 +132,119 @@ eal_mem_win32api_init(void)
>
> #endif /* no VirtualAlloc2() */
>
> +static HANDLE virt2phys_device = INVALID_HANDLE_VALUE;
> +
> +int
> +eal_mem_virt2iova_init(void)
> +{
> + HDEVINFO list = INVALID_HANDLE_VALUE;
> + SP_DEVICE_INTERFACE_DATA ifdata;
> + SP_DEVICE_INTERFACE_DETAIL_DATA *detail = NULL;
> + DWORD detail_size;
> + int ret = -1;
> +
> + list = SetupDiGetClassDevs(
> + &GUID_DEVINTERFACE_VIRT2PHYS, NULL, NULL,
> + DIGCF_DEVICEINTERFACE | DIGCF_PRESENT);
> + if (list == INVALID_HANDLE_VALUE) {
> + RTE_LOG_WIN32_ERR("SetupDiGetClassDevs()");
> + goto exit;
> + }
> +
> + ifdata.cbSize = sizeof(ifdata);
> + if (!SetupDiEnumDeviceInterfaces(
> + list, NULL, &GUID_DEVINTERFACE_VIRT2PHYS, 0, &ifdata)) {
> + RTE_LOG_WIN32_ERR("SetupDiEnumDeviceInterfaces()");
> + goto exit;
> + }
> +
> + if (!SetupDiGetDeviceInterfaceDetail(
> + list, &ifdata, NULL, 0, &detail_size, NULL)) {
> + if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
> + RTE_LOG_WIN32_ERR(
> + "SetupDiGetDeviceInterfaceDetail(probe)");
> + goto exit;
> + }
> + }
> +
> + detail = malloc(detail_size);
> + if (detail == NULL) {
> + RTE_LOG(ERR, EAL, "Cannot allocate virt2phys "
> + "device interface detail data\n");
> + goto exit;
> + }
> +
> + detail->cbSize = sizeof(*detail);
> + if (!SetupDiGetDeviceInterfaceDetail(
> + list, &ifdata, detail, detail_size, NULL, NULL)) {
> + RTE_LOG_WIN32_ERR("SetupDiGetDeviceInterfaceDetail(read)");
> + goto exit;
> + }
> +
> + RTE_LOG(DEBUG, EAL, "Found virt2phys device: %s\n", detail->DevicePath);
> +
> + virt2phys_device = CreateFile(
> + detail->DevicePath, 0, 0, NULL, OPEN_EXISTING, 0, NULL);
> + if (virt2phys_device == INVALID_HANDLE_VALUE) {
> + RTE_LOG_WIN32_ERR("CreateFile()");
> + goto exit;
> + }
> +
> + /* Indicate success. */
> + ret = 0;
> +
> +exit:
> + if (detail != NULL)
> + free(detail);
> + if (list != INVALID_HANDLE_VALUE)
> + SetupDiDestroyDeviceInfoList(list);
> +
> + return ret;
> +}
> +
> +phys_addr_t
> +rte_mem_virt2phy(const void *virt)
> +{
> + LARGE_INTEGER phys;
> + DWORD bytes_returned;
> +
> + if (virt2phys_device == INVALID_HANDLE_VALUE)
> + return RTE_BAD_PHYS_ADDR;
> +
> + if (!DeviceIoControl(
> + virt2phys_device, IOCTL_VIRT2PHYS_TRANSLATE,
> + &virt, sizeof(virt), &phys, sizeof(phys),
> + &bytes_returned, NULL)) {
> + RTE_LOG_WIN32_ERR("DeviceIoControl(IOCTL_VIRT2PHYS_TRANSLATE)");
> + return RTE_BAD_PHYS_ADDR;
> + }
> +
> + return phys.QuadPart;
> +}
> +
> +/* Windows currently only supports IOVA as PA. */
> +rte_iova_t
> +rte_mem_virt2iova(const void *virt)
> +{
> + phys_addr_t phys;
> +
> + if (virt2phys_device == INVALID_HANDLE_VALUE)
> + return RTE_BAD_IOVA;
> +
> + phys = rte_mem_virt2phy(virt);
> + if (phys == RTE_BAD_PHYS_ADDR)
> + return RTE_BAD_IOVA;
> +
> + return (rte_iova_t)phys;
> +}
> +
> +/* Always using physical addresses under Windows if they can be obtained. */
> +int
> +rte_eal_using_phys_addrs(void)
> +{
> + return virt2phys_device != INVALID_HANDLE_VALUE;
> +}
> +
> /* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
> static int
> win32_alloc_error_to_errno(DWORD code)
> @@ -360,7 +485,7 @@ rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
> return NULL;
> }
>
> - /* TODO: there is a race for the requested_addr between mem_free()
> + /* There is a race for the requested_addr between mem_free()
> * and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
> * region with a mapping in a single operation, but it does not support
> * private mappings.
> @@ -410,6 +535,16 @@ rte_mem_unmap(void *virt, size_t size)
> return 0;
> }
>
> +uint64_t
> +eal_get_baseaddr(void)
> +{
> + /* Windows strategy for memory allocation is undocumented.
> + * Returning 0 here effectively disables address guessing
> + * unless user provides an address hint.
> + */
> + return 0;
> +}
> +
> int
> rte_get_page_size(void)
> {
> @@ -431,3 +566,568 @@ rte_mem_lock(const void *virt, size_t size)
>
> return 0;
> }
> +
> +static int
> +memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
> + int n_segs, int socket_id, int type_msl_idx)
> +{
> + return eal_alloc_memseg_list(
> + msl, page_sz, n_segs, socket_id, type_msl_idx, true);
> +}
> +
> +static int
> +memseg_list_reserve(struct rte_memseg_list *msl)
> +{
> + return eal_reserve_memseg_list(msl, 0);
> +}
> +
> +/*
> + * Remaining code in this file largely duplicates Linux EAL.
> + * Although Windows EAL supports only one hugepage size currently,
> + * code structure and comments are preserved so that changes may be
> + * easily ported until duplication is removed.
> + */
> +
> +static int
> +memseg_primary_init(void)
> +{
> + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
> + struct memtype {
> + uint64_t page_sz;
> + int socket_id;
> + } *memtypes = NULL;
> + int i, hpi_idx, msl_idx, ret = -1; /* fail unless told to succeed */
> + struct rte_memseg_list *msl;
> + uint64_t max_mem, max_mem_per_type;
> + unsigned int max_seglists_per_type;
> + unsigned int n_memtypes, cur_type;
> +
> + /* no-huge does not need this at all */
> + if (internal_config.no_hugetlbfs)
> + return 0;
> +
> + /*
> + * figuring out amount of memory we're going to have is a long and very
> + * involved process. the basic element we're operating with is a memory
> + * type, defined as a combination of NUMA node ID and page size (so that
> + * e.g. 2 sockets with 2 page sizes yield 4 memory types in total).
> + *
> + * deciding amount of memory going towards each memory type is a
> + * balancing act between maximum segments per type, maximum memory per
> + * type, and number of detected NUMA nodes. the goal is to make sure
> + * each memory type gets at least one memseg list.
> + *
> + * the total amount of memory is limited by RTE_MAX_MEM_MB value.
> + *
> + * the total amount of memory per type is limited by either
> + * RTE_MAX_MEM_MB_PER_TYPE, or by RTE_MAX_MEM_MB divided by the number
> + * of detected NUMA nodes. additionally, maximum number of segments per
> + * type is also limited by RTE_MAX_MEMSEG_PER_TYPE. this is because for
> + * smaller page sizes, it can take hundreds of thousands of segments to
> + * reach the above specified per-type memory limits.
> + *
> + * additionally, each type may have multiple memseg lists associated
> + * with it, each limited by either RTE_MAX_MEM_MB_PER_LIST for bigger
> + * page sizes, or RTE_MAX_MEMSEG_PER_LIST segments for smaller ones.
> + *
> + * the number of memseg lists per type is decided based on the above
> + * limits, and also taking number of detected NUMA nodes, to make sure
> + * that we don't run out of memseg lists before we populate all NUMA
> + * nodes with memory.
> + *
> + * we do this in three stages. first, we collect the number of types.
> + * then, we figure out memory constraints and populate the list of
> + * would-be memseg lists. then, we go ahead and allocate the memseg
> + * lists.
> + */
> +
> + /* create space for mem types */
> + n_memtypes = internal_config.num_hugepage_sizes * rte_socket_count();
> + memtypes = calloc(n_memtypes, sizeof(*memtypes));
> + if (memtypes == NULL) {
> + RTE_LOG(ERR, EAL, "Cannot allocate space for memory types\n");
> + return -1;
> + }
> +
> + /* populate mem types */
> + cur_type = 0;
> + for (hpi_idx = 0; hpi_idx < (int) internal_config.num_hugepage_sizes;
> + hpi_idx++) {
> + struct hugepage_info *hpi;
> + uint64_t hugepage_sz;
> +
> + hpi = &internal_config.hugepage_info[hpi_idx];
> + hugepage_sz = hpi->hugepage_sz;
> +
> + for (i = 0; i < (int) rte_socket_count(); i++, cur_type++) {
> + int socket_id = rte_socket_id_by_idx(i);
> +
> + memtypes[cur_type].page_sz = hugepage_sz;
> + memtypes[cur_type].socket_id = socket_id;
> +
> + RTE_LOG(DEBUG, EAL, "Detected memory type: "
> + "socket_id:%u hugepage_sz:%" PRIu64 "\n",
> + socket_id, hugepage_sz);
> + }
> + }
> + /* number of memtypes could have been lower due to no NUMA support */
> + n_memtypes = cur_type;
> +
> + /* set up limits for types */
> + max_mem = (uint64_t)RTE_MAX_MEM_MB << 20;
> + max_mem_per_type = RTE_MIN((uint64_t)RTE_MAX_MEM_MB_PER_TYPE << 20,
> + max_mem / n_memtypes);
> +
> + /*
> + * limit maximum number of segment lists per type to ensure there's
> + * space for memseg lists for all NUMA nodes with all page sizes
> + */
> + max_seglists_per_type = RTE_MAX_MEMSEG_LISTS / n_memtypes;
> +
> + if (max_seglists_per_type == 0) {
> + RTE_LOG(ERR, EAL, "Cannot accommodate all memory types, please increase %s\n",
> + RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
> + goto out;
> + }
> +
> + /* go through all mem types and create segment lists */
> + msl_idx = 0;
> + for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
> + unsigned int cur_seglist, n_seglists, n_segs;
> + unsigned int max_segs_per_type, max_segs_per_list;
> + struct memtype *type = &memtypes[cur_type];
> + uint64_t max_mem_per_list, pagesz;
> + int socket_id;
> +
> + pagesz = type->page_sz;
> + socket_id = type->socket_id;
> +
> + /*
> + * we need to create segment lists for this type. we must take
> + * into account the following things:
> + *
> + * 1. total amount of memory we can use for this memory type
> + * 2. total amount of memory per memseg list allowed
> + * 3. number of segments needed to fit the amount of memory
> + * 4. number of segments allowed per type
> + * 5. number of segments allowed per memseg list
> + * 6. number of memseg lists we are allowed to take up
> + */
> +
> + /* calculate how much segments we will need in total */
> + max_segs_per_type = max_mem_per_type / pagesz;
> + /* limit number of segments to maximum allowed per type */
> + max_segs_per_type = RTE_MIN(max_segs_per_type,
> + (unsigned int)RTE_MAX_MEMSEG_PER_TYPE);
> + /* limit number of segments to maximum allowed per list */
> + max_segs_per_list = RTE_MIN(max_segs_per_type,
> + (unsigned int)RTE_MAX_MEMSEG_PER_LIST);
> +
> + /* calculate how much memory we can have per segment list */
> + max_mem_per_list = RTE_MIN(max_segs_per_list * pagesz,
> + (uint64_t)RTE_MAX_MEM_MB_PER_LIST << 20);
> +
> + /* calculate how many segments each segment list will have */
> + n_segs = RTE_MIN(max_segs_per_list, max_mem_per_list / pagesz);
> +
> + /* calculate how many segment lists we can have */
> + n_seglists = RTE_MIN(max_segs_per_type / n_segs,
> + max_mem_per_type / max_mem_per_list);
> +
> + /* limit number of segment lists according to our maximum */
> + n_seglists = RTE_MIN(n_seglists, max_seglists_per_type);
> +
> + RTE_LOG(DEBUG, EAL, "Creating %i segment lists: "
> + "n_segs:%i socket_id:%i hugepage_sz:%" PRIu64 "\n",
> + n_seglists, n_segs, socket_id, pagesz);
> +
> + /* create all segment lists */
> + for (cur_seglist = 0; cur_seglist < n_seglists; cur_seglist++) {
> + if (msl_idx >= RTE_MAX_MEMSEG_LISTS) {
> + RTE_LOG(ERR, EAL,
> + "No more space in memseg lists, please increase %s\n",
> + RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
> + goto out;
> + }
> + msl = &mcfg->memsegs[msl_idx++];
> +
> + if (memseg_list_alloc(msl, pagesz, n_segs,
> + socket_id, cur_seglist))
> + goto out;
> +
> + if (memseg_list_reserve(msl)) {
> + RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
> + goto out;
> + }
> + }
> + }
> + /* we're successful */
> + ret = 0;
> +out:
> + free(memtypes);
> + return ret;
> +}
> +
> +static int
> +memseg_secondary_init(void)
> +{
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +rte_eal_memseg_init(void)
> +{
> + if (rte_eal_process_type() == RTE_PROC_PRIMARY)
> + return memseg_primary_init();
> + return memseg_secondary_init();
> +}
> +
> +static inline uint64_t
> +get_socket_mem_size(int socket)
> +{
> + uint64_t size = 0;
> + unsigned int i;
> +
> + for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
> + struct hugepage_info *hpi = &internal_config.hugepage_info[i];
> + size += hpi->hugepage_sz * hpi->num_pages[socket];
> + }
> +
> + return size;
> +}
> +
> +static int
> +calc_num_pages_per_socket(uint64_t *memory,
> + struct hugepage_info *hp_info,
> + struct hugepage_info *hp_used,
> + unsigned int num_hp_info)
> +{
> + unsigned int socket, j, i = 0;
> + unsigned int requested, available;
> + int total_num_pages = 0;
> + uint64_t remaining_mem, cur_mem;
> + uint64_t total_mem = internal_config.memory;
> +
> + if (num_hp_info == 0)
> + return -1;
> +
> + /* if specific memory amounts per socket weren't requested */
> + if (internal_config.force_sockets == 0) {
> + size_t total_size;
> + int cpu_per_socket[RTE_MAX_NUMA_NODES];
> + size_t default_size;
> + unsigned int lcore_id;
> +
> + /* Compute number of cores per socket */
> + memset(cpu_per_socket, 0, sizeof(cpu_per_socket));
> + RTE_LCORE_FOREACH(lcore_id) {
> + cpu_per_socket[rte_lcore_to_socket_id(lcore_id)]++;
> + }
> +
> + /*
> + * Automatically spread requested memory amongst detected
> + * sockets according to number of cores from cpu mask present
> + * on each socket.
> + */
> + total_size = internal_config.memory;
> + for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
> + socket++) {
> +
> + /* Set memory amount per socket */
> + default_size = internal_config.memory *
> + cpu_per_socket[socket] / rte_lcore_count();
> +
> + /* Limit to maximum available memory on socket */
> + default_size = RTE_MIN(
> + default_size, get_socket_mem_size(socket));
> +
> + /* Update sizes */
> + memory[socket] = default_size;
> + total_size -= default_size;
> + }
> +
> + /*
> + * If some memory is remaining, try to allocate it by getting
> + * all available memory from sockets, one after the other.
> + */
> + for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
> + socket++) {
> + /* take whatever is available */
> + default_size = RTE_MIN(
> + get_socket_mem_size(socket) - memory[socket],
> + total_size);
> +
> + /* Update sizes */
> + memory[socket] += default_size;
> + total_size -= default_size;
> + }
> + }
> +
> + for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_mem != 0;
> + socket++) {
> + /* skips if the memory on specific socket wasn't requested */
> + for (i = 0; i < num_hp_info && memory[socket] != 0; i++) {
> + strncpy(hp_used[i].hugedir, hp_info[i].hugedir,
> + sizeof(hp_used[i].hugedir));
> + hp_used[i].num_pages[socket] = RTE_MIN(
> + memory[socket] / hp_info[i].hugepage_sz,
> + hp_info[i].num_pages[socket]);
> +
> + cur_mem = hp_used[i].num_pages[socket] *
> + hp_used[i].hugepage_sz;
> +
> + memory[socket] -= cur_mem;
> + total_mem -= cur_mem;
> +
> + total_num_pages += hp_used[i].num_pages[socket];
> +
> + /* check if we have met all memory requests */
> + if (memory[socket] == 0)
> + break;
> +
> + /* Check if we have any more pages left at this size,
> + * if so, move on to next size.
> + */
> + if (hp_used[i].num_pages[socket] ==
> + hp_info[i].num_pages[socket])
> + continue;
> +
> + /* At this point we know that there are more pages
> + * available that are bigger than the memory we want,
> + * so lets see if we can get enough from other page
> + * sizes.
> + */
> + remaining_mem = 0;
> + for (j = i+1; j < num_hp_info; j++)
> + remaining_mem += hp_info[j].hugepage_sz *
> + hp_info[j].num_pages[socket];
> +
> + /* Is there enough other memory?
> + * If not, allocate another page and quit.
> + */
> + if (remaining_mem < memory[socket]) {
> + cur_mem = RTE_MIN(
> + memory[socket], hp_info[i].hugepage_sz);
> + memory[socket] -= cur_mem;
> + total_mem -= cur_mem;
> + hp_used[i].num_pages[socket]++;
> + total_num_pages++;
> + break; /* we are done with this socket*/
> + }
> + }
> + /* if we didn't satisfy all memory requirements per socket */
> + if (memory[socket] > 0 &&
> + internal_config.socket_mem[socket] != 0) {
> + /* to prevent icc errors */
> + requested = (unsigned int)(
> + internal_config.socket_mem[socket] / 0x100000);
> + available = requested -
> + ((unsigned int)(memory[socket] / 0x100000));
> + RTE_LOG(ERR, EAL, "Not enough memory available on "
> + "socket %u! Requested: %uMB, available: %uMB\n",
> + socket, requested, available);
> + return -1;
> + }
> + }
> +
> + /* if we didn't satisfy total memory requirements */
> + if (total_mem > 0) {
> + requested = (unsigned int) (internal_config.memory / 0x100000);
> + available = requested - (unsigned int) (total_mem / 0x100000);
> + RTE_LOG(ERR, EAL, "Not enough memory available! "
> + "Requested: %uMB, available: %uMB\n",
> + requested, available);
> + return -1;
> + }
> + return total_num_pages;
> +}
> +
> +/* Limit is checked by validator itself, nothing left to analyze.*/
> +static int
> +limits_callback(int socket_id, size_t cur_limit, size_t new_len)
> +{
> + RTE_SET_USED(socket_id);
> + RTE_SET_USED(cur_limit);
> + RTE_SET_USED(new_len);
> + return -1;
> +}
> +
> +static int
> +eal_hugepage_init(void)
> +{
> + struct hugepage_info used_hp[MAX_HUGEPAGE_SIZES];
> + uint64_t memory[RTE_MAX_NUMA_NODES];
> + int hp_sz_idx, socket_id;
> +
> + memset(used_hp, 0, sizeof(used_hp));
> +
> + for (hp_sz_idx = 0;
> + hp_sz_idx < (int) internal_config.num_hugepage_sizes;
> + hp_sz_idx++) {
> + /* also initialize used_hp hugepage sizes in used_hp */
> + struct hugepage_info *hpi;
> + hpi = &internal_config.hugepage_info[hp_sz_idx];
> + used_hp[hp_sz_idx].hugepage_sz = hpi->hugepage_sz;
> + }
> +
> + /* make a copy of socket_mem, needed for balanced allocation. */
> + for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES; socket_id++)
> + memory[socket_id] = internal_config.socket_mem[socket_id];
> +
> + /* calculate final number of pages */
> + if (calc_num_pages_per_socket(memory,
> + internal_config.hugepage_info, used_hp,
> + internal_config.num_hugepage_sizes) < 0)
> + return -1;
> +
> + for (hp_sz_idx = 0;
> + hp_sz_idx < (int)internal_config.num_hugepage_sizes;
> + hp_sz_idx++) {
> + for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES;
> + socket_id++) {
> + struct rte_memseg **pages;
> + struct hugepage_info *hpi = &used_hp[hp_sz_idx];
> + unsigned int num_pages = hpi->num_pages[socket_id];
> + unsigned int num_pages_alloc;
> +
> + if (num_pages == 0)
> + continue;
> +
> + RTE_LOG(DEBUG, EAL,
> + "Allocating %u pages of size %" PRIu64 "M on socket %i\n",
> + num_pages, hpi->hugepage_sz >> 20, socket_id);
> +
> + /* we may not be able to allocate all pages in one go,
> + * because we break up our memory map into multiple
> + * memseg lists. therefore, try allocating multiple
> + * times and see if we can get the desired number of
> + * pages from multiple allocations.
> + */
> +
> + num_pages_alloc = 0;
> + do {
> + int i, cur_pages, needed;
> +
> + needed = num_pages - num_pages_alloc;
> +
> + pages = malloc(sizeof(*pages) * needed);
> +
> + /* do not request exact number of pages */
> + cur_pages = eal_memalloc_alloc_seg_bulk(pages,
> + needed, hpi->hugepage_sz,
> + socket_id, false);
> + if (cur_pages <= 0) {
> + free(pages);
> + return -1;
> + }
> +
> + /* mark preallocated pages as unfreeable */
> + for (i = 0; i < cur_pages; i++) {
> + struct rte_memseg *ms = pages[i];
> + ms->flags |=
> + RTE_MEMSEG_FLAG_DO_NOT_FREE;
> + }
> + free(pages);
> +
> + num_pages_alloc += cur_pages;
> + } while (num_pages_alloc != num_pages);
> + }
> + }
> + /* if socket limits were specified, set them */
> + if (internal_config.force_socket_limits) {
> + unsigned int i;
> + for (i = 0; i < RTE_MAX_NUMA_NODES; i++) {
> + uint64_t limit = internal_config.socket_limit[i];
> + if (limit == 0)
> + continue;
> + if (rte_mem_alloc_validator_register("socket-limit",
> + limits_callback, i, limit))
> + RTE_LOG(ERR, EAL, "Failed to register socket "
> + "limits validator callback\n");
> + }
> + }
> + return 0;
> +}
> +
> +static int
> +eal_nohuge_init(void)
> +{
> + struct rte_mem_config *mcfg;
> + struct rte_memseg_list *msl;
> + int n_segs, cur_seg;
> + uint64_t page_sz;
> + void *addr;
> + struct rte_fbarray *arr;
> + struct rte_memseg *ms;
> +
> + mcfg = rte_eal_get_configuration()->mem_config;
> +
> + /* nohuge mode is legacy mode */
> + internal_config.legacy_mem = 1;
> +
> + /* create a memseg list */
> + msl = &mcfg->memsegs[0];
> +
> + page_sz = RTE_PGSIZE_4K;
> + n_segs = internal_config.memory / page_sz;
> +
> + if (rte_fbarray_init(&msl->memseg_arr, "nohugemem", n_segs,
> + sizeof(struct rte_memseg))) {
> + RTE_LOG(ERR, EAL, "Cannot allocate memseg list\n");
> + return -1;
> + }
> +
> + addr = eal_mem_alloc(internal_config.memory, 0);
> + if (addr == NULL) {
> + RTE_LOG(ERR, EAL, "Cannot allocate %zu bytes",
> + internal_config.memory);
> + return -1;
> + }
> +
> + msl->base_va = addr;
> + msl->page_sz = page_sz;
> + msl->socket_id = 0;
> + msl->len = internal_config.memory;
> + msl->heap = 1;
> +
> + /* populate memsegs. each memseg is one page long */
> + for (cur_seg = 0; cur_seg < n_segs; cur_seg++) {
> + arr = &msl->memseg_arr;
> +
> + ms = rte_fbarray_get(arr, cur_seg);
> + ms->iova = RTE_BAD_IOVA;
> + ms->addr = addr;
> + ms->hugepage_sz = page_sz;
> + ms->socket_id = 0;
> + ms->len = page_sz;
> +
> + rte_fbarray_set_used(arr, cur_seg);
> +
> + addr = RTE_PTR_ADD(addr, (size_t)page_sz);
> + }
> +
> + if (mcfg->dma_maskbits &&
> + rte_mem_check_dma_mask_thread_unsafe(mcfg->dma_maskbits)) {
> + RTE_LOG(ERR, EAL,
> + "%s(): couldn't allocate memory due to IOVA "
> + "exceeding limits of current DMA mask.\n", __func__);
> + return -1;
> + }
> +
> + return 0;
> +}
> +
> +int
> +rte_eal_hugepage_init(void)
> +{
> + return internal_config.no_hugetlbfs ?
> + eal_nohuge_init() : eal_hugepage_init();
> +}
> +
> +int
> +rte_eal_hugepage_attach(void)
> +{
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> diff --git a/lib/librte_eal/windows/eal_mp.c b/lib/librte_eal/windows/eal_mp.c
> new file mode 100644
> index 000000000..16a5e8ba0
> --- /dev/null
> +++ b/lib/librte_eal/windows/eal_mp.c
> @@ -0,0 +1,103 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2020 Dmitry Kozlyuk
> + */
> +
> +/**
> + * @file Multiprocess support stubs
> + *
> + * Stubs must log an error until implemented. If success is required
> + * for non-multiprocess operation, stub must log a warning and a comment
> + * must document what requires success emulation.
> + */
> +
> +#include <rte_eal.h>
> +#include <rte_errno.h>
> +
> +#include "eal_private.h"
> +#include "eal_windows.h"
> +#include "malloc_mp.h"
> +
> +void
> +rte_mp_channel_cleanup(void)
> +{
> + EAL_LOG_NOT_IMPLEMENTED();
> +}
> +
> +int
> +rte_mp_action_register(const char *name, rte_mp_t action)
> +{
> + RTE_SET_USED(name);
> + RTE_SET_USED(action);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +void
> +rte_mp_action_unregister(const char *name)
> +{
> + RTE_SET_USED(name);
> + EAL_LOG_NOT_IMPLEMENTED();
> +}
> +
> +int
> +rte_mp_sendmsg(struct rte_mp_msg *msg)
> +{
> + RTE_SET_USED(msg);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
> + const struct timespec *ts)
> +{
> + RTE_SET_USED(req);
> + RTE_SET_USED(reply);
> + RTE_SET_USED(ts);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
> + rte_mp_async_reply_t clb)
> +{
> + RTE_SET_USED(req);
> + RTE_SET_USED(ts);
> + RTE_SET_USED(clb);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
> +{
> + RTE_SET_USED(msg);
> + RTE_SET_USED(peer);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +register_mp_requests(void)
> +{
> + /* Non-stub function succeeds if multi-process is not supported. */
> + EAL_LOG_STUB();
> + return 0;
> +}
> +
> +int
> +request_to_primary(struct malloc_mp_req *req)
> +{
> + RTE_SET_USED(req);
> + EAL_LOG_NOT_IMPLEMENTED();
> + return -1;
> +}
> +
> +int
> +request_sync(void)
> +{
> + /* Common memory allocator depends on this function success. */
> + EAL_LOG_STUB();
> + return 0;
> +}
> diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
> index b202a1aa5..083ab8b93 100644
> --- a/lib/librte_eal/windows/eal_windows.h
> +++ b/lib/librte_eal/windows/eal_windows.h
> @@ -9,8 +9,24 @@
> * @file Facilities private to Windows EAL
> */
>
> +#include <rte_errno.h>
> #include <rte_windows.h>
>
> +/**
> + * Log current function as not implemented and set rte_errno.
> + */
> +#define EAL_LOG_NOT_IMPLEMENTED() \
> + do { \
> + RTE_LOG(DEBUG, EAL, "%s() is not implemented\n", __func__); \
> + rte_errno = ENOTSUP; \
> + } while (0)
> +
> +/**
> + * Log current function as a stub.
> + */
> +#define EAL_LOG_STUB() \
> + RTE_LOG(DEBUG, EAL, "Windows: %s() is a stub\n", __func__)
> +
> /**
> * Create a map of processors and cores on the system.
> */
> @@ -36,6 +52,13 @@ int eal_thread_create(pthread_t *thread);
> */
> unsigned int eal_socket_numa_node(unsigned int socket_id);
>
> +/**
> + * Open virt2phys driver interface device.
> + *
> + * @return 0 on success, (-1) on failure.
> + */
> +int eal_mem_virt2iova_init(void);
> +
> /**
> * Locate Win32 memory management routines in system libraries.
> *
> diff --git a/lib/librte_eal/windows/include/meson.build b/lib/librte_eal/windows/include/meson.build
> index 5fb1962ac..b3534b025 100644
> --- a/lib/librte_eal/windows/include/meson.build
> +++ b/lib/librte_eal/windows/include/meson.build
> @@ -5,5 +5,6 @@ includes += include_directories('.')
>
> headers += files(
> 'rte_os.h',
> + 'rte_virt2phys.h',
> 'rte_windows.h',
> )
> diff --git a/lib/librte_eal/windows/include/rte_os.h b/lib/librte_eal/windows/include/rte_os.h
> index 510e39e03..62805a307 100644
> --- a/lib/librte_eal/windows/include/rte_os.h
> +++ b/lib/librte_eal/windows/include/rte_os.h
> @@ -36,6 +36,10 @@ extern "C" {
>
> #define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
>
> +#define open _open
> +#define close _close
> +#define unlink _unlink
> +
> /* cpu_set macros implementation */
> #define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
> #define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
> diff --git a/lib/librte_eal/windows/include/rte_virt2phys.h b/lib/librte_eal/windows/include/rte_virt2phys.h
> new file mode 100644
> index 000000000..4bb2b4aaf
> --- /dev/null
> +++ b/lib/librte_eal/windows/include/rte_virt2phys.h
> @@ -0,0 +1,34 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2020 Dmitry Kozlyuk
> + */
> +
> +/**
> + * @file virt2phys driver interface
> + */
> +
> +/**
> + * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
> + */
> +DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
> + 0x539c2135, 0x793a, 0x4926,
> + 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
> +
> +/**
> + * Driver device type for IO control codes.
> + */
> +#define VIRT2PHYS_DEVTYPE 0x8000
> +
> +/**
> + * Translate a valid non-paged virtual address to a physical address.
> + *
> + * Note: A physical address zero (0) is reported if input address
> + * is paged out or not mapped. However, if input is a valid mapping
> + * of I/O port 0x0000, output is also zero. There is no way
> + * to distinguish between these cases by return value only.
> + *
> + * Input: a non-paged virtual address (PVOID).
> + *
> + * Output: the corresponding physical address (LARGE_INTEGER).
> + */
> +#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
> + VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
> diff --git a/lib/librte_eal/windows/include/rte_windows.h b/lib/librte_eal/windows/include/rte_windows.h
> index ed6e4c148..899ed7d87 100644
> --- a/lib/librte_eal/windows/include/rte_windows.h
> +++ b/lib/librte_eal/windows/include/rte_windows.h
> @@ -23,6 +23,8 @@
>
> #include <basetsd.h>
> #include <psapi.h>
> +#include <setupapi.h>
> +#include <winioctl.h>
>
> /* Have GUIDs defined. */
> #ifndef INITGUID
> diff --git a/lib/librte_eal/windows/include/unistd.h b/lib/librte_eal/windows/include/unistd.h
> index 757b7f3c5..6b33005b2 100644
> --- a/lib/librte_eal/windows/include/unistd.h
> +++ b/lib/librte_eal/windows/include/unistd.h
> @@ -9,4 +9,7 @@
> * as Microsoft libc does not contain unistd.h. This may be removed
> * in future releases.
> */
> +
> +#include <io.h>
> +
> #endif /* _UNISTD_H_ */
> diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
> index 81d3ee095..2f4fa91a9 100644
> --- a/lib/librte_eal/windows/meson.build
> +++ b/lib/librte_eal/windows/meson.build
> @@ -8,7 +8,9 @@ sources += files(
> 'eal_debug.c',
> 'eal_hugepages.c',
> 'eal_lcore.c',
> + 'eal_memalloc.c',
> 'eal_memory.c',
> + 'eal_mp.c',
> 'eal_thread.c',
> 'getopt.c',
> )
> --
> 2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management
2020-04-10 22:04 ` Narcisa Ana Maria Vasile
@ 2020-04-11 1:16 ` Dmitry Kozlyuk
0 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-11 1:16 UTC (permalink / raw)
To: Narcisa Ana Maria Vasile
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon, John McNamara, Marko Kovacevic,
Anatoly Burakov, Bruce Richardson
[snip]
> > +static int
> > +alloc_seg(struct rte_memseg *ms, void *requested_addr, int socket_id,
> > + struct hugepage_info *hi)
> > +{
> > + HANDLE current_process;
> > + unsigned int numa_node;
> > + size_t alloc_sz;
> > + void *addr;
> > + rte_iova_t iova = RTE_BAD_IOVA;
> > + PSAPI_WORKING_SET_EX_INFORMATION info;
> > + PSAPI_WORKING_SET_EX_BLOCK *page;
> > +
> > + if (ms->len > 0) {
> > + /* If a segment is already allocated as needed, return it. */
> > + if ((ms->addr == requested_addr) &&
> > + (ms->socket_id == socket_id) &&
> > + (ms->hugepage_sz == hi->hugepage_sz)) {
> > + return 0;
> > + }
> > +
> > + /* Bugcheck, should not happen. */
> > + RTE_LOG(DEBUG, EAL, "Attempted to reallocate segment %p "
> > + "(size %zu) on socket %d", ms->addr,
> > + ms->len, ms->socket_id);
> > + return -1;
> > + }
> > +
> > + current_process = GetCurrentProcess();
> > + numa_node = eal_socket_numa_node(socket_id);
> > + alloc_sz = hi->hugepage_sz;
> > +
> > + if (requested_addr == NULL) {
> > + /* Request a new chunk of memory and enforce address hint. */
>
> Does requested_addr being NULL means that no hint was provided? It also looks like eal_mem_alloc_socket
> ignores the address hint anyway and just calls VirtualAllocExNuma with NULL for lpAddress. Maybe remove
> the second part of the comment.
Correct, also see below.
>
> > + addr = eal_mem_alloc_socket(alloc_sz, socket_id);
> > + if (addr == NULL) {
> > + RTE_LOG(DEBUG, EAL, "Cannot allocate %zu bytes "
> > + "on socket %d\n", alloc_sz, socket_id);
> > + return -1;
> > + }
> > +
> > + if (addr != requested_addr) {
>
> requested_addr is NULL on this branch and we confirmed with the previous 'if' that addr is not NULL.
> Should this branch be removed, since requested_addr is NULL, so there is no hint provided?
Good catch, this check doesn't belong here. In fact, apart from an allocation
failure, address hint might not be respected iff the hint is not aligned to
hugepage boundary, which would be an allocator bug (use of an incorrect MSL).
> > + RTE_LOG(DEBUG, EAL, "Address hint %p not respected, "
> > + "got %p\n", requested_addr, addr);
> > + goto error;
> > + }
> > + } else {
> > + /* Requested address is already reserved, commit memory. */
> > + addr = eal_mem_commit(requested_addr, alloc_sz, socket_id);
> > + if (addr == NULL) {
> > + RTE_LOG(DEBUG, EAL, "Cannot commit reserved memory %p "
> > + "(size %zu)\n", requested_addr, alloc_sz);
> > + goto error;
>
> Execution jumps to 'error' with an invalid addr, so it will try to call eal_mem_decommit with NULL as parameter.
> Instead of 'goto error', maybe we should return here.
Will fix in v3.
I'd like to also clarify the following. On Windows, eal_mem_commit() is not
atomic: it may first split a reserved region, then commit it. If splitting
succeeds and commit fails, the reserved region remains split into parts.
eal_mem_decommit() does not coalesce these parts intentionally: they're
hugepage-sized, so the next eal_mem_commit() on the same region just doesn't
have to split it.
>
> > + }
> > + }
> > +
> > + /* Force OS to allocate a physical page and select a NUMA node.
> > + * Hugepages are not pageable in Windows, so there's no race
> > + * for physical address.
> > + */
> > + *(volatile int *)addr = *(volatile int *)addr;
> > +
> > + /* Only try to obtain IOVA if it's available, so that applications
> > + * that do not need IOVA can use this allocator.
> > + */
> > + if (rte_eal_using_phys_addrs()) {
> > + iova = rte_mem_virt2iova(addr);
> > + if (iova == RTE_BAD_IOVA) {
> > + RTE_LOG(DEBUG, EAL,
> > + "Cannot get IOVA of allocated segment\n");
> > + goto error;
> > + }
> > + }
> > +
> > + /* Only "Ex" function can handle hugepages. */
> > + info.VirtualAddress = addr;
> > + if (!QueryWorkingSetEx(current_process, &info, sizeof(info))) {
> > + RTE_LOG_WIN32_ERR("QueryWorkingSetEx()");
> > + goto error;
> > + }
> > +
> > + page = &info.VirtualAttributes;
> > + if (!page->Valid || !page->LargePage) {
> > + RTE_LOG(DEBUG, EAL, "Got regular page instead of hugepage\n");
> > + goto error;
> > + }
> > + if (page->Node != numa_node) {
> > + RTE_LOG(DEBUG, EAL,
> > + "NUMA node hint %u (socket %d) not respected, got %u\n",
> > + numa_node, socket_id, page->Node);
> > + goto error;
> > + }
> > +
> > + ms->addr = addr;
> > + ms->hugepage_sz = hi->hugepage_sz;
> > + ms->len = alloc_sz;
> > + ms->nchannel = rte_memory_get_nchannel();
> > + ms->nrank = rte_memory_get_nrank();
> > + ms->iova = iova;
> > + ms->socket_id = socket_id;
> > +
> > + return 0;
> > +
> > +error:
> > + /* Only jump here when `addr` and `alloc_sz` are valid. */
> > + eal_mem_decommit(addr, alloc_sz);
> > + return -1;
> > +}
[snip]
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 00/10] Windows basic memory management
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (9 preceding siblings ...)
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
` (10 more replies)
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 0/8] " Dmitry Kozlyuk
11 siblings, 11 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk
Note: no changes in cover letter since v2.
This patchset implements basic MM with the following features:
* Hugepages are dynamically allocated in user-mode.
* Only 2MB hugepages are supported.
* IOVA is always PA, obtained through kernel-mode driver.
* No 32-bit support (presumably not demanded).
* Ni multi-process support (it is forcefully disabled).
* No-huge mode for testing with IOVA unavailable.
The first commit introduces a new kernel-mode driver, virt2phys.
It translates user-mode virtual addresses into physical addresses.
On Windows community call 2020-04-01 it was decided this driver can be
used for now, later netUIO may pick up its code/interface or not.
New EAL public functions for memory mapping are introduced
to mitigate OS differences in DPDK libraries and applications:
* rte_mem_map
* rte_mem_unmap
* rte_mem_lock
To support common MM routines, internal wrappers for low-level
memory reservation and file management are introduced. These changes
affect Linux and FreeBSD EAL. Shared code is placed unded /unix/
subdirectory (suggested by Thomas).
Also, entire <sys/queue.h> is imported from FreeBSD, replacing existing
partial import. There is already a license exception for this file.
Windows MM duplicates quite a lot of code from Linux EAL:
* eal_memalloc_alloc_seg_bulk
* eal_memalloc_free_seg_bulk
* calc_num_pages_per_socket
* rte_eal_hugepage_init
Perhaps this should be left as-is until Windows MM evolves into having
some specific requirements for these parts.
Notes on checkpatch warnings:
* No space after comma / no space before closing parent in macros---
definitely a false-positive, unclear how to suppress this.
* Issues from imported BSD code---probably should be ignored?
* Checkpatch is not run against dpdk-kmods (Windows drivers).
---
v3:
* Fix Linux build on and aarch64 and 32-bit x86 (reported by CI).
* Fix logic and error handling while allocating segments.
* Fix Unix rte_mem_map(): return NULL on failure.
* Fix some checkpatch.sh issues:
* Do not return positive errno, use DWORD for GetLastError().
* Make dpdk-kmods source files non-executable.
* Improve GSG for Windows Server (suggested by Ranjit Menon).
v2:
* Rebase on ToT. Move all new code shared between Linux and FreeBSD
to /unix/ subdirectory, also factor out some existing code there.
* Improve description of Clang issue with rte_page_sizes on Windows.
Restore -fstrict-enum for EAL. Check running, not target compiler.
* Use EAL prefix for private facilities instead if RTE.
* Improve documentation comments for new functions.
* Remove co-installer for virt2phys. Add a typecast for clarity.
* Document virt2phys in user guide, improve its own README.
* Explicitly and forcefully disable multi-process.
Dmitry Kozlyuk (9):
eal/windows: do not expose private EAL facilities
eal/windows: improve CPU and NUMA node detection
eal/windows: initialize hugepage info
eal: introduce internal wrappers for file operations
eal: introduce memory management wrappers
eal: extract common code for memseg list initialization
eal/windows: fix rte_page_sizes with Clang on Windows
eal/windows: replace sys/queue.h with a complete one from FreeBSD
eal/windows: implement basic memory management
config/meson.build | 12 +-
doc/guides/windows_gsg/build_dpdk.rst | 20 -
doc/guides/windows_gsg/index.rst | 1 +
doc/guides/windows_gsg/run_apps.rst | 84 ++
lib/librte_eal/common/eal_common_fbarray.c | 57 +-
lib/librte_eal/common/eal_common_memory.c | 104 +-
lib/librte_eal/common/eal_private.h | 134 +-
lib/librte_eal/common/malloc_heap.c | 1 +
lib/librte_eal/common/meson.build | 9 +
lib/librte_eal/freebsd/eal_memory.c | 55 +-
lib/librte_eal/include/rte_memory.h | 74 ++
lib/librte_eal/linux/eal_memory.c | 68 +-
lib/librte_eal/meson.build | 4 +
lib/librte_eal/rte_eal_exports.def | 119 ++
lib/librte_eal/rte_eal_version.map | 4 +
lib/librte_eal/unix/eal.c | 47 +
lib/librte_eal/unix/eal_memory.c | 113 ++
lib/librte_eal/unix/meson.build | 7 +
lib/librte_eal/windows/eal.c | 160 +++
lib/librte_eal/windows/eal_hugepages.c | 108 ++
lib/librte_eal/windows/eal_lcore.c | 187 ++-
lib/librte_eal/windows/eal_memalloc.c | 418 ++++++
lib/librte_eal/windows/eal_memory.c | 1141 +++++++++++++++++
lib/librte_eal/windows/eal_mp.c | 103 ++
lib/librte_eal/windows/eal_thread.c | 1 +
lib/librte_eal/windows/eal_windows.h | 129 ++
lib/librte_eal/windows/include/meson.build | 2 +
lib/librte_eal/windows/include/pthread.h | 2 +
lib/librte_eal/windows/include/rte_os.h | 48 +-
.../windows/include/rte_virt2phys.h | 34 +
lib/librte_eal/windows/include/rte_windows.h | 43 +
lib/librte_eal/windows/include/sys/queue.h | 663 +++++++++-
lib/librte_eal/windows/include/unistd.h | 3 +
lib/librte_eal/windows/meson.build | 6 +
34 files changed, 3611 insertions(+), 350 deletions(-)
create mode 100644 doc/guides/windows_gsg/run_apps.rst
create mode 100644 lib/librte_eal/unix/eal.c
create mode 100644 lib/librte_eal/unix/eal_memory.c
create mode 100644 lib/librte_eal/unix/meson.build
create mode 100644 lib/librte_eal/windows/eal_hugepages.c
create mode 100644 lib/librte_eal/windows/eal_memalloc.c
create mode 100644 lib/librte_eal/windows/eal_memory.c
create mode 100644 lib/librte_eal/windows/eal_mp.c
create mode 100644 lib/librte_eal/windows/eal_windows.h
create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
create mode 100644 lib/librte_eal/windows/include/rte_windows.h
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-14 23:35 ` Ranjit Menon
2020-04-21 6:23 ` Ophir Munk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 02/10] eal/windows: do not expose private EAL facilities Dmitry Kozlyuk
` (9 subsequent siblings)
10 siblings, 2 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Ranjit Menon
This driver supports Windows EAL memory management by translating
current process virtual addresses to physical addresses (IOVA).
Standalone virt2phys allows using DPDK without PMD and provides a
reference implementation.
Suggested-by: Ranjit Menon <ranjit.menon@intel.com>
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
windows/README.rst | 103 +++++++++
windows/virt2phys/virt2phys.c | 129 +++++++++++
windows/virt2phys/virt2phys.h | 34 +++
windows/virt2phys/virt2phys.inf | 64 ++++++
windows/virt2phys/virt2phys.sln | 27 +++
windows/virt2phys/virt2phys.vcxproj | 228 ++++++++++++++++++++
windows/virt2phys/virt2phys.vcxproj.filters | 36 ++++
7 files changed, 621 insertions(+)
create mode 100644 windows/README.rst
create mode 100644 windows/virt2phys/virt2phys.c
create mode 100644 windows/virt2phys/virt2phys.h
create mode 100644 windows/virt2phys/virt2phys.inf
create mode 100644 windows/virt2phys/virt2phys.sln
create mode 100644 windows/virt2phys/virt2phys.vcxproj
create mode 100644 windows/virt2phys/virt2phys.vcxproj.filters
diff --git a/windows/README.rst b/windows/README.rst
new file mode 100644
index 0000000..45a1d80
--- /dev/null
+++ b/windows/README.rst
@@ -0,0 +1,103 @@
+Developing Windows Drivers
+==========================
+
+Prerequisites
+-------------
+
+Building Windows Drivers is only possible on Windows.
+
+1. Visual Studio 2019 Community or Professional Edition
+2. Windows Driver Kit (WDK) for Windows 10, version 1903
+
+Follow the official instructions to obtain all of the above:
+https://docs.microsoft.com/en-us/windows-hardware/drivers/download-the-wdk
+
+
+Build the Drivers
+-----------------
+
+Build from Visual Studio
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Open a solution (``*.sln``) with Visual Studio and build it (Ctrl+Shift+B).
+
+
+Build from Command-Line
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Run *Developer Command Prompt for VS 2019* from the Start menu.
+
+Navigate to the solution directory (with ``*.sln``), then run:
+
+.. code-block:: console
+
+ msbuild
+
+To build a particular combination of configuration and platform:
+
+.. code-block:: console
+
+ msbuild -p:Configuration=Debug;Platform=x64
+
+
+Install the Drivers
+-------------------
+
+Disable Driver Signature Enforcement
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default Windows prohibits installing and loading drivers without `digital
+signature`_ obtained from Microsoft. For development signature enforcement may
+be disabled as follows.
+
+In Elevated Command Prompt (from this point, sufficient privileges are
+assumed):
+
+.. code-block:: console
+
+ bcdedit -set loadoptions DISABLE_INTEGRITY_CHECKS
+ bcdedit -set TESTSIGNING ON
+ shutdown -r -t 0
+
+Upon reboot, an overlay message should appear on the desktop informing
+that Windows is in test mode, which means it allows loading unsigned drivers.
+
+.. _digital signature: https://docs.microsoft.com/en-us/windows-hardware/drivers/install/driver-signing
+
+Install, List, and Remove Drivers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Driver package is by default located in a subdirectory of its source tree,
+e.g. ``x64\Debug\virt2phys\virt2phys`` (note two levels of ``virt2phys``).
+
+To install the driver and bind associated devices to it:
+
+.. code-block:: console
+
+ pnputil /add-driver x64\Debug\virt2phys\virt2phys\virt2phys.inf /install
+
+A graphical confirmation to load an unsigned driver will still appear.
+
+On Windows Server additional steps are required if the driver uses a custom
+setup class:
+
+1. From "Device Manager", "Action" menu, select "Add legacy hardware".
+2. It will launch the "Add Hardware Wizard". Click "Next".
+3. Select second option "Install the hardware that I manually select
+ from a list (Advanced)".
+4. On the next screen, locate the driver device class.
+5. Select it, and click "Next".
+6. The previously installed drivers will now be installed for
+ the appropriate devices (software devices will be created).
+
+To list installed drivers:
+
+.. code-block:: console
+
+ pnputil /enum-drivers
+
+To remove the driver package and to uninstall its devices:
+
+.. code-block:: console
+
+ pnputil /delete-driver oem2.inf /uninstall
diff --git a/windows/virt2phys/virt2phys.c b/windows/virt2phys/virt2phys.c
new file mode 100644
index 0000000..e157e9c
--- /dev/null
+++ b/windows/virt2phys/virt2phys.c
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Dmitry Kozlyuk
+ */
+
+#include <ntddk.h>
+#include <wdf.h>
+#include <wdmsec.h>
+#include <initguid.h>
+
+#include "virt2phys.h"
+
+DRIVER_INITIALIZE DriverEntry;
+EVT_WDF_DRIVER_DEVICE_ADD virt2phys_driver_EvtDeviceAdd;
+EVT_WDF_IO_IN_CALLER_CONTEXT virt2phys_device_EvtIoInCallerContext;
+
+NTSTATUS
+DriverEntry(
+ IN PDRIVER_OBJECT driver_object, IN PUNICODE_STRING registry_path)
+{
+ WDF_DRIVER_CONFIG config;
+ WDF_OBJECT_ATTRIBUTES attributes;
+ NTSTATUS status;
+
+ PAGED_CODE();
+
+ WDF_DRIVER_CONFIG_INIT(&config, virt2phys_driver_EvtDeviceAdd);
+ WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
+ status = WdfDriverCreate(
+ driver_object, registry_path,
+ &attributes, &config, WDF_NO_HANDLE);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDriverCreate() failed, status=%08x\n", status));
+ }
+
+ return status;
+}
+
+_Use_decl_annotations_
+NTSTATUS
+virt2phys_driver_EvtDeviceAdd(
+ WDFDRIVER driver, PWDFDEVICE_INIT init)
+{
+ WDF_OBJECT_ATTRIBUTES attributes;
+ WDFDEVICE device;
+ NTSTATUS status;
+
+ UNREFERENCED_PARAMETER(driver);
+
+ PAGED_CODE();
+
+ WdfDeviceInitSetIoType(
+ init, WdfDeviceIoNeither);
+ WdfDeviceInitSetIoInCallerContextCallback(
+ init, virt2phys_device_EvtIoInCallerContext);
+
+ WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
+
+ status = WdfDeviceCreate(&init, &attributes, &device);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDeviceCreate() failed, status=%08x\n", status));
+ return status;
+ }
+
+ status = WdfDeviceCreateDeviceInterface(
+ device, &GUID_DEVINTERFACE_VIRT2PHYS, NULL);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfDeviceCreateDeviceInterface() failed, "
+ "status=%08x\n", status));
+ return status;
+ }
+
+ return STATUS_SUCCESS;
+}
+
+_Use_decl_annotations_
+VOID
+virt2phys_device_EvtIoInCallerContext(
+ IN WDFDEVICE device, IN WDFREQUEST request)
+{
+ WDF_REQUEST_PARAMETERS params;
+ ULONG code;
+ PVOID *virt;
+ PHYSICAL_ADDRESS *phys;
+ size_t size;
+ NTSTATUS status;
+
+ UNREFERENCED_PARAMETER(device);
+
+ PAGED_CODE();
+
+ WDF_REQUEST_PARAMETERS_INIT(¶ms);
+ WdfRequestGetParameters(request, ¶ms);
+
+ if (params.Type != WdfRequestTypeDeviceControl) {
+ KdPrint(("bogus request type=%u\n", params.Type));
+ WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
+ return;
+ }
+
+ code = params.Parameters.DeviceIoControl.IoControlCode;
+ if (code != IOCTL_VIRT2PHYS_TRANSLATE) {
+ KdPrint(("bogus IO control code=%lu\n", code));
+ WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
+ return;
+ }
+
+ status = WdfRequestRetrieveInputBuffer(
+ request, sizeof(*virt), (PVOID *)&virt, &size);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfRequestRetrieveInputBuffer() failed, "
+ "status=%08x\n", status));
+ WdfRequestComplete(request, status);
+ return;
+ }
+
+ status = WdfRequestRetrieveOutputBuffer(
+ request, sizeof(*phys), (PVOID *)&phys, &size);
+ if (!NT_SUCCESS(status)) {
+ KdPrint(("WdfRequestRetrieveOutputBuffer() failed, "
+ "status=%08x\n", status));
+ WdfRequestComplete(request, status);
+ return;
+ }
+
+ *phys = MmGetPhysicalAddress(*virt);
+
+ WdfRequestCompleteWithInformation(
+ request, STATUS_SUCCESS, sizeof(*phys));
+}
diff --git a/windows/virt2phys/virt2phys.h b/windows/virt2phys/virt2phys.h
new file mode 100644
index 0000000..4bb2b4a
--- /dev/null
+++ b/windows/virt2phys/virt2phys.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file virt2phys driver interface
+ */
+
+/**
+ * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
+ */
+DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
+ 0x539c2135, 0x793a, 0x4926,
+ 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
+
+/**
+ * Driver device type for IO control codes.
+ */
+#define VIRT2PHYS_DEVTYPE 0x8000
+
+/**
+ * Translate a valid non-paged virtual address to a physical address.
+ *
+ * Note: A physical address zero (0) is reported if input address
+ * is paged out or not mapped. However, if input is a valid mapping
+ * of I/O port 0x0000, output is also zero. There is no way
+ * to distinguish between these cases by return value only.
+ *
+ * Input: a non-paged virtual address (PVOID).
+ *
+ * Output: the corresponding physical address (LARGE_INTEGER).
+ */
+#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
+ VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
diff --git a/windows/virt2phys/virt2phys.inf b/windows/virt2phys/virt2phys.inf
new file mode 100644
index 0000000..e35765e
--- /dev/null
+++ b/windows/virt2phys/virt2phys.inf
@@ -0,0 +1,64 @@
+; SPDX-License-Identifier: BSD-3-Clause
+; Copyright (c) 2020 Dmitry Kozlyuk
+
+[Version]
+Signature = "$WINDOWS NT$"
+Class = %ClassName%
+ClassGuid = {78A1C341-4539-11d3-B88D-00C04FAD5171}
+Provider = %ManufacturerName%
+CatalogFile = virt2phys.cat
+DriverVer =
+
+[DestinationDirs]
+DefaultDestDir = 12
+
+; ================= Class section =====================
+
+[ClassInstall32]
+Addreg = virt2phys_ClassReg
+
+[virt2phys_ClassReg]
+HKR,,,0,%ClassName%
+HKR,,Icon,,-5
+
+[SourceDisksNames]
+1 = %DiskName%,,,""
+
+[SourceDisksFiles]
+virt2phys.sys = 1,,
+
+;*****************************************
+; Install Section
+;*****************************************
+
+[Manufacturer]
+%ManufacturerName%=Standard,NT$ARCH$
+
+[Standard.NT$ARCH$]
+%virt2phys.DeviceDesc%=virt2phys_Device, Root\virt2phys
+
+[virt2phys_Device.NT]
+CopyFiles = Drivers_Dir
+
+[Drivers_Dir]
+virt2phys.sys
+
+;-------------- Service installation
+[virt2phys_Device.NT.Services]
+AddService = virt2phys,%SPSVCINST_ASSOCSERVICE%, virt2phys_Service_Inst
+
+; -------------- virt2phys driver install sections
+[virt2phys_Service_Inst]
+DisplayName = %virt2phys.SVCDESC%
+ServiceType = 1 ; SERVICE_KERNEL_DRIVER
+StartType = 3 ; SERVICE_DEMAND_START
+ErrorControl = 1 ; SERVICE_ERROR_NORMAL
+ServiceBinary = %12%\virt2phys.sys
+
+[Strings]
+SPSVCINST_ASSOCSERVICE = 0x00000002
+ManufacturerName = "Dmitry Kozlyuk"
+ClassName = "Kernel bypass"
+DiskName = "virt2phys Installation Disk"
+virt2phys.DeviceDesc = "Virtual to physical address translator"
+virt2phys.SVCDESC = "virt2phys Service"
diff --git a/windows/virt2phys/virt2phys.sln b/windows/virt2phys/virt2phys.sln
new file mode 100644
index 0000000..0f5ecdc
--- /dev/null
+++ b/windows/virt2phys/virt2phys.sln
@@ -0,0 +1,27 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 16
+VisualStudioVersion = 16.0.29613.14
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "virt2phys", "virt2phys.vcxproj", "{0EEF826B-9391-43A8-A722-BDD6F6115137}"
+EndProject
+Global
+ GlobalSection(SolutionConfigurationPlatforms) = preSolution
+ Debug|x64 = Debug|x64
+ Release|x64 = Release|x64
+ EndGlobalSection
+ GlobalSection(ProjectConfigurationPlatforms) = postSolution
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.ActiveCfg = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.Build.0 = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.Deploy.0 = Debug|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.ActiveCfg = Release|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.Build.0 = Release|x64
+ {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.Deploy.0 = Release|x64
+ EndGlobalSection
+ GlobalSection(SolutionProperties) = preSolution
+ HideSolutionNode = FALSE
+ EndGlobalSection
+ GlobalSection(ExtensibilityGlobals) = postSolution
+ SolutionGuid = {845012FB-4471-4A12-A1C4-FF7E05C40E8E}
+ EndGlobalSection
+EndGlobal
diff --git a/windows/virt2phys/virt2phys.vcxproj b/windows/virt2phys/virt2phys.vcxproj
new file mode 100644
index 0000000..fa51916
--- /dev/null
+++ b/windows/virt2phys/virt2phys.vcxproj
@@ -0,0 +1,228 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" ToolsVersion="12.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup Label="ProjectConfigurations">
+ <ProjectConfiguration Include="Debug|Win32">
+ <Configuration>Debug</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|Win32">
+ <Configuration>Release</Configuration>
+ <Platform>Win32</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|x64">
+ <Configuration>Debug</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|x64">
+ <Configuration>Release</Configuration>
+ <Platform>x64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|ARM">
+ <Configuration>Debug</Configuration>
+ <Platform>ARM</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|ARM">
+ <Configuration>Release</Configuration>
+ <Platform>ARM</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Debug|ARM64">
+ <Configuration>Debug</Configuration>
+ <Platform>ARM64</Platform>
+ </ProjectConfiguration>
+ <ProjectConfiguration Include="Release|ARM64">
+ <Configuration>Release</Configuration>
+ <Platform>ARM64</Platform>
+ </ProjectConfiguration>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="virt2phys.c" />
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="virt2phys.h" />
+ </ItemGroup>
+ <ItemGroup>
+ <Inf Include="virt2phys.inf" />
+ </ItemGroup>
+ <PropertyGroup Label="Globals">
+ <ProjectGuid>{0EEF826B-9391-43A8-A722-BDD6F6115137}</ProjectGuid>
+ <TemplateGuid>{497e31cb-056b-4f31-abb8-447fd55ee5a5}</TemplateGuid>
+ <TargetFrameworkVersion>v4.5</TargetFrameworkVersion>
+ <MinimumVisualStudioVersion>12.0</MinimumVisualStudioVersion>
+ <Configuration>Debug</Configuration>
+ <Platform Condition="'$(Platform)' == ''">Win32</Platform>
+ <RootNamespace>virt2phys</RootNamespace>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>true</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'" Label="Configuration">
+ <TargetVersion>Windows10</TargetVersion>
+ <UseDebugLibraries>false</UseDebugLibraries>
+ <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>
+ <ConfigurationType>Driver</ConfigurationType>
+ <DriverType>KMDF</DriverType>
+ <DriverTargetPlatform>Universal</DriverTargetPlatform>
+ </PropertyGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+ <ImportGroup Label="ExtensionSettings">
+ </ImportGroup>
+ <ImportGroup Label="PropertySheets">
+ <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+ </ImportGroup>
+ <PropertyGroup Label="UserMacros" />
+ <PropertyGroup />
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">
+ <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>
+ </PropertyGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+ <ClCompile>
+ <WppEnabled>false</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ <Link>
+ <AdditionalDependencies>$(DDK_LIB_PATH)wdmsec.lib;%(AdditionalDependencies)</AdditionalDependencies>
+ </Link>
+ <Inf>
+ <TimeStamp>0.1</TimeStamp>
+ </Inf>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">
+ <ClCompile>
+ <WppEnabled>true</WppEnabled>
+ <WppRecorderEnabled>true</WppRecorderEnabled>
+ <WppScanConfigurationData Condition="'%(ClCompile.ScanConfigurationData)' == ''">trace.h</WppScanConfigurationData>
+ <WppKernelMode>true</WppKernelMode>
+ </ClCompile>
+ </ItemDefinitionGroup>
+ <ItemGroup>
+ <FilesToPackage Include="$(TargetPath)" />
+ </ItemGroup>
+ <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+ <ImportGroup Label="ExtensionTargets">
+ </ImportGroup>
+</Project>
\ No newline at end of file
diff --git a/windows/virt2phys/virt2phys.vcxproj.filters b/windows/virt2phys/virt2phys.vcxproj.filters
new file mode 100644
index 0000000..0fe65fc
--- /dev/null
+++ b/windows/virt2phys/virt2phys.vcxproj.filters
@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+ <ItemGroup>
+ <Filter Include="Source Files">
+ <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
+ <Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+ </Filter>
+ <Filter Include="Header Files">
+ <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+ <Extensions>h;hpp;hxx;hm;inl;inc;xsd</Extensions>
+ </Filter>
+ <Filter Include="Resource Files">
+ <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+ <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
+ </Filter>
+ <Filter Include="Driver Files">
+ <UniqueIdentifier>{8E41214B-6785-4CFE-B992-037D68949A14}</UniqueIdentifier>
+ <Extensions>inf;inv;inx;mof;mc;</Extensions>
+ </Filter>
+ </ItemGroup>
+ <ItemGroup>
+ <Inf Include="virt2phys.inf">
+ <Filter>Driver Files</Filter>
+ </Inf>
+ </ItemGroup>
+ <ItemGroup>
+ <ClInclude Include="virt2phys.h">
+ <Filter>Header Files</Filter>
+ </ClInclude>
+ </ItemGroup>
+ <ItemGroup>
+ <ClCompile Include="virt2phys.c">
+ <Filter>Source Files</Filter>
+ </ClCompile>
+ </ItemGroup>
+</Project>
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
@ 2020-04-14 23:35 ` Ranjit Menon
2020-04-15 15:19 ` Thomas Monjalon
2020-04-21 6:23 ` Ophir Munk
1 sibling, 1 reply; 218+ messages in thread
From: Ranjit Menon @ 2020-04-14 23:35 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman
On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> This driver supports Windows EAL memory management by translating
> current process virtual addresses to physical addresses (IOVA).
> Standalone virt2phys allows using DPDK without PMD and provides a
> reference implementation.
>
> Suggested-by: Ranjit Menon <ranjit.menon@intel.com>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> windows/README.rst | 103 +++++++++
> windows/virt2phys/virt2phys.c | 129 +++++++++++
> windows/virt2phys/virt2phys.h | 34 +++
> windows/virt2phys/virt2phys.inf | 64 ++++++
> windows/virt2phys/virt2phys.sln | 27 +++
> windows/virt2phys/virt2phys.vcxproj | 228 ++++++++++++++++++++
> windows/virt2phys/virt2phys.vcxproj.filters | 36 ++++
> 7 files changed, 621 insertions(+)
> create mode 100644 windows/README.rst
> create mode 100644 windows/virt2phys/virt2phys.c
> create mode 100644 windows/virt2phys/virt2phys.h
> create mode 100644 windows/virt2phys/virt2phys.inf
> create mode 100644 windows/virt2phys/virt2phys.sln
> create mode 100644 windows/virt2phys/virt2phys.vcxproj
> create mode 100644 windows/virt2phys/virt2phys.vcxproj.filters
>
Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
Acked-by: Ranjit Menon <ranjit.menon@intel.com>
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows
2020-04-14 23:35 ` Ranjit Menon
@ 2020-04-15 15:19 ` Thomas Monjalon
0 siblings, 0 replies; 218+ messages in thread
From: Thomas Monjalon @ 2020-04-15 15:19 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Ranjit Menon
15/04/2020 01:35, Ranjit Menon:
> On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> > This driver supports Windows EAL memory management by translating
> > current process virtual addresses to physical addresses (IOVA).
> > Standalone virt2phys allows using DPDK without PMD and provides a
> > reference implementation.
> >
> > Suggested-by: Ranjit Menon <ranjit.menon@intel.com>
> > Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
>
> Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
> Acked-by: Ranjit Menon <ranjit.menon@intel.com>
Applied in dpdk-kmods, thanks.
This is the very first kernel module in this repository:
http://git.dpdk.org/dpdk-kmods/
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
2020-04-14 23:35 ` Ranjit Menon
@ 2020-04-21 6:23 ` Ophir Munk
1 sibling, 0 replies; 218+ messages in thread
From: Ophir Munk @ 2020-04-21 6:23 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Ranjit Menon, Thomas Monjalon
Hi Dmitry,
When trying to test the series under Linux (RedHat 7.4, x86_64-native-linuxapp-gcc) I get compilation errors. I am using make.
It seems that there are calls from common which are not compiled under linux.
x86_64-native-linuxapp-gcc/lib/librte_eal.a(eal_common_memory.o): In function `eal_get_virtual_area':
eal_common_memory.c:(.text+0x27e): undefined reference to `eal_mem_reserve'
[dpdk-branches]$ find lib -name '*.c' | xargs grep eal_mem_reserve
lib/librte_eal/common/eal_common_memory.c: mapped_addr = eal_mem_reserve(
lib/librte_eal/windows/eal_memory.c:eal_mem_reserve(void *requested_addr, size_t size,
lib/librte_eal/unix/eal_memory.c:eal_mem_reserve(void *requested_addr, size_t size,
Does it succeed for you?
If not - can you please resend the series such that it compiles under Linux with Makefile?
> -----Original Message-----
> From: dev <dev-bounces@dpdk.org> On Behalf Of Dmitry Kozlyuk
> Sent: Tuesday, April 14, 2020 10:44 PM
> To: dev@dpdk.org
> Cc: Dmitry Malloy (MESHCHANINOV) <dmitrym@microsoft.com>; Narcisa
> Ana Maria Vasile <Narcisa.Vasile@microsoft.com>; Fady Bader
> <fady@mellanox.com>; Tal Shnaiderman <talshn@mellanox.com>; Dmitry
> Kozlyuk <dmitry.kozliuk@gmail.com>; Ranjit Menon
> <ranjit.menon@intel.com>
> Subject: [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address
> translator for Windows
>
> This driver supports Windows EAL memory management by translating
> current process virtual addresses to physical addresses (IOVA).
> Standalone virt2phys allows using DPDK without PMD and provides a
> reference implementation.
>
> Suggested-by: Ranjit Menon <ranjit.menon@intel.com>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> windows/README.rst | 103 +++++++++
> windows/virt2phys/virt2phys.c | 129 +++++++++++
> windows/virt2phys/virt2phys.h | 34 +++
> windows/virt2phys/virt2phys.inf | 64 ++++++
> windows/virt2phys/virt2phys.sln | 27 +++
> windows/virt2phys/virt2phys.vcxproj | 228 ++++++++++++++++++++
> windows/virt2phys/virt2phys.vcxproj.filters | 36 ++++
> 7 files changed, 621 insertions(+)
> create mode 100644 windows/README.rst
> create mode 100644 windows/virt2phys/virt2phys.c create mode 100644
> windows/virt2phys/virt2phys.h create mode 100644
> windows/virt2phys/virt2phys.inf create mode 100644
> windows/virt2phys/virt2phys.sln create mode 100644
> windows/virt2phys/virt2phys.vcxproj
> create mode 100644 windows/virt2phys/virt2phys.vcxproj.filters
>
> diff --git a/windows/README.rst b/windows/README.rst new file mode
> 100644 index 0000000..45a1d80
> --- /dev/null
> +++ b/windows/README.rst
> @@ -0,0 +1,103 @@
> +Developing Windows Drivers
> +==========================
> +
> +Prerequisites
> +-------------
> +
> +Building Windows Drivers is only possible on Windows.
> +
> +1. Visual Studio 2019 Community or Professional Edition 2. Windows
> +Driver Kit (WDK) for Windows 10, version 1903
> +
> +Follow the official instructions to obtain all of the above:
> +https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdocs
> .
> +microsoft.com%2Fen-us%2Fwindows-hardware%2Fdrivers%2Fdownload-
> the-wdk&a
> +mp;data=02%7C01%7Cophirmu%40mellanox.com%7C86da431f2b904dca3
> d8208d7e0ac
> +4cd0%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637224902
> 939680479&am
> +p;sdata=RSZXmo%2FewOpl9VCCg4BIgYUFvpreZzqX1X%2Bcl9vNRjU%3D&a
> mp;reserved
> +=0
> +
> +
> +Build the Drivers
> +-----------------
> +
> +Build from Visual Studio
> +~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +Open a solution (``*.sln``) with Visual Studio and build it (Ctrl+Shift+B).
> +
> +
> +Build from Command-Line
> +~~~~~~~~~~~~~~~~~~~~~~~
> +
> +Run *Developer Command Prompt for VS 2019* from the Start menu.
> +
> +Navigate to the solution directory (with ``*.sln``), then run:
> +
> +.. code-block:: console
> +
> + msbuild
> +
> +To build a particular combination of configuration and platform:
> +
> +.. code-block:: console
> +
> + msbuild -p:Configuration=Debug;Platform=x64
> +
> +
> +Install the Drivers
> +-------------------
> +
> +Disable Driver Signature Enforcement
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +By default Windows prohibits installing and loading drivers without
> +`digital signature`_ obtained from Microsoft. For development signature
> +enforcement may be disabled as follows.
> +
> +In Elevated Command Prompt (from this point, sufficient privileges are
> +assumed):
> +
> +.. code-block:: console
> +
> + bcdedit -set loadoptions DISABLE_INTEGRITY_CHECKS
> + bcdedit -set TESTSIGNING ON
> + shutdown -r -t 0
> +
> +Upon reboot, an overlay message should appear on the desktop informing
> +that Windows is in test mode, which means it allows loading unsigned
> drivers.
> +
> +.. _digital signature:
> +https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdocs
> .
> +microsoft.com%2Fen-us%2Fwindows-
> hardware%2Fdrivers%2Finstall%2Fdriver-s
> +igning&data=02%7C01%7Cophirmu%40mellanox.com%7C86da431f2b
> 904dca3d82
> +08d7e0ac4cd0%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C63
> 72249029396
> +85478&sdata=tLVdijiQ56xwSDW0zVsVE3TnIpuMPTLd9DBtS3Bnf4Q%3
> D&rese
> +rved=0
> +
> +Install, List, and Remove Drivers
> +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> +
> +Driver package is by default located in a subdirectory of its source
> +tree, e.g. ``x64\Debug\virt2phys\virt2phys`` (note two levels of
> ``virt2phys``).
> +
> +To install the driver and bind associated devices to it:
> +
> +.. code-block:: console
> +
> + pnputil /add-driver x64\Debug\virt2phys\virt2phys\virt2phys.inf
> + /install
> +
> +A graphical confirmation to load an unsigned driver will still appear.
> +
> +On Windows Server additional steps are required if the driver uses a
> +custom setup class:
> +
> +1. From "Device Manager", "Action" menu, select "Add legacy hardware".
> +2. It will launch the "Add Hardware Wizard". Click "Next".
> +3. Select second option "Install the hardware that I manually select
> + from a list (Advanced)".
> +4. On the next screen, locate the driver device class.
> +5. Select it, and click "Next".
> +6. The previously installed drivers will now be installed for
> + the appropriate devices (software devices will be created).
> +
> +To list installed drivers:
> +
> +.. code-block:: console
> +
> + pnputil /enum-drivers
> +
> +To remove the driver package and to uninstall its devices:
> +
> +.. code-block:: console
> +
> + pnputil /delete-driver oem2.inf /uninstall
> diff --git a/windows/virt2phys/virt2phys.c b/windows/virt2phys/virt2phys.c
> new file mode 100644 index 0000000..e157e9c
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.c
> @@ -0,0 +1,129 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2020 Dmitry Kozlyuk
> + */
> +
> +#include <ntddk.h>
> +#include <wdf.h>
> +#include <wdmsec.h>
> +#include <initguid.h>
> +
> +#include "virt2phys.h"
> +
> +DRIVER_INITIALIZE DriverEntry;
> +EVT_WDF_DRIVER_DEVICE_ADD virt2phys_driver_EvtDeviceAdd;
> +EVT_WDF_IO_IN_CALLER_CONTEXT
> virt2phys_device_EvtIoInCallerContext;
> +
> +NTSTATUS
> +DriverEntry(
> + IN PDRIVER_OBJECT driver_object, IN PUNICODE_STRING
> registry_path) {
> + WDF_DRIVER_CONFIG config;
> + WDF_OBJECT_ATTRIBUTES attributes;
> + NTSTATUS status;
> +
> + PAGED_CODE();
> +
> + WDF_DRIVER_CONFIG_INIT(&config,
> virt2phys_driver_EvtDeviceAdd);
> + WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
> + status = WdfDriverCreate(
> + driver_object, registry_path,
> + &attributes, &config, WDF_NO_HANDLE);
> + if (!NT_SUCCESS(status)) {
> + KdPrint(("WdfDriverCreate() failed, status=%08x\n", status));
> + }
> +
> + return status;
> +}
> +
> +_Use_decl_annotations_
> +NTSTATUS
> +virt2phys_driver_EvtDeviceAdd(
> + WDFDRIVER driver, PWDFDEVICE_INIT init) {
> + WDF_OBJECT_ATTRIBUTES attributes;
> + WDFDEVICE device;
> + NTSTATUS status;
> +
> + UNREFERENCED_PARAMETER(driver);
> +
> + PAGED_CODE();
> +
> + WdfDeviceInitSetIoType(
> + init, WdfDeviceIoNeither);
> + WdfDeviceInitSetIoInCallerContextCallback(
> + init, virt2phys_device_EvtIoInCallerContext);
> +
> + WDF_OBJECT_ATTRIBUTES_INIT(&attributes);
> +
> + status = WdfDeviceCreate(&init, &attributes, &device);
> + if (!NT_SUCCESS(status)) {
> + KdPrint(("WdfDeviceCreate() failed, status=%08x\n", status));
> + return status;
> + }
> +
> + status = WdfDeviceCreateDeviceInterface(
> + device, &GUID_DEVINTERFACE_VIRT2PHYS, NULL);
> + if (!NT_SUCCESS(status)) {
> + KdPrint(("WdfDeviceCreateDeviceInterface() failed, "
> + "status=%08x\n", status));
> + return status;
> + }
> +
> + return STATUS_SUCCESS;
> +}
> +
> +_Use_decl_annotations_
> +VOID
> +virt2phys_device_EvtIoInCallerContext(
> + IN WDFDEVICE device, IN WDFREQUEST request) {
> + WDF_REQUEST_PARAMETERS params;
> + ULONG code;
> + PVOID *virt;
> + PHYSICAL_ADDRESS *phys;
> + size_t size;
> + NTSTATUS status;
> +
> + UNREFERENCED_PARAMETER(device);
> +
> + PAGED_CODE();
> +
> + WDF_REQUEST_PARAMETERS_INIT(¶ms);
> + WdfRequestGetParameters(request, ¶ms);
> +
> + if (params.Type != WdfRequestTypeDeviceControl) {
> + KdPrint(("bogus request type=%u\n", params.Type));
> + WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
> + return;
> + }
> +
> + code = params.Parameters.DeviceIoControl.IoControlCode;
> + if (code != IOCTL_VIRT2PHYS_TRANSLATE) {
> + KdPrint(("bogus IO control code=%lu\n", code));
> + WdfRequestComplete(request, STATUS_NOT_SUPPORTED);
> + return;
> + }
> +
> + status = WdfRequestRetrieveInputBuffer(
> + request, sizeof(*virt), (PVOID *)&virt, &size);
> + if (!NT_SUCCESS(status)) {
> + KdPrint(("WdfRequestRetrieveInputBuffer() failed, "
> + "status=%08x\n", status));
> + WdfRequestComplete(request, status);
> + return;
> + }
> +
> + status = WdfRequestRetrieveOutputBuffer(
> + request, sizeof(*phys), (PVOID *)&phys, &size);
> + if (!NT_SUCCESS(status)) {
> + KdPrint(("WdfRequestRetrieveOutputBuffer() failed, "
> + "status=%08x\n", status));
> + WdfRequestComplete(request, status);
> + return;
> + }
> +
> + *phys = MmGetPhysicalAddress(*virt);
> +
> + WdfRequestCompleteWithInformation(
> + request, STATUS_SUCCESS, sizeof(*phys)); }
> diff --git a/windows/virt2phys/virt2phys.h b/windows/virt2phys/virt2phys.h
> new file mode 100644 index 0000000..4bb2b4a
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.h
> @@ -0,0 +1,34 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2020 Dmitry Kozlyuk
> + */
> +
> +/**
> + * @file virt2phys driver interface
> + */
> +
> +/**
> + * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
> + */
> +DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
> + 0x539c2135, 0x793a, 0x4926,
> + 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
> +
> +/**
> + * Driver device type for IO control codes.
> + */
> +#define VIRT2PHYS_DEVTYPE 0x8000
> +
> +/**
> + * Translate a valid non-paged virtual address to a physical address.
> + *
> + * Note: A physical address zero (0) is reported if input address
> + * is paged out or not mapped. However, if input is a valid mapping
> + * of I/O port 0x0000, output is also zero. There is no way
> + * to distinguish between these cases by return value only.
> + *
> + * Input: a non-paged virtual address (PVOID).
> + *
> + * Output: the corresponding physical address (LARGE_INTEGER).
> + */
> +#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
> + VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED,
> FILE_ANY_ACCESS)
> diff --git a/windows/virt2phys/virt2phys.inf
> b/windows/virt2phys/virt2phys.inf new file mode 100644 index
> 0000000..e35765e
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.inf
> @@ -0,0 +1,64 @@
> +; SPDX-License-Identifier: BSD-3-Clause ; Copyright (c) 2020 Dmitry
> +Kozlyuk
> +
> +[Version]
> +Signature = "$WINDOWS NT$"
> +Class = %ClassName%
> +ClassGuid = {78A1C341-4539-11d3-B88D-00C04FAD5171}
> +Provider = %ManufacturerName%
> +CatalogFile = virt2phys.cat
> +DriverVer =
> +
> +[DestinationDirs]
> +DefaultDestDir = 12
> +
> +; ================= Class section =====================
> +
> +[ClassInstall32]
> +Addreg = virt2phys_ClassReg
> +
> +[virt2phys_ClassReg]
> +HKR,,,0,%ClassName%
> +HKR,,Icon,,-5
> +
> +[SourceDisksNames]
> +1 = %DiskName%,,,""
> +
> +[SourceDisksFiles]
> +virt2phys.sys = 1,,
> +
> +;*****************************************
> +; Install Section
> +;*****************************************
> +
> +[Manufacturer]
> +%ManufacturerName%=Standard,NT$ARCH$
> +
> +[Standard.NT$ARCH$]
> +%virt2phys.DeviceDesc%=virt2phys_Device, Root\virt2phys
> +
> +[virt2phys_Device.NT]
> +CopyFiles = Drivers_Dir
> +
> +[Drivers_Dir]
> +virt2phys.sys
> +
> +;-------------- Service installation
> +[virt2phys_Device.NT.Services]
> +AddService = virt2phys,%SPSVCINST_ASSOCSERVICE%,
> virt2phys_Service_Inst
> +
> +; -------------- virt2phys driver install sections
> +[virt2phys_Service_Inst]
> +DisplayName = %virt2phys.SVCDESC%
> +ServiceType = 1 ; SERVICE_KERNEL_DRIVER
> +StartType = 3 ; SERVICE_DEMAND_START
> +ErrorControl = 1 ; SERVICE_ERROR_NORMAL
> +ServiceBinary = %12%\virt2phys.sys
> +
> +[Strings]
> +SPSVCINST_ASSOCSERVICE = 0x00000002
> +ManufacturerName = "Dmitry Kozlyuk"
> +ClassName = "Kernel bypass"
> +DiskName = "virt2phys Installation Disk"
> +virt2phys.DeviceDesc = "Virtual to physical address translator"
> +virt2phys.SVCDESC = "virt2phys Service"
> diff --git a/windows/virt2phys/virt2phys.sln
> b/windows/virt2phys/virt2phys.sln new file mode 100644 index
> 0000000..0f5ecdc
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.sln
> @@ -0,0 +1,27 @@
> ++Microsoft Visual Studio Solution File, Format Version 12.00+# Visual Studio
> Version 16+VisualStudioVersion =
> 16.0.29613.14+MinimumVisualStudioVersion =
> 10.0.40219.1+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") =
> "virt2phys", "virt2phys.vcxproj", "{0EEF826B-9391-43A8-A722-
> BDD6F6115137}"+EndProject+Global+
> GlobalSection(SolutionConfigurationPlatforms) = preSolution+
> Debug|x64 = Debug|x64+ Release|x64 = Release|x64+
> EndGlobalSection+
> GlobalSection(ProjectConfigurationPlatforms) = postSolution+
> {0EEF826B-9391-43A8-A722-BDD6F6115137}.Debug|x64.ActiveCfg =
> Debug|x64+ {0EEF826B-9391-43A8-A722-
> BDD6F6115137}.Debug|x64.Build.0 = Debug|x64+ {0EEF826B-
> 9391-43A8-A722-BDD6F6115137}.Debug|x64.Deploy.0 = Debug|x64+
> {0EEF826B-9391-43A8-A722-BDD6F6115137}.Release|x64.ActiveCfg
> = Release|x64+ {0EEF826B-9391-43A8-A722-
> BDD6F6115137}.Release|x64.Build.0 = Release|x64+ {0EEF826B-
> 9391-43A8-A722-BDD6F6115137}.Release|x64.Deploy.0 = Release|x64+
> EndGlobalSection+ GlobalSection(SolutionProperties) =
> preSolution+ HideSolutionNode = FALSE+ EndGlobalSection+
> GlobalSection(ExtensibilityGlobals) = postSolution+
> SolutionGuid = {845012FB-4471-4A12-A1C4-FF7E05C40E8E}+
> EndGlobalSection+EndGlobaldiff --git
> a/windows/virt2phys/virt2phys.vcxproj
> b/windows/virt2phys/virt2phys.vcxproj
> new file mode 100644
> index 0000000..fa51916
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.vcxproj
> @@ -0,0 +1,228 @@
> +<?xml version="1.0" encoding="utf-8"?>+<Project DefaultTargets="Build"
> ToolsVersion="12.0"
> xmlns="https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2
> Fschemas.microsoft.com%2Fdeveloper%2Fmsbuild%2F2003&data=02%
> 7C01%7Cophirmu%40mellanox.com%7C86da431f2b904dca3d8208d7e0ac4c
> d0%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637224902939
> 685478&sdata=N7HPDma1qrXV6sobOS0tblhsgaEUePD8lXqhnyXD1sU%
> 3D&reserved=0">+ <ItemGroup Label="ProjectConfigurations">+
> <ProjectConfiguration Include="Debug|Win32">+
> <Configuration>Debug</Configuration>+ <Platform>Win32</Platform>+
> </ProjectConfiguration>+ <ProjectConfiguration
> Include="Release|Win32">+ <Configuration>Release</Configuration>+
> <Platform>Win32</Platform>+ </ProjectConfiguration>+
> <ProjectConfiguration Include="Debug|x64">+
> <Configuration>Debug</Configuration>+ <Platform>x64</Platform>+
> </ProjectConfiguration>+ <ProjectConfiguration Include="Release|x64">+
> <Configuration>Release</Configuration>+ <Platform>x64</Platform>+
> </ProjectConfiguration>+ <ProjectConfiguration Include="Debug|ARM">+
> <Configuration>Debug</Configuration>+ <Platform>ARM</Platform>+
> </ProjectConfiguration>+ <ProjectConfiguration Include="Release|ARM">+
> <Configuration>Release</Configuration>+ <Platform>ARM</Platform>+
> </ProjectConfiguration>+ <ProjectConfiguration
> Include="Debug|ARM64">+ <Configuration>Debug</Configuration>+
> <Platform>ARM64</Platform>+ </ProjectConfiguration>+
> <ProjectConfiguration Include="Release|ARM64">+
> <Configuration>Release</Configuration>+
> <Platform>ARM64</Platform>+ </ProjectConfiguration>+ </ItemGroup>+
> <ItemGroup>+ <ClCompile Include="virt2phys.c" />+ </ItemGroup>+
> <ItemGroup>+ <ClInclude Include="virt2phys.h" />+ </ItemGroup>+
> <ItemGroup>+ <Inf Include="virt2phys.inf" />+ </ItemGroup>+
> <PropertyGroup Label="Globals">+ <ProjectGuid>{0EEF826B-9391-43A8-
> A722-BDD6F6115137}</ProjectGuid>+ <TemplateGuid>{497e31cb-056b-
> 4f31-abb8-447fd55ee5a5}</TemplateGuid>+
> <TargetFrameworkVersion>v4.5</TargetFrameworkVersion>+
> <MinimumVisualStudioVersion>12.0</MinimumVisualStudioVersion>+
> <Configuration>Debug</Configuration>+ <Platform
> Condition="'$(Platform)' == ''">Win32</Platform>+
> <RootNamespace>virt2phys</RootNamespace>+ </PropertyGroup>+
> <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />+
> <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>true</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|Win32'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>false</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|x64'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>true</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|x64'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>false</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>true</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>false</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>true</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'"
> Label="Configuration">+ <TargetVersion>Windows10</TargetVersion>+
> <UseDebugLibraries>false</UseDebugLibraries>+
> <PlatformToolset>WindowsKernelModeDriver10.0</PlatformToolset>+
> <ConfigurationType>Driver</ConfigurationType>+
> <DriverType>KMDF</DriverType>+
> <DriverTargetPlatform>Universal</DriverTargetPlatform>+
> </PropertyGroup>+ <Import
> Project="$(VCTargetsPath)\Microsoft.Cpp.props" />+ <ImportGroup
> Label="ExtensionSettings">+ </ImportGroup>+ <ImportGroup
> Label="PropertySheets">+ <Import
> Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props"
> Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')"
> Label="LocalAppDataPlatform" />+ </ImportGroup>+ <PropertyGroup
> Label="UserMacros" />+ <PropertyGroup />+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|x64'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <PropertyGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">+
> <DebuggerFlavor>DbgengKernelDebugger</DebuggerFlavor>+
> </PropertyGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">+ <ClCompile>+
> <WppEnabled>false</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+ <Link>+
> <AdditionalDependencies>$(DDK_LIB_PATH)wdmsec.lib;%(AdditionalDepend
> encies)</AdditionalDependencies>+ </Link>+ <Inf>+
> <TimeStamp>0.1</TimeStamp>+ </Inf>+ </ItemDefinitionGroup>+
> <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|x64'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Release|ARM64'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemDefinitionGroup
> Condition="'$(Configuration)|$(Platform)'=='Debug|ARM64'">+
> <ClCompile>+ <WppEnabled>true</WppEnabled>+
> <WppRecorderEnabled>true</WppRecorderEnabled>+
> <WppScanConfigurationData
> Condition="'%(ClCompile.ScanConfigurationData)' ==
> ''">trace.h</WppScanConfigurationData>+
> <WppKernelMode>true</WppKernelMode>+ </ClCompile>+
> </ItemDefinitionGroup>+ <ItemGroup>+ <FilesToPackage
> Include="$(TargetPath)" />+ </ItemGroup>+ <Import
> Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />+ <ImportGroup
> Label="ExtensionTargets">+ </ImportGroup>+</Project>
> \ No newline at end of file
> diff --git a/windows/virt2phys/virt2phys.vcxproj.filters
> b/windows/virt2phys/virt2phys.vcxproj.filters
> new file mode 100644
> index 0000000..0fe65fc
> --- /dev/null
> +++ b/windows/virt2phys/virt2phys.vcxproj.filters
> @@ -0,0 +1,36 @@
> +<?xml version="1.0" encoding="utf-8"?>+<Project ToolsVersion="4.0"
> xmlns="https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2
> Fschemas.microsoft.com%2Fdeveloper%2Fmsbuild%2F2003&data=02%
> 7C01%7Cophirmu%40mellanox.com%7C86da431f2b904dca3d8208d7e0ac4c
> d0%7Ca652971c7d2e4d9ba6a4d149256f461b%7C0%7C0%7C637224902939
> 685478&sdata=N7HPDma1qrXV6sobOS0tblhsgaEUePD8lXqhnyXD1sU%
> 3D&reserved=0">+ <ItemGroup>+ <Filter Include="Source Files">+
> <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-
> 2A32D752A2FF}</UniqueIdentifier>+
> <Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>+
> </Filter>+ <Filter Include="Header Files">+
> <UniqueIdentifier>{93995380-89BD-4b04-88EB-
> 625FBE52EBFB}</UniqueIdentifier>+
> <Extensions>h;hpp;hxx;hm;inl;inc;xsd</Extensions>+ </Filter>+ <Filter
> Include="Resource Files">+ <UniqueIdentifier>{67DA6AB6-F800-4c08-
> 8B7A-83BB121AAD01}</UniqueIdentifier>+
> <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;pn
> g;wav;mfcribbon-ms</Extensions>+ </Filter>+ <Filter Include="Driver
> Files">+ <UniqueIdentifier>{8E41214B-6785-4CFE-B992-
> 037D68949A14}</UniqueIdentifier>+
> <Extensions>inf;inv;inx;mof;mc;</Extensions>+ </Filter>+ </ItemGroup>+
> <ItemGroup>+ <Inf Include="virt2phys.inf">+ <Filter>Driver
> Files</Filter>+ </Inf>+ </ItemGroup>+ <ItemGroup>+ <ClInclude
> Include="virt2phys.h">+ <Filter>Header Files</Filter>+ </ClInclude>+
> </ItemGroup>+ <ItemGroup>+ <ClCompile Include="virt2phys.c">+
> <Filter>Source Files</Filter>+ </ClCompile>+ </ItemGroup>+</Project>--
> 2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 02/10] eal/windows: do not expose private EAL facilities
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-21 22:40 ` Thomas Monjalon
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 03/10] eal/windows: improve CPU and NUMA node detection Dmitry Kozlyuk
` (8 subsequent siblings)
10 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon, Thomas Monjalon, Anand Rawat
The goal of rte_os.h is to mitigate OS differences for EAL users.
In Windows EAL, rte_os.h did excessive things:
1. It included platform SDK headers (windows.h, etc). Those files are
huge, require specific inclusion order, and are generally unused by
the code including rte_os.h. Declarations from platform SDK may
break otherwise platform-independent code, e.g. min, max, ERROR.
2. It included pthread.h, which is clearly not always required.
3. It defined functions private to Windows EAL.
Reorganize Windows EAL includes in the following way:
1. Create rte_windows.h to properly import Windows-specific facilities.
Primary users are bus drivers, tests, and external applications.
2. Remove platform SDK includes from rte_os.h to prevent breaking
otherwise portable code by including rte_os.h on Windows.
Copy necessary definitions to avoid including those headers.
3. Remove pthread.h include from rte_os.h.
4. Move declarations private to Windows EAL into eal_windows.h.
Fixes: 428eb983f5f7 ("eal: add OS specific header file")
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/eal.c | 2 +
lib/librte_eal/windows/eal_lcore.c | 2 +
lib/librte_eal/windows/eal_thread.c | 1 +
lib/librte_eal/windows/eal_windows.h | 29 +++++++++++++
lib/librte_eal/windows/include/meson.build | 1 +
lib/librte_eal/windows/include/pthread.h | 2 +
lib/librte_eal/windows/include/rte_os.h | 44 ++++++--------------
lib/librte_eal/windows/include/rte_windows.h | 41 ++++++++++++++++++
8 files changed, 91 insertions(+), 31 deletions(-)
create mode 100644 lib/librte_eal/windows/eal_windows.h
create mode 100644 lib/librte_eal/windows/include/rte_windows.h
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index e4b50df3b..2cf7a04ef 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -18,6 +18,8 @@
#include <eal_options.h>
#include <eal_private.h>
+#include "eal_windows.h"
+
/* Allow the application to print its usage message too if set */
static rte_usage_hook_t rte_application_usage_hook;
diff --git a/lib/librte_eal/windows/eal_lcore.c b/lib/librte_eal/windows/eal_lcore.c
index b3a6c63af..82ee45413 100644
--- a/lib/librte_eal/windows/eal_lcore.c
+++ b/lib/librte_eal/windows/eal_lcore.c
@@ -2,12 +2,14 @@
* Copyright(c) 2019 Intel Corporation
*/
+#include <pthread.h>
#include <stdint.h>
#include <rte_common.h>
#include "eal_private.h"
#include "eal_thread.h"
+#include "eal_windows.h"
/* global data structure that contains the CPU map */
static struct _wcpu_map {
diff --git a/lib/librte_eal/windows/eal_thread.c b/lib/librte_eal/windows/eal_thread.c
index 9e4bbaa08..e149199a6 100644
--- a/lib/librte_eal/windows/eal_thread.c
+++ b/lib/librte_eal/windows/eal_thread.c
@@ -14,6 +14,7 @@
#include <eal_thread.h>
#include "eal_private.h"
+#include "eal_windows.h"
RTE_DEFINE_PER_LCORE(unsigned int, _lcore_id) = LCORE_ID_ANY;
RTE_DEFINE_PER_LCORE(unsigned int, _socket_id) = (unsigned int)SOCKET_ID_ANY;
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
new file mode 100644
index 000000000..fadd676b2
--- /dev/null
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#ifndef _EAL_WINDOWS_H_
+#define _EAL_WINDOWS_H_
+
+/**
+ * @file Facilities private to Windows EAL
+ */
+
+#include <rte_windows.h>
+
+/**
+ * Create a map of processors and cores on the system.
+ */
+void eal_create_cpu_map(void);
+
+/**
+ * Create a thread.
+ *
+ * @param thread
+ * The location to store the thread id if successful.
+ * @return
+ * 0 for success, -1 if the thread is not created.
+ */
+int eal_thread_create(pthread_t *thread);
+
+#endif /* _EAL_WINDOWS_H_ */
diff --git a/lib/librte_eal/windows/include/meson.build b/lib/librte_eal/windows/include/meson.build
index 7d18dd52f..5fb1962ac 100644
--- a/lib/librte_eal/windows/include/meson.build
+++ b/lib/librte_eal/windows/include/meson.build
@@ -5,4 +5,5 @@ includes += include_directories('.')
headers += files(
'rte_os.h',
+ 'rte_windows.h',
)
diff --git a/lib/librte_eal/windows/include/pthread.h b/lib/librte_eal/windows/include/pthread.h
index b9dd18e56..cfd53f0b8 100644
--- a/lib/librte_eal/windows/include/pthread.h
+++ b/lib/librte_eal/windows/include/pthread.h
@@ -5,6 +5,8 @@
#ifndef _PTHREAD_H_
#define _PTHREAD_H_
+#include <stdint.h>
+
/**
* This file is required to support the common code in eal_common_proc.c,
* eal_common_thread.c and common\include\rte_per_lcore.h as Microsoft libc
diff --git a/lib/librte_eal/windows/include/rte_os.h b/lib/librte_eal/windows/include/rte_os.h
index e1e0378e6..510e39e03 100644
--- a/lib/librte_eal/windows/include/rte_os.h
+++ b/lib/librte_eal/windows/include/rte_os.h
@@ -8,20 +8,18 @@
/**
* This is header should contain any function/macro definition
* which are not supported natively or named differently in the
- * Windows OS. Functions will be added in future releases.
+ * Windows OS. It must not include Windows-specific headers.
*/
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
#ifdef __cplusplus
extern "C" {
#endif
-#include <windows.h>
-#include <basetsd.h>
-#include <pthread.h>
-#include <stdio.h>
-
-/* limits.h replacement */
-#include <stdlib.h>
+/* limits.h replacement, value as in <windows.h> */
#ifndef PATH_MAX
#define PATH_MAX _MAX_PATH
#endif
@@ -31,8 +29,6 @@ extern "C" {
/* strdup is deprecated in Microsoft libc and _strdup is preferred */
#define strdup(str) _strdup(str)
-typedef SSIZE_T ssize_t;
-
#define strtok_r(str, delim, saveptr) strtok_s(str, delim, saveptr)
#define index(a, b) strchr(a, b)
@@ -40,22 +36,14 @@ typedef SSIZE_T ssize_t;
#define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
-/**
- * Create a thread.
- * This function is private to EAL.
- *
- * @param thread
- * The location to store the thread id if successful.
- * @return
- * 0 for success, -1 if the thread is not created.
- */
-int eal_thread_create(pthread_t *thread);
+/* cpu_set macros implementation */
+#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
+#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
+#define RTE_CPU_FILL(set) CPU_FILL(set)
+#define RTE_CPU_NOT(dst, src) CPU_NOT(dst, src)
-/**
- * Create a map of processors and cores on the system.
- * This function is private to EAL.
- */
-void eal_create_cpu_map(void);
+/* as in <windows.h> */
+typedef long long ssize_t;
#ifndef RTE_TOOLCHAIN_GCC
static inline int
@@ -86,12 +74,6 @@ asprintf(char **buffer, const char *format, ...)
}
#endif /* RTE_TOOLCHAIN_GCC */
-/* cpu_set macros implementation */
-#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
-#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
-#define RTE_CPU_FILL(set) CPU_FILL(set)
-#define RTE_CPU_NOT(dst, src) CPU_NOT(dst, src)
-
#ifdef __cplusplus
}
#endif
diff --git a/lib/librte_eal/windows/include/rte_windows.h b/lib/librte_eal/windows/include/rte_windows.h
new file mode 100644
index 000000000..ed6e4c148
--- /dev/null
+++ b/lib/librte_eal/windows/include/rte_windows.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#ifndef _RTE_WINDOWS_H_
+#define _RTE_WINDOWS_H_
+
+/**
+ * @file Windows-specific facilities
+ *
+ * This file should be included by DPDK libraries and applications
+ * that need access to Windows API. It includes platform SDK headers
+ * in compatible order with proper options and defines error-handling macros.
+ */
+
+/* Disable excessive libraries. */
+#ifndef WIN32_LEAN_AND_MEAN
+#define WIN32_LEAN_AND_MEAN
+#endif
+
+/* Must come first. */
+#include <windows.h>
+
+#include <basetsd.h>
+#include <psapi.h>
+
+/* Have GUIDs defined. */
+#ifndef INITGUID
+#define INITGUID
+#endif
+#include <initguid.h>
+
+/**
+ * Log GetLastError() with context, usually a Win32 API function and arguments.
+ */
+#define RTE_LOG_WIN32_ERR(...) \
+ RTE_LOG(DEBUG, EAL, RTE_FMT("GetLastError()=%lu: " \
+ RTE_FMT_HEAD(__VA_ARGS__,) "\n", GetLastError(), \
+ RTE_FMT_TAIL(__VA_ARGS__,)))
+
+#endif /* _RTE_WINDOWS_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 02/10] eal/windows: do not expose private EAL facilities
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 02/10] eal/windows: do not expose private EAL facilities Dmitry Kozlyuk
@ 2020-04-21 22:40 ` Thomas Monjalon
0 siblings, 0 replies; 218+ messages in thread
From: Thomas Monjalon @ 2020-04-21 22:40 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
14/04/2020 21:44, Dmitry Kozlyuk:
> The goal of rte_os.h is to mitigate OS differences for EAL users.
> In Windows EAL, rte_os.h did excessive things:
>
> 1. It included platform SDK headers (windows.h, etc). Those files are
> huge, require specific inclusion order, and are generally unused by
> the code including rte_os.h. Declarations from platform SDK may
> break otherwise platform-independent code, e.g. min, max, ERROR.
>
> 2. It included pthread.h, which is clearly not always required.
>
> 3. It defined functions private to Windows EAL.
>
> Reorganize Windows EAL includes in the following way:
>
> 1. Create rte_windows.h to properly import Windows-specific facilities.
> Primary users are bus drivers, tests, and external applications.
>
> 2. Remove platform SDK includes from rte_os.h to prevent breaking
> otherwise portable code by including rte_os.h on Windows.
> Copy necessary definitions to avoid including those headers.
>
> 3. Remove pthread.h include from rte_os.h.
>
> 4. Move declarations private to Windows EAL into eal_windows.h.
>
> Fixes: 428eb983f5f7 ("eal: add OS specific header file")
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Applied as a separate patch because it is needed for a patch
fixing compilation on Windows.
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 03/10] eal/windows: improve CPU and NUMA node detection
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 1/1] virt2phys: virtual to physical address translator for Windows Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 02/10] eal/windows: do not expose private EAL facilities Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 04/10] eal/windows: initialize hugepage info Dmitry Kozlyuk
` (7 subsequent siblings)
10 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon, Anand Rawat, Jeff Shaw
1. Map CPU cores to their respective NUMA nodes as reported by system.
2. Support systems with more than 64 cores (multiple processor groups).
3. Fix magic constants, styling issues, and compiler warnings.
4. Add EAL private function to map DPDK socket ID to NUMA node number.
Fixes: 53ffd9f080fc ("eal/windows: add minimum viable code")
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/eal_lcore.c | 185 +++++++++++++++++----------
lib/librte_eal/windows/eal_windows.h | 10 ++
2 files changed, 124 insertions(+), 71 deletions(-)
diff --git a/lib/librte_eal/windows/eal_lcore.c b/lib/librte_eal/windows/eal_lcore.c
index 82ee45413..9d931d50a 100644
--- a/lib/librte_eal/windows/eal_lcore.c
+++ b/lib/librte_eal/windows/eal_lcore.c
@@ -3,103 +3,146 @@
*/
#include <pthread.h>
+#include <stdbool.h>
#include <stdint.h>
#include <rte_common.h>
+#include <rte_debug.h>
+#include <rte_lcore.h>
+#include <rte_os.h>
#include "eal_private.h"
#include "eal_thread.h"
#include "eal_windows.h"
-/* global data structure that contains the CPU map */
-static struct _wcpu_map {
- unsigned int total_procs;
- unsigned int proc_sockets;
- unsigned int proc_cores;
- unsigned int reserved;
- struct _win_lcore_map {
- uint8_t socket_id;
- uint8_t core_id;
- } wlcore_map[RTE_MAX_LCORE];
-} wcpu_map = { 0 };
-
-/*
- * Create a map of all processors and associated cores on the system
- */
+/** Number of logical processors (cores) in a processor group (32 or 64). */
+#define EAL_PROCESSOR_GROUP_SIZE (sizeof(KAFFINITY) * CHAR_BIT)
+
+struct lcore_map {
+ uint8_t socket_id;
+ uint8_t core_id;
+};
+
+struct socket_map {
+ uint16_t node_id;
+};
+
+struct cpu_map {
+ unsigned int socket_count;
+ unsigned int lcore_count;
+ struct lcore_map lcores[RTE_MAX_LCORE];
+ struct socket_map sockets[RTE_MAX_NUMA_NODES];
+};
+
+static struct cpu_map cpu_map = { 0 };
+
void
-eal_create_cpu_map()
+eal_create_cpu_map(void)
{
- wcpu_map.total_procs =
- GetActiveProcessorCount(ALL_PROCESSOR_GROUPS);
-
- LOGICAL_PROCESSOR_RELATIONSHIP lprocRel;
- DWORD lprocInfoSize = 0;
- BOOL ht_enabled = FALSE;
-
- /* First get the processor package information */
- lprocRel = RelationProcessorPackage;
- /* Determine the size of buffer we need (pass NULL) */
- GetLogicalProcessorInformationEx(lprocRel, NULL, &lprocInfoSize);
- wcpu_map.proc_sockets = lprocInfoSize / 48;
-
- lprocInfoSize = 0;
- /* Next get the processor core information */
- lprocRel = RelationProcessorCore;
- GetLogicalProcessorInformationEx(lprocRel, NULL, &lprocInfoSize);
- wcpu_map.proc_cores = lprocInfoSize / 48;
-
- if (wcpu_map.total_procs > wcpu_map.proc_cores)
- ht_enabled = TRUE;
-
- /* Distribute the socket and core ids appropriately
- * across the logical cores. For now, split the cores
- * equally across the sockets.
- */
- unsigned int lcore = 0;
- for (unsigned int socket = 0; socket <
- wcpu_map.proc_sockets; ++socket) {
- for (unsigned int core = 0;
- core < (wcpu_map.proc_cores / wcpu_map.proc_sockets);
- ++core) {
- wcpu_map.wlcore_map[lcore]
- .socket_id = socket;
- wcpu_map.wlcore_map[lcore]
- .core_id = core;
- lcore++;
- if (ht_enabled) {
- wcpu_map.wlcore_map[lcore]
- .socket_id = socket;
- wcpu_map.wlcore_map[lcore]
- .core_id = core;
- lcore++;
+ SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *infos, *info;
+ DWORD infos_size;
+ bool full = false;
+
+ infos_size = 0;
+ if (!GetLogicalProcessorInformationEx(
+ RelationNumaNode, NULL, &infos_size)) {
+ DWORD error = GetLastError();
+ if (error != ERROR_INSUFFICIENT_BUFFER) {
+ rte_panic("cannot get NUMA node info size, error %lu",
+ GetLastError());
+ }
+ }
+
+ infos = malloc(infos_size);
+ if (infos == NULL) {
+ rte_panic("cannot allocate memory for NUMA node information");
+ return;
+ }
+
+ if (!GetLogicalProcessorInformationEx(
+ RelationNumaNode, infos, &infos_size)) {
+ rte_panic("cannot get NUMA node information, error %lu",
+ GetLastError());
+ }
+
+ info = infos;
+ while ((uint8_t *)info - (uint8_t *)infos < infos_size) {
+ unsigned int node_id = info->NumaNode.NodeNumber;
+ GROUP_AFFINITY *cores = &info->NumaNode.GroupMask;
+ struct lcore_map *lcore;
+ unsigned int i, socket_id;
+
+ /* NUMA node may be reported multiple times if it includes
+ * cores from different processor groups, e. g. 80 cores
+ * of a physical processor comprise one NUMA node, but two
+ * processor groups, because group size is limited by 32/64.
+ */
+ for (socket_id = 0; socket_id < cpu_map.socket_count;
+ socket_id++) {
+ if (cpu_map.sockets[socket_id].node_id == node_id)
+ break;
+ }
+
+ if (socket_id == cpu_map.socket_count) {
+ if (socket_id == RTE_DIM(cpu_map.sockets)) {
+ full = true;
+ goto exit;
}
+
+ cpu_map.sockets[socket_id].node_id = node_id;
+ cpu_map.socket_count++;
+ }
+
+ for (i = 0; i < EAL_PROCESSOR_GROUP_SIZE; i++) {
+ if ((cores->Mask & ((KAFFINITY)1 << i)) == 0)
+ continue;
+
+ if (cpu_map.lcore_count == RTE_DIM(cpu_map.lcores)) {
+ full = true;
+ goto exit;
+ }
+
+ lcore = &cpu_map.lcores[cpu_map.lcore_count];
+ lcore->socket_id = socket_id;
+ lcore->core_id =
+ cores->Group * EAL_PROCESSOR_GROUP_SIZE + i;
+ cpu_map.lcore_count++;
}
+
+ info = (SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *)(
+ (uint8_t *)info + info->Size);
+ }
+
+exit:
+ if (full) {
+ /* RTE_LOG() may not be available, but this is important. */
+ fprintf(stderr, "Enumerated maximum of %u NUMA nodes and %u cores\n",
+ cpu_map.socket_count, cpu_map.lcore_count);
}
+
+ free(infos);
}
-/*
- * Check if a cpu is present by the presence of the cpu information for it
- */
int
eal_cpu_detected(unsigned int lcore_id)
{
- return (lcore_id < wcpu_map.total_procs);
+ return lcore_id < cpu_map.lcore_count;
}
-/*
- * Get CPU socket id for a logical core
- */
unsigned
eal_cpu_socket_id(unsigned int lcore_id)
{
- return wcpu_map.wlcore_map[lcore_id].socket_id;
+ return cpu_map.lcores[lcore_id].socket_id;
}
-/*
- * Get CPU socket id (NUMA node) for a logical core
- */
unsigned
eal_cpu_core_id(unsigned int lcore_id)
{
- return wcpu_map.wlcore_map[lcore_id].core_id;
+ return cpu_map.lcores[lcore_id].core_id;
+}
+
+unsigned int
+eal_socket_numa_node(unsigned int socket_id)
+{
+ return cpu_map.sockets[socket_id].node_id;
}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index fadd676b2..390d2fd66 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -26,4 +26,14 @@ void eal_create_cpu_map(void);
*/
int eal_thread_create(pthread_t *thread);
+/**
+ * Get system NUMA node number for a socket ID.
+ *
+ * @param socket_id
+ * Valid EAL socket ID.
+ * @return
+ * NUMA node number to use with Win32 API.
+ */
+unsigned int eal_socket_numa_node(unsigned int socket_id);
+
#endif /* _EAL_WINDOWS_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 04/10] eal/windows: initialize hugepage info
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (2 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 03/10] eal/windows: improve CPU and NUMA node detection Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
` (6 subsequent siblings)
10 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Harini Ramakrishnan,
Omar Cardona, Pallavi Kadam, Ranjit Menon, John McNamara,
Marko Kovacevic
Add hugepages discovery ("large pages" in Windows terminology)
and update documentation for required privilege setup.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 2 +
doc/guides/windows_gsg/build_dpdk.rst | 20 -----
doc/guides/windows_gsg/index.rst | 1 +
doc/guides/windows_gsg/run_apps.rst | 47 +++++++++++
lib/librte_eal/windows/eal.c | 14 ++++
lib/librte_eal/windows/eal_hugepages.c | 108 +++++++++++++++++++++++++
lib/librte_eal/windows/meson.build | 1 +
7 files changed, 173 insertions(+), 20 deletions(-)
create mode 100644 doc/guides/windows_gsg/run_apps.rst
create mode 100644 lib/librte_eal/windows/eal_hugepages.c
diff --git a/config/meson.build b/config/meson.build
index 58421342b..4607655d9 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -263,6 +263,8 @@ if is_windows
if cc.get_id() == 'gcc'
add_project_arguments('-D__USE_MINGW_ANSI_STDIO', language: 'c')
endif
+
+ add_project_link_arguments('-ladvapi32', language: 'c')
endif
if get_option('b_lto')
diff --git a/doc/guides/windows_gsg/build_dpdk.rst b/doc/guides/windows_gsg/build_dpdk.rst
index d46e84e3f..650483e3b 100644
--- a/doc/guides/windows_gsg/build_dpdk.rst
+++ b/doc/guides/windows_gsg/build_dpdk.rst
@@ -111,23 +111,3 @@ Depending on the distribution, paths in this file may need adjustments.
meson --cross-file config/x86/meson_mingw.txt -Dexamples=helloworld build
ninja -C build
-
-
-Run the helloworld example
-==========================
-
-Navigate to the examples in the build directory and run `dpdk-helloworld.exe`.
-
-.. code-block:: console
-
- cd C:\Users\me\dpdk\build\examples
- dpdk-helloworld.exe
- hello from core 1
- hello from core 3
- hello from core 0
- hello from core 2
-
-Note for MinGW-w64: applications are linked to ``libwinpthread-1.dll``
-by default. To run the example, either add toolchain executables directory
-to the PATH or copy the library to the working directory.
-Alternatively, static linking may be used (mind the LGPLv2.1 license).
diff --git a/doc/guides/windows_gsg/index.rst b/doc/guides/windows_gsg/index.rst
index d9b7990a8..e94593572 100644
--- a/doc/guides/windows_gsg/index.rst
+++ b/doc/guides/windows_gsg/index.rst
@@ -12,3 +12,4 @@ Getting Started Guide for Windows
intro
build_dpdk
+ run_apps
diff --git a/doc/guides/windows_gsg/run_apps.rst b/doc/guides/windows_gsg/run_apps.rst
new file mode 100644
index 000000000..21ac7f6c1
--- /dev/null
+++ b/doc/guides/windows_gsg/run_apps.rst
@@ -0,0 +1,47 @@
+.. SPDX-License-Identifier: BSD-3-Clause
+ Copyright(c) 2020 Dmitry Kozlyuk
+
+Running DPDK Applications
+=========================
+
+Grant *Lock pages in memory* Privilege
+--------------------------------------
+
+Use of hugepages ("large pages" in Windows terminolocy) requires
+``SeLockMemoryPrivilege`` for the user running an application.
+
+1. Open *Local Security Policy* snap in, either:
+
+ * Control Panel / Computer Management / Local Security Policy;
+ * or Win+R, type ``secpol``, press Enter.
+
+2. Open *Local Policies / User Rights Assignment / Lock pages in memory.*
+
+3. Add desired users or groups to the list of grantees.
+
+4. Privilege is applied upon next logon. In particular, if privilege has been
+ granted to current user, a logoff is required before it is available.
+
+See `Large-Page Support`_ in MSDN for details.
+
+.. _Large-page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
+
+
+Run the ``helloworld`` Example
+------------------------------
+
+Navigate to the examples in the build directory and run `dpdk-helloworld.exe`.
+
+.. code-block:: console
+
+ cd C:\Users\me\dpdk\build\examples
+ dpdk-helloworld.exe
+ hello from core 1
+ hello from core 3
+ hello from core 0
+ hello from core 2
+
+Note for MinGW-w64: applications are linked to ``libwinpthread-1.dll``
+by default. To run the example, either add toolchain executables directory
+to the PATH or copy the library to the working directory.
+Alternatively, static linking may be used (mind the LGPLv2.1 license).
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 2cf7a04ef..63461f51a 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -18,8 +18,11 @@
#include <eal_options.h>
#include <eal_private.h>
+#include "eal_hugepages.h"
#include "eal_windows.h"
+#define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)
+
/* Allow the application to print its usage message too if set */
static rte_usage_hook_t rte_application_usage_hook;
@@ -242,6 +245,17 @@ rte_eal_init(int argc, char **argv)
if (fctret < 0)
exit(1);
+ if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
+ rte_eal_init_alert("Cannot get hugepage information");
+ rte_errno = EACCES;
+ return -1;
+ }
+
+ if (internal_config.memory == 0 && !internal_config.force_sockets) {
+ if (internal_config.no_hugetlbfs)
+ internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_hugepages.c b/lib/librte_eal/windows/eal_hugepages.c
new file mode 100644
index 000000000..b099d13f9
--- /dev/null
+++ b/lib/librte_eal/windows/eal_hugepages.c
@@ -0,0 +1,108 @@
+#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+#include <rte_memzone.h>
+#include <rte_os.h>
+
+#include "eal_filesystem.h"
+#include "eal_hugepages.h"
+#include "eal_internal_cfg.h"
+#include "eal_windows.h"
+
+static int
+hugepage_claim_privilege(void)
+{
+ static const wchar_t privilege[] = L"SeLockMemoryPrivilege";
+
+ HANDLE token;
+ LUID luid;
+ TOKEN_PRIVILEGES tp;
+ int ret = -1;
+
+ if (!OpenProcessToken(GetCurrentProcess(),
+ TOKEN_ADJUST_PRIVILEGES, &token)) {
+ RTE_LOG_WIN32_ERR("OpenProcessToken()");
+ return -1;
+ }
+
+ if (!LookupPrivilegeValueW(NULL, privilege, &luid)) {
+ RTE_LOG_WIN32_ERR("LookupPrivilegeValue(\"%S\")", privilege);
+ goto exit;
+ }
+
+ tp.PrivilegeCount = 1;
+ tp.Privileges[0].Luid = luid;
+ tp.Privileges[0].Attributes = SE_PRIVILEGE_ENABLED;
+
+ if (!AdjustTokenPrivileges(
+ token, FALSE, &tp, sizeof(tp), NULL, NULL)) {
+ RTE_LOG_WIN32_ERR("AdjustTokenPrivileges()");
+ goto exit;
+ }
+
+ ret = 0;
+
+exit:
+ CloseHandle(token);
+
+ return ret;
+}
+
+static int
+hugepage_info_init(void)
+{
+ struct hugepage_info *hpi;
+ unsigned int socket_id;
+ int ret = 0;
+
+ /* Only one hugepage size available in Windows. */
+ internal_config.num_hugepage_sizes = 1;
+ hpi = &internal_config.hugepage_info[0];
+
+ hpi->hugepage_sz = GetLargePageMinimum();
+ if (hpi->hugepage_sz == 0)
+ return -ENOTSUP;
+
+ /* Assume all memory on each NUMA node available for hugepages,
+ * because Windows neither advertises additional limits,
+ * nor provides an API to query them.
+ */
+ for (socket_id = 0; socket_id < rte_socket_count(); socket_id++) {
+ ULONGLONG bytes;
+ unsigned int numa_node;
+
+ numa_node = eal_socket_numa_node(socket_id);
+ if (!GetNumaAvailableMemoryNodeEx(numa_node, &bytes)) {
+ RTE_LOG_WIN32_ERR("GetNumaAvailableMemoryNodeEx(%u)",
+ numa_node);
+ continue;
+ }
+
+ hpi->num_pages[socket_id] = bytes / hpi->hugepage_sz;
+ RTE_LOG(DEBUG, EAL,
+ "Found %u hugepages of %zu bytes on socket %u\n",
+ hpi->num_pages[socket_id], hpi->hugepage_sz, socket_id);
+ }
+
+ /* No hugepage filesystem in Windows. */
+ hpi->lock_descriptor = -1;
+ memset(hpi->hugedir, 0, sizeof(hpi->hugedir));
+
+ return ret;
+}
+
+int
+eal_hugepage_info_init(void)
+{
+ if (hugepage_claim_privilege() < 0) {
+ RTE_LOG(ERR, EAL, "Cannot claim hugepage privilege\n");
+ return -1;
+ }
+
+ if (hugepage_info_init() < 0) {
+ RTE_LOG(ERR, EAL, "Cannot get hugepage information\n");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 09dd4ab2f..5f118bfe2 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -6,6 +6,7 @@ subdir('include')
sources += files(
'eal.c',
'eal_debug.c',
+ 'eal_hugepages.c',
'eal_lcore.c',
'eal_thread.c',
'getopt.c',
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (3 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 04/10] eal/windows: initialize hugepage info Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-15 21:48 ` Thomas Monjalon
2020-04-17 12:24 ` Burakov, Anatoly
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
` (5 subsequent siblings)
10 siblings, 2 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon
EAL common code uses file locking and truncation. Introduce
OS-independent wrappers in order to support both Linux/FreeBSD
and Windows:
* eal_file_lock: lock or unlock an open file.
* eal_file_truncate: enforce a given size for an open file.
Wrappers follow POSIX semantics, but interface is not POSIX,
so that it can be made more clean, e.g. by not mixing locking
operation and behaviour on conflict.
Implementation for Linux and FreeBSD is placed in "unix" subdirectory,
which is intended for common code between the two. Files should be named
after the ones from which the code is factored in OS subdirectory.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/common/eal_private.h | 45 ++++++++++++++++
lib/librte_eal/meson.build | 4 ++
lib/librte_eal/unix/eal.c | 47 ++++++++++++++++
lib/librte_eal/unix/meson.build | 6 +++
lib/librte_eal/windows/eal.c | 83 +++++++++++++++++++++++++++++
5 files changed, 185 insertions(+)
create mode 100644 lib/librte_eal/unix/eal.c
create mode 100644 lib/librte_eal/unix/meson.build
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index ddcfbe2e4..65d61ff13 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -443,4 +443,49 @@ rte_option_usage(void);
uint64_t
eal_get_baseaddr(void);
+/** File locking operation. */
+enum eal_flock_op {
+ EAL_FLOCK_SHARED, /**< Acquire a shared lock. */
+ EAL_FLOCK_EXCLUSIVE, /**< Acquire an exclusive lock. */
+ EAL_FLOCK_UNLOCK /**< Release a previously taken lock. */
+};
+
+/** Behavior on file locking conflict. */
+enum eal_flock_mode {
+ EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
+ EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
+};
+
+/**
+ * Lock or unlock the file.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX flock(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param op
+ * Operation to perform.
+ * @param mode
+ * Behavior on conflict.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode);
+
+/**
+ * Truncate or extend the file to the specified size.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX ftruncate(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param size
+ * Desired file size.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_truncate(int fd, ssize_t size);
+
#endif /* _EAL_PRIVATE_H_ */
diff --git a/lib/librte_eal/meson.build b/lib/librte_eal/meson.build
index 9d219a0e6..1f89efb88 100644
--- a/lib/librte_eal/meson.build
+++ b/lib/librte_eal/meson.build
@@ -6,6 +6,10 @@ subdir('include')
subdir('common')
+if not is_windows
+ subdir('unix')
+endif
+
dpdk_conf.set('RTE_EXEC_ENV_' + exec_env.to_upper(), 1)
subdir(exec_env)
diff --git a/lib/librte_eal/unix/eal.c b/lib/librte_eal/unix/eal.c
new file mode 100644
index 000000000..a337b59b1
--- /dev/null
+++ b/lib/librte_eal/unix/eal.c
@@ -0,0 +1,47 @@
+#include <sys/file.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <rte_errno.h>
+
+#include "eal_private.h"
+
+int
+eal_file_truncate(int fd, ssize_t size)
+{
+ int ret;
+
+ ret = ftruncate(fd, size);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
+
+int
+eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ int sys_flags = 0;
+ int ret;
+
+ if (mode == EAL_FLOCK_RETURN)
+ sys_flags |= LOCK_NB;
+
+ switch (op) {
+ case EAL_FLOCK_EXCLUSIVE:
+ sys_flags |= LOCK_EX;
+ break;
+ case EAL_FLOCK_SHARED:
+ sys_flags |= LOCK_SH;
+ break;
+ case EAL_FLOCK_UNLOCK:
+ sys_flags |= LOCK_UN;
+ break;
+ }
+
+ ret = flock(fd, sys_flags);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
diff --git a/lib/librte_eal/unix/meson.build b/lib/librte_eal/unix/meson.build
new file mode 100644
index 000000000..13564838e
--- /dev/null
+++ b/lib/librte_eal/unix/meson.build
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2020 Dmitry Kozlyuk
+
+sources += files(
+ 'eal.c',
+)
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 63461f51a..9dba895e7 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -224,6 +224,89 @@ rte_eal_init_alert(const char *msg)
RTE_LOG(ERR, EAL, "%s\n", msg);
}
+int
+eal_file_truncate(int fd, ssize_t size)
+{
+ HANDLE handle;
+ DWORD ret;
+ LONG low = (LONG)((size_t)size);
+ LONG high = (LONG)((size_t)size >> 32);
+
+ handle = (HANDLE)_get_osfhandle(fd);
+ if (handle == INVALID_HANDLE_VALUE) {
+ rte_errno = EBADF;
+ return -1;
+ }
+
+ ret = SetFilePointer(handle, low, &high, FILE_BEGIN);
+ if (ret == INVALID_SET_FILE_POINTER) {
+ RTE_LOG_WIN32_ERR("SetFilePointer()");
+ rte_errno = EINVAL;
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+lock_file(HANDLE handle, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ DWORD sys_flags = 0;
+ OVERLAPPED overlapped;
+
+ if (op == EAL_FLOCK_EXCLUSIVE)
+ sys_flags |= LOCKFILE_EXCLUSIVE_LOCK;
+ if (mode == EAL_FLOCK_RETURN)
+ sys_flags |= LOCKFILE_FAIL_IMMEDIATELY;
+
+ memset(&overlapped, 0, sizeof(overlapped));
+ if (!LockFileEx(handle, sys_flags, 0, 0, 0, &overlapped)) {
+ if ((sys_flags & LOCKFILE_FAIL_IMMEDIATELY) &&
+ (GetLastError() == ERROR_IO_PENDING)) {
+ rte_errno = EWOULDBLOCK;
+ } else {
+ RTE_LOG_WIN32_ERR("LockFileEx()");
+ rte_errno = EINVAL;
+ }
+ return -1;
+ }
+
+ return 0;
+}
+
+static int
+unlock_file(HANDLE handle)
+{
+ if (!UnlockFileEx(handle, 0, 0, 0, NULL)) {
+ RTE_LOG_WIN32_ERR("UnlockFileEx()");
+ rte_errno = EINVAL;
+ return -1;
+ }
+ return 0;
+}
+
+int
+eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ HANDLE handle = (HANDLE)_get_osfhandle(fd);
+
+ if (handle == INVALID_HANDLE_VALUE) {
+ rte_errno = EBADF;
+ return -1;
+ }
+
+ switch (op) {
+ case EAL_FLOCK_EXCLUSIVE:
+ case EAL_FLOCK_SHARED:
+ return lock_file(handle, op, mode);
+ case EAL_FLOCK_UNLOCK:
+ return unlock_file(handle);
+ default:
+ rte_errno = EINVAL;
+ return -1;
+ }
+}
+
/* Launch threads, called at application init(). */
int
rte_eal_init(int argc, char **argv)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
@ 2020-04-15 21:48 ` Thomas Monjalon
2020-04-17 12:24 ` Burakov, Anatoly
1 sibling, 0 replies; 218+ messages in thread
From: Thomas Monjalon @ 2020-04-15 21:48 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
Thanks for starting the new directory for Unix common implementation.
14/04/2020 21:44, Dmitry Kozlyuk:
> --- /dev/null
> +++ b/lib/librte_eal/unix/eal.c
Please take care of not creating a new file without adding
SPDX tag and copyright owner.
> @@ -0,0 +1,47 @@
> +#include <sys/file.h>
> +#include <sys/mman.h>
> +#include <unistd.h>
> +
> +#include <rte_errno.h>
> +
> +#include "eal_private.h"
> +
> +int
> +eal_file_truncate(int fd, ssize_t size)
[...]
> +int
> +eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+1
Adding new abstractions is the way to go in my opinion.
Thanks
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
2020-04-15 21:48 ` Thomas Monjalon
@ 2020-04-17 12:24 ` Burakov, Anatoly
2020-04-28 23:50 ` Dmitry Kozlyuk
1 sibling, 1 reply; 218+ messages in thread
From: Burakov, Anatoly @ 2020-04-17 12:24 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
On 14-Apr-20 8:44 PM, Dmitry Kozlyuk wrote:
> EAL common code uses file locking and truncation. Introduce
> OS-independent wrappers in order to support both Linux/FreeBSD
> and Windows:
>
> * eal_file_lock: lock or unlock an open file.
> * eal_file_truncate: enforce a given size for an open file.
>
> Wrappers follow POSIX semantics, but interface is not POSIX,
> so that it can be made more clean, e.g. by not mixing locking
> operation and behaviour on conflict.
>
> Implementation for Linux and FreeBSD is placed in "unix" subdirectory,
> which is intended for common code between the two. Files should be named
> after the ones from which the code is factored in OS subdirectory.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> lib/librte_eal/common/eal_private.h | 45 ++++++++++++++++
> lib/librte_eal/meson.build | 4 ++
> lib/librte_eal/unix/eal.c | 47 ++++++++++++++++
> lib/librte_eal/unix/meson.build | 6 +++
> lib/librte_eal/windows/eal.c | 83 +++++++++++++++++++++++++++++
> 5 files changed, 185 insertions(+)
> create mode 100644 lib/librte_eal/unix/eal.c
> create mode 100644 lib/librte_eal/unix/meson.build
>
> diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
> index ddcfbe2e4..65d61ff13 100644
> --- a/lib/librte_eal/common/eal_private.h
> +++ b/lib/librte_eal/common/eal_private.h
> @@ -443,4 +443,49 @@ rte_option_usage(void);
> uint64_t
> eal_get_baseaddr(void);
>
> +/** File locking operation. */
> +enum eal_flock_op {
> + EAL_FLOCK_SHARED, /**< Acquire a shared lock. */
> + EAL_FLOCK_EXCLUSIVE, /**< Acquire an exclusive lock. */
> + EAL_FLOCK_UNLOCK /**< Release a previously taken lock. */
> +};
> +
> +/** Behavior on file locking conflict. */
> +enum eal_flock_mode {
> + EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
> + EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
> +};
Nitpicking, but why not blocking/unblocking? The terminology seems
pretty standard.
--
Thanks,
Anatoly
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations
2020-04-17 12:24 ` Burakov, Anatoly
@ 2020-04-28 23:50 ` Dmitry Kozlyuk
0 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-28 23:50 UTC (permalink / raw)
To: Burakov, Anatoly
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
On 2020-04-17 13:24 GMT+0100 Burakov, Anatoly wrote:
[snip]
> > +/** Behavior on file locking conflict. */
> > +enum eal_flock_mode {
> > + EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
> > + EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
> > +};
>
> Nitpicking, but why not blocking/unblocking? The terminology seems
> pretty standard.
On Windows, LockFileEx() call may be non-blocking, but still configured to
fail if the lock is already taken. To avoid confusion, these names reflect
what the behavior will be instead of how it will be achieved.
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (4 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 05/10] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-15 22:17 ` Thomas Monjalon
` (4 more replies)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
` (4 subsequent siblings)
10 siblings, 5 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Anatoly Burakov,
Harini Ramakrishnan, Omar Cardona, Pallavi Kadam, Ranjit Menon
System meory management is implemented differently for POSIX and
Windows. Introduce wrapper functions for operations used across DPDK:
* rte_mem_map()
Create memory mapping for a regular file or a page file (swap).
This supports mapping to a reserved memory region even on Windows.
* rte_mem_unmap()
Remove mapping created with rte_mem_map().
* rte_get_page_size()
Obtain default system page size.
* rte_mem_lock()
Make arbitrary-sized memory region non-swappable.
Wrappers follow POSIX semantics limited to DPDK tasks, but their
signatures deliberately differ from POSIX ones to be more safe and
expressive.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 10 +-
lib/librte_eal/common/eal_private.h | 51 +++-
lib/librte_eal/include/rte_memory.h | 68 +++++
lib/librte_eal/rte_eal_exports.def | 4 +
lib/librte_eal/rte_eal_version.map | 4 +
lib/librte_eal/unix/eal_memory.c | 113 +++++++
lib/librte_eal/unix/meson.build | 1 +
lib/librte_eal/windows/eal.c | 6 +
lib/librte_eal/windows/eal_memory.c | 437 +++++++++++++++++++++++++++
lib/librte_eal/windows/eal_windows.h | 67 ++++
lib/librte_eal/windows/meson.build | 1 +
11 files changed, 758 insertions(+), 4 deletions(-)
create mode 100644 lib/librte_eal/unix/eal_memory.c
create mode 100644 lib/librte_eal/windows/eal_memory.c
diff --git a/config/meson.build b/config/meson.build
index 4607655d9..bceb5ef7b 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -256,14 +256,20 @@ if is_freebsd
endif
if is_windows
- # Minimum supported API is Windows 7.
- add_project_arguments('-D_WIN32_WINNT=0x0601', language: 'c')
+ # VirtualAlloc2() is available since Windows 10 / Server 2016.
+ add_project_arguments('-D_WIN32_WINNT=0x0A00', language: 'c')
# Use MinGW-w64 stdio, because DPDK assumes ANSI-compliant formatting.
if cc.get_id() == 'gcc'
add_project_arguments('-D__USE_MINGW_ANSI_STDIO', language: 'c')
endif
+ # Contrary to docs, VirtualAlloc2() is exported by mincore.lib
+ # in Windows SDK, while MinGW exports it by advapi32.a.
+ if is_ms_linker
+ add_project_link_arguments('-lmincore', language: 'c')
+ endif
+
add_project_link_arguments('-ladvapi32', language: 'c')
endif
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 65d61ff13..1e89338f2 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -11,6 +11,7 @@
#include <rte_dev.h>
#include <rte_lcore.h>
+#include <rte_memory.h>
/**
* Structure storing internal configuration (per-lcore)
@@ -202,6 +203,16 @@ int rte_eal_alarm_init(void);
*/
int rte_eal_check_module(const char *module_name);
+/**
+ * Memory reservation flags.
+ */
+enum eal_mem_reserve_flags {
+ /**< Reserve hugepages (support may be limited or missing). */
+ EAL_RESERVE_HUGEPAGES = 1 << 0,
+ /**< Fail if requested address is not available. */
+ EAL_RESERVE_EXACT_ADDRESS = 1 << 1
+};
+
/**
* Get virtual area of specified size from the OS.
*
@@ -232,8 +243,8 @@ int rte_eal_check_module(const char *module_name);
#define EAL_VIRTUAL_AREA_UNMAP (1 << 2)
/**< immediately unmap reserved virtual area. */
void *
-eal_get_virtual_area(void *requested_addr, size_t *size,
- size_t page_sz, int flags, int mmap_flags);
+eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
+ int flags, int mmap_flags);
/**
* Get cpu core_id.
@@ -488,4 +499,40 @@ int eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode);
*/
int eal_file_truncate(int fd, ssize_t size);
+/**
+ * Reserve a region of virtual memory.
+ *
+ * Use eal_mem_free() to free reserved memory.
+ *
+ * @param requested_addr
+ * A desired reservation address. The system may not respect it.
+ * NULL means the address will be chosen by the system.
+ * @param size
+ * Reservation size. Must be a multiple of system page size.
+ * @param flags
+ * Reservation options.
+ * @returns
+ * Starting address of the reserved area on success, NULL on failure.
+ * Callers must not access this memory until remapping it.
+ */
+void *eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags);
+
+/**
+ * Free memory obtained by eal_mem_reserve() or eal_mem_alloc().
+ *
+ * If @code virt @endcode and @code size @endcode describe a part of the
+ * reserved region, only this part of the region is freed (accurately
+ * up to the system page size). If @code virt @endcode points to allocated
+ * memory, @code size @endcode must match the one specified on allocation.
+ * The behavior is undefined if the memory pointed by @code virt @endcode
+ * is obtained from another source than listed above.
+ *
+ * @param virt
+ * A virtual address in a region previously reserved.
+ * @param size
+ * Number of bytes to unreserve.
+ */
+void eal_mem_free(void *virt, size_t size);
+
#endif /* _EAL_PRIVATE_H_ */
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 3d8d0bd69..1b7c3e5df 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -85,6 +85,74 @@ struct rte_memseg_list {
struct rte_fbarray memseg_arr;
};
+/**
+ * Memory protection flags.
+ */
+enum rte_mem_prot {
+ RTE_PROT_READ = 1 << 0, /**< Read access. */
+ RTE_PROT_WRITE = 1 << 1, /**< Write access. */
+ RTE_PROT_EXECUTE = 1 << 2 /**< Code execution. */
+};
+
+/**
+ * Memory mapping additional flags.
+ *
+ * In Linux and FreeBSD, each flag is semantically equivalent
+ * to OS-specific mmap(3) flag with the same or similar name.
+ * In Windows, POSIX and MAP_ANONYMOUS semantics are followed.
+ */
+enum rte_map_flags {
+ /** Changes of mapped memory are visible to other processes. */
+ RTE_MAP_SHARED = 1 << 0,
+ /** Mapping is not backed by a regular file. */
+ RTE_MAP_ANONYMOUS = 1 << 1,
+ /** Copy-on-write mapping, changes are invisible to other processes. */
+ RTE_MAP_PRIVATE = 1 << 2,
+ /** Fail if requested address cannot be taken. */
+ RTE_MAP_FIXED = 1 << 3
+};
+
+/**
+ * OS-independent implementation of POSIX mmap(3)
+ * with MAP_ANONYMOUS Linux/FreeBSD extension.
+ */
+__rte_experimental
+void *rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset);
+
+/**
+ * OS-independent implementation of POSIX munmap(3).
+ */
+__rte_experimental
+int rte_mem_unmap(void *virt, size_t size);
+
+/**
+ * Get system page size. This function never failes.
+ *
+ * @return
+ * Positive page size in bytes.
+ */
+__rte_experimental
+int rte_get_page_size(void);
+
+/**
+ * Lock region in physical memory and prevent it from swapping.
+ *
+ * @param virt
+ * The virtual address.
+ * @param size
+ * Size of the region.
+ * @return
+ * 0 on success, negative on error.
+ *
+ * @note Implementations may require @p virt and @p size to be multiples
+ * of system page size.
+ * @see rte_get_page_size()
+ * @see rte_mem_lock_page()
+ */
+__rte_experimental
+int rte_mem_lock(const void *virt, size_t size);
+
/**
* Lock page in physical memory and prevent from swapping.
*
diff --git a/lib/librte_eal/rte_eal_exports.def b/lib/librte_eal/rte_eal_exports.def
index 12a6c79d6..bacf9a107 100644
--- a/lib/librte_eal/rte_eal_exports.def
+++ b/lib/librte_eal/rte_eal_exports.def
@@ -5,5 +5,9 @@ EXPORTS
rte_eal_mp_remote_launch
rte_eal_mp_wait_lcore
rte_eal_remote_launch
+ rte_get_page_size
rte_log
+ rte_mem_lock
+ rte_mem_map
+ rte_mem_unmap
rte_vlog
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index f9ede5b41..07128898f 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -337,5 +337,9 @@ EXPERIMENTAL {
rte_thread_is_intr;
# added in 20.05
+ rte_get_page_size;
rte_log_can_log;
+ rte_mem_lock;
+ rte_mem_map;
+ rte_mem_unmap;
};
diff --git a/lib/librte_eal/unix/eal_memory.c b/lib/librte_eal/unix/eal_memory.c
new file mode 100644
index 000000000..6bd087d94
--- /dev/null
+++ b/lib/librte_eal/unix/eal_memory.c
@@ -0,0 +1,113 @@
+#include <string.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
+
+#include "eal_private.h"
+
+static void *
+mem_map(void *requested_addr, size_t size, int prot, int flags,
+ int fd, size_t offset)
+{
+ void *virt = mmap(requested_addr, size, prot, flags, fd, offset);
+ if (virt == MAP_FAILED) {
+ RTE_LOG(ERR, EAL,
+ "Cannot mmap(%p, 0x%zx, 0x%x, 0x%x, %d, 0x%zx): %s\n",
+ requested_addr, size, prot, flags, fd, offset,
+ strerror(errno));
+ rte_errno = errno;
+ return NULL;
+ }
+ return virt;
+}
+
+static int
+mem_unmap(void *virt, size_t size)
+{
+ int ret = munmap(virt, size);
+ if (ret < 0) {
+ RTE_LOG(ERR, EAL, "Cannot munmap(%p, 0x%zx): %s\n",
+ virt, size, strerror(errno));
+ rte_errno = errno;
+ }
+ return ret;
+}
+
+void *
+eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags)
+{
+ int sys_flags = MAP_PRIVATE | MAP_ANONYMOUS;
+
+#ifdef MAP_HUGETLB
+ if (flags & EAL_RESERVE_HUGEPAGES)
+ sys_flags |= MAP_HUGETLB;
+#endif
+ if (flags & EAL_RESERVE_EXACT_ADDRESS)
+ sys_flags |= MAP_FIXED;
+
+ return mem_map(requested_addr, size, PROT_NONE, sys_flags, -1, 0);
+}
+
+void
+eal_mem_free(void *virt, size_t size)
+{
+ mem_unmap(virt, size);
+}
+
+static int
+mem_rte_to_sys_prot(enum rte_mem_prot prot)
+{
+ int sys_prot = 0;
+
+ if (prot & RTE_PROT_READ)
+ sys_prot |= PROT_READ;
+ if (prot & RTE_PROT_WRITE)
+ sys_prot |= PROT_WRITE;
+ if (prot & RTE_PROT_EXECUTE)
+ sys_prot |= PROT_EXEC;
+
+ return sys_prot;
+}
+
+void *
+rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset)
+{
+ int sys_prot = 0;
+ int sys_flags = 0;
+
+ sys_prot = mem_rte_to_sys_prot(prot);
+
+ if (flags & RTE_MAP_SHARED)
+ sys_flags |= MAP_SHARED;
+ if (flags & RTE_MAP_ANONYMOUS)
+ sys_flags |= MAP_ANONYMOUS;
+ if (flags & RTE_MAP_PRIVATE)
+ sys_flags |= MAP_PRIVATE;
+ if (flags & RTE_MAP_FIXED)
+ sys_flags |= MAP_FIXED;
+
+ return mem_map(requested_addr, size, sys_prot, sys_flags, fd, offset);
+}
+
+int
+rte_mem_unmap(void *virt, size_t size)
+{
+ return mem_unmap(virt, size);
+}
+
+int
+rte_get_page_size(void)
+{
+ return getpagesize();
+}
+
+int
+rte_mem_lock(const void *virt, size_t size)
+{
+ return mlock(virt, size);
+}
diff --git a/lib/librte_eal/unix/meson.build b/lib/librte_eal/unix/meson.build
index 13564838e..50c019a56 100644
--- a/lib/librte_eal/unix/meson.build
+++ b/lib/librte_eal/unix/meson.build
@@ -3,4 +3,5 @@
sources += files(
'eal.c',
+ 'eal_memory.c',
)
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index 9dba895e7..cf55b56da 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -339,6 +339,12 @@ rte_eal_init(int argc, char **argv)
internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
}
+ if (eal_mem_win32api_init() < 0) {
+ rte_eal_init_alert("Cannot access Win32 memory management");
+ rte_errno = ENOTSUP;
+ return -1;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
new file mode 100644
index 000000000..5697187ce
--- /dev/null
+++ b/lib/librte_eal/windows/eal_memory.c
@@ -0,0 +1,437 @@
+#include <io.h>
+
+#include <rte_errno.h>
+#include <rte_memory.h>
+
+#include "eal_private.h"
+#include "eal_windows.h"
+
+/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
+ * Provide a copy of definitions and code to load it dynamically.
+ * Note: definitions are copied verbatim from Microsoft documentation
+ * and don't follow DPDK code style.
+ */
+#ifndef MEM_PRESERVE_PLACEHOLDER
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ne-winnt-mem_extended_parameter_type */
+typedef enum MEM_EXTENDED_PARAMETER_TYPE {
+ MemExtendedParameterInvalidType,
+ MemExtendedParameterAddressRequirements,
+ MemExtendedParameterNumaNode,
+ MemExtendedParameterPartitionHandle,
+ MemExtendedParameterMax,
+ MemExtendedParameterUserPhysicalHandle,
+ MemExtendedParameterAttributeFlags
+} *PMEM_EXTENDED_PARAMETER_TYPE;
+
+#define MEM_EXTENDED_PARAMETER_TYPE_BITS 4
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ns-winnt-mem_extended_parameter */
+typedef struct MEM_EXTENDED_PARAMETER {
+ struct {
+ DWORD64 Type : MEM_EXTENDED_PARAMETER_TYPE_BITS;
+ DWORD64 Reserved : 64 - MEM_EXTENDED_PARAMETER_TYPE_BITS;
+ } DUMMYSTRUCTNAME;
+ union {
+ DWORD64 ULong64;
+ PVOID Pointer;
+ SIZE_T Size;
+ HANDLE Handle;
+ DWORD ULong;
+ } DUMMYUNIONNAME;
+} MEM_EXTENDED_PARAMETER, *PMEM_EXTENDED_PARAMETER;
+
+/* https://docs.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualalloc2 */
+typedef PVOID (*VirtualAlloc2_type)(
+ HANDLE Process,
+ PVOID BaseAddress,
+ SIZE_T Size,
+ ULONG AllocationType,
+ ULONG PageProtection,
+ MEM_EXTENDED_PARAMETER *ExtendedParameters,
+ ULONG ParameterCount
+);
+
+/* VirtualAlloc2() flags. */
+#define MEM_COALESCE_PLACEHOLDERS 0x00000001
+#define MEM_PRESERVE_PLACEHOLDER 0x00000002
+#define MEM_REPLACE_PLACEHOLDER 0x00004000
+#define MEM_RESERVE_PLACEHOLDER 0x00040000
+
+/* Named exactly as the function, so that user code does not depend
+ * on it being found at compile time or dynamically.
+ */
+static VirtualAlloc2_type VirtualAlloc2;
+
+int
+eal_mem_win32api_init(void)
+{
+ static const char library_name[] = "kernelbase.dll";
+ static const char function[] = "VirtualAlloc2";
+
+ OSVERSIONINFO info;
+ HMODULE library = NULL;
+ int ret = 0;
+
+ /* Already done. */
+ if (VirtualAlloc2 != NULL)
+ return 0;
+
+ /* IsWindows10OrGreater() may also be unavailable. */
+ memset(&info, 0, sizeof(info));
+ info.dwOSVersionInfoSize = sizeof(info);
+ GetVersionEx(&info);
+
+ /* Checking for Windows 10+ will also detect Windows Server 2016+.
+ * Do not abort, because Windows may report false version depending
+ * on executable manifest, compatibility mode, etc.
+ */
+ if (info.dwMajorVersion < 10)
+ RTE_LOG(DEBUG, EAL, "Windows 10+ or Windows Server 2016+ "
+ "is required for advanced memory features\n");
+
+ library = LoadLibraryA(library_name);
+ if (library == NULL) {
+ RTE_LOG_WIN32_ERR("LoadLibraryA(\"%s\")", library_name);
+ return -1;
+ }
+
+ VirtualAlloc2 = (VirtualAlloc2_type)(
+ (void *)GetProcAddress(library, function));
+ if (VirtualAlloc2 == NULL) {
+ RTE_LOG_WIN32_ERR("GetProcAddress(\"%s\", \"%s\")\n",
+ library_name, function);
+ ret = -1;
+ }
+
+ FreeLibrary(library);
+
+ return ret;
+}
+
+#else
+
+/* Stub in case VirtualAlloc2() is provided by the compiler. */
+int
+eal_mem_win32api_init(void)
+{
+ return 0;
+}
+
+#endif /* no VirtualAlloc2() */
+
+/* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
+static void
+set_errno_from_win32_alloc_error(DWORD code)
+{
+ switch (code) {
+ case ERROR_SUCCESS:
+ rte_errno = 0;
+ break;
+
+ case ERROR_INVALID_ADDRESS:
+ /* A valid requested address is not available. */
+ case ERROR_COMMITMENT_LIMIT:
+ /* May occcur when committing regular memory. */
+ case ERROR_NO_SYSTEM_RESOURCES:
+ /* Occurs when the system runs out of hugepages. */
+ rte_errno = ENOMEM;
+ break;
+
+ case ERROR_INVALID_PARAMETER:
+ default:
+ rte_errno = EINVAL;
+ break;
+ }
+}
+
+void *
+eal_mem_reserve(void *requested_addr, size_t size,
+ enum eal_mem_reserve_flags flags)
+{
+ void *virt;
+
+ /* Windows requires hugepages to be committed. */
+ if (flags & EAL_RESERVE_HUGEPAGES) {
+ RTE_LOG(ERR, EAL, "Hugepage reservation is not supported\n");
+ rte_errno = ENOTSUP;
+ return NULL;
+ }
+
+ virt = VirtualAlloc2(GetCurrentProcess(), requested_addr, size,
+ MEM_RESERVE | MEM_RESERVE_PLACEHOLDER, PAGE_NOACCESS,
+ NULL, 0);
+ if (virt == NULL) {
+ DWORD err = GetLastError();
+ RTE_LOG_WIN32_ERR("VirtualAlloc2()");
+ set_errno_from_win32_alloc_error(err);
+ }
+
+ if ((flags & EAL_RESERVE_EXACT_ADDRESS) && (virt != requested_addr)) {
+ if (!VirtualFree(virt, 0, MEM_RELEASE))
+ RTE_LOG_WIN32_ERR("VirtualFree()");
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+
+ return virt;
+}
+
+void *
+eal_mem_alloc(size_t size, enum rte_page_sizes page_size)
+{
+ if (page_size != 0)
+ return eal_mem_alloc_socket(size, SOCKET_ID_ANY);
+
+ return VirtualAlloc(
+ NULL, size, MEM_RESERVE | MEM_COMMIT, PAGE_READWRITE);
+}
+
+void *
+eal_mem_alloc_socket(size_t size, int socket_id)
+{
+ DWORD flags = MEM_RESERVE | MEM_COMMIT;
+ void *addr;
+
+ flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
+ addr = VirtualAllocExNuma(GetCurrentProcess(), NULL, size, flags,
+ PAGE_READWRITE, eal_socket_numa_node(socket_id));
+ if (addr == NULL)
+ rte_errno = ENOMEM;
+ return addr;
+}
+
+void*
+eal_mem_commit(void *requested_addr, size_t size, int socket_id)
+{
+ MEM_EXTENDED_PARAMETER param;
+ DWORD param_count = 0;
+ DWORD flags;
+ void *addr;
+
+ if (requested_addr != NULL) {
+ MEMORY_BASIC_INFORMATION info;
+ if (VirtualQuery(requested_addr, &info, sizeof(info)) == 0) {
+ RTE_LOG_WIN32_ERR("VirtualQuery()");
+ return NULL;
+ }
+
+ /* Split reserved region if only a part is committed. */
+ flags = MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER;
+ if ((info.RegionSize > size) &&
+ !VirtualFree(requested_addr, size, flags)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, "
+ "<split placeholder>)", requested_addr, size);
+ return NULL;
+ }
+ }
+
+ if (socket_id != SOCKET_ID_ANY) {
+ param_count = 1;
+ memset(¶m, 0, sizeof(param));
+ param.Type = MemExtendedParameterNumaNode;
+ param.ULong = eal_socket_numa_node(socket_id);
+ }
+
+ flags = MEM_RESERVE | MEM_COMMIT | MEM_LARGE_PAGES;
+ if (requested_addr != NULL)
+ flags |= MEM_REPLACE_PLACEHOLDER;
+
+ addr = VirtualAlloc2(GetCurrentProcess(), requested_addr, size,
+ flags, PAGE_READWRITE, ¶m, param_count);
+ if (addr == NULL) {
+ DWORD err = GetLastError();
+ RTE_LOG_WIN32_ERR("VirtualAlloc2(%p, %zu, "
+ "<replace placeholder>)", addr, size);
+ set_errno_from_win32_alloc_error(err);
+ return NULL;
+ }
+
+ return addr;
+}
+
+int
+eal_mem_decommit(void *addr, size_t size)
+{
+ if (!VirtualFree(addr, size, MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, ...)", addr, size);
+ return -1;
+ }
+ return 0;
+}
+
+/**
+ * Free a reserved memory region in full or in part.
+ *
+ * @param addr
+ * Starting address of the area to free.
+ * @param size
+ * Number of bytes to free. Must be a multiple of page size.
+ * @param reserved
+ * Fail if the region is not in reserved state.
+ * @return
+ * * 0 on successful deallocation;
+ * * 1 if region mut be in reserved state but it is not;
+ * * (-1) on system API failures.
+ */
+static int
+mem_free(void *addr, size_t size, bool reserved)
+{
+ MEMORY_BASIC_INFORMATION info;
+ if (VirtualQuery(addr, &info, sizeof(info)) == 0) {
+ RTE_LOG_WIN32_ERR("VirtualQuery()");
+ return -1;
+ }
+
+ if (reserved && (info.State != MEM_RESERVE))
+ return 1;
+
+ /* Free complete region. */
+ if ((addr == info.AllocationBase) && (size == info.RegionSize)) {
+ if (!VirtualFree(addr, 0, MEM_RELEASE)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, 0, MEM_RELEASE)",
+ addr);
+ }
+ return 0;
+ }
+
+ /* Split the part to be freed and the remaining reservation. */
+ if (!VirtualFree(addr, size, MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, "
+ "MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)", addr, size);
+ return -1;
+ }
+
+ /* Actually free reservation part. */
+ if (!VirtualFree(addr, 0, MEM_RELEASE)) {
+ RTE_LOG_WIN32_ERR("VirtualFree(%p, 0, MEM_RELEASE)", addr);
+ return -1;
+ }
+
+ return 0;
+}
+
+void
+eal_mem_free(void *virt, size_t size)
+{
+ mem_free(virt, size, false);
+}
+
+void *
+rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
+ enum rte_map_flags flags, int fd, size_t offset)
+{
+ HANDLE file_handle = INVALID_HANDLE_VALUE;
+ HANDLE mapping_handle = INVALID_HANDLE_VALUE;
+ DWORD sys_prot = 0;
+ DWORD sys_access = 0;
+ DWORD size_high = (DWORD)(size >> 32);
+ DWORD size_low = (DWORD)size;
+ DWORD offset_high = (DWORD)(offset >> 32);
+ DWORD offset_low = (DWORD)offset;
+ LPVOID virt = NULL;
+
+ if (prot & RTE_PROT_EXECUTE) {
+ if (prot & RTE_PROT_READ) {
+ sys_prot = PAGE_EXECUTE_READ;
+ sys_access = FILE_MAP_READ | FILE_MAP_EXECUTE;
+ }
+ if (prot & RTE_PROT_WRITE) {
+ sys_prot = PAGE_EXECUTE_READWRITE;
+ sys_access = FILE_MAP_WRITE | FILE_MAP_EXECUTE;
+ }
+ } else {
+ if (prot & RTE_PROT_READ) {
+ sys_prot = PAGE_READONLY;
+ sys_access = FILE_MAP_READ;
+ }
+ if (prot & RTE_PROT_WRITE) {
+ sys_prot = PAGE_READWRITE;
+ sys_access = FILE_MAP_WRITE;
+ }
+ }
+
+ if (flags & RTE_MAP_PRIVATE)
+ sys_access |= FILE_MAP_COPY;
+
+ if ((flags & RTE_MAP_ANONYMOUS) == 0)
+ file_handle = (HANDLE)_get_osfhandle(fd);
+
+ mapping_handle = CreateFileMapping(
+ file_handle, NULL, sys_prot, size_high, size_low, NULL);
+ if (mapping_handle == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("CreateFileMapping()");
+ return NULL;
+ }
+
+ /* TODO: there is a race for the requested_addr between mem_free()
+ * and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
+ * region with a mapping in a single operation, but it does not support
+ * private mappings.
+ */
+ if (requested_addr != NULL) {
+ int ret = mem_free(requested_addr, size, true);
+ if (ret) {
+ if (ret > 0) {
+ RTE_LOG(ERR, EAL, "Cannot map memory "
+ "to a region not reserved\n");
+ rte_errno = EADDRNOTAVAIL;
+ }
+ return NULL;
+ }
+ }
+
+ virt = MapViewOfFileEx(mapping_handle, sys_access,
+ offset_high, offset_low, size, requested_addr);
+ if (!virt) {
+ RTE_LOG_WIN32_ERR("MapViewOfFileEx()");
+ return NULL;
+ }
+
+ if ((flags & RTE_MAP_FIXED) && (virt != requested_addr)) {
+ BOOL ret = UnmapViewOfFile(virt);
+ virt = NULL;
+ if (!ret)
+ RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
+ }
+
+ if (!CloseHandle(mapping_handle))
+ RTE_LOG_WIN32_ERR("CloseHandle()");
+
+ return virt;
+}
+
+int
+rte_mem_unmap(void *virt, size_t size)
+{
+ RTE_SET_USED(size);
+
+ if (!UnmapViewOfFile(virt)) {
+ rte_errno = GetLastError();
+ RTE_LOG_WIN32_ERR("UnmapViewOfFile()");
+ return -1;
+ }
+ return 0;
+}
+
+int
+rte_get_page_size(void)
+{
+ SYSTEM_INFO info;
+ GetSystemInfo(&info);
+ return info.dwPageSize;
+}
+
+int
+rte_mem_lock(const void *virt, size_t size)
+{
+ /* VirtualLock() takes `void*`, work around compiler warning. */
+ void *addr = (void *)((uintptr_t)virt);
+
+ if (!VirtualLock(addr, size)) {
+ RTE_LOG_WIN32_ERR("VirtualLock()");
+ return -1;
+ }
+
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index 390d2fd66..b202a1aa5 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -36,4 +36,71 @@ int eal_thread_create(pthread_t *thread);
*/
unsigned int eal_socket_numa_node(unsigned int socket_id);
+/**
+ * Locate Win32 memory management routines in system libraries.
+ *
+ * @return 0 on success, (-1) on failure.
+ */
+int eal_mem_win32api_init(void);
+
+/**
+ * Allocate a contiguous chunk of virtual memory.
+ *
+ * Use eal_mem_free() to free allocated memory.
+ *
+ * @param size
+ * Number of bytes to allocate.
+ * @param page_size
+ * If non-zero, means memory must be allocated in hugepages
+ * of the specified size. The @code size @endcode parameter
+ * must then be a multiple of the largest hugepage size requested.
+ * @return
+ * Address of allocated memory or NULL on failure (rte_errno is set).
+ */
+void *eal_mem_alloc(size_t size, enum rte_page_sizes page_size);
+
+/**
+ * Allocate new memory in hugepages on the specified NUMA node.
+ *
+ * @param size
+ * Number of bytes to allocate. Must be a multiple of huge page size.
+ * @param socket_id
+ * Socket ID.
+ * @return
+ * Address of the memory allocated on success or NULL on failure.
+ */
+void *eal_mem_alloc_socket(size_t size, int socket_id);
+
+/**
+ * Commit memory previously reserved with @ref eal_mem_reserve()
+ * or decommitted from hugepages by @ref eal_mem_decommit().
+ *
+ * @param requested_addr
+ * Address within a reserved region. Must not be NULL.
+ * @param size
+ * Number of bytes to commit. Must be a multiple of page size.
+ * @param socket_id
+ * Socket ID to allocate on. Can be SOCKET_ID_ANY.
+ * @return
+ * On success, address of the committed memory, that is, requested_addr.
+ * On failure, NULL and @code rte_errno @endcode is set.
+ */
+void *eal_mem_commit(void *requested_addr, size_t size, int socket_id);
+
+/**
+ * Put allocated or committed memory back into reserved state.
+ *
+ * @param addr
+ * Address of the region to decommit.
+ * @param size
+ * Number of bytes to decommit.
+ *
+ * The @code addr @endcode and @code param @endcode must match
+ * location and size of previously allocated or committed region.
+ *
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_mem_decommit(void *addr, size_t size);
+
#endif /* _EAL_WINDOWS_H_ */
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 5f118bfe2..81d3ee095 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -8,6 +8,7 @@ sources += files(
'eal_debug.c',
'eal_hugepages.c',
'eal_lcore.c',
+ 'eal_memory.c',
'eal_thread.c',
'getopt.c',
)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
@ 2020-04-15 22:17 ` Thomas Monjalon
2020-04-15 23:32 ` Dmitry Kozlyuk
2020-04-17 12:43 ` Burakov, Anatoly
` (3 subsequent siblings)
4 siblings, 1 reply; 218+ messages in thread
From: Thomas Monjalon @ 2020-04-15 22:17 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon, bruce.richardson, david.marchand
14/04/2020 21:44, Dmitry Kozlyuk:
> System meory management is implemented differently for POSIX and
meory -> memory
> Windows. Introduce wrapper functions for operations used across DPDK:
>
> * rte_mem_map()
> Create memory mapping for a regular file or a page file (swap).
> This supports mapping to a reserved memory region even on Windows.
>
> * rte_mem_unmap()
> Remove mapping created with rte_mem_map().
>
> * rte_get_page_size()
> Obtain default system page size.
>
> * rte_mem_lock()
> Make arbitrary-sized memory region non-swappable.
>
> Wrappers follow POSIX semantics limited to DPDK tasks, but their
> signatures deliberately differ from POSIX ones to be more safe and
> expressive.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
[...]
> +/**
> + * Memory reservation flags.
> + */
> +enum eal_mem_reserve_flags {
> + /**< Reserve hugepages (support may be limited or missing). */
> + EAL_RESERVE_HUGEPAGES = 1 << 0,
> + /**< Fail if requested address is not available. */
> + EAL_RESERVE_EXACT_ADDRESS = 1 << 1
> +};
Maybe more context is needed to understand the meaning of these flags.
[...]
> -eal_get_virtual_area(void *requested_addr, size_t *size,
> - size_t page_sz, int flags, int mmap_flags);
> +eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
> + int flags, int mmap_flags);
Is there any change here?
[...]
> + * If @code virt @endcode and @code size @endcode describe a part of the
I am not sure about using @code.
It makes reading from source harder.
Is there a real benefit?
[...]
> +/**
> + * Memory protection flags.
> + */
> +enum rte_mem_prot {
> + RTE_PROT_READ = 1 << 0, /**< Read access. */
> + RTE_PROT_WRITE = 1 << 1, /**< Write access. */
> + RTE_PROT_EXECUTE = 1 << 2 /**< Code execution. */
> +};
Alignment of comments would look better :-)
> +
> +/**
> + * Memory mapping additional flags.
> + *
> + * In Linux and FreeBSD, each flag is semantically equivalent
> + * to OS-specific mmap(3) flag with the same or similar name.
> + * In Windows, POSIX and MAP_ANONYMOUS semantics are followed.
> + */
I don't understand this comment.
The flags and meanings are the same no matter the OS, right?
> +enum rte_map_flags {
> + /** Changes of mapped memory are visible to other processes. */
> + RTE_MAP_SHARED = 1 << 0,
> + /** Mapping is not backed by a regular file. */
> + RTE_MAP_ANONYMOUS = 1 << 1,
> + /** Copy-on-write mapping, changes are invisible to other processes. */
> + RTE_MAP_PRIVATE = 1 << 2,
> + /** Fail if requested address cannot be taken. */
> + RTE_MAP_FIXED = 1 << 3
> +};
> +
> +/**
> + * OS-independent implementation of POSIX mmap(3)
> + * with MAP_ANONYMOUS Linux/FreeBSD extension.
> + */
> +__rte_experimental
> +void *rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
> + enum rte_map_flags flags, int fd, size_t offset);
> +
> +/**
> + * OS-independent implementation of POSIX munmap(3).
> + */
> +__rte_experimental
> +int rte_mem_unmap(void *virt, size_t size);
> +
> +/**
> + * Get system page size. This function never failes.
failes -> fails
> + *
> + * @return
> + * Positive page size in bytes.
> + */
> +__rte_experimental
> +int rte_get_page_size(void);
> +
> +/**
> + * Lock region in physical memory and prevent it from swapping.
> + *
> + * @param virt
> + * The virtual address.
> + * @param size
> + * Size of the region.
> + * @return
> + * 0 on success, negative on error.
> + *
> + * @note Implementations may require @p virt and @p size to be multiples
> + * of system page size.
> + * @see rte_get_page_size()
> + * @see rte_mem_lock_page()
> + */
> +__rte_experimental
> +int rte_mem_lock(const void *virt, size_t size);
[...]
> --- /dev/null
> +++ b/lib/librte_eal/unix/eal_memory.c
License and copyright missing.
> @@ -0,0 +1,113 @@
> +#include <string.h>
> +#include <sys/mman.h>
> +#include <unistd.h>
> +
> +#include <rte_errno.h>
> +#include <rte_log.h>
> +#include <rte_memory.h>
> +
> +#include "eal_private.h"
> +
> +static void *
> +mem_map(void *requested_addr, size_t size, int prot, int flags,
> + int fd, size_t offset)
> +{
> + void *virt = mmap(requested_addr, size, prot, flags, fd, offset);
> + if (virt == MAP_FAILED) {
> + RTE_LOG(ERR, EAL,
Not sure it should be a log level so high.
We could imagine checking a memory map.
What about INFO level?
The real error log will be made by the caller.
> + "Cannot mmap(%p, 0x%zx, 0x%x, 0x%x, %d, 0x%zx): %s\n",
> + requested_addr, size, prot, flags, fd, offset,
> + strerror(errno));
> + rte_errno = errno;
> + return NULL;
[...]
> +void *
> +eal_mem_reserve(void *requested_addr, size_t size,
> + enum eal_mem_reserve_flags flags)
> +{
> + int sys_flags = MAP_PRIVATE | MAP_ANONYMOUS;
> +
> +#ifdef MAP_HUGETLB
> + if (flags & EAL_RESERVE_HUGEPAGES)
> + sys_flags |= MAP_HUGETLB;
> +#endif
If MAP_HUGETLB is false, and flags contain EAL_RESERVE_HUGEPAGES,
I think an error should be returned.
> + if (flags & EAL_RESERVE_EXACT_ADDRESS)
> + sys_flags |= MAP_FIXED;
> +
> + return mem_map(requested_addr, size, PROT_NONE, sys_flags, -1, 0);
> +}
[...]
> +int
> +rte_get_page_size(void)
> +{
> + return getpagesize();
> +}
> +
> +int
> +rte_mem_lock(const void *virt, size_t size)
> +{
> + return mlock(virt, size);
> +}
Why don't you replace existing code with these new functions?
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-15 22:17 ` Thomas Monjalon
@ 2020-04-15 23:32 ` Dmitry Kozlyuk
0 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-15 23:32 UTC (permalink / raw)
To: Thomas Monjalon
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon, bruce.richardson, david.marchand
Answering the questions. All snipped comments will be fixed in v4.
> [...]
> > +/**
> > + * Memory reservation flags.
> > + */
> > +enum eal_mem_reserve_flags {
> > + /**< Reserve hugepages (support may be limited or missing). */
> > + EAL_RESERVE_HUGEPAGES = 1 << 0,
> > + /**< Fail if requested address is not available. */
> > + EAL_RESERVE_EXACT_ADDRESS = 1 << 1
> > +};
>
> Maybe more context is needed to understand the meaning of these flags.
Will extend the comment in v4. It's basically MAP_HUGE and MAP_FIXED.
> [...]
> > -eal_get_virtual_area(void *requested_addr, size_t *size,
> > - size_t page_sz, int flags, int mmap_flags);
> > +eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
> > + int flags, int mmap_flags);
>
> Is there any change here?
No, will fix this artifact.
> [...]
> > + * If @code virt @endcode and @code size @endcode describe a part of the
>
> I am not sure about using @code.
> It makes reading from source harder.
> Is there a real benefit?
It should be either @p or no markup (as in the rest of the comments), @code is
indeed inappropriate.
> > +
> > +/**
> > + * Memory mapping additional flags.
> > + *
> > + * In Linux and FreeBSD, each flag is semantically equivalent
> > + * to OS-specific mmap(3) flag with the same or similar name.
> > + * In Windows, POSIX and MAP_ANONYMOUS semantics are followed.
> > + */
>
> I don't understand this comment.
> The flags and meanings are the same no matter the OS, right?
Correct. MAP_ANONYMOUS is not POSIX so I mentioned it explicitly. I'll try to
come up with better wording.
> > +static void *
> > +mem_map(void *requested_addr, size_t size, int prot, int flags,
> > + int fd, size_t offset)
> > +{
> > + void *virt = mmap(requested_addr, size, prot, flags, fd, offset);
> > + if (virt == MAP_FAILED) {
> > + RTE_LOG(ERR, EAL,
>
> Not sure it should be a log level so high.
> We could imagine checking a memory map.
> What about INFO level?
> The real error log will be made by the caller.
>
> > + "Cannot mmap(%p, 0x%zx, 0x%x, 0x%x, %d, 0x%zx): %s\n",
> > + requested_addr, size, prot, flags, fd, offset,
> > + strerror(errno));
> > + rte_errno = errno;
> > + return NULL;
The same level is used now in places from which this code is extracted:
lib/librte_eal/common/{eal_common_fbarray.c:97,eal_common_memory:131}, see
also lib/librte_pci/rte_pci.c:144. To my understanding, DEBUG is used to log
implementation-specific details like these OS API calls, so I'll change
level to that.
> [...]
> > +int
> > +rte_get_page_size(void)
> > +{
> > + return getpagesize();
> > +}
> > +
> > +int
> > +rte_mem_lock(const void *virt, size_t size)
> > +{
> > + return mlock(virt, size);
> > +}
>
> Why don't you replace existing code with these new functions?
In this patchset I tried to touch existing code as little as possible, at
least I'd like to limit the scope to EAL. Libraries and drivers using Unix
functions directly will fail to compile when enabled on Windows, but patches
will be trivial. I propose replacing calls in EAL in v4.
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
2020-04-15 22:17 ` Thomas Monjalon
@ 2020-04-17 12:43 ` Burakov, Anatoly
2020-04-20 5:59 ` Tal Shnaiderman
` (2 subsequent siblings)
4 siblings, 0 replies; 218+ messages in thread
From: Burakov, Anatoly @ 2020-04-17 12:43 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon
On 14-Apr-20 8:44 PM, Dmitry Kozlyuk wrote:
> System meory management is implemented differently for POSIX and
> Windows. Introduce wrapper functions for operations used across DPDK:
>
> * rte_mem_map()
> Create memory mapping for a regular file or a page file (swap).
> This supports mapping to a reserved memory region even on Windows.
>
> * rte_mem_unmap()
> Remove mapping created with rte_mem_map().
>
> * rte_get_page_size()
> Obtain default system page size.
>
> * rte_mem_lock()
> Make arbitrary-sized memory region non-swappable.
>
> Wrappers follow POSIX semantics limited to DPDK tasks, but their
> signatures deliberately differ from POSIX ones to be more safe and
> expressive.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
<snip>
> +/**
> + * Memory reservation flags.
> + */
> +enum eal_mem_reserve_flags {
> + /**< Reserve hugepages (support may be limited or missing). */
> + EAL_RESERVE_HUGEPAGES = 1 << 0,
> + /**< Fail if requested address is not available. */
> + EAL_RESERVE_EXACT_ADDRESS = 1 << 1
I *really* don't like this terminology.
In Linux et al., MAP_FIXED is not just "reserve at this exact address".
MAP_FIXED is actually fairly dangerous if you don't know what you're
doing, because it will unconditionally unmap any previously mapped
memory. Also, to my knowledge, a call to MAP_FIXED cannot fail unless
something went very wrong - it will *not* "fail if requested address is
not available". We basically use MAP_FIXED because we have already
mapped that area with MAP_ANONYMOUS previously, so we can guarantee that
it's safe to call MAP_FIXED.
I would greatly prefer if this was named to better reflect the above.
EAL_FORCE_RESERVE perhaps? The comment also needs to be adjusted.
> +};
> +
> /**
> * Get virtual area of specified size from the OS.
> *
> @@ -232,8 +243,8 @@ int rte_eal_check_module(const char *module_name);
> #define EAL_VIRTUAL_AREA_UNMAP (1 << 2)
> /**< immediately unmap reserved virtual area. */
> void *
> -eal_get_virtual_area(void *requested_addr, size_t *size,
> - size_t page_sz, int flags, int mmap_flags);
> +eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
> + int flags, int mmap_flags);
>
> /**
<snip>
>
> +/**
> + * Reserve a region of virtual memory.
> + *
> + * Use eal_mem_free() to free reserved memory.
> + *
> + * @param requested_addr
> + * A desired reservation address. The system may not respect it.
> + * NULL means the address will be chosen by the system.
> + * @param size
> + * Reservation size. Must be a multiple of system page size.
> + * @param flags
> + * Reservation options.
> + * @returns
> + * Starting address of the reserved area on success, NULL on failure.
> + * Callers must not access this memory until remapping it.
> + */
> +void *eal_mem_reserve(void *requested_addr, size_t size,
> + enum eal_mem_reserve_flags flags);
This seems fairly suspect to me. I know that technically enum is an int,
but semantically, IIRC an enum value should always contain exactly one
value - you can't use an enum value like a set of flags.
> +
> +/**
> + * Free memory obtained by eal_mem_reserve() or eal_mem_alloc().
> + *
> + * If @code virt @endcode and @code size @endcode describe a part of the
> + * reserved region, only this part of the region is freed (accurately
> + * up to the system page size). If @code virt @endcode points to allocated
> + * memory, @code size @endcode must match the one specified on allocation.
> + * The behavior is undefined if the memory pointed by @code virt @endcode
> + * is obtained from another source than listed above.
> + *
> + * @param virt
<snip>
> +/**
> + * Memory mapping additional flags.
> + *
> + * In Linux and FreeBSD, each flag is semantically equivalent
> + * to OS-specific mmap(3) flag with the same or similar name.
> + * In Windows, POSIX and MAP_ANONYMOUS semantics are followed.
> + */
> +enum rte_map_flags {
> + /** Changes of mapped memory are visible to other processes. */
> + RTE_MAP_SHARED = 1 << 0,
> + /** Mapping is not backed by a regular file. */
> + RTE_MAP_ANONYMOUS = 1 << 1,
> + /** Copy-on-write mapping, changes are invisible to other processes. */
> + RTE_MAP_PRIVATE = 1 << 2,
> + /** Fail if requested address cannot be taken. */
> + RTE_MAP_FIXED = 1 << 3
Again, MAP_FIXED does not behave the way you describe. See above comments.
> +};
> +
> +/**
> + * OS-independent implementation of POSIX mmap(3)
> + * with MAP_ANONYMOUS Linux/FreeBSD extension.
> + */
> +__rte_experimental
> +void *rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
> + enum rte_map_flags flags, int fd, size_t offset);
> +
> +/**
> + * OS-independent implementation of POSIX munmap(3).
> + */
> +__rte_experimental
> +int rte_mem_unmap(void *virt, size_t size);
> +
> +/**
> + * Get system page size. This function never failes.
> + *
> + * @return
> + * Positive page size in bytes.
> + */
> +__rte_experimental
> +int rte_get_page_size(void);
uint32_t? or maybe uint64_t?
> +
> +/**
> + * Lock region in physical memory and prevent it from swapping.
> + *
> + * @param virt
> + * The virtual address.
> + * @param size
> + * Size of the region.
> + * @return
> + * 0 on success, negative on error.
> + *
> + * @note Implementations may require @p virt and @p size to be multiples
> + * of system page size.
> + * @see rte_get_page_size()
> + * @see rte_mem_lock_page()
> + */
> +__rte_experimental
> +int rte_mem_lock(const void *virt, size_t size);
> +
> /**
--
Thanks,
Anatoly
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
2020-04-15 22:17 ` Thomas Monjalon
2020-04-17 12:43 ` Burakov, Anatoly
@ 2020-04-20 5:59 ` Tal Shnaiderman
2020-04-21 23:36 ` Dmitry Kozlyuk
2020-04-22 0:55 ` Ranjit Menon
2020-04-22 2:07 ` Ranjit Menon
4 siblings, 1 reply; 218+ messages in thread
From: Tal Shnaiderman @ 2020-04-20 5:59 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Thomas Monjalon,
Anatoly Burakov, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon
> System meory management is implemented differently for POSIX and
> Windows. Introduce wrapper functions for operations used across DPDK:
>
> * rte_mem_map()
> Create memory mapping for a regular file or a page file (swap).
> This supports mapping to a reserved memory region even on Windows.
>
> * rte_mem_unmap()
> Remove mapping created with rte_mem_map().
>
> * rte_get_page_size()
> Obtain default system page size.
>
> * rte_mem_lock()
> Make arbitrary-sized memory region non-swappable.
>
> Wrappers follow POSIX semantics limited to DPDK tasks, but their signatures
> deliberately differ from POSIX ones to be more safe and expressive.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> config/meson.build | 10 +-
> lib/librte_eal/common/eal_private.h | 51 +++-
> lib/librte_eal/include/rte_memory.h | 68 +++++
> lib/librte_eal/rte_eal_exports.def | 4 +
> lib/librte_eal/rte_eal_version.map | 4 +
> lib/librte_eal/unix/eal_memory.c | 113 +++++++
> lib/librte_eal/unix/meson.build | 1 +
> lib/librte_eal/windows/eal.c | 6 +
> lib/librte_eal/windows/eal_memory.c | 437
> +++++++++++++++++++++++++++ lib/librte_eal/windows/eal_windows.h |
<Snip!>
> +eal_mem_win32api_init(void)
> +{
> + static const char library_name[] = "kernelbase.dll";
> + static const char function[] = "VirtualAlloc2";
> +
> + OSVERSIONINFO info;
> + HMODULE library = NULL;
> + int ret = 0;
> +
> + /* Already done. */
> + if (VirtualAlloc2 != NULL)
> + return 0;
> +
> + /* IsWindows10OrGreater() may also be unavailable. */
> + memset(&info, 0, sizeof(info));
> + info.dwOSVersionInfoSize = sizeof(info);
> + GetVersionEx(&info);
I'd remove the GetVersionEx check entirely and add the comments regarding OS dependency to the RTE_LOG
Of the LoadLibraryA failure below, GetVersionEx returns the Windows 8 OS version on newer servers
Also, it looks like not all Win2016 servers versions support VirtualAlloc2, I'm using Microsoft Windows Server 2016 Datacenter Version 10.0.14393 and LoadLibraryA failed to load VirtualAlloc2.
> + /* Checking for Windows 10+ will also detect Windows Server 2016+.
> + * Do not abort, because Windows may report false version
> depending
> + * on executable manifest, compatibility mode, etc.
> + */
> + if (info.dwMajorVersion < 10)
> + RTE_LOG(DEBUG, EAL, "Windows 10+ or Windows Server
> 2016+ "
> + "is required for advanced memory features\n");
> +
> + library = LoadLibraryA(library_name);
> + if (library == NULL) {
> + RTE_LOG_WIN32_ERR("LoadLibraryA(\"%s\")",
> library_name);
> + return -1;
> + }
> +
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-20 5:59 ` Tal Shnaiderman
@ 2020-04-21 23:36 ` Dmitry Kozlyuk
0 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-21 23:36 UTC (permalink / raw)
To: Tal Shnaiderman
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Thomas Monjalon,
Anatoly Burakov, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon
> I'd remove the GetVersionEx check entirely and add the comments regarding OS dependency to the RTE_LOG
> Of the LoadLibraryA failure below, GetVersionEx returns the Windows 8 OS version on newer servers
Agreed, will do in v4.
> Also, it looks like not all Win2016 servers versions support VirtualAlloc2, I'm using Microsoft Windows Server 2016 Datacenter Version 10.0.14393 and LoadLibraryA failed to load VirtualAlloc2.
I confirm this. Documentation states Windows Server 2016 is supported, but it
is at least partially incorrect, see comments in meson.build and GitHub issue:
https://github.com/MicrosoftDocs/feedback/issues/1129
How would you estimate Server 2016 support importance? Server 2019 and
Windows 10 are known to work.
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
` (2 preceding siblings ...)
2020-04-20 5:59 ` Tal Shnaiderman
@ 2020-04-22 0:55 ` Ranjit Menon
2020-04-22 2:07 ` Ranjit Menon
4 siblings, 0 replies; 218+ messages in thread
From: Ranjit Menon @ 2020-04-22 0:55 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Burakov, Anatoly, Harini Ramakrishnan,
Omar Cardona, Kadam, Pallavi
On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> System meory management is implemented differently for POSIX and
> Windows. Introduce wrapper functions for operations used across DPDK:
>
> * rte_mem_map()
> Create memory mapping for a regular file or a page file (swap).
> This supports mapping to a reserved memory region even on Windows.
>
> * rte_mem_unmap()
> Remove mapping created with rte_mem_map().
>
> * rte_get_page_size()
> Obtain default system page size.
>
> * rte_mem_lock()
> Make arbitrary-sized memory region non-swappable.
>
> Wrappers follow POSIX semantics limited to DPDK tasks, but their
> signatures deliberately differ from POSIX ones to be more safe and
> expressive.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
<Snip!>
> diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
> new file mode 100644
> index 000000000..5697187ce
> --- /dev/null
> +++ b/lib/librte_eal/windows/eal_memory.c
> @@ -0,0 +1,437 @@
> +#include <io.h>
> +
> +#include <rte_errno.h>
> +#include <rte_memory.h>
> +
> +#include "eal_private.h"
> +#include "eal_windows.h"
> +
> +/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
> + * Provide a copy of definitions and code to load it dynamically.
> + * Note: definitions are copied verbatim from Microsoft documentation
> + * and don't follow DPDK code style.
> + */
> +#ifndef MEM_PRESERVE_PLACEHOLDER
> +
> +/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ne-winnt-mem_extended_parameter_type */
> +typedef enum MEM_EXTENDED_PARAMETER_TYPE {
> + MemExtendedParameterInvalidType,
> + MemExtendedParameterAddressRequirements,
> + MemExtendedParameterNumaNode,
> + MemExtendedParameterPartitionHandle,
> + MemExtendedParameterMax,
> + MemExtendedParameterUserPhysicalHandle,
> + MemExtendedParameterAttributeFlags
> +} *PMEM_EXTENDED_PARAMETER_TYPE;
> +
> +#define MEM_EXTENDED_PARAMETER_TYPE_BITS 4
> +
> +/* https://docs.microsoft.com/en-us/windows/win32/api/winnt/ns-winnt-mem_extended_parameter */
> +typedef struct MEM_EXTENDED_PARAMETER {
> + struct {
> + DWORD64 Type : MEM_EXTENDED_PARAMETER_TYPE_BITS;
> + DWORD64 Reserved : 64 - MEM_EXTENDED_PARAMETER_TYPE_BITS;
> + } DUMMYSTRUCTNAME;
> + union {
> + DWORD64 ULong64;
> + PVOID Pointer;
> + SIZE_T Size;
> + HANDLE Handle;
> + DWORD ULong;
> + } DUMMYUNIONNAME;
> +} MEM_EXTENDED_PARAMETER, *PMEM_EXTENDED_PARAMETER;
> +
> +/* https://docs.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-virtualalloc2 */
> +typedef PVOID (*VirtualAlloc2_type)(
> + HANDLE Process,
> + PVOID BaseAddress,
> + SIZE_T Size,
> + ULONG AllocationType,
> + ULONG PageProtection,
> + MEM_EXTENDED_PARAMETER *ExtendedParameters,
> + ULONG ParameterCount
> +);
> +
> +/* VirtualAlloc2() flags. */
> +#define MEM_COALESCE_PLACEHOLDERS 0x00000001
> +#define MEM_PRESERVE_PLACEHOLDER 0x00000002
> +#define MEM_REPLACE_PLACEHOLDER 0x00004000
> +#define MEM_RESERVE_PLACEHOLDER 0x00040000
> +
> +/* Named exactly as the function, so that user code does not depend
> + * on it being found at compile time or dynamically.
> + */
> +static VirtualAlloc2_type VirtualAlloc2;
> +
> +int
> +eal_mem_win32api_init(void)
> +{
> + static const char library_name[] = "kernelbase.dll";
> + static const char function[] = "VirtualAlloc2";
> +
> + OSVERSIONINFO info;
> + HMODULE library = NULL;
> + int ret = 0;
> +
> + /* Already done. */
> + if (VirtualAlloc2 != NULL)
> + return 0;
> +
> + /* IsWindows10OrGreater() may also be unavailable. */
> + memset(&info, 0, sizeof(info));
> + info.dwOSVersionInfoSize = sizeof(info);
> + GetVersionEx(&info);
> +
> + /* Checking for Windows 10+ will also detect Windows Server 2016+.
> + * Do not abort, because Windows may report false version depending
> + * on executable manifest, compatibility mode, etc.
> + */
> + if (info.dwMajorVersion < 10)
> + RTE_LOG(DEBUG, EAL, "Windows 10+ or Windows Server 2016+ "
> + "is required for advanced memory features\n");
> +
> + library = LoadLibraryA(library_name);
> + if (library == NULL) {
> + RTE_LOG_WIN32_ERR("LoadLibraryA(\"%s\")", library_name);
> + return -1;
> + }
> +
> + VirtualAlloc2 = (VirtualAlloc2_type)(
> + (void *)GetProcAddress(library, function));
> + if (VirtualAlloc2 == NULL) {
> + RTE_LOG_WIN32_ERR("GetProcAddress(\"%s\", \"%s\")\n",
> + library_name, function);
> + ret = -1;
> + }
> +
> + FreeLibrary(library);
> +
> + return ret;
> +}
> +
> +#else
> +
> +/* Stub in case VirtualAlloc2() is provided by the compiler. */
> +int
> +eal_mem_win32api_init(void)
> +{
> + return 0;
> +}
> +
> +#endif /* no VirtualAlloc2() */
Can you fix this comment to match the #ifndef definition above?
BTW...Why use MEM_PRESERVE_PLACEHOLDER (which is also defined within the
block?)
ranjit m.
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
` (3 preceding siblings ...)
2020-04-22 0:55 ` Ranjit Menon
@ 2020-04-22 2:07 ` Ranjit Menon
4 siblings, 0 replies; 218+ messages in thread
From: Ranjit Menon @ 2020-04-22 2:07 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Burakov, Anatoly, Harini Ramakrishnan,
Omar Cardona, Kadam, Pallavi
<Snip!>
On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
> new file mode 100644
> index 000000000..5697187ce
> --- /dev/null
> +++ b/lib/librte_eal/windows/eal_memory.c
> @@ -0,0 +1,437 @@
<Snip!>
> +
> + if ((flags & EAL_RESERVE_EXACT_ADDRESS) && (virt != requested_addr)) {
> + if (!VirtualFree(virt, 0, MEM_RELEASE))
Microsoft documentation suggests that we use VirtualFreeEx() to free
memory allocated by VirtualAlloc2(). VirtualFreeEx() would require the
handle to the current process that was passed into VirtualAlloc2()
There are 6 other such occurrences in this file.
ranjit m.
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (5 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 06/10] eal: introduce memory management wrappers Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-15 22:19 ` Thomas Monjalon
2020-04-17 13:04 ` Burakov, Anatoly
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows Dmitry Kozlyuk
` (3 subsequent siblings)
10 siblings, 2 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Anatoly Burakov, Bruce Richardson
All supported OS create memory segment lists (MSL) and reserve VA space
for them in a nearly identical way. Move common code into EAL private
functions to reduce duplication.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/common/eal_common_memory.c | 54 ++++++++++++++++++
lib/librte_eal/common/eal_private.h | 34 ++++++++++++
lib/librte_eal/freebsd/eal_memory.c | 54 +++---------------
lib/librte_eal/linux/eal_memory.c | 68 +++++------------------
4 files changed, 110 insertions(+), 100 deletions(-)
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index cc7d54e0c..d9764681a 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -25,6 +25,7 @@
#include "eal_private.h"
#include "eal_internal_cfg.h"
#include "eal_memcfg.h"
+#include "eal_options.h"
#include "malloc_heap.h"
/*
@@ -182,6 +183,59 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
return aligned_addr;
}
+int
+eal_reserve_memseg_list(struct rte_memseg_list *msl,
+ enum eal_mem_reserve_flags flags)
+{
+ uint64_t page_sz;
+ size_t mem_sz;
+ void *addr;
+
+ page_sz = msl->page_sz;
+ mem_sz = page_sz * msl->memseg_arr.len;
+
+ addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
+ if (addr == NULL) {
+ if (rte_errno == EADDRNOTAVAIL)
+ RTE_LOG(ERR, EAL, "Cannot reserve %llu bytes at [%p] - "
+ "please use '--" OPT_BASE_VIRTADDR "' option\n",
+ (unsigned long long)mem_sz, msl->base_va);
+ else
+ RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
+ return -1;
+ }
+ msl->base_va = addr;
+ msl->len = mem_sz;
+
+ return 0;
+}
+
+int
+eal_alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx, bool heap)
+{
+ char name[RTE_FBARRAY_NAME_LEN];
+
+ snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
+ type_msl_idx);
+ if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
+ sizeof(struct rte_memseg))) {
+ RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
+ rte_strerror(rte_errno));
+ return -1;
+ }
+
+ msl->page_sz = page_sz;
+ msl->socket_id = socket_id;
+ msl->base_va = NULL;
+ msl->heap = heap;
+
+ RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
+ (size_t)page_sz >> 10, socket_id);
+
+ return 0;
+}
+
static struct rte_memseg *
virt2memseg(const void *addr, const struct rte_memseg_list *msl)
{
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 1e89338f2..76938e379 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -246,6 +246,40 @@ void *
eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
int flags, int mmap_flags);
+/**
+ * Reserve VA space for a memory segment list.
+ *
+ * @param msl
+ * Memory segment list with page size defined.
+ * @param flags
+ * Extra memory reservation flags. Can be 0 if unnecessary.
+ * @return
+ * 0 on success, (-1) on failure and rte_errno is set.
+ */
+int
+eal_reserve_memseg_list(struct rte_memseg_list *msl,
+ enum eal_mem_reserve_flags flags);
+
+/**
+ * Initialize a memory segment list with its backing storage.
+ *
+ * @param msl
+ * Memory segment list to be filled.
+ * @param page_sz
+ * Size of segment pages in the MSL.
+ * @param n_segs
+ * Number of segments.
+ * @param socket_id
+ * Socket ID. Must not be SOCKET_ID_ANY.
+ * @param type_msl_idx
+ * Index of the MSL among other MSLs of the same socket and page size.
+ * @param heap
+ * Mark MSL as pointing to a heap.
+ */
+int
+eal_alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx, bool heap);
+
/**
* Get cpu core_id.
*
diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
index a97d8f0f0..5174f9cd0 100644
--- a/lib/librte_eal/freebsd/eal_memory.c
+++ b/lib/librte_eal/freebsd/eal_memory.c
@@ -336,61 +336,23 @@ get_mem_amount(uint64_t page_sz, uint64_t max_mem)
return RTE_ALIGN(area_sz, page_sz);
}
-#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
static int
-alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
int n_segs, int socket_id, int type_msl_idx)
{
- char name[RTE_FBARRAY_NAME_LEN];
-
- snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
- type_msl_idx);
- if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
- sizeof(struct rte_memseg))) {
- RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
- rte_strerror(rte_errno));
- return -1;
- }
-
- msl->page_sz = page_sz;
- msl->socket_id = socket_id;
- msl->base_va = NULL;
-
- RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
- (size_t)page_sz >> 10, socket_id);
-
- return 0;
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, false);
}
static int
-alloc_va_space(struct rte_memseg_list *msl)
+memseg_list_reserve(struct rte_memseg_list *msl)
{
- uint64_t page_sz;
- size_t mem_sz;
- void *addr;
- int flags = 0;
+ enum eal_reserve_flags flags = 0;
#ifdef RTE_ARCH_PPC_64
- flags |= MAP_HUGETLB;
+ flags |= EAL_RESERVE_HUGEPAGES;
#endif
-
- page_sz = msl->page_sz;
- mem_sz = page_sz * msl->memseg_arr.len;
-
- addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
- if (addr == NULL) {
- if (rte_errno == EADDRNOTAVAIL)
- RTE_LOG(ERR, EAL, "Could not mmap %llu bytes at [%p] - "
- "please use '--" OPT_BASE_VIRTADDR "' option\n",
- (unsigned long long)mem_sz, msl->base_va);
- else
- RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
- return -1;
- }
- msl->base_va = addr;
- msl->len = mem_sz;
-
- return 0;
+ return eal_reserve_memseg_list(msl, flags);
}
@@ -479,7 +441,7 @@ memseg_primary_init(void)
cur_max_mem);
n_segs = cur_mem / hugepage_sz;
- if (alloc_memseg_list(msl, hugepage_sz, n_segs,
+ if (memseg_list_alloc(msl, hugepage_sz, n_segs,
0, type_msl_idx))
return -1;
diff --git a/lib/librte_eal/linux/eal_memory.c b/lib/librte_eal/linux/eal_memory.c
index 7a9c97ff8..a01a7ce76 100644
--- a/lib/librte_eal/linux/eal_memory.c
+++ b/lib/librte_eal/linux/eal_memory.c
@@ -802,7 +802,7 @@ get_mem_amount(uint64_t page_sz, uint64_t max_mem)
}
static int
-free_memseg_list(struct rte_memseg_list *msl)
+memseg_list_free(struct rte_memseg_list *msl)
{
if (rte_fbarray_destroy(&msl->memseg_arr)) {
RTE_LOG(ERR, EAL, "Cannot destroy memseg list\n");
@@ -812,58 +812,18 @@ free_memseg_list(struct rte_memseg_list *msl)
return 0;
}
-#define MEMSEG_LIST_FMT "memseg-%" PRIu64 "k-%i-%i"
static int
-alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
int n_segs, int socket_id, int type_msl_idx)
{
- char name[RTE_FBARRAY_NAME_LEN];
-
- snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
- type_msl_idx);
- if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
- sizeof(struct rte_memseg))) {
- RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
- rte_strerror(rte_errno));
- return -1;
- }
-
- msl->page_sz = page_sz;
- msl->socket_id = socket_id;
- msl->base_va = NULL;
- msl->heap = 1; /* mark it as a heap segment */
-
- RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
- (size_t)page_sz >> 10, socket_id);
-
- return 0;
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, true);
}
static int
-alloc_va_space(struct rte_memseg_list *msl)
+memseg_list_reserve(struct rte_memseg_list *msl)
{
- uint64_t page_sz;
- size_t mem_sz;
- void *addr;
- int flags = 0;
-
- page_sz = msl->page_sz;
- mem_sz = page_sz * msl->memseg_arr.len;
-
- addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
- if (addr == NULL) {
- if (rte_errno == EADDRNOTAVAIL)
- RTE_LOG(ERR, EAL, "Could not mmap %llu bytes at [%p] - "
- "please use '--" OPT_BASE_VIRTADDR "' option\n",
- (unsigned long long)mem_sz, msl->base_va);
- else
- RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
- return -1;
- }
- msl->base_va = addr;
- msl->len = mem_sz;
-
- return 0;
+ return eal_reserve_memseg_list(msl, 0);
}
/*
@@ -1009,12 +969,12 @@ prealloc_segments(struct hugepage_file *hugepages, int n_pages)
}
/* now, allocate fbarray itself */
- if (alloc_memseg_list(msl, page_sz, n_segs, socket,
+ if (memseg_list_alloc(msl, page_sz, n_segs, socket,
msl_idx) < 0)
return -1;
/* finally, allocate VA space */
- if (alloc_va_space(msl) < 0)
+ if (memseg_list_reserve(msl) < 0)
return -1;
}
}
@@ -2191,7 +2151,7 @@ memseg_primary_init_32(void)
max_pagesz_mem);
n_segs = cur_mem / hugepage_sz;
- if (alloc_memseg_list(msl, hugepage_sz, n_segs,
+ if (memseg_list_alloc(msl, hugepage_sz, n_segs,
socket_id, type_msl_idx)) {
/* failing to allocate a memseg list is
* a serious error.
@@ -2200,13 +2160,13 @@ memseg_primary_init_32(void)
return -1;
}
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
/* if we couldn't allocate VA space, we
* can try with smaller page sizes.
*/
RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list, retrying with different page size\n");
/* deallocate memseg list */
- if (free_memseg_list(msl))
+ if (memseg_list_free(msl))
return -1;
break;
}
@@ -2395,11 +2355,11 @@ memseg_primary_init(void)
}
msl = &mcfg->memsegs[msl_idx++];
- if (alloc_memseg_list(msl, pagesz, n_segs,
+ if (memseg_list_alloc(msl, pagesz, n_segs,
socket_id, cur_seglist))
goto out;
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
goto out;
}
@@ -2433,7 +2393,7 @@ memseg_secondary_init(void)
}
/* preallocate VA space */
- if (alloc_va_space(msl)) {
+ if (memseg_list_reserve(msl)) {
RTE_LOG(ERR, EAL, "Cannot preallocate VA space for hugepage memory\n");
return -1;
}
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
@ 2020-04-15 22:19 ` Thomas Monjalon
2020-04-17 13:04 ` Burakov, Anatoly
1 sibling, 0 replies; 218+ messages in thread
From: Thomas Monjalon @ 2020-04-15 22:19 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Bruce Richardson
14/04/2020 21:44, Dmitry Kozlyuk:
> All supported OS create memory segment lists (MSL) and reserve VA space
> for them in a nearly identical way. Move common code into EAL private
> functions to reduce duplication.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> lib/librte_eal/common/eal_common_memory.c | 54 ++++++++++++++++++
> lib/librte_eal/common/eal_private.h | 34 ++++++++++++
> lib/librte_eal/freebsd/eal_memory.c | 54 +++---------------
> lib/librte_eal/linux/eal_memory.c | 68 +++++------------------
> 4 files changed, 110 insertions(+), 100 deletions(-)
Didn't review this change, but thanks for doing such cleanup.
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
2020-04-15 22:19 ` Thomas Monjalon
@ 2020-04-17 13:04 ` Burakov, Anatoly
1 sibling, 0 replies; 218+ messages in thread
From: Burakov, Anatoly @ 2020-04-17 13:04 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Bruce Richardson
On 14-Apr-20 8:44 PM, Dmitry Kozlyuk wrote:
> All supported OS create memory segment lists (MSL) and reserve VA space
> for them in a nearly identical way. Move common code into EAL private
> functions to reduce duplication.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> lib/librte_eal/common/eal_common_memory.c | 54 ++++++++++++++++++
> lib/librte_eal/common/eal_private.h | 34 ++++++++++++
> lib/librte_eal/freebsd/eal_memory.c | 54 +++---------------
> lib/librte_eal/linux/eal_memory.c | 68 +++++------------------
> 4 files changed, 110 insertions(+), 100 deletions(-)
>
> diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
> index cc7d54e0c..d9764681a 100644
> --- a/lib/librte_eal/common/eal_common_memory.c
> +++ b/lib/librte_eal/common/eal_common_memory.c
> @@ -25,6 +25,7 @@
> #include "eal_private.h"
> #include "eal_internal_cfg.h"
> #include "eal_memcfg.h"
> +#include "eal_options.h"
> #include "malloc_heap.h"
>
> /*
> @@ -182,6 +183,59 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
> return aligned_addr;
> }
>
> +int
> +eal_reserve_memseg_list(struct rte_memseg_list *msl,
> + enum eal_mem_reserve_flags flags)
This and other similar places in this and other patches: i don't think
using enums for this purpose (i.e. to hold multiple values at once) is
good practice. I would suggest replacing with int.
Also, i don't think "eal_reserve_memseg_list" is a particularly good or
descriptive name (and neither is "eal_alloc_memseg_list" for that
matter). Suggestion: "eal_memseg_list_create" (or "_init") and
"eal_memseg_list_alloc"?
> +{
> + uint64_t page_sz;
> + size_t mem_sz;
> + void *addr;
> +
> + page_sz = msl->page_sz;
> + mem_sz = page_sz * msl->memseg_arr.len;
> +
> + addr = eal_get_virtual_area(msl->base_va, &mem_sz, page_sz, 0, flags);
> + if (addr == NULL) {
> + if (rte_errno == EADDRNOTAVAIL)
> + RTE_LOG(ERR, EAL, "Cannot reserve %llu bytes at [%p] - "
> + "please use '--" OPT_BASE_VIRTADDR "' option\n",
> + (unsigned long long)mem_sz, msl->base_va);
> + else
> + RTE_LOG(ERR, EAL, "Cannot reserve memory\n");
> + return -1;
> + }
> + msl->base_va = addr;
> + msl->len = mem_sz;
> +
> + return 0;
> +}
> +
> +int
> +eal_alloc_memseg_list(struct rte_memseg_list *msl, uint64_t page_sz,
> + int n_segs, int socket_id, int type_msl_idx, bool heap)
> +{
> + char name[RTE_FBARRAY_NAME_LEN];
> +
> + snprintf(name, sizeof(name), MEMSEG_LIST_FMT, page_sz >> 10, socket_id,
> + type_msl_idx);
> + if (rte_fbarray_init(&msl->memseg_arr, name, n_segs,
> + sizeof(struct rte_memseg))) {
> + RTE_LOG(ERR, EAL, "Cannot allocate memseg list: %s\n",
> + rte_strerror(rte_errno));
> + return -1;
> + }
> +
> + msl->page_sz = page_sz;
> + msl->socket_id = socket_id;
> + msl->base_va = NULL;
It probably needs to be documented that eal_alloc_memseg_list must be
called before eal_reserve_memseg_list.
> + msl->heap = heap;
> +
> + RTE_LOG(DEBUG, EAL, "Memseg list allocated: 0x%zxkB at socket %i\n",
> + (size_t)page_sz >> 10, socket_id);
> +
> + return 0;
> +}
> +
> static struct rte_memseg *
> virt2memseg(const void *addr, const struct rte_memseg_list *msl)
> {
--
Thanks,
Anatoly
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (6 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 07/10] eal: extract common code for memseg list initialization Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-15 9:34 ` Jerin Jacob
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD Dmitry Kozlyuk
` (2 subsequent siblings)
10 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Anatoly Burakov
Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
Enum rte_page_size has members valued above this limit, which get
wrapped to zero, resulting in compilation error (duplicate values in
enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
Define these values outside of the enum for Clang on Windows only.
This does not affect runtime, because Windows doesn't run on machines
with 4GiB and 16GiB hugepages.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/include/rte_memory.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 1b7c3e5df..3ec673f51 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -34,8 +34,14 @@ enum rte_page_sizes {
RTE_PGSIZE_256M = 1ULL << 28,
RTE_PGSIZE_512M = 1ULL << 29,
RTE_PGSIZE_1G = 1ULL << 30,
+/* Work around Clang on Windows being limited to 32-bit underlying type. */
+#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
RTE_PGSIZE_4G = 1ULL << 32,
RTE_PGSIZE_16G = 1ULL << 34,
+#else
+#define RTE_PGSIZE_4G (1ULL << 32)
+#define RTE_PGSIZE_16G (1ULL << 34)
+#endif
};
#define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows Dmitry Kozlyuk
@ 2020-04-15 9:34 ` Jerin Jacob
2020-04-15 10:32 ` Dmitry Kozlyuk
0 siblings, 1 reply; 218+ messages in thread
From: Jerin Jacob @ 2020-04-15 9:34 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov
On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>
> Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
> Enum rte_page_size has members valued above this limit, which get
> wrapped to zero, resulting in compilation error (duplicate values in
> enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
>
> Define these values outside of the enum for Clang on Windows only.
> This does not affect runtime, because Windows doesn't run on machines
> with 4GiB and 16GiB hugepages.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> lib/librte_eal/include/rte_memory.h | 6 ++++++
> 1 file changed, 6 insertions(+)
>
> diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
> index 1b7c3e5df..3ec673f51 100644
> --- a/lib/librte_eal/include/rte_memory.h
> +++ b/lib/librte_eal/include/rte_memory.h
> @@ -34,8 +34,14 @@ enum rte_page_sizes {
> RTE_PGSIZE_256M = 1ULL << 28,
> RTE_PGSIZE_512M = 1ULL << 29,
> RTE_PGSIZE_1G = 1ULL << 30,
> +/* Work around Clang on Windows being limited to 32-bit underlying type. */
It does look like "enum rte_page_sizes" NOT used as enum anywhere.
[master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
Why not remove this workaround and define all items as #define to
avoid below ifdef clutter.
> +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
See above.
> RTE_PGSIZE_4G = 1ULL << 32,
> RTE_PGSIZE_16G = 1ULL << 34,
> +#else
> +#define RTE_PGSIZE_4G (1ULL << 32)
> +#define RTE_PGSIZE_16G (1ULL << 34)
> +#endif
> };
>
> #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
> --
> 2.25.1
>
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-15 9:34 ` Jerin Jacob
@ 2020-04-15 10:32 ` Dmitry Kozlyuk
2020-04-15 10:57 ` Jerin Jacob
0 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-15 10:32 UTC (permalink / raw)
To: Jerin Jacob
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov
> On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> >
> > Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
> > Enum rte_page_size has members valued above this limit, which get
> > wrapped to zero, resulting in compilation error (duplicate values in
> > enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
> >
> > Define these values outside of the enum for Clang on Windows only.
> > This does not affect runtime, because Windows doesn't run on machines
> > with 4GiB and 16GiB hugepages.
> >
> > Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> > ---
> > lib/librte_eal/include/rte_memory.h | 6 ++++++
> > 1 file changed, 6 insertions(+)
> >
> > diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
> > index 1b7c3e5df..3ec673f51 100644
> > --- a/lib/librte_eal/include/rte_memory.h
> > +++ b/lib/librte_eal/include/rte_memory.h
> > @@ -34,8 +34,14 @@ enum rte_page_sizes {
> > RTE_PGSIZE_256M = 1ULL << 28,
> > RTE_PGSIZE_512M = 1ULL << 29,
> > RTE_PGSIZE_1G = 1ULL << 30,
> > +/* Work around Clang on Windows being limited to 32-bit underlying type. */
>
> It does look like "enum rte_page_sizes" NOT used as enum anywhere.
>
> [master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
> lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
>
> Why not remove this workaround and define all items as #define to
> avoid below ifdef clutter.
>
> > +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
>
> See above.
>
> > RTE_PGSIZE_4G = 1ULL << 32,
> > RTE_PGSIZE_16G = 1ULL << 34,
> > +#else
> > +#define RTE_PGSIZE_4G (1ULL << 32)
> > +#define RTE_PGSIZE_16G (1ULL << 34)
> > +#endif
> > };
> >
> > #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
> > --
> > 2.25.1
> >
This is a public header and removing enum rte_page_sizes will break API.
Moving members out of enum while keeping enum itself might break compilation
because of integer constants being converted to enum (with -Werror).
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-15 10:32 ` Dmitry Kozlyuk
@ 2020-04-15 10:57 ` Jerin Jacob
2020-04-15 11:09 ` Dmitry Kozlyuk
0 siblings, 1 reply; 218+ messages in thread
From: Jerin Jacob @ 2020-04-15 10:57 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Ray Kinsella
On Wed, Apr 15, 2020 at 4:02 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>
> > On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> > >
> > > Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
> > > Enum rte_page_size has members valued above this limit, which get
> > > wrapped to zero, resulting in compilation error (duplicate values in
> > > enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
> > >
> > > Define these values outside of the enum for Clang on Windows only.
> > > This does not affect runtime, because Windows doesn't run on machines
> > > with 4GiB and 16GiB hugepages.
> > >
> > > Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> > > ---
> > > lib/librte_eal/include/rte_memory.h | 6 ++++++
> > > 1 file changed, 6 insertions(+)
> > >
> > > diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
> > > index 1b7c3e5df..3ec673f51 100644
> > > --- a/lib/librte_eal/include/rte_memory.h
> > > +++ b/lib/librte_eal/include/rte_memory.h
> > > @@ -34,8 +34,14 @@ enum rte_page_sizes {
> > > RTE_PGSIZE_256M = 1ULL << 28,
> > > RTE_PGSIZE_512M = 1ULL << 29,
> > > RTE_PGSIZE_1G = 1ULL << 30,
> > > +/* Work around Clang on Windows being limited to 32-bit underlying type. */
> >
> > It does look like "enum rte_page_sizes" NOT used as enum anywhere.
> >
> > [master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
> > lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
> >
> > Why not remove this workaround and define all items as #define to
> > avoid below ifdef clutter.
> >
> > > +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
> >
> > See above.
> >
> > > RTE_PGSIZE_4G = 1ULL << 32,
> > > RTE_PGSIZE_16G = 1ULL << 34,
> > > +#else
> > > +#define RTE_PGSIZE_4G (1ULL << 32)
> > > +#define RTE_PGSIZE_16G (1ULL << 34)
> > > +#endif
> > > };
> > >
> > > #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
> > > --
> > > 2.25.1
> > >
>
> This is a public header and removing enum rte_page_sizes will break API.
> Moving members out of enum while keeping enum itself might break compilation
> because of integer constants being converted to enum (with -Werror).
If none of the public API is using this enum then I think, we may not
need to make this enum as public.
Since it has ULL, I believe both cases(enum or define), it will be
treated as unsigned long long. ie. NO ABI breakage.
>
> --
> Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-15 10:57 ` Jerin Jacob
@ 2020-04-15 11:09 ` Dmitry Kozlyuk
2020-04-15 11:17 ` Jerin Jacob
0 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-15 11:09 UTC (permalink / raw)
To: Jerin Jacob
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Ray Kinsella
> On Wed, Apr 15, 2020 at 4:02 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> >
> > > On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> > > >
> > > > Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
> > > > Enum rte_page_size has members valued above this limit, which get
> > > > wrapped to zero, resulting in compilation error (duplicate values in
> > > > enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
> > > >
> > > > Define these values outside of the enum for Clang on Windows only.
> > > > This does not affect runtime, because Windows doesn't run on machines
> > > > with 4GiB and 16GiB hugepages.
> > > >
> > > > Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> > > > ---
> > > > lib/librte_eal/include/rte_memory.h | 6 ++++++
> > > > 1 file changed, 6 insertions(+)
> > > >
> > > > diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
> > > > index 1b7c3e5df..3ec673f51 100644
> > > > --- a/lib/librte_eal/include/rte_memory.h
> > > > +++ b/lib/librte_eal/include/rte_memory.h
> > > > @@ -34,8 +34,14 @@ enum rte_page_sizes {
> > > > RTE_PGSIZE_256M = 1ULL << 28,
> > > > RTE_PGSIZE_512M = 1ULL << 29,
> > > > RTE_PGSIZE_1G = 1ULL << 30,
> > > > +/* Work around Clang on Windows being limited to 32-bit underlying type. */
> > >
> > > It does look like "enum rte_page_sizes" NOT used as enum anywhere.
> > >
> > > [master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
> > > lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
> > >
> > > Why not remove this workaround and define all items as #define to
> > > avoid below ifdef clutter.
> > >
> > > > +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
> > >
> > > See above.
> > >
> > > > RTE_PGSIZE_4G = 1ULL << 32,
> > > > RTE_PGSIZE_16G = 1ULL << 34,
> > > > +#else
> > > > +#define RTE_PGSIZE_4G (1ULL << 32)
> > > > +#define RTE_PGSIZE_16G (1ULL << 34)
> > > > +#endif
> > > > };
> > > >
> > > > #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
> > > > --
> > > > 2.25.1
> > > >
> >
> > This is a public header and removing enum rte_page_sizes will break API.
> > Moving members out of enum while keeping enum itself might break compilation
> > because of integer constants being converted to enum (with -Werror).
>
> If none of the public API is using this enum then I think, we may not
> need to make this enum as public.
Agreed.
> Since it has ULL, I believe both cases(enum or define), it will be
> treated as unsigned long long. ie. NO ABI breakage.
I was talking about API only (compile-time compatibility). Getting rid of
#ifdef and workarounds sounds right, we'll just need a notice in release
notes.
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-15 11:09 ` Dmitry Kozlyuk
@ 2020-04-15 11:17 ` Jerin Jacob
2020-05-06 5:41 ` Ray Kinsella
0 siblings, 1 reply; 218+ messages in thread
From: Jerin Jacob @ 2020-04-15 11:17 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov, Ray Kinsella
On Wed, Apr 15, 2020 at 4:39 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>
>
>
> > On Wed, Apr 15, 2020 at 4:02 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> > >
> > > > On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
> > > > >
> > > > > Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
> > > > > Enum rte_page_size has members valued above this limit, which get
> > > > > wrapped to zero, resulting in compilation error (duplicate values in
> > > > > enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
> > > > >
> > > > > Define these values outside of the enum for Clang on Windows only.
> > > > > This does not affect runtime, because Windows doesn't run on machines
> > > > > with 4GiB and 16GiB hugepages.
> > > > >
> > > > > Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> > > > > ---
> > > > > lib/librte_eal/include/rte_memory.h | 6 ++++++
> > > > > 1 file changed, 6 insertions(+)
> > > > >
> > > > > diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
> > > > > index 1b7c3e5df..3ec673f51 100644
> > > > > --- a/lib/librte_eal/include/rte_memory.h
> > > > > +++ b/lib/librte_eal/include/rte_memory.h
> > > > > @@ -34,8 +34,14 @@ enum rte_page_sizes {
> > > > > RTE_PGSIZE_256M = 1ULL << 28,
> > > > > RTE_PGSIZE_512M = 1ULL << 29,
> > > > > RTE_PGSIZE_1G = 1ULL << 30,
> > > > > +/* Work around Clang on Windows being limited to 32-bit underlying type. */
> > > >
> > > > It does look like "enum rte_page_sizes" NOT used as enum anywhere.
> > > >
> > > > [master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
> > > > lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
> > > >
> > > > Why not remove this workaround and define all items as #define to
> > > > avoid below ifdef clutter.
> > > >
> > > > > +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
> > > >
> > > > See above.
> > > >
> > > > > RTE_PGSIZE_4G = 1ULL << 32,
> > > > > RTE_PGSIZE_16G = 1ULL << 34,
> > > > > +#else
> > > > > +#define RTE_PGSIZE_4G (1ULL << 32)
> > > > > +#define RTE_PGSIZE_16G (1ULL << 34)
> > > > > +#endif
> > > > > };
> > > > >
> > > > > #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
> > > > > --
> > > > > 2.25.1
> > > > >
> > >
> > > This is a public header and removing enum rte_page_sizes will break API.
> > > Moving members out of enum while keeping enum itself might break compilation
> > > because of integer constants being converted to enum (with -Werror).
> >
> > If none of the public API is using this enum then I think, we may not
> > need to make this enum as public.
>
> Agreed.
>
> > Since it has ULL, I believe both cases(enum or define), it will be
> > treated as unsigned long long. ie. NO ABI breakage.
>
> I was talking about API only (compile-time compatibility). Getting rid of
> #ifdef and workarounds sounds right, we'll just need a notice in release
> notes.
Good to check ./devtools/check-abi.sh for any ABI breakage.
>
> --
> Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows
2020-04-15 11:17 ` Jerin Jacob
@ 2020-05-06 5:41 ` Ray Kinsella
0 siblings, 0 replies; 218+ messages in thread
From: Ray Kinsella @ 2020-05-06 5:41 UTC (permalink / raw)
To: Jerin Jacob, Dmitry Kozlyuk
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Anatoly Burakov
On 15/04/2020 12:17, Jerin Jacob wrote:
> On Wed, Apr 15, 2020 at 4:39 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>>
>>
>>
>>> On Wed, Apr 15, 2020 at 4:02 PM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>>>>
>>>>> On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>>>>>>
>>>>>> Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
>>>>>> Enum rte_page_size has members valued above this limit, which get
>>>>>> wrapped to zero, resulting in compilation error (duplicate values in
>>>>>> enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
>>>>>>
>>>>>> Define these values outside of the enum for Clang on Windows only.
>>>>>> This does not affect runtime, because Windows doesn't run on machines
>>>>>> with 4GiB and 16GiB hugepages.
>>>>>>
>>>>>> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
>>>>>> ---
>>>>>> lib/librte_eal/include/rte_memory.h | 6 ++++++
>>>>>> 1 file changed, 6 insertions(+)
>>>>>>
>>>>>> diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
>>>>>> index 1b7c3e5df..3ec673f51 100644
>>>>>> --- a/lib/librte_eal/include/rte_memory.h
>>>>>> +++ b/lib/librte_eal/include/rte_memory.h
>>>>>> @@ -34,8 +34,14 @@ enum rte_page_sizes {
>>>>>> RTE_PGSIZE_256M = 1ULL << 28,
>>>>>> RTE_PGSIZE_512M = 1ULL << 29,
>>>>>> RTE_PGSIZE_1G = 1ULL << 30,
>>>>>> +/* Work around Clang on Windows being limited to 32-bit underlying type. */
>>>>>
>>>>> It does look like "enum rte_page_sizes" NOT used as enum anywhere.
>>>>>
>>>>> [master][dpdk.org] $ grep -ri "enum rte_page_sizes" lib/
>>>>> lib/librte_eal/include/rte_memory.h:enum rte_page_sizes {
>>>>>
>>>>> Why not remove this workaround and define all items as #define to
>>>>> avoid below ifdef clutter.
>>>>>
>>>>>> +#if !defined(RTE_CC_CLANG) || !defined(RTE_EXEC_ENV_WINDOWS)
>>>>>
>>>>> See above.
>>>>>
>>>>>> RTE_PGSIZE_4G = 1ULL << 32,
>>>>>> RTE_PGSIZE_16G = 1ULL << 34,
>>>>>> +#else
>>>>>> +#define RTE_PGSIZE_4G (1ULL << 32)
>>>>>> +#define RTE_PGSIZE_16G (1ULL << 34)
>>>>>> +#endif
>>>>>> };
>>>>>>
>>>>>> #define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
>>>>>> --
>>>>>> 2.25.1
>>>>>>
>>>>
>>>> This is a public header and removing enum rte_page_sizes will break API.
>>>> Moving members out of enum while keeping enum itself might break compilation
>>>> because of integer constants being converted to enum (with -Werror).
>>>
>>> If none of the public API is using this enum then I think, we may not
>>> need to make this enum as public.
>>
>> Agreed.
>>
>>> Since it has ULL, I believe both cases(enum or define), it will be
>>> treated as unsigned long long. ie. NO ABI breakage.
>>
>> I was talking about API only (compile-time compatibility). Getting rid of
>> #ifdef and workarounds sounds right, we'll just need a notice in release
>> notes.
>
> Good to check ./devtools/check-abi.sh for any ABI breakage.
or something like this to cover all the bases.
DPDK_ABI_REF_DIR=/build/dpdk/reference/ DPDK_ABI_REF_VERSION=v20.02 ./devtools/test-meson-builds.sh
>>
>> --
>> Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (7 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 08/10] eal/windows: fix rte_page_sizes with Clang on Windows Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
2020-04-14 23:37 ` [dpdk-dev] [PATCH v3 00/10] Windows " Kadam, Pallavi
10 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Harini Ramakrishnan, Omar Cardona, Pallavi Kadam,
Ranjit Menon
Limited version imported previously lacks at least SLIST macros.
Import a complete file from FreeBSD, since its license exception is
already approved by Technical Board.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/windows/include/sys/queue.h | 663 +++++++++++++++++++--
1 file changed, 601 insertions(+), 62 deletions(-)
diff --git a/lib/librte_eal/windows/include/sys/queue.h b/lib/librte_eal/windows/include/sys/queue.h
index a65949a78..9756bee6f 100644
--- a/lib/librte_eal/windows/include/sys/queue.h
+++ b/lib/librte_eal/windows/include/sys/queue.h
@@ -8,7 +8,36 @@
#define _SYS_QUEUE_H_
/*
- * This file defines tail queues.
+ * This file defines four types of data structures: singly-linked lists,
+ * singly-linked tail queues, lists and tail queues.
+ *
+ * A singly-linked list is headed by a single forward pointer. The elements
+ * are singly linked for minimum space and pointer manipulation overhead at
+ * the expense of O(n) removal for arbitrary elements. New elements can be
+ * added to the list after an existing element or at the head of the list.
+ * Elements being removed from the head of the list should use the explicit
+ * macro for this purpose for optimum efficiency. A singly-linked list may
+ * only be traversed in the forward direction. Singly-linked lists are ideal
+ * for applications with large datasets and few or no removals or for
+ * implementing a LIFO queue.
+ *
+ * A singly-linked tail queue is headed by a pair of pointers, one to the
+ * head of the list and the other to the tail of the list. The elements are
+ * singly linked for minimum space and pointer manipulation overhead at the
+ * expense of O(n) removal for arbitrary elements. New elements can be added
+ * to the list after an existing element, at the head of the list, or at the
+ * end of the list. Elements being removed from the head of the tail queue
+ * should use the explicit macro for this purpose for optimum efficiency.
+ * A singly-linked tail queue may only be traversed in the forward direction.
+ * Singly-linked tail queues are ideal for applications with large datasets
+ * and few or no removals or for implementing a FIFO queue.
+ *
+ * A list is headed by a single forward pointer (or an array of forward
+ * pointers for a hash table header). The elements are doubly linked
+ * so that an arbitrary element can be removed without a need to
+ * traverse the list. New elements can be added to the list before
+ * or after an existing element or at the head of the list. A list
+ * may be traversed in either direction.
*
* A tail queue is headed by a pair of pointers, one to the head of the
* list and the other to the tail of the list. The elements are doubly
@@ -17,65 +46,93 @@
* after an existing element, at the head of the list, or at the end of
* the list. A tail queue may be traversed in either direction.
*
+ * For details on the use of these macros, see the queue(3) manual page.
+ *
* Below is a summary of implemented functions where:
* + means the macro is available
* - means the macro is not available
* s means the macro is available but is slow (runs in O(n) time)
*
- * TAILQ
- * _HEAD +
- * _CLASS_HEAD +
- * _HEAD_INITIALIZER +
- * _ENTRY +
- * _CLASS_ENTRY +
- * _INIT +
- * _EMPTY +
- * _FIRST +
- * _NEXT +
- * _PREV +
- * _LAST +
- * _LAST_FAST +
- * _FOREACH +
- * _FOREACH_FROM +
- * _FOREACH_SAFE +
- * _FOREACH_FROM_SAFE +
- * _FOREACH_REVERSE +
- * _FOREACH_REVERSE_FROM +
- * _FOREACH_REVERSE_SAFE +
- * _FOREACH_REVERSE_FROM_SAFE +
- * _INSERT_HEAD +
- * _INSERT_BEFORE +
- * _INSERT_AFTER +
- * _INSERT_TAIL +
- * _CONCAT +
- * _REMOVE_AFTER -
- * _REMOVE_HEAD -
- * _REMOVE +
- * _SWAP +
+ * SLIST LIST STAILQ TAILQ
+ * _HEAD + + + +
+ * _CLASS_HEAD + + + +
+ * _HEAD_INITIALIZER + + + +
+ * _ENTRY + + + +
+ * _CLASS_ENTRY + + + +
+ * _INIT + + + +
+ * _EMPTY + + + +
+ * _FIRST + + + +
+ * _NEXT + + + +
+ * _PREV - + - +
+ * _LAST - - + +
+ * _LAST_FAST - - - +
+ * _FOREACH + + + +
+ * _FOREACH_FROM + + + +
+ * _FOREACH_SAFE + + + +
+ * _FOREACH_FROM_SAFE + + + +
+ * _FOREACH_REVERSE - - - +
+ * _FOREACH_REVERSE_FROM - - - +
+ * _FOREACH_REVERSE_SAFE - - - +
+ * _FOREACH_REVERSE_FROM_SAFE - - - +
+ * _INSERT_HEAD + + + +
+ * _INSERT_BEFORE - + - +
+ * _INSERT_AFTER + + + +
+ * _INSERT_TAIL - - + +
+ * _CONCAT s s + +
+ * _REMOVE_AFTER + - + -
+ * _REMOVE_HEAD + - + -
+ * _REMOVE s + s +
+ * _SWAP + + + +
*
*/
-
-#ifdef __cplusplus
-extern "C" {
+#ifdef QUEUE_MACRO_DEBUG
+#warn Use QUEUE_MACRO_DEBUG_TRACE and/or QUEUE_MACRO_DEBUG_TRASH
+#define QUEUE_MACRO_DEBUG_TRACE
+#define QUEUE_MACRO_DEBUG_TRASH
#endif
-/*
- * List definitions.
- */
-#define LIST_HEAD(name, type) \
-struct name { \
- struct type *lh_first; /* first element */ \
-}
+#ifdef QUEUE_MACRO_DEBUG_TRACE
+/* Store the last 2 places the queue element or head was altered */
+struct qm_trace {
+ unsigned long lastline;
+ unsigned long prevline;
+ const char *lastfile;
+ const char *prevfile;
+};
+
+#define TRACEBUF struct qm_trace trace;
+#define TRACEBUF_INITIALIZER { __LINE__, 0, __FILE__, NULL } ,
+
+#define QMD_TRACE_HEAD(head) do { \
+ (head)->trace.prevline = (head)->trace.lastline; \
+ (head)->trace.prevfile = (head)->trace.lastfile; \
+ (head)->trace.lastline = __LINE__; \
+ (head)->trace.lastfile = __FILE__; \
+} while (0)
+#define QMD_TRACE_ELEM(elem) do { \
+ (elem)->trace.prevline = (elem)->trace.lastline; \
+ (elem)->trace.prevfile = (elem)->trace.lastfile; \
+ (elem)->trace.lastline = __LINE__; \
+ (elem)->trace.lastfile = __FILE__; \
+} while (0)
+
+#else /* !QUEUE_MACRO_DEBUG_TRACE */
#define QMD_TRACE_ELEM(elem)
#define QMD_TRACE_HEAD(head)
#define TRACEBUF
#define TRACEBUF_INITIALIZER
+#endif /* QUEUE_MACRO_DEBUG_TRACE */
+#ifdef QUEUE_MACRO_DEBUG_TRASH
+#define QMD_SAVELINK(name, link) void **name = (void *)&(link)
+#define TRASHIT(x) do {(x) = (void *)-1;} while (0)
+#define QMD_IS_TRASHED(x) ((x) == (void *)(intptr_t)-1)
+#else /* !QUEUE_MACRO_DEBUG_TRASH */
+#define QMD_SAVELINK(name, link)
#define TRASHIT(x)
#define QMD_IS_TRASHED(x) 0
-
-#define QMD_SAVELINK(name, link)
+#endif /* QUEUE_MACRO_DEBUG_TRASH */
#ifdef __cplusplus
/*
@@ -86,6 +143,445 @@ struct name { \
#define QUEUE_TYPEOF(type) struct type
#endif
+/*
+ * Singly-linked List declarations.
+ */
+#define SLIST_HEAD(name, type) \
+struct name { \
+ struct type *slh_first; /* first element */ \
+}
+
+#define SLIST_CLASS_HEAD(name, type) \
+struct name { \
+ class type *slh_first; /* first element */ \
+}
+
+#define SLIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define SLIST_ENTRY(type) \
+struct { \
+ struct type *sle_next; /* next element */ \
+}
+
+#define SLIST_CLASS_ENTRY(type) \
+struct { \
+ class type *sle_next; /* next element */ \
+}
+
+/*
+ * Singly-linked List functions.
+ */
+#if (defined(_KERNEL) && defined(INVARIANTS))
+#define QMD_SLIST_CHECK_PREVPTR(prevp, elm) do { \
+ if (*(prevp) != (elm)) \
+ panic("Bad prevptr *(%p) == %p != %p", \
+ (prevp), *(prevp), (elm)); \
+} while (0)
+#else
+#define QMD_SLIST_CHECK_PREVPTR(prevp, elm)
+#endif
+
+#define SLIST_CONCAT(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *curelm = SLIST_FIRST(head1); \
+ if (curelm == NULL) { \
+ if ((SLIST_FIRST(head1) = SLIST_FIRST(head2)) != NULL) \
+ SLIST_INIT(head2); \
+ } else if (SLIST_FIRST(head2) != NULL) { \
+ while (SLIST_NEXT(curelm, field) != NULL) \
+ curelm = SLIST_NEXT(curelm, field); \
+ SLIST_NEXT(curelm, field) = SLIST_FIRST(head2); \
+ SLIST_INIT(head2); \
+ } \
+} while (0)
+
+#define SLIST_EMPTY(head) ((head)->slh_first == NULL)
+
+#define SLIST_FIRST(head) ((head)->slh_first)
+
+#define SLIST_FOREACH(var, head, field) \
+ for ((var) = SLIST_FIRST((head)); \
+ (var); \
+ (var) = SLIST_NEXT((var), field))
+
+#define SLIST_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : SLIST_FIRST((head))); \
+ (var); \
+ (var) = SLIST_NEXT((var), field))
+
+#define SLIST_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = SLIST_FIRST((head)); \
+ (var) && ((tvar) = SLIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define SLIST_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : SLIST_FIRST((head))); \
+ (var) && ((tvar) = SLIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define SLIST_FOREACH_PREVPTR(var, varp, head, field) \
+ for ((varp) = &SLIST_FIRST((head)); \
+ ((var) = *(varp)) != NULL; \
+ (varp) = &SLIST_NEXT((var), field))
+
+#define SLIST_INIT(head) do { \
+ SLIST_FIRST((head)) = NULL; \
+} while (0)
+
+#define SLIST_INSERT_AFTER(slistelm, elm, field) do { \
+ SLIST_NEXT((elm), field) = SLIST_NEXT((slistelm), field); \
+ SLIST_NEXT((slistelm), field) = (elm); \
+} while (0)
+
+#define SLIST_INSERT_HEAD(head, elm, field) do { \
+ SLIST_NEXT((elm), field) = SLIST_FIRST((head)); \
+ SLIST_FIRST((head)) = (elm); \
+} while (0)
+
+#define SLIST_NEXT(elm, field) ((elm)->field.sle_next)
+
+#define SLIST_REMOVE(head, elm, type, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.sle_next); \
+ if (SLIST_FIRST((head)) == (elm)) { \
+ SLIST_REMOVE_HEAD((head), field); \
+ } \
+ else { \
+ QUEUE_TYPEOF(type) *curelm = SLIST_FIRST(head); \
+ while (SLIST_NEXT(curelm, field) != (elm)) \
+ curelm = SLIST_NEXT(curelm, field); \
+ SLIST_REMOVE_AFTER(curelm, field); \
+ } \
+ TRASHIT(*oldnext); \
+} while (0)
+
+#define SLIST_REMOVE_AFTER(elm, field) do { \
+ SLIST_NEXT(elm, field) = \
+ SLIST_NEXT(SLIST_NEXT(elm, field), field); \
+} while (0)
+
+#define SLIST_REMOVE_HEAD(head, field) do { \
+ SLIST_FIRST((head)) = SLIST_NEXT(SLIST_FIRST((head)), field); \
+} while (0)
+
+#define SLIST_REMOVE_PREVPTR(prevp, elm, field) do { \
+ QMD_SLIST_CHECK_PREVPTR(prevp, elm); \
+ *(prevp) = SLIST_NEXT(elm, field); \
+ TRASHIT((elm)->field.sle_next); \
+} while (0)
+
+#define SLIST_SWAP(head1, head2, type) do { \
+ QUEUE_TYPEOF(type) *swap_first = SLIST_FIRST(head1); \
+ SLIST_FIRST(head1) = SLIST_FIRST(head2); \
+ SLIST_FIRST(head2) = swap_first; \
+} while (0)
+
+/*
+ * Singly-linked Tail queue declarations.
+ */
+#define STAILQ_HEAD(name, type) \
+struct name { \
+ struct type *stqh_first;/* first element */ \
+ struct type **stqh_last;/* addr of last next element */ \
+}
+
+#define STAILQ_CLASS_HEAD(name, type) \
+struct name { \
+ class type *stqh_first; /* first element */ \
+ class type **stqh_last; /* addr of last next element */ \
+}
+
+#define STAILQ_HEAD_INITIALIZER(head) \
+ { NULL, &(head).stqh_first }
+
+#define STAILQ_ENTRY(type) \
+struct { \
+ struct type *stqe_next; /* next element */ \
+}
+
+#define STAILQ_CLASS_ENTRY(type) \
+struct { \
+ class type *stqe_next; /* next element */ \
+}
+
+/*
+ * Singly-linked Tail queue functions.
+ */
+#define STAILQ_CONCAT(head1, head2) do { \
+ if (!STAILQ_EMPTY((head2))) { \
+ *(head1)->stqh_last = (head2)->stqh_first; \
+ (head1)->stqh_last = (head2)->stqh_last; \
+ STAILQ_INIT((head2)); \
+ } \
+} while (0)
+
+#define STAILQ_EMPTY(head) ((head)->stqh_first == NULL)
+
+#define STAILQ_FIRST(head) ((head)->stqh_first)
+
+#define STAILQ_FOREACH(var, head, field) \
+ for((var) = STAILQ_FIRST((head)); \
+ (var); \
+ (var) = STAILQ_NEXT((var), field))
+
+#define STAILQ_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : STAILQ_FIRST((head))); \
+ (var); \
+ (var) = STAILQ_NEXT((var), field))
+
+#define STAILQ_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = STAILQ_FIRST((head)); \
+ (var) && ((tvar) = STAILQ_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define STAILQ_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : STAILQ_FIRST((head))); \
+ (var) && ((tvar) = STAILQ_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define STAILQ_INIT(head) do { \
+ STAILQ_FIRST((head)) = NULL; \
+ (head)->stqh_last = &STAILQ_FIRST((head)); \
+} while (0)
+
+#define STAILQ_INSERT_AFTER(head, tqelm, elm, field) do { \
+ if ((STAILQ_NEXT((elm), field) = STAILQ_NEXT((tqelm), field)) == NULL)\
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+ STAILQ_NEXT((tqelm), field) = (elm); \
+} while (0)
+
+#define STAILQ_INSERT_HEAD(head, elm, field) do { \
+ if ((STAILQ_NEXT((elm), field) = STAILQ_FIRST((head))) == NULL) \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+ STAILQ_FIRST((head)) = (elm); \
+} while (0)
+
+#define STAILQ_INSERT_TAIL(head, elm, field) do { \
+ STAILQ_NEXT((elm), field) = NULL; \
+ *(head)->stqh_last = (elm); \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+} while (0)
+
+#define STAILQ_LAST(head, type, field) \
+ (STAILQ_EMPTY((head)) ? NULL : \
+ __containerof((head)->stqh_last, \
+ QUEUE_TYPEOF(type), field.stqe_next))
+
+#define STAILQ_NEXT(elm, field) ((elm)->field.stqe_next)
+
+#define STAILQ_REMOVE(head, elm, type, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.stqe_next); \
+ if (STAILQ_FIRST((head)) == (elm)) { \
+ STAILQ_REMOVE_HEAD((head), field); \
+ } \
+ else { \
+ QUEUE_TYPEOF(type) *curelm = STAILQ_FIRST(head); \
+ while (STAILQ_NEXT(curelm, field) != (elm)) \
+ curelm = STAILQ_NEXT(curelm, field); \
+ STAILQ_REMOVE_AFTER(head, curelm, field); \
+ } \
+ TRASHIT(*oldnext); \
+} while (0)
+
+#define STAILQ_REMOVE_AFTER(head, elm, field) do { \
+ if ((STAILQ_NEXT(elm, field) = \
+ STAILQ_NEXT(STAILQ_NEXT(elm, field), field)) == NULL) \
+ (head)->stqh_last = &STAILQ_NEXT((elm), field); \
+} while (0)
+
+#define STAILQ_REMOVE_HEAD(head, field) do { \
+ if ((STAILQ_FIRST((head)) = \
+ STAILQ_NEXT(STAILQ_FIRST((head)), field)) == NULL) \
+ (head)->stqh_last = &STAILQ_FIRST((head)); \
+} while (0)
+
+#define STAILQ_SWAP(head1, head2, type) do { \
+ QUEUE_TYPEOF(type) *swap_first = STAILQ_FIRST(head1); \
+ QUEUE_TYPEOF(type) **swap_last = (head1)->stqh_last; \
+ STAILQ_FIRST(head1) = STAILQ_FIRST(head2); \
+ (head1)->stqh_last = (head2)->stqh_last; \
+ STAILQ_FIRST(head2) = swap_first; \
+ (head2)->stqh_last = swap_last; \
+ if (STAILQ_EMPTY(head1)) \
+ (head1)->stqh_last = &STAILQ_FIRST(head1); \
+ if (STAILQ_EMPTY(head2)) \
+ (head2)->stqh_last = &STAILQ_FIRST(head2); \
+} while (0)
+
+
+/*
+ * List declarations.
+ */
+#define LIST_HEAD(name, type) \
+struct name { \
+ struct type *lh_first; /* first element */ \
+}
+
+#define LIST_CLASS_HEAD(name, type) \
+struct name { \
+ class type *lh_first; /* first element */ \
+}
+
+#define LIST_HEAD_INITIALIZER(head) \
+ { NULL }
+
+#define LIST_ENTRY(type) \
+struct { \
+ struct type *le_next; /* next element */ \
+ struct type **le_prev; /* address of previous next element */ \
+}
+
+#define LIST_CLASS_ENTRY(type) \
+struct { \
+ class type *le_next; /* next element */ \
+ class type **le_prev; /* address of previous next element */ \
+}
+
+/*
+ * List functions.
+ */
+
+#if (defined(_KERNEL) && defined(INVARIANTS))
+/*
+ * QMD_LIST_CHECK_HEAD(LIST_HEAD *head, LIST_ENTRY NAME)
+ *
+ * If the list is non-empty, validates that the first element of the list
+ * points back at 'head.'
+ */
+#define QMD_LIST_CHECK_HEAD(head, field) do { \
+ if (LIST_FIRST((head)) != NULL && \
+ LIST_FIRST((head))->field.le_prev != \
+ &LIST_FIRST((head))) \
+ panic("Bad list head %p first->prev != head", (head)); \
+} while (0)
+
+/*
+ * QMD_LIST_CHECK_NEXT(TYPE *elm, LIST_ENTRY NAME)
+ *
+ * If an element follows 'elm' in the list, validates that the next element
+ * points back at 'elm.'
+ */
+#define QMD_LIST_CHECK_NEXT(elm, field) do { \
+ if (LIST_NEXT((elm), field) != NULL && \
+ LIST_NEXT((elm), field)->field.le_prev != \
+ &((elm)->field.le_next)) \
+ panic("Bad link elm %p next->prev != elm", (elm)); \
+} while (0)
+
+/*
+ * QMD_LIST_CHECK_PREV(TYPE *elm, LIST_ENTRY NAME)
+ *
+ * Validates that the previous element (or head of the list) points to 'elm.'
+ */
+#define QMD_LIST_CHECK_PREV(elm, field) do { \
+ if (*(elm)->field.le_prev != (elm)) \
+ panic("Bad link elm %p prev->next != elm", (elm)); \
+} while (0)
+#else
+#define QMD_LIST_CHECK_HEAD(head, field)
+#define QMD_LIST_CHECK_NEXT(elm, field)
+#define QMD_LIST_CHECK_PREV(elm, field)
+#endif /* (_KERNEL && INVARIANTS) */
+
+#define LIST_CONCAT(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *curelm = LIST_FIRST(head1); \
+ if (curelm == NULL) { \
+ if ((LIST_FIRST(head1) = LIST_FIRST(head2)) != NULL) { \
+ LIST_FIRST(head2)->field.le_prev = \
+ &LIST_FIRST((head1)); \
+ LIST_INIT(head2); \
+ } \
+ } else if (LIST_FIRST(head2) != NULL) { \
+ while (LIST_NEXT(curelm, field) != NULL) \
+ curelm = LIST_NEXT(curelm, field); \
+ LIST_NEXT(curelm, field) = LIST_FIRST(head2); \
+ LIST_FIRST(head2)->field.le_prev = &LIST_NEXT(curelm, field); \
+ LIST_INIT(head2); \
+ } \
+} while (0)
+
+#define LIST_EMPTY(head) ((head)->lh_first == NULL)
+
+#define LIST_FIRST(head) ((head)->lh_first)
+
+#define LIST_FOREACH(var, head, field) \
+ for ((var) = LIST_FIRST((head)); \
+ (var); \
+ (var) = LIST_NEXT((var), field))
+
+#define LIST_FOREACH_FROM(var, head, field) \
+ for ((var) = ((var) ? (var) : LIST_FIRST((head))); \
+ (var); \
+ (var) = LIST_NEXT((var), field))
+
+#define LIST_FOREACH_SAFE(var, head, field, tvar) \
+ for ((var) = LIST_FIRST((head)); \
+ (var) && ((tvar) = LIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define LIST_FOREACH_FROM_SAFE(var, head, field, tvar) \
+ for ((var) = ((var) ? (var) : LIST_FIRST((head))); \
+ (var) && ((tvar) = LIST_NEXT((var), field), 1); \
+ (var) = (tvar))
+
+#define LIST_INIT(head) do { \
+ LIST_FIRST((head)) = NULL; \
+} while (0)
+
+#define LIST_INSERT_AFTER(listelm, elm, field) do { \
+ QMD_LIST_CHECK_NEXT(listelm, field); \
+ if ((LIST_NEXT((elm), field) = LIST_NEXT((listelm), field)) != NULL)\
+ LIST_NEXT((listelm), field)->field.le_prev = \
+ &LIST_NEXT((elm), field); \
+ LIST_NEXT((listelm), field) = (elm); \
+ (elm)->field.le_prev = &LIST_NEXT((listelm), field); \
+} while (0)
+
+#define LIST_INSERT_BEFORE(listelm, elm, field) do { \
+ QMD_LIST_CHECK_PREV(listelm, field); \
+ (elm)->field.le_prev = (listelm)->field.le_prev; \
+ LIST_NEXT((elm), field) = (listelm); \
+ *(listelm)->field.le_prev = (elm); \
+ (listelm)->field.le_prev = &LIST_NEXT((elm), field); \
+} while (0)
+
+#define LIST_INSERT_HEAD(head, elm, field) do { \
+ QMD_LIST_CHECK_HEAD((head), field); \
+ if ((LIST_NEXT((elm), field) = LIST_FIRST((head))) != NULL) \
+ LIST_FIRST((head))->field.le_prev = &LIST_NEXT((elm), field);\
+ LIST_FIRST((head)) = (elm); \
+ (elm)->field.le_prev = &LIST_FIRST((head)); \
+} while (0)
+
+#define LIST_NEXT(elm, field) ((elm)->field.le_next)
+
+#define LIST_PREV(elm, head, type, field) \
+ ((elm)->field.le_prev == &LIST_FIRST((head)) ? NULL : \
+ __containerof((elm)->field.le_prev, \
+ QUEUE_TYPEOF(type), field.le_next))
+
+#define LIST_REMOVE(elm, field) do { \
+ QMD_SAVELINK(oldnext, (elm)->field.le_next); \
+ QMD_SAVELINK(oldprev, (elm)->field.le_prev); \
+ QMD_LIST_CHECK_NEXT(elm, field); \
+ QMD_LIST_CHECK_PREV(elm, field); \
+ if (LIST_NEXT((elm), field) != NULL) \
+ LIST_NEXT((elm), field)->field.le_prev = \
+ (elm)->field.le_prev; \
+ *(elm)->field.le_prev = LIST_NEXT((elm), field); \
+ TRASHIT(*oldnext); \
+ TRASHIT(*oldprev); \
+} while (0)
+
+#define LIST_SWAP(head1, head2, type, field) do { \
+ QUEUE_TYPEOF(type) *swap_tmp = LIST_FIRST(head1); \
+ LIST_FIRST((head1)) = LIST_FIRST((head2)); \
+ LIST_FIRST((head2)) = swap_tmp; \
+ if ((swap_tmp = LIST_FIRST((head1))) != NULL) \
+ swap_tmp->field.le_prev = &LIST_FIRST((head1)); \
+ if ((swap_tmp = LIST_FIRST((head2))) != NULL) \
+ swap_tmp->field.le_prev = &LIST_FIRST((head2)); \
+} while (0)
+
/*
* Tail queue declarations.
*/
@@ -123,10 +619,58 @@ struct { \
/*
* Tail queue functions.
*/
+#if (defined(_KERNEL) && defined(INVARIANTS))
+/*
+ * QMD_TAILQ_CHECK_HEAD(TAILQ_HEAD *head, TAILQ_ENTRY NAME)
+ *
+ * If the tailq is non-empty, validates that the first element of the tailq
+ * points back at 'head.'
+ */
+#define QMD_TAILQ_CHECK_HEAD(head, field) do { \
+ if (!TAILQ_EMPTY(head) && \
+ TAILQ_FIRST((head))->field.tqe_prev != \
+ &TAILQ_FIRST((head))) \
+ panic("Bad tailq head %p first->prev != head", (head)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_TAIL(TAILQ_HEAD *head, TAILQ_ENTRY NAME)
+ *
+ * Validates that the tail of the tailq is a pointer to pointer to NULL.
+ */
+#define QMD_TAILQ_CHECK_TAIL(head, field) do { \
+ if (*(head)->tqh_last != NULL) \
+ panic("Bad tailq NEXT(%p->tqh_last) != NULL", (head)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_NEXT(TYPE *elm, TAILQ_ENTRY NAME)
+ *
+ * If an element follows 'elm' in the tailq, validates that the next element
+ * points back at 'elm.'
+ */
+#define QMD_TAILQ_CHECK_NEXT(elm, field) do { \
+ if (TAILQ_NEXT((elm), field) != NULL && \
+ TAILQ_NEXT((elm), field)->field.tqe_prev != \
+ &((elm)->field.tqe_next)) \
+ panic("Bad link elm %p next->prev != elm", (elm)); \
+} while (0)
+
+/*
+ * QMD_TAILQ_CHECK_PREV(TYPE *elm, TAILQ_ENTRY NAME)
+ *
+ * Validates that the previous element (or head of the tailq) points to 'elm.'
+ */
+#define QMD_TAILQ_CHECK_PREV(elm, field) do { \
+ if (*(elm)->field.tqe_prev != (elm)) \
+ panic("Bad link elm %p prev->next != elm", (elm)); \
+} while (0)
+#else
#define QMD_TAILQ_CHECK_HEAD(head, field)
#define QMD_TAILQ_CHECK_TAIL(head, headname)
#define QMD_TAILQ_CHECK_NEXT(elm, field)
#define QMD_TAILQ_CHECK_PREV(elm, field)
+#endif /* (_KERNEL && INVARIANTS) */
#define TAILQ_CONCAT(head1, head2, field) do { \
if (!TAILQ_EMPTY(head2)) { \
@@ -191,9 +735,8 @@ struct { \
#define TAILQ_INSERT_AFTER(head, listelm, elm, field) do { \
QMD_TAILQ_CHECK_NEXT(listelm, field); \
- TAILQ_NEXT((elm), field) = TAILQ_NEXT((listelm), field); \
- if (TAILQ_NEXT((listelm), field) != NULL) \
- TAILQ_NEXT((elm), field)->field.tqe_prev = \
+ if ((TAILQ_NEXT((elm), field) = TAILQ_NEXT((listelm), field)) != NULL)\
+ TAILQ_NEXT((elm), field)->field.tqe_prev = \
&TAILQ_NEXT((elm), field); \
else { \
(head)->tqh_last = &TAILQ_NEXT((elm), field); \
@@ -217,8 +760,7 @@ struct { \
#define TAILQ_INSERT_HEAD(head, elm, field) do { \
QMD_TAILQ_CHECK_HEAD(head, field); \
- TAILQ_NEXT((elm), field) = TAILQ_FIRST((head)); \
- if (TAILQ_FIRST((head)) != NULL) \
+ if ((TAILQ_NEXT((elm), field) = TAILQ_FIRST((head))) != NULL) \
TAILQ_FIRST((head))->field.tqe_prev = \
&TAILQ_NEXT((elm), field); \
else \
@@ -250,21 +792,24 @@ struct { \
* you may want to prefetch the last data element.
*/
#define TAILQ_LAST_FAST(head, type, field) \
- (TAILQ_EMPTY(head) ? NULL : __containerof((head)->tqh_last, \
- QUEUE_TYPEOF(type), field.tqe_next))
+ (TAILQ_EMPTY(head) ? NULL : __containerof((head)->tqh_last, QUEUE_TYPEOF(type), field.tqe_next))
#define TAILQ_NEXT(elm, field) ((elm)->field.tqe_next)
#define TAILQ_PREV(elm, headname, field) \
(*(((struct headname *)((elm)->field.tqe_prev))->tqh_last))
+#define TAILQ_PREV_FAST(elm, head, type, field) \
+ ((elm)->field.tqe_prev == &(head)->tqh_first ? NULL : \
+ __containerof((elm)->field.tqe_prev, QUEUE_TYPEOF(type), field.tqe_next))
+
#define TAILQ_REMOVE(head, elm, field) do { \
QMD_SAVELINK(oldnext, (elm)->field.tqe_next); \
QMD_SAVELINK(oldprev, (elm)->field.tqe_prev); \
QMD_TAILQ_CHECK_NEXT(elm, field); \
QMD_TAILQ_CHECK_PREV(elm, field); \
if ((TAILQ_NEXT((elm), field)) != NULL) \
- TAILQ_NEXT((elm), field)->field.tqe_prev = \
+ TAILQ_NEXT((elm), field)->field.tqe_prev = \
(elm)->field.tqe_prev; \
else { \
(head)->tqh_last = (elm)->field.tqe_prev; \
@@ -277,26 +822,20 @@ struct { \
} while (0)
#define TAILQ_SWAP(head1, head2, type, field) do { \
- QUEUE_TYPEOF(type) * swap_first = (head1)->tqh_first; \
- QUEUE_TYPEOF(type) * *swap_last = (head1)->tqh_last; \
+ QUEUE_TYPEOF(type) *swap_first = (head1)->tqh_first; \
+ QUEUE_TYPEOF(type) **swap_last = (head1)->tqh_last; \
(head1)->tqh_first = (head2)->tqh_first; \
(head1)->tqh_last = (head2)->tqh_last; \
(head2)->tqh_first = swap_first; \
(head2)->tqh_last = swap_last; \
- swap_first = (head1)->tqh_first; \
- if (swap_first != NULL) \
+ if ((swap_first = (head1)->tqh_first) != NULL) \
swap_first->field.tqe_prev = &(head1)->tqh_first; \
else \
(head1)->tqh_last = &(head1)->tqh_first; \
- swap_first = (head2)->tqh_first; \
- if (swap_first != NULL) \
+ if ((swap_first = (head2)->tqh_first) != NULL) \
swap_first->field.tqe_prev = &(head2)->tqh_first; \
else \
(head2)->tqh_last = &(head2)->tqh_first; \
} while (0)
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* _SYS_QUEUE_H_ */
+#endif /* !_SYS_QUEUE_H_ */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (8 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 09/10] eal/windows: replace sys/queue.h with a complete one from FreeBSD Dmitry Kozlyuk
@ 2020-04-14 19:44 ` Dmitry Kozlyuk
2020-04-15 9:42 ` Jerin Jacob
2020-04-16 18:34 ` Ranjit Menon
2020-04-14 23:37 ` [dpdk-dev] [PATCH v3 00/10] Windows " Kadam, Pallavi
10 siblings, 2 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-14 19:44 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Thomas Monjalon, Harini Ramakrishnan,
Omar Cardona, Pallavi Kadam, Ranjit Menon, John McNamara,
Marko Kovacevic, Anatoly Burakov, Bruce Richardson
Basic memory management supports core libraries and PMDs operating in
IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
IOVAs of hugepages allocated from user-mode.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
config/meson.build | 2 +-
doc/guides/windows_gsg/run_apps.rst | 43 +-
lib/librte_eal/common/eal_common_fbarray.c | 57 +-
lib/librte_eal/common/eal_common_memory.c | 50 +-
lib/librte_eal/common/eal_private.h | 6 +-
lib/librte_eal/common/malloc_heap.c | 1 +
lib/librte_eal/common/meson.build | 9 +
lib/librte_eal/freebsd/eal_memory.c | 1 -
lib/librte_eal/rte_eal_exports.def | 119 ++-
lib/librte_eal/windows/eal.c | 55 ++
lib/librte_eal/windows/eal_memalloc.c | 418 +++++++++++
lib/librte_eal/windows/eal_memory.c | 706 +++++++++++++++++-
lib/librte_eal/windows/eal_mp.c | 103 +++
lib/librte_eal/windows/eal_windows.h | 23 +
lib/librte_eal/windows/include/meson.build | 1 +
lib/librte_eal/windows/include/rte_os.h | 4 +
.../windows/include/rte_virt2phys.h | 34 +
lib/librte_eal/windows/include/rte_windows.h | 2 +
lib/librte_eal/windows/include/unistd.h | 3 +
lib/librte_eal/windows/meson.build | 4 +
20 files changed, 1571 insertions(+), 70 deletions(-)
create mode 100644 lib/librte_eal/windows/eal_memalloc.c
create mode 100644 lib/librte_eal/windows/eal_mp.c
create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
diff --git a/config/meson.build b/config/meson.build
index bceb5ef7b..7b8baa788 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -270,7 +270,7 @@ if is_windows
add_project_link_arguments('-lmincore', language: 'c')
endif
- add_project_link_arguments('-ladvapi32', language: 'c')
+ add_project_link_arguments('-ladvapi32', '-lsetupapi', language: 'c')
endif
if get_option('b_lto')
diff --git a/doc/guides/windows_gsg/run_apps.rst b/doc/guides/windows_gsg/run_apps.rst
index 21ac7f6c1..323d050dc 100644
--- a/doc/guides/windows_gsg/run_apps.rst
+++ b/doc/guides/windows_gsg/run_apps.rst
@@ -7,10 +7,10 @@ Running DPDK Applications
Grant *Lock pages in memory* Privilege
--------------------------------------
-Use of hugepages ("large pages" in Windows terminolocy) requires
+Use of hugepages ("large pages" in Windows terminology) requires
``SeLockMemoryPrivilege`` for the user running an application.
-1. Open *Local Security Policy* snap in, either:
+1. Open *Local Security Policy* snap-in, either:
* Control Panel / Computer Management / Local Security Policy;
* or Win+R, type ``secpol``, press Enter.
@@ -24,7 +24,44 @@ Use of hugepages ("large pages" in Windows terminolocy) requires
See `Large-Page Support`_ in MSDN for details.
-.. _Large-page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
+.. _Large-Page Support: https://docs.microsoft.com/en-us/windows/win32/memory/large-page-support
+
+
+Load virt2phys Driver
+---------------------
+
+Access to physical addresses is provided by a kernel-mode driver, virt2phys.
+It is mandatory at least for using hardware PMDs, but may also be required
+for mempools.
+
+Refer to documentation in ``dpdk-kmods`` repository for details on system
+setup, driver build and installation. This driver is not signed, so signature
+checking must be disabled to load it.
+
+.. warning::
+
+ Disabling driver signature enforcement weakens OS security.
+ It is discouraged in production environments.
+
+Compiled package consists of ``virt2phys.inf``, ``virt2phys.cat``,
+and ``virt2phys.sys``. It can be installed as follows
+from Elevated Command Prompt:
+
+.. code-block:: console
+
+ pnputil /add-driver Z:\path\to\virt2phys.inf /install
+
+When loaded successfully, the driver is shown in *Device Manager* as *Virtual
+to physical address translator* device under *Kernel bypass* category.
+Installed driver persists across reboots.
+
+If DPDK is unable to communicate with the driver, a warning is printed
+on initialization (debug-level logs provide more details):
+
+.. code-block:: text
+
+ EAL: Cannot open virt2phys driver interface
+
Run the ``helloworld`` Example
diff --git a/lib/librte_eal/common/eal_common_fbarray.c b/lib/librte_eal/common/eal_common_fbarray.c
index 1312f936b..236db9cb7 100644
--- a/lib/librte_eal/common/eal_common_fbarray.c
+++ b/lib/librte_eal/common/eal_common_fbarray.c
@@ -5,15 +5,15 @@
#include <fcntl.h>
#include <inttypes.h>
#include <limits.h>
-#include <sys/mman.h>
#include <stdint.h>
#include <errno.h>
-#include <sys/file.h>
#include <string.h>
+#include <unistd.h>
#include <rte_common.h>
-#include <rte_log.h>
#include <rte_errno.h>
+#include <rte_log.h>
+#include <rte_memory.h>
#include <rte_spinlock.h>
#include <rte_tailq.h>
@@ -85,19 +85,16 @@ resize_and_map(int fd, void *addr, size_t len)
char path[PATH_MAX];
void *map_addr;
- if (ftruncate(fd, len)) {
+ if (eal_file_truncate(fd, len)) {
RTE_LOG(ERR, EAL, "Cannot truncate %s\n", path);
/* pass errno up the chain */
rte_errno = errno;
return -1;
}
- map_addr = mmap(addr, len, PROT_READ | PROT_WRITE,
- MAP_SHARED | MAP_FIXED, fd, 0);
+ map_addr = rte_mem_map(addr, len, RTE_PROT_READ | RTE_PROT_WRITE,
+ RTE_MAP_SHARED | RTE_MAP_FIXED, fd, 0);
if (map_addr != addr) {
- RTE_LOG(ERR, EAL, "mmap() failed: %s\n", strerror(errno));
- /* pass errno up the chain */
- rte_errno = errno;
return -1;
}
return 0;
@@ -735,7 +732,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
return -1;
}
- page_sz = sysconf(_SC_PAGESIZE);
+ page_sz = rte_get_page_size();
if (page_sz == (size_t)-1) {
free(ma);
return -1;
@@ -756,9 +753,12 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
if (internal_config.no_shconf) {
/* remap virtual area as writable */
- void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
- MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, fd, 0);
- if (new_data == MAP_FAILED) {
+ void *new_data = rte_mem_map(
+ data, mmap_len,
+ RTE_PROT_READ | RTE_PROT_WRITE,
+ RTE_MAP_FIXED | RTE_MAP_PRIVATE | RTE_MAP_ANONYMOUS,
+ fd, 0);
+ if (new_data == NULL) {
RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
__func__, strerror(errno));
goto fail;
@@ -778,7 +778,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
__func__, path, strerror(errno));
rte_errno = errno;
goto fail;
- } else if (flock(fd, LOCK_EX | LOCK_NB)) {
+ } else if (eal_file_lock(
+ fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
__func__, path, strerror(errno));
rte_errno = EBUSY;
@@ -789,10 +790,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
* still attach to it, but no other process could reinitialize
* it.
*/
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -824,7 +823,7 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
return 0;
fail:
if (data)
- munmap(data, mmap_len);
+ rte_mem_unmap(data, mmap_len);
if (fd >= 0)
close(fd);
free(ma);
@@ -862,7 +861,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
return -1;
}
- page_sz = sysconf(_SC_PAGESIZE);
+ page_sz = rte_get_page_size();
if (page_sz == (size_t)-1) {
free(ma);
return -1;
@@ -895,10 +894,8 @@ rte_fbarray_attach(struct rte_fbarray *arr)
}
/* lock the file, to let others know we're using it */
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -916,7 +913,7 @@ rte_fbarray_attach(struct rte_fbarray *arr)
return 0;
fail:
if (data)
- munmap(data, mmap_len);
+ rte_mem_unmap(data, mmap_len);
if (fd >= 0)
close(fd);
free(ma);
@@ -944,8 +941,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
* really do anything about it, things will blow up either way.
*/
- size_t page_sz = sysconf(_SC_PAGESIZE);
-
+ size_t page_sz = rte_get_page_size();
if (page_sz == (size_t)-1)
return -1;
@@ -964,7 +960,7 @@ rte_fbarray_detach(struct rte_fbarray *arr)
goto out;
}
- munmap(arr->data, mmap_len);
+ rte_mem_unmap(arr->data, mmap_len);
/* area is unmapped, close fd and remove the tailq entry */
if (tmp->fd >= 0)
@@ -999,8 +995,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* really do anything about it, things will blow up either way.
*/
- size_t page_sz = sysconf(_SC_PAGESIZE);
-
+ size_t page_sz = rte_get_page_size();
if (page_sz == (size_t)-1)
return -1;
@@ -1025,7 +1020,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* has been detached by all other processes
*/
fd = tmp->fd;
- if (flock(fd, LOCK_EX | LOCK_NB)) {
+ if (eal_file_lock(fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "Cannot destroy fbarray - another process is using it\n");
rte_errno = EBUSY;
ret = -1;
@@ -1042,14 +1037,14 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* we're still holding an exclusive lock, so drop it to
* shared.
*/
- flock(fd, LOCK_SH | LOCK_NB);
+ eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN);
ret = -1;
goto out;
}
close(fd);
}
- munmap(arr->data, mmap_len);
+ rte_mem_unmap(arr->data, mmap_len);
/* area is unmapped, remove the tailq entry */
TAILQ_REMOVE(&mem_area_tailq, tmp, next);
diff --git a/lib/librte_eal/common/eal_common_memory.c b/lib/librte_eal/common/eal_common_memory.c
index d9764681a..5c3cf1f75 100644
--- a/lib/librte_eal/common/eal_common_memory.c
+++ b/lib/librte_eal/common/eal_common_memory.c
@@ -11,7 +11,6 @@
#include <string.h>
#include <unistd.h>
#include <inttypes.h>
-#include <sys/mman.h>
#include <sys/queue.h>
#include <rte_fbarray.h>
@@ -44,7 +43,7 @@ static uint64_t system_page_sz;
#define MAX_MMAP_WITH_DEFINED_ADDR_TRIES 5
void *
eal_get_virtual_area(void *requested_addr, size_t *size,
- size_t page_sz, int flags, int mmap_flags)
+ size_t page_sz, int flags, enum eal_mem_reserve_flags reserve_flags)
{
bool addr_is_hint, allow_shrink, unmap, no_align;
uint64_t map_sz;
@@ -52,9 +51,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
uint8_t try = 0;
if (system_page_sz == 0)
- system_page_sz = sysconf(_SC_PAGESIZE);
-
- mmap_flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+ system_page_sz = rte_get_page_size();
RTE_LOG(DEBUG, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
@@ -98,24 +95,24 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
return NULL;
}
- mapped_addr = mmap(requested_addr, (size_t)map_sz, PROT_NONE,
- mmap_flags, -1, 0);
- if (mapped_addr == MAP_FAILED && allow_shrink)
- *size -= page_sz;
+ mapped_addr = eal_mem_reserve(
+ requested_addr, (size_t)map_sz, reserve_flags);
+ if ((mapped_addr == NULL) && allow_shrink)
+ size -= page_sz;
- if (mapped_addr != MAP_FAILED && addr_is_hint &&
- mapped_addr != requested_addr) {
+ if ((mapped_addr != NULL) && addr_is_hint &&
+ (mapped_addr != requested_addr)) {
try++;
next_baseaddr = RTE_PTR_ADD(next_baseaddr, page_sz);
if (try <= MAX_MMAP_WITH_DEFINED_ADDR_TRIES) {
/* hint was not used. Try with another offset */
- munmap(mapped_addr, map_sz);
- mapped_addr = MAP_FAILED;
+ eal_mem_free(mapped_addr, *size);
+ mapped_addr = NULL;
requested_addr = next_baseaddr;
}
}
} while ((allow_shrink || addr_is_hint) &&
- mapped_addr == MAP_FAILED && *size > 0);
+ (mapped_addr == NULL) && (*size > 0));
/* align resulting address - if map failed, we will ignore the value
* anyway, so no need to add additional checks.
@@ -125,20 +122,17 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
if (*size == 0) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area of any size: %s\n",
- strerror(errno));
- rte_errno = errno;
+ strerror(rte_errno));
return NULL;
- } else if (mapped_addr == MAP_FAILED) {
+ } else if (mapped_addr == NULL) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area: %s\n",
- strerror(errno));
- /* pass errno up the call chain */
- rte_errno = errno;
+ strerror(rte_errno));
return NULL;
} else if (requested_addr != NULL && !addr_is_hint &&
aligned_addr != requested_addr) {
RTE_LOG(ERR, EAL, "Cannot get a virtual area at requested address: %p (got %p)\n",
requested_addr, aligned_addr);
- munmap(mapped_addr, map_sz);
+ eal_mem_free(mapped_addr, map_sz);
rte_errno = EADDRNOTAVAIL;
return NULL;
} else if (requested_addr != NULL && addr_is_hint &&
@@ -154,7 +148,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
aligned_addr, *size);
if (unmap) {
- munmap(mapped_addr, map_sz);
+ eal_mem_free(mapped_addr, map_sz);
} else if (!no_align) {
void *map_end, *aligned_end;
size_t before_len, after_len;
@@ -172,12 +166,12 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
/* unmap space before aligned mmap address */
before_len = RTE_PTR_DIFF(aligned_addr, mapped_addr);
if (before_len > 0)
- munmap(mapped_addr, before_len);
+ eal_mem_free(mapped_addr, before_len);
/* unmap space after aligned end mmap address */
after_len = RTE_PTR_DIFF(map_end, aligned_end);
if (after_len > 0)
- munmap(aligned_end, after_len);
+ eal_mem_free(aligned_end, after_len);
}
return aligned_addr;
@@ -586,10 +580,10 @@ rte_eal_memdevice_init(void)
int
rte_mem_lock_page(const void *virt)
{
- unsigned long virtual = (unsigned long)virt;
- int page_size = getpagesize();
- unsigned long aligned = (virtual & ~(page_size - 1));
- return mlock((void *)aligned, page_size);
+ uintptr_t virtual = (uintptr_t)virt;
+ int page_size = rte_get_page_size();
+ uintptr_t aligned = (virtual & ~(page_size - 1));
+ return rte_mem_lock((void *)aligned, page_size);
}
int
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index 76938e379..59ac41916 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -226,8 +226,8 @@ enum eal_mem_reserve_flags {
* Page size on which to align requested virtual area.
* @param flags
* EAL_VIRTUAL_AREA_* flags.
- * @param mmap_flags
- * Extra flags passed directly to mmap().
+ * @param reserve_flags
+ * Extra flags passed directly to rte_mem_reserve().
*
* @return
* Virtual area address if successful.
@@ -244,7 +244,7 @@ enum eal_mem_reserve_flags {
/**< immediately unmap reserved virtual area. */
void *
eal_get_virtual_area(void *requested_addr, size_t *size, size_t page_sz,
- int flags, int mmap_flags);
+ int flags, enum eal_mem_reserve_flags reserve_flags);
/**
* Reserve VA space for a memory segment list.
diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
index 842eb9de7..6534c895c 100644
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -729,6 +729,7 @@ malloc_heap_alloc(const char *type, size_t size, int socket_arg,
if (ret != NULL)
return ret;
}
+
return NULL;
}
diff --git a/lib/librte_eal/common/meson.build b/lib/librte_eal/common/meson.build
index 02d9280cc..6dcdcc890 100644
--- a/lib/librte_eal/common/meson.build
+++ b/lib/librte_eal/common/meson.build
@@ -9,11 +9,20 @@ if is_windows
'eal_common_class.c',
'eal_common_devargs.c',
'eal_common_errno.c',
+ 'eal_common_fbarray.c',
'eal_common_launch.c',
'eal_common_lcore.c',
'eal_common_log.c',
+ 'eal_common_mcfg.c',
+ 'eal_common_memalloc.c',
+ 'eal_common_memory.c',
+ 'eal_common_memzone.c',
'eal_common_options.c',
+ 'eal_common_tailqs.c',
'eal_common_thread.c',
+ 'malloc_elem.c',
+ 'malloc_heap.c',
+ 'rte_malloc.c',
'rte_option.c',
)
subdir_done()
diff --git a/lib/librte_eal/freebsd/eal_memory.c b/lib/librte_eal/freebsd/eal_memory.c
index 5174f9cd0..99bf6ec9e 100644
--- a/lib/librte_eal/freebsd/eal_memory.c
+++ b/lib/librte_eal/freebsd/eal_memory.c
@@ -355,7 +355,6 @@ memseg_list_reserve(struct rte_memseg_list *msl)
return eal_reserve_memseg_list(msl, flags);
}
-
static int
memseg_primary_init(void)
{
diff --git a/lib/librte_eal/rte_eal_exports.def b/lib/librte_eal/rte_eal_exports.def
index bacf9a107..854b83bcd 100644
--- a/lib/librte_eal/rte_eal_exports.def
+++ b/lib/librte_eal/rte_eal_exports.def
@@ -1,13 +1,128 @@
EXPORTS
__rte_panic
+ rte_calloc
+ rte_calloc_socket
rte_eal_get_configuration
+ rte_eal_has_hugepages
rte_eal_init
+ rte_eal_iova_mode
rte_eal_mp_remote_launch
rte_eal_mp_wait_lcore
+ rte_eal_process_type
rte_eal_remote_launch
- rte_get_page_size
+ rte_eal_tailq_lookup
+ rte_eal_tailq_register
+ rte_eal_using_phys_addrs
+ rte_free
rte_log
+ rte_malloc
+ rte_malloc_dump_stats
+ rte_malloc_get_socket_stats
+ rte_malloc_set_limit
+ rte_malloc_socket
+ rte_malloc_validate
+ rte_malloc_virt2iova
+ rte_mcfg_mem_read_lock
+ rte_mcfg_mem_read_unlock
+ rte_mcfg_mem_write_lock
+ rte_mcfg_mem_write_unlock
+ rte_mcfg_mempool_read_lock
+ rte_mcfg_mempool_read_unlock
+ rte_mcfg_mempool_write_lock
+ rte_mcfg_mempool_write_unlock
+ rte_mcfg_tailq_read_lock
+ rte_mcfg_tailq_read_unlock
+ rte_mcfg_tailq_write_lock
+ rte_mcfg_tailq_write_unlock
+ rte_mem_lock_page
+ rte_mem_virt2iova
+ rte_mem_virt2phy
+ rte_memory_get_nchannel
+ rte_memory_get_nrank
+ rte_memzone_dump
+ rte_memzone_free
+ rte_memzone_lookup
+ rte_memzone_reserve
+ rte_memzone_reserve_aligned
+ rte_memzone_reserve_bounded
+ rte_memzone_walk
+ rte_vlog
+ rte_realloc
+ rte_zmalloc
+ rte_zmalloc_socket
+
+ rte_mp_action_register
+ rte_mp_action_unregister
+ rte_mp_reply
+ rte_mp_sendmsg
+
+ rte_fbarray_attach
+ rte_fbarray_destroy
+ rte_fbarray_detach
+ rte_fbarray_dump_metadata
+ rte_fbarray_find_contig_free
+ rte_fbarray_find_contig_used
+ rte_fbarray_find_idx
+ rte_fbarray_find_next_free
+ rte_fbarray_find_next_n_free
+ rte_fbarray_find_next_n_used
+ rte_fbarray_find_next_used
+ rte_fbarray_get
+ rte_fbarray_init
+ rte_fbarray_is_used
+ rte_fbarray_set_free
+ rte_fbarray_set_used
+ rte_malloc_dump_heaps
+ rte_mem_alloc_validator_register
+ rte_mem_alloc_validator_unregister
+ rte_mem_check_dma_mask
+ rte_mem_event_callback_register
+ rte_mem_event_callback_unregister
+ rte_mem_iova2virt
+ rte_mem_virt2memseg
+ rte_mem_virt2memseg_list
+ rte_memseg_contig_walk
+ rte_memseg_list_walk
+ rte_memseg_walk
+ rte_mp_request_async
+ rte_mp_request_sync
+
+ rte_fbarray_find_prev_free
+ rte_fbarray_find_prev_n_free
+ rte_fbarray_find_prev_n_used
+ rte_fbarray_find_prev_used
+ rte_fbarray_find_rev_contig_free
+ rte_fbarray_find_rev_contig_used
+ rte_memseg_contig_walk_thread_unsafe
+ rte_memseg_list_walk_thread_unsafe
+ rte_memseg_walk_thread_unsafe
+
+ rte_malloc_heap_create
+ rte_malloc_heap_destroy
+ rte_malloc_heap_get_socket
+ rte_malloc_heap_memory_add
+ rte_malloc_heap_memory_attach
+ rte_malloc_heap_memory_detach
+ rte_malloc_heap_memory_remove
+ rte_malloc_heap_socket_is_external
+ rte_mem_check_dma_mask_thread_unsafe
+ rte_mem_set_dma_mask
+ rte_memseg_get_fd
+ rte_memseg_get_fd_offset
+ rte_memseg_get_fd_offset_thread_unsafe
+ rte_memseg_get_fd_thread_unsafe
+
+ rte_extmem_attach
+ rte_extmem_detach
+ rte_extmem_register
+ rte_extmem_unregister
+
+ rte_fbarray_find_biggest_free
+ rte_fbarray_find_biggest_used
+ rte_fbarray_find_rev_biggest_free
+ rte_fbarray_find_rev_biggest_used
+
+ rte_get_page_size
rte_mem_lock
rte_mem_map
rte_mem_unmap
- rte_vlog
diff --git a/lib/librte_eal/windows/eal.c b/lib/librte_eal/windows/eal.c
index cf55b56da..38f17f09c 100644
--- a/lib/librte_eal/windows/eal.c
+++ b/lib/librte_eal/windows/eal.c
@@ -93,6 +93,24 @@ eal_proc_type_detect(void)
return ptype;
}
+enum rte_proc_type_t
+rte_eal_process_type(void)
+{
+ return rte_config.process_type;
+}
+
+int
+rte_eal_has_hugepages(void)
+{
+ return !internal_config.no_hugetlbfs;
+}
+
+enum rte_iova_mode
+rte_eal_iova_mode(void)
+{
+ return rte_config.iova_mode;
+}
+
/* display usage */
static void
eal_usage(const char *prgname)
@@ -328,6 +346,13 @@ rte_eal_init(int argc, char **argv)
if (fctret < 0)
exit(1);
+ /* Prevent creation of shared memory files. */
+ if (internal_config.no_shconf == 0) {
+ RTE_LOG(WARNING, EAL, "Multi-process support is requested, "
+ "but not available.\n");
+ internal_config.no_shconf = 1;
+ }
+
if (!internal_config.no_hugetlbfs && (eal_hugepage_info_init() < 0)) {
rte_eal_init_alert("Cannot get hugepage information");
rte_errno = EACCES;
@@ -345,6 +370,36 @@ rte_eal_init(int argc, char **argv)
return -1;
}
+ if (eal_mem_virt2iova_init() < 0) {
+ /* Non-fatal error if physical addresses are not required. */
+ RTE_LOG(WARNING, EAL, "Cannot access virt2phys driver, "
+ "PA will not be available\n");
+ }
+
+ if (rte_eal_memzone_init() < 0) {
+ rte_eal_init_alert("Cannot init memzone");
+ rte_errno = ENODEV;
+ return -1;
+ }
+
+ if (rte_eal_memory_init() < 0) {
+ rte_eal_init_alert("Cannot init memory");
+ rte_errno = ENOMEM;
+ return -1;
+ }
+
+ if (rte_eal_malloc_heap_init() < 0) {
+ rte_eal_init_alert("Cannot init malloc heap");
+ rte_errno = ENODEV;
+ return -1;
+ }
+
+ if (rte_eal_tailqs_init() < 0) {
+ rte_eal_init_alert("Cannot init tail queues for objects");
+ rte_errno = EFAULT;
+ return -1;
+ }
+
eal_thread_init_master(rte_config.master_lcore);
RTE_LCORE_FOREACH_SLAVE(i) {
diff --git a/lib/librte_eal/windows/eal_memalloc.c b/lib/librte_eal/windows/eal_memalloc.c
new file mode 100644
index 000000000..e72e785b8
--- /dev/null
+++ b/lib/librte_eal/windows/eal_memalloc.c
@@ -0,0 +1,418 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+#include <rte_errno.h>
+#include <rte_os.h>
+#include <rte_windows.h>
+
+#include "eal_internal_cfg.h"
+#include "eal_memalloc.h"
+#include "eal_memcfg.h"
+#include "eal_private.h"
+#include "eal_windows.h"
+
+int
+eal_memalloc_get_seg_fd(int list_idx, int seg_idx)
+{
+ /* Hugepages have no assiciated files in Windows. */
+ RTE_SET_USED(list_idx);
+ RTE_SET_USED(seg_idx);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+eal_memalloc_get_seg_fd_offset(int list_idx, int seg_idx, size_t *offset)
+{
+ /* Hugepages have no assiciated files in Windows. */
+ RTE_SET_USED(list_idx);
+ RTE_SET_USED(seg_idx);
+ RTE_SET_USED(offset);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+static int
+alloc_seg(struct rte_memseg *ms, void *requested_addr, int socket_id,
+ struct hugepage_info *hi)
+{
+ HANDLE current_process;
+ unsigned int numa_node;
+ size_t alloc_sz;
+ void *addr;
+ rte_iova_t iova = RTE_BAD_IOVA;
+ PSAPI_WORKING_SET_EX_INFORMATION info;
+ PSAPI_WORKING_SET_EX_BLOCK *page;
+
+ if (ms->len > 0) {
+ /* If a segment is already allocated as needed, return it. */
+ if ((ms->addr == requested_addr) &&
+ (ms->socket_id == socket_id) &&
+ (ms->hugepage_sz == hi->hugepage_sz)) {
+ return 0;
+ }
+
+ /* Bugcheck, should not happen. */
+ RTE_LOG(DEBUG, EAL, "Attempted to reallocate segment %p "
+ "(size %zu) on socket %d", ms->addr,
+ ms->len, ms->socket_id);
+ return -1;
+ }
+
+ current_process = GetCurrentProcess();
+ numa_node = eal_socket_numa_node(socket_id);
+ alloc_sz = hi->hugepage_sz;
+
+ if (requested_addr == NULL) {
+ /* Request a new chunk of memory from OS. */
+ addr = eal_mem_alloc_socket(alloc_sz, socket_id);
+ if (addr == NULL) {
+ RTE_LOG(DEBUG, EAL, "Cannot allocate %zu bytes "
+ "on socket %d\n", alloc_sz, socket_id);
+ return -1;
+ }
+ } else {
+ /* Requested address is already reserved, commit memory. */
+ addr = eal_mem_commit(requested_addr, alloc_sz, socket_id);
+ if (addr == NULL) {
+ RTE_LOG(DEBUG, EAL, "Cannot commit reserved memory %p "
+ "(size %zu) on socket %d\n",
+ requested_addr, alloc_sz, socket_id);
+ return -1;
+ }
+ }
+
+ /* Force OS to allocate a physical page and select a NUMA node.
+ * Hugepages are not pageable in Windows, so there's no race
+ * for physical address.
+ */
+ *(volatile int *)addr = *(volatile int *)addr;
+
+ /* Only try to obtain IOVA if it's available, so that applications
+ * that do not need IOVA can use this allocator.
+ */
+ if (rte_eal_using_phys_addrs()) {
+ iova = rte_mem_virt2iova(addr);
+ if (iova == RTE_BAD_IOVA) {
+ RTE_LOG(DEBUG, EAL,
+ "Cannot get IOVA of allocated segment\n");
+ goto error;
+ }
+ }
+
+ /* Only "Ex" function can handle hugepages. */
+ info.VirtualAddress = addr;
+ if (!QueryWorkingSetEx(current_process, &info, sizeof(info))) {
+ RTE_LOG_WIN32_ERR("QueryWorkingSetEx()");
+ goto error;
+ }
+
+ page = &info.VirtualAttributes;
+ if (!page->Valid || !page->LargePage) {
+ RTE_LOG(DEBUG, EAL, "Got regular page instead of a hugepage\n");
+ goto error;
+ }
+ if (page->Node != numa_node) {
+ RTE_LOG(DEBUG, EAL,
+ "NUMA node hint %u (socket %d) not respected, got %u\n",
+ numa_node, socket_id, page->Node);
+ goto error;
+ }
+
+ ms->addr = addr;
+ ms->hugepage_sz = hi->hugepage_sz;
+ ms->len = alloc_sz;
+ ms->nchannel = rte_memory_get_nchannel();
+ ms->nrank = rte_memory_get_nrank();
+ ms->iova = iova;
+ ms->socket_id = socket_id;
+
+ return 0;
+
+error:
+ /* Only jump here when `addr` and `alloc_sz` are valid. */
+ eal_mem_decommit(addr, alloc_sz);
+ return -1;
+}
+
+static int
+free_seg(struct rte_memseg *ms)
+{
+ if (eal_mem_decommit(ms->addr, ms->len))
+ return -1;
+
+ /* Must clear the segment, because alloc_seg() inspects it. */
+ memset(ms, 0, sizeof(*ms));
+ return 0;
+}
+
+struct alloc_walk_param {
+ struct hugepage_info *hi;
+ struct rte_memseg **ms;
+ size_t page_sz;
+ unsigned int segs_allocated;
+ unsigned int n_segs;
+ int socket;
+ bool exact;
+};
+
+static int
+alloc_seg_walk(const struct rte_memseg_list *msl, void *arg)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct alloc_walk_param *wa = arg;
+ struct rte_memseg_list *cur_msl;
+ size_t page_sz;
+ int cur_idx, start_idx, j;
+ unsigned int msl_idx, need, i;
+
+ if (msl->page_sz != wa->page_sz)
+ return 0;
+ if (msl->socket_id != wa->socket)
+ return 0;
+
+ page_sz = (size_t)msl->page_sz;
+
+ msl_idx = msl - mcfg->memsegs;
+ cur_msl = &mcfg->memsegs[msl_idx];
+
+ need = wa->n_segs;
+
+ /* try finding space in memseg list */
+ if (wa->exact) {
+ /* if we require exact number of pages in a list, find them */
+ cur_idx = rte_fbarray_find_next_n_free(
+ &cur_msl->memseg_arr, 0, need);
+ if (cur_idx < 0)
+ return 0;
+ start_idx = cur_idx;
+ } else {
+ int cur_len;
+
+ /* we don't require exact number of pages, so we're going to go
+ * for best-effort allocation. that means finding the biggest
+ * unused block, and going with that.
+ */
+ cur_idx = rte_fbarray_find_biggest_free(
+ &cur_msl->memseg_arr, 0);
+ if (cur_idx < 0)
+ return 0;
+ start_idx = cur_idx;
+ /* adjust the size to possibly be smaller than original
+ * request, but do not allow it to be bigger.
+ */
+ cur_len = rte_fbarray_find_contig_free(
+ &cur_msl->memseg_arr, cur_idx);
+ need = RTE_MIN(need, (unsigned int)cur_len);
+ }
+
+ for (i = 0; i < need; i++, cur_idx++) {
+ struct rte_memseg *cur;
+ void *map_addr;
+
+ cur = rte_fbarray_get(&cur_msl->memseg_arr, cur_idx);
+ map_addr = RTE_PTR_ADD(cur_msl->base_va, cur_idx * page_sz);
+
+ if (alloc_seg(cur, map_addr, wa->socket, wa->hi)) {
+ RTE_LOG(DEBUG, EAL, "attempted to allocate %i segments, "
+ "but only %i were allocated\n", need, i);
+
+ /* if exact number wasn't requested, stop */
+ if (!wa->exact)
+ goto out;
+
+ /* clean up */
+ for (j = start_idx; j < cur_idx; j++) {
+ struct rte_memseg *tmp;
+ struct rte_fbarray *arr = &cur_msl->memseg_arr;
+
+ tmp = rte_fbarray_get(arr, j);
+ rte_fbarray_set_free(arr, j);
+
+ if (free_seg(tmp))
+ RTE_LOG(DEBUG, EAL, "Cannot free page\n");
+ }
+ /* clear the list */
+ if (wa->ms)
+ memset(wa->ms, 0, sizeof(*wa->ms) * wa->n_segs);
+
+ return -1;
+ }
+ if (wa->ms)
+ wa->ms[i] = cur;
+
+ rte_fbarray_set_used(&cur_msl->memseg_arr, cur_idx);
+ }
+
+out:
+ wa->segs_allocated = i;
+ if (i > 0)
+ cur_msl->version++;
+
+ /* if we didn't allocate any segments, move on to the next list */
+ return i > 0;
+}
+
+struct free_walk_param {
+ struct hugepage_info *hi;
+ struct rte_memseg *ms;
+};
+static int
+free_seg_walk(const struct rte_memseg_list *msl, void *arg)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct rte_memseg_list *found_msl;
+ struct free_walk_param *wa = arg;
+ uintptr_t start_addr, end_addr;
+ int msl_idx, seg_idx, ret;
+
+ start_addr = (uintptr_t) msl->base_va;
+ end_addr = start_addr + msl->len;
+
+ if ((uintptr_t)wa->ms->addr < start_addr ||
+ (uintptr_t)wa->ms->addr >= end_addr)
+ return 0;
+
+ msl_idx = msl - mcfg->memsegs;
+ seg_idx = RTE_PTR_DIFF(wa->ms->addr, start_addr) / msl->page_sz;
+
+ /* msl is const */
+ found_msl = &mcfg->memsegs[msl_idx];
+ found_msl->version++;
+
+ rte_fbarray_set_free(&found_msl->memseg_arr, seg_idx);
+
+ ret = free_seg(wa->ms);
+
+ return (ret < 0) ? (-1) : 1;
+}
+
+int
+eal_memalloc_alloc_seg_bulk(struct rte_memseg **ms, int n_segs,
+ size_t page_sz, int socket, bool exact)
+{
+ unsigned int i;
+ int ret = -1;
+ struct alloc_walk_param wa;
+ struct hugepage_info *hi = NULL;
+
+ if (internal_config.legacy_mem) {
+ RTE_LOG(ERR, EAL, "dynamic allocation not supported in legacy mode\n");
+ return -ENOTSUP;
+ }
+
+ for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
+ struct hugepage_info *hpi = &internal_config.hugepage_info[i];
+ if (page_sz == hpi->hugepage_sz) {
+ hi = hpi;
+ break;
+ }
+ }
+ if (!hi) {
+ RTE_LOG(ERR, EAL, "cannot find relevant hugepage_info entry\n");
+ return -1;
+ }
+
+ memset(&wa, 0, sizeof(wa));
+ wa.exact = exact;
+ wa.hi = hi;
+ wa.ms = ms;
+ wa.n_segs = n_segs;
+ wa.page_sz = page_sz;
+ wa.socket = socket;
+ wa.segs_allocated = 0;
+
+ /* memalloc is locked, so it's safe to use thread-unsafe version */
+ ret = rte_memseg_list_walk_thread_unsafe(alloc_seg_walk, &wa);
+ if (ret == 0) {
+ RTE_LOG(ERR, EAL, "cannot find suitable memseg_list\n");
+ ret = -1;
+ } else if (ret > 0) {
+ ret = (int)wa.segs_allocated;
+ }
+
+ return ret;
+}
+
+struct rte_memseg *
+eal_memalloc_alloc_seg(size_t page_sz, int socket)
+{
+ struct rte_memseg *ms = NULL;
+ eal_memalloc_alloc_seg_bulk(&ms, 1, page_sz, socket, true);
+ return ms;
+}
+
+int
+eal_memalloc_free_seg_bulk(struct rte_memseg **ms, int n_segs)
+{
+ int seg, ret = 0;
+
+ /* dynamic free not supported in legacy mode */
+ if (internal_config.legacy_mem)
+ return -1;
+
+ for (seg = 0; seg < n_segs; seg++) {
+ struct rte_memseg *cur = ms[seg];
+ struct hugepage_info *hi = NULL;
+ struct free_walk_param wa;
+ size_t i;
+ int walk_res;
+
+ /* if this page is marked as unfreeable, fail */
+ if (cur->flags & RTE_MEMSEG_FLAG_DO_NOT_FREE) {
+ RTE_LOG(DEBUG, EAL, "Page is not allowed to be freed\n");
+ ret = -1;
+ continue;
+ }
+
+ memset(&wa, 0, sizeof(wa));
+
+ for (i = 0; i < RTE_DIM(internal_config.hugepage_info);
+ i++) {
+ hi = &internal_config.hugepage_info[i];
+ if (cur->hugepage_sz == hi->hugepage_sz)
+ break;
+ }
+ if (i == RTE_DIM(internal_config.hugepage_info)) {
+ RTE_LOG(ERR, EAL, "Can't find relevant hugepage_info entry\n");
+ ret = -1;
+ continue;
+ }
+
+ wa.ms = cur;
+ wa.hi = hi;
+
+ /* memalloc is locked, so it's safe to use thread-unsafe version
+ */
+ walk_res = rte_memseg_list_walk_thread_unsafe(free_seg_walk,
+ &wa);
+ if (walk_res == 1)
+ continue;
+ if (walk_res == 0)
+ RTE_LOG(ERR, EAL, "Couldn't find memseg list\n");
+ ret = -1;
+ }
+ return ret;
+}
+
+int
+eal_memalloc_free_seg(struct rte_memseg *ms)
+{
+ return eal_memalloc_free_seg_bulk(&ms, 1);
+}
+
+int
+eal_memalloc_sync_with_primary(void)
+{
+ /* No multi-process support. */
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+eal_memalloc_init(void)
+{
+ /* No action required. */
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_memory.c b/lib/librte_eal/windows/eal_memory.c
index 5697187ce..82f3dafe6 100644
--- a/lib/librte_eal/windows/eal_memory.c
+++ b/lib/librte_eal/windows/eal_memory.c
@@ -1,11 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2010-2014 Intel Corporation (functions from Linux EAL)
+ * Copyright (c) 2020 Dmitry Kozlyuk (Windows specifics)
+ */
+
+#include <inttypes.h>
#include <io.h>
#include <rte_errno.h>
#include <rte_memory.h>
+#include "eal_internal_cfg.h"
+#include "eal_memalloc.h"
+#include "eal_memcfg.h"
+#include "eal_options.h"
#include "eal_private.h"
#include "eal_windows.h"
+#include <rte_virt2phys.h>
+
/* MinGW-w64 headers lack VirtualAlloc2() in some distributions.
* Provide a copy of definitions and code to load it dynamically.
* Note: definitions are copied verbatim from Microsoft documentation
@@ -120,6 +132,119 @@ eal_mem_win32api_init(void)
#endif /* no VirtualAlloc2() */
+static HANDLE virt2phys_device = INVALID_HANDLE_VALUE;
+
+int
+eal_mem_virt2iova_init(void)
+{
+ HDEVINFO list = INVALID_HANDLE_VALUE;
+ SP_DEVICE_INTERFACE_DATA ifdata;
+ SP_DEVICE_INTERFACE_DETAIL_DATA *detail = NULL;
+ DWORD detail_size;
+ int ret = -1;
+
+ list = SetupDiGetClassDevs(
+ &GUID_DEVINTERFACE_VIRT2PHYS, NULL, NULL,
+ DIGCF_DEVICEINTERFACE | DIGCF_PRESENT);
+ if (list == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("SetupDiGetClassDevs()");
+ goto exit;
+ }
+
+ ifdata.cbSize = sizeof(ifdata);
+ if (!SetupDiEnumDeviceInterfaces(
+ list, NULL, &GUID_DEVINTERFACE_VIRT2PHYS, 0, &ifdata)) {
+ RTE_LOG_WIN32_ERR("SetupDiEnumDeviceInterfaces()");
+ goto exit;
+ }
+
+ if (!SetupDiGetDeviceInterfaceDetail(
+ list, &ifdata, NULL, 0, &detail_size, NULL)) {
+ if (GetLastError() != ERROR_INSUFFICIENT_BUFFER) {
+ RTE_LOG_WIN32_ERR(
+ "SetupDiGetDeviceInterfaceDetail(probe)");
+ goto exit;
+ }
+ }
+
+ detail = malloc(detail_size);
+ if (detail == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate virt2phys "
+ "device interface detail data\n");
+ goto exit;
+ }
+
+ detail->cbSize = sizeof(*detail);
+ if (!SetupDiGetDeviceInterfaceDetail(
+ list, &ifdata, detail, detail_size, NULL, NULL)) {
+ RTE_LOG_WIN32_ERR("SetupDiGetDeviceInterfaceDetail(read)");
+ goto exit;
+ }
+
+ RTE_LOG(DEBUG, EAL, "Found virt2phys device: %s\n", detail->DevicePath);
+
+ virt2phys_device = CreateFile(
+ detail->DevicePath, 0, 0, NULL, OPEN_EXISTING, 0, NULL);
+ if (virt2phys_device == INVALID_HANDLE_VALUE) {
+ RTE_LOG_WIN32_ERR("CreateFile()");
+ goto exit;
+ }
+
+ /* Indicate success. */
+ ret = 0;
+
+exit:
+ if (detail != NULL)
+ free(detail);
+ if (list != INVALID_HANDLE_VALUE)
+ SetupDiDestroyDeviceInfoList(list);
+
+ return ret;
+}
+
+phys_addr_t
+rte_mem_virt2phy(const void *virt)
+{
+ LARGE_INTEGER phys;
+ DWORD bytes_returned;
+
+ if (virt2phys_device == INVALID_HANDLE_VALUE)
+ return RTE_BAD_PHYS_ADDR;
+
+ if (!DeviceIoControl(
+ virt2phys_device, IOCTL_VIRT2PHYS_TRANSLATE,
+ &virt, sizeof(virt), &phys, sizeof(phys),
+ &bytes_returned, NULL)) {
+ RTE_LOG_WIN32_ERR("DeviceIoControl(IOCTL_VIRT2PHYS_TRANSLATE)");
+ return RTE_BAD_PHYS_ADDR;
+ }
+
+ return phys.QuadPart;
+}
+
+/* Windows currently only supports IOVA as PA. */
+rte_iova_t
+rte_mem_virt2iova(const void *virt)
+{
+ phys_addr_t phys;
+
+ if (virt2phys_device == INVALID_HANDLE_VALUE)
+ return RTE_BAD_IOVA;
+
+ phys = rte_mem_virt2phy(virt);
+ if (phys == RTE_BAD_PHYS_ADDR)
+ return RTE_BAD_IOVA;
+
+ return (rte_iova_t)phys;
+}
+
+/* Always using physical addresses under Windows if they can be obtained. */
+int
+rte_eal_using_phys_addrs(void)
+{
+ return virt2phys_device != INVALID_HANDLE_VALUE;
+}
+
/* Approximate error mapping from VirtualAlloc2() to POSIX mmap(3). */
static void
set_errno_from_win32_alloc_error(DWORD code)
@@ -253,6 +378,10 @@ eal_mem_commit(void *requested_addr, size_t size, int socket_id)
int
eal_mem_decommit(void *addr, size_t size)
{
+ /* Decommit memory, which might be a part of a larger reserved region.
+ * Allocator commits hugepage-sized placeholders, so there's no need
+ * to coalesce placeholders back into region, they can be reused as is.
+ */
if (!VirtualFree(addr, size, MEM_RELEASE | MEM_PRESERVE_PLACEHOLDER)) {
RTE_LOG_WIN32_ERR("VirtualFree(%p, %zu, ...)", addr, size);
return -1;
@@ -364,7 +493,7 @@ rte_mem_map(void *requested_addr, size_t size, enum rte_mem_prot prot,
return NULL;
}
- /* TODO: there is a race for the requested_addr between mem_free()
+ /* There is a race for the requested_addr between mem_free()
* and MapViewOfFileEx(). MapViewOfFile3() that can replace a reserved
* region with a mapping in a single operation, but it does not support
* private mappings.
@@ -414,6 +543,16 @@ rte_mem_unmap(void *virt, size_t size)
return 0;
}
+uint64_t
+eal_get_baseaddr(void)
+{
+ /* Windows strategy for memory allocation is undocumented.
+ * Returning 0 here effectively disables address guessing
+ * unless user provides an address hint.
+ */
+ return 0;
+}
+
int
rte_get_page_size(void)
{
@@ -435,3 +574,568 @@ rte_mem_lock(const void *virt, size_t size)
return 0;
}
+
+static int
+memseg_list_alloc(struct rte_memseg_list *msl, uint64_t page_sz,
+ int n_segs, int socket_id, int type_msl_idx)
+{
+ return eal_alloc_memseg_list(
+ msl, page_sz, n_segs, socket_id, type_msl_idx, true);
+}
+
+static int
+memseg_list_reserve(struct rte_memseg_list *msl)
+{
+ return eal_reserve_memseg_list(msl, 0);
+}
+
+/*
+ * Remaining code in this file largely duplicates Linux EAL.
+ * Although Windows EAL supports only one hugepage size currently,
+ * code structure and comments are preserved so that changes may be
+ * easily ported until duplication is removed.
+ */
+
+static int
+memseg_primary_init(void)
+{
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config;
+ struct memtype {
+ uint64_t page_sz;
+ int socket_id;
+ } *memtypes = NULL;
+ int i, hpi_idx, msl_idx, ret = -1; /* fail unless told to succeed */
+ struct rte_memseg_list *msl;
+ uint64_t max_mem, max_mem_per_type;
+ unsigned int max_seglists_per_type;
+ unsigned int n_memtypes, cur_type;
+
+ /* no-huge does not need this at all */
+ if (internal_config.no_hugetlbfs)
+ return 0;
+
+ /*
+ * figuring out amount of memory we're going to have is a long and very
+ * involved process. the basic element we're operating with is a memory
+ * type, defined as a combination of NUMA node ID and page size (so that
+ * e.g. 2 sockets with 2 page sizes yield 4 memory types in total).
+ *
+ * deciding amount of memory going towards each memory type is a
+ * balancing act between maximum segments per type, maximum memory per
+ * type, and number of detected NUMA nodes. the goal is to make sure
+ * each memory type gets at least one memseg list.
+ *
+ * the total amount of memory is limited by RTE_MAX_MEM_MB value.
+ *
+ * the total amount of memory per type is limited by either
+ * RTE_MAX_MEM_MB_PER_TYPE, or by RTE_MAX_MEM_MB divided by the number
+ * of detected NUMA nodes. additionally, maximum number of segments per
+ * type is also limited by RTE_MAX_MEMSEG_PER_TYPE. this is because for
+ * smaller page sizes, it can take hundreds of thousands of segments to
+ * reach the above specified per-type memory limits.
+ *
+ * additionally, each type may have multiple memseg lists associated
+ * with it, each limited by either RTE_MAX_MEM_MB_PER_LIST for bigger
+ * page sizes, or RTE_MAX_MEMSEG_PER_LIST segments for smaller ones.
+ *
+ * the number of memseg lists per type is decided based on the above
+ * limits, and also taking number of detected NUMA nodes, to make sure
+ * that we don't run out of memseg lists before we populate all NUMA
+ * nodes with memory.
+ *
+ * we do this in three stages. first, we collect the number of types.
+ * then, we figure out memory constraints and populate the list of
+ * would-be memseg lists. then, we go ahead and allocate the memseg
+ * lists.
+ */
+
+ /* create space for mem types */
+ n_memtypes = internal_config.num_hugepage_sizes * rte_socket_count();
+ memtypes = calloc(n_memtypes, sizeof(*memtypes));
+ if (memtypes == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate space for memory types\n");
+ return -1;
+ }
+
+ /* populate mem types */
+ cur_type = 0;
+ for (hpi_idx = 0; hpi_idx < (int) internal_config.num_hugepage_sizes;
+ hpi_idx++) {
+ struct hugepage_info *hpi;
+ uint64_t hugepage_sz;
+
+ hpi = &internal_config.hugepage_info[hpi_idx];
+ hugepage_sz = hpi->hugepage_sz;
+
+ for (i = 0; i < (int) rte_socket_count(); i++, cur_type++) {
+ int socket_id = rte_socket_id_by_idx(i);
+
+ memtypes[cur_type].page_sz = hugepage_sz;
+ memtypes[cur_type].socket_id = socket_id;
+
+ RTE_LOG(DEBUG, EAL, "Detected memory type: "
+ "socket_id:%u hugepage_sz:%" PRIu64 "\n",
+ socket_id, hugepage_sz);
+ }
+ }
+ /* number of memtypes could have been lower due to no NUMA support */
+ n_memtypes = cur_type;
+
+ /* set up limits for types */
+ max_mem = (uint64_t)RTE_MAX_MEM_MB << 20;
+ max_mem_per_type = RTE_MIN((uint64_t)RTE_MAX_MEM_MB_PER_TYPE << 20,
+ max_mem / n_memtypes);
+
+ /*
+ * limit maximum number of segment lists per type to ensure there's
+ * space for memseg lists for all NUMA nodes with all page sizes
+ */
+ max_seglists_per_type = RTE_MAX_MEMSEG_LISTS / n_memtypes;
+
+ if (max_seglists_per_type == 0) {
+ RTE_LOG(ERR, EAL, "Cannot accommodate all memory types, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ goto out;
+ }
+
+ /* go through all mem types and create segment lists */
+ msl_idx = 0;
+ for (cur_type = 0; cur_type < n_memtypes; cur_type++) {
+ unsigned int cur_seglist, n_seglists, n_segs;
+ unsigned int max_segs_per_type, max_segs_per_list;
+ struct memtype *type = &memtypes[cur_type];
+ uint64_t max_mem_per_list, pagesz;
+ int socket_id;
+
+ pagesz = type->page_sz;
+ socket_id = type->socket_id;
+
+ /*
+ * we need to create segment lists for this type. we must take
+ * into account the following things:
+ *
+ * 1. total amount of memory we can use for this memory type
+ * 2. total amount of memory per memseg list allowed
+ * 3. number of segments needed to fit the amount of memory
+ * 4. number of segments allowed per type
+ * 5. number of segments allowed per memseg list
+ * 6. number of memseg lists we are allowed to take up
+ */
+
+ /* calculate how much segments we will need in total */
+ max_segs_per_type = max_mem_per_type / pagesz;
+ /* limit number of segments to maximum allowed per type */
+ max_segs_per_type = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_TYPE);
+ /* limit number of segments to maximum allowed per list */
+ max_segs_per_list = RTE_MIN(max_segs_per_type,
+ (unsigned int)RTE_MAX_MEMSEG_PER_LIST);
+
+ /* calculate how much memory we can have per segment list */
+ max_mem_per_list = RTE_MIN(max_segs_per_list * pagesz,
+ (uint64_t)RTE_MAX_MEM_MB_PER_LIST << 20);
+
+ /* calculate how many segments each segment list will have */
+ n_segs = RTE_MIN(max_segs_per_list, max_mem_per_list / pagesz);
+
+ /* calculate how many segment lists we can have */
+ n_seglists = RTE_MIN(max_segs_per_type / n_segs,
+ max_mem_per_type / max_mem_per_list);
+
+ /* limit number of segment lists according to our maximum */
+ n_seglists = RTE_MIN(n_seglists, max_seglists_per_type);
+
+ RTE_LOG(DEBUG, EAL, "Creating %i segment lists: "
+ "n_segs:%i socket_id:%i hugepage_sz:%" PRIu64 "\n",
+ n_seglists, n_segs, socket_id, pagesz);
+
+ /* create all segment lists */
+ for (cur_seglist = 0; cur_seglist < n_seglists; cur_seglist++) {
+ if (msl_idx >= RTE_MAX_MEMSEG_LISTS) {
+ RTE_LOG(ERR, EAL,
+ "No more space in memseg lists, please increase %s\n",
+ RTE_STR(CONFIG_RTE_MAX_MEMSEG_LISTS));
+ goto out;
+ }
+ msl = &mcfg->memsegs[msl_idx++];
+
+ if (memseg_list_alloc(msl, pagesz, n_segs,
+ socket_id, cur_seglist))
+ goto out;
+
+ if (memseg_list_reserve(msl)) {
+ RTE_LOG(ERR, EAL, "Cannot allocate VA space for memseg list\n");
+ goto out;
+ }
+ }
+ }
+ /* we're successful */
+ ret = 0;
+out:
+ free(memtypes);
+ return ret;
+}
+
+static int
+memseg_secondary_init(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_eal_memseg_init(void)
+{
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ return memseg_primary_init();
+ return memseg_secondary_init();
+}
+
+static inline uint64_t
+get_socket_mem_size(int socket)
+{
+ uint64_t size = 0;
+ unsigned int i;
+
+ for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
+ struct hugepage_info *hpi = &internal_config.hugepage_info[i];
+ size += hpi->hugepage_sz * hpi->num_pages[socket];
+ }
+
+ return size;
+}
+
+static int
+calc_num_pages_per_socket(uint64_t *memory,
+ struct hugepage_info *hp_info,
+ struct hugepage_info *hp_used,
+ unsigned int num_hp_info)
+{
+ unsigned int socket, j, i = 0;
+ unsigned int requested, available;
+ int total_num_pages = 0;
+ uint64_t remaining_mem, cur_mem;
+ uint64_t total_mem = internal_config.memory;
+
+ if (num_hp_info == 0)
+ return -1;
+
+ /* if specific memory amounts per socket weren't requested */
+ if (internal_config.force_sockets == 0) {
+ size_t total_size;
+ int cpu_per_socket[RTE_MAX_NUMA_NODES];
+ size_t default_size;
+ unsigned int lcore_id;
+
+ /* Compute number of cores per socket */
+ memset(cpu_per_socket, 0, sizeof(cpu_per_socket));
+ RTE_LCORE_FOREACH(lcore_id) {
+ cpu_per_socket[rte_lcore_to_socket_id(lcore_id)]++;
+ }
+
+ /*
+ * Automatically spread requested memory amongst detected
+ * sockets according to number of cores from cpu mask present
+ * on each socket.
+ */
+ total_size = internal_config.memory;
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
+ socket++) {
+
+ /* Set memory amount per socket */
+ default_size = internal_config.memory *
+ cpu_per_socket[socket] / rte_lcore_count();
+
+ /* Limit to maximum available memory on socket */
+ default_size = RTE_MIN(
+ default_size, get_socket_mem_size(socket));
+
+ /* Update sizes */
+ memory[socket] = default_size;
+ total_size -= default_size;
+ }
+
+ /*
+ * If some memory is remaining, try to allocate it by getting
+ * all available memory from sockets, one after the other.
+ */
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_size != 0;
+ socket++) {
+ /* take whatever is available */
+ default_size = RTE_MIN(
+ get_socket_mem_size(socket) - memory[socket],
+ total_size);
+
+ /* Update sizes */
+ memory[socket] += default_size;
+ total_size -= default_size;
+ }
+ }
+
+ for (socket = 0; socket < RTE_MAX_NUMA_NODES && total_mem != 0;
+ socket++) {
+ /* skips if the memory on specific socket wasn't requested */
+ for (i = 0; i < num_hp_info && memory[socket] != 0; i++) {
+ strncpy(hp_used[i].hugedir, hp_info[i].hugedir,
+ sizeof(hp_used[i].hugedir));
+ hp_used[i].num_pages[socket] = RTE_MIN(
+ memory[socket] / hp_info[i].hugepage_sz,
+ hp_info[i].num_pages[socket]);
+
+ cur_mem = hp_used[i].num_pages[socket] *
+ hp_used[i].hugepage_sz;
+
+ memory[socket] -= cur_mem;
+ total_mem -= cur_mem;
+
+ total_num_pages += hp_used[i].num_pages[socket];
+
+ /* check if we have met all memory requests */
+ if (memory[socket] == 0)
+ break;
+
+ /* Check if we have any more pages left at this size,
+ * if so, move on to next size.
+ */
+ if (hp_used[i].num_pages[socket] ==
+ hp_info[i].num_pages[socket])
+ continue;
+
+ /* At this point we know that there are more pages
+ * available that are bigger than the memory we want,
+ * so lets see if we can get enough from other page
+ * sizes.
+ */
+ remaining_mem = 0;
+ for (j = i+1; j < num_hp_info; j++)
+ remaining_mem += hp_info[j].hugepage_sz *
+ hp_info[j].num_pages[socket];
+
+ /* Is there enough other memory?
+ * If not, allocate another page and quit.
+ */
+ if (remaining_mem < memory[socket]) {
+ cur_mem = RTE_MIN(
+ memory[socket], hp_info[i].hugepage_sz);
+ memory[socket] -= cur_mem;
+ total_mem -= cur_mem;
+ hp_used[i].num_pages[socket]++;
+ total_num_pages++;
+ break; /* we are done with this socket*/
+ }
+ }
+ /* if we didn't satisfy all memory requirements per socket */
+ if (memory[socket] > 0 &&
+ internal_config.socket_mem[socket] != 0) {
+ /* to prevent icc errors */
+ requested = (unsigned int)(
+ internal_config.socket_mem[socket] / 0x100000);
+ available = requested -
+ ((unsigned int)(memory[socket] / 0x100000));
+ RTE_LOG(ERR, EAL, "Not enough memory available on "
+ "socket %u! Requested: %uMB, available: %uMB\n",
+ socket, requested, available);
+ return -1;
+ }
+ }
+
+ /* if we didn't satisfy total memory requirements */
+ if (total_mem > 0) {
+ requested = (unsigned int) (internal_config.memory / 0x100000);
+ available = requested - (unsigned int) (total_mem / 0x100000);
+ RTE_LOG(ERR, EAL, "Not enough memory available! "
+ "Requested: %uMB, available: %uMB\n",
+ requested, available);
+ return -1;
+ }
+ return total_num_pages;
+}
+
+/* Limit is checked by validator itself, nothing left to analyze.*/
+static int
+limits_callback(int socket_id, size_t cur_limit, size_t new_len)
+{
+ RTE_SET_USED(socket_id);
+ RTE_SET_USED(cur_limit);
+ RTE_SET_USED(new_len);
+ return -1;
+}
+
+static int
+eal_hugepage_init(void)
+{
+ struct hugepage_info used_hp[MAX_HUGEPAGE_SIZES];
+ uint64_t memory[RTE_MAX_NUMA_NODES];
+ int hp_sz_idx, socket_id;
+
+ memset(used_hp, 0, sizeof(used_hp));
+
+ for (hp_sz_idx = 0;
+ hp_sz_idx < (int) internal_config.num_hugepage_sizes;
+ hp_sz_idx++) {
+ /* also initialize used_hp hugepage sizes in used_hp */
+ struct hugepage_info *hpi;
+ hpi = &internal_config.hugepage_info[hp_sz_idx];
+ used_hp[hp_sz_idx].hugepage_sz = hpi->hugepage_sz;
+ }
+
+ /* make a copy of socket_mem, needed for balanced allocation. */
+ for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES; socket_id++)
+ memory[socket_id] = internal_config.socket_mem[socket_id];
+
+ /* calculate final number of pages */
+ if (calc_num_pages_per_socket(memory,
+ internal_config.hugepage_info, used_hp,
+ internal_config.num_hugepage_sizes) < 0)
+ return -1;
+
+ for (hp_sz_idx = 0;
+ hp_sz_idx < (int)internal_config.num_hugepage_sizes;
+ hp_sz_idx++) {
+ for (socket_id = 0; socket_id < RTE_MAX_NUMA_NODES;
+ socket_id++) {
+ struct rte_memseg **pages;
+ struct hugepage_info *hpi = &used_hp[hp_sz_idx];
+ unsigned int num_pages = hpi->num_pages[socket_id];
+ unsigned int num_pages_alloc;
+
+ if (num_pages == 0)
+ continue;
+
+ RTE_LOG(DEBUG, EAL,
+ "Allocating %u pages of size %" PRIu64 "M on socket %i\n",
+ num_pages, hpi->hugepage_sz >> 20, socket_id);
+
+ /* we may not be able to allocate all pages in one go,
+ * because we break up our memory map into multiple
+ * memseg lists. therefore, try allocating multiple
+ * times and see if we can get the desired number of
+ * pages from multiple allocations.
+ */
+
+ num_pages_alloc = 0;
+ do {
+ int i, cur_pages, needed;
+
+ needed = num_pages - num_pages_alloc;
+
+ pages = malloc(sizeof(*pages) * needed);
+
+ /* do not request exact number of pages */
+ cur_pages = eal_memalloc_alloc_seg_bulk(pages,
+ needed, hpi->hugepage_sz,
+ socket_id, false);
+ if (cur_pages <= 0) {
+ free(pages);
+ return -1;
+ }
+
+ /* mark preallocated pages as unfreeable */
+ for (i = 0; i < cur_pages; i++) {
+ struct rte_memseg *ms = pages[i];
+ ms->flags |=
+ RTE_MEMSEG_FLAG_DO_NOT_FREE;
+ }
+ free(pages);
+
+ num_pages_alloc += cur_pages;
+ } while (num_pages_alloc != num_pages);
+ }
+ }
+ /* if socket limits were specified, set them */
+ if (internal_config.force_socket_limits) {
+ unsigned int i;
+ for (i = 0; i < RTE_MAX_NUMA_NODES; i++) {
+ uint64_t limit = internal_config.socket_limit[i];
+ if (limit == 0)
+ continue;
+ if (rte_mem_alloc_validator_register("socket-limit",
+ limits_callback, i, limit))
+ RTE_LOG(ERR, EAL, "Failed to register socket "
+ "limits validator callback\n");
+ }
+ }
+ return 0;
+}
+
+static int
+eal_nohuge_init(void)
+{
+ struct rte_mem_config *mcfg;
+ struct rte_memseg_list *msl;
+ int n_segs, cur_seg;
+ uint64_t page_sz;
+ void *addr;
+ struct rte_fbarray *arr;
+ struct rte_memseg *ms;
+
+ mcfg = rte_eal_get_configuration()->mem_config;
+
+ /* nohuge mode is legacy mode */
+ internal_config.legacy_mem = 1;
+
+ /* create a memseg list */
+ msl = &mcfg->memsegs[0];
+
+ page_sz = RTE_PGSIZE_4K;
+ n_segs = internal_config.memory / page_sz;
+
+ if (rte_fbarray_init(&msl->memseg_arr, "nohugemem", n_segs,
+ sizeof(struct rte_memseg))) {
+ RTE_LOG(ERR, EAL, "Cannot allocate memseg list\n");
+ return -1;
+ }
+
+ addr = eal_mem_alloc(internal_config.memory, 0);
+ if (addr == NULL) {
+ RTE_LOG(ERR, EAL, "Cannot allocate %zu bytes",
+ internal_config.memory);
+ return -1;
+ }
+
+ msl->base_va = addr;
+ msl->page_sz = page_sz;
+ msl->socket_id = 0;
+ msl->len = internal_config.memory;
+ msl->heap = 1;
+
+ /* populate memsegs. each memseg is one page long */
+ for (cur_seg = 0; cur_seg < n_segs; cur_seg++) {
+ arr = &msl->memseg_arr;
+
+ ms = rte_fbarray_get(arr, cur_seg);
+ ms->iova = RTE_BAD_IOVA;
+ ms->addr = addr;
+ ms->hugepage_sz = page_sz;
+ ms->socket_id = 0;
+ ms->len = page_sz;
+
+ rte_fbarray_set_used(arr, cur_seg);
+
+ addr = RTE_PTR_ADD(addr, (size_t)page_sz);
+ }
+
+ if (mcfg->dma_maskbits &&
+ rte_mem_check_dma_mask_thread_unsafe(mcfg->dma_maskbits)) {
+ RTE_LOG(ERR, EAL,
+ "%s(): couldn't allocate memory due to IOVA "
+ "exceeding limits of current DMA mask.\n", __func__);
+ return -1;
+ }
+
+ return 0;
+}
+
+int
+rte_eal_hugepage_init(void)
+{
+ return internal_config.no_hugetlbfs ?
+ eal_nohuge_init() : eal_hugepage_init();
+}
+
+int
+rte_eal_hugepage_attach(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
diff --git a/lib/librte_eal/windows/eal_mp.c b/lib/librte_eal/windows/eal_mp.c
new file mode 100644
index 000000000..16a5e8ba0
--- /dev/null
+++ b/lib/librte_eal/windows/eal_mp.c
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file Multiprocess support stubs
+ *
+ * Stubs must log an error until implemented. If success is required
+ * for non-multiprocess operation, stub must log a warning and a comment
+ * must document what requires success emulation.
+ */
+
+#include <rte_eal.h>
+#include <rte_errno.h>
+
+#include "eal_private.h"
+#include "eal_windows.h"
+#include "malloc_mp.h"
+
+void
+rte_mp_channel_cleanup(void)
+{
+ EAL_LOG_NOT_IMPLEMENTED();
+}
+
+int
+rte_mp_action_register(const char *name, rte_mp_t action)
+{
+ RTE_SET_USED(name);
+ RTE_SET_USED(action);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+void
+rte_mp_action_unregister(const char *name)
+{
+ RTE_SET_USED(name);
+ EAL_LOG_NOT_IMPLEMENTED();
+}
+
+int
+rte_mp_sendmsg(struct rte_mp_msg *msg)
+{
+ RTE_SET_USED(msg);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
+ const struct timespec *ts)
+{
+ RTE_SET_USED(req);
+ RTE_SET_USED(reply);
+ RTE_SET_USED(ts);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
+ rte_mp_async_reply_t clb)
+{
+ RTE_SET_USED(req);
+ RTE_SET_USED(ts);
+ RTE_SET_USED(clb);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
+{
+ RTE_SET_USED(msg);
+ RTE_SET_USED(peer);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+register_mp_requests(void)
+{
+ /* Non-stub function succeeds if multi-process is not supported. */
+ EAL_LOG_STUB();
+ return 0;
+}
+
+int
+request_to_primary(struct malloc_mp_req *req)
+{
+ RTE_SET_USED(req);
+ EAL_LOG_NOT_IMPLEMENTED();
+ return -1;
+}
+
+int
+request_sync(void)
+{
+ /* Common memory allocator depends on this function success. */
+ EAL_LOG_STUB();
+ return 0;
+}
diff --git a/lib/librte_eal/windows/eal_windows.h b/lib/librte_eal/windows/eal_windows.h
index b202a1aa5..083ab8b93 100644
--- a/lib/librte_eal/windows/eal_windows.h
+++ b/lib/librte_eal/windows/eal_windows.h
@@ -9,8 +9,24 @@
* @file Facilities private to Windows EAL
*/
+#include <rte_errno.h>
#include <rte_windows.h>
+/**
+ * Log current function as not implemented and set rte_errno.
+ */
+#define EAL_LOG_NOT_IMPLEMENTED() \
+ do { \
+ RTE_LOG(DEBUG, EAL, "%s() is not implemented\n", __func__); \
+ rte_errno = ENOTSUP; \
+ } while (0)
+
+/**
+ * Log current function as a stub.
+ */
+#define EAL_LOG_STUB() \
+ RTE_LOG(DEBUG, EAL, "Windows: %s() is a stub\n", __func__)
+
/**
* Create a map of processors and cores on the system.
*/
@@ -36,6 +52,13 @@ int eal_thread_create(pthread_t *thread);
*/
unsigned int eal_socket_numa_node(unsigned int socket_id);
+/**
+ * Open virt2phys driver interface device.
+ *
+ * @return 0 on success, (-1) on failure.
+ */
+int eal_mem_virt2iova_init(void);
+
/**
* Locate Win32 memory management routines in system libraries.
*
diff --git a/lib/librte_eal/windows/include/meson.build b/lib/librte_eal/windows/include/meson.build
index 5fb1962ac..b3534b025 100644
--- a/lib/librte_eal/windows/include/meson.build
+++ b/lib/librte_eal/windows/include/meson.build
@@ -5,5 +5,6 @@ includes += include_directories('.')
headers += files(
'rte_os.h',
+ 'rte_virt2phys.h',
'rte_windows.h',
)
diff --git a/lib/librte_eal/windows/include/rte_os.h b/lib/librte_eal/windows/include/rte_os.h
index 510e39e03..62805a307 100644
--- a/lib/librte_eal/windows/include/rte_os.h
+++ b/lib/librte_eal/windows/include/rte_os.h
@@ -36,6 +36,10 @@ extern "C" {
#define strncasecmp(s1, s2, count) _strnicmp(s1, s2, count)
+#define open _open
+#define close _close
+#define unlink _unlink
+
/* cpu_set macros implementation */
#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
#define RTE_CPU_OR(dst, src1, src2) CPU_OR(dst, src1, src2)
diff --git a/lib/librte_eal/windows/include/rte_virt2phys.h b/lib/librte_eal/windows/include/rte_virt2phys.h
new file mode 100644
index 000000000..4bb2b4aaf
--- /dev/null
+++ b/lib/librte_eal/windows/include/rte_virt2phys.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2020 Dmitry Kozlyuk
+ */
+
+/**
+ * @file virt2phys driver interface
+ */
+
+/**
+ * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
+ */
+DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
+ 0x539c2135, 0x793a, 0x4926,
+ 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
+
+/**
+ * Driver device type for IO control codes.
+ */
+#define VIRT2PHYS_DEVTYPE 0x8000
+
+/**
+ * Translate a valid non-paged virtual address to a physical address.
+ *
+ * Note: A physical address zero (0) is reported if input address
+ * is paged out or not mapped. However, if input is a valid mapping
+ * of I/O port 0x0000, output is also zero. There is no way
+ * to distinguish between these cases by return value only.
+ *
+ * Input: a non-paged virtual address (PVOID).
+ *
+ * Output: the corresponding physical address (LARGE_INTEGER).
+ */
+#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
+ VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
diff --git a/lib/librte_eal/windows/include/rte_windows.h b/lib/librte_eal/windows/include/rte_windows.h
index ed6e4c148..899ed7d87 100644
--- a/lib/librte_eal/windows/include/rte_windows.h
+++ b/lib/librte_eal/windows/include/rte_windows.h
@@ -23,6 +23,8 @@
#include <basetsd.h>
#include <psapi.h>
+#include <setupapi.h>
+#include <winioctl.h>
/* Have GUIDs defined. */
#ifndef INITGUID
diff --git a/lib/librte_eal/windows/include/unistd.h b/lib/librte_eal/windows/include/unistd.h
index 757b7f3c5..6b33005b2 100644
--- a/lib/librte_eal/windows/include/unistd.h
+++ b/lib/librte_eal/windows/include/unistd.h
@@ -9,4 +9,7 @@
* as Microsoft libc does not contain unistd.h. This may be removed
* in future releases.
*/
+
+#include <io.h>
+
#endif /* _UNISTD_H_ */
diff --git a/lib/librte_eal/windows/meson.build b/lib/librte_eal/windows/meson.build
index 81d3ee095..0bd56cd8f 100644
--- a/lib/librte_eal/windows/meson.build
+++ b/lib/librte_eal/windows/meson.build
@@ -8,7 +8,11 @@ sources += files(
'eal_debug.c',
'eal_hugepages.c',
'eal_lcore.c',
+ 'eal_memalloc.c',
'eal_memory.c',
+ 'eal_mp.c',
'eal_thread.c',
'getopt.c',
)
+
+dpdk_conf.set10('RTE_EAL_NUMA_AWARE_HUGEPAGES', true)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
@ 2020-04-15 9:42 ` Jerin Jacob
2020-04-16 18:34 ` Ranjit Menon
1 sibling, 0 replies; 218+ messages in thread
From: Jerin Jacob @ 2020-04-15 9:42 UTC (permalink / raw)
To: Dmitry Kozlyuk
Cc: dpdk-dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona,
Pallavi Kadam, Ranjit Menon, John McNamara, Marko Kovacevic,
Anatoly Burakov, Bruce Richardson
On Wed, Apr 15, 2020 at 1:16 AM Dmitry Kozlyuk <dmitry.kozliuk@gmail.com> wrote:
>
> Basic memory management supports core libraries and PMDs operating in
> IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
> IOVAs of hugepages allocated from user-mode.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
> config/meson.build | 2 +-
> doc/guides/windows_gsg/run_apps.rst | 43 +-
> lib/librte_eal/common/eal_common_fbarray.c | 57 +-
> lib/librte_eal/common/eal_common_memory.c | 50 +-
> lib/librte_eal/common/eal_private.h | 6 +-
> lib/librte_eal/common/malloc_heap.c | 1 +
> lib/librte_eal/common/meson.build | 9 +
IMO, We should split the lib/librte_eal/common/e and
ib/librte_eal/windows/ as separate
patch for better review and align the patch title accordingly.
> lib/librte_eal/freebsd/eal_memory.c | 1 -
> lib/librte_eal/rte_eal_exports.def | 119 ++-
> lib/librte_eal/windows/eal.c | 55 ++
> lib/librte_eal/windows/eal_memalloc.c | 418 +++++++++++
> lib/librte_eal/windows/eal_memory.c | 706 +++++++++++++++++-
> lib/librte_eal/windows/eal_mp.c | 103 +++
> lib/librte_eal/windows/eal_windows.h | 23 +
> lib/librte_eal/windows/include/meson.build | 1 +
> lib/librte_eal/windows/include/rte_os.h | 4 +
> .../windows/include/rte_virt2phys.h | 34 +
> lib/librte_eal/windows/include/rte_windows.h | 2 +
> lib/librte_eal/windows/include/unistd.h | 3 +
> lib/librte_eal/windows/meson.build | 4 +
> 20 files changed, 1571 insertions(+), 70 deletions(-)
> create mode 100644 lib/librte_eal/windows/eal_memalloc.c
> create mode 100644 lib/librte_eal/windows/eal_mp.c
> create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
2020-04-15 9:42 ` Jerin Jacob
@ 2020-04-16 18:34 ` Ranjit Menon
2020-04-23 1:00 ` Dmitry Kozlyuk
1 sibling, 1 reply; 218+ messages in thread
From: Ranjit Menon @ 2020-04-16 18:34 UTC (permalink / raw)
To: Dmitry Kozlyuk, dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona, Kadam,
Pallavi, Mcnamara, John, Kovacevic, Marko, Burakov, Anatoly,
Richardson, Bruce
On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> Basic memory management supports core libraries and PMDs operating in
> IOVA as PA mode. It uses a kernel-mode driver, virt2phys, to obtain
> IOVAs of hugepages allocated from user-mode.
>
> Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
> ---
<Snip!>
> diff --git a/lib/librte_eal/windows/include/rte_virt2phys.h b/lib/librte_eal/windows/include/rte_virt2phys.h
> new file mode 100644
> index 000000000..4bb2b4aaf
> --- /dev/null
> +++ b/lib/librte_eal/windows/include/rte_virt2phys.h
> @@ -0,0 +1,34 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright (c) 2020 Dmitry Kozlyuk
> + */
> +
> +/**
> + * @file virt2phys driver interface
> + */
> +
> +/**
> + * Driver device interface GUID {539c2135-793a-4926-afec-d3a1b61bbc8a}.
> + */
> +DEFINE_GUID(GUID_DEVINTERFACE_VIRT2PHYS,
> + 0x539c2135, 0x793a, 0x4926,
> + 0xaf, 0xec, 0xd3, 0xa1, 0xb6, 0x1b, 0xbc, 0x8a);
> +
> +/**
> + * Driver device type for IO control codes.
> + */
> +#define VIRT2PHYS_DEVTYPE 0x8000
> +
> +/**
> + * Translate a valid non-paged virtual address to a physical address.
> + *
> + * Note: A physical address zero (0) is reported if input address
> + * is paged out or not mapped. However, if input is a valid mapping
> + * of I/O port 0x0000, output is also zero. There is no way
> + * to distinguish between these cases by return value only.
> + *
> + * Input: a non-paged virtual address (PVOID).
> + *
> + * Output: the corresponding physical address (LARGE_INTEGER).
> + */
> +#define IOCTL_VIRT2PHYS_TRANSLATE CTL_CODE( \
> + VIRT2PHYS_DEVTYPE, 0x800, METHOD_BUFFERED, FILE_ANY_ACCESS)
This file is a duplicate of: <kmods>: windows/virt2phys/virt2phys.h
This is by design, since it documents the driver interface.
So, to prevent the two files going out-of-sync, should we:
1. Make the two filenames the same?
2. Add comments to both files referencing each other and the need to
keep them both in sync?
3. Do both (1) and (2)?
This will also be an issue for the upcoming Windows netuio kernel driver
and I reckon this could be an issue for Linux kernel modules too.
Thoughts?
ranjit m.
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management
2020-04-16 18:34 ` Ranjit Menon
@ 2020-04-23 1:00 ` Dmitry Kozlyuk
0 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-23 1:00 UTC (permalink / raw)
To: Ranjit Menon
Cc: dev, Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Thomas Monjalon, Harini Ramakrishnan, Omar Cardona, Kadam,
Pallavi, Mcnamara, John, Kovacevic, Marko, Burakov, Anatoly,
Richardson, Bruce
On 2020-04-16 11:34 GMT-0700 Ranjit Menon wrote:
[snip]
> > --- /dev/null
> > +++ b/lib/librte_eal/windows/include/rte_virt2phys.h
[snip]
>
> This file is a duplicate of: <kmods>: windows/virt2phys/virt2phys.h
> This is by design, since it documents the driver interface.
>
> So, to prevent the two files going out-of-sync, should we:
> 1. Make the two filenames the same?
> 2. Add comments to both files referencing each other and the need to
> keep them both in sync?
> 3. Do both (1) and (2)?
>
> This will also be an issue for the upcoming Windows netuio kernel driver
> and I reckon this could be an issue for Linux kernel modules too.
>
> Thoughts?
I guess it won't be much of an issue in practice. When you edit driver
interface you're already considering user-mode and kernel interaction, by
definition of that interface, so you can't forget about the counterpart.
I'd be more worried about ABI, because memory corruption in driver will crash
the system, being hard to debug. Can we leverage abigail for these interfaces?
--
Dmitry Kozlyuk
^ permalink raw reply [flat|nested] 218+ messages in thread
* Re: [dpdk-dev] [PATCH v3 00/10] Windows basic memory management
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
` (9 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 10/10] eal/windows: implement basic memory management Dmitry Kozlyuk
@ 2020-04-14 23:37 ` Kadam, Pallavi
10 siblings, 0 replies; 218+ messages in thread
From: Kadam, Pallavi @ 2020-04-14 23:37 UTC (permalink / raw)
To: dev, Dmitry Kozlyuk
On 4/14/2020 12:44 PM, Dmitry Kozlyuk wrote:
> Note: no changes in cover letter since v2.
>
> This patchset implements basic MM with the following features:
>
> * Hugepages are dynamically allocated in user-mode.
> * Only 2MB hugepages are supported.
> * IOVA is always PA, obtained through kernel-mode driver.
> * No 32-bit support (presumably not demanded).
> * Ni multi-process support (it is forcefully disabled).
> * No-huge mode for testing with IOVA unavailable.
>
>
> The first commit introduces a new kernel-mode driver, virt2phys.
> It translates user-mode virtual addresses into physical addresses.
> On Windows community call 2020-04-01 it was decided this driver can be
> used for now, later netUIO may pick up its code/interface or not.
>
>
> New EAL public functions for memory mapping are introduced
> to mitigate OS differences in DPDK libraries and applications:
>
> * rte_mem_map
> * rte_mem_unmap
> * rte_mem_lock
>
> To support common MM routines, internal wrappers for low-level
> memory reservation and file management are introduced. These changes
> affect Linux and FreeBSD EAL. Shared code is placed unded /unix/
> subdirectory (suggested by Thomas).
>
> Also, entire <sys/queue.h> is imported from FreeBSD, replacing existing
> partial import. There is already a license exception for this file.
>
>
> Windows MM duplicates quite a lot of code from Linux EAL:
>
> * eal_memalloc_alloc_seg_bulk
> * eal_memalloc_free_seg_bulk
> * calc_num_pages_per_socket
> * rte_eal_hugepage_init
>
> Perhaps this should be left as-is until Windows MM evolves into having
> some specific requirements for these parts.
>
>
> Notes on checkpatch warnings:
>
> * No space after comma / no space before closing parent in macros---
> definitely a false-positive, unclear how to suppress this.
>
> * Issues from imported BSD code---probably should be ignored?
>
> * Checkpatch is not run against dpdk-kmods (Windows drivers).
>
> ---
>
> v3:
>
> * Fix Linux build on and aarch64 and 32-bit x86 (reported by CI).
> * Fix logic and error handling while allocating segments.
> * Fix Unix rte_mem_map(): return NULL on failure.
> * Fix some checkpatch.sh issues:
> * Do not return positive errno, use DWORD for GetLastError().
> * Make dpdk-kmods source files non-executable.
> * Improve GSG for Windows Server (suggested by Ranjit Menon).
>
> v2:
>
> * Rebase on ToT. Move all new code shared between Linux and FreeBSD
> to /unix/ subdirectory, also factor out some existing code there.
> * Improve description of Clang issue with rte_page_sizes on Windows.
> Restore -fstrict-enum for EAL. Check running, not target compiler.
> * Use EAL prefix for private facilities instead if RTE.
> * Improve documentation comments for new functions.
> * Remove co-installer for virt2phys. Add a typecast for clarity.
> * Document virt2phys in user guide, improve its own README.
> * Explicitly and forcefully disable multi-process.
>
> Dmitry Kozlyuk (9):
> eal/windows: do not expose private EAL facilities
> eal/windows: improve CPU and NUMA node detection
> eal/windows: initialize hugepage info
> eal: introduce internal wrappers for file operations
> eal: introduce memory management wrappers
> eal: extract common code for memseg list initialization
> eal/windows: fix rte_page_sizes with Clang on Windows
> eal/windows: replace sys/queue.h with a complete one from FreeBSD
> eal/windows: implement basic memory management
>
> config/meson.build | 12 +-
> doc/guides/windows_gsg/build_dpdk.rst | 20 -
> doc/guides/windows_gsg/index.rst | 1 +
> doc/guides/windows_gsg/run_apps.rst | 84 ++
> lib/librte_eal/common/eal_common_fbarray.c | 57 +-
> lib/librte_eal/common/eal_common_memory.c | 104 +-
> lib/librte_eal/common/eal_private.h | 134 +-
> lib/librte_eal/common/malloc_heap.c | 1 +
> lib/librte_eal/common/meson.build | 9 +
> lib/librte_eal/freebsd/eal_memory.c | 55 +-
> lib/librte_eal/include/rte_memory.h | 74 ++
> lib/librte_eal/linux/eal_memory.c | 68 +-
> lib/librte_eal/meson.build | 4 +
> lib/librte_eal/rte_eal_exports.def | 119 ++
> lib/librte_eal/rte_eal_version.map | 4 +
> lib/librte_eal/unix/eal.c | 47 +
> lib/librte_eal/unix/eal_memory.c | 113 ++
> lib/librte_eal/unix/meson.build | 7 +
> lib/librte_eal/windows/eal.c | 160 +++
> lib/librte_eal/windows/eal_hugepages.c | 108 ++
> lib/librte_eal/windows/eal_lcore.c | 187 ++-
> lib/librte_eal/windows/eal_memalloc.c | 418 ++++++
> lib/librte_eal/windows/eal_memory.c | 1141 +++++++++++++++++
> lib/librte_eal/windows/eal_mp.c | 103 ++
> lib/librte_eal/windows/eal_thread.c | 1 +
> lib/librte_eal/windows/eal_windows.h | 129 ++
> lib/librte_eal/windows/include/meson.build | 2 +
> lib/librte_eal/windows/include/pthread.h | 2 +
> lib/librte_eal/windows/include/rte_os.h | 48 +-
> .../windows/include/rte_virt2phys.h | 34 +
> lib/librte_eal/windows/include/rte_windows.h | 43 +
> lib/librte_eal/windows/include/sys/queue.h | 663 +++++++++-
> lib/librte_eal/windows/include/unistd.h | 3 +
> lib/librte_eal/windows/meson.build | 6 +
> 34 files changed, 3611 insertions(+), 350 deletions(-)
> create mode 100644 doc/guides/windows_gsg/run_apps.rst
> create mode 100644 lib/librte_eal/unix/eal.c
> create mode 100644 lib/librte_eal/unix/eal_memory.c
> create mode 100644 lib/librte_eal/unix/meson.build
> create mode 100644 lib/librte_eal/windows/eal_hugepages.c
> create mode 100644 lib/librte_eal/windows/eal_memalloc.c
> create mode 100644 lib/librte_eal/windows/eal_memory.c
> create mode 100644 lib/librte_eal/windows/eal_mp.c
> create mode 100644 lib/librte_eal/windows/eal_windows.h
> create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
> create mode 100644 lib/librte_eal/windows/include/rte_windows.h
>
Tested-by: Pallavi Kadam <pallavi.kadam@intel.com>
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v4 0/8] Windows basic memory management
2020-04-10 16:43 ` [dpdk-dev] [PATCH v2 00/10] eal: Windows " Dmitry Kozlyuk
` (10 preceding siblings ...)
2020-04-14 19:44 ` [dpdk-dev] [PATCH v3 00/10] Windows " Dmitry Kozlyuk
@ 2020-04-28 23:50 ` Dmitry Kozlyuk
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 1/8] eal: replace rte_page_sizes with a set of constants Dmitry Kozlyuk
` (8 more replies)
11 siblings, 9 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-28 23:50 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk
Note: symbols and release notes updated for v20.05, despite this patch
now targeting v20.08, because proper sections don't yet exist.
This patchset implements basic MM with the following features:
* Hugepages are dynamically allocated in user-mode.
* Only 2MB hugepages are supported.
* IOVA is always PA, obtained through kernel-mode driver.
* No 32-bit support (presumably not demanded).
* Ni multi-process support (it is forcefully disabled).
* No-huge mode for testing with IOVA unavailable.
New EAL public functions for memory mapping are introduced
to mitigate OS differences in DPDK libraries and applications:
* rte_mem_map
* rte_mem_unmap
* rte_mem_lock
* rte_get_page_size
To support common MM routines, internal wrappers for low-level
memory reservation and file management are introduced. These changes
affect Linux and FreeBSD EAL. Shared code is placed unded /unix/
subdirectory (suggested by Thomas).
Also, entire <sys/queue.h> is imported from FreeBSD, replacing existing
partial import. There is already a license exception for this file.
Windows MM duplicates quite a lot of code from Linux EAL:
* eal_memalloc_alloc_seg_bulk
* eal_memalloc_free_seg_bulk
* calc_num_pages_per_socket
* rte_eal_hugepage_init
Perhaps this should be left as-is until Windows MM evolves into having
some specific requirements for these parts.
Notes on checkpatch warnings:
* No space after comma / no space before closing parent in macros---
definitely a false-positive, unclear how to suppress this.
* Issues from imported BSD code---probably should be ignored?
---
v4:
* Rebase on ToT, drop patches merged into master.
* Rearrange patches to split Windows code (Jerin).
* Fix Linux and FreeBSD build with make (Ophir).
* Use int instead of enum to hold a set of flags (Anatoly).
* Rename eal_mem_reserve items and fix their description (Anatoly).
* Add eal_mem_set_dump() wrapper around madvise (Anatoly).
* Don't claim Windows Server 2016 support due to lack of API (Tal).
* Replace enum rte_page_sizes with a set of #defines (Jerin).
* Fix documentation, SPDX tags, logging (Thomas).
v3:
* Fix Linux build on and aarch64 and 32-bit x86 (reported by CI).
* Fix logic and error handling while allocating segments.
* Fix Unix rte_mem_map(): return NULL on failure.
* Fix some checkpatch.sh issues:
* Do not return positive errno, use DWORD for GetLastError().
* Make dpdk-kmods source files non-executable.
* Improve GSG for Windows Server (suggested by Ranjit Menon).
v2:
* Rebase on ToT. Move all new code shared between Linux and FreeBSD
to /unix/ subdirectory, also factor out some existing code there.
* Improve description of Clang issue with rte_page_sizes on Windows.
Restore -fstrict-enum for EAL. Check running, not target compiler.
* Use EAL prefix for private facilities instead if RTE.
* Improve documentation comments for new functions.
* Remove co-installer for virt2phys. Add a typecast for clarity.
* Document virt2phys in user guide, improve its own README.
* Explicitly and forcefully disable multi-process.
Dmitry Kozlyuk (8):
eal: replace rte_page_sizes with a set of constants
eal: introduce internal wrappers for file operations
eal: introduce memory management wrappers
eal: extract common code for memseg list initialization
eal/windows: replace sys/queue.h with a complete one from FreeBSD
eal/windows: improve CPU and NUMA node detection
eal/windows: initialize hugepage info
eal/windows: implement basic memory management
config/meson.build | 12 +-
doc/guides/rel_notes/release_20_05.rst | 2 +
doc/guides/windows_gsg/build_dpdk.rst | 20 -
doc/guides/windows_gsg/index.rst | 1 +
doc/guides/windows_gsg/run_apps.rst | 95 ++
lib/librte_eal/common/eal_common_fbarray.c | 56 +-
lib/librte_eal/common/eal_common_memory.c | 116 +-
lib/librte_eal/common/eal_common_memzone.c | 7 +
lib/librte_eal/common/eal_private.h | 155 ++-
lib/librte_eal/common/meson.build | 10 +
lib/librte_eal/common/rte_malloc.c | 9 +
lib/librte_eal/freebsd/Makefile | 5 +
lib/librte_eal/freebsd/eal_memory.c | 57 +-
lib/librte_eal/include/rte_memory.h | 109 +-
lib/librte_eal/linux/Makefile | 5 +
lib/librte_eal/linux/eal_memalloc.c | 5 +-
lib/librte_eal/linux/eal_memory.c | 68 +-
lib/librte_eal/meson.build | 4 +
lib/librte_eal/rte_eal_exports.def | 119 ++
lib/librte_eal/rte_eal_version.map | 4 +
lib/librte_eal/unix/eal_unix.c | 51 +
lib/librte_eal/unix/eal_unix_memory.c | 144 ++
lib/librte_eal/unix/meson.build | 7 +
lib/librte_eal/windows/eal.c | 158 +++
lib/librte_eal/windows/eal_hugepages.c | 108 ++
lib/librte_eal/windows/eal_lcore.c | 185 ++-
lib/librte_eal/windows/eal_memalloc.c | 418 ++++++
lib/librte_eal/windows/eal_memory.c | 1155 +++++++++++++++++
lib/librte_eal/windows/eal_mp.c | 103 ++
lib/librte_eal/windows/eal_windows.h | 100 ++
lib/librte_eal/windows/include/meson.build | 1 +
lib/librte_eal/windows/include/rte_os.h | 4 +
.../windows/include/rte_virt2phys.h | 34 +
lib/librte_eal/windows/include/rte_windows.h | 2 +
lib/librte_eal/windows/include/sys/queue.h | 663 +++++++++-
lib/librte_eal/windows/include/unistd.h | 3 +
lib/librte_eal/windows/meson.build | 6 +
37 files changed, 3655 insertions(+), 346 deletions(-)
create mode 100644 doc/guides/windows_gsg/run_apps.rst
create mode 100644 lib/librte_eal/unix/eal_unix.c
create mode 100644 lib/librte_eal/unix/eal_unix_memory.c
create mode 100644 lib/librte_eal/unix/meson.build
create mode 100644 lib/librte_eal/windows/eal_hugepages.c
create mode 100644 lib/librte_eal/windows/eal_memalloc.c
create mode 100644 lib/librte_eal/windows/eal_memory.c
create mode 100644 lib/librte_eal/windows/eal_mp.c
create mode 100644 lib/librte_eal/windows/include/rte_virt2phys.h
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v4 1/8] eal: replace rte_page_sizes with a set of constants
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 0/8] " Dmitry Kozlyuk
@ 2020-04-28 23:50 ` Dmitry Kozlyuk
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 2/8] eal: introduce internal wrappers for file operations Dmitry Kozlyuk
` (7 subsequent siblings)
8 siblings, 0 replies; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-28 23:50 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Jerin Jacob, John McNamara, Marko Kovacevic,
Anatoly Burakov
Clang on Windows follows MS ABI where enum values are limited to 2^31-1.
Enum rte_page_sizes has members valued above this limit, which get
wrapped to zero, resulting in compilation error (duplicate values in
enum). Using MS ABI is mandatory for Windows EAL to call Win32 APIs.
Remove rte_page_sizes and replace its values with #define's.
This enumeration is not used in public API, so there's no ABI breakage.
Document API change in release notes.
Suggested-by: Jerin Jacob <jerinjacobk@gmail.com>
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
doc/guides/rel_notes/release_20_05.rst | 2 ++
lib/librte_eal/include/rte_memory.h | 23 ++++++++++-------------
2 files changed, 12 insertions(+), 13 deletions(-)
diff --git a/doc/guides/rel_notes/release_20_05.rst b/doc/guides/rel_notes/release_20_05.rst
index b124c3f28..76ba59220 100644
--- a/doc/guides/rel_notes/release_20_05.rst
+++ b/doc/guides/rel_notes/release_20_05.rst
@@ -225,6 +225,8 @@ Removed Items
Also, make sure to start the actual text at the margin.
=========================================================
+* ``enum rte_page_sizes`` is removed, ``RTE_PGSIZE_*`` constants are kept.
+
API Changes
-----------
diff --git a/lib/librte_eal/include/rte_memory.h b/lib/librte_eal/include/rte_memory.h
index 3d8d0bd69..65374d53a 100644
--- a/lib/librte_eal/include/rte_memory.h
+++ b/lib/librte_eal/include/rte_memory.h
@@ -24,19 +24,16 @@ extern "C" {
#include <rte_config.h>
#include <rte_fbarray.h>
-__extension__
-enum rte_page_sizes {
- RTE_PGSIZE_4K = 1ULL << 12,
- RTE_PGSIZE_64K = 1ULL << 16,
- RTE_PGSIZE_256K = 1ULL << 18,
- RTE_PGSIZE_2M = 1ULL << 21,
- RTE_PGSIZE_16M = 1ULL << 24,
- RTE_PGSIZE_256M = 1ULL << 28,
- RTE_PGSIZE_512M = 1ULL << 29,
- RTE_PGSIZE_1G = 1ULL << 30,
- RTE_PGSIZE_4G = 1ULL << 32,
- RTE_PGSIZE_16G = 1ULL << 34,
-};
+#define RTE_PGSIZE_4K (1ULL << 12)
+#define RTE_PGSIZE_64K (1ULL << 16)
+#define RTE_PGSIZE_256K (1ULL << 18)
+#define RTE_PGSIZE_2M (1ULL << 21)
+#define RTE_PGSIZE_16M (1ULL << 24)
+#define RTE_PGSIZE_256M (1ULL << 28)
+#define RTE_PGSIZE_512M (1ULL << 29)
+#define RTE_PGSIZE_1G (1ULL << 30)
+#define RTE_PGSIZE_4G (1ULL << 32)
+#define RTE_PGSIZE_16G (1ULL << 34)
#define SOCKET_ID_ANY -1 /**< Any NUMA socket. */
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread
* [dpdk-dev] [PATCH v4 2/8] eal: introduce internal wrappers for file operations
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 0/8] " Dmitry Kozlyuk
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 1/8] eal: replace rte_page_sizes with a set of constants Dmitry Kozlyuk
@ 2020-04-28 23:50 ` Dmitry Kozlyuk
2020-04-29 16:41 ` Burakov, Anatoly
2020-04-28 23:50 ` [dpdk-dev] [PATCH v4 3/8] eal: introduce memory management wrappers Dmitry Kozlyuk
` (6 subsequent siblings)
8 siblings, 1 reply; 218+ messages in thread
From: Dmitry Kozlyuk @ 2020-04-28 23:50 UTC (permalink / raw)
To: dev
Cc: Dmitry Malloy (MESHCHANINOV),
Narcisa Ana Maria Vasile, Fady Bader, Tal Shnaiderman,
Dmitry Kozlyuk, Anatoly Burakov, Bruce Richardson
EAL common code uses file locking and truncation. Introduce
OS-independent wrappers in order to support both Linux/FreeBSD
and Windows:
* eal_file_lock: lock or unlock an open file.
* eal_file_truncate: enforce a given size for an open file.
Wrappers follow POSIX semantics, but interface is not POSIX,
so that it can be made more clean, e.g. by not mixing locking
operation and behaviour on conflict.
Implementation for Linux and FreeBSD is placed in "unix" subdirectory,
which is intended for common code between the two. Files should be named
after the ones from which the code is factored in OS subdirectory.
Signed-off-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
---
lib/librte_eal/common/eal_common_fbarray.c | 19 ++++----
lib/librte_eal/common/eal_private.h | 45 +++++++++++++++++++
lib/librte_eal/freebsd/Makefile | 4 ++
lib/librte_eal/linux/Makefile | 4 ++
lib/librte_eal/meson.build | 4 ++
lib/librte_eal/unix/eal_unix.c | 51 ++++++++++++++++++++++
lib/librte_eal/unix/meson.build | 6 +++
7 files changed, 122 insertions(+), 11 deletions(-)
create mode 100644 lib/librte_eal/unix/eal_unix.c
create mode 100644 lib/librte_eal/unix/meson.build
diff --git a/lib/librte_eal/common/eal_common_fbarray.c b/lib/librte_eal/common/eal_common_fbarray.c
index 4f8f1af73..1e55757ca 100644
--- a/lib/librte_eal/common/eal_common_fbarray.c
+++ b/lib/librte_eal/common/eal_common_fbarray.c
@@ -8,8 +8,8 @@
#include <sys/mman.h>
#include <stdint.h>
#include <errno.h>
-#include <sys/file.h>
#include <string.h>
+#include <unistd.h>
#include <rte_common.h>
#include <rte_log.h>
@@ -85,7 +85,7 @@ resize_and_map(int fd, void *addr, size_t len)
char path[PATH_MAX];
void *map_addr;
- if (ftruncate(fd, len)) {
+ if (eal_file_truncate(fd, len)) {
RTE_LOG(ERR, EAL, "Cannot truncate %s\n", path);
/* pass errno up the chain */
rte_errno = errno;
@@ -778,7 +778,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
__func__, path, strerror(errno));
rte_errno = errno;
goto fail;
- } else if (flock(fd, LOCK_EX | LOCK_NB)) {
+ } else if (eal_file_lock(
+ fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
__func__, path, strerror(errno));
rte_errno = EBUSY;
@@ -789,10 +790,8 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
* still attach to it, but no other process could reinitialize
* it.
*/
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -895,10 +894,8 @@ rte_fbarray_attach(struct rte_fbarray *arr)
}
/* lock the file, to let others know we're using it */
- if (flock(fd, LOCK_SH | LOCK_NB)) {
- rte_errno = errno;
+ if (eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN))
goto fail;
- }
if (resize_and_map(fd, data, mmap_len))
goto fail;
@@ -1025,7 +1022,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* has been detached by all other processes
*/
fd = tmp->fd;
- if (flock(fd, LOCK_EX | LOCK_NB)) {
+ if (eal_file_lock(fd, EAL_FLOCK_EXCLUSIVE, EAL_FLOCK_RETURN)) {
RTE_LOG(DEBUG, EAL, "Cannot destroy fbarray - another process is using it\n");
rte_errno = EBUSY;
ret = -1;
@@ -1042,7 +1039,7 @@ rte_fbarray_destroy(struct rte_fbarray *arr)
* we're still holding an exclusive lock, so drop it to
* shared.
*/
- flock(fd, LOCK_SH | LOCK_NB);
+ eal_file_lock(fd, EAL_FLOCK_SHARED, EAL_FLOCK_RETURN);
ret = -1;
goto out;
diff --git a/lib/librte_eal/common/eal_private.h b/lib/librte_eal/common/eal_private.h
index ecf827914..3aafd892f 100644
--- a/lib/librte_eal/common/eal_private.h
+++ b/lib/librte_eal/common/eal_private.h
@@ -448,4 +448,49 @@ eal_malloc_no_trace(const char *type, size_t size, unsigned int align);
void eal_free_no_trace(void *addr);
+/** File locking operation. */
+enum eal_flock_op {
+ EAL_FLOCK_SHARED, /**< Acquire a shared lock. */
+ EAL_FLOCK_EXCLUSIVE, /**< Acquire an exclusive lock. */
+ EAL_FLOCK_UNLOCK /**< Release a previously taken lock. */
+};
+
+/** Behavior on file locking conflict. */
+enum eal_flock_mode {
+ EAL_FLOCK_WAIT, /**< Wait until the file gets unlocked to lock it. */
+ EAL_FLOCK_RETURN /**< Return immediately if the file is locked. */
+};
+
+/**
+ * Lock or unlock the file.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX flock(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param op
+ * Operation to perform.
+ * @param mode
+ * Behavior on conflict.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode);
+
+/**
+ * Truncate or extend the file to the specified size.
+ *
+ * On failure @code rte_errno @endcode is set to the error code
+ * specified by POSIX ftruncate(3) description.
+ *
+ * @param fd
+ * Opened file descriptor.
+ * @param size
+ * Desired file size.
+ * @return
+ * 0 on success, (-1) on failure.
+ */
+int eal_file_truncate(int fd, ssize_t size);
+
#endif /* _EAL_PRIVATE_H_ */
diff --git a/lib/librte_eal/freebsd/Makefile b/lib/librte_eal/freebsd/Makefile
index a8400f20a..a26c455c7 100644
--- a/lib/librte_eal/freebsd/Makefile
+++ b/lib/librte_eal/freebsd/Makefile
@@ -7,6 +7,7 @@ LIB = librte_eal.a
ARCH_DIR ?= $(RTE_ARCH)
VPATH += $(RTE_SDK)/lib/librte_eal/$(ARCH_DIR)
+VPATH += $(RTE_SDK)/lib/librte_eal/unix
VPATH += $(RTE_SDK)/lib/librte_eal/common
CFLAGS += -I$(SRCDIR)/include
@@ -74,6 +75,9 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_service.c
SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_random.c
SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_reciprocal.c
+# from unix dir
+SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += eal_unix.c
+
# from arch dir
SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_cpuflags.c
SRCS-$(CONFIG_RTE_EXEC_ENV_FREEBSD) += rte_hypervisor.c
diff --git a/lib/librte_eal/linux/Makefile b/lib/librte_eal/linux/Makefile
index a77eb1757..fa41f00bf 100644
--- a/lib/librte_eal/linux/Makefile
+++ b/lib/librte_eal/linux/Makefile
@@ -7,6 +7,7 @@ LIB = librte_eal.a
ARCH_DIR ?= $(RTE_ARCH)
VPATH += $(RTE_SDK)/lib/librte_eal/$(ARCH_DIR)
+VPATH += $(RTE_SDK)/lib/librte_eal/unix
VPATH += $(RTE_SDK)/lib/librte_eal/common
CFLAGS += -I$(SRCDIR)/include
@@ -81,6 +82,9 @@ SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_service.c
SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_random.c
SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_reciprocal.c
+# from unix dir
+SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += eal_unix.c
+
# from arch dir
SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_cpuflags.c
SRCS-$(CONFIG_RTE_EXEC_ENV_LINUX) += rte_hypervisor.c
diff --git a/lib/librte_eal/meson.build b/lib/librte_eal/meson.build
index 0267c3b9d..98c97dd07 100644
--- a/lib/librte_eal/meson.build
+++ b/lib/librte_eal/meson.build
@@ -6,6 +6,10 @@ subdir('include')
subdir('common')
+if not is_windows
+ subdir('unix')
+endif
+
dpdk_conf.set('RTE_EXEC_ENV_' + exec_env.to_upper(), 1)
subdir(exec_env)
diff --git a/lib/librte_eal/unix/eal_unix.c b/lib/librte_eal/unix/eal_unix.c
new file mode 100644
index 000000000..b9c57ef18
--- /dev/null
+++ b/lib/librte_eal/unix/eal_unix.c
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Dmitry Kozlyuk
+ */
+
+#include <sys/file.h>
+#include <sys/mman.h>
+#include <unistd.h>
+
+#include <rte_errno.h>
+
+#include "eal_private.h"
+
+int
+eal_file_truncate(int fd, ssize_t size)
+{
+ int ret;
+
+ ret = ftruncate(fd, size);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
+
+int
+eal_file_lock(int fd, enum eal_flock_op op, enum eal_flock_mode mode)
+{
+ int sys_flags = 0;
+ int ret;
+
+ if (mode == EAL_FLOCK_RETURN)
+ sys_flags |= LOCK_NB;
+
+ switch (op) {
+ case EAL_FLOCK_EXCLUSIVE:
+ sys_flags |= LOCK_EX;
+ break;
+ case EAL_FLOCK_SHARED:
+ sys_flags |= LOCK_SH;
+ break;
+ case EAL_FLOCK_UNLOCK:
+ sys_flags |= LOCK_UN;
+ break;
+ }
+
+ ret = flock(fd, sys_flags);
+ if (ret)
+ rte_errno = errno;
+
+ return ret;
+}
diff --git a/lib/librte_eal/unix/meson.build b/lib/librte_eal/unix/meson.build
new file mode 100644
index 000000000..cfa1b4ef9
--- /dev/null
+++ b/lib/librte_eal/unix/meson.build
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2020 Dmitry Kozlyuk
+
+sources += files(
+ 'eal_unix.c',
+)
--
2.25.1
^ permalink raw reply [flat|nested] 218+ messages in thread