diff options
207 files changed, 2167 insertions, 1179 deletions
diff --git a/Documentation/admin-guide/laptops/thinkpad-acpi.rst b/Documentation/admin-guide/laptops/thinkpad-acpi.rst index 6721a80a2d4f..475eb0e81e4a 100644 --- a/Documentation/admin-guide/laptops/thinkpad-acpi.rst +++ b/Documentation/admin-guide/laptops/thinkpad-acpi.rst @@ -1520,15 +1520,15 @@ This sysfs attribute controls the keyboard "face" that will be shown on the Lenovo X1 Carbon 2nd gen (2014)'s adaptive keyboard. The value can be read and set. -- 1 = Home mode -- 2 = Web-browser mode -- 3 = Web-conference mode -- 4 = Function mode -- 5 = Layflat mode +- 0 = Home mode +- 1 = Web-browser mode +- 2 = Web-conference mode +- 3 = Function mode +- 4 = Layflat mode For more details about which buttons will appear depending on the mode, please review the laptop's user guide: -http://www.lenovo.com/shop/americas/content/user_guides/x1carbon_2_ug_en.pdf +https://download.lenovo.com/ibmdl/pub/pc/pccbbs/mobiles_pdf/x1carbon_2_ug_en.pdf Battery charge control ---------------------- diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 426162009ce9..0e486f41185e 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -1099,7 +1099,7 @@ task_delayacct =============== Enables/disables task delay accounting (see -:doc:`accounting/delay-accounting.rst`). Enabling this feature incurs +Documentation/accounting/delay-accounting.rst. Enabling this feature incurs a small amount of overhead in the scheduler but is useful for debugging and performance tuning. It is required by some tools such as iotop. diff --git a/Documentation/arm/marvell.rst b/Documentation/arm/marvell.rst index 8323c79d321b..9485a5a2e2e9 100644 --- a/Documentation/arm/marvell.rst +++ b/Documentation/arm/marvell.rst @@ -104,6 +104,8 @@ Discovery family Not supported by the Linux kernel. + Homepage: + https://web.archive.org/web/20110924171043/http://www.marvell.com/embedded-processors/discovery-innovation/ Core: Feroceon 88fr571-vd ARMv5 compatible @@ -120,6 +122,7 @@ EBU Armada family - 88F6707 - 88F6W11 + - Product infos: https://web.archive.org/web/20141002083258/http://www.marvell.com/embedded-processors/armada-370/ - Product Brief: https://web.archive.org/web/20121115063038/http://www.marvell.com/embedded-processors/armada-300/assets/Marvell_ARMADA_370_SoC.pdf - Hardware Spec: https://web.archive.org/web/20140617183747/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-datasheet.pdf - Functional Spec: https://web.archive.org/web/20140617183701/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA370-FunctionalSpec-datasheet.pdf @@ -127,9 +130,29 @@ EBU Armada family Core: Sheeva ARMv7 compatible PJ4B + Armada XP Flavors: + - MV78230 + - MV78260 + - MV78460 + + NOTE: + not to be confused with the non-SMP 78xx0 SoCs + + - Product infos: https://web.archive.org/web/20150101215721/http://www.marvell.com/embedded-processors/armada-xp/ + - Product Brief: https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf + - Functional Spec: https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf + - Hardware Specs: + - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF + - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF + - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF + + Core: + Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP + Armada 375 Flavors: - 88F6720 + - Product infos: https://web.archive.org/web/20140108032402/http://www.marvell.com/embedded-processors/armada-375/ - Product Brief: https://web.archive.org/web/20131216023516/http://www.marvell.com/embedded-processors/armada-300/assets/ARMADA_375_SoC-01_product_brief.pdf Core: @@ -162,29 +185,6 @@ EBU Armada family Core: ARM Cortex-A9 - Armada XP Flavors: - - MV78230 - - MV78260 - - MV78460 - - NOTE: - not to be confused with the non-SMP 78xx0 SoCs - - Product Brief: - https://web.archive.org/web/20121021173528/http://www.marvell.com/embedded-processors/armada-xp/assets/Marvell-ArmadaXP-SoC-product%20brief.pdf - - Functional Spec: - https://web.archive.org/web/20180829171131/http://www.marvell.com/embedded-processors/armada-xp/assets/ARMADA-XP-Functional-SpecDatasheet.pdf - - - Hardware Specs: - - - https://web.archive.org/web/20141127013651/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78230_OS.PDF - - https://web.archive.org/web/20141222000224/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78260_OS.PDF - - https://web.archive.org/web/20141222000230/http://www.marvell.com/embedded-processors/armada-xp/assets/HW_MV78460_OS.PDF - - Core: - Sheeva ARMv7 compatible Dual-core or Quad-core PJ4B-MP - Linux kernel mach directory: arch/arm/mach-mvebu Linux kernel plat directory: @@ -436,7 +436,7 @@ Berlin family (Multimedia Solutions) - Flavors: - 88DE3010, Armada 1000 (no Linux support) - Core: Marvell PJ1 (ARMv5TE), Dual-core - - Product Brief: http://www.marvell.com.cn/digital-entertainment/assets/armada_1000_pb.pdf + - Product Brief: https://web.archive.org/web/20131103162620/http://www.marvell.com/digital-entertainment/assets/armada_1000_pb.pdf - 88DE3005, Armada 1500 Mini - Design name: BG2CD - Core: ARM Cortex-A9, PL310 L2CC diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index 37f273a7e8b6..610450f59e05 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -15,7 +15,7 @@ that goes into great technical depth about the BPF Architecture. libbpf ====== -Documentation/bpf/libbpf/libbpf.rst is a userspace library for loading and interacting with bpf programs. +Documentation/bpf/libbpf/index.rst is a userspace library for loading and interacting with bpf programs. BPF Type Format (BTF) ===================== diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst index ec3e71f56009..e445cb146efe 100644 --- a/Documentation/doc-guide/sphinx.rst +++ b/Documentation/doc-guide/sphinx.rst @@ -27,7 +27,7 @@ Sphinx Install ============== The ReST markups currently used by the Documentation/ files are meant to be -built with ``Sphinx`` version 1.3 or higher. +built with ``Sphinx`` version 1.7 or higher. There's a script that checks for the Sphinx requirements. Please see :ref:`sphinx-pre-install` for further details. @@ -43,10 +43,6 @@ or ``virtualenv``, depending on how your distribution packaged Python 3. .. note:: - #) Sphinx versions below 1.5 don't work properly with Python's - docutils version 0.13.1 or higher. So, if you're willing to use - those versions, you should run ``pip install 'docutils==0.12'``. - #) It is recommended to use the RTD theme for html output. Depending on the Sphinx version, it should be installed separately, with ``pip install sphinx_rtd_theme``. @@ -55,13 +51,13 @@ or ``virtualenv``, depending on how your distribution packaged Python 3. those expressions are written using LaTeX notation. It needs texlive installed with amsfonts and amsmath in order to evaluate them. -In summary, if you want to install Sphinx version 1.7.9, you should do:: +In summary, if you want to install Sphinx version 2.4.4, you should do:: - $ virtualenv sphinx_1.7.9 - $ . sphinx_1.7.9/bin/activate - (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt + $ virtualenv sphinx_2.4.4 + $ . sphinx_2.4.4/bin/activate + (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt -After running ``. sphinx_1.7.9/bin/activate``, the prompt will change, +After running ``. sphinx_2.4.4/bin/activate``, the prompt will change, in order to indicate that you're using the new environment. If you open a new shell, you need to rerun this command to enter again at the virtual environment before building the documentation. @@ -81,7 +77,7 @@ output. PDF and LaTeX builds -------------------- -Such builds are currently supported only with Sphinx versions 1.4 and higher. +Such builds are currently supported only with Sphinx versions 2.4 and higher. For PDF and LaTeX output, you'll also need ``XeLaTeX`` version 3.14159265. @@ -104,8 +100,8 @@ command line options for your distro:: You should run: sudo dnf install -y texlive-luatex85 - /usr/bin/virtualenv sphinx_1.7.9 - . sphinx_1.7.9/bin/activate + /usr/bin/virtualenv sphinx_2.4.4 + . sphinx_2.4.4/bin/activate pip install -r Documentation/sphinx/requirements.txt Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468. diff --git a/Documentation/filesystems/autofs.rst b/Documentation/filesystems/autofs.rst index 681c6a492bc0..4f490278d22f 100644 --- a/Documentation/filesystems/autofs.rst +++ b/Documentation/filesystems/autofs.rst @@ -35,7 +35,7 @@ This document describes only the kernel module and the interactions required with any user-space program. Subsequent text refers to this as the "automount daemon" or simply "the daemon". -"autofs" is a Linux kernel module with provides the "autofs" +"autofs" is a Linux kernel module which provides the "autofs" filesystem type. Several "autofs" filesystems can be mounted and they can each be managed separately, or all managed by the same daemon. diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst index 8a2788afe89b..5ac62a7b4b7c 100644 --- a/Documentation/power/energy-model.rst +++ b/Documentation/power/energy-model.rst @@ -84,6 +84,16 @@ CONFIG_ENERGY_MODEL must be enabled to use the EM framework. 2.2 Registration of performance domains ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +Registration of 'advanced' EM +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'advanced' EM gets it's name due to the fact that the driver is allowed +to provide more precised power model. It's not limited to some implemented math +formula in the framework (like it's in 'simple' EM case). It can better reflect +the real power measurements performed for each performance state. Thus, this +registration method should be preferred in case considering EM static power +(leakage) is important. + Drivers are expected to register performance domains into the EM framework by calling the following API:: @@ -103,6 +113,18 @@ to: return warning/error, stop working or panic. See Section 3. for an example of driver implementing this callback, or Section 2.4 for further documentation on this API +Registration of 'simple' EM +~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'simple' EM is registered using the framework helper function +cpufreq_register_em_with_opp(). It implements a power model which is tight to +math formula:: + + Power = C * V^2 * f + +The EM which is registered using this method might not reflect correctly the +physics of a real device, e.g. when static power (leakage) is important. + 2.3 Accessing performance domains ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -138,6 +160,10 @@ or in Section 2.4 3. Example driver ----------------- +The CPUFreq framework supports dedicated callback for registering +the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em(). +That callback has to be implemented properly for a given driver, +because the framework would call it at the right time during setup. This section provides a simple example of a CPUFreq driver registering a performance domain in the Energy Model framework using the (fake) 'foo' protocol. The driver implements an est_power() function to be provided to the @@ -167,25 +193,22 @@ EM framework:: 20 return 0; 21 } 22 - 23 static int foo_cpufreq_init(struct cpufreq_policy *policy) + 23 static void foo_cpufreq_register_em(struct cpufreq_policy *policy) 24 { 25 struct em_data_callback em_cb = EM_DATA_CB(est_power); 26 struct device *cpu_dev; - 27 int nr_opp, ret; + 27 int nr_opp; 28 29 cpu_dev = get_cpu_device(cpumask_first(policy->cpus)); 30 - 31 /* Do the actual CPUFreq init work ... */ - 32 ret = do_foo_cpufreq_init(policy); - 33 if (ret) - 34 return ret; - 35 - 36 /* Find the number of OPPs for this policy */ - 37 nr_opp = foo_get_nr_opp(policy); + 31 /* Find the number of OPPs for this policy */ + 32 nr_opp = foo_get_nr_opp(policy); + 33 + 34 /* And register the new performance domain */ + 35 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus, + 36 true); + 37 } 38 - 39 /* And register the new performance domain */ - 40 em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus, - 41 true); - 42 - 43 return 0; - 44 } + 39 static struct cpufreq_driver foo_cpufreq_driver = { + 40 .register_em = foo_cpufreq_register_em, + 41 }; diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index e35ab74a0f80..b398b8576417 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -54,7 +54,7 @@ mcelog 0.6 mcelog --version iptables 1.4.2 iptables -V openssl & libcrypto 1.0.0 openssl version bc 1.06.95 bc --version -Sphinx\ [#f1]_ 1.3 sphinx-build --version +Sphinx\ [#f1]_ 1.7 sphinx-build --version ====================== =============== ======================================== .. [#f1] Sphinx is needed only to build the Kernel documentation diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index a0cc96923ea7..da085d63af9b 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -22,8 +22,8 @@ use it, it will make your life as a kernel developer and in general much easier. Some subsystems and maintainer trees have additional information about -their workflow and expectations, see :ref:`Documentation/process/maintainer -handbooks <maintainer_handbooks_main>`. +their workflow and expectations, see +:ref:`Documentation/process/maintainer-handbooks.rst <maintainer_handbooks_main>`. Obtain a current source tree ---------------------------- diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 4e5b26f03d5b..b3166c4a7867 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -2442,11 +2442,10 @@ Or this simple script! #!/bin/bash tracefs=`sed -ne 's/^tracefs \(.*\) tracefs.*/\1/p' /proc/mounts` - echo nop > $tracefs/tracing/current_tracer - echo 0 > $tracefs/tracing/tracing_on - echo $$ > $tracefs/tracing/set_ftrace_pid - echo function > $tracefs/tracing/current_tracer - echo 1 > $tracefs/tracing/tracing_on + echo 0 > $tracefs/tracing_on + echo $$ > $tracefs/set_ftrace_pid + echo function > $tracefs/current_tracer + echo 1 > $tracefs/tracing_on exec "$@" diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst index 0046d75d9a70..9762452c584c 100644 --- a/Documentation/translations/it_IT/doc-guide/sphinx.rst +++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst @@ -35,7 +35,7 @@ Installazione Sphinx ==================== I marcatori ReST utilizzati nei file in Documentation/ sono pensati per essere -processati da ``Sphinx`` nella versione 1.3 o superiore. +processati da ``Sphinx`` nella versione 1.7 o superiore. Esiste uno script che verifica i requisiti Sphinx. Per ulteriori dettagli consultate :ref:`it_sphinx-pre-install`. @@ -53,11 +53,6 @@ pacchettizzato dalla vostra distribuzione. .. note:: - #) Le versioni di Sphinx inferiori alla 1.5 non funzionano bene - con il pacchetto Python docutils versione 0.13.1 o superiore. - Se volete usare queste versioni, allora dovere eseguire - ``pip install 'docutils==0.12'``. - #) Viene raccomandato l'uso del tema RTD per la documentazione in HTML. A seconda della versione di Sphinx, potrebbe essere necessaria l'installazione tramite il comando ``pip install sphinx_rtd_theme``. @@ -67,13 +62,13 @@ pacchettizzato dalla vostra distribuzione. utilizzando LaTeX. Per una corretta interpretazione, è necessario aver installato texlive con i pacchetti amdfonts e amsmath. -Riassumendo, se volete installare la versione 1.7.9 di Sphinx dovete eseguire:: +Riassumendo, se volete installare la versione 2.4.4 di Sphinx dovete eseguire:: - $ virtualenv sphinx_1.7.9 - $ . sphinx_1.7.9/bin/activate - (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt + $ virtualenv sphinx_2.4.4 + $ . sphinx_2.4.4/bin/activate + (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt -Dopo aver eseguito ``. sphinx_1.7.9/bin/activate``, il prompt cambierà per +Dopo aver eseguito ``. sphinx_2.4.4/bin/activate``, il prompt cambierà per indicare che state usando il nuovo ambiente. Se aprite un nuova sessione, prima di generare la documentazione, dovrete rieseguire questo comando per rientrare nell'ambiente virtuale. @@ -94,7 +89,7 @@ Generazione in PDF e LaTeX -------------------------- Al momento, la generazione di questi documenti è supportata solo dalle -versioni di Sphinx superiori alla 1.4. +versioni di Sphinx superiori alla 2.4. Per la generazione di PDF e LaTeX, avrete bisogno anche del pacchetto ``XeLaTeX`` nella versione 3.14159265 @@ -119,8 +114,8 @@ l'installazione:: You should run: sudo dnf install -y texlive-luatex85 - /usr/bin/virtualenv sphinx_1.7.9 - . sphinx_1.7.9/bin/activate + /usr/bin/virtualenv sphinx_2.4.4 + . sphinx_2.4.4/bin/activate pip install -r Documentation/sphinx/requirements.txt Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468. diff --git a/Documentation/translations/it_IT/process/changes.rst b/Documentation/translations/it_IT/process/changes.rst index 87d081889bfc..dc7193377b7f 100644 --- a/Documentation/translations/it_IT/process/changes.rst +++ b/Documentation/translations/it_IT/process/changes.rst @@ -57,7 +57,7 @@ mcelog 0.6 mcelog --version iptables 1.4.2 iptables -V openssl & libcrypto 1.0.0 openssl version bc 1.06.95 bc --version -Sphinx\ [#f1]_ 1.3 sphinx-build --version +Sphinx\ [#f1]_ 1.7 sphinx-build --version ====================== ================= ======================================== .. [#f1] Sphinx è necessario solo per produrre la documentazione del Kernel diff --git a/Documentation/translations/zh_CN/doc-guide/sphinx.rst b/Documentation/translations/zh_CN/doc-guide/sphinx.rst index 951595c7d599..23eac67fbc30 100644 --- a/Documentation/translations/zh_CN/doc-guide/sphinx.rst +++ b/Documentation/translations/zh_CN/doc-guide/sphinx.rst @@ -26,7 +26,7 @@ reStructuredText文件å¯èƒ½åŒ…å«åŒ…å«æ¥è‡ªæºæ–‡ä»¶çš„结构化文档注释æ 安装Sphinx ========== -Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。 +Documentation/ 下的ReST文件现在使用sphinx1.7或更高版本构建。 这有一个脚本å¯ä»¥æ£€æŸ¥Sphinxçš„ä¾èµ–项。更多详细信æ¯è§ :ref:`sphinx-pre-install_zh` 。 @@ -40,22 +40,19 @@ Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。 .. note:: - #) 低于1.5版本的Sphinxæ— æ³•ä¸ŽPythonçš„0.13.1或更高版本docutils一起æ£å¸¸å·¥ä½œã€‚ - 如果您想使用这些版本，那么应该è¿è¡Œ ``pip install 'docutils==0.12'`` 。 - #) html输出建议使用RTDä¸»é¢˜ã€‚æ ¹æ®Sphinx版本的ä¸åŒï¼Œå®ƒåº”该用 ``pip install sphinx_rtd_theme`` å•ç‹¬å®‰è£…。 #) 一些ReST页é¢åŒ…å«æ•°å¦è¡¨è¾¾å¼ã€‚由于Sphinx的工作方å¼ï¼Œè¿™äº›è¡¨è¾¾å¼æ˜¯ä½¿ç”¨ LaTeX 编写的。它需è¦å®‰è£…amsfontså’Œamsmathå®åŒ…，以便显示。 -总之，如您è¦å®‰è£…Sphinx 1.7.9版本，应执行:: +总之，如您è¦å®‰è£…Sphinx 2.4.4版本，应执行:: - $ virtualenv sphinx_1.7.9 - $ . sphinx_1.7.9/bin/activate - (sphinx_1.7.9) $ pip install -r Documentation/sphinx/requirements.txt + $ virtualenv sphinx_2.4.4 + $ . sphinx_2.4.4/bin/activate + (sphinx_2.4.4) $ pip install -r Documentation/sphinx/requirements.txt -在è¿è¡Œ ``. sphinx_1.7.9/bin/activate`` 之åŽï¼Œæ示符将å˜åŒ–，以指示您æ£åœ¨ä½¿ç”¨æ–° +在è¿è¡Œ ``. sphinx_2.4.4/bin/activate`` 之åŽï¼Œæ示符将å˜åŒ–，以指示您æ£åœ¨ä½¿ç”¨æ–° 环境。如果您打开了一个新的shell，那么在构建文档之å‰ï¼Œæ‚¨éœ€è¦é‡æ–°è¿è¡Œæ¤å‘½ä»¤ä»¥å† 次进入虚拟环境ä¸ã€‚ @@ -71,7 +68,7 @@ Documentation/ 下的ReST文件现在使用sphinx1.3或更高版本构建。 PDFå’ŒLaTeX构建 -------------- -ç›®å‰åªæœ‰Sphinx 1.4åŠæ›´é«˜ç‰ˆæœ¬æ‰æ”¯æŒè¿™ç§æž„建。 +ç›®å‰åªæœ‰Sphinx 2.4åŠæ›´é«˜ç‰ˆæœ¬æ‰æ”¯æŒè¿™ç§æž„建。 对于PDFå’ŒLaTeXè¾“å‡ºï¼Œè¿˜éœ€è¦ ``XeLaTeX`` 3.14159265版本。（译注：æ¤ç‰ˆæœ¬å·çœŸå®ž å˜åœ¨ï¼‰ @@ -93,8 +90,8 @@ PDFå’ŒLaTeX构建 You should run: sudo dnf install -y texlive-luatex85 - /usr/bin/virtualenv sphinx_1.7.9 - . sphinx_1.7.9/bin/activate + /usr/bin/virtualenv sphinx_2.4.4 + . sphinx_2.4.4/bin/activate pip install -r Documentation/sphinx/requirements.txt Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468. diff --git a/Documentation/translations/zh_CN/process/management-style.rst b/Documentation/translations/zh_CN/process/management-style.rst index c6a5bb285797..8053ae474328 100644 --- a/Documentation/translations/zh_CN/process/management-style.rst +++ b/Documentation/translations/zh_CN/process/management-style.rst @@ -36,14 +36,14 @@ Linuxå†…æ ¸ç®¡ç†é£Žæ ¼ æ¯ä¸ªäººéƒ½è®¤ä¸ºç®¡ç†è€…åšå†³å®šï¼Œè€Œä¸”决ç–很é‡è¦ã€‚决定越大越痛苦，管ç†è€…就必须越高级。 这很明显，但事实并éžå¦‚æ¤ã€‚ -游æˆçš„åå—是 **é¿å…** åšå‡ºå†³å®šã€‚å°¤å…¶æ˜¯ï¼Œå¦‚æžœæœ‰äººå‘Šè¯‰ä½ â€œé€‰æ‹©ï¼ˆa）或（b）， +最é‡è¦çš„是 **é¿å…** åšå‡ºå†³å®šã€‚å°¤å…¶æ˜¯ï¼Œå¦‚æžœæœ‰äººå‘Šè¯‰ä½ â€œé€‰æ‹©ï¼ˆa）或（b）， 我们真的需è¦ä½ æ¥åšå†³å®šâ€ï¼Œä½ 就是陷入麻烦的管ç†è€…ã€‚ä½ ç®¡ç†çš„äººæ¯”ä½ æ›´äº†è§£ç»†èŠ‚ï¼Œ 所以如果他们æ¥æ‰¾ä½ åšæŠ€æœ¯å†³ç–ï¼Œä½ å®Œè›‹äº†ã€‚ä½ æ˜¾ç„¶æ²¡æœ‰èƒ½åŠ›ä¸ºä»–ä»¬åšè¿™ä¸ªå†³å®šã€‚ ï¼ˆæŽ¨è®ºï¼šå¦‚æžœä½ ç®¡ç†çš„人ä¸æ¯”ä½ æ›´äº†è§£ç»†èŠ‚ï¼Œä½ ä¹Ÿä¼šè¢«æžç ¸ï¼Œå°½ç®¡åŽŸå› 完全ä¸åŒã€‚ ä¹Ÿå°±æ˜¯è¯´ï¼Œä½ çš„å·¥ä½œæ˜¯é”™çš„ï¼Œä»–ä»¬åº”è¯¥ç®¡ç†ä½ çš„æ‰æ™ºï¼‰ -所以游æˆçš„åå—是 **é¿å…** åšå‡ºå†³å®šï¼Œè‡³å°‘是那些大而痛苦的决定。åšä¸€äº›å°çš„ +所以最é‡è¦çš„是 **é¿å…** åšå‡ºå†³å®šï¼Œè‡³å°‘是那些大而痛苦的决定。åšä¸€äº›å°çš„ å’Œéžç»“果性的决定是很好的，并且使您看起æ¥å¥½åƒçŸ¥é“自己在åšä»€ä¹ˆï¼Œæ‰€ä»¥å†…æ ¸ç®¡ç†è€… 需è¦åšçš„是将那些大的和痛苦的决定å˜æˆé‚£äº›æ²¡æœ‰äººçœŸæ£å…³å¿ƒçš„å°äº‹æƒ…。 diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..10c8ae3a8c73 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3733,7 +3733,7 @@ F: drivers/scsi/bnx2i/ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER M: Ariel Elior <aelior@marvell.com> M: Sudarsana Kalluru <skalluru@marvell.com> -M: GR-everest-linux-l2@marvell.com +M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/bnx2x/ @@ -15593,7 +15593,7 @@ F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER M: Ariel Elior <aelior@marvell.com> -M: GR-everest-linux-l2@marvell.com +M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/qlogic/qed/ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 2f03cbfefe67..e4727dc771bf 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -223,7 +223,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + /* + * ARM64 treats KVM_CAP_NR_CPUS differently from all other + * architectures, as it does not always bound it to + * KVM_CAP_MAX_VCPUS. It should not matter much because + * this is just an advisory value. + */ + r = min_t(unsigned int, num_online_cpus(), + kvm_arm_default_max_vcpus()); break; case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c index 5a3e325275d0..1c91064cb448 100644 --- a/arch/mips/bcm63xx/clk.c +++ b/arch/mips/bcm63xx/clk.c @@ -381,6 +381,12 @@ void clk_disable(struct clk *clk) EXPORT_SYMBOL(clk_disable); +struct clk *clk_get_parent(struct clk *clk) +{ + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); + unsigned long clk_get_rate(struct clk *clk) { if (!clk) diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c index a3aa22c77cad..a07a5edbcda7 100644 --- a/arch/mips/generic/yamon-dt.c +++ b/arch/mips/generic/yamon-dt.c @@ -75,7 +75,7 @@ static unsigned int __init gen_fdt_mem_array( __init int yamon_dt_append_memory(void *fdt, const struct yamon_mem_region *regions) { - unsigned long phys_memsize, memsize; + unsigned long phys_memsize = 0, memsize; __be32 mem_array[2 * MAX_MEM_ARRAY_ENTRIES]; unsigned int mem_entries; int i, err, mem_off; diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 70e32de2bcaa..72d02d363f36 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -387,3 +387,4 @@ 446 n32 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease +449 n32 futex_waitv sys_futex_waitv diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 1ca7bc337932..e2c481fcede6 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -363,3 +363,4 @@ 446 n64 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease +449 n64 futex_waitv sys_futex_waitv diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index a61c35edaa74..3714c97b2643 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -436,3 +436,4 @@ 446 o32 landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease +449 o32 futex_waitv sys_futex_waitv diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 562aa878b266..aa20d074d388 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1067,7 +1067,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c index dd819e31fcbb..4916cccf378f 100644 --- a/arch/mips/lantiq/clk.c +++ b/arch/mips/lantiq/clk.c @@ -158,6 +158,12 @@ void clk_deactivate(struct clk *clk) } EXPORT_SYMBOL(clk_deactivate); +struct clk *clk_get_parent(struct clk *clk) +{ + return NULL; +} +EXPORT_SYMBOL(clk_get_parent); + static inline u32 get_counter_resolution(void) { u32 res; diff --git a/arch/parisc/configs/generic-32bit_defconfig b/arch/parisc/configs/generic-32bit_defconfig index d6fd8fa7ed8c..53061cb2cf7f 100644 --- a/arch/parisc/configs/generic-32bit_defconfig +++ b/arch/parisc/configs/generic-32bit_defconfig @@ -231,6 +231,7 @@ CONFIG_CRYPTO_DEFLATE=y CONFIG_CRC_CCITT=m CONFIG_CRC_T10DIF=y CONFIG_FONTS=y +CONFIG_PRINTK_TIME=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 7085df079702..39e7985086f9 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -3,38 +3,19 @@ * Copyright (C) 1999 Hewlett-Packard (Frank Rowand) * Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org> * Copyright (C) 1999 SuSE GmbH + * Copyright (C) 2021 Helge Deller <deller@gmx.de> */ #ifndef _PARISC_ASSEMBLY_H #define _PARISC_ASSEMBLY_H -#define CALLEE_FLOAT_FRAME_SIZE 80 - #ifdef CONFIG_64BIT -#define LDREG ldd -#define STREG std -#define LDREGX ldd,s -#define LDREGM ldd,mb -#define STREGM std,ma -#define SHRREG shrd -#define SHLREG shld -#define ANDCM andcm,* -#define COND(x) * ## x #define RP_OFFSET 16 #define FRAME_SIZE 128 #define CALLEE_REG_FRAME_SIZE 144 #define REG_SZ 8 #define ASM_ULONG_INSN .dword #else /* CONFIG_64BIT */ -#define LDREG ldw -#define STREG stw -#define LDREGX ldwx,s -#define LDREGM ldwm -#define STREGM stwm -#define SHRREG shr -#define SHLREG shlw -#define ANDCM andcm -#define COND(x) x #define RP_OFFSET 20 #define FRAME_SIZE 64 #define CALLEE_REG_FRAME_SIZE 128 @@ -45,6 +26,7 @@ /* Frame alignment for 32- and 64-bit */ #define FRAME_ALIGN 64 +#define CALLEE_FLOAT_FRAME_SIZE 80 #define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE) #ifdef CONFIG_PA20 @@ -68,6 +50,28 @@ #ifdef __ASSEMBLY__ #ifdef CONFIG_64BIT +#define LDREG ldd +#define STREG std +#define LDREGX ldd,s +#define LDREGM ldd,mb +#define STREGM std,ma +#define SHRREG shrd +#define SHLREG shld +#define ANDCM andcm,* +#define COND(x) * ## x +#else /* CONFIG_64BIT */ +#define LDREG ldw +#define STREG stw +#define LDREGX ldwx,s +#define LDREGM ldwm +#define STREGM stwm +#define SHRREG shr +#define SHLREG shlw +#define ANDCM andcm +#define COND(x) x +#endif + +#ifdef CONFIG_64BIT /* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so * work around that for now... */ .level 2.0w diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index 7efb1aa2f7f8..af2a598bc0f8 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -5,6 +5,7 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/stringify.h> #include <asm/assembly.h> #define JUMP_LABEL_NOP_SIZE 4 diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h index 4b9e3d707571..2b3010ade00e 100644 --- a/arch/parisc/include/asm/rt_sigframe.h +++ b/arch/parisc/include/asm/rt_sigframe.h @@ -2,7 +2,7 @@ #ifndef _ASM_PARISC_RT_SIGFRAME_H #define _ASM_PARISC_RT_SIGFRAME_H -#define SIGRETURN_TRAMP 3 +#define SIGRETURN_TRAMP 4 #define SIGRESTARTBLOCK_TRAMP 5 #define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP) diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index bbfe23c40c01..46b1050640b8 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -288,21 +288,22 @@ setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs, already in userspace. The first words of tramp are used to save the previous sigrestartblock trampoline that might be on the stack. We start the sigreturn trampoline at - SIGRESTARTBLOCK_TRAMP. */ + SIGRESTARTBLOCK_TRAMP+X. */ err |= __put_user(in_syscall ? INSN_LDI_R25_1 : INSN_LDI_R25_0, &frame->tramp[SIGRESTARTBLOCK_TRAMP+0]); - err |= __put_user(INSN_BLE_SR2_R0, + err |= __put_user(INSN_LDI_R20, &frame->tramp[SIGRESTARTBLOCK_TRAMP+1]); - err |= __put_user(INSN_LDI_R20, + err |= __put_user(INSN_BLE_SR2_R0, &frame->tramp[SIGRESTARTBLOCK_TRAMP+2]); + err |= __put_user(INSN_NOP, &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]); - start = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+0]; - end = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]; + start = (unsigned long) &frame->tramp[0]; + end = (unsigned long) &frame->tramp[TRAMP_SIZE]; flush_user_dcache_range_asm(start, end); flush_user_icache_range_asm(start, end); /* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP - * TRAMP Words 5-7, Length 3 = SIGRETURN_TRAMP + * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP * So the SIGRETURN_TRAMP is at the end of SIGRESTARTBLOCK_TRAMP */ rp = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP]; diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h index a5bdbb5678b7..f166250f2d06 100644 --- a/arch/parisc/kernel/signal32.h +++ b/arch/parisc/kernel/signal32.h @@ -36,7 +36,7 @@ struct compat_regfile { compat_int_t rf_sar; }; -#define COMPAT_SIGRETURN_TRAMP 3 +#define COMPAT_SIGRETURN_TRAMP 4 #define COMPAT_SIGRESTARTBLOCK_TRAMP 5 #define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \ COMPAT_SIGRESTARTBLOCK_TRAMP) diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index bf751e0732b7..358c00000755 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -446,3 +446,4 @@ 446 common landlock_restrict_self sys_landlock_restrict_self # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease +449 common futex_waitv sys_futex_waitv diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index f9ea0e5357f9..3fa6d240bade 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -187,6 +187,12 @@ static void watchdog_smp_panic(int cpu, u64 tb) if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 35e9cccdeef9..a72920f4f221 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -641,9 +641,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * implementations just count online CPUs. */ if (hv_enabled) - r = num_present_cpus(); + r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS); else - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e3d3aed46184..fb84619df012 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -740,7 +740,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * Ensure we set mode to IN_GUEST_MODE after we disable * interrupts and before the final VCPU requests check. * See the comment in kvm_vcpu_exiting_guest_mode() and - * Documentation/virtual/kvm/vcpu-requests.rst + * Documentation/virt/kvm/vcpu-requests.rst */ vcpu->mode = IN_GUEST_MODE; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index eb3c045edf11..3b0e703d22cf 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * Copyright (c) 2019 Western Digital Corporation or its affiliates. * * Authors: diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 26399df15b63..fb18af34a4b5 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -74,7 +74,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index c6257f625929..14a18ba5ff2c 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; else if (sclp.has_esca && sclp.has_64bscao) r = KVM_S390_ESCA_CPU_SLOTS; + if (ext == KVM_CAP_NR_VCPUS) + r = min_t(unsigned int, num_online_cpus(), r); break; case KVM_CAP_S390_COW: r = MACHINE_HAS_ESOP; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 24f4a06ac46a..96eb7db31c8e 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -177,6 +177,9 @@ void set_hv_tscchange_cb(void (*cb)(void)) return; } + if (!hv_vp_index) + return; + hv_reenlightenment_cb = cb; /* Make sure callback is registered before we write to MSRs */ @@ -383,20 +386,13 @@ static void __init hv_get_partition_id(void) */ void __init hyperv_init(void) { - u64 guest_id, required_msrs; + u64 guest_id; union hv_x64_msr_hypercall_contents hypercall_msr; int cpuhp; if (x86_hyper_type != X86_HYPER_MS_HYPERV) return; - /* Absolutely required MSRs */ - required_msrs = HV_MSR_HYPERCALL_AVAILABLE | - HV_MSR_VP_INDEX_AVAILABLE; - - if ((ms_hyperv.features & required_msrs) != required_msrs) - return; - if (hv_common_init()) return; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e5d8700319cc..6ac61f85e07b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -363,6 +363,7 @@ union kvm_mmu_extended_role { unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int efer_lma:1; }; }; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 4794b716ec79..ff55df60228f 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -163,12 +163,22 @@ static uint32_t __init ms_hyperv_platform(void) cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); - if (eax >= HYPERV_CPUID_MIN && - eax <= HYPERV_CPUID_MAX && - !memcmp("Microsoft Hv", hyp_signature, 12)) - return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; + if (eax < HYPERV_CPUID_MIN || eax > HYPERV_CPUID_MAX || + memcmp("Microsoft Hv", hyp_signature, 12)) + return 0; - return 0; + /* HYPERCALL and VP_INDEX MSRs are mandatory for all features. */ + eax = cpuid_eax(HYPERV_CPUID_FEATURES); + if (!(eax & HV_MSR_HYPERCALL_AVAILABLE)) { + pr_warn("x86/hyperv: HYPERCALL MSR not available.\n"); + return 0; + } + if (!(eax & HV_MSR_VP_INDEX_AVAILABLE)) { + pr_warn("x86/hyperv: VP_INDEX MSR not available.\n"); + return 0; + } + + return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; } static unsigned char hv_get_nmi_reason(void) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index e19dabf1848b..07e9215e911d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -125,7 +125,7 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) } } -struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) +static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { u32 base = vcpu->arch.kvm_cpuid_base; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4a555f32885a..5e19e6e4c2ce 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2022,7 +2022,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) { bool longmode; - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (longmode) kvm_rax_write(vcpu, result); else { @@ -2171,7 +2171,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } #ifdef CONFIG_X86_64 - if (is_64_bit_mode(vcpu)) { + if (is_64_bit_hypercall(vcpu)) { hc.param = kvm_rcx_read(vcpu); hc.ingpa = kvm_rdx_read(vcpu); hc.outgpa = kvm_r8_read(vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 33794379949e..3be9beea838d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4682,6 +4682,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu, /* PKEY and LA57 are active iff long mode is active. */ ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs); ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs); + ext.efer_lma = ____is_efer_lma(regs); } ext.valid = 1; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 902c52a8dd0c..21ac0a5de4e0 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -237,7 +237,6 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - bool es_active = argp->id == KVM_SEV_ES_INIT; int asid, ret; if (kvm->created_vcpus) @@ -247,7 +246,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) if (unlikely(sev->active)) return ret; - sev->es_active = es_active; + sev->active = true; + sev->es_active = argp->id == KVM_SEV_ES_INIT; asid = sev_asid_new(sev); if (asid < 0) goto e_no_asid; @@ -257,8 +257,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) if (ret) goto e_free; - sev->active = true; - sev->asid = asid; INIT_LIST_HEAD(&sev->regions_list); return 0; @@ -268,6 +266,7 @@ e_free: sev->asid = 0; e_no_asid: sev->es_active = false; + sev->active = false; return ret; } @@ -1530,7 +1529,7 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp) return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error); } -static bool cmd_allowed_from_miror(u32 cmd_id) +static bool is_cmd_allowed_from_mirror(u32 cmd_id) { /* * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES @@ -1757,7 +1756,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp) /* Only the enc_context_owner handles some memory enc operations. */ if (is_mirroring_enc_context(kvm) && - !cmd_allowed_from_miror(sev_cmd.id)) { + !is_cmd_allowed_from_mirror(sev_cmd.id)) { r = -EINVAL; goto out; } @@ -1990,7 +1989,12 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) mutex_unlock(&source_kvm->lock); mutex_lock(&kvm->lock); - if (sev_guest(kvm)) { + /* + * Disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || kvm->created_vcpus) { ret = -EINVAL; goto e_mirror_unlock; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 437e68504e66..5faad3dc10e2 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -247,7 +247,7 @@ static __always_inline bool sev_es_guest(struct kvm *kvm) #ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - return sev_guest(kvm) && sev->es_active; + return sev->es_active && !WARN_ON_ONCE(!sev->active); #else return false; #endif diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index b213ca966d41..1e2f66951566 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -670,33 +670,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - struct kvm_host_map map; - struct vmcs12 *shadow; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; - shadow = get_shadow_vmcs12(vcpu); - - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)) + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) return; - memcpy(shadow, map.hva, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; if (!nested_cpu_has_shadow_vmcs(vmcs12) || vmcs12->vmcs_link_pointer == INVALID_GPA) return; - kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer, - get_shadow_vmcs12(vcpu), VMCS12_SIZE); + if (ghc->gpa != vmcs12->vmcs_link_pointer && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE)) + return; + + kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu), + VMCS12_SIZE); } /* @@ -2830,6 +2836,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return 0; } +static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ +#ifdef CONFIG_X86_64 + if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) != + !!(vcpu->arch.efer & EFER_LMA))) + return -EINVAL; +#endif + return 0; +} + static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -2854,18 +2871,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_X86_64 - ia32e = !!(vcpu->arch.efer & EFER_LMA); + ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); #else ia32e = false; #endif if (ia32e) { - if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || - CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; } else { - if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || - CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || CC((vmcs12->host_rip) >> 32)) return -EINVAL; @@ -2910,9 +2925,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int r = 0; - struct vmcs12 *shadow; - struct kvm_host_map map; + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache; + struct vmcs_hdr hdr; if (vmcs12->vmcs_link_pointer == INVALID_GPA) return 0; @@ -2920,17 +2935,21 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu, if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer))) return -EINVAL; - if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))) - return -EINVAL; + if (ghc->gpa != vmcs12->vmcs_link_pointer && + CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, + vmcs12->vmcs_link_pointer, VMCS12_SIZE))) + return -EINVAL; - shadow = map.hva; + if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr)))) + return -EINVAL; - if (CC(shadow->hdr.revision_id != VMCS12_REVISION) || - CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) - r = -EINVAL; + if (CC(hdr.revision_id != VMCS12_REVISION) || + CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12))) + return -EINVAL; - kvm_vcpu_unmap(vcpu, &map, false); - return r; + return 0; } /* @@ -3535,6 +3554,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (nested_vmx_check_controls(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + if (nested_vmx_check_address_space_size(vcpu, vmcs12)) + return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); + if (nested_vmx_check_host_state(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); @@ -5264,10 +5286,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return 1; if (vmx->nested.current_vmptr != vmptr) { - struct kvm_host_map map; - struct vmcs12 *new_vmcs12; + struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache; + struct vmcs_hdr hdr; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) { + if (ghc->gpa != vmptr && + kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) { /* * Reads from an unbacked page return all 1s, * which means that the 32 bits located at the @@ -5278,12 +5301,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } - new_vmcs12 = map.hva; + if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr, + offsetof(struct vmcs12, hdr), + sizeof(hdr))) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } - if (new_vmcs12->hdr.revision_id != VMCS12_REVISION || - (new_vmcs12->hdr.shadow_vmcs && + if (hdr.revision_id != VMCS12_REVISION || + (hdr.shadow_vmcs && !nested_cpu_has_vmx_shadow_vmcs(vcpu))) { - kvm_vcpu_unmap(vcpu, &map, false); return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); } @@ -5294,8 +5321,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) * Load VMCS12 from guest memory since it is not already * cached. */ - memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE); - kvm_vcpu_unmap(vcpu, &map, false); + if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12, + VMCS12_SIZE)) { + return nested_vmx_fail(vcpu, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID); + } set_current_vmptr(vmx, vmptr); } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a4ead6023133..4df2ac24ffc1 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -142,6 +142,16 @@ struct nested_vmx { struct vmcs12 *cached_shadow_vmcs12; /* + * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer + */ + struct gfn_to_hva_cache shadow_vmcs12_cache; + + /* + * GPA to HVA cache for VMCS12 + */ + struct gfn_to_hva_cache vmcs12_cache; + + /* * Indicates if the shadow vmcs or enlightened vmcs must be updated * with the data held by struct vmcs12. */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index dc7eb5fddfd3..5a403d92833f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3307,9 +3307,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu) "xor %1, %1\n" "2:\n" _ASM_EXTABLE_UA(1b, 2b) - : "+r" (st_preempted), - "+&r" (err) - : "m" (st->preempted)); + : "+q" (st_preempted), + "+&r" (err), + "+m" (st->preempted)); if (err) goto out; @@ -4179,7 +4179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: - r = num_online_cpus(); + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); break; case KVM_CAP_MAX_VCPUS: r = KVM_MAX_VCPUS; @@ -8848,7 +8848,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_mode(vcpu); + op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -9547,12 +9547,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - if (to_hv_vcpu(vcpu)) + if (to_hv_vcpu(vcpu)) { bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); + static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + return; + } - static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + static_call(kvm_x86_load_eoi_exitmap)( + vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index ea264c4502e4..997669ae9caa 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -153,12 +153,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) { int cs_db, cs_l; + WARN_ON_ONCE(vcpu->arch.guest_state_protected); + if (!is_long_mode(vcpu)) return false; static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); return cs_l; } +static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu) +{ + /* + * If running with protected guest state, the CS register is not + * accessible. The hypercall register values will have had to been + * provided in 64-bit mode, so assume the guest is in 64-bit. + */ + return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu); +} + static inline bool x86_exception_has_error_code(unsigned int vector) { static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8f62baebd028..dff2bdf9507a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -127,9 +127,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) state_entry_time = vx->runstate_entry_time; state_entry_time |= XEN_RUNSTATE_UPDATE; - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) != + BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -144,9 +144,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != offsetof(struct compat_vcpu_runstate_info, state)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) != + BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -163,9 +163,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) offsetof(struct vcpu_runstate_info, time) - sizeof(u64)); BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != - sizeof(((struct compat_vcpu_runstate_info *)0)->time)); - BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) != + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != + sizeof_field(struct compat_vcpu_runstate_info, time)); + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, @@ -205,9 +205,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) != offsetof(struct compat_vcpu_info, evtchn_upcall_pending)); BUILD_BUG_ON(sizeof(rc) != - sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending)); + sizeof_field(struct vcpu_info, evtchn_upcall_pending)); BUILD_BUG_ON(sizeof(rc) != - sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending)); + sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending)); /* * For efficiency, this mirrors the checks for using the valid @@ -299,7 +299,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn); + data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn; r = 0; break; @@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (!longmode) { params[0] = (u32)kvm_rbx_read(vcpu); params[1] = (u32)kvm_rcx_read(vcpu); diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 7cd0009e7ff3..ef104809f27b 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -347,28 +347,3 @@ void acpi_device_notify_remove(struct device *dev) acpi_unbind_one(dev); } - -int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used) -{ - struct acpi_device *adev = to_acpi_device(dev); - - /* - * Skip device objects with device IDs, because they may be in use even - * if they are not companions of any physical device objects. - */ - if (adev->pnp.type.hardware_id) - return 0; - - mutex_lock(&adev->physical_node_lock); - - /* - * Device objects without device IDs are not in use if they have no - * corresponding physical device objects. - */ - if (list_empty(&adev->physical_node_list)) - acpi_device_set_power(adev, ACPI_STATE_D3_COLD); - - mutex_unlock(&adev->physical_node_lock); - - return 0; -} diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 8fbdc172864b..d91b560e8867 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -117,7 +117,6 @@ bool acpi_device_is_battery(struct acpi_device *adev); bool acpi_device_is_first_physical_node(struct acpi_device *adev, const struct device *dev); int acpi_bus_register_early_device(int type); -int acpi_dev_turn_off_if_unused(struct device *dev, void *not_used); /* -------------------------------------------------------------------------- Device Matching and Notification diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a50f1967c73d..2c80765670bc 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2564,12 +2564,6 @@ int __init acpi_scan_init(void) } } - /* - * Make sure that power management resources are not blocked by ACPI - * device objects with no users. - */ - bus_for_each_dev(&acpi_bus_type, NULL, NULL, acpi_dev_turn_off_if_unused); - acpi_turn_off_unused_power_resources(); acpi_scan_initialized = true; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 7f11ea07d698..ca873a3b98db 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -480,7 +480,7 @@ module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR)); MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure"); static atomic_t trans_id = ATOMIC_INIT(0); -static int dm_ring_size = 20 * 1024; +static int dm_ring_size = VMBUS_RING_SIZE(16 * 1024); /* * Driver specific state. diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 47a04c330885..b732ee9a50ef 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3286,7 +3286,7 @@ static void __exit amt_fini(void) { rtnl_link_unregister(&amt_link_ops); unregister_netdevice_notifier(&amt_notifier_block); - cancel_delayed_work(&source_gc_wq); + cancel_delayed_work_sync(&source_gc_wq); __amt_source_gc_work(); destroy_workqueue(amt_wq); } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index fc0e66006644..3f1704cbe1cb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -559,6 +559,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, goto err_exit; if (fw.len == 0xFFFFU) { + if (sw.len > sizeof(self->rpc)) { + printk(KERN_INFO "Invalid sw len: %x\n", sw.len); + err = -EINVAL; + goto err_exit; + } err = hw_atl_utils_fw_rpc_call(self, sw.len); if (err < 0) goto err_exit; @@ -567,6 +572,11 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, if (rpc) { if (fw.len) { + if (fw.len > sizeof(self->rpc)) { + printk(KERN_INFO "Invalid fw len: %x\n", fw.len); + err = -EINVAL; + goto err_exit; + } err = hw_atl_utils_fw_downld_dwords(self, self->rpc_addr, diff --git a/drivers/net/ethernet/asix/ax88796c_main.h b/drivers/net/ethernet/asix/ax88796c_main.h index 80263c3cef75..4a83c991dcbe 100644 --- a/drivers/net/ethernet/asix/ax88796c_main.h +++ b/drivers/net/ethernet/asix/ax88796c_main.h @@ -127,9 +127,9 @@ struct ax88796c_device { #define AX_PRIV_FLAGS_MASK (AX_CAP_COMP) unsigned long flags; - #define EVENT_INTR BIT(0) - #define EVENT_TX BIT(1) - #define EVENT_SET_MULTI BIT(2) + #define EVENT_INTR 0 + #define EVENT_TX 1 + #define EVENT_SET_MULTI 2 }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h index 1835d2e451c0..fc7fce642666 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init_ops.h @@ -635,11 +635,13 @@ static int bnx2x_ilt_client_mem_op(struct bnx2x *bp, int cli_num, { int i, rc; struct bnx2x_ilt *ilt = BP_ILT(bp); - struct ilt_client_info *ilt_cli = &ilt->clients[cli_num]; + struct ilt_client_info *ilt_cli; if (!ilt || !ilt->lines) return -1; + ilt_cli = &ilt->clients[cli_num]; + if (ilt_cli->flags & (ILT_CLIENT_SKIP_INIT | ILT_CLIENT_SKIP_MEM)) return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index d0d5da9b78f8..4c9507d82fd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2258,6 +2258,16 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db, } } +/* Must hold rtnl_lock */ +static inline bool bnxt_sriov_cfg(struct bnxt *bp) +{ +#if defined(CONFIG_BNXT_SRIOV) + return BNXT_PF(bp) && (bp->pf.active_vfs || bp->sriov_cfg); +#else + return false; +#endif +} + extern const u16 bnxt_lhint_arr[]; int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 5c464ea73576..951c4c569a9b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -360,7 +360,7 @@ bnxt_dl_livepatch_report_err(struct bnxt *bp, struct netlink_ext_ack *extack, NL_SET_ERR_MSG_MOD(extack, "Live patch already applied"); break; default: - netdev_err(bp->dev, "Unexpected live patch error: %hhd\n", err); + netdev_err(bp->dev, "Unexpected live patch error: %d\n", err); NL_SET_ERR_MSG_MOD(extack, "Failed to activate live patch"); break; } @@ -441,12 +441,13 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, switch (action) { case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: { - if (BNXT_PF(bp) && bp->pf.active_vfs) { + rtnl_lock(); + if (bnxt_sriov_cfg(bp)) { NL_SET_ERR_MSG_MOD(extack, - "reload is unsupported when VFs are allocated"); + "reload is unsupported while VFs are allocated or being configured"); + rtnl_unlock(); return -EOPNOTSUPP; } - rtnl_lock(); if (bp->dev->reg_state == NETREG_UNREGISTERED) { rtnl_unlock(); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index e6a4a768b10b..1471b6130a2b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -1868,7 +1868,7 @@ static int bnxt_tc_setup_indr_block_cb(enum tc_setup_type type, struct flow_cls_offload *flower = type_data; struct bnxt *bp = priv->bp; - if (flower->common.chain_index) + if (!tc_cls_can_offload_and_chain0(bp->dev, type_data)) return -EOPNOTSUPP; switch (type) { diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c index 13121c4dcfe6..71730ef4cd57 100644 --- a/drivers/net/ethernet/dec/tulip/de4x5.c +++ b/drivers/net/ethernet/dec/tulip/de4x5.c @@ -4709,6 +4709,10 @@ type3_infoblock(struct net_device *dev, u_char count, u_char *p) lp->ibn = 3; lp->active = *p++; if (MOTO_SROM_BUG) lp->active = 0; + /* if (MOTO_SROM_BUG) statement indicates lp->active could + * be 8 (i.e. the size of array lp->phy) */ + if (WARN_ON(lp->active >= ARRAY_SIZE(lp->phy))) + return -EINVAL; lp->phy[lp->active].gep = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].rst = (*p ? p : NULL); p += (2 * (*p) + 1); lp->phy[lp->active].mc = get_unaligned_le16(p); p += 2; @@ -5000,19 +5004,23 @@ mii_get_phy(struct net_device *dev) } if ((j == limit) && (i < DE4X5_MAX_MII)) { for (k=0; k < DE4X5_MAX_PHY && lp->phy[k].id; k++); - lp->phy[k].addr = i; - lp->phy[k].id = id; - lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ - lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ - lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ - lp->mii_cnt++; - lp->active++; - printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); - j = de4x5_debug; - de4x5_debug |= DEBUG_MII; - de4x5_dbg_mii(dev, k); - de4x5_debug = j; - printk("\n"); + if (k < DE4X5_MAX_PHY) { + lp->phy[k].addr = i; + lp->phy[k].id = id; + lp->phy[k].spd.reg = GENERIC_REG; /* ANLPA register */ + lp->phy[k].spd.mask = GENERIC_MASK; /* 100Mb/s technologies */ + lp->phy[k].spd.value = GENERIC_VALUE; /* TX & T4, H/F Duplex */ + lp->mii_cnt++; + lp->active++; + printk("%s: Using generic MII device control. If the board doesn't operate,\nplease mail the following dump to the author:\n", dev->name); + j = de4x5_debug; + de4x5_debug |= DEBUG_MII; + de4x5_dbg_mii(dev, k); + de4x5_debug = j; + printk("\n"); + } else { + goto purgatory; + } } } purgatory: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 714e961e7a77..6451c8383639 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4550,10 +4550,10 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) fsl_mc_portal_free(priv->mc_io); - free_netdev(net_dev); - dev_dbg(net_dev->dev.parent, "Removed interface %s\n", net_dev->name); + free_netdev(net_dev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index 23d9cbf262c3..740850b64aff 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -400,6 +400,10 @@ static void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, return; if (!HNS_DSAF_IS_DEBUG(dsaf_dev)) { + /* DSAF_MAX_PORT_NUM is 6, but DSAF_GE_NUM is 8. + We need check to prevent array overflow */ + if (port >= DSAF_MAX_PORT_NUM) + return; reg_val_1 = 0x1 << port; port_rst_off = dsaf_dev->mac_cb[port]->port_rst_off; /* there is difference between V1 and V2 in register.*/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 5039a2536951..0bf3d47bb90d 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -3003,9 +3003,10 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) struct net_device *netdev = pci_get_drvdata(pdev); struct nic *nic = netdev_priv(netdev); + netif_device_detach(netdev); + if (netif_running(netdev)) e100_down(nic); - netif_device_detach(netdev); if ((nic->flags & wol_magic) | e100_asf(nic)) { /* enable reverse auto-negotiation */ @@ -3022,7 +3023,7 @@ static void __e100_shutdown(struct pci_dev *pdev, bool *enable_wake) *enable_wake = false; } - pci_clear_master(pdev); + pci_disable_device(pdev); } static int __e100_power_off(struct pci_dev *pdev, bool wake) @@ -3042,8 +3043,6 @@ static int __maybe_unused e100_suspend(struct device *dev_d) __e100_shutdown(to_pci_dev(dev_d), &wake); - device_wakeup_disable(dev_d); - return 0; } @@ -3051,6 +3050,14 @@ static int __maybe_unused e100_resume(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct nic *nic = netdev_priv(netdev); + int err; + + err = pci_enable_device(to_pci_dev(dev_d)); + if (err) { + netdev_err(netdev, "Resume cannot enable PCI device, aborting\n"); + return err; + } + pci_set_master(to_pci_dev(dev_d)); /* disable reverse auto-negotiation */ if (nic->phy == phy_82552_v) { @@ -3062,10 +3069,11 @@ static int __maybe_unused e100_resume(struct device *dev_d) smartspeed & ~(E100_82552_REV_ANEG)); } - netif_device_attach(netdev); if (netif_running(netdev)) e100_up(nic); + netif_device_attach(netdev); + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 3d528fba754b..4d939af0a626 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -161,6 +161,7 @@ enum i40e_vsi_state_t { __I40E_VSI_OVERFLOW_PROMISC, __I40E_VSI_REINIT_REQUESTED, __I40E_VSI_DOWN_REQUESTED, + __I40E_VSI_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_VSI_STATE_SIZE__, }; @@ -1247,6 +1248,7 @@ void i40e_ptp_restore_hw_time(struct i40e_pf *pf); void i40e_ptp_init(struct i40e_pf *pf); void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf); i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ba862131b9bd..e118cf9265c7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1790,6 +1790,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, bool is_add) { struct i40e_pf *pf = vsi->back; + u16 num_tc_qps = 0; u16 sections = 0; u8 netdev_tc = 0; u16 numtc = 1; @@ -1797,13 +1798,33 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, u8 offset; u16 qmap; int i; - u16 num_tc_qps = 0; sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID; offset = 0; + /* zero out queue mapping, it will get updated on the end of the function */ + memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping)); + + if (vsi->type == I40E_VSI_MAIN) { + /* This code helps add more queue to the VSI if we have + * more cores than RSS can support, the higher cores will + * be served by ATR or other filters. Furthermore, the + * non-zero req_queue_pairs says that user requested a new + * queue count via ethtool's set_channels, so use this + * value for queues distribution across traffic classes + */ + if (vsi->req_queue_pairs > 0) + vsi->num_queue_pairs = vsi->req_queue_pairs; + else if (pf->flags & I40E_FLAG_MSIX_ENABLED) + vsi->num_queue_pairs = pf->num_lan_msix; + } /* Number of queues per enabled TC */ - num_tc_qps = vsi->alloc_queue_pairs; + if (vsi->type == I40E_VSI_MAIN || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0)) + num_tc_qps = vsi->num_queue_pairs; + else + num_tc_qps = vsi->alloc_queue_pairs; + if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) { /* Find numtc from enabled TC bitmap */ for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { @@ -1881,15 +1902,11 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi, } ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } - - /* Set actual Tx/Rx queue pairs */ - vsi->num_queue_pairs = offset; - if ((vsi->type == I40E_VSI_MAIN) && (numtc == 1)) { - if (vsi->req_queue_pairs > 0) - vsi->num_queue_pairs = vsi->req_queue_pairs; - else if (pf->flags & I40E_FLAG_MSIX_ENABLED) - vsi->num_queue_pairs = pf->num_lan_msix; - } + /* Do not change previously set num_queue_pairs for PFs and VFs*/ + if ((vsi->type == I40E_VSI_MAIN && numtc != 1) || + (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) || + (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV)) + vsi->num_queue_pairs = offset; /* Scheduler section valid can only be set for ADD VSI */ if (is_add) { @@ -2623,7 +2640,8 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && - (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) { + (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED) && + !test_bit(__I40E_VSI_RELEASING, pf->vsi[v]->state)) { int ret = i40e_sync_vsi_filters(pf->vsi[v]); if (ret) { @@ -5427,6 +5445,58 @@ static void i40e_vsi_update_queue_map(struct i40e_vsi *vsi, } /** + * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI + * @vsi: the VSI being reconfigured + * @vsi_offset: offset from main VF VSI + */ +int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) +{ + struct i40e_vsi_context ctxt = {}; + struct i40e_pf *pf; + struct i40e_hw *hw; + int ret; + + if (!vsi) + return I40E_ERR_PARAM; + pf = vsi->back; + hw = &pf->hw; + + ctxt.seid = vsi->seid; + ctxt.pf_num = hw->pf_id; + ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset; + ctxt.uplink_seid = vsi->uplink_seid; + ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL; + ctxt.flags = I40E_AQ_VSI_TYPE_VF; + ctxt.info = vsi->info; + + i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc, + false); + if (vsi->reconfig_rss) { + vsi->rss_size = min_t(int, pf->alloc_rss_size, + vsi->num_queue_pairs); + ret = i40e_vsi_config_rss(vsi); + if (ret) { + dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n"); + return ret; + } + vsi->reconfig_rss = false; + } + + ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); + if (ret) { + dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n", + i40e_stat_str(hw, ret), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return ret; + } + /* update the local VSI info with updated queue map */ + i40e_vsi_update_queue_map(vsi, &ctxt); + vsi->info.valid_sections = 0; + + return ret; +} + +/** * i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map * @vsi: VSI to be configured * @enabled_tc: TC bitmap @@ -5717,24 +5787,6 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) } /** - * i40e_is_any_channel - channel exist or not - * @vsi: ptr to VSI to which channels are associated with - * - * Returns true or false if channel(s) exist for associated VSI or not - **/ -static bool i40e_is_any_channel(struct i40e_vsi *vsi) -{ - struct i40e_channel *ch, *ch_tmp; - - list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) { - if (ch->initialized) - return true; - } - - return false; -} - -/** * i40e_get_max_queues_for_channel * @vsi: ptr to VSI to which channels are associated with * @@ -6240,26 +6292,15 @@ int i40e_create_queue_channel(struct i40e_vsi *vsi, /* By default we are in VEPA mode, if this is the first VF/VMDq * VSI to be added switch to VEB mode. */ - if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) || - (!i40e_is_any_channel(vsi))) { - if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) { - dev_dbg(&pf->pdev->dev, - "Failed to create channel. Override queues (%u) not power of 2\n", - vsi->tc_config.tc_info[0].qcount); - return -EINVAL; - } - if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { - pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; + if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { + pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; - if (vsi->type == I40E_VSI_MAIN) { - if (pf->flags & I40E_FLAG_TC_MQPRIO) - i40e_do_reset(pf, I40E_PF_RESET_FLAG, - true); - else - i40e_do_reset_safe(pf, - I40E_PF_RESET_FLAG); - } + if (vsi->type == I40E_VSI_MAIN) { + if (pf->flags & I40E_FLAG_TC_MQPRIO) + i40e_do_reset(pf, I40E_PF_RESET_FLAG, true); + else + i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } /* now onwards for main VSI, number of queues will be value * of TC0's queue count @@ -7912,12 +7953,20 @@ config_tc: vsi->seid); need_reset = true; goto exit; - } else { - dev_info(&vsi->back->pdev->dev, - "Setup channel (id:%u) utilizing num_queues %d\n", - vsi->seid, vsi->tc_config.tc_info[0].qcount); + } else if (enabled_tc && + (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) { + netdev_info(netdev, + "Failed to create channel. Override queues (%u) not power of 2\n", + vsi->tc_config.tc_info[0].qcount); + ret = -EINVAL; + need_reset = true; + goto exit; } + dev_info(&vsi->back->pdev->dev, + "Setup channel (id:%u) utilizing num_queues %d\n", + vsi->seid, vsi->tc_config.tc_info[0].qcount); + if (pf->flags & I40E_FLAG_TC_MQPRIO) { if (vsi->mqprio_qopt.max_rate[0]) { u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0]; @@ -8482,9 +8531,8 @@ static int i40e_configure_clsflower(struct i40e_vsi *vsi, err = i40e_add_del_cloud_filter(vsi, filter, true); if (err) { - dev_err(&pf->pdev->dev, - "Failed to add cloud filter, err %s\n", - i40e_stat_str(&pf->hw, err)); + dev_err(&pf->pdev->dev, "Failed to add cloud filter, err %d\n", + err); goto err; } @@ -13771,7 +13819,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) dev_info(&pf->pdev->dev, "Can't remove PF VSI\n"); return -ENODEV; } - + set_bit(__I40E_VSI_RELEASING, vsi->state); uplink_seid = vsi->uplink_seid; if (vsi->type != I40E_VSI_SRIOV) { if (vsi->netdev_registered) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 472f56b360b8..80ae264c99ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -183,17 +183,18 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) /***********************misc routines*****************************/ /** - * i40e_vc_disable_vf + * i40e_vc_reset_vf * @vf: pointer to the VF info - * - * Disable the VF through a SW reset. + * @notify_vf: notify vf about reset or not + * Reset VF handler. **/ -static inline void i40e_vc_disable_vf(struct i40e_vf *vf) +static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; - i40e_vc_notify_vf_reset(vf); + if (notify_vf) + i40e_vc_notify_vf_reset(vf); /* We want to ensure that an actual reset occurs initiated after this * function was called. However, we do not want to wait forever, so @@ -211,9 +212,14 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) usleep_range(10000, 20000); } - dev_warn(&vf->pf->pdev->dev, - "Failed to initiate reset for VF %d after 200 milliseconds\n", - vf->vf_id); + if (notify_vf) + dev_warn(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); + else + dev_dbg(&vf->pf->pdev->dev, + "Failed to initiate reset for VF %d after 200 milliseconds\n", + vf->vf_id); } /** @@ -674,14 +680,13 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, u16 vsi_queue_id, struct virtchnl_rxq_info *info) { + u16 pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); struct i40e_pf *pf = vf->pf; + struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; struct i40e_hw *hw = &pf->hw; struct i40e_hmc_obj_rxq rx_ctx; - u16 pf_queue_id; int ret = 0; - pf_queue_id = i40e_vc_get_pf_queue_id(vf, vsi_id, vsi_queue_id); - /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(struct i40e_hmc_obj_rxq)); @@ -719,6 +724,10 @@ static int i40e_config_vsi_rx_queue(struct i40e_vf *vf, u16 vsi_id, } rx_ctx.rxmax = info->max_pkt_size; + /* if port VLAN is configured increase the max packet size */ + if (vsi->info.pvid) + rx_ctx.rxmax += VLAN_HLEN; + /* enable 32bytes desc always */ rx_ctx.dsize = 1; @@ -2106,20 +2115,6 @@ err: } /** - * i40e_vc_reset_vf_msg - * @vf: pointer to the VF info - * - * called from the VF to reset itself, - * unlike other virtchnl messages, PF driver - * doesn't send the response back to the VF - **/ -static void i40e_vc_reset_vf_msg(struct i40e_vf *vf) -{ - if (test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) - i40e_reset_vf(vf, false); -} - -/** * i40e_vc_config_promiscuous_mode_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2217,11 +2212,12 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; - struct i40e_pf *pf = vf->pf; u16 vsi_id, vsi_queue_id = 0; - u16 num_qps_all = 0; + struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; int i, j = 0, idx = 0; + struct i40e_vsi *vsi; + u16 num_qps_all = 0; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; @@ -2310,9 +2306,15 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) pf->vsi[vf->lan_vsi_idx]->num_queue_pairs = qci->num_queue_pairs; } else { - for (i = 0; i < vf->num_tc; i++) - pf->vsi[vf->ch[i].vsi_idx]->num_queue_pairs = - vf->ch[i].num_qps; + for (i = 0; i < vf->num_tc; i++) { + vsi = pf->vsi[vf->ch[i].vsi_idx]; + vsi->num_queue_pairs = vf->ch[i].num_qps; + + if (i40e_update_adq_vsi_queues(vsi, i)) { + aq_ret = I40E_ERR_CONFIG; + goto error_param; + } + } } error_param: @@ -2607,8 +2609,7 @@ static int i40e_vc_request_queues_msg(struct i40e_vf *vf, u8 *msg) } else { /* successful request */ vf->num_req_queues = req_pairs; - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return 0; } @@ -3803,8 +3804,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) vf->num_req_queues = 0; /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3844,8 +3844,7 @@ static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) } /* reset the VF in order to allocate resources */ - i40e_vc_notify_vf_reset(vf); - i40e_reset_vf(vf, false); + i40e_vc_reset_vf(vf, true); return I40E_SUCCESS; @@ -3907,7 +3906,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, i40e_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: - i40e_vc_reset_vf_msg(vf); + i40e_vc_reset_vf(vf, false); ret = 0; break; case VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE: @@ -4161,7 +4160,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* Force the VF interface down so it has to bring up with new MAC * address */ - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n"); error_param: @@ -4170,34 +4169,6 @@ error_param: } /** - * i40e_vsi_has_vlans - True if VSI has configured VLANs - * @vsi: pointer to the vsi - * - * Check if a VSI has configured any VLANs. False if we have a port VLAN or if - * we have no configured VLANs. Do not call while holding the - * mac_filter_hash_lock. - */ -static bool i40e_vsi_has_vlans(struct i40e_vsi *vsi) -{ - bool have_vlans; - - /* If we have a port VLAN, then the VSI cannot have any VLANs - * configured, as all MAC/VLAN filters will be assigned to the PVID. - */ - if (vsi->info.pvid) - return false; - - /* Since we don't have a PVID, we know that if the device is in VLAN - * mode it must be because of a VLAN filter configured on this VSI. - */ - spin_lock_bh(&vsi->mac_filter_hash_lock); - have_vlans = i40e_is_vsi_in_vlan(vsi); - spin_unlock_bh(&vsi->mac_filter_hash_lock); - - return have_vlans; -} - -/** * i40e_ndo_set_vf_port_vlan * @netdev: network interface device structure * @vf_id: VF identifier @@ -4253,19 +4224,9 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; - if (i40e_vsi_has_vlans(vsi)) { - dev_err(&pf->pdev->dev, - "VF %d has already configured VLAN filters and the administrator is requesting a port VLAN override.\nPlease unload and reload the VF driver for this change to take effect.\n", - vf_id); - /* Administrator Error - knock the VF offline until he does - * the right thing by reconfiguring his network correctly - * and then reloading the VF driver. - */ - i40e_vc_disable_vf(vf); - /* During reset the VF got a new VSI, so refresh the pointer. */ - vsi = pf->vsi[vf->lan_vsi_idx]; - } - + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; /* Locked once because multiple functions below iterate list */ spin_lock_bh(&vsi->mac_filter_hash_lock); @@ -4641,7 +4602,7 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) goto out; vf->trusted = setting; - i40e_vc_disable_vf(vf); + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index e6e7c1da47fb..75635bd57cf6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -39,6 +39,7 @@ #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 #define PFX "iavf: " diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 5a359a0a20ec..144a77679359 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1776,6 +1776,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; + int i; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1786,7 +1787,7 @@ static int iavf_set_channels(struct net_device *netdev, /* All of these should have already been checked by ethtool before this * even gets to us, but just to be sure. */ - if (num_req > adapter->vsi_res->num_queue_pairs) + if (num_req == 0 || num_req > adapter->vsi_res->num_queue_pairs) return -EINVAL; if (num_req == adapter->num_active_queues) @@ -1798,6 +1799,20 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; iavf_schedule_reset(adapter); + + /* wait for the reset is done */ + for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { + msleep(IAVF_RESET_WAIT_MS); + if (adapter->flags & IAVF_FLAG_RESET_PENDING) + continue; + break; + } + if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->num_active_queues = num_req; + return -EOPNOTSUPP; + } + return 0; } @@ -1844,14 +1859,13 @@ static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, if (hfunc) *hfunc = ETH_RSS_HASH_TOP; - if (!indir) - return 0; - - memcpy(key, adapter->rss_key, adapter->rss_key_size); + if (key) + memcpy(key, adapter->rss_key, adapter->rss_key_size); - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - indir[i] = (u32)adapter->rss_lut[i]; + if (indir) + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 847d67e32a54..336e6bf95e48 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -697,6 +697,23 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) } /** + * iavf_restore_filters + * @adapter: board private structure + * + * Restore existing non MAC filters when VF netdev comes back up + **/ +static void iavf_restore_filters(struct iavf_adapter *adapter) +{ + /* re-add all VLAN filters */ + if (VLAN_ALLOWED(adapter)) { + u16 vid; + + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); + } +} + +/** * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data @@ -709,8 +726,11 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, if (!VLAN_ALLOWED(adapter)) return -EIO; + if (iavf_add_vlan(adapter, vid) == NULL) return -ENOMEM; + + set_bit(vid, adapter->vsi.active_vlans); return 0; } @@ -725,11 +745,13 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (VLAN_ALLOWED(adapter)) { - iavf_del_vlan(adapter, vid); - return 0; - } - return -EIO; + if (!VLAN_ALLOWED(adapter)) + return -EIO; + + iavf_del_vlan(adapter, vid); + clear_bit(vid, adapter->vsi.active_vlans); + + return 0; } /** @@ -1639,8 +1661,7 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); return 0; } - - if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) || (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { iavf_set_promiscuous(adapter, 0); return 0; @@ -2123,8 +2144,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); - iavf_free_queues(adapter); iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; @@ -2410,7 +2431,7 @@ static void iavf_adminq_task(struct work_struct *work) /* check for error indications */ val = rd32(hw, hw->aq.arq.len); - if (val == 0xdeadbeef) /* indicates device in reset */ + if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */ goto freedom; oldval = val; if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { @@ -3095,8 +3116,10 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, return -ENOMEM; while (!mutex_trylock(&adapter->crit_lock)) { - if (--count == 0) - goto err; + if (--count == 0) { + kfree(filter); + return err; + } udelay(1); } @@ -3107,11 +3130,11 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; err = iavf_parse_cls_flower(adapter, cls_flower, filter); - if (err < 0) + if (err) goto err; err = iavf_handle_tclass(adapter, tc, filter); - if (err < 0) + if (err) goto err; /* add filter to the list */ @@ -3308,6 +3331,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* Restore VLAN filters that were removed with IFF_DOWN */ + iavf_restore_filters(adapter); + iavf_configure(adapter); iavf_up_complete(adapter); @@ -3503,7 +3529,8 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) + if (adapter->vf_res && + !(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) features &= ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER); diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 6433c909c6b2..072391c494ce 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -25,6 +25,7 @@ #include <linux/io.h> #include <linux/dma-mapping.h> #include <linux/module.h> +#include <linux/property.h> #include <asm/checksum.h> @@ -239,6 +240,7 @@ ltq_etop_hw_init(struct net_device *dev) { struct ltq_etop_priv *priv = netdev_priv(dev); int i; + int err; ltq_pmu_enable(PMU_PPE); @@ -273,7 +275,13 @@ ltq_etop_hw_init(struct net_device *dev) if (IS_TX(i)) { ltq_dma_alloc_tx(&ch->dma); - request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv); + err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_tx", priv); + if (err) { + netdev_err(dev, + "Unable to get Tx DMA IRQ %d\n", + irq); + return err; + } } else if (IS_RX(i)) { ltq_dma_alloc_rx(&ch->dma); for (ch->dma.desc = 0; ch->dma.desc < LTQ_DESC_NUM; @@ -281,7 +289,13 @@ ltq_etop_hw_init(struct net_device *dev) if (ltq_etop_alloc_skb(ch)) return -ENOMEM; ch->dma.desc = 0; - request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv); + err = request_irq(irq, ltq_etop_dma_irq, 0, "etop_rx", priv); + if (err) { + netdev_err(dev, + "Unable to get Rx DMA IRQ %d\n", + irq); + return err; + } } ch->dma.irq = irq; } @@ -726,7 +740,7 @@ static struct platform_driver ltq_mii_driver = { }, }; -int __init +static int __init init_ltq_etop(void) { int ret = platform_driver_probe(<q_mii_driver, ltq_etop_probe); diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 62a97c46fba0..ef878973b859 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -429,12 +429,14 @@ static const struct of_device_id orion_mdio_match[] = { }; MODULE_DEVICE_TABLE(of, orion_mdio_match); +#ifdef CONFIG_ACPI static const struct acpi_device_id orion_mdio_acpi_match[] = { { "MRVL0100", BUS_TYPE_SMI }, { "MRVL0101", BUS_TYPE_XSMI }, { }, }; MODULE_DEVICE_TABLE(acpi, orion_mdio_acpi_match); +#endif static struct platform_driver orion_mdio_driver = { .probe = orion_mdio_probe, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index c7fd466a0efd..a09a507369ac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -236,10 +236,11 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, u64 lmt_addr, val, tbl_base; int pf, vf, num_vfs, hw_vfs; void __iomem *lmt_map_base; - int index = 0, off = 0; - int bytes_not_copied; int buf_size = 10240; + size_t off = 0; + int index = 0; char *buf; + int ret; /* don't allow partial reads */ if (*ppos != 0) @@ -303,15 +304,17 @@ static ssize_t rvu_dbg_lmtst_map_table_display(struct file *filp, } off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); - bytes_not_copied = copy_to_user(buffer, buf, off); + ret = min(off, count); + if (copy_to_user(buffer, buf, ret)) + ret = -EFAULT; kfree(buf); iounmap(lmt_map_base); - if (bytes_not_copied) - return -EFAULT; + if (ret < 0) + return ret; - *ppos = off; - return off; + *ppos = ret; + return ret; } RVU_DEBUG_FOPS(lmtst_map_table, lmtst_map_table_display, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index f71ec4d9d68e..8eaa24d865c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -339,6 +339,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_PAGE_FAULT_RESUME: case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS: case MLX5_CMD_OP_DEALLOC_SF: + case MLX5_CMD_OP_DESTROY_UCTX: + case MLX5_CMD_OP_DESTROY_UMEM: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -464,9 +466,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT: case MLX5_CMD_OP_QUERY_GENERAL_OBJECT: case MLX5_CMD_OP_CREATE_UCTX: - case MLX5_CMD_OP_DESTROY_UCTX: case MLX5_CMD_OP_CREATE_UMEM: - case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: case MLX5_CMD_OP_MODIFY_XRQ: case MLX5_CMD_OP_RELEASE_XRQ_ERROR: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 02e77ffe5c3e..5371ad0a12eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -164,13 +164,14 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) MLX5_SET(destroy_cq_in, in, cqn, cq->cqn); MLX5_SET(destroy_cq_in, in, uid, cq->uid); err = mlx5_cmd_exec_in(dev, destroy_cq, in); + if (err) + return err; synchronize_irq(cq->irqn); - mlx5_cq_put(cq); wait_for_completion(&cq->free); - return err; + return 0; } EXPORT_SYMBOL(mlx5_core_destroy_cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 07c8d9811bc8..10d195042ab5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -507,6 +507,8 @@ void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) if (!mlx5_debugfs_root) return; - if (cq->dbg) + if (cq->dbg) { rem_res_tree(cq->dbg); + cq->dbg = NULL; + } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c1c6e74c79c4..2445e2ae3324 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -1356,9 +1356,13 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; + int err; + if (!priv) { NL_SET_ERR_MSG_MOD(extack, "offload of ct action isn't available"); @@ -1369,6 +1373,17 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, attr->ct_attr.ct_action = act->ct.action; attr->ct_attr.nf_ft = act->ct.flow_table; + if (!clear_action) + goto out; + + err = mlx5_tc_ct_entry_set_registers(priv, mod_acts, 0, 0, 0, 0); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to set registers for ct clear"); + return err; + } + attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; + +out: return 0; } @@ -1898,23 +1913,16 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, memcpy(pre_ct_attr, attr, attr_sz); - err = mlx5_tc_ct_entry_set_registers(ct_priv, mod_acts, 0, 0, 0, 0); - if (err) { - ct_dbg("Failed to set register for ct clear"); - goto err_set_registers; - } - mod_hdr = mlx5_modify_header_alloc(priv->mdev, ct_priv->ns_type, mod_acts->num_actions, mod_acts->actions); if (IS_ERR(mod_hdr)) { err = PTR_ERR(mod_hdr); ct_dbg("Failed to add create ct clear mod hdr"); - goto err_set_registers; + goto err_mod_hdr; } pre_ct_attr->modify_hdr = mod_hdr; - pre_ct_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; rule = mlx5_tc_rule_insert(priv, orig_spec, pre_ct_attr); if (IS_ERR(rule)) { @@ -1930,7 +1938,7 @@ __mlx5_tc_ct_flow_offload_clear(struct mlx5_tc_ct_priv *ct_priv, err_insert: mlx5_modify_header_dealloc(priv->mdev, mod_hdr); -err_set_registers: +err_mod_hdr: netdev_warn(priv->netdev, "Failed to offload ct clear flow, err %d\n", err); kfree(pre_ct_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 363329f4aac6..99662af1e41a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -110,6 +110,7 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec); int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack); @@ -172,6 +173,7 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) static inline int mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *attr, + struct mlx5e_tc_mod_hdr_acts *mod_acts, const struct flow_action_entry *act, struct netlink_ext_ack *extack) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 8f64f2c8895a..b689701ac7d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -102,6 +102,7 @@ struct mlx5e_tc_flow { refcount_t refcnt; struct rcu_head rcu_head; struct completion init_done; + struct completion del_hw_done; int tunnel_id; /* the mapped tunnel id of this flow */ struct mlx5_flow_attr *attr; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 660cca73c36c..042b1abe1437 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -245,8 +245,14 @@ static void mlx5e_take_tmp_flow(struct mlx5e_tc_flow *flow, struct list_head *flow_list, int index) { - if (IS_ERR(mlx5e_flow_get(flow))) + if (IS_ERR(mlx5e_flow_get(flow))) { + /* Flow is being deleted concurrently. Wait for it to be + * unoffloaded from hardware, otherwise deleting encap will + * fail. + */ + wait_for_completion(&flow->del_hw_done); return; + } wait_for_completion(&flow->init_done); flow->tmp_entry_index = index; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index 62abce008c7b..a2a9f68579dd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -55,6 +55,7 @@ struct mlx5e_ktls_offload_context_rx { DECLARE_BITMAP(flags, MLX5E_NUM_PRIV_RX_FLAGS); /* resync */ + spinlock_t lock; /* protects resync fields */ struct mlx5e_ktls_rx_resync_ctx resync; struct list_head list; }; @@ -386,14 +387,18 @@ static void resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_r struct mlx5e_icosq *sq; bool trigger_poll; - memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); - sq = &c->async_icosq; ktls_resync = sq->ktls_resync; + trigger_poll = false; spin_lock_bh(&ktls_resync->lock); - list_add_tail(&priv_rx->list, &ktls_resync->list); - trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + spin_lock_bh(&priv_rx->lock); + memcpy(info->rec_seq, &priv_rx->resync.sw_rcd_sn_be, sizeof(info->rec_seq)); + if (list_empty(&priv_rx->list)) { + list_add_tail(&priv_rx->list, &ktls_resync->list); + trigger_poll = !test_and_set_bit(MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC, &sq->state); + } + spin_unlock_bh(&priv_rx->lock); spin_unlock_bh(&ktls_resync->lock); if (!trigger_poll) @@ -617,6 +622,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, if (err) goto err_create_key; + INIT_LIST_HEAD(&priv_rx->list); + spin_lock_init(&priv_rx->lock); priv_rx->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; @@ -730,10 +737,14 @@ bool mlx5e_ktls_rx_handle_resync_list(struct mlx5e_channel *c, int budget) priv_rx = list_first_entry(&local_list, struct mlx5e_ktls_offload_context_rx, list); + spin_lock(&priv_rx->lock); cseg = post_static_params(sq, priv_rx); - if (IS_ERR(cseg)) + if (IS_ERR(cseg)) { + spin_unlock(&priv_rx->lock); break; - list_del(&priv_rx->list); + } + list_del_init(&priv_rx->list); + spin_unlock(&priv_rx->lock); db_cseg = cseg; } if (db_cseg) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 835caa1c7b74..3d45f4ae80c0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1600,6 +1600,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); } + complete_all(&flow->del_hw_done); if (mlx5_flow_has_geneve_opt(flow)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); @@ -3607,7 +3608,9 @@ parse_tc_nic_actions(struct mlx5e_priv *priv, attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; @@ -4276,7 +4279,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, NL_SET_ERR_MSG_MOD(extack, "Sample action with connection tracking is not supported"); return -EOPNOTSUPP; } - err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, act, extack); + err = mlx5_tc_ct_parse_action(get_ct_priv(priv), attr, + &parse_attr->mod_hdr_acts, + act, extack); if (err) return err; @@ -4465,6 +4470,7 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, INIT_LIST_HEAD(&flow->l3_to_l2_reformat); refcount_set(&flow->refcnt, 1); init_completion(&flow->init_done); + init_completion(&flow->del_hw_done); *__flow = flow; *__parse_attr = parse_attr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ec136b499204..51a8cecc4a7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1305,12 +1305,17 @@ abort: */ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) { + bool toggle_lag; int ret; if (!mlx5_esw_allowed(esw)) return 0; - mlx5_lag_disable_change(esw->dev); + toggle_lag = esw->mode == MLX5_ESWITCH_NONE; + + if (toggle_lag) + mlx5_lag_disable_change(esw->dev); + down_write(&esw->mode_lock); if (esw->mode == MLX5_ESWITCH_NONE) { ret = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_LEGACY, num_vfs); @@ -1324,7 +1329,10 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) esw->esw_funcs.num_vfs = num_vfs; } up_write(&esw->mode_lock); - mlx5_lag_enable_change(esw->dev); + + if (toggle_lag) + mlx5_lag_enable_change(esw->dev); + return ret; } @@ -1572,6 +1580,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->enabled_vports = 0; esw->mode = MLX5_ESWITCH_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; + else + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); @@ -1934,7 +1947,7 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1948,7 +1961,7 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) struct mlx5_eswitch *esw; esw = dev->priv.eswitch; - return mlx5_esw_allowed(esw) ? esw->offloads.encap : + return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) ? esw->offloads.encap : DEVLINK_ESWITCH_ENCAP_MODE_NONE; } EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f4eaa5893886..a46455694f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3183,12 +3183,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) u64 mapping_id; int err; - if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && - MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap)) - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; - else - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - mutex_init(&esw->offloads.termtbl_mutex); mlx5_rdma_enable_roce(esw->dev); @@ -3286,7 +3280,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw) esw_offloads_metadata_uninit(esw); mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) @@ -3630,7 +3623,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, *encap = esw->offloads.encap; unlock: up_write(&esw->mode_lock); - return 0; + return err; } static bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 31c99d53faf7..7e0e04cf26f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,7 +40,7 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) -#define MLX5_SF_NUM_COUNTERS_BULK 6 +#define MLX5_SF_NUM_COUNTERS_BULK 8 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 48d2ea690d7a..4ddf6b330a44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -615,6 +615,7 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, bool is_bonded, is_in_lag, mode_supported; int bond_status = 0; int num_slaves = 0; + int changed = 0; int idx; if (!netif_is_lag_master(upper)) @@ -653,27 +654,27 @@ static int mlx5_handle_changeupper_event(struct mlx5_lag *ldev, */ is_in_lag = num_slaves == MLX5_MAX_PORTS && bond_status == 0x3; - if (!mlx5_lag_is_ready(ldev) && is_in_lag) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, PF is configured with more than 64 VFs"); - return 0; - } - /* Lag mode must be activebackup or hash. */ mode_supported = tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP || tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH; - if (is_in_lag && !mode_supported) - NL_SET_ERR_MSG_MOD(info->info.extack, - "Can't activate LAG offload, TX type isn't supported"); - is_bonded = is_in_lag && mode_supported; if (tracker->is_bonded != is_bonded) { tracker->is_bonded = is_bonded; - return 1; + changed = 1; } - return 0; + if (!is_in_lag) + return changed; + + if (!mlx5_lag_is_ready(ldev)) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, PF is configured with more than 64 VFs"); + else if (!mode_supported) + NL_SET_ERR_MSG_MOD(info->info.extack, + "Can't activate LAG offload, TX type isn't supported"); + + return changed; } static int mlx5_handle_changelowerstate_event(struct mlx5_lag *ldev, @@ -716,9 +717,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this, ldev = container_of(this, struct mlx5_lag, nb); - if (!mlx5_lag_is_ready(ldev) && event == NETDEV_CHANGELOWERSTATE) - return NOTIFY_DONE; - tracker = ldev->tracker; switch (event) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 49089cbe897c..8cbd36c82b3b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -135,25 +135,14 @@ static void dr_domain_fill_uplink_caps(struct mlx5dr_domain *dmn, static int dr_domain_query_vport(struct mlx5dr_domain *dmn, u16 vport_number, + bool other_vport, struct mlx5dr_cmd_vport_cap *vport_caps) { - u16 cmd_vport = vport_number; - bool other_vport = true; int ret; - if (vport_number == MLX5_VPORT_UPLINK) { - dr_domain_fill_uplink_caps(dmn, vport_caps); - return 0; - } - - if (dmn->info.caps.is_ecpf && vport_number == MLX5_VPORT_ECPF) { - other_vport = false; - cmd_vport = 0; - } - ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->icm_address_rx, &vport_caps->icm_address_tx); if (ret) @@ -161,7 +150,7 @@ static int dr_domain_query_vport(struct mlx5dr_domain *dmn, ret = mlx5dr_cmd_query_gvmi(dmn->mdev, other_vport, - cmd_vport, + vport_number, &vport_caps->vport_gvmi); if (ret) return ret; @@ -176,9 +165,15 @@ static int dr_domain_query_esw_mngr(struct mlx5dr_domain *dmn) { return dr_domain_query_vport(dmn, dmn->info.caps.is_ecpf ? MLX5_VPORT_ECPF : 0, + false, &dmn->info.caps.vports.esw_manager_caps); } +static void dr_domain_query_uplink(struct mlx5dr_domain *dmn) +{ + dr_domain_fill_uplink_caps(dmn, &dmn->info.caps.vports.uplink_caps); +} + static struct mlx5dr_cmd_vport_cap * dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { @@ -190,7 +185,7 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) if (!vport_caps) return NULL; - ret = dr_domain_query_vport(dmn, vport, vport_caps); + ret = dr_domain_query_vport(dmn, vport, true, vport_caps); if (ret) { kvfree(vport_caps); return NULL; @@ -207,16 +202,26 @@ dr_domain_add_vport_cap(struct mlx5dr_domain *dmn, u16 vport) return vport_caps; } +static bool dr_domain_is_esw_mgr_vport(struct mlx5dr_domain *dmn, u16 vport) +{ + struct mlx5dr_cmd_caps *caps = &dmn->info.caps; + + return (caps->is_ecpf && vport == MLX5_VPORT_ECPF) || + (!caps->is_ecpf && vport == 0); +} + struct mlx5dr_cmd_vport_cap * mlx5dr_domain_get_vport_cap(struct mlx5dr_domain *dmn, u16 vport) { struct mlx5dr_cmd_caps *caps = &dmn->info.caps; struct mlx5dr_cmd_vport_cap *vport_caps; - if ((caps->is_ecpf && vport == MLX5_VPORT_ECPF) || - (!caps->is_ecpf && vport == 0)) + if (dr_domain_is_esw_mgr_vport(dmn, vport)) return &caps->vports.esw_manager_caps; + if (vport == MLX5_VPORT_UPLINK) + return &caps->vports.uplink_caps; + vport_load: vport_caps = xa_load(&caps->vports.vports_caps_xa, vport); if (vport_caps) @@ -241,17 +246,6 @@ static void dr_domain_clear_vports(struct mlx5dr_domain *dmn) } } -static int dr_domain_query_uplink(struct mlx5dr_domain *dmn) -{ - struct mlx5dr_cmd_vport_cap *vport_caps; - - vport_caps = mlx5dr_domain_get_vport_cap(dmn, MLX5_VPORT_UPLINK); - if (!vport_caps) - return -EINVAL; - - return 0; -} - static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, struct mlx5dr_domain *dmn) { @@ -281,11 +275,7 @@ static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, goto free_vports_caps_xa; } - ret = dr_domain_query_uplink(dmn); - if (ret) { - mlx5dr_err(dmn, "Failed to query uplink vport caps (err: %d)", ret); - goto free_vports_caps_xa; - } + dr_domain_query_uplink(dmn); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 75c775bee351..793365242e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -924,11 +924,12 @@ static int dr_matcher_init(struct mlx5dr_matcher *matcher, /* Check that all mask data was consumed */ for (i = 0; i < consumed_mask.match_sz; i++) { - if (consumed_mask.match_buf[i]) { - mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); - ret = -EOPNOTSUPP; - goto free_consumed_mask; - } + if (!((u8 *)consumed_mask.match_buf)[i]) + continue; + + mlx5dr_dbg(dmn, "Match param mask contains unsupported parameters\n"); + ret = -EOPNOTSUPP; + goto free_consumed_mask; } ret = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 3028b776da00..2333c2439c28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -764,6 +764,7 @@ struct mlx5dr_roce_cap { struct mlx5dr_vports { struct mlx5dr_cmd_vport_cap esw_manager_caps; + struct mlx5dr_cmd_vport_cap uplink_caps; struct xarray vports_caps_xa; }; diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index cc2d907c4c4b..23a336c5096e 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -392,7 +392,7 @@ static int sis96x_get_mac_addr(struct pci_dev *pci_dev, /* get MAC address from EEPROM */ for (i = 0; i < 3; i++) addr[i] = read_eeprom(ioaddr, i + EEPROMMACAddr); - eth_hw_addr_set(net_dev, (u8 *)addr); + eth_hw_addr_set(net_dev, (u8 *)addr); rc = 1; break; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 85208128f135..b7c2579c963b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -485,8 +485,28 @@ static int socfpga_dwmac_resume(struct device *dev) } #endif /* CONFIG_PM_SLEEP */ -static SIMPLE_DEV_PM_OPS(socfpga_dwmac_pm_ops, stmmac_suspend, - socfpga_dwmac_resume); +static int __maybe_unused socfpga_dwmac_runtime_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + stmmac_bus_clks_config(priv, false); + + return 0; +} + +static int __maybe_unused socfpga_dwmac_runtime_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + return stmmac_bus_clks_config(priv, true); +} + +static const struct dev_pm_ops socfpga_dwmac_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(stmmac_suspend, socfpga_dwmac_resume) + SET_RUNTIME_PM_OPS(socfpga_dwmac_runtime_suspend, socfpga_dwmac_runtime_resume, NULL) +}; static const struct socfpga_dwmac_ops socfpga_gen5_ops = { .set_phy_mode = socfpga_gen5_set_phy_mode, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d3f350c25b9b..2eb284576336 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -511,6 +511,14 @@ bool stmmac_eee_init(struct stmmac_priv *priv) return true; } +static inline u32 stmmac_cdc_adjust(struct stmmac_priv *priv) +{ + /* Correct the clk domain crossing(CDC) error */ + if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) + return (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; + return 0; +} + /* stmmac_get_tx_hwtstamp - get HW TX timestamps * @priv: driver private structure * @p : descriptor pointer @@ -524,7 +532,6 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, { struct skb_shared_hwtstamps shhwtstamp; bool found = false; - s64 adjust = 0; u64 ns = 0; if (!priv->hwts_tx_en) @@ -543,12 +550,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, } if (found) { - /* Correct the clk domain crossing(CDC) error */ - if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) { - adjust += -(2 * (NSEC_PER_SEC / - priv->plat->clk_ptp_rate)); - ns += adjust; - } + ns -= stmmac_cdc_adjust(priv); memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -573,7 +575,6 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, { struct skb_shared_hwtstamps *shhwtstamp = NULL; struct dma_desc *desc = p; - u64 adjust = 0; u64 ns = 0; if (!priv->hwts_rx_en) @@ -586,11 +587,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) { stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns); - /* Correct the clk domain crossing(CDC) error */ - if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) { - adjust += 2 * (NSEC_PER_SEC / priv->plat->clk_ptp_rate); - ns -= adjust; - } + ns -= stmmac_cdc_adjust(priv); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index bfdf89e54752..8a19a06b505d 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -306,7 +306,6 @@ static void sp_setup(struct net_device *dev) { /* Finish setting up the DEVICE info. */ dev->netdev_ops = &sp_netdev_ops; - dev->needs_free_netdev = true; dev->mtu = SIXP_MTU; dev->hard_header_len = AX25_MAX_HEADER_LEN; dev->header_ops = &ax25_header_ops; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 5528d97110d5..ef790fd0ab56 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -853,6 +853,7 @@ static void ipa_endpoint_init_hol_block_timer(struct ipa_endpoint *endpoint, u32 offset; u32 val; + /* This should only be changed when HOL_BLOCK_EN is disabled */ offset = IPA_REG_ENDP_INIT_HOL_BLOCK_TIMER_N_OFFSET(endpoint_id); val = hol_block_timer_val(ipa, microseconds); iowrite32(val, ipa->reg_virt + offset); @@ -868,6 +869,9 @@ ipa_endpoint_init_hol_block_enable(struct ipa_endpoint *endpoint, bool enable) val = enable ? HOL_BLOCK_EN_FMASK : 0; offset = IPA_REG_ENDP_INIT_HOL_BLOCK_EN_N_OFFSET(endpoint_id); iowrite32(val, endpoint->ipa->reg_virt + offset); + /* When enabling, the register must be written twice for IPA v4.5+ */ + if (enable && endpoint->ipa->version >= IPA_VERSION_4_5) + iowrite32(val, endpoint->ipa->reg_virt + offset); } void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa) @@ -880,6 +884,7 @@ void ipa_endpoint_modem_hol_block_clear_all(struct ipa *ipa) if (endpoint->toward_ipa || endpoint->ee_id != GSI_EE_MODEM) continue; + ipa_endpoint_init_hol_block_enable(endpoint, false); ipa_endpoint_init_hol_block_timer(endpoint, 0); ipa_endpoint_init_hol_block_enable(endpoint, true); } diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c index e3da95d69409..06cec7199382 100644 --- a/drivers/net/ipa/ipa_resource.c +++ b/drivers/net/ipa/ipa_resource.c @@ -52,7 +52,7 @@ static bool ipa_resource_limits_valid(struct ipa *ipa, return false; } - group_count = data->rsrc_group_src_count; + group_count = data->rsrc_group_dst_count; if (!group_count || group_count > IPA_RESOURCE_GROUP_MAX) return false; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fecc9a1d293a..1572878c3403 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1010,6 +1010,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; + struct netdev_queue *queue; struct tun_file *tfile; int len = skb->len; @@ -1054,6 +1055,10 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) if (ptr_ring_produce(&tfile->tx_ring, skb)) goto drop; + /* NETIF_F_LLTX requires to do our own update of trans_start */ + queue = netdev_get_tx_queue(dev, txq); + queue->trans_start = jiffies; + /* Notify and wake up reader process */ if (tfile->flags & TUN_FASYNC) kill_fasync(&tfile->fasync, SIGIO, POLL_IN); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 4a02f33f0643..f9877a3e83ac 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9603,12 +9603,9 @@ static int rtl8152_probe(struct usb_interface *intf, netdev->hw_features &= ~NETIF_F_RXCSUM; } - if (le16_to_cpu(udev->descriptor.idVendor) == VENDOR_ID_LENOVO) { - switch (le16_to_cpu(udev->descriptor.idProduct)) { - case DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2: - case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2: - tp->lenovo_macpassthru = 1; - } + if (udev->parent && + le16_to_cpu(udev->parent->descriptor.idVendor) == VENDOR_ID_LENOVO) { + tp->lenovo_macpassthru = 1; } if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial && diff --git a/drivers/platform/mellanox/mlxreg-lc.c b/drivers/platform/mellanox/mlxreg-lc.c index 0b7f58feb701..c897a2f15840 100644 --- a/drivers/platform/mellanox/mlxreg-lc.c +++ b/drivers/platform/mellanox/mlxreg-lc.c @@ -413,7 +413,7 @@ mlxreg_lc_create_static_devices(struct mlxreg_lc *mlxreg_lc, struct mlxreg_hotpl int size) { struct mlxreg_hotplug_device *dev = devs; - int i; + int i, ret; /* Create static I2C device feeding by auxiliary or main power. */ for (i = 0; i < size; i++, dev++) { @@ -423,6 +423,7 @@ mlxreg_lc_create_static_devices(struct mlxreg_lc *mlxreg_lc, struct mlxreg_hotpl dev->brdinfo->type, dev->nr, dev->brdinfo->addr); dev->adapter = NULL; + ret = PTR_ERR(dev->client); goto fail_create_static_devices; } } @@ -435,7 +436,7 @@ fail_create_static_devices: i2c_unregister_device(dev->client); dev->client = NULL; } - return IS_ERR(dev->client); + return ret; } static void diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index d4c079f4afc6..7400bc5da5be 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -185,7 +185,7 @@ config ACER_WMI config AMD_PMC tristate "AMD SoC PMC driver" - depends on ACPI && PCI + depends on ACPI && PCI && RTC_CLASS help The driver provides support for AMD Power Management Controller primarily responsible for S2Idle transactions that are driven from diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig index 2fffa57e596e..fe224a54f24c 100644 --- a/drivers/platform/x86/dell/Kconfig +++ b/drivers/platform/x86/dell/Kconfig @@ -187,7 +187,7 @@ config DELL_WMI_AIO config DELL_WMI_DESCRIPTOR tristate - default m + default n depends on ACPI_WMI config DELL_WMI_LED diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c index b183967ecfb7..435a91fe2568 100644 --- a/drivers/platform/x86/hp_accel.c +++ b/drivers/platform/x86/hp_accel.c @@ -331,9 +331,11 @@ static int lis3lv02d_probe(struct platform_device *device) INIT_WORK(&hpled_led.work, delayed_set_status_worker); ret = led_classdev_register(NULL, &hpled_led.led_classdev); if (ret) { + i8042_remove_filter(hp_accel_i8042_filter); lis3lv02d_joystick_disable(&lis3_dev); lis3lv02d_poweroff(&lis3_dev); flush_work(&hpled_led.work); + lis3lv02d_remove_fs(&lis3_dev); return ret; } diff --git a/drivers/platform/x86/samsung-laptop.c b/drivers/platform/x86/samsung-laptop.c index 7ee010aa740a..c1d9ed9b7b67 100644 --- a/drivers/platform/x86/samsung-laptop.c +++ b/drivers/platform/x86/samsung-laptop.c @@ -152,7 +152,7 @@ struct sabi_config { static const struct sabi_config sabi_configs[] = { { - /* I don't know if it is really 2, but it it is + /* I don't know if it is really 2, but it is * less than 3 anyway */ .sabi_version = 2, diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 9472aae72df2..c4d9c45350f7 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -888,8 +888,10 @@ static int tlmi_analyze(void) break; if (!item) break; - if (!*item) + if (!*item) { + kfree(item); continue; + } /* It is not allowed to have '/' for file name. Convert it into '\'. */ strreplace(item, '/', '\\'); @@ -902,6 +904,7 @@ static int tlmi_analyze(void) setting = kzalloc(sizeof(*setting), GFP_KERNEL); if (!setting) { ret = -ENOMEM; + kfree(item); goto fail_clear_attr; } setting->index = i; @@ -916,7 +919,6 @@ static int tlmi_analyze(void) } kobject_init(&setting->kobj, &tlmi_attr_setting_ktype); tlmi_priv.setting[i] = setting; - tlmi_priv.settings_count++; kfree(item); } @@ -983,7 +985,12 @@ static void tlmi_remove(struct wmi_device *wdev) static int tlmi_probe(struct wmi_device *wdev, const void *context) { - tlmi_analyze(); + int ret; + + ret = tlmi_analyze(); + if (ret) + return ret; + return tlmi_sysfs_init(); } diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h index f8e26823075f..2ce5086a5af2 100644 --- a/drivers/platform/x86/think-lmi.h +++ b/drivers/platform/x86/think-lmi.h @@ -55,7 +55,6 @@ struct tlmi_attr_setting { struct think_lmi { struct wmi_device *wmi_device; - int settings_count; bool can_set_bios_settings; bool can_get_bios_selections; bool can_set_bios_password; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9c632df734bb..b3ac9c3f3b7c 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -1105,15 +1105,6 @@ static int tpacpi_rfk_update_swstate(const struct tpacpi_rfk *tp_rfk) return status; } -/* Query FW and update rfkill sw state for all rfkill switches */ -static void tpacpi_rfk_update_swstate_all(void) -{ - unsigned int i; - - for (i = 0; i < TPACPI_RFK_SW_MAX; i++) - tpacpi_rfk_update_swstate(tpacpi_rfkill_switches[i]); -} - /* * Sync the HW-blocking state of all rfkill switches, * do notice it causes the rfkill core to schedule uevents @@ -3074,9 +3065,6 @@ static void tpacpi_send_radiosw_update(void) if (wlsw == TPACPI_RFK_RADIO_OFF) tpacpi_rfk_update_hwblock_state(true); - /* Sync sw blocking state */ - tpacpi_rfk_update_swstate_all(); - /* Sync hw blocking state last if it is hw-unblocked */ if (wlsw == TPACPI_RFK_RADIO_ON) tpacpi_rfk_update_hwblock_state(false); @@ -8766,6 +8754,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '2', 'E', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (1st gen) */ TPACPI_Q_LNV3('N', '2', 'O', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (2nd gen) */ TPACPI_Q_LNV3('N', '2', 'V', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (3nd gen) */ + TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ }; diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 44faa3a74db6..b740866b228d 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -166,16 +166,13 @@ static struct dtpm_ops dtpm_ops = { static int cpuhp_dtpm_cpu_offline(unsigned int cpu) { - struct em_perf_domain *pd; struct dtpm_cpu *dtpm_cpu; - pd = em_cpu_get(cpu); - if (!pd) - return -EINVAL; - dtpm_cpu = per_cpu(dtpm_per_cpu, cpu); + if (dtpm_cpu) + dtpm_update_power(&dtpm_cpu->dtpm); - return dtpm_update_power(&dtpm_cpu->dtpm); + return 0; } static int cpuhp_dtpm_cpu_online(unsigned int cpu) diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 6bc5791a7ec5..08e429a06922 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -1699,12 +1699,9 @@ static int initialize_dco_operating_mode(struct idtcm_channel *channel) /* PTP Hardware Clock interface */ -/** +/* * Maximum absolute value for write phase offset in picoseconds * - * @channel: channel - * @delta_ns: delta in nanoseconds - * * Destination signed register is 32-bit register in resolution of 50ps * * 0x7fffffff * 50 = 2147483647 * 50 = 107374182350 diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 34f943c8c9fd..0f1b5a7d2a89 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -1304,10 +1304,11 @@ ptp_ocp_register_ext(struct ptp_ocp *bp, struct ocp_resource *r) if (!ext) return -ENOMEM; - err = -EINVAL; ext->mem = ptp_ocp_get_mem(bp, r); - if (!ext->mem) + if (IS_ERR(ext->mem)) { + err = PTR_ERR(ext->mem); goto out; + } ext->bp = bp; ext->info = r->extra; @@ -1371,8 +1372,8 @@ ptp_ocp_register_mem(struct ptp_ocp *bp, struct ocp_resource *r) void __iomem *mem; mem = ptp_ocp_get_mem(bp, r); - if (!mem) - return -EINVAL; + if (IS_ERR(mem)) + return PTR_ERR(mem); bp_assign_entry(bp, r, mem); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 8b3d268ac63c..b808c94641fa 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -37,6 +37,7 @@ #define CQSPI_NEEDS_WR_DELAY BIT(0) #define CQSPI_DISABLE_DAC_MODE BIT(1) #define CQSPI_SUPPORT_EXTERNAL_DMA BIT(2) +#define CQSPI_NO_SUPPORT_WR_COMPLETION BIT(3) /* Capabilities */ #define CQSPI_SUPPORTS_OCTAL BIT(0) @@ -86,6 +87,7 @@ struct cqspi_st { struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT]; bool use_dma_read; u32 pd_dev_id; + bool wr_completion; }; struct cqspi_driver_platdata { @@ -996,9 +998,11 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata, * polling on the controller's side. spinand and spi-nor will take * care of polling the status register. */ - reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL); - reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL; - writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL); + if (cqspi->wr_completion) { + reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL); + reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL; + writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL); + } reg = readl(reg_base + CQSPI_REG_SIZE); reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK; @@ -1736,6 +1740,10 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk); master->max_speed_hz = cqspi->master_ref_clk_hz; + + /* write completion is supported by default */ + cqspi->wr_completion = true; + ddata = of_device_get_match_data(dev); if (ddata) { if (ddata->quirks & CQSPI_NEEDS_WR_DELAY) @@ -1747,6 +1755,8 @@ static int cqspi_probe(struct platform_device *pdev) cqspi->use_direct_mode = true; if (ddata->quirks & CQSPI_SUPPORT_EXTERNAL_DMA) cqspi->use_dma_read = true; + if (ddata->quirks & CQSPI_NO_SUPPORT_WR_COMPLETION) + cqspi->wr_completion = false; if (of_device_is_compatible(pdev->dev.of_node, "xlnx,versal-ospi-1.0")) @@ -1859,6 +1869,10 @@ static const struct cqspi_driver_platdata intel_lgm_qspi = { .quirks = CQSPI_DISABLE_DAC_MODE, }; +static const struct cqspi_driver_platdata socfpga_qspi = { + .quirks = CQSPI_NO_SUPPORT_WR_COMPLETION, +}; + static const struct cqspi_driver_platdata versal_ospi = { .hwcaps_mask = CQSPI_SUPPORTS_OCTAL, .quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_SUPPORT_EXTERNAL_DMA, @@ -1887,6 +1901,10 @@ static const struct of_device_id cqspi_dt_ids[] = { .compatible = "xlnx,versal-ospi-1.0", .data = (void *)&versal_ospi, }, + { + .compatible = "intel,socfpga-qspi", + .data = (void *)&socfpga_qspi, + }, { /* end of table */ } }; diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 5d98611dd999..c72e501c270f 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -912,7 +912,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev) ret = devm_spi_register_controller(&pdev->dev, controller); if (ret < 0) { - dev_err(&pdev->dev, "spi_register_controller error.\n"); + dev_err_probe(&pdev->dev, ret, "spi_register_controller error: %i\n", ret); goto out_pm_get; } diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c index 27a446faf143..e2affaee4e76 100644 --- a/drivers/spi/spi-geni-qcom.c +++ b/drivers/spi/spi-geni-qcom.c @@ -491,22 +491,26 @@ static int spi_geni_grab_gpi_chan(struct spi_geni_master *mas) int ret; mas->tx = dma_request_chan(mas->dev, "tx"); - ret = dev_err_probe(mas->dev, IS_ERR(mas->tx), "Failed to get tx DMA ch\n"); - if (ret < 0) + if (IS_ERR(mas->tx)) { + ret = dev_err_probe(mas->dev, PTR_ERR(mas->tx), + "Failed to get tx DMA ch\n"); goto err_tx; + } mas->rx = dma_request_chan(mas->dev, "rx"); - ret = dev_err_probe(mas->dev, IS_ERR(mas->rx), "Failed to get rx DMA ch\n"); - if (ret < 0) + if (IS_ERR(mas->rx)) { + ret = dev_err_probe(mas->dev, PTR_ERR(mas->rx), + "Failed to get rx DMA ch\n"); goto err_rx; + } return 0; err_rx: + mas->rx = NULL; dma_release_channel(mas->tx); - mas->tx = NULL; err_tx: - mas->rx = NULL; + mas->tx = NULL; return ret; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index b23e675953e1..fdd530b150a7 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3099,12 +3099,6 @@ void spi_unregister_controller(struct spi_controller *ctlr) device_del(&ctlr->dev); - /* Release the last reference on the controller if its driver - * has not yet been converted to devm_spi_alloc_master/slave(). - */ - if (!ctlr->devm_allocated) - put_device(&ctlr->dev); - /* free bus id */ mutex_lock(&board_lock); if (found == ctlr) @@ -3113,6 +3107,12 @@ void spi_unregister_controller(struct spi_controller *ctlr) if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) mutex_unlock(&ctlr->add_lock); + + /* Release the last reference on the controller if its driver + * has not yet been converted to devm_spi_alloc_master/slave(). + */ + if (!ctlr->devm_allocated) + put_device(&ctlr->dev); } EXPORT_SYMBOL_GPL(spi_unregister_controller); diff --git a/drivers/video/console/sticon.c b/drivers/video/console/sticon.c index 1b451165311c..40496e9e9b43 100644 --- a/drivers/video/console/sticon.c +++ b/drivers/video/console/sticon.c @@ -332,13 +332,13 @@ static u8 sticon_build_attr(struct vc_data *conp, u8 color, bool blink, bool underline, bool reverse, bool italic) { - u8 attr = ((color & 0x70) >> 1) | ((color & 7)); + u8 fg = color & 7; + u8 bg = (color & 0x70) >> 4; - if (reverse) { - color = ((color >> 3) & 0x7) | ((color & 0x7) << 3); - } - - return attr; + if (reverse) + return (fg << 3) | bg; + else + return (bg << 3) | fg; } static void sticon_invert_region(struct vc_data *conp, u16 *p, int count) diff --git a/fs/attr.c b/fs/attr.c index 473d21b3a86d..66899b6e9bd8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -35,7 +35,7 @@ static bool chown_ok(struct user_namespace *mnt_userns, kuid_t uid) { kuid_t kuid = i_uid_into_mnt(mnt_userns, inode); - if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid)) + if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, inode->i_uid)) return true; if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; @@ -62,7 +62,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns, { kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) && - (in_group_p(gid) || gid_eq(gid, kgid))) + (in_group_p(gid) || gid_eq(gid, inode->i_gid))) return true; if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 309516e6a968..43c89952b7d2 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -234,6 +234,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq, ordered_list); if (!test_bit(WORK_DONE_BIT, &work->flags)) break; + /* + * Orders all subsequent loads after reading WORK_DONE_BIT, + * paired with the smp_mb__before_atomic in btrfs_work_helper + * this guarantees that the ordered function will see all + * updates from ordinary work function. + */ + smp_rmb(); /* * we are going to call the ordered done function, but @@ -317,6 +324,13 @@ static void btrfs_work_helper(struct work_struct *normal_work) thresh_exec_hook(wq); work->func(work); if (need_order) { + /* + * Ensures all memory accesses done in the work function are + * ordered before setting the WORK_DONE_BIT. Ensuring the thread + * which is going to executed the ordered work sees them. + * Pairs with the smp_rmb in run_ordered_work. + */ + smp_mb__before_atomic(); set_bit(WORK_DONE_BIT, &work->flags); run_ordered_work(wq, work); } else { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59c3be8c1f4c..514ead6e93b6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3978,11 +3978,23 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct request_queue *q = bdev_get_queue(device->bdev); struct bio *bio = device->flush_bio; +#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY + /* + * When a disk has write caching disabled, we skip submission of a bio + * with flush and sync requests before writing the superblock, since + * it's not needed. However when the integrity checker is enabled, this + * results in reports that there are metadata blocks referred by a + * superblock that were not properly flushed. So don't skip the bio + * submission only when the integrity checker is enabled for the sake + * of simplicity, since this is a debug tool and not meant for use in + * non-debug builds. + */ + struct request_queue *q = bdev_get_queue(device->bdev); if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return; +#endif bio_reset(bio); bio->bi_end_io = btrfs_end_empty_barrier; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fb8cc9642ac4..92138ac2a4e2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3985,6 +3985,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) bool need_unlock; /* for mut. excl. ops lock */ int ret; + if (!arg) + btrfs_warn(fs_info, + "IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18"); + if (!capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 65cb0766e62d..9febb8025825 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -125,6 +125,7 @@ static inline size_t read_compress_length(const char *buf) static int copy_compressed_data_to_page(char *compressed_data, size_t compressed_size, struct page **out_pages, + unsigned long max_nr_page, u32 *cur_out, const u32 sectorsize) { @@ -133,6 +134,9 @@ static int copy_compressed_data_to_page(char *compressed_data, struct page *cur_page; char *kaddr; + if ((*cur_out / PAGE_SIZE) >= max_nr_page) + return -E2BIG; + /* * We never allow a segment header crossing sector boundary, previous * run should ensure we have enough space left inside the sector. @@ -161,6 +165,10 @@ static int copy_compressed_data_to_page(char *compressed_data, orig_out + compressed_size - *cur_out); kunmap(cur_page); + + if ((*cur_out / PAGE_SIZE) >= max_nr_page) + return -E2BIG; + cur_page = out_pages[*cur_out / PAGE_SIZE]; /* Allocate a new page */ if (!cur_page) { @@ -203,6 +211,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize; struct page *page_in = NULL; char *sizes_ptr; + const unsigned long max_nr_page = *out_pages; int ret = 0; /* Points to the file offset of input data */ u64 cur_in = start; @@ -210,6 +219,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, u32 cur_out = 0; u32 len = *total_out; + ASSERT(max_nr_page > 0); *out_pages = 0; *total_out = 0; *total_in = 0; @@ -248,7 +258,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, } ret = copy_compressed_data_to_page(workspace->cbuf, out_len, - pages, &cur_out, sectorsize); + pages, max_nr_page, + &cur_out, sectorsize); if (ret < 0) goto out; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf82ea6f54fb..8f6ceea33969 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -73,8 +73,8 @@ struct scrub_page { u64 physical_for_dev_replace; atomic_t refs; u8 mirror_num; - int have_csum:1; - int io_error:1; + unsigned int have_csum:1; + unsigned int io_error:1; u8 csum[BTRFS_CSUM_SIZE]; struct scrub_recover *recover; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 61ac57bcbf1a..0997e3cd74e9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7559,6 +7559,19 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) fs_info->fs_devices->total_rw_bytes = 0; /* + * Lockdep complains about possible circular locking dependency between + * a disk's open_mutex (struct gendisk.open_mutex), the rw semaphores + * used for freeze procection of a fs (struct super_block.s_writers), + * which we take when starting a transaction, and extent buffers of the + * chunk tree if we call read_one_dev() while holding a lock on an + * extent buffer of the chunk tree. Since we are mounting the filesystem + * and at this point there can't be any concurrent task modifying the + * chunk tree, to keep it simple, just skip locking on the chunk tree. + */ + ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); + path->skip_locking = 1; + + /* * Read all device items, and then all the chunk items. All * device items are found before any chunk item (their object id * is smaller than the lowest possible object id for a chunk @@ -7583,10 +7596,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) goto error; break; } - /* - * The nodes on level 1 are not locked but we don't need to do - * that during mount time as nothing else can access the tree - */ node = path->nodes[1]; if (node) { if (last_ra_node != node->start) { @@ -7614,7 +7623,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * requirement for chunk allocation, see the comment on * top of btrfs_chunk_alloc() for details. */ - ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); ret = read_one_chunk(&found_key, leaf, chunk); if (ret) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 7235d539e969..d67108489148 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -940,7 +940,7 @@ do_alloc: else if (height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); else - iomap->length = size - pos; + iomap->length = size - iomap->offset; } else if (flags & IOMAP_WRITE) { u64 alloc_size; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index adafaaf7d24d..3e718cfc19a7 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -773,8 +773,8 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, size_t *prev_count, size_t *window_size) { - char __user *p = i->iov[0].iov_base + i->iov_offset; size_t count = iov_iter_count(i); + char __user *p; int pages = 1; if (likely(!count)) @@ -787,14 +787,14 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, if (*prev_count != count || !*window_size) { int pages, nr_dirtied; - pages = min_t(int, BIO_MAX_VECS, - DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE)); + pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE)); nr_dirtied = max(current->nr_dirtied_pause - current->nr_dirtied, 1); pages = min(pages, nr_dirtied); } *prev_count = count; + p = i->iov[0].iov_base + i->iov_offset; *window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p); return true; } @@ -1013,6 +1013,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_holder *statfs_gh = NULL; size_t prev_count = 0, window_size = 0; + size_t orig_count = iov_iter_count(from); size_t read = 0; ssize_t ret; @@ -1057,6 +1058,7 @@ retry_under_glock: if (inode == sdp->sd_rindex) gfs2_glock_dq_uninit(statfs_gh); + from->count = orig_count - read; if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { size_t leftover; @@ -1064,6 +1066,7 @@ retry_under_glock: leftover = fault_in_iov_iter_readable(from, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { + from->count = min(from->count, window_size - leftover); if (!gfs2_holder_queued(gh)) { if (read) goto out_uninit; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 19f38aee1b61..8dbd6fe66420 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -411,14 +411,14 @@ static void do_error(struct gfs2_glock *gl, const int ret) static void demote_incompat_holders(struct gfs2_glock *gl, struct gfs2_holder *new_gh) { - struct gfs2_holder *gh; + struct gfs2_holder *gh, *tmp; /* * Demote incompatible holders before we make ourselves eligible. * (This holder may or may not allow auto-demoting, but we don't want * to demote the new holder before it's even granted.) */ - list_for_each_entry(gh, &gl->gl_holders, gh_list) { + list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) { /* * Since holders are at the front of the list, we stop when we * find the first non-holder. @@ -496,7 +496,7 @@ again: * Since we unlock the lockref lock, we set a flag to indicate * instantiate is in progress. */ - if (test_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) { + if (test_and_set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) { wait_on_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG, TASK_UNINTERRUPTIBLE); /* @@ -509,14 +509,10 @@ again: goto again; } - set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); - ret = glops->go_instantiate(gh); if (!ret) clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags); - clear_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); - smp_mb__after_atomic(); - wake_up_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG); + clear_and_wake_up_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); return ret; } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5b121371508a..0f93e8beca4d 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1402,13 +1402,6 @@ out: gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); - if (ip->i_gl) { - glock_clear_object(ip->i_gl, ip); - wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); - gfs2_glock_add_to_lru(ip->i_gl); - gfs2_glock_put_eventually(ip->i_gl); - ip->i_gl = NULL; - } if (gfs2_holder_initialized(&ip->i_iopen_gh)) { struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; @@ -1421,6 +1414,13 @@ out: gfs2_holder_uninit(&ip->i_iopen_gh); gfs2_glock_put_eventually(gl); } + if (ip->i_gl) { + glock_clear_object(ip->i_gl, ip); + wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); + gfs2_glock_add_to_lru(ip->i_gl); + gfs2_glock_put_eventually(ip->i_gl); + ip->i_gl = NULL; + } } static struct inode *gfs2_alloc_inode(struct super_block *sb) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index b2a1d969a172..5a93a5db4fb0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -288,11 +288,8 @@ nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen) p = xdr_inline_decode(argp->xdr, count << 2); if (!p) return nfserr_bad_xdr; - i = 0; - while (i < count) - bmval[i++] = be32_to_cpup(p++); - while (i < bmlen) - bmval[i++] = 0; + for (i = 0; i < bmlen; i++) + bmval[i] = (i < count) ? be32_to_cpup(p++) : 0; return nfs_ok; } diff --git a/fs/udf/dir.c b/fs/udf/dir.c index 70abdfad2df1..42e3e551fa4c 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -31,6 +31,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/bio.h> +#include <linux/iversion.h> #include "udf_i.h" #include "udf_sb.h" @@ -43,7 +44,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) struct fileIdentDesc *fi = NULL; struct fileIdentDesc cfi; udf_pblk_t block, iblock; - loff_t nf_pos; + loff_t nf_pos, emit_pos = 0; int flen; unsigned char *fname = NULL, *copy_name = NULL; unsigned char *nameptr; @@ -57,6 +58,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) int i, num, ret = 0; struct extent_position epos = { NULL, 0, {0, 0} }; struct super_block *sb = dir->i_sb; + bool pos_valid = false; if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) @@ -67,6 +69,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) if (nf_pos >= size) goto out; + /* + * Something changed since last readdir (either lseek was called or dir + * changed)? We need to verify the position correctly points at the + * beginning of some dir entry so that the directory parsing code does + * not get confused. Since UDF does not have any reliable way of + * identifying beginning of dir entry (names are under user control), + * we need to scan the directory from the beginning. + */ + if (!inode_eq_iversion(dir, file->f_version)) { + emit_pos = nf_pos; + nf_pos = 0; + } else { + pos_valid = true; + } + fname = kmalloc(UDF_NAME_LEN, GFP_NOFS); if (!fname) { ret = -ENOMEM; @@ -122,13 +139,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) while (nf_pos < size) { struct kernel_lb_addr tloc; + loff_t cur_pos = nf_pos; - ctx->pos = (nf_pos >> 2) + 1; + /* Update file position only if we got past the current one */ + if (nf_pos >= emit_pos) { + ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; + } fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc, &elen, &offset); if (!fi) goto out; + /* Still not at offset where user asked us to read from? */ + if (cur_pos < emit_pos) + continue; liu = le16_to_cpu(cfi.lengthOfImpUse); lfi = cfi.lengthFileIdent; @@ -186,8 +211,11 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) } /* end while */ ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; out: + if (pos_valid) + file->f_version = inode_query_iversion(dir); if (fibh.sbh != fibh.ebh) brelse(fibh.ebh); brelse(fibh.sbh); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index caeef08efed2..0ed4861b038f 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> +#include <linux/iversion.h> static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) @@ -134,6 +135,8 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, mark_buffer_dirty_inode(fibh->ebh, inode); mark_buffer_dirty_inode(fibh->sbh, inode); } + inode_inc_iversion(inode); + return 0; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 34247fba6df9..f26b5e0b84b6 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -57,6 +57,7 @@ #include <linux/crc-itu-t.h> #include <linux/log2.h> #include <asm/byteorder.h> +#include <linux/iversion.h> #include "udf_sb.h" #include "udf_i.h" @@ -149,6 +150,7 @@ static struct inode *udf_alloc_inode(struct super_block *sb) init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); + inode_set_iversion(&ei->vfs_inode, 1); return &ei->vfs_inode; } diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..e7a163a3146b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9e0667e3723e..c310648cc8f1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -874,7 +874,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -950,12 +950,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2237abb93ccd..234eab059839 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,13 +53,6 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; -struct gfn_to_pfn_cache { - u64 generation; - gfn_t gfn; - kvm_pfn_t pfn; - bool dirty; -}; - #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb8c6f5f19bc..c3a6e6209600 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,7 +105,18 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 98a9371133f8..ae4004e7957e 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -6,7 +6,6 @@ #include <linux/preempt.h> #include <linux/smp.h> #include <linux/cpumask.h> -#include <linux/printk.h> #include <linux/pfn.h> #include <linux/init.h> diff --git a/include/linux/printk.h b/include/linux/printk.h index 85b656f82d75..9497f6b98339 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -198,6 +198,7 @@ void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; +void printk_trigger_flush(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -274,6 +275,9 @@ static inline void dump_stack_lvl(const char *log_lvl) static inline void dump_stack(void) { } +static inline void printk_trigger_flush(void) +{ +} #endif #ifdef CONFIG_SMP diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 686a666d073d..c8cb7e697d47 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4226,7 +4226,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, return; } - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 50453b287615..2d167ac3452c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,7 +673,7 @@ struct trace_event_file { #define PERF_MAX_TRACE_SIZE 8192 -#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ +#define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ enum event_trigger_type { ETT_NONE = (0), diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b465f8f3e554..04e87f4b9417 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -120,10 +120,15 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); + /* UFO may not include transport header in gso_size. */ + if (gso_type & SKB_GSO_UDP) + nh_off -= thlen; + /* Too small packets are not really GSO ones. */ - if (skb->len - p_off > gso_size) { + if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index a964daedc17b..ea8595651c38 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -30,6 +30,7 @@ enum nci_flag { NCI_UP, NCI_DATA_EXCHANGE, NCI_DATA_EXCHANGE_TO, + NCI_UNREG, }; /* NCI device states */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3855f069627f..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,14 +216,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/init/Kconfig b/init/Kconfig index 036b750e8d8a..4b7bac10c72d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -887,7 +887,7 @@ config CC_HAS_INT128 config CC_IMPLICIT_FALLTHROUGH string - default "-Wimplicit-fallthrough=5" if CC_IS_GCC + default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough) # diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 2ca643af9a54..43eb3501721b 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1809,6 +1809,8 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return cgroup_base_func_proto(func_id, prog); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..649f07623df6 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1364,8 +1364,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..1033ee8c0caf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1184,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1611,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 890b3ec375a3..50efda51515b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1151,7 +1151,8 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) /* transfer reg's id which is unique for every map_lookup_elem * as UID of the inner map. */ - reg->map_uid = reg->id; + if (map_value_has_timer(map->inner_map_meta)) + reg->map_uid = reg->id; } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { reg->type = PTR_TO_XDP_SOCK; } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP || @@ -4055,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) @@ -11631,6 +11647,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if (map_value_has_timer(map)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_timer yet\n"); + return -EINVAL; + } + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 013bfd6dcc34..57b132b658e1 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3253,6 +3253,11 @@ void defer_console_output(void) preempt_enable(); } +void printk_trigger_flush(void) +{ + defer_console_output(); +} + int vprintk_deferred(const char *fmt, va_list args) { int r; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..ae9755037b7e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1111,8 +1111,6 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; - case BPF_FUNC_ktime_get_coarse_ns: - return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 8a10046c775f..5ea2c9ec54a6 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3026,8 +3026,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, if (val->flags & HIST_FIELD_FL_STRING) { char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; + unsigned int size; - strscpy(str, val_str, val->size); + size = min(val->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -4914,6 +4916,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, if (hist_field->flags & HIST_FIELD_FL_STRING) { unsigned int str_start, var_str_idx, idx; char *str, *val_str; + unsigned int size; str_start = hist_data->n_field_var_str + hist_data->n_save_var_str; @@ -4922,7 +4925,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - strscpy(str, val_str, hist_field->size); + + size = min(hist_field->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); hist_val = (u64)(uintptr_t)str; } diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index f9e89001b52e..199ab201d501 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -75,6 +75,12 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, touch_softlockup_watchdog(); } + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + clear_bit_unlock(0, &backtrace_flag); put_cpu(); } diff --git a/net/core/devlink.c b/net/core/devlink.c index 5ba4f9434acd..5ad72dbfcd07 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4229,7 +4229,9 @@ static void __devlink_flash_update_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) diff --git a/net/core/filter.c b/net/core/filter.c index e471c9b09670..6102f093d59a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7162,6 +7162,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10327,6 +10329,8 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } @@ -10833,6 +10837,8 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b60e4301a44..1a6978427d6c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,12 +49,6 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { - /* DMA-mapping is not supported on 32-bit systems with - * 64-bit DMA mapping. - */ - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - return -EOPNOTSUPP; - if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -75,6 +69,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; diff --git a/net/core/sock.c b/net/core/sock.c index 8f2b2f2c0e7b..41e91d0f7061 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2124,8 +2124,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_prot_creator = prot; /* SANITY */ - if (likely(newsk->sk_net_refcnt)) + if (likely(newsk->sk_net_refcnt)) { get_net(sock_net(newsk)); + sock_inuse_add(sock_net(newsk), 1); + } sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); @@ -2197,8 +2199,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); - if (likely(newsk->sk_net_refcnt)) - sock_inuse_add(sock_net(newsk), 1); /* Before updating sk_refcnt, we must commit prior changes to memory * (Documentation/RCU/rculist_nulls.rst for details) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 2cf02b4d77fb..4bb9401b0a3f 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -205,6 +205,8 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, offsetof(struct tcp_congestion_ops, release)) return &bpf_sk_getsockopt_proto; return NULL; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id); } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ec73a0d52d3e..323e622ff9b7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2591,7 +2591,7 @@ static int __devinet_sysctl_register(struct net *net, char *dev_name, free: kfree(t); out: - return -ENOBUFS; + return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b7796b4cf0a0..bbb3d39c69af 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1758,6 +1758,9 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, { skb_frag_t *frag; + if (unlikely(offset_skb >= skb->len)) + return NULL; + offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 319dd7bbfe33..8bcecdd6aeda 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1807,6 +1807,17 @@ int udp_read_sock(struct sock *sk, read_descriptor_t *desc, skb = skb_recv_udp(sk, 0, 1, &err); if (!skb) return err; + + if (udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + continue; + } + used = recv_actor(desc, skb, 0, skb->len); if (used <= 0) { if (!copied) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index ed2f061b8768..f0bac6f7ab6b 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -808,6 +808,12 @@ int esp6_input_done2(struct sk_buff *skb, int err) struct tcphdr *th; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); + + if (offset < 0) { + err = -EINVAL; + goto out; + } + uh = (void *)(skb->data + offset); th = (void *)(skb->data + offset); hdr_len += offset; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e2b791c37591..bd3d3195097f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -80,7 +80,8 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, } /* also validate MU-MIMO change */ - monitor_sdata = rtnl_dereference(local->monitor_sdata); + monitor_sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) @@ -840,7 +841,8 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy, mutex_lock(&local->mtx); if (local->use_chanctx) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata) { ieee80211_vif_release_channel(sdata); ret = ieee80211_vif_use_channel(sdata, chandef, @@ -2707,7 +2709,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (!sdata) return -EOPNOTSUPP; } @@ -2767,7 +2770,8 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, mutex_unlock(&local->iflist_mtx); if (has_monitor) { - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata) { sdata->user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 9a2145c8192b..20aa5cc31f77 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -588,7 +588,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do */ if (local->suspended) { WARN_ON(local->wowlan); - WARN_ON(rtnl_dereference(local->monitor_sdata)); + WARN_ON(rcu_access_pointer(local->monitor_sdata)); return; } @@ -961,6 +961,7 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return 0; ASSERT_RTNL(); + lockdep_assert_wiphy(local->hw.wiphy); if (local->monitor_sdata) return 0; @@ -1028,6 +1029,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) return; ASSERT_RTNL(); + lockdep_assert_wiphy(local->hw.wiphy); mutex_lock(&local->iflist_mtx); diff --git a/net/mac80211/led.h b/net/mac80211/led.h index fb3aaa3c5606..b71a1428d883 100644 --- a/net/mac80211/led.h +++ b/net/mac80211/led.h @@ -72,19 +72,19 @@ static inline void ieee80211_mod_tpt_led_trig(struct ieee80211_local *local, #endif static inline void -ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, __le16 fc, int bytes) +ieee80211_tpt_led_trig_tx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) + if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->tx_bytes += bytes; #endif } static inline void -ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, __le16 fc, int bytes) +ieee80211_tpt_led_trig_rx(struct ieee80211_local *local, int bytes) { #ifdef CONFIG_MAC80211_LEDS - if (ieee80211_is_data(fc) && atomic_read(&local->tpt_led_active)) + if (atomic_read(&local->tpt_led_active)) local->tpt_led_trigger->rx_bytes += bytes; #endif } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index fc5c608d02e2..9541a4c30aca 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -364,7 +364,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, * the compiler to think we have walked past the end of the * struct member. */ - pos = (void *)&rthdr->it_optional[it_present - rthdr->it_optional]; + pos = (void *)&rthdr->it_optional[it_present + 1 - rthdr->it_optional]; /* the order of the following fields is important */ @@ -1952,7 +1952,8 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) int keyid = rx->sta->ptk_idx; sta_ptk = rcu_dereference(rx->sta->ptk[keyid]); - if (ieee80211_has_protected(fc)) { + if (ieee80211_has_protected(fc) && + !(status->flag & RX_FLAG_IV_STRIPPED)) { cs = rx->sta->cipher_scheme; keyid = ieee80211_get_keyid(rx->skb, cs); @@ -4863,6 +4864,7 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, struct ieee80211_rate *rate = NULL; struct ieee80211_supported_band *sband; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; WARN_ON_ONCE(softirq_count() == 0); @@ -4959,9 +4961,9 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, if (!(status->flag & RX_FLAG_8023)) skb = ieee80211_rx_monitor(local, skb, rate); if (skb) { - ieee80211_tpt_led_trig_rx(local, - ((struct ieee80211_hdr *)skb->data)->frame_control, - skb->len); + if ((status->flag & RX_FLAG_8023) || + ieee80211_is_data_present(hdr->frame_control)) + ieee80211_tpt_led_trig_rx(local, skb->len); if (status->flag & RX_FLAG_8023) __ieee80211_rx_handle_8023(hw, pubsta, skb, list); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a756a197c770..278945e3e08a 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1721,21 +1721,19 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local, * Returns false if the frame couldn't be transmitted but was queued instead. */ static bool __ieee80211_tx(struct ieee80211_local *local, - struct sk_buff_head *skbs, int led_len, - struct sta_info *sta, bool txpending) + struct sk_buff_head *skbs, struct sta_info *sta, + bool txpending) { struct ieee80211_tx_info *info; struct ieee80211_sub_if_data *sdata; struct ieee80211_vif *vif; struct sk_buff *skb; bool result; - __le16 fc; if (WARN_ON(skb_queue_empty(skbs))) return true; skb = skb_peek(skbs); - fc = ((struct ieee80211_hdr *)skb->data)->frame_control; info = IEEE80211_SKB_CB(skb); sdata = vif_to_sdata(info->control.vif); if (sta && !sta->uploaded) @@ -1769,8 +1767,6 @@ static bool __ieee80211_tx(struct ieee80211_local *local, result = ieee80211_tx_frags(local, vif, sta, skbs, txpending); - ieee80211_tpt_led_trig_tx(local, fc, led_len); - WARN_ON_ONCE(!skb_queue_empty(skbs)); return result; @@ -1920,7 +1916,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, ieee80211_tx_result res_prepare; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); bool result = true; - int led_len; if (unlikely(skb->len < 10)) { dev_kfree_skb(skb); @@ -1928,7 +1923,6 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, } /* initialises tx */ - led_len = skb->len; res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb); if (unlikely(res_prepare == TX_DROP)) { @@ -1951,8 +1945,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, return true; if (!invoke_tx_handlers_late(&tx)) - result = __ieee80211_tx(local, &tx.skbs, led_len, - tx.sta, txpending); + result = __ieee80211_tx(local, &tx.skbs, tx.sta, txpending); return result; } @@ -4175,6 +4168,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct ieee80211_local *local = sdata->local; struct sta_info *sta; struct sk_buff *next; + int len = skb->len; if (unlikely(skb->len < ETH_HLEN)) { kfree_skb(skb); @@ -4221,10 +4215,8 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, } } else { /* we cannot process non-linear frames on this path */ - if (skb_linearize(skb)) { - kfree_skb(skb); - goto out; - } + if (skb_linearize(skb)) + goto out_free; /* the frame could be fragmented, software-encrypted, and other * things so we cannot really handle checksum offload with it - @@ -4258,7 +4250,10 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, goto out; out_free: kfree_skb(skb); + len = 0; out: + if (len) + ieee80211_tpt_led_trig_tx(local, len); rcu_read_unlock(); } @@ -4396,8 +4391,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, } static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, - struct sk_buff *skb, int led_len, - struct sta_info *sta, + struct sk_buff *skb, struct sta_info *sta, bool txpending) { struct ieee80211_local *local = sdata->local; @@ -4410,6 +4404,8 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata, if (sta) sk_pacing_shift_update(skb->sk, local->hw.tx_sk_pacing_shift); + ieee80211_tpt_led_trig_tx(local, skb->len); + if (ieee80211_queue_skb(local, sdata, sta, skb)) return true; @@ -4498,7 +4494,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, if (key) info->control.hw_key = &key->conf; - ieee80211_tx_8023(sdata, skb, skb->len, sta, false); + ieee80211_tx_8023(sdata, skb, sta, false); return; @@ -4637,7 +4633,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, if (IS_ERR(sta) || (sta && !sta->uploaded)) sta = NULL; - result = ieee80211_tx_8023(sdata, skb, skb->len, sta, true); + result = ieee80211_tx_8023(sdata, skb, sta, true); } else { struct sk_buff_head skbs; @@ -4647,7 +4643,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local, hdr = (struct ieee80211_hdr *)skb->data; sta = sta_info_get(sdata, hdr->addr1); - result = __ieee80211_tx(local, &skbs, skb->len, sta, true); + result = __ieee80211_tx(local, &skbs, sta, true); } return result; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 39fa2a50385d..43df2f0c5db9 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -796,7 +796,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || - lockdep_rtnl_is_held()); + lockdep_is_held(&local->hw.wiphy->mtx)); if (sdata && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) @@ -2381,7 +2381,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) IEEE80211_TPT_LEDTRIG_FL_RADIO, 0); /* add interfaces */ - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata) { /* in HW restart it exists already */ WARN_ON(local->resuming); @@ -2426,7 +2426,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) WARN_ON(drv_add_chanctx(local, ctx)); mutex_unlock(&local->chanctx_mtx); - sdata = rtnl_dereference(local->monitor_sdata); + sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); if (sdata && ieee80211_sdata_running(sdata)) ieee80211_assign_chanctx(local, sdata); } diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 9ea6004abe1b..62c6733e0792 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -143,7 +143,6 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata, u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct mac80211_qos_map *qos_map; bool qos; @@ -156,7 +155,7 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, else qos = false; - if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) { + if (!qos) { skb->priority = 0; /* required for correct WPA/11i MIC */ return IEEE80211_AC_BE; } diff --git a/net/nfc/core.c b/net/nfc/core.c index 3c645c1d99c9..dc7a2404efdf 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -94,13 +94,13 @@ int nfc_dev_up(struct nfc_dev *dev) device_lock(&dev->dev); - if (dev->rfkill && rfkill_blocked(dev->rfkill)) { - rc = -ERFKILL; + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; goto error; } - if (!device_is_registered(&dev->dev)) { - rc = -ENODEV; + if (dev->rfkill && rfkill_blocked(dev->rfkill)) { + rc = -ERFKILL; goto error; } @@ -1125,11 +1125,7 @@ int nfc_register_device(struct nfc_dev *dev) if (rc) pr_err("Could not register llcp device\n"); - rc = nfc_genl_device_added(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s was added\n", - dev_name(&dev->dev)); - + device_lock(&dev->dev); dev->rfkill = rfkill_alloc(dev_name(&dev->dev), &dev->dev, RFKILL_TYPE_NFC, &nfc_rfkill_ops, dev); if (dev->rfkill) { @@ -1138,6 +1134,12 @@ int nfc_register_device(struct nfc_dev *dev) dev->rfkill = NULL; } } + device_unlock(&dev->dev); + + rc = nfc_genl_device_added(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s was added\n", + dev_name(&dev->dev)); return 0; } @@ -1154,10 +1156,17 @@ void nfc_unregister_device(struct nfc_dev *dev) pr_debug("dev_name=%s\n", dev_name(&dev->dev)); + rc = nfc_genl_device_removed(dev); + if (rc) + pr_debug("The userspace won't be notified that the device %s " + "was removed\n", dev_name(&dev->dev)); + + device_lock(&dev->dev); if (dev->rfkill) { rfkill_unregister(dev->rfkill); rfkill_destroy(dev->rfkill); } + device_unlock(&dev->dev); if (dev->ops->check_presence) { device_lock(&dev->dev); @@ -1167,11 +1176,6 @@ void nfc_unregister_device(struct nfc_dev *dev) cancel_work_sync(&dev->check_pres_work); } - rc = nfc_genl_device_removed(dev); - if (rc) - pr_debug("The userspace won't be notified that the device %s " - "was removed\n", dev_name(&dev->dev)); - nfc_llcp_unregister_device(dev); mutex_lock(&nfc_devlist_mutex); diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6fd873aa86be..d2537383a3e8 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -144,12 +144,15 @@ inline int nci_request(struct nci_dev *ndev, { int rc; - if (!test_bit(NCI_UP, &ndev->flags)) - return -ENETDOWN; - /* Serialize all requests */ mutex_lock(&ndev->req_lock); - rc = __nci_request(ndev, req, opt, timeout); + /* check the state after obtaing the lock against any races + * from nci_close_device when the device gets removed. + */ + if (test_bit(NCI_UP, &ndev->flags)) + rc = __nci_request(ndev, req, opt, timeout); + else + rc = -ENETDOWN; mutex_unlock(&ndev->req_lock); return rc; @@ -473,6 +476,11 @@ static int nci_open_device(struct nci_dev *ndev) mutex_lock(&ndev->req_lock); + if (test_bit(NCI_UNREG, &ndev->flags)) { + rc = -ENODEV; + goto done; + } + if (test_bit(NCI_UP, &ndev->flags)) { rc = -EALREADY; goto done; @@ -545,6 +553,10 @@ done: static int nci_close_device(struct nci_dev *ndev) { nci_req_cancel(ndev, ENODEV); + + /* This mutex needs to be held as a barrier for + * caller nci_unregister_device + */ mutex_lock(&ndev->req_lock); if (!test_and_clear_bit(NCI_UP, &ndev->flags)) { @@ -582,8 +594,8 @@ static int nci_close_device(struct nci_dev *ndev) del_timer_sync(&ndev->cmd_timer); - /* Clear flags */ - ndev->flags = 0; + /* Clear flags except NCI_UNREG */ + ndev->flags &= BIT(NCI_UNREG); mutex_unlock(&ndev->req_lock); @@ -1266,6 +1278,12 @@ void nci_unregister_device(struct nci_dev *ndev) { struct nci_conn_info *conn_info, *n; + /* This set_bit is not protected with specialized barrier, + * However, it is fine because the mutex_lock(&ndev->req_lock); + * in nci_close_device() will help to emit one. + */ + set_bit(NCI_UNREG, &ndev->flags); + nci_close_device(ndev); destroy_workqueue(ndev->cmd_wq); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index d64b0eeccbe4..efc963ab995a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -19,6 +19,7 @@ #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <net/dst.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> @@ -228,6 +229,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool want_ingress; bool is_redirect; bool expects_nh; + bool at_ingress; int m_eaction; int mac_len; bool at_nh; @@ -263,7 +265,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, * ingress - that covers the TC S/W datapath. */ is_redirect = tcf_mirred_is_act_redirect(m_eaction); - use_reinsert = skb_at_tc_ingress(skb) && is_redirect && + at_ingress = skb_at_tc_ingress(skb); + use_reinsert = at_ingress && is_redirect && tcf_mirred_can_reinsert(retval); if (!use_reinsert) { skb2 = skb_clone(skb, GFP_ATOMIC); @@ -271,10 +274,12 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } + want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb2); - - want_ingress = tcf_mirred_act_wants_ingress(m_eaction); + if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ + skb_dst_drop(skb2); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 59284da9116d..b61c802e3bf3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -566,6 +566,10 @@ static void smc_stat_fallback(struct smc_sock *smc) static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { + wait_queue_head_t *smc_wait = sk_sleep(&smc->sk); + wait_queue_head_t *clc_wait = sk_sleep(smc->clcsock->sk); + unsigned long flags; + smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -575,6 +579,16 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->file->private_data = smc->clcsock; smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; + + /* There may be some entries remaining in + * smc socket->wq, which should be removed + * to clcsocket->wq during the fallback. + */ + spin_lock_irqsave(&smc_wait->lock, flags); + spin_lock(&clc_wait->lock); + list_splice_init(&smc_wait->head, &clc_wait->head); + spin_unlock(&clc_wait->lock); + spin_unlock_irqrestore(&smc_wait->lock, flags); } } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 49b8ba3bb683..25ebd30feecd 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -708,13 +708,14 @@ static u8 smcr_next_link_id(struct smc_link_group *lgr) int i; while (1) { +again: link_id = ++lgr->next_link_id; if (!link_id) /* skip zero as link_id */ link_id = ++lgr->next_link_id; for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (smc_link_usable(&lgr->lnk[i]) && lgr->lnk[i].link_id == link_id) - continue; + goto again; } break; } diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index dc60c32bb70d..b4d9419a015b 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -524,7 +524,7 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, return -EEXIST; /* Allocate a new AEAD */ - tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC); + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); if (unlikely(!tmp)) return -ENOMEM; @@ -597,6 +597,10 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey, tmp->cloned = NULL; tmp->authsize = TIPC_AES_GCM_TAG_SIZE; tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL); + if (!tmp->key) { + tipc_aead_free(&tmp->rcu); + return -ENOMEM; + } memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE); atomic_set(&tmp->users, 0); atomic64_set(&tmp->seqno, 0); @@ -1470,7 +1474,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, return -EEXIST; /* Allocate crypto */ - c = kzalloc(sizeof(*c), GFP_ATOMIC); + c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; @@ -1484,7 +1488,7 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net, } /* Allocate statistic structure */ - c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC); + c->stats = alloc_percpu(struct tipc_crypto_stats); if (!c->stats) { if (c->wq) destroy_workqueue(c->wq); @@ -2457,7 +2461,7 @@ static void tipc_crypto_work_tx(struct work_struct *work) } /* Lets duplicate it first */ - skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC); + skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_KERNEL); rcu_read_unlock(); /* Now, generate new key, initiate & distribute it */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 1b7a487c8841..09ae8448f394 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1298,8 +1298,11 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, return false; #ifdef CONFIG_TIPC_CRYPTO case MSG_CRYPTO: - tipc_crypto_msg_rcv(l->net, skb); - return true; + if (TIPC_SKB_CB(skb)->decrypted) { + tipc_crypto_msg_rcv(l->net, skb); + return true; + } + fallthrough; #endif default: pr_warn("Dropping received illegal msg type\n"); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 81232b73df8f..a27b3b5fa210 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -936,33 +936,37 @@ nl80211_packet_pattern_policy[MAX_NL80211_PKTPAT + 1] = { [NL80211_PKTPAT_OFFSET] = { .type = NLA_U32 }, }; -int nl80211_prepare_wdev_dump(struct netlink_callback *cb, - struct cfg80211_registered_device **rdev, - struct wireless_dev **wdev) +static int nl80211_prepare_wdev_dump(struct netlink_callback *cb, + struct cfg80211_registered_device **rdev, + struct wireless_dev **wdev, + struct nlattr **attrbuf) { int err; if (!cb->args[0]) { - struct nlattr **attrbuf; + struct nlattr **attrbuf_free = NULL; - attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), - GFP_KERNEL); - if (!attrbuf) - return -ENOMEM; + if (!attrbuf) { + attrbuf = kcalloc(NUM_NL80211_ATTR, sizeof(*attrbuf), + GFP_KERNEL); + if (!attrbuf) + return -ENOMEM; + attrbuf_free = attrbuf; + } err = nlmsg_parse_deprecated(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, attrbuf, nl80211_fam.maxattr, nl80211_policy, NULL); if (err) { - kfree(attrbuf); + kfree(attrbuf_free); return err; } rtnl_lock(); *wdev = __cfg80211_wdev_from_attrs(NULL, sock_net(cb->skb->sk), attrbuf); - kfree(attrbuf); + kfree(attrbuf_free); if (IS_ERR(*wdev)) { rtnl_unlock(); return PTR_ERR(*wdev); @@ -6197,7 +6201,7 @@ static int nl80211_dump_station(struct sk_buff *skb, int sta_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -7092,7 +7096,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -7292,7 +7296,7 @@ static int nl80211_dump_mpp(struct sk_buff *skb, int path_idx = cb->args[2]; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -9718,7 +9722,7 @@ static int nl80211_dump_scan(struct sk_buff *skb, struct netlink_callback *cb) int start = cb->args[2], idx = 0; int err; - err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + err = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, NULL); if (err) return err; /* nl80211_prepare_wdev_dump acquired it in the successful case */ @@ -9851,7 +9855,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, struct netlink_callback *cb) if (!attrbuf) return -ENOMEM; - res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev); + res = nl80211_prepare_wdev_dump(cb, &rdev, &wdev, attrbuf); if (res) { kfree(attrbuf); return res; diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index a3f387770f1b..d642e3be4ee7 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file - * Copyright (C) 2018, 2020 Intel Corporation + * Copyright (C) 2018, 2020-2021 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H @@ -22,10 +22,6 @@ static inline u64 wdev_id(struct wireless_dev *wdev) ((u64)wiphy_to_rdev(wdev->wiphy)->wiphy_idx << 32); } -int nl80211_prepare_wdev_dump(struct netlink_callback *cb, - struct cfg80211_registered_device **rdev, - struct wireless_dev **wdev); - int nl80211_parse_chandef(struct cfg80211_registered_device *rdev, struct genl_info *info, struct cfg80211_chan_def *chandef); diff --git a/net/wireless/util.c b/net/wireless/util.c index 5ff1f8726faf..41ea65deb6e1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1046,6 +1046,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, switch (otype) { case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, true); break; case NL80211_IFTYPE_ADHOC: diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 90c4e1e819d3..bc4ad48ea4f0 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -500,7 +500,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool) pool->free_list_cnt--; xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); - list_del(&xskb->free_list_node); + list_del_init(&xskb->free_list_node); } xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM; @@ -568,7 +568,7 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3 i = nb_entries; while (i--) { xskb = list_first_entry(&pool->free_list, struct xdp_buff_xsk, free_list_node); - list_del(&xskb->free_list_node); + list_del_init(&xskb->free_list_node); *xdp = &xskb->xdp; xdp++; @@ -615,6 +615,9 @@ EXPORT_SYMBOL(xp_can_alloc); void xp_free(struct xdp_buff_xsk *xskb) { + if (!list_empty(&xskb->free_list_node)) + return; + xskb->pool->free_list_cnt++; list_add(&xskb->free_list_node, &xskb->pool->free_list); } diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index 722b3fadb467..1752a46a2b05 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -9,8 +9,6 @@ * Include file for sample Host Bandwidth Manager (HBM) BPF programs */ #define KBUILD_MODNAME "foo" -#include <stddef.h> -#include <stdbool.h> #include <uapi/linux/bpf.h> #include <uapi/linux/if_ether.h> #include <uapi/linux/if_packet.h> diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index d84e6949007c..a81704d3317b 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -309,7 +309,6 @@ int main(int argc, char **argv) const char *mprog_filename = NULL, *mprog_name = NULL; struct xdp_redirect_cpu *skel; struct bpf_map_info info = {}; - char ifname_buf[IF_NAMESIZE]; struct bpf_cpumap_val value; __u32 infosz = sizeof(info); int ret = EXIT_FAIL_OPTION; @@ -390,10 +389,10 @@ int main(int argc, char **argv) case 'd': if (strlen(optarg) >= IF_NAMESIZE) { fprintf(stderr, "-d/--dev name too long\n"); + usage(argv, long_options, __doc__, mask, true, skel->obj); goto end_cpu; } - safe_strncpy(ifname_buf, optarg, strlen(ifname_buf)); - ifindex = if_nametoindex(ifname_buf); + ifindex = if_nametoindex(optarg); if (!ifindex) ifindex = strtoul(optarg, NULL, 0); if (!ifindex) { diff --git a/samples/bpf/xdp_sample_user.c b/samples/bpf/xdp_sample_user.c index b32d82178199..8740838e7767 100644 --- a/samples/bpf/xdp_sample_user.c +++ b/samples/bpf/xdp_sample_user.c @@ -120,7 +120,10 @@ struct sample_output { __u64 xmit; } totals; struct { - __u64 pps; + union { + __u64 pps; + __u64 num; + }; __u64 drop; __u64 err; } rx_cnt; @@ -1322,7 +1325,7 @@ int sample_install_xdp(struct bpf_program *xdp_prog, int ifindex, bool generic, static void sample_summary_print(void) { - double period = sample_out.rx_cnt.pps; + double num = sample_out.rx_cnt.num; if (sample_out.totals.rx) { double pkts = sample_out.totals.rx; @@ -1330,7 +1333,7 @@ static void sample_summary_print(void) print_always(" Packets received : %'-10llu\n", sample_out.totals.rx); print_always(" Average packets/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } if (sample_out.totals.redir) { double pkts = sample_out.totals.redir; @@ -1338,7 +1341,7 @@ static void sample_summary_print(void) print_always(" Packets redirected : %'-10llu\n", sample_out.totals.redir); print_always(" Average redir/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } if (sample_out.totals.drop) print_always(" Rx dropped : %'-10llu\n", @@ -1355,7 +1358,7 @@ static void sample_summary_print(void) print_always(" Packets transmitted : %'-10llu\n", sample_out.totals.xmit); print_always(" Average transmit/s : %'-10.0f\n", - sample_round(pkts / period)); + sample_round(pkts / num)); } } @@ -1422,7 +1425,7 @@ static int sample_stats_collect(struct stats_record *rec) return 0; } -static void sample_summary_update(struct sample_output *out, int interval) +static void sample_summary_update(struct sample_output *out) { sample_out.totals.rx += out->totals.rx; sample_out.totals.redir += out->totals.redir; @@ -1430,12 +1433,11 @@ static void sample_summary_update(struct sample_output *out, int interval) sample_out.totals.drop_xmit += out->totals.drop_xmit; sample_out.totals.err += out->totals.err; sample_out.totals.xmit += out->totals.xmit; - sample_out.rx_cnt.pps += interval; + sample_out.rx_cnt.num++; } static void sample_stats_print(int mask, struct stats_record *cur, - struct stats_record *prev, char *prog_name, - int interval) + struct stats_record *prev, char *prog_name) { struct sample_output out = {}; @@ -1452,7 +1454,7 @@ static void sample_stats_print(int mask, struct stats_record *cur, else if (mask & SAMPLE_DEVMAP_XMIT_CNT_MULTI) stats_get_devmap_xmit_multi(cur, prev, 0, &out, mask & SAMPLE_DEVMAP_XMIT_CNT); - sample_summary_update(&out, interval); + sample_summary_update(&out); stats_print(prog_name, mask, cur, prev, &out); } @@ -1495,7 +1497,7 @@ static void swap(struct stats_record **a, struct stats_record **b) } static int sample_timer_cb(int timerfd, struct stats_record **rec, - struct stats_record **prev, int interval) + struct stats_record **prev) { char line[64] = "Summary"; int ret; @@ -1524,7 +1526,7 @@ static int sample_timer_cb(int timerfd, struct stats_record **rec, snprintf(line, sizeof(line), "%s->%s", f ?: "?", t ?: "?"); } - sample_stats_print(sample_mask, *rec, *prev, line, interval); + sample_stats_print(sample_mask, *rec, *prev, line); return 0; } @@ -1579,7 +1581,7 @@ int sample_run(int interval, void (*post_cb)(void *), void *ctx) if (pfd[0].revents & POLLIN) ret = sample_signal_cb(); else if (pfd[1].revents & POLLIN) - ret = sample_timer_cb(timerfd, &rec, &prev, interval); + ret = sample_timer_cb(timerfd, &rec, &prev); if (ret) break; diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index bbd1150578f7..8791d0e2762b 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -88,5 +88,4 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OU $(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT) \ - LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT) \ - LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD) + CC=$(HOSTCC) LD=$(HOSTLD) diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h index d26e5472fe50..6f3df004479b 100644 --- a/tools/lib/bpf/bpf_gen_internal.h +++ b/tools/lib/bpf/bpf_gen_internal.h @@ -45,8 +45,8 @@ struct bpf_gen { int nr_fd_array; }; -void bpf_gen__init(struct bpf_gen *gen, int log_level); -int bpf_gen__finish(struct bpf_gen *gen); +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps); +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps); void bpf_gen__free(struct bpf_gen *gen); void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size); void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx); diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c index 502dea53a742..9934851ccde7 100644 --- a/tools/lib/bpf/gen_loader.c +++ b/tools/lib/bpf/gen_loader.c @@ -18,7 +18,7 @@ #define MAX_USED_MAPS 64 #define MAX_USED_PROGS 32 #define MAX_KFUNC_DESCS 256 -#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS) +#define MAX_FD_ARRAY_SZ (MAX_USED_MAPS + MAX_KFUNC_DESCS) /* The following structure describes the stack layout of the loader program. * In addition R6 contains the pointer to context. @@ -33,8 +33,8 @@ */ struct loader_stack { __u32 btf_fd; - __u32 prog_fd[MAX_USED_PROGS]; __u32 inner_map_fd; + __u32 prog_fd[MAX_USED_PROGS]; }; #define stack_off(field) \ @@ -42,6 +42,11 @@ struct loader_stack { #define attr_field(attr, field) (attr + offsetof(union bpf_attr, field)) +static int blob_fd_array_off(struct bpf_gen *gen, int index) +{ + return gen->fd_array + index * sizeof(int); +} + static int realloc_insn_buf(struct bpf_gen *gen, __u32 size) { size_t off = gen->insn_cur - gen->insn_start; @@ -102,11 +107,15 @@ static void emit2(struct bpf_gen *gen, struct bpf_insn insn1, struct bpf_insn in emit(gen, insn2); } -void bpf_gen__init(struct bpf_gen *gen, int log_level) +static int add_data(struct bpf_gen *gen, const void *data, __u32 size); +static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off); + +void bpf_gen__init(struct bpf_gen *gen, int log_level, int nr_progs, int nr_maps) { - size_t stack_sz = sizeof(struct loader_stack); + size_t stack_sz = sizeof(struct loader_stack), nr_progs_sz; int i; + gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); gen->log_level = log_level; /* save ctx pointer into R6 */ emit(gen, BPF_MOV64_REG(BPF_REG_6, BPF_REG_1)); @@ -118,19 +127,27 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level) emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_probe_read_kernel)); + /* amount of stack actually used, only used to calculate iterations, not stack offset */ + nr_progs_sz = offsetof(struct loader_stack, prog_fd[nr_progs]); /* jump over cleanup code */ emit(gen, BPF_JMP_IMM(BPF_JA, 0, 0, - /* size of cleanup code below */ - (stack_sz / 4) * 3 + 2)); + /* size of cleanup code below (including map fd cleanup) */ + (nr_progs_sz / 4) * 3 + 2 + + /* 6 insns for emit_sys_close_blob, + * 6 insns for debug_regs in emit_sys_close_blob + */ + nr_maps * (6 + (gen->log_level ? 6 : 0)))); /* remember the label where all error branches will jump to */ gen->cleanup_label = gen->insn_cur - gen->insn_start; /* emit cleanup code: close all temp FDs */ - for (i = 0; i < stack_sz; i += 4) { + for (i = 0; i < nr_progs_sz; i += 4) { emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -stack_sz + i)); emit(gen, BPF_JMP_IMM(BPF_JSLE, BPF_REG_1, 0, 1)); emit(gen, BPF_EMIT_CALL(BPF_FUNC_sys_close)); } + for (i = 0; i < nr_maps; i++) + emit_sys_close_blob(gen, blob_fd_array_off(gen, i)); /* R7 contains the error code from sys_bpf. Copy it into R0 and exit. */ emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_7)); emit(gen, BPF_EXIT_INSN()); @@ -160,8 +177,6 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size) */ static int add_map_fd(struct bpf_gen *gen) { - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_maps == MAX_USED_MAPS) { pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS); gen->error = -E2BIG; @@ -174,8 +189,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) { int cur; - if (!gen->fd_array) - gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int)); if (gen->nr_fd_array == MAX_KFUNC_DESCS) { cur = add_data(gen, NULL, sizeof(int)); return (cur - gen->fd_array) / sizeof(int); @@ -183,11 +196,6 @@ static int add_kfunc_btf_fd(struct bpf_gen *gen) return MAX_USED_MAPS + gen->nr_fd_array++; } -static int blob_fd_array_off(struct bpf_gen *gen, int index) -{ - return gen->fd_array + index * sizeof(int); -} - static int insn_bytes_to_bpf_size(__u32 sz) { switch (sz) { @@ -359,10 +367,15 @@ static void emit_sys_close_blob(struct bpf_gen *gen, int blob_off) __emit_sys_close(gen); } -int bpf_gen__finish(struct bpf_gen *gen) +int bpf_gen__finish(struct bpf_gen *gen, int nr_progs, int nr_maps) { int i; + if (nr_progs != gen->nr_progs || nr_maps != gen->nr_maps) { + pr_warn("progs/maps mismatch\n"); + gen->error = -EFAULT; + return gen->error; + } emit_sys_close_stack(gen, stack_off(btf_fd)); for (i = 0; i < gen->nr_progs; i++) move_stack2ctx(gen, diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a1bea1953df6..7c74342bb668 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -7258,7 +7258,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) } if (obj->gen_loader) - bpf_gen__init(obj->gen_loader, attr->log_level); + bpf_gen__init(obj->gen_loader, attr->log_level, obj->nr_programs, obj->nr_maps); err = bpf_object__probe_loading(obj); err = err ? : bpf_object__load_vmlinux_btf(obj, false); @@ -7277,7 +7277,7 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) for (i = 0; i < obj->nr_maps; i++) obj->maps[i].fd = -1; if (!err) - err = bpf_gen__finish(obj->gen_loader); + err = bpf_gen__finish(obj->gen_loader, obj->nr_programs, obj->nr_maps); } /* clean up fd_array */ diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 54b0a41a3775..62fafbeb4672 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -187,7 +187,7 @@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower \ OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ - BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/ \ + BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ diff --git a/tools/testing/selftests/bpf/prog_tests/helper_restricted.c b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c new file mode 100644 index 000000000000..e1de5f80c3b2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/helper_restricted.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "test_helper_restricted.skel.h" + +void test_helper_restricted(void) +{ + int prog_i = 0, prog_cnt; + int duration = 0; + + do { + struct test_helper_restricted *test; + int maybeOK; + + test = test_helper_restricted__open(); + if (!ASSERT_OK_PTR(test, "open")) + return; + + prog_cnt = test->skeleton->prog_cnt; + + for (int j = 0; j < prog_cnt; ++j) { + struct bpf_program *prog = *test->skeleton->progs[j].prog; + + maybeOK = bpf_program__set_autoload(prog, prog_i == j); + ASSERT_OK(maybeOK, "set autoload"); + } + + maybeOK = test_helper_restricted__load(test); + CHECK(!maybeOK, test->skeleton->progs[prog_i].name, "helper isn't restricted"); + + test_helper_restricted__destroy(test); + } while (++prog_i < prog_cnt); +} diff --git a/tools/testing/selftests/bpf/progs/test_helper_restricted.c b/tools/testing/selftests/bpf/progs/test_helper_restricted.c new file mode 100644 index 000000000000..68d64c365f90 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_helper_restricted.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <time.h> +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +struct timer { + struct bpf_timer t; +}; + +struct lock { + struct bpf_spin_lock l; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct timer); +} timers SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, __u32); + __type(value, struct lock); +} locks SEC(".maps"); + +static int timer_cb(void *map, int *key, struct timer *timer) +{ + return 0; +} + +static void timer_work(void) +{ + struct timer *timer; + const int key = 0; + + timer = bpf_map_lookup_elem(&timers, &key); + if (timer) { + bpf_timer_init(&timer->t, &timers, CLOCK_MONOTONIC); + bpf_timer_set_callback(&timer->t, timer_cb); + bpf_timer_start(&timer->t, 10E9, 0); + bpf_timer_cancel(&timer->t); + } +} + +static void spin_lock_work(void) +{ + const int key = 0; + struct lock *lock; + + lock = bpf_map_lookup_elem(&locks, &key); + if (lock) { + bpf_spin_lock(&lock->l); + bpf_spin_unlock(&lock->l); + } +} + +SEC("raw_tp/sys_enter") +int raw_tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_timer(void *ctx) +{ + timer_work(); + + return 0; +} + +SEC("raw_tp/sys_enter") +int raw_tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("tp/syscalls/sys_enter_nanosleep") +int tp_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("kprobe/sys_nanosleep") +int kprobe_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +SEC("perf_event") +int perf_event_spin_lock(void *ctx) +{ + spin_lock_work(); + + return 0; +} + +const char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 25afe423b3f0..465ef3f112c0 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -92,6 +92,7 @@ struct bpf_test { int fixup_map_event_output[MAX_FIXUPS]; int fixup_map_reuseport_array[MAX_FIXUPS]; int fixup_map_ringbuf[MAX_FIXUPS]; + int fixup_map_timer[MAX_FIXUPS]; /* Expected verifier log output for result REJECT or VERBOSE_ACCEPT. * Can be a tab-separated sequence of expected strings. An empty string * means no log verification. @@ -604,8 +605,15 @@ static int create_cgroup_storage(bool percpu) * int cnt; * struct bpf_spin_lock l; * }; + * struct bpf_timer { + * __u64 :64; + * __u64 :64; + * } __attribute__((aligned(8))); + * struct timer { + * struct bpf_timer t; + * }; */ -static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; +static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l\0bpf_timer\0timer\0t"; static __u32 btf_raw_types[] = { /* int */ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ @@ -616,6 +624,11 @@ static __u32 btf_raw_types[] = { BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ + /* struct bpf_timer */ /* [4] */ + BTF_TYPE_ENC(25, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 0), 16), + /* struct timer */ /* [5] */ + BTF_TYPE_ENC(35, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 16), + BTF_MEMBER_ENC(41, 4, 0), /* struct bpf_timer t; */ }; static int load_btf(void) @@ -696,6 +709,29 @@ static int create_sk_storage_map(void) return fd; } +static int create_map_timer(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = 4, + .value_size = 16, + .max_entries = 1, + .btf_key_type_id = 1, + .btf_value_type_id = 5, + }; + int fd, btf_fd; + + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + if (fd < 0) + printf("Failed to create map with timer\n"); + return fd; +} + static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, @@ -722,6 +758,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_event_output = test->fixup_map_event_output; int *fixup_map_reuseport_array = test->fixup_map_reuseport_array; int *fixup_map_ringbuf = test->fixup_map_ringbuf; + int *fixup_map_timer = test->fixup_map_timer; if (test->fill_helper) { test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn)); @@ -907,6 +944,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_ringbuf++; } while (*fixup_map_ringbuf); } + if (*fixup_map_timer) { + map_fds[21] = create_map_timer(); + do { + prog[*fixup_map_timer].imm = map_fds[21]; + fixup_map_timer++; + } while (*fixup_map_timer); + } } struct libcap { diff --git a/tools/testing/selftests/bpf/verifier/helper_restricted.c b/tools/testing/selftests/bpf/verifier/helper_restricted.c new file mode 100644 index 000000000000..a067b7098b97 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/helper_restricted.c @@ -0,0 +1,196 @@ +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_ktime_get_coarse_ns is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_ktime_get_coarse_ns), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .errstr = "unknown func bpf_ktime_get_coarse_ns", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_timer_init isn restricted in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_timer_init is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_2, 0), + BPF_MOV64_IMM(BPF_REG_3, 1), + BPF_EMIT_CALL(BPF_FUNC_timer_init), + BPF_EXIT_INSN(), + }, + .fixup_map_timer = { 3, 8 }, + .errstr = "tracing progs cannot use bpf_timer yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_KPROBE", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_KPROBE, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_PERF_EVENT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_PERF_EVENT, +}, +{ + "bpf_spin_lock is forbidden in BPF_PROG_TYPE_RAW_TRACEPOINT", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_spin_lock), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .errstr = "tracing progs cannot use bpf_spin_lock yet", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT, +}, diff --git a/tools/testing/selftests/bpf/verifier/map_in_map.c b/tools/testing/selftests/bpf/verifier/map_in_map.c index 2798927ee9ff..128a348b762d 100644 --- a/tools/testing/selftests/bpf/verifier/map_in_map.c +++ b/tools/testing/selftests/bpf/verifier/map_in_map.c @@ -19,6 +19,40 @@ .result = ACCEPT, }, { + "map in map state pruning", + .insns = { + BPF_ST_MEM(0, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 11), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_in_map = { 4, 14 }, + .flags = BPF_F_TEST_STATE_FREQ, + .result = VERBOSE_ACCEPT, + .errstr = "processed 25 insns", + .prog_type = BPF_PROG_TYPE_XDP, +}, +{ "invalid inner map pointer", .insns = { BPF_ST_MEM(0, BPF_REG_10, -4, 0), diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d4a830139683..3763105029fb 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -23,6 +23,7 @@ /x86_64/platform_info_test /x86_64/set_boot_cpu_id /x86_64/set_sregs_test +/x86_64/sev_migrate_tests /x86_64/smm_test /x86_64/state_test /x86_64/svm_vmcall_test diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c index 5d95113c7b7c..d8909032317a 100644 --- a/tools/testing/selftests/kvm/access_tracking_perf_test.c +++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c @@ -47,7 +47,7 @@ #include "guest_modes.h" /* Global variable used to synchronize all of the vCPU threads. */ -static int iteration = -1; +static int iteration; /* Defines what vCPU threads should do during a given iteration. */ static enum { @@ -215,12 +215,11 @@ static bool spin_wait_for_next_iteration(int *current_iteration) return true; } -static void *vcpu_thread_main(void *arg) +static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args) { - struct perf_test_vcpu_args *vcpu_args = arg; struct kvm_vm *vm = perf_test_args.vm; int vcpu_id = vcpu_args->vcpu_id; - int current_iteration = -1; + int current_iteration = 0; while (spin_wait_for_next_iteration(¤t_iteration)) { switch (READ_ONCE(iteration_work)) { @@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg) vcpu_last_completed_iteration[vcpu_id] = current_iteration; } - - return NULL; } static void spin_wait_for_vcpu(int vcpu_id, int target_iteration) @@ -277,8 +274,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description) static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access, const char *description) { - perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1; - sync_global_to_guest(vm, perf_test_args); + perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1); iteration_work = ITERATION_ACCESS_MEMORY; run_iteration(vm, vcpus, description); } @@ -296,48 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus) run_iteration(vm, vcpus, "Mark memory idle"); } -static pthread_t *create_vcpu_threads(int vcpus) -{ - pthread_t *vcpu_threads; - int i; - - vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0])); - TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads."); - - for (i = 0; i < vcpus; i++) { - vcpu_last_completed_iteration[i] = iteration; - pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main, - &perf_test_args.vcpu_args[i]); - } - - return vcpu_threads; -} - -static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus) -{ - int i; - - /* Set done to signal the vCPU threads to exit */ - done = true; - - for (i = 0; i < vcpus; i++) - pthread_join(vcpu_threads[i], NULL); -} - static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *params = arg; struct kvm_vm *vm; - pthread_t *vcpu_threads; int vcpus = params->vcpus; vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1, - params->backing_src); + params->backing_src, !overlap_memory_access); - perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes, - !overlap_memory_access); - - vcpu_threads = create_vcpu_threads(vcpus); + perf_test_start_vcpu_threads(vcpus, vcpu_thread_main); pr_info("\n"); access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory"); @@ -352,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) mark_memory_idle(vm, vcpus); access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory"); - terminate_vcpu_threads(vcpu_threads, vcpus); - free(vcpu_threads); + /* Set done to signal the vCPU threads to exit */ + done = true; + + perf_test_join_vcpu_threads(vcpus); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 1510b21e6306..6a719d065599 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static size_t demand_paging_size; static char *guest_data_prototype; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -68,8 +67,6 @@ static void *vcpu_worker(void *data) ts_diff = timespec_elapsed(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); - - return NULL; } static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr) @@ -282,7 +279,6 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; struct timespec start; @@ -293,9 +289,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) int r; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - p->src_type); - - perf_test_args.wr_fract = 1; + p->src_type, p->partition_vcpu_memory_access); demand_paging_size = get_backing_src_pagesz(p->src_type); @@ -304,12 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) "Failed to allocate buffer for guest data pattern"); memset(guest_data_prototype, 0xAB, demand_paging_size); - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - if (p->uffd_mode) { uffd_handler_threads = malloc(nr_vcpus * sizeof(*uffd_handler_threads)); @@ -322,26 +310,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; + struct perf_test_vcpu_args *vcpu_args; void *vcpu_hva; void *vcpu_alias; - uint64_t vcpu_mem_size; - - if (p->partition_vcpu_memory_access) { - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * guest_percpu_mem_size); - vcpu_mem_size = guest_percpu_mem_size; - } else { - vcpu_gpa = guest_test_phys_mem; - vcpu_mem_size = guest_percpu_mem_size * nr_vcpus; - } - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size); + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; /* Cache the host addresses of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - vcpu_alias = addr_gpa2alias(vm, vcpu_gpa); + vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa); + vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa); /* * Set up user fault fd to handle demand paging @@ -355,32 +332,18 @@ static void run_test(enum vm_guest_mode mode, void *arg) pipefds[vcpu_id * 2], p->uffd_mode, p->uffd_delay, &uffd_args[vcpu_id], vcpu_hva, vcpu_alias, - vcpu_mem_size); + vcpu_args->pages * perf_test_args.guest_page_size); } } - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); - pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } - + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { - pthread_join(vcpu_threads[vcpu_id], NULL); - PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); - } - + perf_test_join_vcpu_threads(nr_vcpus); ts_diff = timespec_elapsed(start); - pr_info("All vCPU threads joined\n"); if (p->uffd_mode) { @@ -404,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) perf_test_destroy_vm(vm); free(guest_data_prototype); - free(vcpu_threads); if (p->uffd_mode) { free(uffd_handler_threads); free(uffd_args); diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 7ffab5bd5ce5..1954b964d1cf 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -31,7 +31,7 @@ static bool host_quit; static int iteration; static int vcpu_last_completed_iteration[KVM_MAX_VCPUS]; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; struct kvm_vm *vm = perf_test_args.vm; @@ -41,7 +41,6 @@ static void *vcpu_worker(void *data) struct timespec ts_diff; struct timespec total = (struct timespec){0}; struct timespec avg; - struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; run = vcpu_state(vm, vcpu_id); @@ -83,8 +82,6 @@ static void *vcpu_worker(void *data) pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); - - return NULL; } struct test_params { @@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots) static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; unsigned long **bitmaps; uint64_t guest_num_pages; @@ -186,9 +182,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) struct timespec clear_dirty_log_total = (struct timespec){0}; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, - p->slots, p->backing_src); + p->slots, p->backing_src, + p->partition_vcpu_memory_access); - perf_test_args.wr_fract = p->wr_fract; + perf_test_set_wr_fract(vm, p->wr_fract); guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); @@ -203,25 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg) vm_enable_cap(vm, &cap); } - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - sync_global_to_guest(vm, perf_test_args); - /* Start the iterations */ iteration = 0; host_quit = false; clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) vcpu_last_completed_iteration[vcpu_id] = -1; - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); - } + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); /* Allow the vCPUs to populate memory */ pr_debug("Starting iteration %d - Populating\n", iteration); @@ -290,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg) /* Tell the vcpu thread to quit */ host_quit = true; - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); + perf_test_join_vcpu_threads(nr_vcpus); avg = timespec_div(get_dirty_log_total, p->iterations); pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", @@ -306,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg) } free_bitmaps(bitmaps, p->slots); - free(vcpu_threads); perf_test_destroy_vm(vm); } diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 792c60e1b17d..3fcd89e195c7 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -115,7 +115,7 @@ static void guest_code(void) addr = guest_test_virt_mem; addr += (READ_ONCE(random_array[i]) % guest_num_pages) * guest_page_size; - addr &= ~(host_page_size - 1); + addr = align_down(addr, host_page_size); *(uint64_t *)addr = READ_ONCE(iteration); } @@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg) if (!p->phys_offset) { guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size); } else { guest_test_phys_mem = p->phys_offset; } #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20); #endif pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h index df9f1a3a3ffb..a86f953d8d36 100644 --- a/tools/testing/selftests/kvm/include/perf_test_util.h +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -8,6 +8,8 @@ #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H #define SELFTEST_KVM_PERF_TEST_UTIL_H +#include <pthread.h> + #include "kvm_util.h" /* Default guest test virtual memory offset */ @@ -18,6 +20,7 @@ #define PERF_TEST_MEM_SLOT_INDEX 1 struct perf_test_vcpu_args { + uint64_t gpa; uint64_t gva; uint64_t pages; @@ -27,7 +30,7 @@ struct perf_test_vcpu_args { struct perf_test_args { struct kvm_vm *vm; - uint64_t host_page_size; + uint64_t gpa; uint64_t guest_page_size; int wr_fract; @@ -36,19 +39,15 @@ struct perf_test_args { extern struct perf_test_args perf_test_args; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -extern uint64_t guest_test_phys_mem; - struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src); + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access); void perf_test_destroy_vm(struct kvm_vm *vm); -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access); + +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract); + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)); +void perf_test_join_vcpu_threads(int vcpus); #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index f8fddc84c0d3..99e0dcdc923f 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void); size_t get_def_hugetlb_pagesz(void); const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i); size_t get_backing_src_pagesz(uint32_t i); +bool is_backing_src_hugetlb(uint32_t i); void backing_src_help(const char *flag); enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name); long get_run_delay(void); @@ -117,4 +118,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t) return vm_mem_backing_src_alias(t)->flag & MAP_SHARED; } +/* Aligns x up to the next multiple of size. Size must be a power of 2. */ +static inline uint64_t align_up(uint64_t x, uint64_t size) +{ + uint64_t mask = size - 1; + + TEST_ASSERT(size != 0 && !(size & (size - 1)), + "size not a power of 2: %lu", size); + return ((x + mask) & ~mask); +} + +static inline uint64_t align_down(uint64_t x, uint64_t size) +{ + uint64_t x_aligned_up = align_up(x, size); + + if (x == x_aligned_up) + return x; + else + return x_aligned_up - size; +} + +static inline void *align_ptr_up(void *x, size_t size) +{ + return (void *)align_up((unsigned long)x, size); +} + #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c index 36407cb0ec85..3836322add00 100644 --- a/tools/testing/selftests/kvm/kvm_page_table_test.c +++ b/tools/testing/selftests/kvm/kvm_page_table_test.c @@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg) #ifdef __s390x__ alignment = max(0x100000, alignment); #endif - guest_test_phys_mem &= ~(alignment - 1); + guest_test_phys_mem = align_down(guest_test_virt_mem, alignment); /* Set up the shared data structure test_args */ test_args.vm = vm; diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index eac44f5d0db0..13e8e3dcf984 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) "memsize of 0,\n" " phdr index: %u p_memsz: 0x%" PRIx64, n1, (uint64_t) phdr.p_memsz); - vm_vaddr_t seg_vstart = phdr.p_vaddr; - seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1); + vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size); vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1; seg_vend |= vm->page_size - 1; size_t seg_size = seg_vend - seg_vstart + 1; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 14bb4d5b6bb7..8f2e0bb1ef96 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -22,15 +22,6 @@ static int vcpu_mmap_sz(void); -/* Aligns x up to the next multiple of size. Size must be a power of 2. */ -static void *align(void *x, size_t size) -{ - size_t mask = size - 1; - TEST_ASSERT(size != 0 && !(size & (size - 1)), - "size not a power of 2: %lu", size); - return (void *) (((size_t) x + mask) & ~mask); -} - int open_path_or_exit(const char *path, int flags) { int fd; @@ -191,15 +182,15 @@ const char *vm_guest_mode_string(uint32_t i) } const struct vm_guest_mode_params vm_guest_mode_params[] = { - { 52, 48, 0x1000, 12 }, - { 52, 48, 0x10000, 16 }, - { 48, 48, 0x1000, 12 }, - { 48, 48, 0x10000, 16 }, - { 40, 48, 0x1000, 12 }, - { 40, 48, 0x10000, 16 }, - { 0, 0, 0x1000, 12 }, - { 47, 64, 0x1000, 12 }, - { 44, 64, 0x1000, 12 }, + [VM_MODE_P52V48_4K] = { 52, 48, 0x1000, 12 }, + [VM_MODE_P52V48_64K] = { 52, 48, 0x10000, 16 }, + [VM_MODE_P48V48_4K] = { 48, 48, 0x1000, 12 }, + [VM_MODE_P48V48_64K] = { 48, 48, 0x10000, 16 }, + [VM_MODE_P40V48_4K] = { 40, 48, 0x1000, 12 }, + [VM_MODE_P40V48_64K] = { 40, 48, 0x10000, 16 }, + [VM_MODE_PXXV48_4K] = { 0, 0, 0x1000, 12 }, + [VM_MODE_P47V64_4K] = { 47, 64, 0x1000, 12 }, + [VM_MODE_P44V64_4K] = { 44, 64, 0x1000, 12 }, }; _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES, "Missing new mode params?"); @@ -879,9 +870,17 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, alignment = 1; #endif + /* + * When using THP mmap is not guaranteed to returned a hugepage aligned + * address so we have to pad the mmap. Padding is not needed for HugeTLB + * because mmap will always return an address aligned to the HugeTLB + * page size. + */ if (src_type == VM_MEM_SRC_ANONYMOUS_THP) alignment = max(backing_src_pagesz, alignment); + ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz)); + /* Add enough memory to align up if necessary */ if (alignment > 1) region->mmap_size += alignment; @@ -914,8 +913,13 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "test_malloc failed, mmap_start: %p errno: %i", region->mmap_start, errno); + TEST_ASSERT(!is_backing_src_hugetlb(src_type) || + region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), + "mmap_start %p is not aligned to HugeTLB page size 0x%lx", + region->mmap_start, backing_src_pagesz); + /* Align host address */ - region->host_mem = align(region->mmap_start, alignment); + region->host_mem = align_ptr_up(region->mmap_start, alignment); /* As needed perform madvise */ if ((src_type == VM_MEM_SRC_ANONYMOUS || @@ -958,7 +962,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, "mmap of alias failed, errno: %i", errno); /* Align host alias address */ - region->host_alias = align(region->mmap_alias, alignment); + region->host_alias = align_ptr_up(region->mmap_alias, alignment); } } diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c index 0ef80dbdc116..722df3a28791 100644 --- a/tools/testing/selftests/kvm/lib/perf_test_util.c +++ b/tools/testing/selftests/kvm/lib/perf_test_util.c @@ -10,21 +10,40 @@ struct perf_test_args perf_test_args; -uint64_t guest_test_phys_mem; - /* * Guest virtual memory offset of the testing memory slot. * Must not conflict with identity mapped test code. */ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +struct vcpu_thread { + /* The id of the vCPU. */ + int vcpu_id; + + /* The pthread backing the vCPU. */ + pthread_t thread; + + /* Set to true once the vCPU thread is up and running. */ + bool running; +}; + +/* The vCPU threads involved in this test. */ +static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS]; + +/* The function run by each vCPU thread, as provided by the test. */ +static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *); + +/* Set to true once all vCPU threads are up and running. */ +static bool all_vcpu_threads_running; + /* * Continuously write to the first 8 bytes of each page in the * specified region. */ static void guest_code(uint32_t vcpu_id) { - struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id]; uint64_t gva; uint64_t pages; int i; @@ -37,9 +56,9 @@ static void guest_code(uint32_t vcpu_id) while (true) { for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * perf_test_args.guest_page_size); + uint64_t addr = gva + (i * pta->guest_page_size); - if (i % perf_test_args.wr_fract == 0) + if (i % pta->wr_fract == 0) *(uint64_t *)addr = 0x0123456789ABCDEF; else READ_ONCE(*(uint64_t *)addr); @@ -49,35 +68,81 @@ static void guest_code(uint32_t vcpu_id) } } +void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, + uint64_t vcpu_memory_bytes, + bool partition_vcpu_memory_access) +{ + struct perf_test_args *pta = &perf_test_args; + struct perf_test_vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &pta->vcpu_args[vcpu_id]; + + vcpu_args->vcpu_id = vcpu_id; + if (partition_vcpu_memory_access) { + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes); + } else { + vcpu_args->gva = guest_test_virt_mem; + vcpu_args->pages = (vcpus * vcpu_memory_bytes) / + pta->guest_page_size; + vcpu_args->gpa = pta->gpa; + } + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_args->gpa, vcpu_args->gpa + + (vcpu_args->pages * pta->guest_page_size)); + } +} + struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, uint64_t vcpu_memory_bytes, int slots, - enum vm_mem_backing_src_type backing_src) + enum vm_mem_backing_src_type backing_src, + bool partition_vcpu_memory_access) { + struct perf_test_args *pta = &perf_test_args; struct kvm_vm *vm; uint64_t guest_num_pages; + uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src); int i; pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - perf_test_args.host_page_size = getpagesize(); - perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size; + /* By default vCPUs will write to memory. */ + pta->wr_fract = 1; + + /* + * Snapshot the non-huge page size. This is used by the guest code to + * access/dirty pages at the logging granularity. + */ + pta->guest_page_size = vm_guest_mode_params[mode].page_size; guest_num_pages = vm_adjust_num_guest_pages(mode, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size); + (vcpus * vcpu_memory_bytes) / pta->guest_page_size); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0, "Guest memory size is not host page size aligned."); - TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0, "Guest memory size is not guest page size aligned."); TEST_ASSERT(guest_num_pages % slots == 0, "Guest memory cannot be evenly divided into %d slots.", slots); + /* + * Pass guest_num_pages to populate the page tables for test memory. + * The memory is also added to memslot 0, but that's a benign side + * effect as KVM allows aliasing HVAs in meslots. + */ vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES, - (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size, - 0, guest_code, NULL); + guest_num_pages, 0, guest_code, NULL); - perf_test_args.vm = vm; + pta->vm = vm; /* * If there should be more memory in the guest test region than there @@ -90,20 +155,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, guest_num_pages, vm_get_max_gfn(vm), vcpus, vcpu_memory_bytes); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - perf_test_args.guest_page_size; - guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size; + pta->gpa = align_down(pta->gpa, backing_src_pagesz); #ifdef __s390x__ /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); + pta->gpa = align_down(pta->gpa, 1 << 20); #endif - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa); /* Add extra memory slots for testing */ for (i = 0; i < slots; i++) { uint64_t region_pages = guest_num_pages / slots; - vm_paddr_t region_start = guest_test_phys_mem + - region_pages * perf_test_args.guest_page_size * i; + vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i; vm_userspace_mem_region_add(vm, backing_src, region_start, PERF_TEST_MEM_SLOT_INDEX + i, @@ -111,10 +174,15 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus, } /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages); + virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages); + + perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access); ucall_init(vm, NULL); + /* Export the shared variables to the guest. */ + sync_global_to_guest(vm, perf_test_args); + return vm; } @@ -124,36 +192,60 @@ void perf_test_destroy_vm(struct kvm_vm *vm) kvm_vm_free(vm); } -void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus, - uint64_t vcpu_memory_bytes, - bool partition_vcpu_memory_access) +void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract) +{ + perf_test_args.wr_fract = wr_fract; + sync_global_to_guest(vm, perf_test_args); +} + +static void *vcpu_thread_main(void *data) +{ + struct vcpu_thread *vcpu = data; + + WRITE_ONCE(vcpu->running, true); + + /* + * Wait for all vCPU threads to be up and running before calling the test- + * provided vCPU thread function. This prevents thread creation (which + * requires taking the mmap_sem in write mode) from interfering with the + * guest faulting in its memory. + */ + while (!READ_ONCE(all_vcpu_threads_running)) + ; + + vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]); + + return NULL; +} + +void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *)) { - vm_paddr_t vcpu_gpa; - struct perf_test_vcpu_args *vcpu_args; int vcpu_id; + vcpu_thread_fn = vcpu_fn; + WRITE_ONCE(all_vcpu_threads_running, false); + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id]; - vcpu_args->vcpu_id = vcpu_id; - if (partition_vcpu_memory_access) { - vcpu_args->gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args->pages = vcpu_memory_bytes / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem + - (vcpu_id * vcpu_memory_bytes); - } else { - vcpu_args->gva = guest_test_virt_mem; - vcpu_args->pages = (vcpus * vcpu_memory_bytes) / - perf_test_args.guest_page_size; - vcpu_gpa = guest_test_phys_mem; - } + vcpu->vcpu_id = vcpu_id; + WRITE_ONCE(vcpu->running, false); - vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu); + } - pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + - (vcpu_args->pages * perf_test_args.guest_page_size)); + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + while (!READ_ONCE(vcpu_threads[vcpu_id].running)) + ; } + + WRITE_ONCE(all_vcpu_threads_running, true); +} + +void perf_test_join_vcpu_threads(int vcpus) +{ + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id].thread, NULL); } diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index b72429108993..6d23878bbfe1 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i) } } +bool is_backing_src_hugetlb(uint32_t i) +{ + return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB); +} + static void print_available_backing_src_types(const char *prefix) { int i; diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c index 4cfcafea9f5a..1410d0a9141a 100644 --- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c +++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c @@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; static bool run_vcpus = true; -static void *vcpu_worker(void *data) +static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args) { int ret; - struct perf_test_vcpu_args *vcpu_args = - (struct perf_test_vcpu_args *)data; int vcpu_id = vcpu_args->vcpu_id; struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; @@ -59,8 +57,6 @@ static void *vcpu_worker(void *data) "Invalid guest sync status: exit_reason=%s\n", exit_reason_str(run->exit_reason)); } - - return NULL; } struct memslot_antagonist_args { @@ -80,7 +76,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay, * Add the dummy memslot just below the perf_test_util memslot, which is * at the top of the guest physical address space. */ - gpa = guest_test_phys_mem - pages * vm_get_page_size(vm); + gpa = perf_test_args.gpa - pages * vm_get_page_size(vm); for (i = 0; i < nr_modifications; i++) { usleep(delay); @@ -100,29 +96,15 @@ struct test_params { static void run_test(enum vm_guest_mode mode, void *arg) { struct test_params *p = arg; - pthread_t *vcpu_threads; struct kvm_vm *vm; - int vcpu_id; vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1, - VM_MEM_SRC_ANONYMOUS); - - perf_test_args.wr_fract = 1; - - vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); - TEST_ASSERT(vcpu_threads, "Memory allocation failed"); - - perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size, - p->partition_vcpu_memory_access); - - /* Export the shared variables to the guest */ - sync_global_to_guest(vm, perf_test_args); + VM_MEM_SRC_ANONYMOUS, + p->partition_vcpu_memory_access); pr_info("Finished creating vCPUs\n"); - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &perf_test_args.vcpu_args[vcpu_id]); + perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker); pr_info("Started all vCPUs\n"); @@ -131,16 +113,10 @@ static void run_test(enum vm_guest_mode mode, void *arg) run_vcpus = false; - /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) - pthread_join(vcpu_threads[vcpu_id], NULL); - + perf_test_join_vcpu_threads(nr_vcpus); pr_info("All vCPU threads joined\n"); - ucall_uninit(vm); - kvm_vm_free(vm); - - free(vcpu_threads); + perf_test_destroy_vm(vm); } static void help(char *name) diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index eda0d2a51224..a0699f00b3d6 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -24,8 +24,12 @@ #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) +#define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) +#define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) + +#define EVTCHN_VECTOR 0x10 static struct kvm_vm *vm; @@ -56,15 +60,44 @@ struct vcpu_runstate_info { uint64_t time[4]; }; +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; + +struct vcpu_info { + uint8_t evtchn_upcall_pending; + uint8_t evtchn_upcall_mask; + unsigned long evtchn_pending_sel; + struct arch_vcpu_info arch; + struct pvclock_vcpu_time_info time; +}; /* 64 bytes (x86) */ + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static void evtchn_handler(struct ex_regs *regs) +{ + struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; + vi->evtchn_upcall_pending = 0; + + GUEST_SYNC(0x20); +} + static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + __asm__ __volatile__( + "sti\n" + "nop\n" + ); + + /* Trigger an interrupt injection */ + GUEST_SYNC(0); + /* Test having the host set runstates manually */ GUEST_SYNC(RUNSTATE_runnable); GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0); @@ -153,7 +186,7 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, - .u.gpa = SHINFO_REGION_GPA + 0x40, + .u.gpa = VCPU_INFO_ADDR, }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi); @@ -163,6 +196,16 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock); + struct kvm_xen_hvm_attr vec = { + .type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR, + .u.vector = EVTCHN_VECTOR, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler); + if (do_runstate_tests) { struct kvm_xen_vcpu_attr st = { .type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR, @@ -171,9 +214,14 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); + vinfo->evtchn_upcall_pending = 0; + struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR); rs->state = 0x5a; + bool evtchn_irq_expected = false; + for (;;) { volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID); struct ucall uc; @@ -193,16 +241,21 @@ int main(int argc, char *argv[]) struct kvm_xen_vcpu_attr rst; long rundelay; - /* If no runstate support, bail out early */ - if (!do_runstate_tests) - goto done; - - TEST_ASSERT(rs->state_entry_time == rs->time[0] + - rs->time[1] + rs->time[2] + rs->time[3], - "runstate times don't add up"); + if (do_runstate_tests) + TEST_ASSERT(rs->state_entry_time == rs->time[0] + + rs->time[1] + rs->time[2] + rs->time[3], + "runstate times don't add up"); switch (uc.args[1]) { - case RUNSTATE_running...RUNSTATE_offline: + case 0: + evtchn_irq_expected = true; + vinfo->evtchn_upcall_pending = 1; + break; + + case RUNSTATE_runnable...RUNSTATE_offline: + TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); + if (!do_runstate_tests) + goto done; rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); @@ -236,6 +289,10 @@ int main(int argc, char *argv[]) sched_yield(); } while (get_run_delay() < rundelay); break; + case 0x20: + TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); + evtchn_irq_expected = false; + break; } break; } diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index a4bd1b087303..697994a9278b 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -6,6 +6,7 @@ CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_NET_VRF=m CONFIG_BPF_SYSCALL=y CONFIG_CGROUP_BPF=y +CONFIG_NET_ACT_CT=m CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_MPLS=m CONFIG_NET_ACT_VLAN=m diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca227136b..de19eb6c38f0 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,7 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test mirred_egress_to_ingress_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -13,10 +13,12 @@ tcflags="skip_hw" h1_create() { simple_if_init $h1 192.0.2.1/24 + tc qdisc add dev $h1 clsact } h1_destroy() { + tc qdisc del dev $h1 clsact simple_if_fini $h1 192.0.2.1/24 } @@ -153,6 +155,49 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_test() +{ + RET=0 + + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action \ + ct commit nat src addr 192.0.2.2 pipe \ + ct clear pipe \ + ct commit nat dst addr 192.0.2.1 pipe \ + mirred ingress redirect dev $h1 + + tc filter add dev $swp1 protocol ip pref 11 handle 111 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 8 action drop + tc filter add dev $swp1 protocol ip pref 12 handle 112 ingress flower \ + ip_proto icmp src_ip 192.0.2.1 dst_ip 192.0.2.2 type 0 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t icmp "ping,id=42,seq=10" -q + + tc_check_packets "dev $h1 egress" 100 1 + check_err $? "didn't mirror first packet" + + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect first packet" + tc_check_packets "dev $swp1 ingress" 112 1 + check_err $? "didn't receive reply to first packet" + + ping 192.0.2.2 -I$h1 -c1 -w1 -q 1>/dev/null 2>&1 + + tc_check_packets "dev $h1 egress" 100 2 + check_err $? "didn't mirror second packet" + tc_check_packets "dev $swp1 ingress" 111 1 + check_fail $? "didn't redirect second packet" + tc_check_packets "dev $swp1 ingress" 112 2 + check_err $? "didn't receive reply to second packet" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $swp1 ingress protocol ip pref 11 handle 111 flower + tc filter del dev $swp1 ingress protocol ip pref 12 handle 112 flower + + log_test "mirred_egress_to_ingress ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/gre_gso.sh b/tools/testing/selftests/net/gre_gso.sh index fdeb44d621eb..3224651db97b 100755 --- a/tools/testing/selftests/net/gre_gso.sh +++ b/tools/testing/selftests/net/gre_gso.sh @@ -118,16 +118,18 @@ gre_gst_test_checks() local addr=$2 local proto=$3 - $NS_EXEC nc $proto -kl $port >/dev/null & + [ "$proto" == 6 ] && addr="[$addr]" + + $NS_EXEC socat - tcp${proto}-listen:$port,reuseaddr,fork >/dev/null & PID=$! while ! $NS_EXEC ss -ltn | grep -q $port; do ((i++)); sleep 0.01; done - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ TSO" ethtool -K veth0 tso off - cat $TMPFILE | timeout 1 nc $proto -N $addr $port + cat $TMPFILE | timeout 1 socat -u STDIN TCP:$addr:$port log_test $? 0 "$name - copy file w/ GSO" ethtool -K veth0 tso on @@ -155,8 +157,8 @@ gre6_gso_test() sleep 2 - gre_gst_test_checks GREv6/v4 172.16.2.2 - gre_gst_test_checks GREv6/v6 2001:db8:1::2 -6 + gre_gst_test_checks GREv6/v4 172.16.2.2 4 + gre_gst_test_checks GREv6/v6 2001:db8:1::2 6 cleanup } @@ -212,8 +214,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi -if [ ! -x "$(command -v nc)" ]; then - echo "SKIP: Could not run test without nc tool" +if [ ! -x "$(command -v socat)" ]; then + echo "SKIP: Could not run test without socat tool" exit $ksft_skip fi diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d31724500501..9646bb9112c1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2548,72 +2548,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache) +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty) { if (pfn == 0) return; - if (cache) - cache->pfn = cache->gfn = 0; - if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } -static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn, - struct gfn_to_pfn_cache *cache, u64 gen) -{ - kvm_release_pfn(cache->pfn, cache->dirty, cache); - - cache->pfn = gfn_to_pfn_memslot(slot, gfn); - cache->gfn = gfn; - cache->dirty = false; - cache->generation = gen; -} - -static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool atomic) +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; - struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn); - u64 gen = slots->generation; if (!map) return -EINVAL; - if (cache) { - if (!cache->pfn || cache->gfn != gfn || - cache->generation != gen) { - if (atomic) - return -EAGAIN; - kvm_cache_gfn_to_pfn(slot, gfn, cache, gen); - } - pfn = cache->pfn; - } else { - if (atomic) - return -EAGAIN; - pfn = gfn_to_pfn_memslot(slot, gfn); - } + pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); - if (atomic) - hva = kmap_atomic(page); - else - hva = kmap(page); + hva = kmap(page); #ifdef CONFIG_HAS_IOMEM - } else if (!atomic) { - hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); } else { - return -EINVAL; + hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } @@ -2627,27 +2591,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, return 0; } - -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic) -{ - return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map, - cache, atomic); -} -EXPORT_SYMBOL_GPL(kvm_map_gfn); - -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) -{ - return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map, - NULL, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_map); -static void __kvm_unmap_gfn(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool dirty, bool atomic) +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; @@ -2655,45 +2601,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm, if (!map->hva) return; - if (map->page != KVM_UNMAPPED_PAGE) { - if (atomic) - kunmap_atomic(map->hva); - else - kunmap(map->page); - } + if (map->page != KVM_UNMAPPED_PAGE) + kunmap(map->page); #ifdef CONFIG_HAS_IOMEM - else if (!atomic) - memunmap(map->hva); else - WARN_ONCE(1, "Unexpected unmapping in atomic context"); + memunmap(map->hva); #endif if (dirty) - mark_page_dirty_in_slot(kvm, memslot, map->gfn); + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); - if (cache) - cache->dirty |= dirty; - else - kvm_release_pfn(map->pfn, dirty, NULL); + kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } - -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic) -{ - __kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map, - cache, dirty, atomic); - return 0; -} -EXPORT_SYMBOL_GPL(kvm_unmap_gfn); - -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) -{ - __kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), - map, NULL, dirty, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) |