diff --git a/.mailmap b/.mailmap index 85307aeed9da..84309a39d329 100644 --- a/.mailmap +++ b/.mailmap @@ -303,6 +303,7 @@ Hans de Goede Hans Verkuil Hans Verkuil Hans Verkuil +Hao Ge Harry Yoo <42.hyeyoo@gmail.com> Heiko Carstens Heiko Carstens @@ -503,9 +504,7 @@ Mark Brown Mark Starovoytov Markus Schneider-Pargmann Mark Yao -Martin Kepplinger -Martin Kepplinger -Martin Kepplinger +Martin Kepplinger-Novakovic Martyna Szapar-Mudlaw Mathieu Othacehe Mat Martineau @@ -856,6 +855,9 @@ Vivien Didelot Vlad Dogaru Vladimir Davydov Vladimir Davydov +WangYuli +WangYuli +WangYuli Weiwen Hu WeiXiong Liao Wen Gong @@ -867,6 +869,7 @@ Yakir Yang Yanteng Si Ying Huang Yosry Ahmed +Yu-Chun Lin Yusuke Goda Zack Rusin Zhu Yanjun diff --git a/CREDITS b/CREDITS index fa5397f4ebcd..85bdc8828734 100644 --- a/CREDITS +++ b/CREDITS @@ -2056,16 +2056,15 @@ S: Korte Heul 95 S: 1403 ND BUSSUM S: The Netherlands -N: Martin Kepplinger +N: Martin Kepplinger-Novakovic E: martink@posteo.de -E: martin.kepplinger@puri.sm -W: http://www.martinkepplinger.com P: 4096R/5AB387D3 F208 2B88 0F9E 4239 3468 6E3F 5003 98DF 5AB3 87D3 D: mma8452 accelerators iio driver D: pegasus_notetaker input driver +D: imx8m media and hi846 sensor driver D: Kernel fixes and cleanups -S: Garnisonstraße 26 -S: 4020 Linz +S: Keplerstr. 6 +S: 4050 Traun S: Austria N: Karl Keyte diff --git a/Documentation/ABI/obsolete/sysfs-kernel-kexec-kdump b/Documentation/ABI/obsolete/sysfs-kernel-kexec-kdump new file mode 100644 index 000000000000..ba26a6a1d2be --- /dev/null +++ b/Documentation/ABI/obsolete/sysfs-kernel-kexec-kdump @@ -0,0 +1,71 @@ +NOTE: all the ABIs listed in this file are deprecated and will be removed after 2028. + +Here are the alternative ABIs: ++------------------------------------+-----------------------------------------+ +| Deprecated | Alternative | ++------------------------------------+-----------------------------------------+ +| /sys/kernel/kexec_loaded | /sys/kernel/kexec/loaded | ++------------------------------------+-----------------------------------------+ +| /sys/kernel/kexec_crash_loaded | /sys/kernel/kexec/crash_loaded | ++------------------------------------+-----------------------------------------+ +| /sys/kernel/kexec_crash_size | /sys/kernel/kexec/crash_size | ++------------------------------------+-----------------------------------------+ +| /sys/kernel/crash_elfcorehdr_size | /sys/kernel/kexec/crash_elfcorehdr_size | ++------------------------------------+-----------------------------------------+ +| /sys/kernel/kexec_crash_cma_ranges | /sys/kernel/kexec/crash_cma_ranges | ++------------------------------------+-----------------------------------------+ + + +What: /sys/kernel/kexec_loaded +Date: Jun 2006 +Contact: kexec@lists.infradead.org +Description: read only + Indicates whether a new kernel image has been loaded + into memory using the kexec system call. It shows 1 if + a kexec image is present and ready to boot, or 0 if none + is loaded. +User: kexec tools, kdump service + +What: /sys/kernel/kexec_crash_loaded +Date: Jun 2006 +Contact: kexec@lists.infradead.org +Description: read only + Indicates whether a crash (kdump) kernel is currently + loaded into memory. It shows 1 if a crash kernel has been + successfully loaded for panic handling, or 0 if no crash + kernel is present. +User: Kexec tools, Kdump service + +What: /sys/kernel/kexec_crash_size +Date: Dec 2009 +Contact: kexec@lists.infradead.org +Description: read/write + Shows the amount of memory reserved for loading the crash + (kdump) kernel. It reports the size, in bytes, of the + crash kernel area defined by the crashkernel= parameter. + This interface also allows reducing the crashkernel + reservation by writing a smaller value, and the reclaimed + space is added back to the system RAM. +User: Kdump service + +What: /sys/kernel/crash_elfcorehdr_size +Date: Aug 2023 +Contact: kexec@lists.infradead.org +Description: read only + Indicates the preferred size of the memory buffer for the + ELF core header used by the crash (kdump) kernel. It defines + how much space is needed to hold metadata about the crashed + system, including CPU and memory information. This information + is used by the user space utility kexec to support updating the + in-kernel kdump image during hotplug operations. +User: Kexec tools + +What: /sys/kernel/kexec_crash_cma_ranges +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read only + Provides information about the memory ranges reserved from + the Contiguous Memory Allocator (CMA) area that are allocated + to the crash (kdump) kernel. It lists the start and end physical + addresses of CMA regions assigned for crashkernel use. +User: kdump service diff --git a/Documentation/ABI/testing/sysfs-kernel-kexec-kdump b/Documentation/ABI/testing/sysfs-kernel-kexec-kdump new file mode 100644 index 000000000000..f59051b5d96d --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-kexec-kdump @@ -0,0 +1,61 @@ +What: /sys/kernel/kexec/* +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: + The /sys/kernel/kexec/* directory contains sysfs files + that provide information about the configuration status + of kexec and kdump. + +What: /sys/kernel/kexec/loaded +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read only + Indicates whether a new kernel image has been loaded + into memory using the kexec system call. It shows 1 if + a kexec image is present and ready to boot, or 0 if none + is loaded. +User: kexec tools, kdump service + +What: /sys/kernel/kexec/crash_loaded +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read only + Indicates whether a crash (kdump) kernel is currently + loaded into memory. It shows 1 if a crash kernel has been + successfully loaded for panic handling, or 0 if no crash + kernel is present. +User: Kexec tools, Kdump service + +What: /sys/kernel/kexec/crash_size +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read/write + Shows the amount of memory reserved for loading the crash + (kdump) kernel. It reports the size, in bytes, of the + crash kernel area defined by the crashkernel= parameter. + This interface also allows reducing the crashkernel + reservation by writing a smaller value, and the reclaimed + space is added back to the system RAM. +User: Kdump service + +What: /sys/kernel/kexec/crash_elfcorehdr_size +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read only + Indicates the preferred size of the memory buffer for the + ELF core header used by the crash (kdump) kernel. It defines + how much space is needed to hold metadata about the crashed + system, including CPU and memory information. This information + is used by the user space utility kexec to support updating the + in-kernel kdump image during hotplug operations. +User: Kexec tools + +What: /sys/kernel/kexec/crash_cma_ranges +Date: Nov 2025 +Contact: kexec@lists.infradead.org +Description: read only + Provides information about the memory ranges reserved from + the Contiguous Memory Allocator (CMA) area that are allocated + to the crash (kdump) kernel. It lists the start and end physical + addresses of CMA regions assigned for crashkernel use. +User: kdump service diff --git a/Documentation/admin-guide/dynamic-debug-howto.rst b/Documentation/admin-guide/dynamic-debug-howto.rst index 7c036590cd07..095a63892257 100644 --- a/Documentation/admin-guide/dynamic-debug-howto.rst +++ b/Documentation/admin-guide/dynamic-debug-howto.rst @@ -223,12 +223,13 @@ The flags are:: f Include the function name s Include the source file name l Include line number + d Include call trace For ``print_hex_dump_debug()`` and ``print_hex_dump_bytes()``, only the ``p`` flag has meaning, other flags are ignored. -Note the regexp ``^[-+=][fslmpt_]+$`` matches a flags specification. -To clear all flags at once, use ``=_`` or ``-fslmpt``. +Note the regexp ``^[-+=][fslmptd_]+$`` matches a flags specification. +To clear all flags at once, use ``=_`` or ``-fslmptd``. Debug messages during Boot Process diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b242519f57da..b86b6d946d88 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2114,14 +2114,20 @@ Kernel parameters the added memory block itself do not be affected. hung_task_panic= - [KNL] Should the hung task detector generate panics. - Format: 0 | 1 + [KNL] Number of hung tasks to trigger kernel panic. + Format: - A value of 1 instructs the kernel to panic when a - hung task is detected. The default value is controlled - by the CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time - option. The value selected by this boot parameter can - be changed later by the kernel.hung_task_panic sysctl. + When set to a non-zero value, a kernel panic will be triggered if + the number of detected hung tasks reaches this value. + + 0: don't panic + 1: panic immediately on first hung task + N: panic after N hung tasks are detected in a single scan + + The default value is controlled by the + CONFIG_BOOTPARAM_HUNG_TASK_PANIC build-time option. The value + selected by this boot parameter can be changed later by the + kernel.hung_task_panic sysctl. hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC) terminal devices. Valid values: 0..8 diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index f3ee807b5d8b..239da22c4e28 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -397,13 +397,14 @@ a hung task is detected. hung_task_panic =============== -Controls the kernel's behavior when a hung task is detected. +When set to a non-zero value, a kernel panic will be triggered if the +number of hung tasks found during a single scan reaches this value. This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled. -= ================================================= += ======================================================= 0 Continue operation. This is the default behavior. -1 Panic immediately. -= ================================================= +N Panic when N hung tasks are found during a single scan. += ======================================================= hung_task_check_count @@ -421,6 +422,11 @@ the system boot. This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled. +hung_task_sys_info +================== +A comma separated list of extra system information to be dumped when +hung task is detected, for example, "tasks,mem,timers,locks,...". +Refer 'panic_sys_info' section below for more details. hung_task_timeout_secs ====================== @@ -515,6 +521,15 @@ default), only processes with the CAP_SYS_ADMIN capability may create io_uring instances. +kernel_sys_info +=============== +A comma separated list of extra system information to be dumped when +soft/hard lockup is detected, for example, "tasks,mem,timers,locks,...". +Refer 'panic_sys_info' section below for more details. + +It serves as the default kernel control knob, which will take effect +when a kernel module calls sys_info() with parameter==0. + kexec_load_disabled =================== @@ -576,6 +591,11 @@ if leaking kernel pointer values to unprivileged users is a concern. When ``kptr_restrict`` is set to 2, kernel pointers printed using %pK will be replaced with 0s regardless of privileges. +softlockup_sys_info & hardlockup_sys_info +========================================= +A comma separated list of extra system information to be dumped when +soft/hard lockup is detected, for example, "tasks,mem,timers,locks,...". +Refer 'panic_sys_info' section below for more details. modprobe ======== @@ -910,8 +930,8 @@ to 'panic_print'. Possible values are: ============= =================================================== tasks print all tasks info mem print system memory info -timer print timers info -lock print locks info if CONFIG_LOCKDEP is on +timers print timers info +locks print locks info if CONFIG_LOCKDEP is on ftrace print ftrace buffer all_bt print all CPUs backtrace (if available in the arch) blocked_tasks print only tasks in uninterruptible (blocked) state diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst index 6cbdcbfa79c3..5eb0fbbbc323 100644 --- a/Documentation/core-api/index.rst +++ b/Documentation/core-api/index.rst @@ -138,6 +138,7 @@ Documents that don't fit elsewhere or which have yet to be categorized. :maxdepth: 1 librs + liveupdate netlink .. only:: subproject and html diff --git a/Documentation/core-api/kho/concepts.rst b/Documentation/core-api/kho/concepts.rst index 36d5c05cfb30..d626d1dbd678 100644 --- a/Documentation/core-api/kho/concepts.rst +++ b/Documentation/core-api/kho/concepts.rst @@ -70,5 +70,5 @@ in the FDT. That state is called the KHO finalization phase. Public API ========== -.. kernel-doc:: kernel/kexec_handover.c +.. kernel-doc:: kernel/liveupdate/kexec_handover.c :export: diff --git a/Documentation/core-api/liveupdate.rst b/Documentation/core-api/liveupdate.rst new file mode 100644 index 000000000000..7960eb15a81f --- /dev/null +++ b/Documentation/core-api/liveupdate.rst @@ -0,0 +1,61 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +Live Update Orchestrator +======================== +:Author: Pasha Tatashin + +.. kernel-doc:: kernel/liveupdate/luo_core.c + :doc: Live Update Orchestrator (LUO) + +LUO Sessions +============ +.. kernel-doc:: kernel/liveupdate/luo_session.c + :doc: LUO Sessions + +LUO Preserving File Descriptors +=============================== +.. kernel-doc:: kernel/liveupdate/luo_file.c + :doc: LUO File Descriptors + +Live Update Orchestrator ABI +============================ +.. kernel-doc:: include/linux/kho/abi/luo.h + :doc: Live Update Orchestrator ABI + +The following types of file descriptors can be preserved + +.. toctree:: + :maxdepth: 1 + + ../mm/memfd_preservation + +Public API +========== +.. kernel-doc:: include/linux/liveupdate.h + +.. kernel-doc:: include/linux/kho/abi/luo.h + :functions: + +.. kernel-doc:: kernel/liveupdate/luo_core.c + :export: + +.. kernel-doc:: kernel/liveupdate/luo_file.c + :export: + +Internal API +============ +.. kernel-doc:: kernel/liveupdate/luo_core.c + :internal: + +.. kernel-doc:: kernel/liveupdate/luo_session.c + :internal: + +.. kernel-doc:: kernel/liveupdate/luo_file.c + :internal: + +See Also +======== + +- :doc:`Live Update uAPI ` +- :doc:`/core-api/kho/concepts` diff --git a/Documentation/dev-tools/checkpatch.rst b/Documentation/dev-tools/checkpatch.rst index dfaad0a279ff..fa2988dd4657 100644 --- a/Documentation/dev-tools/checkpatch.rst +++ b/Documentation/dev-tools/checkpatch.rst @@ -1238,6 +1238,16 @@ Others The patch file does not appear to be in unified-diff format. Please regenerate the patch file before sending it to the maintainer. + **PLACEHOLDER_USE** + Detects unhandled placeholder text left in cover letters or commit headers/logs. + Common placeholders include lines like:: + + *** SUBJECT HERE *** + *** BLURB HERE *** + + These typically come from autogenerated templates. Replace them with a proper + subject and description before sending. + **PRINTF_0XDECIMAL** Prefixing 0x with decimal output is defective and should be corrected. diff --git a/Documentation/driver-api/hw-recoverable-errors.rst b/Documentation/driver-api/hw-recoverable-errors.rst new file mode 100644 index 000000000000..fc526c3454bd --- /dev/null +++ b/Documentation/driver-api/hw-recoverable-errors.rst @@ -0,0 +1,60 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================================= +Recoverable Hardware Error Tracking in vmcoreinfo +================================================= + +Overview +-------- + +This feature provides a generic infrastructure within the Linux kernel to track +and log recoverable hardware errors. These are hardware recoverable errors +visible that might not cause immediate panics but may influence health, mainly +because new code path will be executed in the kernel. + +By recording counts and timestamps of recoverable errors into the vmcoreinfo +crash dump notes, this infrastructure aids post-mortem crash analysis tools in +correlating hardware events with kernel failures. This enables faster triage +and better understanding of root causes, especially in large-scale cloud +environments where hardware issues are common. + +Benefits +-------- + +- Facilitates correlation of hardware recoverable errors with kernel panics or + unusual code paths that lead to system crashes. +- Provides operators and cloud providers quick insights, improving reliability + and reducing troubleshooting time. +- Complements existing full hardware diagnostics without replacing them. + +Data Exposure and Consumption +----------------------------- + +- The tracked error data consists of per-error-type counts and timestamps of + last occurrence. +- This data is stored in the `hwerror_data` array, categorized by error source + types like CPU, memory, PCI, CXL, and others. +- It is exposed via vmcoreinfo crash dump notes and can be read using tools + like `crash`, `drgn`, or other kernel crash analysis utilities. +- There is no other way to read these data other than from crash dumps. +- These errors are divided by area, which includes CPU, Memory, PCI, CXL and + others. + +Typical usage example (in drgn REPL): + +.. code-block:: python + + >>> prog['hwerror_data'] + (struct hwerror_info[HWERR_RECOV_MAX]){ + { + .count = (int)844, + .timestamp = (time64_t)1752852018, + }, + ... + } + +Enabling +-------- + +- This feature is enabled when CONFIG_VMCORE_INFO is set. + diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index baff96b5cf0b..1833e6a0687e 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -97,6 +97,7 @@ Subsystem-specific APIs gpio/index hsi hte/index + hw-recoverable-errors i2c iio/index infiniband diff --git a/Documentation/mm/index.rst b/Documentation/mm/index.rst index ba6a8872849b..7aa2a8886908 100644 --- a/Documentation/mm/index.rst +++ b/Documentation/mm/index.rst @@ -48,6 +48,7 @@ documentation, or deleted if it has served its purpose. hugetlbfs_reserv ksm memory-model + memfd_preservation mmu_notifier multigen_lru numa diff --git a/Documentation/mm/memfd_preservation.rst b/Documentation/mm/memfd_preservation.rst new file mode 100644 index 000000000000..66e0fb6d5ef0 --- /dev/null +++ b/Documentation/mm/memfd_preservation.rst @@ -0,0 +1,23 @@ +.. SPDX-License-Identifier: GPL-2.0-or-later + +========================== +Memfd Preservation via LUO +========================== + +.. kernel-doc:: mm/memfd_luo.c + :doc: Memfd Preservation via LUO + +Memfd Preservation ABI +====================== + +.. kernel-doc:: include/linux/kho/abi/memfd.h + :doc: DOC: memfd Live Update ABI + +.. kernel-doc:: include/linux/kho/abi/memfd.h + :internal: + +See Also +======== + +- :doc:`/core-api/liveupdate` +- :doc:`/core-api/kho/concepts` diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index b8c73be4fb11..8a61ac4c1bf1 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -61,6 +61,7 @@ Everything else :maxdepth: 1 ELF + liveupdate netlink/index sysfs-platform_profile vduse diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 7c527a01d1cf..7232b3544cec 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -385,6 +385,8 @@ Code Seq# Include File Comments 0xB8 01-02 uapi/misc/mrvl_cn10k_dpi.h Marvell CN10K DPI driver 0xB8 all uapi/linux/mshv.h Microsoft Hyper-V /dev/mshv driver +0xBA 00-0F uapi/linux/liveupdate.h Pasha Tatashin + 0xC0 00-0F linux/usb/iowarrior.h 0xCA 00-0F uapi/misc/cxl.h Dead since 6.15 0xCA 10-2F uapi/misc/ocxl.h diff --git a/Documentation/userspace-api/liveupdate.rst b/Documentation/userspace-api/liveupdate.rst new file mode 100644 index 000000000000..41c0473e4f16 --- /dev/null +++ b/Documentation/userspace-api/liveupdate.rst @@ -0,0 +1,20 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================ +Live Update uAPI +================ +:Author: Pasha Tatashin + +ioctl interface +=============== +.. kernel-doc:: kernel/liveupdate/luo_core.c + :doc: LUO ioctl Interface + +ioctl uAPI +=========== +.. kernel-doc:: include/uapi/linux/liveupdate.h + +See Also +======== + +- :doc:`Live Update Orchestrator ` diff --git a/MAINTAINERS b/MAINTAINERS index 78b32a60849a..9a3657a40000 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11659,7 +11659,7 @@ T: git git://linuxtv.org/media.git F: drivers/media/i2c/hi556.c HYNIX HI846 SENSOR DRIVER -M: Martin Kepplinger +M: Martin Kepplinger-Novakovic L: linux-media@vger.kernel.org S: Maintained F: drivers/media/i2c/hi846.c @@ -11744,6 +11744,7 @@ HUNG TASK DETECTOR M: Andrew Morton R: Lance Yang R: Masami Hiramatsu +R: Petr Mladek L: linux-kernel@vger.kernel.org S: Maintained F: include/linux/hung_task.h @@ -13891,14 +13892,15 @@ F: kernel/kexec* KEXEC HANDOVER (KHO) M: Alexander Graf M: Mike Rapoport -M: Changyuan Lyu +M: Pasha Tatashin +R: Pratyush Yadav L: kexec@lists.infradead.org L: linux-mm@kvack.org S: Maintained F: Documentation/admin-guide/mm/kho.rst F: Documentation/core-api/kho/* F: include/linux/kexec_handover.h -F: kernel/kexec_handover.c +F: kernel/liveupdate/kexec_handover* F: lib/test_kho.c F: tools/testing/selftests/kho/ @@ -14567,6 +14569,22 @@ F: samples/livepatch/ F: scripts/livepatch/ F: tools/testing/selftests/livepatch/ +LIVE UPDATE +M: Pasha Tatashin +M: Mike Rapoport +R: Pratyush Yadav +L: linux-kernel@vger.kernel.org +S: Maintained +F: Documentation/core-api/liveupdate.rst +F: Documentation/mm/memfd_preservation.rst +F: Documentation/userspace-api/liveupdate.rst +F: include/linux/liveupdate.h +F: include/linux/liveupdate/ +F: include/uapi/linux/liveupdate.h +F: kernel/liveupdate/ +F: mm/memfd_luo.c +F: tools/testing/selftests/liveupdate/ + LLC (802.2) L: netdev@vger.kernel.org S: Odd fixes @@ -15668,7 +15686,7 @@ F: include/media/imx.h MEDIA DRIVERS FOR FREESCALE IMX7/8 M: Rui Miguel Silva M: Laurent Pinchart -M: Martin Kepplinger +M: Martin Kepplinger-Novakovic R: Purism Kernel Team R: Frank Li L: imx@lists.linux.dev @@ -18420,10 +18438,11 @@ F: net/sunrpc/ NILFS2 FILESYSTEM M: Ryusuke Konishi +M: Viacheslav Dubeyko L: linux-nilfs@vger.kernel.org -S: Supported +S: Maintained W: https://nilfs.sourceforge.io/ -T: git https://github.com/konis/nilfs2.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/vdubeyko/nilfs2.git F: Documentation/filesystems/nilfs2.rst F: fs/nilfs2/ F: include/trace/events/nilfs2.h @@ -25103,7 +25122,6 @@ F: drivers/regulator/sy8106a-regulator.c SYNC FILE FRAMEWORK M: Sumit Semwal -R: Gustavo Padovan L: linux-media@vger.kernel.org L: dri-devel@lists.freedesktop.org S: Maintained @@ -26308,7 +26326,7 @@ M: Jarkko Sakkinen R: Jason Gunthorpe L: linux-integrity@vger.kernel.org S: Maintained -W: https://codeberg.org/jarkko/linux-tpmdd-test +W: https://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd-test.git/about/ Q: https://patchwork.kernel.org/project/linux-integrity/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git F: Documentation/devicetree/bindings/tpm/ diff --git a/arch/Kconfig b/arch/Kconfig index 61130b88964b..31220f512b16 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -232,17 +232,14 @@ config HAVE_EFFICIENT_UNALIGNED_ACCESS config ARCH_USE_BUILTIN_BSWAP bool help - Modern versions of GCC (since 4.4) have builtin functions - for handling byte-swapping. Using these, instead of the old - inline assembler that the architecture code provides in the - __arch_bswapXX() macros, allows the compiler to see what's - happening and offers more opportunity for optimisation. In - particular, the compiler will be able to combine the byteswap - with a nearby load or store and use load-and-swap or - store-and-swap instructions if the architecture has them. It - should almost *never* result in code which is worse than the - hand-coded assembler in . But just in case it - does, the use of the builtins is optional. + GCC and Clang have builtin functions for handling byte-swapping. + Using these allows the compiler to see what's happening and + offers more opportunity for optimisation. In particular, the + compiler will be able to combine the byteswap with a nearby load + or store and use load-and-swap or store-and-swap instructions if + the architecture has them. It should almost *never* result in code + which is worse than the hand-coded assembler in . + But just in case it does, the use of the builtins is optional. Any architecture with load-and-swap or store-and-swap instructions should set this. And it shouldn't hurt to set it diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 4fb985b76e97..ff61891abe53 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1161,8 +1161,6 @@ config AEABI disambiguate both ABIs and allow for backward compatibility support (selected with CONFIG_OABI_COMPAT). - To use this you need GCC version 4.0.0 or later. - config OABI_COMPAT bool "Allow old ABI binaries to run with this kernel (EXPERIMENTAL)" depends on AEABI && !THUMB2_KERNEL diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 61cee1e7ebea..c3b0d5f06889 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -308,7 +308,7 @@ CONFIG_PANIC_ON_OOPS=y CONFIG_PANIC_TIMEOUT=-1 CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y -CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=1 CONFIG_WQ_WATCHDOG=y # CONFIG_SCHED_DEBUG is not set CONFIG_FUNCTION_TRACER=y diff --git a/arch/powerpc/include/asm/crash_reserve.h b/arch/powerpc/include/asm/crash_reserve.h index 6467ce29b1fa..d1b570ddbf98 100644 --- a/arch/powerpc/include/asm/crash_reserve.h +++ b/arch/powerpc/include/asm/crash_reserve.h @@ -5,4 +5,12 @@ /* crash kernel regions are Page size agliged */ #define CRASH_ALIGN PAGE_SIZE +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +static inline bool arch_add_crash_res_to_iomem(void) +{ + return false; +} +#define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem +#endif + #endif /* _ASM_POWERPC_CRASH_RESERVE_H */ diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h index 9931e4c7d73f..30fd06ede751 100644 --- a/arch/x86/include/asm/div64.h +++ b/arch/x86/include/asm/div64.h @@ -60,6 +60,12 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) } #define div_u64_rem div_u64_rem +/* + * gcc tends to zero extend 32bit values and do full 64bit maths. + * Define asm functions that avoid this. + * (clang generates better code for the C versions.) + */ +#ifndef __clang__ static inline u64 mul_u32_u32(u32 a, u32 b) { u32 high, low; @@ -71,6 +77,19 @@ static inline u64 mul_u32_u32(u32 a, u32 b) } #define mul_u32_u32 mul_u32_u32 +static inline u64 add_u64_u32(u64 a, u32 b) +{ + u32 high = a >> 32, low = a; + + asm ("addl %[b], %[low]; adcl $0, %[high]" + : [low] "+r" (low), [high] "+r" (high) + : [b] "rm" (b) ); + + return low | (u64)high << 32; +} +#define add_u64_u32 add_u64_u32 +#endif + /* * __div64_32() is never called on x86, so prevent the * generic definition from getting built. @@ -84,21 +103,25 @@ static inline u64 mul_u32_u32(u32 a, u32 b) * Will generate an #DE when the result doesn't fit u64, could fix with an * __ex_table[] entry when it becomes an issue. */ -static inline u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div) +static inline u64 mul_u64_add_u64_div_u64(u64 rax, u64 mul, u64 add, u64 div) { - u64 q; + u64 rdx; - asm ("mulq %2; divq %3" : "=a" (q) - : "a" (a), "rm" (mul), "rm" (div) - : "rdx"); + asm ("mulq %[mul]" : "+a" (rax), "=d" (rdx) : [mul] "rm" (mul)); - return q; + if (!statically_true(!add)) + asm ("addq %[add], %[lo]; adcq $0, %[hi]" : + [lo] "+r" (rax), [hi] "+r" (rdx) : [add] "irm" (add)); + + asm ("divq %[div]" : "+a" (rax), "+d" (rdx) : [div] "rm" (div)); + + return rax; } -#define mul_u64_u64_div_u64 mul_u64_u64_div_u64 +#define mul_u64_add_u64_div_u64 mul_u64_add_u64_div_u64 static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div) { - return mul_u64_u64_div_u64(a, mul, div); + return mul_u64_add_u64_div_u64(a, mul, 0, div); } #define mul_u64_u32_div mul_u64_u32_div diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6297416647ed..34440021e8cf 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -1729,6 +1730,9 @@ noinstr void do_machine_check(struct pt_regs *regs) } out: + /* Given it didn't panic, mark it as recoverable */ + hwerr_log_error_type(HWERR_RECOV_OTHERS); + instrumentation_end(); clear: diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 626908491d8f..0dc767392a6c 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -864,6 +865,40 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) } EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL"); +static void ghes_log_hwerr(int sev, guid_t *sec_type) +{ + if (sev != CPER_SEV_RECOVERABLE) + return; + + if (guid_equal(sec_type, &CPER_SEC_PROC_ARM) || + guid_equal(sec_type, &CPER_SEC_PROC_GENERIC) || + guid_equal(sec_type, &CPER_SEC_PROC_IA)) { + hwerr_log_error_type(HWERR_RECOV_CPU); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR) || + guid_equal(sec_type, &CPER_SEC_CXL_GEN_MEDIA_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_DRAM_GUID) || + guid_equal(sec_type, &CPER_SEC_CXL_MEM_MODULE_GUID)) { + hwerr_log_error_type(HWERR_RECOV_CXL); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_PCIE) || + guid_equal(sec_type, &CPER_SEC_PCI_X_BUS)) { + hwerr_log_error_type(HWERR_RECOV_PCI); + return; + } + + if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { + hwerr_log_error_type(HWERR_RECOV_MEMORY); + return; + } + + hwerr_log_error_type(HWERR_RECOV_OTHERS); +} + static void ghes_do_proc(struct ghes *ghes, const struct acpi_hest_generic_status *estatus) { @@ -885,6 +920,7 @@ static void ghes_do_proc(struct ghes *ghes, if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) fru_text = gdata->fru_text; + ghes_log_hwerr(sev, sec_type); if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) { struct cper_sec_mem_err *mem_err = acpi_hest_get_payload(gdata); diff --git a/drivers/nvme/common/auth.c b/drivers/nvme/common/auth.c index 1f51fbebd9fa..e07e7d4bf8b6 100644 --- a/drivers/nvme/common/auth.c +++ b/drivers/nvme/common/auth.c @@ -178,7 +178,7 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret, if (!key) return ERR_PTR(-ENOMEM); - key_len = base64_decode(secret, allocated_len, key->key); + key_len = base64_decode(secret, allocated_len, key->key, true, BASE64_STD); if (key_len < 0) { pr_debug("base64 key decoding error %d\n", key_len); @@ -663,7 +663,7 @@ int nvme_auth_generate_digest(u8 hmac_id, u8 *psk, size_t psk_len, if (ret) goto out_free_digest; - ret = base64_encode(digest, digest_len, enc); + ret = base64_encode(digest, digest_len, enc, true, BASE64_STD); if (ret < hmac_len) { ret = -ENOKEY; goto out_free_digest; diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 0b5ed4722ac3..e0bcaa896803 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -765,6 +766,7 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev, break; case AER_NONFATAL: aer_info->dev_total_nonfatal_errs++; + hwerr_log_error_type(HWERR_RECOV_PCI); counter = &aer_info->dev_nonfatal_errs[0]; max = AER_MAX_TYPEOF_UNCOR_ERRS; break; diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index 928746b92512..0ea4db650f85 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -15,59 +15,6 @@ #include "mds_client.h" #include "crypto.h" -/* - * The base64url encoding used by fscrypt includes the '_' character, which may - * cause problems in snapshot names (which can not start with '_'). Thus, we - * used the base64 encoding defined for IMAP mailbox names (RFC 3501) instead, - * which replaces '-' and '_' by '+' and ','. - */ -static const char base64_table[65] = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,"; - -int ceph_base64_encode(const u8 *src, int srclen, char *dst) -{ - u32 ac = 0; - int bits = 0; - int i; - char *cp = dst; - - for (i = 0; i < srclen; i++) { - ac = (ac << 8) | src[i]; - bits += 8; - do { - bits -= 6; - *cp++ = base64_table[(ac >> bits) & 0x3f]; - } while (bits >= 6); - } - if (bits) - *cp++ = base64_table[(ac << (6 - bits)) & 0x3f]; - return cp - dst; -} - -int ceph_base64_decode(const char *src, int srclen, u8 *dst) -{ - u32 ac = 0; - int bits = 0; - int i; - u8 *bp = dst; - - for (i = 0; i < srclen; i++) { - const char *p = strchr(base64_table, src[i]); - - if (p == NULL || src[i] == 0) - return -1; - ac = (ac << 6) | (p - base64_table); - bits += 6; - if (bits >= 8) { - bits -= 8; - *bp++ = (u8)(ac >> bits); - } - } - if (ac & ((1 << bits) - 1)) - return -1; - return bp - dst; -} - static int ceph_crypt_get_context(struct inode *inode, void *ctx, size_t len) { struct ceph_inode_info *ci = ceph_inode(inode); @@ -318,7 +265,7 @@ int ceph_encode_encrypted_dname(struct inode *parent, char *buf, int elen) } /* base64 encode the encrypted name */ - elen = ceph_base64_encode(cryptbuf, len, p); + elen = base64_encode(cryptbuf, len, p, false, BASE64_IMAP); doutc(cl, "base64-encoded ciphertext name = %.*s\n", elen, p); /* To understand the 240 limit, see CEPH_NOHASH_NAME_MAX comments */ @@ -412,7 +359,8 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, tname = &_tname; } - declen = ceph_base64_decode(name, name_len, tname->name); + declen = base64_decode(name, name_len, + tname->name, false, BASE64_IMAP); if (declen <= 0) { ret = -EIO; goto out; @@ -426,7 +374,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, ret = fscrypt_fname_disk_to_usr(dir, 0, 0, &iname, oname); if (!ret && (dir != fname->dir)) { - char tmp_buf[CEPH_BASE64_CHARS(NAME_MAX)]; + char tmp_buf[BASE64_CHARS(NAME_MAX)]; name_len = snprintf(tmp_buf, sizeof(tmp_buf), "_%.*s_%ld", oname->len, oname->name, dir->i_ino); diff --git a/fs/ceph/crypto.h b/fs/ceph/crypto.h index 23612b2e9837..b748e2060bc9 100644 --- a/fs/ceph/crypto.h +++ b/fs/ceph/crypto.h @@ -8,6 +8,7 @@ #include #include +#include #define CEPH_FSCRYPT_BLOCK_SHIFT 12 #define CEPH_FSCRYPT_BLOCK_SIZE (_AC(1, UL) << CEPH_FSCRYPT_BLOCK_SHIFT) @@ -89,11 +90,6 @@ static inline u32 ceph_fscrypt_auth_len(struct ceph_fscrypt_auth *fa) */ #define CEPH_NOHASH_NAME_MAX (180 - SHA256_DIGEST_SIZE) -#define CEPH_BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) - -int ceph_base64_encode(const u8 *src, int srclen, char *dst); -int ceph_base64_decode(const char *src, int srclen, u8 *dst); - void ceph_fscrypt_set_ops(struct super_block *sb); void ceph_fscrypt_free_dummy_policy(struct ceph_fs_client *fsc); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index bf50c6e7a029..86d7aa594ea9 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -998,13 +998,14 @@ static int prep_encrypted_symlink_target(struct ceph_mds_request *req, if (err) goto out; - req->r_path2 = kmalloc(CEPH_BASE64_CHARS(osd_link.len) + 1, GFP_KERNEL); + req->r_path2 = kmalloc(BASE64_CHARS(osd_link.len) + 1, GFP_KERNEL); if (!req->r_path2) { err = -ENOMEM; goto out; } - len = ceph_base64_encode(osd_link.name, osd_link.len, req->r_path2); + len = base64_encode(osd_link.name, osd_link.len, + req->r_path2, false, BASE64_IMAP); req->r_path2[len] = '\0'; out: fscrypt_fname_free_buffer(&osd_link); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index a596cb53f1ac..2966f88310e3 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -947,7 +947,7 @@ static int decode_encrypted_symlink(struct ceph_mds_client *mdsc, if (!sym) return -ENOMEM; - declen = ceph_base64_decode(encsym, enclen, sym); + declen = base64_decode(encsym, enclen, sym, false, BASE64_IMAP); if (declen < 0) { pr_err_client(cl, "can't decode symlink (%d). Content: %.*s\n", diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 8e4c213d418b..a9a4432d12ba 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "fscrypt_private.h" @@ -71,7 +72,7 @@ struct fscrypt_nokey_name { /* Encoded size of max-size no-key name */ #define FSCRYPT_NOKEY_NAME_MAX_ENCODED \ - FSCRYPT_BASE64URL_CHARS(FSCRYPT_NOKEY_NAME_MAX) + BASE64_CHARS(FSCRYPT_NOKEY_NAME_MAX) static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) { @@ -162,84 +163,6 @@ static int fname_decrypt(const struct inode *inode, return 0; } -static const char base64url_table[65] = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_"; - -#define FSCRYPT_BASE64URL_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) - -/** - * fscrypt_base64url_encode() - base64url-encode some binary data - * @src: the binary data to encode - * @srclen: the length of @src in bytes - * @dst: (output) the base64url-encoded string. Not NUL-terminated. - * - * Encodes data using base64url encoding, i.e. the "Base 64 Encoding with URL - * and Filename Safe Alphabet" specified by RFC 4648. '='-padding isn't used, - * as it's unneeded and not required by the RFC. base64url is used instead of - * base64 to avoid the '/' character, which isn't allowed in filenames. - * - * Return: the length of the resulting base64url-encoded string in bytes. - * This will be equal to FSCRYPT_BASE64URL_CHARS(srclen). - */ -static int fscrypt_base64url_encode(const u8 *src, int srclen, char *dst) -{ - u32 ac = 0; - int bits = 0; - int i; - char *cp = dst; - - for (i = 0; i < srclen; i++) { - ac = (ac << 8) | src[i]; - bits += 8; - do { - bits -= 6; - *cp++ = base64url_table[(ac >> bits) & 0x3f]; - } while (bits >= 6); - } - if (bits) - *cp++ = base64url_table[(ac << (6 - bits)) & 0x3f]; - return cp - dst; -} - -/** - * fscrypt_base64url_decode() - base64url-decode a string - * @src: the string to decode. Doesn't need to be NUL-terminated. - * @srclen: the length of @src in bytes - * @dst: (output) the decoded binary data - * - * Decodes a string using base64url encoding, i.e. the "Base 64 Encoding with - * URL and Filename Safe Alphabet" specified by RFC 4648. '='-padding isn't - * accepted, nor are non-encoding characters such as whitespace. - * - * This implementation hasn't been optimized for performance. - * - * Return: the length of the resulting decoded binary data in bytes, - * or -1 if the string isn't a valid base64url string. - */ -static int fscrypt_base64url_decode(const char *src, int srclen, u8 *dst) -{ - u32 ac = 0; - int bits = 0; - int i; - u8 *bp = dst; - - for (i = 0; i < srclen; i++) { - const char *p = strchr(base64url_table, src[i]); - - if (p == NULL || src[i] == 0) - return -1; - ac = (ac << 6) | (p - base64url_table); - bits += 6; - if (bits >= 8) { - bits -= 8; - *bp++ = (u8)(ac >> bits); - } - } - if (ac & ((1 << bits) - 1)) - return -1; - return bp - dst; -} - bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, u32 orig_len, u32 max_len, u32 *encrypted_len_ret) @@ -387,8 +310,8 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode, nokey_name.sha256); size = FSCRYPT_NOKEY_NAME_MAX; } - oname->len = fscrypt_base64url_encode((const u8 *)&nokey_name, size, - oname->name); + oname->len = base64_encode((const u8 *)&nokey_name, size, + oname->name, false, BASE64_URLSAFE); return 0; } EXPORT_SYMBOL(fscrypt_fname_disk_to_usr); @@ -467,8 +390,8 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, if (fname->crypto_buf.name == NULL) return -ENOMEM; - ret = fscrypt_base64url_decode(iname->name, iname->len, - fname->crypto_buf.name); + ret = base64_decode(iname->name, iname->len, + fname->crypto_buf.name, false, BASE64_URLSAFE); if (ret < (int)offsetof(struct fscrypt_nokey_name, bytes[1]) || (ret > offsetof(struct fscrypt_nokey_name, sha256) && ret != FSCRYPT_NOKEY_NAME_MAX)) { diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 3288c3b4be9e..e17b8da66491 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -49,7 +49,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs, void *, size_t, size_t)) { void *buf; - void __user *base = (void __user *)(unsigned long)argv->v_base; + void __user *base = u64_to_user_ptr(argv->v_base); size_t maxmembs, total, n; ssize_t nr; int ret, i; @@ -836,7 +836,6 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, sizeof(struct nilfs_bdesc), sizeof(__u64), }; - void __user *base; void *kbufs[5]; struct the_nilfs *nilfs; size_t len, nsegs; @@ -863,7 +862,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, * use kmalloc() for its buffer because the memory used for the * segment numbers is small enough. */ - kbufs[4] = memdup_array_user((void __user *)(unsigned long)argv[4].v_base, + kbufs[4] = memdup_array_user(u64_to_user_ptr(argv[4].v_base), nsegs, sizeof(__u64)); if (IS_ERR(kbufs[4])) { ret = PTR_ERR(kbufs[4]); @@ -883,20 +882,14 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, goto out_free; len = argv[n].v_size * argv[n].v_nmembs; - base = (void __user *)(unsigned long)argv[n].v_base; if (len == 0) { kbufs[n] = NULL; continue; } - kbufs[n] = vmalloc(len); - if (!kbufs[n]) { - ret = -ENOMEM; - goto out_free; - } - if (copy_from_user(kbufs[n], base, len)) { - ret = -EFAULT; - vfree(kbufs[n]); + kbufs[n] = vmemdup_user(u64_to_user_ptr(argv[n].v_base), len); + if (IS_ERR(kbufs[n])) { + ret = PTR_ERR(kbufs[n]); goto out_free; } } @@ -928,7 +921,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, out_free: while (--n >= 0) - vfree(kbufs[n]); + kvfree(kbufs[n]); kfree(kbufs[4]); out: mnt_drop_write_file(filp); @@ -1181,7 +1174,6 @@ static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, struct nilfs_transaction_info ti; struct nilfs_argv argv; size_t len; - void __user *base; void *kbuf; int ret; @@ -1212,18 +1204,12 @@ static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, goto out; } - base = (void __user *)(unsigned long)argv.v_base; - kbuf = vmalloc(len); - if (!kbuf) { - ret = -ENOMEM; + kbuf = vmemdup_user(u64_to_user_ptr(argv.v_base), len); + if (IS_ERR(kbuf)) { + ret = PTR_ERR(kbuf); goto out; } - if (copy_from_user(kbuf, base, len)) { - ret = -EFAULT; - goto out_free; - } - nilfs_transaction_begin(inode->i_sb, &ti, 0); ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size, argv.v_nmembs); @@ -1232,8 +1218,7 @@ static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp, else nilfs_transaction_commit(inode->i_sb); /* never fails */ -out_free: - vfree(kbuf); + kvfree(kbuf); out: mnt_drop_write_file(filp); return ret; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 8c9c4825f984..2785ff245e79 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -302,8 +302,21 @@ static int ocfs2_check_dir_entry(struct inode *dir, unsigned long offset) { const char *error_msg = NULL; - const int rlen = le16_to_cpu(de->rec_len); - const unsigned long next_offset = ((char *) de - buf) + rlen; + unsigned long next_offset; + int rlen; + + if (offset > size - OCFS2_DIR_REC_LEN(1)) { + /* Dirent is (maybe partially) beyond the buffer + * boundaries so touching 'de' members is unsafe. + */ + mlog(ML_ERROR, "directory entry (#%llu: offset=%lu) " + "too close to end or out-of-bounds", + (unsigned long long)OCFS2_I(dir)->ip_blkno, offset); + return 0; + } + + rlen = le16_to_cpu(de->rec_len); + next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < OCFS2_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; @@ -778,6 +791,14 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode, struct ocfs2_extent_block *eb; struct ocfs2_extent_rec *rec = NULL; + if (le16_to_cpu(el->l_count) != + ocfs2_extent_recs_per_dx_root(inode->i_sb)) { + ret = ocfs2_error(inode->i_sb, + "Inode %lu has invalid extent list length %u\n", + inode->i_ino, le16_to_cpu(el->l_count)); + goto out; + } + if (el->l_tree_depth) { ret = ocfs2_find_leaf(INODE_CACHE(inode), el, major_hash, &eb_bh); @@ -3423,6 +3444,14 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, offset += le16_to_cpu(de->rec_len); } + if (!last_de) { + ret = ocfs2_error(sb, "Directory entry (#%llu: size=%lld) " + "is unexpectedly short", + (unsigned long long)OCFS2_I(dir)->ip_blkno, + i_size_read(dir)); + goto out; + } + /* * We're going to require expansion of the directory - figure * out how many blocks we'll need so that a place for the @@ -4104,10 +4133,15 @@ static int ocfs2_expand_inline_dx_root(struct inode *dir, } dx_root->dr_flags &= ~OCFS2_DX_FLAG_INLINE; - memset(&dx_root->dr_list, 0, osb->sb->s_blocksize - - offsetof(struct ocfs2_dx_root_block, dr_list)); + + dx_root->dr_list.l_tree_depth = 0; dx_root->dr_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb)); + dx_root->dr_list.l_next_free_rec = 0; + memset(&dx_root->dr_list.l_recs, 0, + osb->sb->s_blocksize - + (offsetof(struct ocfs2_dx_root_block, dr_list) + + offsetof(struct ocfs2_extent_list, l_recs))); /* This should never fail considering we start with an empty * dx_root. */ diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 78f81950c9ee..8340525e5589 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -201,13 +201,15 @@ bail: static int ocfs2_dinode_has_extents(struct ocfs2_dinode *di) { /* inodes flagged with other stuff in id2 */ - if (di->i_flags & (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL | - OCFS2_CHAIN_FL | OCFS2_DEALLOC_FL)) + if (le32_to_cpu(di->i_flags) & + (OCFS2_SUPER_BLOCK_FL | OCFS2_LOCAL_ALLOC_FL | OCFS2_CHAIN_FL | + OCFS2_DEALLOC_FL)) return 0; /* i_flags doesn't indicate when id2 is a fast symlink */ - if (S_ISLNK(di->i_mode) && di->i_size && di->i_clusters == 0) + if (S_ISLNK(le16_to_cpu(di->i_mode)) && le64_to_cpu(di->i_size) && + !le32_to_cpu(di->i_clusters)) return 0; - if (di->i_dyn_features & OCFS2_INLINE_DATA_FL) + if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) return 0; return 1; @@ -1460,7 +1462,7 @@ int ocfs2_validate_inode_block(struct super_block *sb, goto bail; } - if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) { + if (!(le32_to_cpu(di->i_flags) & OCFS2_VALID_FL)) { rc = ocfs2_error(sb, "Invalid dinode #%llu: OCFS2_VALID_FL not set\n", (unsigned long long)bh->b_blocknr); @@ -1484,6 +1486,41 @@ int ocfs2_validate_inode_block(struct super_block *sb, goto bail; } + if ((le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) && + le32_to_cpu(di->i_clusters)) { + rc = ocfs2_error(sb, "Invalid dinode %llu: %u clusters\n", + (unsigned long long)bh->b_blocknr, + le32_to_cpu(di->i_clusters)); + goto bail; + } + + if (le32_to_cpu(di->i_flags) & OCFS2_CHAIN_FL) { + struct ocfs2_chain_list *cl = &di->id2.i_chain; + u16 bpc = 1 << (OCFS2_SB(sb)->s_clustersize_bits - + sb->s_blocksize_bits); + + if (le16_to_cpu(cl->cl_count) != ocfs2_chain_recs_per_inode(sb)) { + rc = ocfs2_error(sb, "Invalid dinode %llu: chain list count %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(cl->cl_count)); + goto bail; + } + if (le16_to_cpu(cl->cl_next_free_rec) > le16_to_cpu(cl->cl_count)) { + rc = ocfs2_error(sb, "Invalid dinode %llu: chain list index %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(cl->cl_next_free_rec)); + goto bail; + } + if (OCFS2_SB(sb)->bitmap_blkno && + OCFS2_SB(sb)->bitmap_blkno != le64_to_cpu(di->i_blkno) && + le16_to_cpu(cl->cl_bpc) != bpc) { + rc = ocfs2_error(sb, "Invalid dinode %llu: bits per cluster %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(cl->cl_bpc)); + goto bail; + } + } + rc = 0; bail: @@ -1671,6 +1708,8 @@ int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh, rc = ocfs2_read_blocks(INODE_CACHE(inode), OCFS2_I(inode)->ip_blkno, 1, &tmp, flags, ocfs2_validate_inode_block); + if (rc < 0) + make_bad_inode(inode); /* If ocfs2_read_blocks() got us a new bh, pass it up. */ if (!rc && !*bh) *bh = tmp; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 10923bf7c8b8..ce978a2497d9 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -98,7 +98,13 @@ static int __ocfs2_move_extent(handle_t *handle, rec = &el->l_recs[index]; - BUG_ON(ext_flags != rec->e_flags); + if (ext_flags != rec->e_flags) { + ret = ocfs2_error(inode->i_sb, + "Inode %llu has corrupted extent %d with flags 0x%x at cpos %u\n", + (unsigned long long)ino, index, rec->e_flags, cpos); + goto out; + } + /* * after moving/defraging to new location, the extent is not going * to be refcounted anymore. @@ -1036,6 +1042,12 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) if (range.me_threshold > i_size_read(inode)) range.me_threshold = i_size_read(inode); + if (range.me_flags & ~(OCFS2_MOVE_EXT_FL_AUTO_DEFRAG | + OCFS2_MOVE_EXT_FL_PART_DEFRAG)) { + status = -EINVAL; + goto out_free; + } + if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) { context->auto_defrag = 1; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index ae0e44e5f2ad..f7763da5c4a2 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -468,7 +468,8 @@ struct ocfs2_extent_list { __le16 l_reserved1; __le64 l_reserved2; /* Pad to sizeof(ocfs2_extent_rec) */ -/*10*/ struct ocfs2_extent_rec l_recs[]; /* Extent records */ + /* Extent records */ +/*10*/ struct ocfs2_extent_rec l_recs[] __counted_by_le(l_count); }; /* @@ -482,7 +483,8 @@ struct ocfs2_chain_list { __le16 cl_count; /* Total chains in this list */ __le16 cl_next_free_rec; /* Next unused chain slot */ __le64 cl_reserved1; -/*10*/ struct ocfs2_chain_rec cl_recs[]; /* Chain records */ + /* Chain records */ +/*10*/ struct ocfs2_chain_rec cl_recs[] __counted_by_le(cl_count); }; /* @@ -494,7 +496,8 @@ struct ocfs2_truncate_log { /*00*/ __le16 tl_count; /* Total records in this log */ __le16 tl_used; /* Number of records in use */ __le32 tl_reserved1; -/*08*/ struct ocfs2_truncate_rec tl_recs[]; /* Truncate records */ + /* Truncate records */ +/*08*/ struct ocfs2_truncate_rec tl_recs[] __counted_by_le(tl_count); }; /* @@ -796,9 +799,10 @@ struct ocfs2_dx_entry_list { * possible in de_entries */ __le16 de_num_used; /* Current number of * de_entries entries */ - struct ocfs2_dx_entry de_entries[]; /* Indexed dir entries - * in a packed array of - * length de_num_used */ + /* Indexed dir entries in a packed + * array of length de_num_used. + */ + struct ocfs2_dx_entry de_entries[] __counted_by_le(de_count); }; #define OCFS2_DX_FLAG_INLINE 0x01 @@ -934,7 +938,8 @@ struct ocfs2_refcount_list { __le16 rl_used; /* Current number of used records */ __le32 rl_reserved2; __le64 rl_reserved1; /* Pad to sizeof(ocfs2_refcount_record) */ -/*10*/ struct ocfs2_refcount_rec rl_recs[]; /* Refcount records */ + /* Refcount records */ +/*10*/ struct ocfs2_refcount_rec rl_recs[] __counted_by_le(rl_count); }; @@ -1020,7 +1025,8 @@ struct ocfs2_xattr_header { buckets. A block uses xb_check and sets this field to zero.) */ - struct ocfs2_xattr_entry xh_entries[]; /* xattr entry list. */ + /* xattr entry list. */ + struct ocfs2_xattr_entry xh_entries[] __counted_by_le(xh_count); }; /* diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 267b50e8e42e..c92e0ea85bca 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -621,7 +622,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode, /* Initialize ocfs2_refcount_block. */ rb = (struct ocfs2_refcount_block *)new_bh->b_data; memset(rb, 0, inode->i_sb->s_blocksize); - strcpy((void *)rb, OCFS2_REFCOUNT_BLOCK_SIGNATURE); + strscpy(rb->rf_signature, OCFS2_REFCOUNT_BLOCK_SIGNATURE); rb->rf_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); rb->rf_suballoc_loc = cpu_to_le64(suballoc_loc); rb->rf_suballoc_bit = cpu_to_le16(suballoc_bit_start); @@ -1562,7 +1563,7 @@ static int ocfs2_new_leaf_refcount_block(handle_t *handle, /* Initialize ocfs2_refcount_block. */ new_rb = (struct ocfs2_refcount_block *)new_bh->b_data; memset(new_rb, 0, sb->s_blocksize); - strcpy((void *)new_rb, OCFS2_REFCOUNT_BLOCK_SIGNATURE); + strscpy(new_rb->rf_signature, OCFS2_REFCOUNT_BLOCK_SIGNATURE); new_rb->rf_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); new_rb->rf_suballoc_loc = cpu_to_le64(suballoc_loc); new_rb->rf_suballoc_bit = cpu_to_le16(suballoc_bit_start); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index d70a20d29e3e..73c028f452ac 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -2908,7 +2908,7 @@ static int ocfs2_create_xattr_block(struct inode *inode, /* Initialize ocfs2_xattr_block */ xblk = (struct ocfs2_xattr_block *)new_bh->b_data; memset(xblk, 0, inode->i_sb->s_blocksize); - strcpy((void *)xblk, OCFS2_XATTR_BLOCK_SIGNATURE); + strscpy(xblk->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE); xblk->xb_suballoc_slot = cpu_to_le16(ctxt->meta_ac->ac_alloc_slot); xblk->xb_suballoc_loc = cpu_to_le64(suballoc_loc); xblk->xb_suballoc_bit = cpu_to_le16(suballoc_bit_start); diff --git a/fs/proc/page.c b/fs/proc/page.c index fc64f23e05e5..f9b2c2c906cd 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -20,7 +20,6 @@ #define KPMSIZE sizeof(u64) #define KPMMASK (KPMSIZE - 1) -#define KPMBITS (KPMSIZE * BITS_PER_BYTE) enum kpage_operation { KPAGE_FLAGS, diff --git a/include/linux/base64.h b/include/linux/base64.h index 660d4cb1ef31..a2c6c9222da3 100644 --- a/include/linux/base64.h +++ b/include/linux/base64.h @@ -8,9 +8,15 @@ #include +enum base64_variant { + BASE64_STD, /* RFC 4648 (standard) */ + BASE64_URLSAFE, /* RFC 4648 (base64url) */ + BASE64_IMAP, /* RFC 3501 */ +}; + #define BASE64_CHARS(nbytes) DIV_ROUND_UP((nbytes) * 4, 3) -int base64_encode(const u8 *src, int len, char *dst); -int base64_decode(const char *src, int len, u8 *dst); +int base64_encode(const u8 *src, int len, char *dst, bool padding, enum base64_variant variant); +int base64_decode(const char *src, int len, u8 *dst, bool padding, enum base64_variant variant); #endif /* _LINUX_BASE64_H */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index ab181d87d71d..ff71bebe56f5 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -273,12 +273,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __ASSEMBLY__ */ -#ifdef CONFIG_64BIT -#define ARCH_SEL(a,b) a -#else -#define ARCH_SEL(a,b) b -#endif - /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h index 7b44b41d0a20..f0dc03d94ca2 100644 --- a/include/linux/crash_reserve.h +++ b/include/linux/crash_reserve.h @@ -32,6 +32,12 @@ int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, void __init reserve_crashkernel_cma(unsigned long long cma_size); #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#ifndef arch_add_crash_res_to_iomem +static inline bool arch_add_crash_res_to_iomem(void) +{ + return true; +} +#endif #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE #define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) #endif diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index ff44ec346162..05743900a116 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -38,11 +38,12 @@ struct _ddebug { #define _DPRINTK_FLAGS_INCL_LINENO (1<<3) #define _DPRINTK_FLAGS_INCL_TID (1<<4) #define _DPRINTK_FLAGS_INCL_SOURCENAME (1<<5) +#define _DPRINTK_FLAGS_INCL_STACK (1<<6) #define _DPRINTK_FLAGS_INCL_ANY \ (_DPRINTK_FLAGS_INCL_MODNAME | _DPRINTK_FLAGS_INCL_FUNCNAME |\ _DPRINTK_FLAGS_INCL_LINENO | _DPRINTK_FLAGS_INCL_TID |\ - _DPRINTK_FLAGS_INCL_SOURCENAME) + _DPRINTK_FLAGS_INCL_SOURCENAME | _DPRINTK_FLAGS_INCL_STACK) #if defined DEBUG #define _DPRINTK_FLAGS_DEFAULT _DPRINTK_FLAGS_PRINT @@ -160,6 +161,12 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, const struct ib_device *ibdev, const char *fmt, ...); +#define __dynamic_dump_stack(desc) \ +{ \ + if (desc.flags & _DPRINTK_FLAGS_INCL_STACK) \ + dump_stack(); \ +} + #define DEFINE_DYNAMIC_DEBUG_METADATA_CLS(name, cls, fmt) \ static struct _ddebug __aligned(8) \ __section("__dyndbg") name = { \ @@ -220,8 +227,10 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, */ #define __dynamic_func_call_cls(id, cls, fmt, func, ...) do { \ DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt); \ - if (DYNAMIC_DEBUG_BRANCH(id)) \ + if (DYNAMIC_DEBUG_BRANCH(id)) { \ func(&id, ##__VA_ARGS__); \ + __dynamic_dump_stack(id); \ + } \ } while (0) #define __dynamic_func_call(id, fmt, func, ...) \ __dynamic_func_call_cls(id, _DPRINTK_CLASS_DFLT, fmt, \ @@ -229,8 +238,10 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define __dynamic_func_call_cls_no_desc(id, cls, fmt, func, ...) do { \ DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt); \ - if (DYNAMIC_DEBUG_BRANCH(id)) \ + if (DYNAMIC_DEBUG_BRANCH(id)) { \ func(__VA_ARGS__); \ + __dynamic_dump_stack(id); \ + } \ } while (0) #define __dynamic_func_call_no_desc(id, fmt, func, ...) \ __dynamic_func_call_cls_no_desc(id, _DPRINTK_CLASS_DFLT, \ diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h index 25042c1d8d54..5f7b9de97e8d 100644 --- a/include/linux/kexec_handover.h +++ b/include/linux/kexec_handover.h @@ -2,22 +2,16 @@ #ifndef LINUX_KEXEC_HANDOVER_H #define LINUX_KEXEC_HANDOVER_H -#include +#include #include +#include struct kho_scratch { phys_addr_t addr; phys_addr_t size; }; -/* KHO Notifier index */ -enum kho_event { - KEXEC_KHO_FINALIZE = 0, - KEXEC_KHO_ABORT = 1, -}; - struct folio; -struct notifier_block; struct page; #define DECLARE_KHOSER_PTR(name, type) \ @@ -37,8 +31,6 @@ struct page; (typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \ }) -struct kho_serialization; - struct kho_vmalloc_chunk; struct kho_vmalloc { DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *); @@ -52,17 +44,21 @@ bool kho_is_enabled(void); bool is_kho_boot(void); int kho_preserve_folio(struct folio *folio); +void kho_unpreserve_folio(struct folio *folio); int kho_preserve_pages(struct page *page, unsigned int nr_pages); +void kho_unpreserve_pages(struct page *page, unsigned int nr_pages); int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation); +void kho_unpreserve_vmalloc(struct kho_vmalloc *preservation); +void *kho_alloc_preserve(size_t size); +void kho_unpreserve_free(void *mem); +void kho_restore_free(void *mem); struct folio *kho_restore_folio(phys_addr_t phys); struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages); void *kho_restore_vmalloc(const struct kho_vmalloc *preservation); -int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt); +int kho_add_subtree(const char *name, void *fdt); +void kho_remove_subtree(void *fdt); int kho_retrieve_subtree(const char *name, phys_addr_t *phys); -int register_kho_notifier(struct notifier_block *nb); -int unregister_kho_notifier(struct notifier_block *nb); - void kho_memory_init(void); void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, @@ -83,17 +79,31 @@ static inline int kho_preserve_folio(struct folio *folio) return -EOPNOTSUPP; } +static inline void kho_unpreserve_folio(struct folio *folio) { } + static inline int kho_preserve_pages(struct page *page, unsigned int nr_pages) { return -EOPNOTSUPP; } +static inline void kho_unpreserve_pages(struct page *page, unsigned int nr_pages) { } + static inline int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation) { return -EOPNOTSUPP; } +static inline void kho_unpreserve_vmalloc(struct kho_vmalloc *preservation) { } + +static inline void *kho_alloc_preserve(size_t size) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void kho_unpreserve_free(void *mem) { } +static inline void kho_restore_free(void *mem) { } + static inline struct folio *kho_restore_folio(phys_addr_t phys) { return NULL; @@ -110,30 +120,19 @@ static inline void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) return NULL; } -static inline int kho_add_subtree(struct kho_serialization *ser, - const char *name, void *fdt) +static inline int kho_add_subtree(const char *name, void *fdt) { return -EOPNOTSUPP; } +static inline void kho_remove_subtree(void *fdt) { } + static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys) { return -EOPNOTSUPP; } -static inline int register_kho_notifier(struct notifier_block *nb) -{ - return -EOPNOTSUPP; -} - -static inline int unregister_kho_notifier(struct notifier_block *nb) -{ - return -EOPNOTSUPP; -} - -static inline void kho_memory_init(void) -{ -} +static inline void kho_memory_init(void) { } static inline void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys, u64 scratch_len) diff --git a/include/linux/kho/abi/luo.h b/include/linux/kho/abi/luo.h new file mode 100644 index 000000000000..bb099c92e469 --- /dev/null +++ b/include/linux/kho/abi/luo.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +/** + * DOC: Live Update Orchestrator ABI + * + * This header defines the stable Application Binary Interface used by the + * Live Update Orchestrator to pass state from a pre-update kernel to a + * post-update kernel. The ABI is built upon the Kexec HandOver framework + * and uses a Flattened Device Tree to describe the preserved data. + * + * This interface is a contract. Any modification to the FDT structure, node + * properties, compatible strings, or the layout of the `__packed` serialization + * structures defined here constitutes a breaking change. Such changes require + * incrementing the version number in the relevant `_COMPATIBLE` string to + * prevent a new kernel from misinterpreting data from an old kernel. + * + * Changes are allowed provided the compatibility version is incremented; + * however, backward/forward compatibility is only guaranteed for kernels + * supporting the same ABI version. + * + * FDT Structure Overview: + * The entire LUO state is encapsulated within a single KHO entry named "LUO". + * This entry contains an FDT with the following layout: + * + * .. code-block:: none + * + * / { + * compatible = "luo-v1"; + * liveupdate-number = <...>; + * + * luo-session { + * compatible = "luo-session-v1"; + * luo-session-header = ; + * }; + * }; + * + * Main LUO Node (/): + * + * - compatible: "luo-v1" + * Identifies the overall LUO ABI version. + * - liveupdate-number: u64 + * A counter tracking the number of successful live updates performed. + * + * Session Node (luo-session): + * This node describes all preserved user-space sessions. + * + * - compatible: "luo-session-v1" + * Identifies the session ABI version. + * - luo-session-header: u64 + * The physical address of a `struct luo_session_header_ser`. This structure + * is the header for a contiguous block of memory containing an array of + * `struct luo_session_ser`, one for each preserved session. + * + * Serialization Structures: + * The FDT properties point to memory regions containing arrays of simple, + * `__packed` structures. These structures contain the actual preserved state. + * + * - struct luo_session_header_ser: + * Header for the session array. Contains the total page count of the + * preserved memory block and the number of `struct luo_session_ser` + * entries that follow. + * + * - struct luo_session_ser: + * Metadata for a single session, including its name and a physical pointer + * to another preserved memory block containing an array of + * `struct luo_file_ser` for all files in that session. + * + * - struct luo_file_ser: + * Metadata for a single preserved file. Contains the `compatible` string to + * find the correct handler in the new kernel, a user-provided `token` for + * identification, and an opaque `data` handle for the handler to use. + */ + +#ifndef _LINUX_KHO_ABI_LUO_H +#define _LINUX_KHO_ABI_LUO_H + +#include + +/* + * The LUO FDT hooks all LUO state for sessions, fds, etc. + * In the root it also carries "liveupdate-number" 64-bit property that + * corresponds to the number of live-updates performed on this machine. + */ +#define LUO_FDT_SIZE PAGE_SIZE +#define LUO_FDT_KHO_ENTRY_NAME "LUO" +#define LUO_FDT_COMPATIBLE "luo-v1" +#define LUO_FDT_LIVEUPDATE_NUM "liveupdate-number" + +#define LIVEUPDATE_HNDL_COMPAT_LENGTH 48 + +/** + * struct luo_file_ser - Represents the serialized preserves files. + * @compatible: File handler compatible string. + * @data: Private data + * @token: User provided token for this file + * + * If this structure is modified, LUO_SESSION_COMPATIBLE must be updated. + */ +struct luo_file_ser { + char compatible[LIVEUPDATE_HNDL_COMPAT_LENGTH]; + u64 data; + u64 token; +} __packed; + +/** + * struct luo_file_set_ser - Represents the serialized metadata for file set + * @files: The physical address of a contiguous memory block that holds + * the serialized state of files (array of luo_file_ser) in this file + * set. + * @count: The total number of files that were part of this session during + * serialization. Used for iteration and validation during + * restoration. + */ +struct luo_file_set_ser { + u64 files; + u64 count; +} __packed; + +/* + * LUO FDT session node + * LUO_FDT_SESSION_HEADER: is a u64 physical address of struct + * luo_session_header_ser + */ +#define LUO_FDT_SESSION_NODE_NAME "luo-session" +#define LUO_FDT_SESSION_COMPATIBLE "luo-session-v2" +#define LUO_FDT_SESSION_HEADER "luo-session-header" + +/** + * struct luo_session_header_ser - Header for the serialized session data block. + * @count: The number of `struct luo_session_ser` entries that immediately + * follow this header in the memory block. + * + * This structure is located at the beginning of a contiguous block of + * physical memory preserved across the kexec. It provides the necessary + * metadata to interpret the array of session entries that follow. + * + * If this structure is modified, `LUO_FDT_SESSION_COMPATIBLE` must be updated. + */ +struct luo_session_header_ser { + u64 count; +} __packed; + +/** + * struct luo_session_ser - Represents the serialized metadata for a LUO session. + * @name: The unique name of the session, provided by the userspace at + * the time of session creation. + * @file_set_ser: Serialized files belonging to this session, + * + * This structure is used to package session-specific metadata for transfer + * between kernels via Kexec Handover. An array of these structures (one per + * session) is created and passed to the new kernel, allowing it to reconstruct + * the session context. + * + * If this structure is modified, `LUO_FDT_SESSION_COMPATIBLE` must be updated. + */ +struct luo_session_ser { + char name[LIVEUPDATE_SESSION_NAME_LENGTH]; + struct luo_file_set_ser file_set_ser; +} __packed; + +#endif /* _LINUX_KHO_ABI_LUO_H */ diff --git a/include/linux/kho/abi/memfd.h b/include/linux/kho/abi/memfd.h new file mode 100644 index 000000000000..da7d063474a1 --- /dev/null +++ b/include/linux/kho/abi/memfd.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + * + * Copyright (C) 2025 Amazon.com Inc. or its affiliates. + * Pratyush Yadav + */ + +#ifndef _LINUX_KHO_ABI_MEMFD_H +#define _LINUX_KHO_ABI_MEMFD_H + +#include +#include + +/** + * DOC: memfd Live Update ABI + * + * This header defines the ABI for preserving the state of a memfd across a + * kexec reboot using the LUO. + * + * The state is serialized into a packed structure `struct memfd_luo_ser` + * which is handed over to the next kernel via the KHO mechanism. + * + * This interface is a contract. Any modification to the structure layout + * constitutes a breaking change. Such changes require incrementing the + * version number in the MEMFD_LUO_FH_COMPATIBLE string. + */ + +/** + * MEMFD_LUO_FOLIO_DIRTY - The folio is dirty. + * + * This flag indicates the folio contains data from user. A non-dirty folio is + * one that was allocated (say using fallocate(2)) but not written to. + */ +#define MEMFD_LUO_FOLIO_DIRTY BIT(0) + +/** + * MEMFD_LUO_FOLIO_UPTODATE - The folio is up-to-date. + * + * An up-to-date folio has been zeroed out. shmem zeroes out folios on first + * use. This flag tracks which folios need zeroing. + */ +#define MEMFD_LUO_FOLIO_UPTODATE BIT(1) + +/** + * struct memfd_luo_folio_ser - Serialized state of a single folio. + * @pfn: The page frame number of the folio. + * @flags: Flags to describe the state of the folio. + * @index: The page offset (pgoff_t) of the folio within the original file. + */ +struct memfd_luo_folio_ser { + u64 pfn:52; + u64 flags:12; + u64 index; +} __packed; + +/** + * struct memfd_luo_ser - Main serialization structure for a memfd. + * @pos: The file's current position (f_pos). + * @size: The total size of the file in bytes (i_size). + * @nr_folios: Number of folios in the folios array. + * @folios: KHO vmalloc descriptor pointing to the array of + * struct memfd_luo_folio_ser. + */ +struct memfd_luo_ser { + u64 pos; + u64 size; + u64 nr_folios; + struct kho_vmalloc folios; +} __packed; + +/* The compatibility string for memfd file handler */ +#define MEMFD_LUO_FH_COMPATIBLE "memfd-v1" + +#endif /* _LINUX_KHO_ABI_MEMFD_H */ diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h new file mode 100644 index 000000000000..a7f6ee5b6771 --- /dev/null +++ b/include/linux/liveupdate.h @@ -0,0 +1,138 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ +#ifndef _LINUX_LIVEUPDATE_H +#define _LINUX_LIVEUPDATE_H + +#include +#include +#include +#include +#include +#include + +struct liveupdate_file_handler; +struct file; + +/** + * struct liveupdate_file_op_args - Arguments for file operation callbacks. + * @handler: The file handler being called. + * @retrieved: The retrieve status for the 'can_finish / finish' + * operation. + * @file: The file object. For retrieve: [OUT] The callback sets + * this to the new file. For other ops: [IN] The caller sets + * this to the file being operated on. + * @serialized_data: The opaque u64 handle, preserve/prepare/freeze may update + * this field. + * @private_data: Private data for the file used to hold runtime state that + * is not preserved. Set by the handler's .preserve() + * callback, and must be freed in the handler's + * .unpreserve() callback. + * + * This structure bundles all parameters for the file operation callbacks. + * The 'data' and 'file' fields are used for both input and output. + */ +struct liveupdate_file_op_args { + struct liveupdate_file_handler *handler; + bool retrieved; + struct file *file; + u64 serialized_data; + void *private_data; +}; + +/** + * struct liveupdate_file_ops - Callbacks for live-updatable files. + * @can_preserve: Required. Lightweight check to see if this handler is + * compatible with the given file. + * @preserve: Required. Performs state-saving for the file. + * @unpreserve: Required. Cleans up any resources allocated by @preserve. + * @freeze: Optional. Final actions just before kernel transition. + * @unfreeze: Optional. Undo freeze operations. + * @retrieve: Required. Restores the file in the new kernel. + * @can_finish: Optional. Check if this FD can finish, i.e. all restoration + * pre-requirements for this FD are satisfied. Called prior to + * finish, in order to do successful finish calls for all + * resources in the session. + * @finish: Required. Final cleanup in the new kernel. + * @owner: Module reference + * + * All operations (except can_preserve) receive a pointer to a + * 'struct liveupdate_file_op_args' containing the necessary context. + */ +struct liveupdate_file_ops { + bool (*can_preserve)(struct liveupdate_file_handler *handler, + struct file *file); + int (*preserve)(struct liveupdate_file_op_args *args); + void (*unpreserve)(struct liveupdate_file_op_args *args); + int (*freeze)(struct liveupdate_file_op_args *args); + void (*unfreeze)(struct liveupdate_file_op_args *args); + int (*retrieve)(struct liveupdate_file_op_args *args); + bool (*can_finish)(struct liveupdate_file_op_args *args); + void (*finish)(struct liveupdate_file_op_args *args); + struct module *owner; +}; + +/** + * struct liveupdate_file_handler - Represents a handler for a live-updatable file type. + * @ops: Callback functions + * @compatible: The compatibility string (e.g., "memfd-v1", "vfiofd-v1") + * that uniquely identifies the file type this handler + * supports. This is matched against the compatible string + * associated with individual &struct file instances. + * + * Modules that want to support live update for specific file types should + * register an instance of this structure. LUO uses this registration to + * determine if a given file can be preserved and to find the appropriate + * operations to manage its state across the update. + */ +struct liveupdate_file_handler { + const struct liveupdate_file_ops *ops; + const char compatible[LIVEUPDATE_HNDL_COMPAT_LENGTH]; + + /* private: */ + + /* + * Used for linking this handler instance into a global list of + * registered file handlers. + */ + struct list_head __private list; +}; + +#ifdef CONFIG_LIVEUPDATE + +/* Return true if live update orchestrator is enabled */ +bool liveupdate_enabled(void); + +/* Called during kexec to tell LUO that entered into reboot */ +int liveupdate_reboot(void); + +int liveupdate_register_file_handler(struct liveupdate_file_handler *fh); +int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh); + +#else /* CONFIG_LIVEUPDATE */ + +static inline bool liveupdate_enabled(void) +{ + return false; +} + +static inline int liveupdate_reboot(void) +{ + return 0; +} + +static inline int liveupdate_register_file_handler(struct liveupdate_file_handler *fh) +{ + return -EOPNOTSUPP; +} + +static inline int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh) +{ + return -EOPNOTSUPP; +} + +#endif /* CONFIG_LIVEUPDATE */ +#endif /* _LINUX_LIVEUPDATE_H */ diff --git a/include/linux/math.h b/include/linux/math.h index 0198c92cbe3e..6dc1d1d32fbc 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -148,11 +148,16 @@ __STRUCT_FRACT(u32) /** * abs - return absolute value of an argument - * @x: the value. If it is unsigned type, it is converted to signed type first. - * char is treated as if it was signed (regardless of whether it really is) - * but the macro's return type is preserved as char. + * @x: the value. * - * Return: an absolute value of x. + * If it is unsigned type, @x is converted to signed type first. + * char is treated as if it was signed (regardless of whether it really is) + * but the macro's return type is preserved as char. + * + * NOTE, for signed type if @x is the minimum, the returned result is undefined + * as there is not enough bits to represent it as a positive number. + * + * Return: an absolute value of @x. */ #define abs(x) __abs_choose_expr(x, long long, \ __abs_choose_expr(x, long, \ diff --git a/include/linux/math64.h b/include/linux/math64.h index 6aaccc1626ab..cc305206d89f 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -158,6 +158,17 @@ static inline u64 mul_u32_u32(u32 a, u32 b) } #endif +#ifndef add_u64_u32 +/* + * Many a GCC version also messes this up. + * Zero extending b and then spilling everything to stack. + */ +static inline u64 add_u64_u32(u64 a, u32 b) +{ + return a + b; +} +#endif + #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) #ifndef mul_u64_u32_shr @@ -282,7 +293,53 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ -u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); +/** + * mul_u64_add_u64_div_u64 - unsigned 64bit multiply, add, and divide + * @a: first unsigned 64bit multiplicand + * @b: second unsigned 64bit multiplicand + * @c: unsigned 64bit addend + * @d: unsigned 64bit divisor + * + * Multiply two 64bit values together to generate a 128bit product + * add a third value and then divide by a fourth. + * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. + * Architecture specific code may trap on zero or overflow. + * + * Return: (@a * @b + @c) / @d + */ +u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d); + +/** + * mul_u64_u64_div_u64 - unsigned 64bit multiply and divide + * @a: first unsigned 64bit multiplicand + * @b: second unsigned 64bit multiplicand + * @d: unsigned 64bit divisor + * + * Multiply two 64bit values together to generate a 128bit product + * and then divide by a third value. + * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. + * Architecture specific code may trap on zero or overflow. + * + * Return: @a * @b / @d + */ +#define mul_u64_u64_div_u64(a, b, d) mul_u64_add_u64_div_u64(a, b, 0, d) + +/** + * mul_u64_u64_div_u64_roundup - unsigned 64bit multiply and divide rounded up + * @a: first unsigned 64bit multiplicand + * @b: second unsigned 64bit multiplicand + * @d: unsigned 64bit divisor + * + * Multiply two 64bit values together to generate a 128bit product + * and then divide and round up. + * The Generic code divides by 0 if @d is zero and returns ~0 on overflow. + * Architecture specific code may trap on zero or overflow. + * + * Return: (@a * @b + @d - 1) / @d + */ +#define mul_u64_u64_div_u64_roundup(a, b, d) \ + ({ u64 _tmp = (d); mul_u64_add_u64_div_u64(a, b, _tmp - 1, _tmp); }) + /** * DIV64_U64_ROUND_UP - unsigned 64bit divide with 64bit divisor rounded up diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h index 27de7bc32a06..236592c4eeb1 100644 --- a/include/linux/once_lite.h +++ b/include/linux/once_lite.h @@ -16,7 +16,7 @@ bool __ret_cond = !!(condition); \ bool __ret_once = false; \ \ - if (unlikely(__ret_cond && !__already_done)) { \ + if (unlikely(__ret_cond) && unlikely(!__already_done)) {\ __already_done = true; \ __ret_once = true; \ } \ diff --git a/include/linux/panic.h b/include/linux/panic.h index 6f972a66c13e..a00bc0937698 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -86,7 +86,6 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) struct taint_flag { char c_true; /* character printed when tainted */ char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ const char *desc; /* verbose description of the set taint flag */ }; diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h index 8d2ba3749866..4091e978aef2 100644 --- a/include/linux/rbtree.h +++ b/include/linux/rbtree.h @@ -43,8 +43,36 @@ extern void rb_erase(struct rb_node *, struct rb_root *); /* Find logical next and previous nodes in a tree */ extern struct rb_node *rb_next(const struct rb_node *); extern struct rb_node *rb_prev(const struct rb_node *); -extern struct rb_node *rb_first(const struct rb_root *); -extern struct rb_node *rb_last(const struct rb_root *); + +/* + * This function returns the first node (in sort order) of the tree. + */ +static inline struct rb_node *rb_first(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_left) + n = n->rb_left; + return n; +} + +/* + * This function returns the last node (in sort order) of the tree. + */ +static inline struct rb_node *rb_last(const struct rb_root *root) +{ + struct rb_node *n; + + n = root->rb_node; + if (!n) + return NULL; + while (n->rb_right) + n = n->rb_right; + return n; +} /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 5e4b3c1ae5c2..e2069b3179c4 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -10,6 +10,7 @@ #include #include #include +#include struct swap_iocb; @@ -19,6 +20,19 @@ struct swap_iocb; #define SHMEM_MAXQUOTAS 2 #endif +/* Suppress pre-accounting of the entire object size. */ +#define SHMEM_F_NORESERVE BIT(0) +/* Disallow swapping. */ +#define SHMEM_F_LOCKED BIT(1) +/* + * Disallow growing, shrinking, or hole punching in the inode. Combined with + * folio pinning, makes sure the inode's mapping stays fixed. + * + * In some ways similar to F_SEAL_GROW | F_SEAL_SHRINK, but can be removed and + * isn't directly visible to userspace. + */ +#define SHMEM_F_MAPPING_FROZEN BIT(2) + struct shmem_inode_info { spinlock_t lock; unsigned int seals; /* shmem seals */ @@ -186,6 +200,15 @@ static inline bool shmem_file(struct file *file) return shmem_mapping(file->f_mapping); } +/* Must be called with inode lock taken exclusive. */ +static inline void shmem_freeze(struct inode *inode, bool freeze) +{ + if (freeze) + SHMEM_I(inode)->flags |= SHMEM_F_MAPPING_FROZEN; + else + SHMEM_I(inode)->flags &= ~SHMEM_F_MAPPING_FROZEN; +} + /* * If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages * beyond i_size's notion of EOF, which fallocate has committed to reserving: diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h index 89d77dc4f2ed..a5bc3ea3d44b 100644 --- a/include/linux/sys_info.h +++ b/include/linux/sys_info.h @@ -14,7 +14,7 @@ #define SYS_INFO_LOCKS 0x00000008 #define SYS_INFO_FTRACE 0x00000010 #define SYS_INFO_PANIC_CONSOLE_REPLAY 0x00000020 -#define SYS_INFO_ALL_CPU_BT 0x00000040 +#define SYS_INFO_ALL_BT 0x00000040 #define SYS_INFO_BLOCKED_TASKS 0x00000080 void sys_info(unsigned long si_mask); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index be395f5f7ee3..1f3804245c06 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -161,8 +161,6 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) * directly in the normal copy_to/from_user(), the other ones go * through an extern _copy_to/from_user(), which expands the same code * here. - * - * Rust code always uses the extern definition. */ static inline __must_check unsigned long _inline_copy_from_user(void *to, const void __user *from, unsigned long n) @@ -192,8 +190,10 @@ fail: memset(to + (n - res), 0, res); return res; } +#ifndef INLINE_COPY_FROM_USER extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); +#endif static inline __must_check unsigned long _inline_copy_to_user(void __user *to, const void *from, unsigned long n) @@ -207,8 +207,10 @@ _inline_copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } +#ifndef INLINE_COPY_TO_USER extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); +#endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 9373962aade9..2eb528058d0d 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -136,10 +136,10 @@ #define PTR_IF(cond, ptr) ((cond) ? (ptr) : NULL) /** - * to_user_ptr - cast a pointer passed as u64 from user space to void __user * + * u64_to_user_ptr - cast a pointer passed as u64 from user space to void __user * * @x: The u64 value from user space, usually via IOCTL * - * to_user_ptr() simply casts a pointer passed as u64 from user space to void + * u64_to_user_ptr() simply casts a pointer passed as u64 from user space to void * __user * correctly. Using this lets us get rid of all the tiresome casts. */ #define u64_to_user_ptr(x) \ diff --git a/include/linux/vmcore_info.h b/include/linux/vmcore_info.h index 37e003ae5262..e71518caacdf 100644 --- a/include/linux/vmcore_info.h +++ b/include/linux/vmcore_info.h @@ -5,6 +5,7 @@ #include #include #include +#include #define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) #define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(NN_PRSTATUS), 4) @@ -77,4 +78,11 @@ extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); void final_note(Elf_Word *buf); + +#ifdef CONFIG_VMCORE_INFO +void hwerr_log_error_type(enum hwerr_error_type src); +#else +static inline void hwerr_log_error_type(enum hwerr_error_type src) {}; +#endif + #endif /* LINUX_VMCORE_INFO_H */ diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h index 27f57eca8cb1..587122e2c29c 100644 --- a/include/linux/xxhash.h +++ b/include/linux/xxhash.h @@ -141,21 +141,7 @@ static inline unsigned long xxhash(const void *input, size_t length, */ /** - * struct xxh32_state - private xxh32 state, do not use members directly - */ -struct xxh32_state { - uint32_t total_len_32; - uint32_t large_len; - uint32_t v1; - uint32_t v2; - uint32_t v3; - uint32_t v4; - uint32_t mem32[4]; - uint32_t memsize; -}; - -/** - * struct xxh32_state - private xxh64 state, do not use members directly + * struct xxh64_state - private xxh64 state, do not use members directly */ struct xxh64_state { uint64_t total_len; @@ -167,16 +153,6 @@ struct xxh64_state { uint32_t memsize; }; -/** - * xxh32_reset() - reset the xxh32 state to start a new hashing operation - * - * @state: The xxh32 state to reset. - * @seed: Initialize the hash state with this seed. - * - * Call this function on any xxh32_state to prepare for a new hashing operation. - */ -void xxh32_reset(struct xxh32_state *state, uint32_t seed); - /** * xxh64_reset() - reset the xxh64 state to start a new hashing operation * @@ -210,24 +186,4 @@ int xxh64_update(struct xxh64_state *state, const void *input, size_t length); */ uint64_t xxh64_digest(const struct xxh64_state *state); -/*-************************** - * Utils - ***************************/ - -/** - * xxh32_copy_state() - copy the source state into the destination state - * - * @src: The source xxh32 state. - * @dst: The destination xxh32 state. - */ -void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src); - -/** - * xxh64_copy_state() - copy the source state into the destination state - * - * @src: The source xxh64 state. - * @dst: The destination xxh64 state. - */ -void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src); - #endif /* XXHASH_H */ diff --git a/include/uapi/linux/liveupdate.h b/include/uapi/linux/liveupdate.h new file mode 100644 index 000000000000..30bc66ee9436 --- /dev/null +++ b/include/uapi/linux/liveupdate.h @@ -0,0 +1,216 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +/* + * Userspace interface for /dev/liveupdate + * Live Update Orchestrator + * + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +#ifndef _UAPI_LIVEUPDATE_H +#define _UAPI_LIVEUPDATE_H + +#include +#include + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility. Each + * ioctl is passed in a structure pointer as the argument providing the size of + * the structure in the first u32. The kernel checks that any structure space + * beyond what it understands is 0. This allows userspace to use the backward + * compatible portion while consistently using the newer, larger, structures. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: A provided token does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ + +/* The ioctl type, documented in ioctl-number.rst */ +#define LIVEUPDATE_IOCTL_TYPE 0xBA + +/* The maximum length of session name including null termination */ +#define LIVEUPDATE_SESSION_NAME_LENGTH 64 + +/* The /dev/liveupdate ioctl commands */ +enum { + LIVEUPDATE_CMD_BASE = 0x00, + LIVEUPDATE_CMD_CREATE_SESSION = LIVEUPDATE_CMD_BASE, + LIVEUPDATE_CMD_RETRIEVE_SESSION = 0x01, +}; + +/* ioctl commands for session file descriptors */ +enum { + LIVEUPDATE_CMD_SESSION_BASE = 0x40, + LIVEUPDATE_CMD_SESSION_PRESERVE_FD = LIVEUPDATE_CMD_SESSION_BASE, + LIVEUPDATE_CMD_SESSION_RETRIEVE_FD = 0x41, + LIVEUPDATE_CMD_SESSION_FINISH = 0x42, +}; + +/** + * struct liveupdate_ioctl_create_session - ioctl(LIVEUPDATE_IOCTL_CREATE_SESSION) + * @size: Input; sizeof(struct liveupdate_ioctl_create_session) + * @fd: Output; The new file descriptor for the created session. + * @name: Input; A null-terminated string for the session name, max + * length %LIVEUPDATE_SESSION_NAME_LENGTH including termination + * character. + * + * Creates a new live update session for managing preserved resources. + * This ioctl can only be called on the main /dev/liveupdate device. + * + * Return: 0 on success, negative error code on failure. + */ +struct liveupdate_ioctl_create_session { + __u32 size; + __s32 fd; + __u8 name[LIVEUPDATE_SESSION_NAME_LENGTH]; +}; + +#define LIVEUPDATE_IOCTL_CREATE_SESSION \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_CREATE_SESSION) + +/** + * struct liveupdate_ioctl_retrieve_session - ioctl(LIVEUPDATE_IOCTL_RETRIEVE_SESSION) + * @size: Input; sizeof(struct liveupdate_ioctl_retrieve_session) + * @fd: Output; The new file descriptor for the retrieved session. + * @name: Input; A null-terminated string identifying the session to retrieve. + * The name must exactly match the name used when the session was + * created in the previous kernel. + * + * Retrieves a handle (a new file descriptor) for a preserved session by its + * name. This is the primary mechanism for a userspace agent to regain control + * of its preserved resources after a live update. + * + * The userspace application provides the null-terminated `name` of a session + * it created before the live update. If a preserved session with a matching + * name is found, the kernel instantiates it and returns a new file descriptor + * in the `fd` field. This new session FD can then be used for all file-specific + * operations, such as restoring individual file descriptors with + * LIVEUPDATE_SESSION_RETRIEVE_FD. + * + * It is the responsibility of the userspace application to know the names of + * the sessions it needs to retrieve. If no session with the given name is + * found, the ioctl will fail with -ENOENT. + * + * This ioctl can only be called on the main /dev/liveupdate device when the + * system is in the LIVEUPDATE_STATE_UPDATED state. + */ +struct liveupdate_ioctl_retrieve_session { + __u32 size; + __s32 fd; + __u8 name[LIVEUPDATE_SESSION_NAME_LENGTH]; +}; + +#define LIVEUPDATE_IOCTL_RETRIEVE_SESSION \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_RETRIEVE_SESSION) + +/* Session specific IOCTLs */ + +/** + * struct liveupdate_session_preserve_fd - ioctl(LIVEUPDATE_SESSION_PRESERVE_FD) + * @size: Input; sizeof(struct liveupdate_session_preserve_fd) + * @fd: Input; The user-space file descriptor to be preserved. + * @token: Input; An opaque, unique token for preserved resource. + * + * Holds parameters for preserving a file descriptor. + * + * User sets the @fd field identifying the file descriptor to preserve + * (e.g., memfd, kvm, iommufd, VFIO). The kernel validates if this FD type + * and its dependencies are supported for preservation. If validation passes, + * the kernel marks the FD internally and *initiates the process* of preparing + * its state for saving. The actual snapshotting of the state typically occurs + * during the subsequent %LIVEUPDATE_IOCTL_PREPARE execution phase, though + * some finalization might occur during freeze. + * On successful validation and initiation, the kernel uses the @token + * field with an opaque identifier representing the resource being preserved. + * This token confirms the FD is targeted for preservation and is required for + * the subsequent %LIVEUPDATE_SESSION_RETRIEVE_FD call after the live update. + * + * Return: 0 on success (validation passed, preservation initiated), negative + * error code on failure (e.g., unsupported FD type, dependency issue, + * validation failed). + */ +struct liveupdate_session_preserve_fd { + __u32 size; + __s32 fd; + __aligned_u64 token; +}; + +#define LIVEUPDATE_SESSION_PRESERVE_FD \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_PRESERVE_FD) + +/** + * struct liveupdate_session_retrieve_fd - ioctl(LIVEUPDATE_SESSION_RETRIEVE_FD) + * @size: Input; sizeof(struct liveupdate_session_retrieve_fd) + * @fd: Output; The new file descriptor representing the fully restored + * kernel resource. + * @token: Input; An opaque, token that was used to preserve the resource. + * + * Retrieve a previously preserved file descriptor. + * + * User sets the @token field to the value obtained from a successful + * %LIVEUPDATE_IOCTL_FD_PRESERVE call before the live update. On success, + * the kernel restores the state (saved during the PREPARE/FREEZE phases) + * associated with the token and populates the @fd field with a new file + * descriptor referencing the restored resource in the current (new) kernel. + * This operation must be performed *before* signaling completion via + * %LIVEUPDATE_IOCTL_FINISH. + * + * Return: 0 on success, negative error code on failure (e.g., invalid token). + */ +struct liveupdate_session_retrieve_fd { + __u32 size; + __s32 fd; + __aligned_u64 token; +}; + +#define LIVEUPDATE_SESSION_RETRIEVE_FD \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_RETRIEVE_FD) + +/** + * struct liveupdate_session_finish - ioctl(LIVEUPDATE_SESSION_FINISH) + * @size: Input; sizeof(struct liveupdate_session_finish) + * @reserved: Input; Must be zero. Reserved for future use. + * + * Signals the completion of the restoration process for a retrieved session. + * This is the final operation that should be performed on a session file + * descriptor after a live update. + * + * This ioctl must be called once all required file descriptors for the session + * have been successfully retrieved (using %LIVEUPDATE_SESSION_RETRIEVE_FD) and + * are fully restored from the userspace and kernel perspective. + * + * Upon success, the kernel releases its ownership of the preserved resources + * associated with this session. This allows internal resources to be freed, + * typically by decrementing reference counts on the underlying preserved + * objects. + * + * If this operation fails, the resources remain preserved in memory. Userspace + * may attempt to call finish again. The resources will otherwise be reset + * during the next live update cycle. + * + * Return: 0 on success, negative error code on failure. + */ +struct liveupdate_session_finish { + __u32 size; + __u32 reserved; +}; + +#define LIVEUPDATE_SESSION_FINISH \ + _IO(LIVEUPDATE_IOCTL_TYPE, LIVEUPDATE_CMD_SESSION_FINISH) + +#endif /* _UAPI_LIVEUPDATE_H */ diff --git a/include/uapi/linux/vmcore.h b/include/uapi/linux/vmcore.h index 3e9da91866ff..2ba89fafa518 100644 --- a/include/uapi/linux/vmcore.h +++ b/include/uapi/linux/vmcore.h @@ -15,4 +15,13 @@ struct vmcoredd_header { __u8 dump_name[VMCOREDD_MAX_NAME_BYTES]; /* Device dump's name */ }; +enum hwerr_error_type { + HWERR_RECOV_CPU, + HWERR_RECOV_MEMORY, + HWERR_RECOV_PCI, + HWERR_RECOV_CXL, + HWERR_RECOV_OTHERS, + HWERR_RECOV_MAX, +}; + #endif /* _UAPI_VMCORE_H */ diff --git a/init/Kconfig b/init/Kconfig index ad42558d842d..fa79feb8fe57 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1519,6 +1519,24 @@ config BOOT_CONFIG_EMBED_FILE This bootconfig will be used if there is no initrd or no other bootconfig in the initrd. +config CMDLINE_LOG_WRAP_IDEAL_LEN + int "Length to try to wrap the cmdline when logged at boot" + default 1021 + range 0 1021 + help + At boot time, the kernel command line is logged to the console. + The log message will start with the prefix "Kernel command line: ". + The log message will attempt to be wrapped (split into multiple log + messages) at spaces based on CMDLINE_LOG_WRAP_IDEAL_LEN characters. + If wrapping happens, each log message will start with the prefix and + all but the last message will end with " \". Messages may exceed the + ideal length if a place to wrap isn't found before the specified + number of characters. + + A value of 0 disables wrapping, though be warned that the maximum + length of a log message (1021 characters) may cause the cmdline to + be truncated. + config INITRAMFS_PRESERVE_MTIME bool "Preserve cpio archive mtimes in initramfs" depends on BLK_DEV_INITRD @@ -2171,6 +2189,8 @@ config TRACEPOINTS source "kernel/Kconfig.kexec" +source "kernel/liveupdate/Kconfig" + endmenu # General setup source "arch/Kconfig" diff --git a/init/calibrate.c b/init/calibrate.c index f3831272f113..63be4c65bc52 100644 --- a/init/calibrate.c +++ b/init/calibrate.c @@ -5,19 +5,22 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ -#include #include #include -#include -#include +#include +#include #include +#include +#include +#include +#include unsigned long lpj_fine; unsigned long preset_lpj; + static int __init lpj_setup(char *str) { - preset_lpj = simple_strtoul(str,NULL,0); - return 1; + return kstrtoul(str, 0, &preset_lpj) == 0; } __setup("lpj=", lpj_setup); diff --git a/init/main.c b/init/main.c index 07a3116811c5..b84818ad9685 100644 --- a/init/main.c +++ b/init/main.c @@ -906,6 +906,101 @@ static void __init early_numa_node_init(void) #endif } +#define KERNEL_CMDLINE_PREFIX "Kernel command line: " +#define KERNEL_CMDLINE_PREFIX_LEN (sizeof(KERNEL_CMDLINE_PREFIX) - 1) +#define KERNEL_CMDLINE_CONTINUATION " \\" +#define KERNEL_CMDLINE_CONTINUATION_LEN (sizeof(KERNEL_CMDLINE_CONTINUATION) - 1) + +#define MIN_CMDLINE_LOG_WRAP_IDEAL_LEN (KERNEL_CMDLINE_PREFIX_LEN + \ + KERNEL_CMDLINE_CONTINUATION_LEN) +#define CMDLINE_LOG_WRAP_IDEAL_LEN (CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN > \ + MIN_CMDLINE_LOG_WRAP_IDEAL_LEN ? \ + CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN : \ + MIN_CMDLINE_LOG_WRAP_IDEAL_LEN) + +#define IDEAL_CMDLINE_LEN (CMDLINE_LOG_WRAP_IDEAL_LEN - KERNEL_CMDLINE_PREFIX_LEN) +#define IDEAL_CMDLINE_SPLIT_LEN (IDEAL_CMDLINE_LEN - KERNEL_CMDLINE_CONTINUATION_LEN) + +/** + * print_kernel_cmdline() - Print the kernel cmdline with wrapping. + * @cmdline: The cmdline to print. + * + * Print the kernel command line, trying to wrap based on the Kconfig knob + * CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN. + * + * Wrapping is based on spaces, ignoring quotes. All lines are prefixed + * with "Kernel command line: " and lines that are not the last line have + * a " \" suffix added to them. The prefix and suffix count towards the + * line length for wrapping purposes. The ideal length will be exceeded + * if no appropriate place to wrap is found. + * + * Example output if CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN is 40: + * Kernel command line: loglevel=7 \ + * Kernel command line: init=/sbin/init \ + * Kernel command line: root=PARTUUID=8c3efc1a-768b-6642-8d0c-89eb782f19f0/PARTNROFF=1 \ + * Kernel command line: rootwait ro \ + * Kernel command line: my_quoted_arg="The \ + * Kernel command line: quick brown fox \ + * Kernel command line: jumps over the \ + * Kernel command line: lazy dog." + */ +static void __init print_kernel_cmdline(const char *cmdline) +{ + size_t len; + + /* Config option of 0 or anything longer than the max disables wrapping */ + if (CONFIG_CMDLINE_LOG_WRAP_IDEAL_LEN == 0 || + IDEAL_CMDLINE_LEN >= COMMAND_LINE_SIZE - 1) { + pr_notice("%s%s\n", KERNEL_CMDLINE_PREFIX, cmdline); + return; + } + + len = strlen(cmdline); + while (len > IDEAL_CMDLINE_LEN) { + const char *first_space; + const char *prev_cutoff; + const char *cutoff; + int to_print; + size_t used; + + /* Find the last ' ' that wouldn't make the line too long */ + prev_cutoff = NULL; + cutoff = cmdline; + while (true) { + cutoff = strchr(cutoff + 1, ' '); + if (!cutoff || cutoff - cmdline > IDEAL_CMDLINE_SPLIT_LEN) + break; + prev_cutoff = cutoff; + } + if (prev_cutoff) + cutoff = prev_cutoff; + else if (!cutoff) + break; + + /* Find the beginning and end of the string of spaces */ + first_space = cutoff; + while (first_space > cmdline && first_space[-1] == ' ') + first_space--; + to_print = first_space - cmdline; + while (*cutoff == ' ') + cutoff++; + used = cutoff - cmdline; + + /* If the whole string is used, break and do the final printout */ + if (len == used) + break; + + if (to_print) + pr_notice("%s%.*s%s\n", KERNEL_CMDLINE_PREFIX, + to_print, cmdline, KERNEL_CMDLINE_CONTINUATION); + + len -= used; + cmdline += used; + } + if (len) + pr_notice("%s%s\n", KERNEL_CMDLINE_PREFIX, cmdline); +} + asmlinkage __visible __init __no_sanitize_address __noreturn __no_stack_protector void start_kernel(void) { @@ -942,7 +1037,7 @@ void start_kernel(void) early_numa_node_init(); boot_cpu_hotplug_init(); - pr_notice("Kernel command line: %s\n", saved_command_line); + print_kernel_cmdline(saved_command_line); /* parameters may set static keys */ parse_early_param(); after_dashes = parse_args("Booting kernel", diff --git a/ipc/namespace.c b/ipc/namespace.c index c0dbfdd9015f..535f16ea40e1 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -76,10 +76,10 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, err = -ENOMEM; if (!setup_mq_sysctls(ns)) - goto fail_put; + goto fail_mq_mount; if (!setup_ipc_sysctls(ns)) - goto fail_mq; + goto fail_mq_sysctls; err = msg_init_ns(ns); if (err) @@ -93,9 +93,10 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, fail_ipc: retire_ipc_sysctls(ns); -fail_mq: +fail_mq_sysctls: retire_mq_sysctls(ns); - +fail_mq_mount: + mntput(ns->mq_mnt); fail_put: put_user_ns(ns->user_ns); ns_common_free(ns); diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 54e581072617..15632358bcf7 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -94,30 +94,6 @@ config KEXEC_JUMP Jump between original kernel and kexeced kernel and invoke code in physical address mode via KEXEC -config KEXEC_HANDOVER - bool "kexec handover" - depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE - depends on !DEFERRED_STRUCT_PAGE_INIT - select MEMBLOCK_KHO_SCRATCH - select KEXEC_FILE - select DEBUG_FS - select LIBFDT - select CMA - help - Allow kexec to hand over state across kernels by generating and - passing additional metadata to the target kernel. This is useful - to keep data or state alive across the kexec. For this to work, - both source and target kernels need to have this option enabled. - -config KEXEC_HANDOVER_DEBUG - bool "Enable Kexec Handover debug checks" - depends on KEXEC_HANDOVER - help - This option enables extra sanity checks for the Kexec Handover - subsystem. Since, KHO performance is crucial in live update - scenarios and the extra code might be adding overhead it is - only optionally enabled. - config CRASH_DUMP bool "kernel crash dumps" default ARCH_DEFAULT_CRASH_DUMP diff --git a/kernel/Makefile b/kernel/Makefile index 9fe722305c9b..e83669841b8c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -52,6 +52,7 @@ obj-y += printk/ obj-y += irq/ obj-y += rcu/ obj-y += livepatch/ +obj-y += liveupdate/ obj-y += dma/ obj-y += entry/ obj-y += unwind/ @@ -82,8 +83,6 @@ obj-$(CONFIG_CRASH_DUMP_KUNIT_TEST) += crash_core_test.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o -obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o -obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o obj-$(CONFIG_CGROUPS) += cgroup/ diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index e81327d2cd63..9f6ab7dabf67 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -83,7 +83,7 @@ CONFIG_SLUB_DEBUG_ON=y # # Debug Oops, Lockups and Hangs # -# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=0 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DETECT_HUNG_TASK=y diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c index 87bf4d41eabb..62e60e0223cf 100644 --- a/kernel/crash_reserve.c +++ b/kernel/crash_reserve.c @@ -524,6 +524,9 @@ void __init reserve_crashkernel_cma(unsigned long long cma_size) #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY static __init int insert_crashkernel_resources(void) { + if (!arch_add_crash_res_to_iomem()) + return 0; + if (crashk_res.start < crashk_res.end) insert_resource(&iomem_resource, &crashk_res); diff --git a/kernel/exit.c b/kernel/exit.c index 4dc1918db67b..8a87021211ae 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -251,10 +251,8 @@ repeat: memset(&post, 0, sizeof(post)); /* don't need to get the RCU readlock here - the process is dead and - * can't be modifying its own credentials. But shut RCU-lockdep up */ - rcu_read_lock(); + * can't be modifying its own credentials. */ dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); - rcu_read_unlock(); pidfs_exit(p); cgroup_task_release(p); diff --git a/kernel/fork.c b/kernel/fork.c index 198e02e21e6e..b1f3915d5f8e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -208,15 +208,62 @@ struct vm_stack { struct vm_struct *stack_vm_area; }; +static struct vm_struct *alloc_thread_stack_node_from_cache(struct task_struct *tsk, int node) +{ + struct vm_struct *vm_area; + unsigned int i; + + /* + * If the node has memory, we are guaranteed the stacks are backed by local pages. + * Otherwise the pages are arbitrary. + * + * Note that depending on cpuset it is possible we will get migrated to a different + * node immediately after allocating here, so this does *not* guarantee locality for + * arbitrary callers. + */ + scoped_guard(preempt) { + if (node != NUMA_NO_NODE && numa_node_id() != node) + return NULL; + + for (i = 0; i < NR_CACHED_STACKS; i++) { + vm_area = this_cpu_xchg(cached_stacks[i], NULL); + if (vm_area) + return vm_area; + } + } + + return NULL; +} + static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area) { unsigned int i; + int nid; - for (i = 0; i < NR_CACHED_STACKS; i++) { - struct vm_struct *tmp = NULL; + /* + * Don't cache stacks if any of the pages don't match the local domain, unless + * there is no local memory to begin with. + * + * Note that lack of local memory does not automatically mean it makes no difference + * performance-wise which other domain backs the stack. In this case we are merely + * trying to avoid constantly going to vmalloc. + */ + scoped_guard(preempt) { + nid = numa_node_id(); + if (node_state(nid, N_MEMORY)) { + for (i = 0; i < vm_area->nr_pages; i++) { + struct page *page = vm_area->pages[i]; + if (page_to_nid(page) != nid) + return false; + } + } - if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) - return true; + for (i = 0; i < NR_CACHED_STACKS; i++) { + struct vm_struct *tmp = NULL; + + if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) + return true; + } } return false; } @@ -283,13 +330,9 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; - int i; - - for (i = 0; i < NR_CACHED_STACKS; i++) { - vm_area = this_cpu_xchg(cached_stacks[i], NULL); - if (!vm_area) - continue; + vm_area = alloc_thread_stack_node_from_cache(tsk, node); + if (vm_area) { if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b2c1f14b8129..d2254c91450b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -24,6 +24,7 @@ #include #include #include +#include #include @@ -50,7 +51,6 @@ static unsigned long __read_mostly sysctl_hung_task_detect_count; * Zero means infinite timeout - no checking done: */ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; -EXPORT_SYMBOL_GPL(sysctl_hung_task_timeout_secs); /* * Zero (default value) means use sysctl_hung_task_timeout_secs: @@ -60,12 +60,17 @@ static unsigned long __read_mostly sysctl_hung_task_check_interval_secs; static int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; -static bool hung_task_show_lock; static bool hung_task_call_panic; -static bool hung_task_show_all_bt; static struct task_struct *watchdog_task; +/* + * A bitmask to control what kinds of system info to be printed when + * a hung task is detected, it could be task, memory, lock etc. Refer + * include/linux/sys_info.h for detailed bit definition. + */ +static unsigned long hung_task_si_mask; + #ifdef CONFIG_SMP /* * Should we dump all CPUs backtraces in a hung task event? @@ -81,7 +86,7 @@ static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; * hung task is detected: */ static unsigned int __read_mostly sysctl_hung_task_panic = - IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); + CONFIG_BOOTPARAM_HUNG_TASK_PANIC; static int hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) @@ -218,8 +223,11 @@ static inline void debug_show_blocker(struct task_struct *task, unsigned long ti } #endif -static void check_hung_task(struct task_struct *t, unsigned long timeout) +static void check_hung_task(struct task_struct *t, unsigned long timeout, + unsigned long prev_detect_count) { + unsigned long total_hung_task; + if (!task_is_hung(t, timeout)) return; @@ -229,11 +237,11 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) */ sysctl_hung_task_detect_count++; + total_hung_task = sysctl_hung_task_detect_count - prev_detect_count; trace_sched_process_hang(t); - if (sysctl_hung_task_panic) { + if (sysctl_hung_task_panic && total_hung_task >= sysctl_hung_task_panic) { console_verbose(); - hung_task_show_lock = true; hung_task_call_panic = true; } @@ -256,10 +264,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) " disables this message.\n"); sched_show_task(t); debug_show_blocker(t, timeout); - hung_task_show_lock = true; - if (sysctl_hung_task_all_cpu_backtrace) - hung_task_show_all_bt = true; if (!sysctl_hung_task_warnings) pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n"); } @@ -300,6 +305,9 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) int max_count = sysctl_hung_task_check_count; unsigned long last_break = jiffies; struct task_struct *g, *t; + unsigned long prev_detect_count = sysctl_hung_task_detect_count; + int need_warning = sysctl_hung_task_warnings; + unsigned long si_mask = hung_task_si_mask; /* * If the system crashed already then all bets are off, @@ -308,7 +316,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) if (test_taint(TAINT_DIE) || did_panic) return; - hung_task_show_lock = false; + rcu_read_lock(); for_each_process_thread(g, t) { @@ -320,18 +328,23 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) last_break = jiffies; } - check_hung_task(t, timeout); + check_hung_task(t, timeout, prev_detect_count); } unlock: rcu_read_unlock(); - if (hung_task_show_lock) - debug_show_all_locks(); - if (hung_task_show_all_bt) { - hung_task_show_all_bt = false; - trigger_all_cpu_backtrace(); + if (!(sysctl_hung_task_detect_count - prev_detect_count)) + return; + + if (need_warning || hung_task_call_panic) { + si_mask |= SYS_INFO_LOCKS; + + if (sysctl_hung_task_all_cpu_backtrace) + si_mask |= SYS_INFO_ALL_BT; } + sys_info(si_mask); + if (hung_task_call_panic) panic("hung_task: blocked tasks"); } @@ -389,7 +402,7 @@ static const struct ctl_table hung_task_sysctls[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "hung_task_check_count", @@ -430,6 +443,13 @@ static const struct ctl_table hung_task_sysctls[] = { .mode = 0444, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "hung_task_sys_info", + .data = &hung_task_si_mask, + .maxlen = sizeof(hung_task_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, }; static void __init hung_task_sysctl_init(void) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index fa00b239c5d9..0f92acdd354d 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include @@ -742,7 +744,6 @@ static int kimage_load_cma_segment(struct kimage *image, int idx) struct kexec_segment *segment = &image->segment[idx]; struct page *cma = image->segment_cma[idx]; char *ptr = page_address(cma); - unsigned long maddr; size_t ubytes, mbytes; int result = 0; unsigned char __user *buf = NULL; @@ -754,15 +755,12 @@ static int kimage_load_cma_segment(struct kimage *image, int idx) buf = segment->buf; ubytes = segment->bufsz; mbytes = segment->memsz; - maddr = segment->mem; /* Then copy from source buffer to the CMA one */ while (mbytes) { size_t uchunk, mchunk; - ptr += maddr & ~PAGE_MASK; - mchunk = min_t(size_t, mbytes, - PAGE_SIZE - (maddr & ~PAGE_MASK)); + mchunk = min_t(size_t, mbytes, PAGE_SIZE); uchunk = min(ubytes, mchunk); if (uchunk) { @@ -784,7 +782,6 @@ static int kimage_load_cma_segment(struct kimage *image, int idx) } ptr += mchunk; - maddr += mchunk; mbytes -= mchunk; cond_resched(); @@ -839,9 +836,7 @@ static int kimage_load_normal_segment(struct kimage *image, int idx) ptr = kmap_local_page(page); /* Start with a clear page */ clear_page(ptr); - ptr += maddr & ~PAGE_MASK; - mchunk = min_t(size_t, mbytes, - PAGE_SIZE - (maddr & ~PAGE_MASK)); + mchunk = min_t(size_t, mbytes, PAGE_SIZE); uchunk = min(ubytes, mchunk); if (uchunk) { @@ -904,9 +899,7 @@ static int kimage_load_crash_segment(struct kimage *image, int idx) } arch_kexec_post_alloc_pages(page_address(page), 1, 0); ptr = kmap_local_page(page); - ptr += maddr & ~PAGE_MASK; - mchunk = min_t(size_t, mbytes, - PAGE_SIZE - (maddr & ~PAGE_MASK)); + mchunk = min_t(size_t, mbytes, PAGE_SIZE); uchunk = min(ubytes, mchunk); if (mchunk > uchunk) { /* Zero the trailing part of the page */ @@ -1146,6 +1139,10 @@ int kernel_kexec(void) goto Unlock; } + error = liveupdate_reboot(); + if (error) + goto Unlock; + #ifdef CONFIG_KEXEC_JUMP if (kexec_image->preserve_context) { /* @@ -1229,3 +1226,143 @@ int kernel_kexec(void) kexec_unlock(); return error; } + +static ssize_t loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", !!kexec_image); +} +static struct kobj_attribute loaded_attr = __ATTR_RO(loaded); + +#ifdef CONFIG_CRASH_DUMP +static ssize_t crash_loaded_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%d\n", kexec_crash_loaded()); +} +static struct kobj_attribute crash_loaded_attr = __ATTR_RO(crash_loaded); + +#ifdef CONFIG_CRASH_RESERVE +static ssize_t crash_cma_ranges_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + + ssize_t len = 0; + int i; + + for (i = 0; i < crashk_cma_cnt; ++i) { + len += sysfs_emit_at(buf, len, "%08llx-%08llx\n", + crashk_cma_ranges[i].start, + crashk_cma_ranges[i].end); + } + return len; +} +static struct kobj_attribute crash_cma_ranges_attr = __ATTR_RO(crash_cma_ranges); +#endif + +static ssize_t crash_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + ssize_t size = crash_get_memory_size(); + + if (size < 0) + return size; + + return sysfs_emit(buf, "%zd\n", size); +} +static ssize_t crash_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + unsigned long cnt; + int ret; + + if (kstrtoul(buf, 0, &cnt)) + return -EINVAL; + + ret = crash_shrink_memory(cnt); + return ret < 0 ? ret : count; +} +static struct kobj_attribute crash_size_attr = __ATTR_RW(crash_size); + +#ifdef CONFIG_CRASH_HOTPLUG +static ssize_t crash_elfcorehdr_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + unsigned int sz = crash_get_elfcorehdr_size(); + + return sysfs_emit(buf, "%u\n", sz); +} +static struct kobj_attribute crash_elfcorehdr_size_attr = __ATTR_RO(crash_elfcorehdr_size); + +#endif /* CONFIG_CRASH_HOTPLUG */ +#endif /* CONFIG_CRASH_DUMP */ + +static struct attribute *kexec_attrs[] = { + &loaded_attr.attr, +#ifdef CONFIG_CRASH_DUMP + &crash_loaded_attr.attr, + &crash_size_attr.attr, +#ifdef CONFIG_CRASH_RESERVE + &crash_cma_ranges_attr.attr, +#endif +#ifdef CONFIG_CRASH_HOTPLUG + &crash_elfcorehdr_size_attr.attr, +#endif +#endif + NULL +}; + +struct kexec_link_entry { + const char *target; + const char *name; +}; + +static struct kexec_link_entry kexec_links[] = { + { "loaded", "kexec_loaded" }, +#ifdef CONFIG_CRASH_DUMP + { "crash_loaded", "kexec_crash_loaded" }, + { "crash_size", "kexec_crash_size" }, +#ifdef CONFIG_CRASH_RESERVE + {"crash_cma_ranges", "kexec_crash_cma_ranges"}, +#endif +#ifdef CONFIG_CRASH_HOTPLUG + { "crash_elfcorehdr_size", "crash_elfcorehdr_size" }, +#endif +#endif +}; + +static struct kobject *kexec_kobj; +ATTRIBUTE_GROUPS(kexec); + +static int __init init_kexec_sysctl(void) +{ + int error; + int i; + + kexec_kobj = kobject_create_and_add("kexec", kernel_kobj); + if (!kexec_kobj) { + pr_err("failed to create kexec kobject\n"); + return -ENOMEM; + } + + error = sysfs_create_groups(kexec_kobj, kexec_groups); + if (error) + goto kset_exit; + + for (i = 0; i < ARRAY_SIZE(kexec_links); i++) { + error = compat_only_sysfs_link_entry_to_kobj(kernel_kobj, kexec_kobj, + kexec_links[i].target, + kexec_links[i].name); + if (error) + pr_err("Unable to create %s symlink (%d)", kexec_links[i].name, error); + } + + return 0; + +kset_exit: + kobject_put(kexec_kobj); + return error; +} + +subsys_initcall(init_kexec_sysctl); diff --git a/kernel/kexec_handover_internal.h b/kernel/kexec_handover_internal.h deleted file mode 100644 index 3c3c7148ceed..000000000000 --- a/kernel/kexec_handover_internal.h +++ /dev/null @@ -1,20 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H -#define LINUX_KEXEC_HANDOVER_INTERNAL_H - -#include -#include - -extern struct kho_scratch *kho_scratch; -extern unsigned int kho_scratch_cnt; - -#ifdef CONFIG_KEXEC_HANDOVER_DEBUG -bool kho_scratch_overlap(phys_addr_t phys, size_t size); -#else -static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size) -{ - return false; -} -#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */ - -#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */ diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index eefb67d9883c..a9e6354d9e25 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include @@ -119,50 +119,6 @@ static ssize_t profiling_store(struct kobject *kobj, KERNEL_ATTR_RW(profiling); #endif -#ifdef CONFIG_KEXEC_CORE -static ssize_t kexec_loaded_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%d\n", !!kexec_image); -} -KERNEL_ATTR_RO(kexec_loaded); - -#ifdef CONFIG_CRASH_DUMP -static ssize_t kexec_crash_loaded_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%d\n", kexec_crash_loaded()); -} -KERNEL_ATTR_RO(kexec_crash_loaded); - -static ssize_t kexec_crash_size_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - ssize_t size = crash_get_memory_size(); - - if (size < 0) - return size; - - return sysfs_emit(buf, "%zd\n", size); -} -static ssize_t kexec_crash_size_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - unsigned long cnt; - int ret; - - if (kstrtoul(buf, 0, &cnt)) - return -EINVAL; - - ret = crash_shrink_memory(cnt); - return ret < 0 ? ret : count; -} -KERNEL_ATTR_RW(kexec_crash_size); - -#endif /* CONFIG_CRASH_DUMP*/ -#endif /* CONFIG_KEXEC_CORE */ - #ifdef CONFIG_VMCORE_INFO static ssize_t vmcoreinfo_show(struct kobject *kobj, @@ -174,18 +130,6 @@ static ssize_t vmcoreinfo_show(struct kobject *kobj, } KERNEL_ATTR_RO(vmcoreinfo); -#ifdef CONFIG_CRASH_HOTPLUG -static ssize_t crash_elfcorehdr_size_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - unsigned int sz = crash_get_elfcorehdr_size(); - - return sysfs_emit(buf, "%u\n", sz); -} -KERNEL_ATTR_RO(crash_elfcorehdr_size); - -#endif - #endif /* CONFIG_VMCORE_INFO */ /* whether file capabilities are enabled */ @@ -255,18 +199,8 @@ static struct attribute * kernel_attrs[] = { #ifdef CONFIG_PROFILING &profiling_attr.attr, #endif -#ifdef CONFIG_KEXEC_CORE - &kexec_loaded_attr.attr, -#ifdef CONFIG_CRASH_DUMP - &kexec_crash_loaded_attr.attr, - &kexec_crash_size_attr.attr, -#endif -#endif #ifdef CONFIG_VMCORE_INFO &vmcoreinfo_attr.attr, -#ifdef CONFIG_CRASH_HOTPLUG - &crash_elfcorehdr_size_attr.attr, -#endif #endif #ifndef CONFIG_TINY_RCU &rcu_expedited_attr.attr, diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig new file mode 100644 index 000000000000..9b2515f31afb --- /dev/null +++ b/kernel/liveupdate/Kconfig @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: GPL-2.0-only + +menu "Live Update and Kexec HandOver" + depends on !DEFERRED_STRUCT_PAGE_INIT + +config KEXEC_HANDOVER + bool "kexec handover" + depends on ARCH_SUPPORTS_KEXEC_HANDOVER && ARCH_SUPPORTS_KEXEC_FILE + depends on !DEFERRED_STRUCT_PAGE_INIT + select MEMBLOCK_KHO_SCRATCH + select KEXEC_FILE + select LIBFDT + select CMA + help + Allow kexec to hand over state across kernels by generating and + passing additional metadata to the target kernel. This is useful + to keep data or state alive across the kexec. For this to work, + both source and target kernels need to have this option enabled. + +config KEXEC_HANDOVER_DEBUG + bool "Enable Kexec Handover debug checks" + depends on KEXEC_HANDOVER + help + This option enables extra sanity checks for the Kexec Handover + subsystem. Since, KHO performance is crucial in live update + scenarios and the extra code might be adding overhead it is + only optionally enabled. + +config KEXEC_HANDOVER_DEBUGFS + bool "kexec handover debugfs interface" + default KEXEC_HANDOVER + depends on KEXEC_HANDOVER + select DEBUG_FS + help + Allow to control kexec handover device tree via debugfs + interface, i.e. finalize the state or aborting the finalization. + Also, enables inspecting the KHO fdt trees with the debugfs binary + blobs. + +config KEXEC_HANDOVER_ENABLE_DEFAULT + bool "Enable kexec handover by default" + depends on KEXEC_HANDOVER + help + Enable Kexec Handover by default. This avoids the need to + explicitly pass 'kho=on' on the kernel command line. + + This is useful for systems where KHO is a prerequisite for other + features, such as Live Update, ensuring the mechanism is always + active. + + The default behavior can still be overridden at boot time by + passing 'kho=off'. + +config LIVEUPDATE + bool "Live Update Orchestrator" + depends on KEXEC_HANDOVER + help + Enable the Live Update Orchestrator. Live Update is a mechanism, + typically based on kexec, that allows the kernel to be updated + while keeping selected devices operational across the transition. + These devices are intended to be reclaimed by the new kernel and + re-attached to their original workload without requiring a device + reset. + + Ability to handover a device from current to the next kernel depends + on specific support within device drivers and related kernel + subsystems. + + This feature primarily targets virtual machine hosts to quickly update + the kernel hypervisor with minimal disruption to the running virtual + machines. + + If unsure, say N. + +endmenu diff --git a/kernel/liveupdate/Makefile b/kernel/liveupdate/Makefile new file mode 100644 index 000000000000..7cad2eece32d --- /dev/null +++ b/kernel/liveupdate/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +luo-y := \ + luo_core.o \ + luo_file.o \ + luo_session.o + +obj-$(CONFIG_KEXEC_HANDOVER) += kexec_handover.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUG) += kexec_handover_debug.o +obj-$(CONFIG_KEXEC_HANDOVER_DEBUGFS) += kexec_handover_debugfs.o + +obj-$(CONFIG_LIVEUPDATE) += luo.o diff --git a/kernel/kexec_handover.c b/kernel/liveupdate/kexec_handover.c similarity index 75% rename from kernel/kexec_handover.c rename to kernel/liveupdate/kexec_handover.c index 03d12e27189f..9dc51fab604f 100644 --- a/kernel/kexec_handover.c +++ b/kernel/liveupdate/kexec_handover.c @@ -4,21 +4,22 @@ * Copyright (C) 2023 Alexander Graf * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport * Copyright (C) 2025 Google LLC, Changyuan Lyu + * Copyright (C) 2025 Pasha Tatashin */ #define pr_fmt(fmt) "KHO: " fmt #include #include +#include #include -#include #include #include #include #include #include -#include #include +#include #include #include @@ -28,8 +29,9 @@ * KHO is tightly coupled with mm init and needs access to some of mm * internal APIs. */ -#include "../mm/internal.h" -#include "kexec_internal.h" +#include "../../mm/internal.h" +#include "../kexec_internal.h" +#include "kexec_handover_internal.h" #define KHO_FDT_COMPATIBLE "kho-v1" #define PROP_PRESERVED_MEMORY_MAP "preserved-memory-map" @@ -51,7 +53,7 @@ union kho_page_info { static_assert(sizeof(union kho_page_info) == sizeof(((struct page *)0)->private)); -static bool kho_enable __ro_after_init; +static bool kho_enable __ro_after_init = IS_ENABLED(CONFIG_KEXEC_HANDOVER_ENABLE_DEFAULT); bool kho_is_enabled(void) { @@ -103,34 +105,19 @@ struct kho_mem_track { struct khoser_mem_chunk; -struct kho_serialization { - struct page *fdt; - struct list_head fdt_list; - struct dentry *sub_fdt_dir; - struct kho_mem_track track; - /* First chunk of serialized preserved memory map */ - struct khoser_mem_chunk *preserved_mem_map; -}; - struct kho_out { - struct blocking_notifier_head chain_head; - - struct dentry *dir; - + void *fdt; + bool finalized; struct mutex lock; /* protects KHO FDT finalization */ - struct kho_serialization ser; - bool finalized; + struct kho_mem_track track; + struct kho_debugfs dbg; }; static struct kho_out kho_out = { - .chain_head = BLOCKING_NOTIFIER_INIT(kho_out.chain_head), .lock = __MUTEX_INITIALIZER(kho_out.lock), - .ser = { - .fdt_list = LIST_HEAD_INIT(kho_out.ser.fdt_list), - .track = { - .orders = XARRAY_INIT(kho_out.ser.track.orders, 0), - }, + .track = { + .orders = XARRAY_INIT(kho_out.track.orders, 0), }, .finalized = false, }; @@ -159,26 +146,33 @@ static void *xa_load_or_alloc(struct xarray *xa, unsigned long index) return no_free_ptr(elm); } -static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, - unsigned long end_pfn) +static void __kho_unpreserve_order(struct kho_mem_track *track, unsigned long pfn, + unsigned int order) { struct kho_mem_phys_bits *bits; struct kho_mem_phys *physxa; + const unsigned long pfn_high = pfn >> order; + + physxa = xa_load(&track->orders, order); + if (WARN_ON_ONCE(!physxa)) + return; + + bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS); + if (WARN_ON_ONCE(!bits)) + return; + + clear_bit(pfn_high % PRESERVE_BITS, bits->preserve); +} + +static void __kho_unpreserve(struct kho_mem_track *track, unsigned long pfn, + unsigned long end_pfn) +{ + unsigned int order; while (pfn < end_pfn) { - const unsigned int order = - min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); - const unsigned long pfn_high = pfn >> order; + order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); - physxa = xa_load(&track->orders, order); - if (WARN_ON_ONCE(!physxa)) - return; - - bits = xa_load(&physxa->phys_bits, pfn_high / PRESERVE_BITS); - if (WARN_ON_ONCE(!bits)) - return; - - clear_bit(pfn_high % PRESERVE_BITS, bits->preserve); + __kho_unpreserve_order(track, pfn, order); pfn += 1 << order; } @@ -192,10 +186,6 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, const unsigned long pfn_high = pfn >> order; might_sleep(); - - if (kho_out.finalized) - return -EBUSY; - physxa = xa_load(&track->orders, order); if (!physxa) { int err; @@ -229,11 +219,11 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn, return 0; } -static struct page *kho_restore_page(phys_addr_t phys) +static struct page *kho_restore_page(phys_addr_t phys, bool is_folio) { struct page *page = pfn_to_online_page(PHYS_PFN(phys)); + unsigned int nr_pages, ref_cnt; union kho_page_info info; - unsigned int nr_pages; if (!page) return NULL; @@ -253,11 +243,16 @@ static struct page *kho_restore_page(phys_addr_t phys) /* Head page gets refcount of 1. */ set_page_count(page, 1); - /* For higher order folios, tail pages get a page count of zero. */ + /* + * For higher order folios, tail pages get a page count of zero. + * For physically contiguous order-0 pages every pages gets a page + * count of 1 + */ + ref_cnt = is_folio ? 0 : 1; for (unsigned int i = 1; i < nr_pages; i++) - set_page_count(page + i, 0); + set_page_count(page + i, ref_cnt); - if (info.order > 0) + if (is_folio && info.order) prep_compound_page(page, info.order); adjust_managed_page_count(page, nr_pages); @@ -272,7 +267,7 @@ static struct page *kho_restore_page(phys_addr_t phys) */ struct folio *kho_restore_folio(phys_addr_t phys) { - struct page *page = kho_restore_page(phys); + struct page *page = kho_restore_page(phys, true); return page ? page_folio(page) : NULL; } @@ -297,11 +292,10 @@ struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages) while (pfn < end_pfn) { const unsigned int order = min(count_trailing_zeros(pfn), ilog2(end_pfn - pfn)); - struct page *page = kho_restore_page(PFN_PHYS(pfn)); + struct page *page = kho_restore_page(PFN_PHYS(pfn), false); if (!page) return NULL; - split_page(page, order); pfn += 1 << order; } @@ -371,11 +365,32 @@ static void kho_mem_ser_free(struct khoser_mem_chunk *first_chunk) struct khoser_mem_chunk *tmp = chunk; chunk = KHOSER_LOAD_PTR(chunk->hdr.next); - kfree(tmp); + free_page((unsigned long)tmp); } } -static int kho_mem_serialize(struct kho_serialization *ser) +/* + * Update memory map property, if old one is found discard it via + * kho_mem_ser_free(). + */ +static void kho_update_memory_map(struct khoser_mem_chunk *first_chunk) +{ + void *ptr; + u64 phys; + + ptr = fdt_getprop_w(kho_out.fdt, 0, PROP_PRESERVED_MEMORY_MAP, NULL); + + /* Check and discard previous memory map */ + phys = get_unaligned((u64 *)ptr); + if (phys) + kho_mem_ser_free((struct khoser_mem_chunk *)phys_to_virt(phys)); + + /* Update with the new value */ + phys = first_chunk ? (u64)virt_to_phys(first_chunk) : 0; + put_unaligned(phys, (u64 *)ptr); +} + +static int kho_mem_serialize(struct kho_out *kho_out) { struct khoser_mem_chunk *first_chunk = NULL; struct khoser_mem_chunk *chunk = NULL; @@ -383,7 +398,7 @@ static int kho_mem_serialize(struct kho_serialization *ser) unsigned long order; int err = -ENOMEM; - xa_for_each(&ser->track.orders, order, physxa) { + xa_for_each(&kho_out->track.orders, order, physxa) { struct kho_mem_phys_bits *bits; unsigned long phys; @@ -415,7 +430,7 @@ static int kho_mem_serialize(struct kho_serialization *ser) } } - ser->preserved_mem_map = first_chunk; + kho_update_memory_map(first_chunk); return 0; @@ -445,20 +460,27 @@ static void __init deserialize_bitmap(unsigned int order, } } -static void __init kho_mem_deserialize(const void *fdt) +/* Return true if memory was deserizlied */ +static bool __init kho_mem_deserialize(const void *fdt) { struct khoser_mem_chunk *chunk; - const phys_addr_t *mem; + const void *mem_ptr; + u64 mem; int len; - mem = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len); - - if (!mem || len != sizeof(*mem)) { + mem_ptr = fdt_getprop(fdt, 0, PROP_PRESERVED_MEMORY_MAP, &len); + if (!mem_ptr || len != sizeof(u64)) { pr_err("failed to get preserved memory bitmaps\n"); - return; + return false; } - chunk = *mem ? phys_to_virt(*mem) : NULL; + mem = get_unaligned((const u64 *)mem_ptr); + chunk = mem ? phys_to_virt(mem) : NULL; + + /* No preserved physical pages were passed, no deserialization */ + if (!chunk) + return false; + while (chunk) { unsigned int i; @@ -467,6 +489,8 @@ static void __init kho_mem_deserialize(const void *fdt) &chunk->bitmaps[i]); chunk = KHOSER_LOAD_PTR(chunk->hdr.next); } + + return true; } /* @@ -674,40 +698,8 @@ err_disable_kho: kho_enable = false; } -struct fdt_debugfs { - struct list_head list; - struct debugfs_blob_wrapper wrapper; - struct dentry *file; -}; - -static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, - const char *name, const void *fdt) -{ - struct fdt_debugfs *f; - struct dentry *file; - - f = kmalloc(sizeof(*f), GFP_KERNEL); - if (!f) - return -ENOMEM; - - f->wrapper.data = (void *)fdt; - f->wrapper.size = fdt_totalsize(fdt); - - file = debugfs_create_blob(name, 0400, dir, &f->wrapper); - if (IS_ERR(file)) { - kfree(f); - return PTR_ERR(file); - } - - f->file = file; - list_add(&f->list, list); - - return 0; -} - /** * kho_add_subtree - record the physical address of a sub FDT in KHO root tree. - * @ser: serialization control object passed by KHO notifiers. * @name: name of the sub tree. * @fdt: the sub tree blob. * @@ -716,38 +708,76 @@ static int kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, * by KHO for the new kernel to retrieve it after kexec. * * A debugfs blob entry is also created at - * ``/sys/kernel/debug/kho/out/sub_fdts/@name``. + * ``/sys/kernel/debug/kho/out/sub_fdts/@name`` when kernel is configured with + * CONFIG_KEXEC_HANDOVER_DEBUGFS * * Return: 0 on success, error code on failure */ -int kho_add_subtree(struct kho_serialization *ser, const char *name, void *fdt) +int kho_add_subtree(const char *name, void *fdt) { - int err = 0; - u64 phys = (u64)virt_to_phys(fdt); - void *root = page_to_virt(ser->fdt); + phys_addr_t phys = virt_to_phys(fdt); + void *root_fdt = kho_out.fdt; + int err = -ENOMEM; + int off, fdt_err; - err |= fdt_begin_node(root, name); - err |= fdt_property(root, PROP_SUB_FDT, &phys, sizeof(phys)); - err |= fdt_end_node(root); + guard(mutex)(&kho_out.lock); - if (err) + fdt_err = fdt_open_into(root_fdt, root_fdt, PAGE_SIZE); + if (fdt_err < 0) return err; - return kho_debugfs_fdt_add(&ser->fdt_list, ser->sub_fdt_dir, name, fdt); + off = fdt_add_subnode(root_fdt, 0, name); + if (off < 0) { + if (off == -FDT_ERR_EXISTS) + err = -EEXIST; + goto out_pack; + } + + err = fdt_setprop(root_fdt, off, PROP_SUB_FDT, &phys, sizeof(phys)); + if (err < 0) + goto out_pack; + + WARN_ON_ONCE(kho_debugfs_fdt_add(&kho_out.dbg, name, fdt, false)); + +out_pack: + fdt_pack(root_fdt); + + return err; } EXPORT_SYMBOL_GPL(kho_add_subtree); -int register_kho_notifier(struct notifier_block *nb) +void kho_remove_subtree(void *fdt) { - return blocking_notifier_chain_register(&kho_out.chain_head, nb); -} -EXPORT_SYMBOL_GPL(register_kho_notifier); + phys_addr_t target_phys = virt_to_phys(fdt); + void *root_fdt = kho_out.fdt; + int off; + int err; -int unregister_kho_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&kho_out.chain_head, nb); + guard(mutex)(&kho_out.lock); + + err = fdt_open_into(root_fdt, root_fdt, PAGE_SIZE); + if (err < 0) + return; + + for (off = fdt_first_subnode(root_fdt, 0); off >= 0; + off = fdt_next_subnode(root_fdt, off)) { + const u64 *val; + int len; + + val = fdt_getprop(root_fdt, off, PROP_SUB_FDT, &len); + if (!val || len != sizeof(phys_addr_t)) + continue; + + if ((phys_addr_t)*val == target_phys) { + fdt_del_node(root_fdt, off); + kho_debugfs_fdt_remove(&kho_out.dbg, fdt); + break; + } + } + + fdt_pack(root_fdt); } -EXPORT_SYMBOL_GPL(unregister_kho_notifier); +EXPORT_SYMBOL_GPL(kho_remove_subtree); /** * kho_preserve_folio - preserve a folio across kexec. @@ -762,7 +792,7 @@ int kho_preserve_folio(struct folio *folio) { const unsigned long pfn = folio_pfn(folio); const unsigned int order = folio_order(folio); - struct kho_mem_track *track = &kho_out.ser.track; + struct kho_mem_track *track = &kho_out.track; if (WARN_ON(kho_scratch_overlap(pfn << PAGE_SHIFT, PAGE_SIZE << order))) return -EINVAL; @@ -771,6 +801,24 @@ int kho_preserve_folio(struct folio *folio) } EXPORT_SYMBOL_GPL(kho_preserve_folio); +/** + * kho_unpreserve_folio - unpreserve a folio. + * @folio: folio to unpreserve. + * + * Instructs KHO to unpreserve a folio that was preserved by + * kho_preserve_folio() before. The provided @folio (pfn and order) + * must exactly match a previously preserved folio. + */ +void kho_unpreserve_folio(struct folio *folio) +{ + const unsigned long pfn = folio_pfn(folio); + const unsigned int order = folio_order(folio); + struct kho_mem_track *track = &kho_out.track; + + __kho_unpreserve_order(track, pfn, order); +} +EXPORT_SYMBOL_GPL(kho_unpreserve_folio); + /** * kho_preserve_pages - preserve contiguous pages across kexec * @page: first page in the list. @@ -783,7 +831,7 @@ EXPORT_SYMBOL_GPL(kho_preserve_folio); */ int kho_preserve_pages(struct page *page, unsigned int nr_pages) { - struct kho_mem_track *track = &kho_out.ser.track; + struct kho_mem_track *track = &kho_out.track; const unsigned long start_pfn = page_to_pfn(page); const unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn = start_pfn; @@ -815,6 +863,26 @@ int kho_preserve_pages(struct page *page, unsigned int nr_pages) } EXPORT_SYMBOL_GPL(kho_preserve_pages); +/** + * kho_unpreserve_pages - unpreserve contiguous pages. + * @page: first page in the list. + * @nr_pages: number of pages. + * + * Instructs KHO to unpreserve @nr_pages contiguous pages starting from @page. + * This must be called with the same @page and @nr_pages as the corresponding + * kho_preserve_pages() call. Unpreserving arbitrary sub-ranges of larger + * preserved blocks is not supported. + */ +void kho_unpreserve_pages(struct page *page, unsigned int nr_pages) +{ + struct kho_mem_track *track = &kho_out.track; + const unsigned long start_pfn = page_to_pfn(page); + const unsigned long end_pfn = start_pfn + nr_pages; + + __kho_unpreserve(track, start_pfn, end_pfn); +} +EXPORT_SYMBOL_GPL(kho_unpreserve_pages); + struct kho_vmalloc_hdr { DECLARE_KHOSER_PTR(next, struct kho_vmalloc_chunk *); }; @@ -885,7 +953,7 @@ err_free: static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk, unsigned short order) { - struct kho_mem_track *track = &kho_out.ser.track; + struct kho_mem_track *track = &kho_out.track; unsigned long pfn = PHYS_PFN(virt_to_phys(chunk)); __kho_unpreserve(track, pfn, pfn + 1); @@ -896,20 +964,6 @@ static void kho_vmalloc_unpreserve_chunk(struct kho_vmalloc_chunk *chunk, } } -static void kho_vmalloc_free_chunks(struct kho_vmalloc *kho_vmalloc) -{ - struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(kho_vmalloc->first); - - while (chunk) { - struct kho_vmalloc_chunk *tmp = chunk; - - kho_vmalloc_unpreserve_chunk(chunk, kho_vmalloc->order); - - chunk = KHOSER_LOAD_PTR(chunk->hdr.next); - free_page((unsigned long)tmp); - } -} - /** * kho_preserve_vmalloc - preserve memory allocated with vmalloc() across kexec * @ptr: pointer to the area in vmalloc address space @@ -971,11 +1025,33 @@ int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation) return 0; err_free: - kho_vmalloc_free_chunks(preservation); + kho_unpreserve_vmalloc(preservation); return err; } EXPORT_SYMBOL_GPL(kho_preserve_vmalloc); +/** + * kho_unpreserve_vmalloc - unpreserve memory allocated with vmalloc() + * @preservation: preservation metadata returned by kho_preserve_vmalloc() + * + * Instructs KHO to unpreserve the area in vmalloc address space that was + * previously preserved with kho_preserve_vmalloc(). + */ +void kho_unpreserve_vmalloc(struct kho_vmalloc *preservation) +{ + struct kho_vmalloc_chunk *chunk = KHOSER_LOAD_PTR(preservation->first); + + while (chunk) { + struct kho_vmalloc_chunk *tmp = chunk; + + kho_vmalloc_unpreserve_chunk(chunk, preservation->order); + + chunk = KHOSER_LOAD_PTR(chunk->hdr.next); + free_page((unsigned long)tmp); + } +} +EXPORT_SYMBOL_GPL(kho_unpreserve_vmalloc); + /** * kho_restore_vmalloc - recreates and populates an area in vmalloc address * space from the preserved memory. @@ -1024,7 +1100,7 @@ void *kho_restore_vmalloc(const struct kho_vmalloc *preservation) goto err_free_pages_array; for (int j = 0; j < contig_pages; j++) - pages[idx++] = page; + pages[idx++] = page + j; phys += contig_pages * PAGE_SIZE; } @@ -1065,217 +1141,122 @@ err_free_pages_array: } EXPORT_SYMBOL_GPL(kho_restore_vmalloc); -/* Handling for debug/kho/out */ - -static struct dentry *debugfs_root; - -static int kho_out_update_debugfs_fdt(void) +/** + * kho_alloc_preserve - Allocate, zero, and preserve memory. + * @size: The number of bytes to allocate. + * + * Allocates a physically contiguous block of zeroed pages that is large + * enough to hold @size bytes. The allocated memory is then registered with + * KHO for preservation across a kexec. + * + * Note: The actual allocated size will be rounded up to the nearest + * power-of-two page boundary. + * + * @return A virtual pointer to the allocated and preserved memory on success, + * or an ERR_PTR() encoded error on failure. + */ +void *kho_alloc_preserve(size_t size) { - int err = 0; - struct fdt_debugfs *ff, *tmp; + struct folio *folio; + int order, ret; - if (kho_out.finalized) { - err = kho_debugfs_fdt_add(&kho_out.ser.fdt_list, kho_out.dir, - "fdt", page_to_virt(kho_out.ser.fdt)); - } else { - list_for_each_entry_safe(ff, tmp, &kho_out.ser.fdt_list, list) { - debugfs_remove(ff->file); - list_del(&ff->list); - kfree(ff); - } + if (!size) + return ERR_PTR(-EINVAL); + + order = get_order(size); + if (order > MAX_PAGE_ORDER) + return ERR_PTR(-E2BIG); + + folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, order); + if (!folio) + return ERR_PTR(-ENOMEM); + + ret = kho_preserve_folio(folio); + if (ret) { + folio_put(folio); + return ERR_PTR(ret); } - return err; + return folio_address(folio); } +EXPORT_SYMBOL_GPL(kho_alloc_preserve); -static int kho_abort(void) +/** + * kho_unpreserve_free - Unpreserve and free memory. + * @mem: Pointer to the memory allocated by kho_alloc_preserve(). + * + * Unregisters the memory from KHO preservation and frees the underlying + * pages back to the system. This function should be called to clean up + * memory allocated with kho_alloc_preserve(). + */ +void kho_unpreserve_free(void *mem) { - int err; - unsigned long order; - struct kho_mem_phys *physxa; + struct folio *folio; - xa_for_each(&kho_out.ser.track.orders, order, physxa) { - struct kho_mem_phys_bits *bits; - unsigned long phys; + if (!mem) + return; - xa_for_each(&physxa->phys_bits, phys, bits) - kfree(bits); - - xa_destroy(&physxa->phys_bits); - kfree(physxa); - } - xa_destroy(&kho_out.ser.track.orders); - - if (kho_out.ser.preserved_mem_map) { - kho_mem_ser_free(kho_out.ser.preserved_mem_map); - kho_out.ser.preserved_mem_map = NULL; - } - - err = blocking_notifier_call_chain(&kho_out.chain_head, KEXEC_KHO_ABORT, - NULL); - err = notifier_to_errno(err); - - if (err) - pr_err("Failed to abort KHO finalization: %d\n", err); - - return err; + folio = virt_to_folio(mem); + kho_unpreserve_folio(folio); + folio_put(folio); } +EXPORT_SYMBOL_GPL(kho_unpreserve_free); -static int kho_finalize(void) +/** + * kho_restore_free - Restore and free memory after kexec. + * @mem: Pointer to the memory (in the new kernel's address space) + * that was allocated by the old kernel. + * + * This function is intended to be called in the new kernel (post-kexec) + * to take ownership of and free a memory region that was preserved by the + * old kernel using kho_alloc_preserve(). + * + * It first restores the pages from KHO (using their physical address) + * and then frees the pages back to the new kernel's page allocator. + */ +void kho_restore_free(void *mem) { - int err = 0; - u64 *preserved_mem_map; - void *fdt = page_to_virt(kho_out.ser.fdt); + struct folio *folio; - err |= fdt_create(fdt, PAGE_SIZE); - err |= fdt_finish_reservemap(fdt); - err |= fdt_begin_node(fdt, ""); - err |= fdt_property_string(fdt, "compatible", KHO_FDT_COMPATIBLE); - /** - * Reserve the preserved-memory-map property in the root FDT, so - * that all property definitions will precede subnodes created by - * KHO callers. - */ - err |= fdt_property_placeholder(fdt, PROP_PRESERVED_MEMORY_MAP, - sizeof(*preserved_mem_map), - (void **)&preserved_mem_map); - if (err) - goto abort; + if (!mem) + return; - err = kho_preserve_folio(page_folio(kho_out.ser.fdt)); - if (err) - goto abort; - - err = blocking_notifier_call_chain(&kho_out.chain_head, - KEXEC_KHO_FINALIZE, &kho_out.ser); - err = notifier_to_errno(err); - if (err) - goto abort; - - err = kho_mem_serialize(&kho_out.ser); - if (err) - goto abort; - - *preserved_mem_map = (u64)virt_to_phys(kho_out.ser.preserved_mem_map); - - err |= fdt_end_node(fdt); - err |= fdt_finish(fdt); - -abort: - if (err) { - pr_err("Failed to convert KHO state tree: %d\n", err); - kho_abort(); - } - - return err; + folio = kho_restore_folio(__pa(mem)); + if (!WARN_ON(!folio)) + folio_put(folio); } +EXPORT_SYMBOL_GPL(kho_restore_free); -static int kho_out_finalize_get(void *data, u64 *val) +int kho_finalize(void) { - mutex_lock(&kho_out.lock); - *val = kho_out.finalized; - mutex_unlock(&kho_out.lock); + int ret; - return 0; -} - -static int kho_out_finalize_set(void *data, u64 _val) -{ - int ret = 0; - bool val = !!_val; - - mutex_lock(&kho_out.lock); - - if (val == kho_out.finalized) { - if (kho_out.finalized) - ret = -EEXIST; - else - ret = -ENOENT; - goto unlock; - } - - if (val) - ret = kho_finalize(); - else - ret = kho_abort(); + if (!kho_enable) + return -EOPNOTSUPP; + guard(mutex)(&kho_out.lock); + ret = kho_mem_serialize(&kho_out); if (ret) - goto unlock; + return ret; - kho_out.finalized = val; - ret = kho_out_update_debugfs_fdt(); - -unlock: - mutex_unlock(&kho_out.lock); - return ret; -} - -DEFINE_DEBUGFS_ATTRIBUTE(fops_kho_out_finalize, kho_out_finalize_get, - kho_out_finalize_set, "%llu\n"); - -static int scratch_phys_show(struct seq_file *m, void *v) -{ - for (int i = 0; i < kho_scratch_cnt; i++) - seq_printf(m, "0x%llx\n", kho_scratch[i].addr); + kho_out.finalized = true; return 0; } -DEFINE_SHOW_ATTRIBUTE(scratch_phys); -static int scratch_len_show(struct seq_file *m, void *v) +bool kho_finalized(void) { - for (int i = 0; i < kho_scratch_cnt; i++) - seq_printf(m, "0x%llx\n", kho_scratch[i].size); - - return 0; -} -DEFINE_SHOW_ATTRIBUTE(scratch_len); - -static __init int kho_out_debugfs_init(void) -{ - struct dentry *dir, *f, *sub_fdt_dir; - - dir = debugfs_create_dir("out", debugfs_root); - if (IS_ERR(dir)) - return -ENOMEM; - - sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); - if (IS_ERR(sub_fdt_dir)) - goto err_rmdir; - - f = debugfs_create_file("scratch_phys", 0400, dir, NULL, - &scratch_phys_fops); - if (IS_ERR(f)) - goto err_rmdir; - - f = debugfs_create_file("scratch_len", 0400, dir, NULL, - &scratch_len_fops); - if (IS_ERR(f)) - goto err_rmdir; - - f = debugfs_create_file("finalize", 0600, dir, NULL, - &fops_kho_out_finalize); - if (IS_ERR(f)) - goto err_rmdir; - - kho_out.dir = dir; - kho_out.ser.sub_fdt_dir = sub_fdt_dir; - return 0; - -err_rmdir: - debugfs_remove_recursive(dir); - return -ENOENT; + guard(mutex)(&kho_out.lock); + return kho_out.finalized; } struct kho_in { - struct dentry *dir; phys_addr_t fdt_phys; phys_addr_t scratch_phys; - struct list_head fdt_list; + struct kho_debugfs dbg; }; static struct kho_in kho_in = { - .fdt_list = LIST_HEAD_INIT(kho_in.fdt_list), }; static const void *kho_get_fdt(void) @@ -1339,91 +1320,52 @@ int kho_retrieve_subtree(const char *name, phys_addr_t *phys) } EXPORT_SYMBOL_GPL(kho_retrieve_subtree); -/* Handling for debugfs/kho/in */ - -static __init int kho_in_debugfs_init(const void *fdt) +static __init int kho_out_fdt_setup(void) { - struct dentry *sub_fdt_dir; - int err, child; + void *root = kho_out.fdt; + u64 empty_mem_map = 0; + int err; - kho_in.dir = debugfs_create_dir("in", debugfs_root); - if (IS_ERR(kho_in.dir)) - return PTR_ERR(kho_in.dir); + err = fdt_create(root, PAGE_SIZE); + err |= fdt_finish_reservemap(root); + err |= fdt_begin_node(root, ""); + err |= fdt_property_string(root, "compatible", KHO_FDT_COMPATIBLE); + err |= fdt_property(root, PROP_PRESERVED_MEMORY_MAP, &empty_mem_map, + sizeof(empty_mem_map)); + err |= fdt_end_node(root); + err |= fdt_finish(root); - sub_fdt_dir = debugfs_create_dir("sub_fdts", kho_in.dir); - if (IS_ERR(sub_fdt_dir)) { - err = PTR_ERR(sub_fdt_dir); - goto err_rmdir; - } - - err = kho_debugfs_fdt_add(&kho_in.fdt_list, kho_in.dir, "fdt", fdt); - if (err) - goto err_rmdir; - - fdt_for_each_subnode(child, fdt, 0) { - int len = 0; - const char *name = fdt_get_name(fdt, child, NULL); - const u64 *fdt_phys; - - fdt_phys = fdt_getprop(fdt, child, "fdt", &len); - if (!fdt_phys) - continue; - if (len != sizeof(*fdt_phys)) { - pr_warn("node `%s`'s prop `fdt` has invalid length: %d\n", - name, len); - continue; - } - err = kho_debugfs_fdt_add(&kho_in.fdt_list, sub_fdt_dir, name, - phys_to_virt(*fdt_phys)); - if (err) { - pr_warn("failed to add fdt `%s` to debugfs: %d\n", name, - err); - continue; - } - } - - return 0; - -err_rmdir: - debugfs_remove_recursive(kho_in.dir); return err; } static __init int kho_init(void) { - int err = 0; const void *fdt = kho_get_fdt(); + int err = 0; if (!kho_enable) return 0; - kho_out.ser.fdt = alloc_page(GFP_KERNEL); - if (!kho_out.ser.fdt) { - err = -ENOMEM; + kho_out.fdt = kho_alloc_preserve(PAGE_SIZE); + if (IS_ERR(kho_out.fdt)) { + err = PTR_ERR(kho_out.fdt); goto err_free_scratch; } - debugfs_root = debugfs_create_dir("kho", NULL); - if (IS_ERR(debugfs_root)) { - err = -ENOENT; + err = kho_debugfs_init(); + if (err) goto err_free_fdt; - } - err = kho_out_debugfs_init(); + err = kho_out_debugfs_init(&kho_out.dbg); + if (err) + goto err_free_fdt; + + err = kho_out_fdt_setup(); if (err) goto err_free_fdt; if (fdt) { - err = kho_in_debugfs_init(fdt); - /* - * Failure to create /sys/kernel/debug/kho/in does not prevent - * reviving state from KHO and setting up KHO for the next - * kexec. - */ - if (err) - pr_err("failed exposing handover FDT in debugfs: %d\n", - err); - + kho_in_debugfs_init(&kho_in.dbg, fdt); return 0; } @@ -1432,17 +1374,29 @@ static __init int kho_init(void) unsigned long count = kho_scratch[i].size >> PAGE_SHIFT; unsigned long pfn; + /* + * When debug_pagealloc is enabled, __free_pages() clears the + * corresponding PRESENT bit in the kernel page table. + * Subsequent kmemleak scans of these pages cause the + * non-PRESENT page faults. + * Mark scratch areas with kmemleak_ignore_phys() to exclude + * them from kmemleak scanning. + */ + kmemleak_ignore_phys(kho_scratch[i].addr); for (pfn = base_pfn; pfn < base_pfn + count; pfn += pageblock_nr_pages) init_cma_reserved_pageblock(pfn_to_page(pfn)); } + WARN_ON_ONCE(kho_debugfs_fdt_add(&kho_out.dbg, "fdt", + kho_out.fdt, true)); + return 0; err_free_fdt: - put_page(kho_out.ser.fdt); - kho_out.ser.fdt = NULL; + kho_unpreserve_free(kho_out.fdt); err_free_scratch: + kho_out.fdt = NULL; for (int i = 0; i < kho_scratch_cnt; i++) { void *start = __va(kho_scratch[i].addr); void *end = start + kho_scratch[i].size; @@ -1452,7 +1406,7 @@ err_free_scratch: kho_enable = false; return err; } -late_initcall(kho_init); +fs_initcall(kho_init); static void __init kho_release_scratch(void) { @@ -1480,16 +1434,12 @@ static void __init kho_release_scratch(void) void __init kho_memory_init(void) { - struct folio *folio; - if (kho_in.scratch_phys) { kho_scratch = phys_to_virt(kho_in.scratch_phys); kho_release_scratch(); - kho_mem_deserialize(kho_get_fdt()); - folio = kho_restore_folio(kho_in.fdt_phys); - if (!folio) - pr_warn("failed to restore folio for KHO fdt\n"); + if (!kho_mem_deserialize(kho_get_fdt())) + kho_in.fdt_phys = 0; } else { kho_reserve_scratch(); } @@ -1545,8 +1495,8 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, memblock_add(area->addr, size); err = memblock_mark_kho_scratch(area->addr, size); if (WARN_ON(err)) { - pr_warn("failed to mark the scratch region 0x%pa+0x%pa: %d", - &area->addr, &size, err); + pr_warn("failed to mark the scratch region 0x%pa+0x%pa: %pe", + &area->addr, &size, ERR_PTR(err)); goto out; } pr_debug("Marked 0x%pa+0x%pa as scratch", &area->addr, &size); @@ -1566,7 +1516,7 @@ void __init kho_populate(phys_addr_t fdt_phys, u64 fdt_len, kho_in.fdt_phys = fdt_phys; kho_in.scratch_phys = scratch_phys; kho_scratch_cnt = scratch_cnt; - pr_info("found kexec handover data. Will skip init for some devices\n"); + pr_info("found kexec handover data.\n"); out: if (fdt) @@ -1585,10 +1535,10 @@ int kho_fill_kimage(struct kimage *image) int err = 0; struct kexec_buf scratch; - if (!kho_out.finalized) + if (!kho_enable) return 0; - image->kho.fdt = page_to_phys(kho_out.ser.fdt); + image->kho.fdt = virt_to_phys(kho_out.fdt); scratch_size = sizeof(*kho_scratch) * kho_scratch_cnt; scratch = (struct kexec_buf){ diff --git a/kernel/kexec_handover_debug.c b/kernel/liveupdate/kexec_handover_debug.c similarity index 100% rename from kernel/kexec_handover_debug.c rename to kernel/liveupdate/kexec_handover_debug.c diff --git a/kernel/liveupdate/kexec_handover_debugfs.c b/kernel/liveupdate/kexec_handover_debugfs.c new file mode 100644 index 000000000000..2abbf62ba942 --- /dev/null +++ b/kernel/liveupdate/kexec_handover_debugfs.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_handover_debugfs.c - kexec handover debugfs interfaces + * Copyright (C) 2023 Alexander Graf + * Copyright (C) 2025 Microsoft Corporation, Mike Rapoport + * Copyright (C) 2025 Google LLC, Changyuan Lyu + * Copyright (C) 2025 Google LLC, Pasha Tatashin + */ + +#define pr_fmt(fmt) "KHO: " fmt + +#include +#include +#include +#include +#include "kexec_handover_internal.h" + +static struct dentry *debugfs_root; + +struct fdt_debugfs { + struct list_head list; + struct debugfs_blob_wrapper wrapper; + struct dentry *file; +}; + +static int __kho_debugfs_fdt_add(struct list_head *list, struct dentry *dir, + const char *name, const void *fdt) +{ + struct fdt_debugfs *f; + struct dentry *file; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return -ENOMEM; + + f->wrapper.data = (void *)fdt; + f->wrapper.size = fdt_totalsize(fdt); + + file = debugfs_create_blob(name, 0400, dir, &f->wrapper); + if (IS_ERR(file)) { + kfree(f); + return PTR_ERR(file); + } + + f->file = file; + list_add(&f->list, list); + + return 0; +} + +int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root) +{ + struct dentry *dir; + + if (root) + dir = dbg->dir; + else + dir = dbg->sub_fdt_dir; + + return __kho_debugfs_fdt_add(&dbg->fdt_list, dir, name, fdt); +} + +void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt) +{ + struct fdt_debugfs *ff; + + list_for_each_entry(ff, &dbg->fdt_list, list) { + if (ff->wrapper.data == fdt) { + debugfs_remove(ff->file); + list_del(&ff->list); + kfree(ff); + break; + } + } +} + +static int kho_out_finalize_get(void *data, u64 *val) +{ + *val = kho_finalized(); + + return 0; +} + +static int kho_out_finalize_set(void *data, u64 val) +{ + if (val) + return kho_finalize(); + else + return -EINVAL; +} + +DEFINE_DEBUGFS_ATTRIBUTE(kho_out_finalize_fops, kho_out_finalize_get, + kho_out_finalize_set, "%llu\n"); + +static int scratch_phys_show(struct seq_file *m, void *v) +{ + for (int i = 0; i < kho_scratch_cnt; i++) + seq_printf(m, "0x%llx\n", kho_scratch[i].addr); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(scratch_phys); + +static int scratch_len_show(struct seq_file *m, void *v) +{ + for (int i = 0; i < kho_scratch_cnt; i++) + seq_printf(m, "0x%llx\n", kho_scratch[i].size); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(scratch_len); + +__init void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt) +{ + struct dentry *dir, *sub_fdt_dir; + int err, child; + + INIT_LIST_HEAD(&dbg->fdt_list); + + dir = debugfs_create_dir("in", debugfs_root); + if (IS_ERR(dir)) { + err = PTR_ERR(dir); + goto err_out; + } + + sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); + if (IS_ERR(sub_fdt_dir)) { + err = PTR_ERR(sub_fdt_dir); + goto err_rmdir; + } + + err = __kho_debugfs_fdt_add(&dbg->fdt_list, dir, "fdt", fdt); + if (err) + goto err_rmdir; + + fdt_for_each_subnode(child, fdt, 0) { + int len = 0; + const char *name = fdt_get_name(fdt, child, NULL); + const u64 *fdt_phys; + + fdt_phys = fdt_getprop(fdt, child, "fdt", &len); + if (!fdt_phys) + continue; + if (len != sizeof(*fdt_phys)) { + pr_warn("node %s prop fdt has invalid length: %d\n", + name, len); + continue; + } + err = __kho_debugfs_fdt_add(&dbg->fdt_list, sub_fdt_dir, name, + phys_to_virt(*fdt_phys)); + if (err) { + pr_warn("failed to add fdt %s to debugfs: %pe\n", name, + ERR_PTR(err)); + continue; + } + } + + dbg->dir = dir; + dbg->sub_fdt_dir = sub_fdt_dir; + + return; +err_rmdir: + debugfs_remove_recursive(dir); +err_out: + /* + * Failure to create /sys/kernel/debug/kho/in does not prevent + * reviving state from KHO and setting up KHO for the next + * kexec. + */ + if (err) { + pr_err("failed exposing handover FDT in debugfs: %pe\n", + ERR_PTR(err)); + } +} + +__init int kho_out_debugfs_init(struct kho_debugfs *dbg) +{ + struct dentry *dir, *f, *sub_fdt_dir; + + INIT_LIST_HEAD(&dbg->fdt_list); + + dir = debugfs_create_dir("out", debugfs_root); + if (IS_ERR(dir)) + return -ENOMEM; + + sub_fdt_dir = debugfs_create_dir("sub_fdts", dir); + if (IS_ERR(sub_fdt_dir)) + goto err_rmdir; + + f = debugfs_create_file("scratch_phys", 0400, dir, NULL, + &scratch_phys_fops); + if (IS_ERR(f)) + goto err_rmdir; + + f = debugfs_create_file("scratch_len", 0400, dir, NULL, + &scratch_len_fops); + if (IS_ERR(f)) + goto err_rmdir; + + f = debugfs_create_file("finalize", 0600, dir, NULL, + &kho_out_finalize_fops); + if (IS_ERR(f)) + goto err_rmdir; + + dbg->dir = dir; + dbg->sub_fdt_dir = sub_fdt_dir; + return 0; + +err_rmdir: + debugfs_remove_recursive(dir); + return -ENOENT; +} + +__init int kho_debugfs_init(void) +{ + debugfs_root = debugfs_create_dir("kho", NULL); + if (IS_ERR(debugfs_root)) + return -ENOENT; + return 0; +} diff --git a/kernel/liveupdate/kexec_handover_internal.h b/kernel/liveupdate/kexec_handover_internal.h new file mode 100644 index 000000000000..0202c85ad14f --- /dev/null +++ b/kernel/liveupdate/kexec_handover_internal.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_KEXEC_HANDOVER_INTERNAL_H +#define LINUX_KEXEC_HANDOVER_INTERNAL_H + +#include +#include +#include + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS +#include + +struct kho_debugfs { + struct dentry *dir; + struct dentry *sub_fdt_dir; + struct list_head fdt_list; +}; + +#else +struct kho_debugfs {}; +#endif + +extern struct kho_scratch *kho_scratch; +extern unsigned int kho_scratch_cnt; + +bool kho_finalized(void); +int kho_finalize(void); + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUGFS +int kho_debugfs_init(void); +void kho_in_debugfs_init(struct kho_debugfs *dbg, const void *fdt); +int kho_out_debugfs_init(struct kho_debugfs *dbg); +int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root); +void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, void *fdt); +#else +static inline int kho_debugfs_init(void) { return 0; } +static inline void kho_in_debugfs_init(struct kho_debugfs *dbg, + const void *fdt) { } +static inline int kho_out_debugfs_init(struct kho_debugfs *dbg) { return 0; } +static inline int kho_debugfs_fdt_add(struct kho_debugfs *dbg, const char *name, + const void *fdt, bool root) { return 0; } +static inline void kho_debugfs_fdt_remove(struct kho_debugfs *dbg, + void *fdt) { } +#endif /* CONFIG_KEXEC_HANDOVER_DEBUGFS */ + +#ifdef CONFIG_KEXEC_HANDOVER_DEBUG +bool kho_scratch_overlap(phys_addr_t phys, size_t size); +#else +static inline bool kho_scratch_overlap(phys_addr_t phys, size_t size) +{ + return false; +} +#endif /* CONFIG_KEXEC_HANDOVER_DEBUG */ + +#endif /* LINUX_KEXEC_HANDOVER_INTERNAL_H */ diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c new file mode 100644 index 000000000000..f7ecaf7740d1 --- /dev/null +++ b/kernel/liveupdate/luo_core.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +/** + * DOC: Live Update Orchestrator (LUO) + * + * Live Update is a specialized, kexec-based reboot process that allows a + * running kernel to be updated from one version to another while preserving + * the state of selected resources and keeping designated hardware devices + * operational. For these devices, DMA activity may continue throughout the + * kernel transition. + * + * While the primary use case driving this work is supporting live updates of + * the Linux kernel when it is used as a hypervisor in cloud environments, the + * LUO framework itself is designed to be workload-agnostic. Live Update + * facilitates a full kernel version upgrade for any type of system. + * + * For example, a non-hypervisor system running an in-memory cache like + * memcached with many gigabytes of data can use LUO. The userspace service + * can place its cache into a memfd, have its state preserved by LUO, and + * restore it immediately after the kernel kexec. + * + * Whether the system is running virtual machines, containers, a + * high-performance database, or networking services, LUO's primary goal is to + * enable a full kernel update by preserving critical userspace state and + * keeping essential devices operational. + * + * The core of LUO is a mechanism that tracks the progress of a live update, + * along with a callback API that allows other kernel subsystems to participate + * in the process. Example subsystems that can hook into LUO include: kvm, + * iommu, interrupts, vfio, participating filesystems, and memory management. + * + * LUO uses Kexec Handover to transfer memory state from the current kernel to + * the next kernel. For more details see + * Documentation/core-api/kho/concepts.rst. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "kexec_handover_internal.h" +#include "luo_internal.h" + +static struct { + bool enabled; + void *fdt_out; + void *fdt_in; + u64 liveupdate_num; +} luo_global; + +static int __init early_liveupdate_param(char *buf) +{ + return kstrtobool(buf, &luo_global.enabled); +} +early_param("liveupdate", early_liveupdate_param); + +static int __init luo_early_startup(void) +{ + phys_addr_t fdt_phys; + int err, ln_size; + const void *ptr; + + if (!kho_is_enabled()) { + if (liveupdate_enabled()) + pr_warn("Disabling liveupdate because KHO is disabled\n"); + luo_global.enabled = false; + return 0; + } + + /* Retrieve LUO subtree, and verify its format. */ + err = kho_retrieve_subtree(LUO_FDT_KHO_ENTRY_NAME, &fdt_phys); + if (err) { + if (err != -ENOENT) { + pr_err("failed to retrieve FDT '%s' from KHO: %pe\n", + LUO_FDT_KHO_ENTRY_NAME, ERR_PTR(err)); + return err; + } + + return 0; + } + + luo_global.fdt_in = phys_to_virt(fdt_phys); + err = fdt_node_check_compatible(luo_global.fdt_in, 0, + LUO_FDT_COMPATIBLE); + if (err) { + pr_err("FDT '%s' is incompatible with '%s' [%d]\n", + LUO_FDT_KHO_ENTRY_NAME, LUO_FDT_COMPATIBLE, err); + + return -EINVAL; + } + + ln_size = 0; + ptr = fdt_getprop(luo_global.fdt_in, 0, LUO_FDT_LIVEUPDATE_NUM, + &ln_size); + if (!ptr || ln_size != sizeof(luo_global.liveupdate_num)) { + pr_err("Unable to get live update number '%s' [%d]\n", + LUO_FDT_LIVEUPDATE_NUM, ln_size); + + return -EINVAL; + } + + luo_global.liveupdate_num = get_unaligned((u64 *)ptr); + pr_info("Retrieved live update data, liveupdate number: %lld\n", + luo_global.liveupdate_num); + + err = luo_session_setup_incoming(luo_global.fdt_in); + if (err) + return err; + + return 0; +} + +static int __init liveupdate_early_init(void) +{ + int err; + + err = luo_early_startup(); + if (err) { + luo_global.enabled = false; + luo_restore_fail("The incoming tree failed to initialize properly [%pe], disabling live update\n", + ERR_PTR(err)); + } + + return err; +} +early_initcall(liveupdate_early_init); + +/* Called during boot to create outgoing LUO fdt tree */ +static int __init luo_fdt_setup(void) +{ + const u64 ln = luo_global.liveupdate_num + 1; + void *fdt_out; + int err; + + fdt_out = kho_alloc_preserve(LUO_FDT_SIZE); + if (IS_ERR(fdt_out)) { + pr_err("failed to allocate/preserve FDT memory\n"); + return PTR_ERR(fdt_out); + } + + err = fdt_create(fdt_out, LUO_FDT_SIZE); + err |= fdt_finish_reservemap(fdt_out); + err |= fdt_begin_node(fdt_out, ""); + err |= fdt_property_string(fdt_out, "compatible", LUO_FDT_COMPATIBLE); + err |= fdt_property(fdt_out, LUO_FDT_LIVEUPDATE_NUM, &ln, sizeof(ln)); + err |= luo_session_setup_outgoing(fdt_out); + err |= fdt_end_node(fdt_out); + err |= fdt_finish(fdt_out); + if (err) + goto exit_free; + + err = kho_add_subtree(LUO_FDT_KHO_ENTRY_NAME, fdt_out); + if (err) + goto exit_free; + luo_global.fdt_out = fdt_out; + + return 0; + +exit_free: + kho_unpreserve_free(fdt_out); + pr_err("failed to prepare LUO FDT: %d\n", err); + + return err; +} + +/* + * late initcall because it initializes the outgoing tree that is needed only + * once userspace starts using /dev/liveupdate. + */ +static int __init luo_late_startup(void) +{ + int err; + + if (!liveupdate_enabled()) + return 0; + + err = luo_fdt_setup(); + if (err) + luo_global.enabled = false; + + return err; +} +late_initcall(luo_late_startup); + +/* Public Functions */ + +/** + * liveupdate_reboot() - Kernel reboot notifier for live update final + * serialization. + * + * This function is invoked directly from the reboot() syscall pathway + * if kexec is in progress. + * + * If any callback fails, this function aborts KHO, undoes the freeze() + * callbacks, and returns an error. + */ +int liveupdate_reboot(void) +{ + int err; + + if (!liveupdate_enabled()) + return 0; + + err = luo_session_serialize(); + if (err) + return err; + + err = kho_finalize(); + if (err) { + pr_err("kho_finalize failed %d\n", err); + /* + * kho_finalize() may return libfdt errors, to aboid passing to + * userspace unknown errors, change this to EAGAIN. + */ + err = -EAGAIN; + } + + return err; +} + +/** + * liveupdate_enabled - Check if the live update feature is enabled. + * + * This function returns the state of the live update feature flag, which + * can be controlled via the ``liveupdate`` kernel command-line parameter. + * + * @return true if live update is enabled, false otherwise. + */ +bool liveupdate_enabled(void) +{ + return luo_global.enabled; +} + +/** + * DOC: LUO ioctl Interface + * + * The IOCTL user-space control interface for the LUO subsystem. + * It registers a character device, typically found at ``/dev/liveupdate``, + * which allows a userspace agent to manage the LUO state machine and its + * associated resources, such as preservable file descriptors. + * + * To ensure that the state machine is controlled by a single entity, access + * to this device is exclusive: only one process is permitted to have + * ``/dev/liveupdate`` open at any given time. Subsequent open attempts will + * fail with -EBUSY until the first process closes its file descriptor. + * This singleton model simplifies state management by preventing conflicting + * commands from multiple userspace agents. + */ + +struct luo_device_state { + struct miscdevice miscdev; + atomic_t in_use; +}; + +static int luo_ioctl_create_session(struct luo_ucmd *ucmd) +{ + struct liveupdate_ioctl_create_session *argp = ucmd->cmd; + struct file *file; + int err; + + argp->fd = get_unused_fd_flags(O_CLOEXEC); + if (argp->fd < 0) + return argp->fd; + + err = luo_session_create(argp->name, &file); + if (err) + goto err_put_fd; + + err = luo_ucmd_respond(ucmd, sizeof(*argp)); + if (err) + goto err_put_file; + + fd_install(argp->fd, file); + + return 0; + +err_put_file: + fput(file); +err_put_fd: + put_unused_fd(argp->fd); + + return err; +} + +static int luo_ioctl_retrieve_session(struct luo_ucmd *ucmd) +{ + struct liveupdate_ioctl_retrieve_session *argp = ucmd->cmd; + struct file *file; + int err; + + argp->fd = get_unused_fd_flags(O_CLOEXEC); + if (argp->fd < 0) + return argp->fd; + + err = luo_session_retrieve(argp->name, &file); + if (err < 0) + goto err_put_fd; + + err = luo_ucmd_respond(ucmd, sizeof(*argp)); + if (err) + goto err_put_file; + + fd_install(argp->fd, file); + + return 0; + +err_put_file: + fput(file); +err_put_fd: + put_unused_fd(argp->fd); + + return err; +} + +static int luo_open(struct inode *inodep, struct file *filep) +{ + struct luo_device_state *ldev = container_of(filep->private_data, + struct luo_device_state, + miscdev); + + if (atomic_cmpxchg(&ldev->in_use, 0, 1)) + return -EBUSY; + + /* Always return -EIO to user if deserialization fail */ + if (luo_session_deserialize()) { + atomic_set(&ldev->in_use, 0); + return -EIO; + } + + return 0; +} + +static int luo_release(struct inode *inodep, struct file *filep) +{ + struct luo_device_state *ldev = container_of(filep->private_data, + struct luo_device_state, + miscdev); + atomic_set(&ldev->in_use, 0); + + return 0; +} + +union ucmd_buffer { + struct liveupdate_ioctl_create_session create; + struct liveupdate_ioctl_retrieve_session retrieve; +}; + +struct luo_ioctl_op { + unsigned int size; + unsigned int min_size; + unsigned int ioctl_num; + int (*execute)(struct luo_ucmd *ucmd); +}; + +#define IOCTL_OP(_ioctl, _fn, _struct, _last) \ + [_IOC_NR(_ioctl) - LIVEUPDATE_CMD_BASE] = { \ + .size = sizeof(_struct) + \ + BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) < \ + sizeof(_struct)), \ + .min_size = offsetofend(_struct, _last), \ + .ioctl_num = _ioctl, \ + .execute = _fn, \ + } + +static const struct luo_ioctl_op luo_ioctl_ops[] = { + IOCTL_OP(LIVEUPDATE_IOCTL_CREATE_SESSION, luo_ioctl_create_session, + struct liveupdate_ioctl_create_session, name), + IOCTL_OP(LIVEUPDATE_IOCTL_RETRIEVE_SESSION, luo_ioctl_retrieve_session, + struct liveupdate_ioctl_retrieve_session, name), +}; + +static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) +{ + const struct luo_ioctl_op *op; + struct luo_ucmd ucmd = {}; + union ucmd_buffer buf; + unsigned int nr; + int err; + + nr = _IOC_NR(cmd); + if (nr < LIVEUPDATE_CMD_BASE || + (nr - LIVEUPDATE_CMD_BASE) >= ARRAY_SIZE(luo_ioctl_ops)) { + return -EINVAL; + } + + ucmd.ubuffer = (void __user *)arg; + err = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); + if (err) + return err; + + op = &luo_ioctl_ops[nr - LIVEUPDATE_CMD_BASE]; + if (op->ioctl_num != cmd) + return -ENOIOCTLCMD; + if (ucmd.user_size < op->min_size) + return -EINVAL; + + ucmd.cmd = &buf; + err = copy_struct_from_user(ucmd.cmd, op->size, ucmd.ubuffer, + ucmd.user_size); + if (err) + return err; + + return op->execute(&ucmd); +} + +static const struct file_operations luo_fops = { + .owner = THIS_MODULE, + .open = luo_open, + .release = luo_release, + .unlocked_ioctl = luo_ioctl, +}; + +static struct luo_device_state luo_dev = { + .miscdev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "liveupdate", + .fops = &luo_fops, + }, + .in_use = ATOMIC_INIT(0), +}; + +static int __init liveupdate_ioctl_init(void) +{ + if (!liveupdate_enabled()) + return 0; + + return misc_register(&luo_dev.miscdev); +} +late_initcall(liveupdate_ioctl_init); diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c new file mode 100644 index 000000000000..ddff87917b21 --- /dev/null +++ b/kernel/liveupdate/luo_file.c @@ -0,0 +1,889 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +/** + * DOC: LUO File Descriptors + * + * LUO provides the infrastructure to preserve specific, stateful file + * descriptors across a kexec-based live update. The primary goal is to allow + * workloads, such as virtual machines using vfio, memfd, or iommufd, to + * retain access to their essential resources without interruption. + * + * The framework is built around a callback-based handler model and a well- + * defined lifecycle for each preserved file. + * + * Handler Registration: + * Kernel modules responsible for a specific file type (e.g., memfd, vfio) + * register a &struct liveupdate_file_handler. This handler provides a set of + * callbacks that LUO invokes at different stages of the update process, most + * notably: + * + * - can_preserve(): A lightweight check to determine if the handler is + * compatible with a given 'struct file'. + * - preserve(): The heavyweight operation that saves the file's state and + * returns an opaque u64 handle. This is typically performed while the + * workload is still active to minimize the downtime during the + * actual reboot transition. + * - unpreserve(): Cleans up any resources allocated by .preserve(), called + * if the preservation process is aborted before the reboot (i.e. session is + * closed). + * - freeze(): A final pre-reboot opportunity to prepare the state for kexec. + * We are already in reboot syscall, and therefore userspace cannot mutate + * the file anymore. + * - unfreeze(): Undoes the actions of .freeze(), called if the live update + * is aborted after the freeze phase. + * - retrieve(): Reconstructs the file in the new kernel from the preserved + * handle. + * - finish(): Performs final check and cleanup in the new kernel. After + * succesul finish call, LUO gives up ownership to this file. + * + * File Preservation Lifecycle happy path: + * + * 1. Preserve (Normal Operation): A userspace agent preserves files one by one + * via an ioctl. For each file, luo_preserve_file() finds a compatible + * handler, calls its .preserve() operation, and creates an internal &struct + * luo_file to track the live state. + * + * 2. Freeze (Pre-Reboot): Just before the kexec, luo_file_freeze() is called. + * It iterates through all preserved files, calls their respective .freeze() + * operation, and serializes their final metadata (compatible string, token, + * and data handle) into a contiguous memory block for KHO. + * + * 3. Deserialize: After kexec, luo_file_deserialize() runs when session gets + * deserialized (which is when /dev/liveupdate is first opened). It reads the + * serialized data from the KHO memory region and reconstructs the in-memory + * list of &struct luo_file instances for the new kernel, linking them to + * their corresponding handlers. + * + * 4. Retrieve (New Kernel - Userspace Ready): The userspace agent can now + * restore file descriptors by providing a token. luo_retrieve_file() + * searches for the matching token, calls the handler's .retrieve() op to + * re-create the 'struct file', and returns a new FD. Files can be + * retrieved in ANY order. + * + * 5. Finish (New Kernel - Cleanup): Once a session retrival is complete, + * luo_file_finish() is called. It iterates through all files, invokes their + * .finish() operations for final cleanup, and releases all associated kernel + * resources. + * + * File Preservation Lifecycle unhappy paths: + * + * 1. Abort Before Reboot: If the userspace agent aborts the live update + * process before calling reboot (e.g., by closing the session file + * descriptor), the session's release handler calls + * luo_file_unpreserve_files(). This invokes the .unpreserve() callback on + * all preserved files, ensuring all allocated resources are cleaned up and + * returning the system to a clean state. + * + * 2. Freeze Failure: During the reboot() syscall, if any handler's .freeze() + * op fails, the .unfreeze() op is invoked on all previously *successful* + * freezes to roll back their state. The reboot() syscall then returns an + * error to userspace, canceling the live update. + * + * 3. Finish Failure: In the new kernel, if a handler's .finish() op fails, + * the luo_file_finish() operation is aborted. LUO retains ownership of + * all files within that session, including those that were not yet + * processed. The userspace agent can attempt to call the finish operation + * again later. If the issue cannot be resolved, these resources will be held + * by LUO until the next live update cycle, at which point they will be + * discarded. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "luo_internal.h" + +static LIST_HEAD(luo_file_handler_list); + +/* 2 4K pages, give space for 128 files per file_set */ +#define LUO_FILE_PGCNT 2ul +#define LUO_FILE_MAX \ + ((LUO_FILE_PGCNT << PAGE_SHIFT) / sizeof(struct luo_file_ser)) + +/** + * struct luo_file - Represents a single preserved file instance. + * @fh: Pointer to the &struct liveupdate_file_handler that manages + * this type of file. + * @file: Pointer to the kernel's &struct file that is being preserved. + * This is NULL in the new kernel until the file is successfully + * retrieved. + * @serialized_data: The opaque u64 handle to the serialized state of the file. + * This handle is passed back to the handler's .freeze(), + * .retrieve(), and .finish() callbacks, allowing it to track + * and update its serialized state across phases. + * @private_data: Pointer to the private data for the file used to hold runtime + * state that is not preserved. Set by the handler's .preserve() + * callback, and must be freed in the handler's .unpreserve() + * callback. + * @retrieved: A flag indicating whether a user/kernel in the new kernel has + * successfully called retrieve() on this file. This prevents + * multiple retrieval attempts. + * @mutex: A mutex that protects the fields of this specific instance + * (e.g., @retrieved, @file), ensuring that operations like + * retrieving or finishing a file are atomic. + * @list: The list_head linking this instance into its parent + * file_set's list of preserved files. + * @token: The user-provided unique token used to identify this file. + * + * This structure is the core in-kernel representation of a single file being + * managed through a live update. An instance is created by luo_preserve_file() + * to link a 'struct file' to its corresponding handler, a user-provided token, + * and the serialized state handle returned by the handler's .preserve() + * operation. + * + * These instances are tracked in a per-file_set list. The @serialized_data + * field, which holds a handle to the file's serialized state, may be updated + * during the .freeze() callback before being serialized for the next kernel. + * After reboot, these structures are recreated by luo_file_deserialize() and + * are finally cleaned up by luo_file_finish(). + */ +struct luo_file { + struct liveupdate_file_handler *fh; + struct file *file; + u64 serialized_data; + void *private_data; + bool retrieved; + struct mutex mutex; + struct list_head list; + u64 token; +}; + +static int luo_alloc_files_mem(struct luo_file_set *file_set) +{ + size_t size; + void *mem; + + if (file_set->files) + return 0; + + WARN_ON_ONCE(file_set->count); + + size = LUO_FILE_PGCNT << PAGE_SHIFT; + mem = kho_alloc_preserve(size); + if (IS_ERR(mem)) + return PTR_ERR(mem); + + file_set->files = mem; + + return 0; +} + +static void luo_free_files_mem(struct luo_file_set *file_set) +{ + /* If file_set has files, no need to free preservation memory */ + if (file_set->count) + return; + + if (!file_set->files) + return; + + kho_unpreserve_free(file_set->files); + file_set->files = NULL; +} + +static bool luo_token_is_used(struct luo_file_set *file_set, u64 token) +{ + struct luo_file *iter; + + list_for_each_entry(iter, &file_set->files_list, list) { + if (iter->token == token) + return true; + } + + return false; +} + +/** + * luo_preserve_file - Initiate the preservation of a file descriptor. + * @file_set: The file_set to which the preserved file will be added. + * @token: A unique, user-provided identifier for the file. + * @fd: The file descriptor to be preserved. + * + * This function orchestrates the first phase of preserving a file. Upon entry, + * it takes a reference to the 'struct file' via fget(), effectively making LUO + * a co-owner of the file. This reference is held until the file is either + * unpreserved or successfully finished in the next kernel, preventing the file + * from being prematurely destroyed. + * + * This function orchestrates the first phase of preserving a file. It performs + * the following steps: + * + * 1. Validates that the @token is not already in use within the file_set. + * 2. Ensures the file_set's memory for files serialization is allocated + * (allocates if needed). + * 3. Iterates through registered handlers, calling can_preserve() to find one + * compatible with the given @fd. + * 4. Calls the handler's .preserve() operation, which saves the file's state + * and returns an opaque private data handle. + * 5. Adds the new instance to the file_set's internal list. + * + * On success, LUO takes a reference to the 'struct file' and considers it + * under its management until it is unpreserved or finished. + * + * In case of any failure, all intermediate allocations (file reference, memory + * for the 'luo_file' struct, etc.) are cleaned up before returning an error. + * + * Context: Can be called from an ioctl handler during normal system operation. + * Return: 0 on success. Returns a negative errno on failure: + * -EEXIST if the token is already used. + * -EBADF if the file descriptor is invalid. + * -ENOSPC if the file_set is full. + * -ENOENT if no compatible handler is found. + * -ENOMEM on memory allocation failure. + * Other erros might be returned by .preserve(). + */ +int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd) +{ + struct liveupdate_file_op_args args = {0}; + struct liveupdate_file_handler *fh; + struct luo_file *luo_file; + struct file *file; + int err; + + if (luo_token_is_used(file_set, token)) + return -EEXIST; + + if (file_set->count == LUO_FILE_MAX) + return -ENOSPC; + + file = fget(fd); + if (!file) + return -EBADF; + + err = luo_alloc_files_mem(file_set); + if (err) + goto err_fput; + + err = -ENOENT; + luo_list_for_each_private(fh, &luo_file_handler_list, list) { + if (fh->ops->can_preserve(fh, file)) { + err = 0; + break; + } + } + + /* err is still -ENOENT if no handler was found */ + if (err) + goto err_free_files_mem; + + luo_file = kzalloc(sizeof(*luo_file), GFP_KERNEL); + if (!luo_file) { + err = -ENOMEM; + goto err_free_files_mem; + } + + luo_file->file = file; + luo_file->fh = fh; + luo_file->token = token; + luo_file->retrieved = false; + mutex_init(&luo_file->mutex); + + args.handler = fh; + args.file = file; + err = fh->ops->preserve(&args); + if (err) + goto err_kfree; + + luo_file->serialized_data = args.serialized_data; + luo_file->private_data = args.private_data; + list_add_tail(&luo_file->list, &file_set->files_list); + file_set->count++; + + return 0; + +err_kfree: + kfree(luo_file); +err_free_files_mem: + luo_free_files_mem(file_set); +err_fput: + fput(file); + + return err; +} + +/** + * luo_file_unpreserve_files - Unpreserves all files from a file_set. + * @file_set: The files to be cleaned up. + * + * This function serves as the primary cleanup path for a file_set. It is + * invoked when the userspace agent closes the file_set's file descriptor. + * + * For each file, it performs the following cleanup actions: + * 1. Calls the handler's .unpreserve() callback to allow the handler to + * release any resources it allocated. + * 2. Removes the file from the file_set's internal tracking list. + * 3. Releases the reference to the 'struct file' that was taken by + * luo_preserve_file() via fput(), returning ownership. + * 4. Frees the memory associated with the internal 'struct luo_file'. + * + * After all individual files are unpreserved, it frees the contiguous memory + * block that was allocated to hold their serialization data. + */ +void luo_file_unpreserve_files(struct luo_file_set *file_set) +{ + struct luo_file *luo_file; + + while (!list_empty(&file_set->files_list)) { + struct liveupdate_file_op_args args = {0}; + + luo_file = list_last_entry(&file_set->files_list, + struct luo_file, list); + + args.handler = luo_file->fh; + args.file = luo_file->file; + args.serialized_data = luo_file->serialized_data; + args.private_data = luo_file->private_data; + luo_file->fh->ops->unpreserve(&args); + + list_del(&luo_file->list); + file_set->count--; + + fput(luo_file->file); + mutex_destroy(&luo_file->mutex); + kfree(luo_file); + } + + luo_free_files_mem(file_set); +} + +static int luo_file_freeze_one(struct luo_file_set *file_set, + struct luo_file *luo_file) +{ + int err = 0; + + guard(mutex)(&luo_file->mutex); + + if (luo_file->fh->ops->freeze) { + struct liveupdate_file_op_args args = {0}; + + args.handler = luo_file->fh; + args.file = luo_file->file; + args.serialized_data = luo_file->serialized_data; + args.private_data = luo_file->private_data; + + err = luo_file->fh->ops->freeze(&args); + if (!err) + luo_file->serialized_data = args.serialized_data; + } + + return err; +} + +static void luo_file_unfreeze_one(struct luo_file_set *file_set, + struct luo_file *luo_file) +{ + guard(mutex)(&luo_file->mutex); + + if (luo_file->fh->ops->unfreeze) { + struct liveupdate_file_op_args args = {0}; + + args.handler = luo_file->fh; + args.file = luo_file->file; + args.serialized_data = luo_file->serialized_data; + args.private_data = luo_file->private_data; + + luo_file->fh->ops->unfreeze(&args); + } + + luo_file->serialized_data = 0; +} + +static void __luo_file_unfreeze(struct luo_file_set *file_set, + struct luo_file *failed_entry) +{ + struct list_head *files_list = &file_set->files_list; + struct luo_file *luo_file; + + list_for_each_entry(luo_file, files_list, list) { + if (luo_file == failed_entry) + break; + + luo_file_unfreeze_one(file_set, luo_file); + } + + memset(file_set->files, 0, LUO_FILE_PGCNT << PAGE_SHIFT); +} + +/** + * luo_file_freeze - Freezes all preserved files and serializes their metadata. + * @file_set: The file_set whose files are to be frozen. + * @file_set_ser: Where to put the serialized file_set. + * + * This function is called from the reboot() syscall path, just before the + * kernel transitions to the new image via kexec. Its purpose is to perform the + * final preparation and serialization of all preserved files in the file_set. + * + * It iterates through each preserved file in FIFO order (the order of + * preservation) and performs two main actions: + * + * 1. Freezes the File: It calls the handler's .freeze() callback for each + * file. This gives the handler a final opportunity to quiesce the device or + * prepare its state for the upcoming reboot. The handler may update its + * private data handle during this step. + * + * 2. Serializes Metadata: After a successful freeze, it copies the final file + * metadata—the handler's compatible string, the user token, and the final + * private data handle—into the pre-allocated contiguous memory buffer + * (file_set->files) that will be handed over to the next kernel via KHO. + * + * Error Handling (Rollback): + * This function is atomic. If any handler's .freeze() operation fails, the + * entire live update is aborted. The __luo_file_unfreeze() helper is + * immediately called to invoke the .unfreeze() op on all files that were + * successfully frozen before the point of failure, rolling them back to a + * running state. The function then returns an error, causing the reboot() + * syscall to fail. + * + * Context: Called only from the liveupdate_reboot() path. + * Return: 0 on success, or a negative errno on failure. + */ +int luo_file_freeze(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser) +{ + struct luo_file_ser *file_ser = file_set->files; + struct luo_file *luo_file; + int err; + int i; + + if (!file_set->count) + return 0; + + if (WARN_ON(!file_ser)) + return -EINVAL; + + i = 0; + list_for_each_entry(luo_file, &file_set->files_list, list) { + err = luo_file_freeze_one(file_set, luo_file); + if (err < 0) { + pr_warn("Freeze failed for token[%#0llx] handler[%s] err[%pe]\n", + luo_file->token, luo_file->fh->compatible, + ERR_PTR(err)); + goto err_unfreeze; + } + + strscpy(file_ser[i].compatible, luo_file->fh->compatible, + sizeof(file_ser[i].compatible)); + file_ser[i].data = luo_file->serialized_data; + file_ser[i].token = luo_file->token; + i++; + } + + file_set_ser->count = file_set->count; + if (file_set->files) + file_set_ser->files = virt_to_phys(file_set->files); + + return 0; + +err_unfreeze: + __luo_file_unfreeze(file_set, luo_file); + + return err; +} + +/** + * luo_file_unfreeze - Unfreezes all files in a file_set and clear serialization + * @file_set: The file_set whose files are to be unfrozen. + * @file_set_ser: Serialized file_set. + * + * This function rolls back the state of all files in a file_set after the + * freeze phase has begun but must be aborted. It is the counterpart to + * luo_file_freeze(). + * + * It invokes the __luo_file_unfreeze() helper with a NULL argument, which + * signals the helper to iterate through all files in the file_set and call + * their respective .unfreeze() handler callbacks. + * + * Context: This is called when the live update is aborted during + * the reboot() syscall, after luo_file_freeze() has been called. + */ +void luo_file_unfreeze(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser) +{ + if (!file_set->count) + return; + + __luo_file_unfreeze(file_set, NULL); + memset(file_set_ser, 0, sizeof(*file_set_ser)); +} + +/** + * luo_retrieve_file - Restores a preserved file from a file_set by its token. + * @file_set: The file_set from which to retrieve the file. + * @token: The unique token identifying the file to be restored. + * @filep: Output parameter; on success, this is populated with a pointer + * to the newly retrieved 'struct file'. + * + * This function is the primary mechanism for recreating a file in the new + * kernel after a live update. It searches the file_set's list of deserialized + * files for an entry matching the provided @token. + * + * The operation is idempotent: if a file has already been successfully + * retrieved, this function will simply return a pointer to the existing + * 'struct file' and report success without re-executing the retrieve + * operation. This is handled by checking the 'retrieved' flag under a lock. + * + * File retrieval can happen in any order; it is not bound by the order of + * preservation. + * + * Context: Can be called from an ioctl or other in-kernel code in the new + * kernel. + * Return: 0 on success. Returns a negative errno on failure: + * -ENOENT if no file with the matching token is found. + * Any error code returned by the handler's .retrieve() op. + */ +int luo_retrieve_file(struct luo_file_set *file_set, u64 token, + struct file **filep) +{ + struct liveupdate_file_op_args args = {0}; + struct luo_file *luo_file; + int err; + + if (list_empty(&file_set->files_list)) + return -ENOENT; + + list_for_each_entry(luo_file, &file_set->files_list, list) { + if (luo_file->token == token) + break; + } + + if (luo_file->token != token) + return -ENOENT; + + guard(mutex)(&luo_file->mutex); + if (luo_file->retrieved) { + /* + * Someone is asking for this file again, so get a reference + * for them. + */ + get_file(luo_file->file); + *filep = luo_file->file; + return 0; + } + + args.handler = luo_file->fh; + args.serialized_data = luo_file->serialized_data; + err = luo_file->fh->ops->retrieve(&args); + if (!err) { + luo_file->file = args.file; + + /* Get reference so we can keep this file in LUO until finish */ + get_file(luo_file->file); + *filep = luo_file->file; + luo_file->retrieved = true; + } + + return err; +} + +static int luo_file_can_finish_one(struct luo_file_set *file_set, + struct luo_file *luo_file) +{ + bool can_finish = true; + + guard(mutex)(&luo_file->mutex); + + if (luo_file->fh->ops->can_finish) { + struct liveupdate_file_op_args args = {0}; + + args.handler = luo_file->fh; + args.file = luo_file->file; + args.serialized_data = luo_file->serialized_data; + args.retrieved = luo_file->retrieved; + can_finish = luo_file->fh->ops->can_finish(&args); + } + + return can_finish ? 0 : -EBUSY; +} + +static void luo_file_finish_one(struct luo_file_set *file_set, + struct luo_file *luo_file) +{ + struct liveupdate_file_op_args args = {0}; + + guard(mutex)(&luo_file->mutex); + + args.handler = luo_file->fh; + args.file = luo_file->file; + args.serialized_data = luo_file->serialized_data; + args.retrieved = luo_file->retrieved; + + luo_file->fh->ops->finish(&args); +} + +/** + * luo_file_finish - Completes the lifecycle for all files in a file_set. + * @file_set: The file_set to be finalized. + * + * This function orchestrates the final teardown of a live update file_set in + * the new kernel. It should be called after all necessary files have been + * retrieved and the userspace agent is ready to release the preserved state. + * + * The function iterates through all tracked files. For each file, it performs + * the following sequence of cleanup actions: + * + * 1. If file is not yet retrieved, retrieves it, and calls can_finish() on + * every file in the file_set. If all can_finish return true, continue to + * finish. + * 2. Calls the handler's .finish() callback (via luo_file_finish_one) to + * allow for final resource cleanup within the handler. + * 3. Releases LUO's ownership reference on the 'struct file' via fput(). This + * is the counterpart to the get_file() call in luo_retrieve_file(). + * 4. Removes the 'struct luo_file' from the file_set's internal list. + * 5. Frees the memory for the 'struct luo_file' instance itself. + * + * After successfully finishing all individual files, it frees the + * contiguous memory block that was used to transfer the serialized metadata + * from the previous kernel. + * + * Error Handling (Atomic Failure): + * This operation is atomic. If any handler's .can_finish() op fails, the entire + * function aborts immediately and returns an error. + * + * Context: Can be called from an ioctl handler in the new kernel. + * Return: 0 on success, or a negative errno on failure. + */ +int luo_file_finish(struct luo_file_set *file_set) +{ + struct list_head *files_list = &file_set->files_list; + struct luo_file *luo_file; + int err; + + if (!file_set->count) + return 0; + + list_for_each_entry(luo_file, files_list, list) { + err = luo_file_can_finish_one(file_set, luo_file); + if (err) + return err; + } + + while (!list_empty(&file_set->files_list)) { + luo_file = list_last_entry(&file_set->files_list, + struct luo_file, list); + + luo_file_finish_one(file_set, luo_file); + + if (luo_file->file) + fput(luo_file->file); + list_del(&luo_file->list); + file_set->count--; + mutex_destroy(&luo_file->mutex); + kfree(luo_file); + } + + if (file_set->files) { + kho_restore_free(file_set->files); + file_set->files = NULL; + } + + return 0; +} + +/** + * luo_file_deserialize - Reconstructs the list of preserved files in the new kernel. + * @file_set: The incoming file_set to fill with deserialized data. + * @file_set_ser: Serialized KHO file_set data from the previous kernel. + * + * This function is called during the early boot process of the new kernel. It + * takes the raw, contiguous memory block of 'struct luo_file_ser' entries, + * provided by the previous kernel, and transforms it back into a live, + * in-memory linked list of 'struct luo_file' instances. + * + * For each serialized entry, it performs the following steps: + * 1. Reads the 'compatible' string. + * 2. Searches the global list of registered file handlers for one that + * matches the compatible string. + * 3. Allocates a new 'struct luo_file'. + * 4. Populates the new structure with the deserialized data (token, private + * data handle) and links it to the found handler. The 'file' pointer is + * initialized to NULL, as the file has not been retrieved yet. + * 5. Adds the new 'struct luo_file' to the file_set's files_list. + * + * This prepares the file_set for userspace, which can later call + * luo_retrieve_file() to restore the actual file descriptors. + * + * Context: Called from session deserialization. + */ +int luo_file_deserialize(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser) +{ + struct luo_file_ser *file_ser; + u64 i; + + if (!file_set_ser->files) { + WARN_ON(file_set_ser->count); + return 0; + } + + file_set->count = file_set_ser->count; + file_set->files = phys_to_virt(file_set_ser->files); + + /* + * Note on error handling: + * + * If deserialization fails (e.g., allocation failure or corrupt data), + * we intentionally skip cleanup of files that were already restored. + * + * A partial failure leaves the preserved state inconsistent. + * Implementing a safe "undo" to unwind complex dependencies (sessions, + * files, hardware state) is error-prone and provides little value, as + * the system is effectively in a broken state. + * + * We treat these resources as leaked. The expected recovery path is for + * userspace to detect the failure and trigger a reboot, which will + * reliably reset devices and reclaim memory. + */ + file_ser = file_set->files; + for (i = 0; i < file_set->count; i++) { + struct liveupdate_file_handler *fh; + bool handler_found = false; + struct luo_file *luo_file; + + luo_list_for_each_private(fh, &luo_file_handler_list, list) { + if (!strcmp(fh->compatible, file_ser[i].compatible)) { + handler_found = true; + break; + } + } + + if (!handler_found) { + pr_warn("No registered handler for compatible '%s'\n", + file_ser[i].compatible); + return -ENOENT; + } + + luo_file = kzalloc(sizeof(*luo_file), GFP_KERNEL); + if (!luo_file) + return -ENOMEM; + + luo_file->fh = fh; + luo_file->file = NULL; + luo_file->serialized_data = file_ser[i].data; + luo_file->token = file_ser[i].token; + luo_file->retrieved = false; + mutex_init(&luo_file->mutex); + list_add_tail(&luo_file->list, &file_set->files_list); + } + + return 0; +} + +void luo_file_set_init(struct luo_file_set *file_set) +{ + INIT_LIST_HEAD(&file_set->files_list); +} + +void luo_file_set_destroy(struct luo_file_set *file_set) +{ + WARN_ON(file_set->count); + WARN_ON(!list_empty(&file_set->files_list)); +} + +/** + * liveupdate_register_file_handler - Register a file handler with LUO. + * @fh: Pointer to a caller-allocated &struct liveupdate_file_handler. + * The caller must initialize this structure, including a unique + * 'compatible' string and a valid 'fh' callbacks. This function adds the + * handler to the global list of supported file handlers. + * + * Context: Typically called during module initialization for file types that + * support live update preservation. + * + * Return: 0 on success. Negative errno on failure. + */ +int liveupdate_register_file_handler(struct liveupdate_file_handler *fh) +{ + struct liveupdate_file_handler *fh_iter; + int err; + + if (!liveupdate_enabled()) + return -EOPNOTSUPP; + + /* Sanity check that all required callbacks are set */ + if (!fh->ops->preserve || !fh->ops->unpreserve || !fh->ops->retrieve || + !fh->ops->finish || !fh->ops->can_preserve) { + return -EINVAL; + } + + /* + * Ensure the system is quiescent (no active sessions). + * This prevents registering new handlers while sessions are active or + * while deserialization is in progress. + */ + if (!luo_session_quiesce()) + return -EBUSY; + + /* Check for duplicate compatible strings */ + luo_list_for_each_private(fh_iter, &luo_file_handler_list, list) { + if (!strcmp(fh_iter->compatible, fh->compatible)) { + pr_err("File handler registration failed: Compatible string '%s' already registered.\n", + fh->compatible); + err = -EEXIST; + goto err_resume; + } + } + + /* Pin the module implementing the handler */ + if (!try_module_get(fh->ops->owner)) { + err = -EAGAIN; + goto err_resume; + } + + INIT_LIST_HEAD(&ACCESS_PRIVATE(fh, list)); + list_add_tail(&ACCESS_PRIVATE(fh, list), &luo_file_handler_list); + luo_session_resume(); + + return 0; + +err_resume: + luo_session_resume(); + return err; +} + +/** + * liveupdate_unregister_file_handler - Unregister a liveupdate file handler + * @fh: The file handler to unregister + * + * Unregisters the file handler from the liveupdate core. This function + * reverses the operations of liveupdate_register_file_handler(). + * + * It ensures safe removal by checking that: + * No live update session is currently in progress. + * + * If the unregistration fails, the internal test state is reverted. + * + * Return: 0 Success. -EOPNOTSUPP when live update is not enabled. -EBUSY A live + * update is in progress, can't quiesce live update. + */ +int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh) +{ + if (!liveupdate_enabled()) + return -EOPNOTSUPP; + + if (!luo_session_quiesce()) + return -EBUSY; + + list_del(&ACCESS_PRIVATE(fh, list)); + module_put(fh->ops->owner); + luo_session_resume(); + + return 0; +} diff --git a/kernel/liveupdate/luo_internal.h b/kernel/liveupdate/luo_internal.h new file mode 100644 index 000000000000..c8973b543d1d --- /dev/null +++ b/kernel/liveupdate/luo_internal.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +#ifndef _LINUX_LUO_INTERNAL_H +#define _LINUX_LUO_INTERNAL_H + +#include +#include + +struct luo_ucmd { + void __user *ubuffer; + u32 user_size; + void *cmd; +}; + +static inline int luo_ucmd_respond(struct luo_ucmd *ucmd, + size_t kernel_cmd_size) +{ + /* + * Copy the minimum of what the user provided and what we actually + * have. + */ + if (copy_to_user(ucmd->ubuffer, ucmd->cmd, + min_t(size_t, ucmd->user_size, kernel_cmd_size))) { + return -EFAULT; + } + return 0; +} + +/* + * Handles a deserialization failure: devices and memory is in unpredictable + * state. + * + * Continuing the boot process after a failure is dangerous because it could + * lead to leaks of private data. + */ +#define luo_restore_fail(__fmt, ...) panic(__fmt, ##__VA_ARGS__) + +/* Mimics list_for_each_entry() but for private list head entries */ +#define luo_list_for_each_private(pos, head, member) \ + for (struct list_head *__iter = (head)->next; \ + __iter != (head) && \ + ({ pos = container_of(__iter, typeof(*(pos)), member); 1; }); \ + __iter = __iter->next) + +/** + * struct luo_file_set - A set of files that belong to the same sessions. + * @files_list: An ordered list of files associated with this session, it is + * ordered by preservation time. + * @files: The physically contiguous memory block that holds the serialized + * state of files. + * @count: A counter tracking the number of files currently stored in the + * @files_list for this session. + */ +struct luo_file_set { + struct list_head files_list; + struct luo_file_ser *files; + long count; +}; + +/** + * struct luo_session - Represents an active or incoming Live Update session. + * @name: A unique name for this session, used for identification and + * retrieval. + * @ser: Pointer to the serialized data for this session. + * @list: A list_head member used to link this session into a global list + * of either outgoing (to be preserved) or incoming (restored from + * previous kernel) sessions. + * @retrieved: A boolean flag indicating whether this session has been + * retrieved by a consumer in the new kernel. + * @file_set: A set of files that belong to this session. + * @mutex: protects fields in the luo_session. + */ +struct luo_session { + char name[LIVEUPDATE_SESSION_NAME_LENGTH]; + struct luo_session_ser *ser; + struct list_head list; + bool retrieved; + struct luo_file_set file_set; + struct mutex mutex; +}; + +int luo_session_create(const char *name, struct file **filep); +int luo_session_retrieve(const char *name, struct file **filep); +int __init luo_session_setup_outgoing(void *fdt); +int __init luo_session_setup_incoming(void *fdt); +int luo_session_serialize(void); +int luo_session_deserialize(void); +bool luo_session_quiesce(void); +void luo_session_resume(void); + +int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd); +void luo_file_unpreserve_files(struct luo_file_set *file_set); +int luo_file_freeze(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser); +void luo_file_unfreeze(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser); +int luo_retrieve_file(struct luo_file_set *file_set, u64 token, + struct file **filep); +int luo_file_finish(struct luo_file_set *file_set); +int luo_file_deserialize(struct luo_file_set *file_set, + struct luo_file_set_ser *file_set_ser); +void luo_file_set_init(struct luo_file_set *file_set); +void luo_file_set_destroy(struct luo_file_set *file_set); + +#endif /* _LINUX_LUO_INTERNAL_H */ diff --git a/kernel/liveupdate/luo_session.c b/kernel/liveupdate/luo_session.c new file mode 100644 index 000000000000..dbdbc3bd7929 --- /dev/null +++ b/kernel/liveupdate/luo_session.c @@ -0,0 +1,646 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +/** + * DOC: LUO Sessions + * + * LUO Sessions provide the core mechanism for grouping and managing `struct + * file *` instances that need to be preserved across a kexec-based live + * update. Each session acts as a named container for a set of file objects, + * allowing a userspace agent to manage the lifecycle of resources critical to a + * workload. + * + * Core Concepts: + * + * - Named Containers: Sessions are identified by a unique, user-provided name, + * which is used for both creation in the current kernel and retrieval in the + * next kernel. + * + * - Userspace Interface: Session management is driven from userspace via + * ioctls on /dev/liveupdate. + * + * - Serialization: Session metadata is preserved using the KHO framework. When + * a live update is triggered via kexec, an array of `struct luo_session_ser` + * is populated and placed in a preserved memory region. An FDT node is also + * created, containing the count of sessions and the physical address of this + * array. + * + * Session Lifecycle: + * + * 1. Creation: A userspace agent calls `luo_session_create()` to create a + * new, empty session and receives a file descriptor for it. + * + * 2. Serialization: When the `reboot(LINUX_REBOOT_CMD_KEXEC)` syscall is + * made, `luo_session_serialize()` is called. It iterates through all + * active sessions and writes their metadata into a memory area preserved + * by KHO. + * + * 3. Deserialization (in new kernel): After kexec, `luo_session_deserialize()` + * runs, reading the serialized data and creating a list of `struct + * luo_session` objects representing the preserved sessions. + * + * 4. Retrieval: A userspace agent in the new kernel can then call + * `luo_session_retrieve()` with a session name to get a new file + * descriptor and access the preserved state. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "luo_internal.h" + +/* 16 4K pages, give space for 744 sessions */ +#define LUO_SESSION_PGCNT 16ul +#define LUO_SESSION_MAX (((LUO_SESSION_PGCNT << PAGE_SHIFT) - \ + sizeof(struct luo_session_header_ser)) / \ + sizeof(struct luo_session_ser)) + +/** + * struct luo_session_header - Header struct for managing LUO sessions. + * @count: The number of sessions currently tracked in the @list. + * @list: The head of the linked list of `struct luo_session` instances. + * @rwsem: A read-write semaphore providing synchronized access to the + * session list and other fields in this structure. + * @header_ser: The header data of serialization array. + * @ser: The serialized session data (an array of + * `struct luo_session_ser`). + * @active: Set to true when first initialized. If previous kernel did not + * send session data, active stays false for incoming. + */ +struct luo_session_header { + long count; + struct list_head list; + struct rw_semaphore rwsem; + struct luo_session_header_ser *header_ser; + struct luo_session_ser *ser; + bool active; +}; + +/** + * struct luo_session_global - Global container for managing LUO sessions. + * @incoming: The sessions passed from the previous kernel. + * @outgoing: The sessions that are going to be passed to the next kernel. + */ +struct luo_session_global { + struct luo_session_header incoming; + struct luo_session_header outgoing; +}; + +static struct luo_session_global luo_session_global = { + .incoming = { + .list = LIST_HEAD_INIT(luo_session_global.incoming.list), + .rwsem = __RWSEM_INITIALIZER(luo_session_global.incoming.rwsem), + }, + .outgoing = { + .list = LIST_HEAD_INIT(luo_session_global.outgoing.list), + .rwsem = __RWSEM_INITIALIZER(luo_session_global.outgoing.rwsem), + }, +}; + +static struct luo_session *luo_session_alloc(const char *name) +{ + struct luo_session *session = kzalloc(sizeof(*session), GFP_KERNEL); + + if (!session) + return ERR_PTR(-ENOMEM); + + strscpy(session->name, name, sizeof(session->name)); + INIT_LIST_HEAD(&session->file_set.files_list); + luo_file_set_init(&session->file_set); + INIT_LIST_HEAD(&session->list); + mutex_init(&session->mutex); + + return session; +} + +static void luo_session_free(struct luo_session *session) +{ + luo_file_set_destroy(&session->file_set); + mutex_destroy(&session->mutex); + kfree(session); +} + +static int luo_session_insert(struct luo_session_header *sh, + struct luo_session *session) +{ + struct luo_session *it; + + guard(rwsem_write)(&sh->rwsem); + + /* + * For outgoing we should make sure there is room in serialization array + * for new session. + */ + if (sh == &luo_session_global.outgoing) { + if (sh->count == LUO_SESSION_MAX) + return -ENOMEM; + } + + /* + * For small number of sessions this loop won't hurt performance + * but if we ever start using a lot of sessions, this might + * become a bottle neck during deserialization time, as it would + * cause O(n*n) complexity. + */ + list_for_each_entry(it, &sh->list, list) { + if (!strncmp(it->name, session->name, sizeof(it->name))) + return -EEXIST; + } + list_add_tail(&session->list, &sh->list); + sh->count++; + + return 0; +} + +static void luo_session_remove(struct luo_session_header *sh, + struct luo_session *session) +{ + guard(rwsem_write)(&sh->rwsem); + list_del(&session->list); + sh->count--; +} + +static int luo_session_finish_one(struct luo_session *session) +{ + guard(mutex)(&session->mutex); + return luo_file_finish(&session->file_set); +} + +static void luo_session_unfreeze_one(struct luo_session *session, + struct luo_session_ser *ser) +{ + guard(mutex)(&session->mutex); + luo_file_unfreeze(&session->file_set, &ser->file_set_ser); +} + +static int luo_session_freeze_one(struct luo_session *session, + struct luo_session_ser *ser) +{ + guard(mutex)(&session->mutex); + return luo_file_freeze(&session->file_set, &ser->file_set_ser); +} + +static int luo_session_release(struct inode *inodep, struct file *filep) +{ + struct luo_session *session = filep->private_data; + struct luo_session_header *sh; + + /* If retrieved is set, it means this session is from incoming list */ + if (session->retrieved) { + int err = luo_session_finish_one(session); + + if (err) { + pr_warn("Unable to finish session [%s] on release\n", + session->name); + return err; + } + sh = &luo_session_global.incoming; + } else { + scoped_guard(mutex, &session->mutex) + luo_file_unpreserve_files(&session->file_set); + sh = &luo_session_global.outgoing; + } + + luo_session_remove(sh, session); + luo_session_free(session); + + return 0; +} + +static int luo_session_preserve_fd(struct luo_session *session, + struct luo_ucmd *ucmd) +{ + struct liveupdate_session_preserve_fd *argp = ucmd->cmd; + int err; + + guard(mutex)(&session->mutex); + err = luo_preserve_file(&session->file_set, argp->token, argp->fd); + if (err) + return err; + + err = luo_ucmd_respond(ucmd, sizeof(*argp)); + if (err) + pr_warn("The file was successfully preserved, but response to user failed\n"); + + return err; +} + +static int luo_session_retrieve_fd(struct luo_session *session, + struct luo_ucmd *ucmd) +{ + struct liveupdate_session_retrieve_fd *argp = ucmd->cmd; + struct file *file; + int err; + + argp->fd = get_unused_fd_flags(O_CLOEXEC); + if (argp->fd < 0) + return argp->fd; + + guard(mutex)(&session->mutex); + err = luo_retrieve_file(&session->file_set, argp->token, &file); + if (err < 0) + goto err_put_fd; + + err = luo_ucmd_respond(ucmd, sizeof(*argp)); + if (err) + goto err_put_file; + + fd_install(argp->fd, file); + + return 0; + +err_put_file: + fput(file); +err_put_fd: + put_unused_fd(argp->fd); + + return err; +} + +static int luo_session_finish(struct luo_session *session, + struct luo_ucmd *ucmd) +{ + struct liveupdate_session_finish *argp = ucmd->cmd; + int err = luo_session_finish_one(session); + + if (err) + return err; + + return luo_ucmd_respond(ucmd, sizeof(*argp)); +} + +union ucmd_buffer { + struct liveupdate_session_finish finish; + struct liveupdate_session_preserve_fd preserve; + struct liveupdate_session_retrieve_fd retrieve; +}; + +struct luo_ioctl_op { + unsigned int size; + unsigned int min_size; + unsigned int ioctl_num; + int (*execute)(struct luo_session *session, struct luo_ucmd *ucmd); +}; + +#define IOCTL_OP(_ioctl, _fn, _struct, _last) \ + [_IOC_NR(_ioctl) - LIVEUPDATE_CMD_SESSION_BASE] = { \ + .size = sizeof(_struct) + \ + BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) < \ + sizeof(_struct)), \ + .min_size = offsetofend(_struct, _last), \ + .ioctl_num = _ioctl, \ + .execute = _fn, \ + } + +static const struct luo_ioctl_op luo_session_ioctl_ops[] = { + IOCTL_OP(LIVEUPDATE_SESSION_FINISH, luo_session_finish, + struct liveupdate_session_finish, reserved), + IOCTL_OP(LIVEUPDATE_SESSION_PRESERVE_FD, luo_session_preserve_fd, + struct liveupdate_session_preserve_fd, token), + IOCTL_OP(LIVEUPDATE_SESSION_RETRIEVE_FD, luo_session_retrieve_fd, + struct liveupdate_session_retrieve_fd, token), +}; + +static long luo_session_ioctl(struct file *filep, unsigned int cmd, + unsigned long arg) +{ + struct luo_session *session = filep->private_data; + const struct luo_ioctl_op *op; + struct luo_ucmd ucmd = {}; + union ucmd_buffer buf; + unsigned int nr; + int ret; + + nr = _IOC_NR(cmd); + if (nr < LIVEUPDATE_CMD_SESSION_BASE || (nr - LIVEUPDATE_CMD_SESSION_BASE) >= + ARRAY_SIZE(luo_session_ioctl_ops)) { + return -EINVAL; + } + + ucmd.ubuffer = (void __user *)arg; + ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); + if (ret) + return ret; + + op = &luo_session_ioctl_ops[nr - LIVEUPDATE_CMD_SESSION_BASE]; + if (op->ioctl_num != cmd) + return -ENOIOCTLCMD; + if (ucmd.user_size < op->min_size) + return -EINVAL; + + ucmd.cmd = &buf; + ret = copy_struct_from_user(ucmd.cmd, op->size, ucmd.ubuffer, + ucmd.user_size); + if (ret) + return ret; + + return op->execute(session, &ucmd); +} + +static const struct file_operations luo_session_fops = { + .owner = THIS_MODULE, + .release = luo_session_release, + .unlocked_ioctl = luo_session_ioctl, +}; + +/* Create a "struct file" for session */ +static int luo_session_getfile(struct luo_session *session, struct file **filep) +{ + char name_buf[128]; + struct file *file; + + lockdep_assert_held(&session->mutex); + snprintf(name_buf, sizeof(name_buf), "[luo_session] %s", session->name); + file = anon_inode_getfile(name_buf, &luo_session_fops, session, O_RDWR); + if (IS_ERR(file)) + return PTR_ERR(file); + + *filep = file; + + return 0; +} + +int luo_session_create(const char *name, struct file **filep) +{ + struct luo_session *session; + int err; + + session = luo_session_alloc(name); + if (IS_ERR(session)) + return PTR_ERR(session); + + err = luo_session_insert(&luo_session_global.outgoing, session); + if (err) + goto err_free; + + scoped_guard(mutex, &session->mutex) + err = luo_session_getfile(session, filep); + if (err) + goto err_remove; + + return 0; + +err_remove: + luo_session_remove(&luo_session_global.outgoing, session); +err_free: + luo_session_free(session); + + return err; +} + +int luo_session_retrieve(const char *name, struct file **filep) +{ + struct luo_session_header *sh = &luo_session_global.incoming; + struct luo_session *session = NULL; + struct luo_session *it; + int err; + + scoped_guard(rwsem_read, &sh->rwsem) { + list_for_each_entry(it, &sh->list, list) { + if (!strncmp(it->name, name, sizeof(it->name))) { + session = it; + break; + } + } + } + + if (!session) + return -ENOENT; + + guard(mutex)(&session->mutex); + if (session->retrieved) + return -EINVAL; + + err = luo_session_getfile(session, filep); + if (!err) + session->retrieved = true; + + return err; +} + +int __init luo_session_setup_outgoing(void *fdt_out) +{ + struct luo_session_header_ser *header_ser; + u64 header_ser_pa; + int err; + + header_ser = kho_alloc_preserve(LUO_SESSION_PGCNT << PAGE_SHIFT); + if (IS_ERR(header_ser)) + return PTR_ERR(header_ser); + header_ser_pa = virt_to_phys(header_ser); + + err = fdt_begin_node(fdt_out, LUO_FDT_SESSION_NODE_NAME); + err |= fdt_property_string(fdt_out, "compatible", + LUO_FDT_SESSION_COMPATIBLE); + err |= fdt_property(fdt_out, LUO_FDT_SESSION_HEADER, &header_ser_pa, + sizeof(header_ser_pa)); + err |= fdt_end_node(fdt_out); + + if (err) + goto err_unpreserve; + + luo_session_global.outgoing.header_ser = header_ser; + luo_session_global.outgoing.ser = (void *)(header_ser + 1); + luo_session_global.outgoing.active = true; + + return 0; + +err_unpreserve: + kho_unpreserve_free(header_ser); + return err; +} + +int __init luo_session_setup_incoming(void *fdt_in) +{ + struct luo_session_header_ser *header_ser; + int err, header_size, offset; + u64 header_ser_pa; + const void *ptr; + + offset = fdt_subnode_offset(fdt_in, 0, LUO_FDT_SESSION_NODE_NAME); + if (offset < 0) { + pr_err("Unable to get session node: [%s]\n", + LUO_FDT_SESSION_NODE_NAME); + return -EINVAL; + } + + err = fdt_node_check_compatible(fdt_in, offset, + LUO_FDT_SESSION_COMPATIBLE); + if (err) { + pr_err("Session node incompatible [%s]\n", + LUO_FDT_SESSION_COMPATIBLE); + return -EINVAL; + } + + header_size = 0; + ptr = fdt_getprop(fdt_in, offset, LUO_FDT_SESSION_HEADER, &header_size); + if (!ptr || header_size != sizeof(u64)) { + pr_err("Unable to get session header '%s' [%d]\n", + LUO_FDT_SESSION_HEADER, header_size); + return -EINVAL; + } + + header_ser_pa = get_unaligned((u64 *)ptr); + header_ser = phys_to_virt(header_ser_pa); + + luo_session_global.incoming.header_ser = header_ser; + luo_session_global.incoming.ser = (void *)(header_ser + 1); + luo_session_global.incoming.active = true; + + return 0; +} + +int luo_session_deserialize(void) +{ + struct luo_session_header *sh = &luo_session_global.incoming; + static bool is_deserialized; + static int err; + + /* If has been deserialized, always return the same error code */ + if (is_deserialized) + return err; + + is_deserialized = true; + if (!sh->active) + return 0; + + /* + * Note on error handling: + * + * If deserialization fails (e.g., allocation failure or corrupt data), + * we intentionally skip cleanup of sessions that were already restored. + * + * A partial failure leaves the preserved state inconsistent. + * Implementing a safe "undo" to unwind complex dependencies (sessions, + * files, hardware state) is error-prone and provides little value, as + * the system is effectively in a broken state. + * + * We treat these resources as leaked. The expected recovery path is for + * userspace to detect the failure and trigger a reboot, which will + * reliably reset devices and reclaim memory. + */ + for (int i = 0; i < sh->header_ser->count; i++) { + struct luo_session *session; + + session = luo_session_alloc(sh->ser[i].name); + if (IS_ERR(session)) { + pr_warn("Failed to allocate session [%s] during deserialization %pe\n", + sh->ser[i].name, session); + return PTR_ERR(session); + } + + err = luo_session_insert(sh, session); + if (err) { + pr_warn("Failed to insert session [%s] %pe\n", + session->name, ERR_PTR(err)); + luo_session_free(session); + return err; + } + + scoped_guard(mutex, &session->mutex) { + luo_file_deserialize(&session->file_set, + &sh->ser[i].file_set_ser); + } + } + + kho_restore_free(sh->header_ser); + sh->header_ser = NULL; + sh->ser = NULL; + + return 0; +} + +int luo_session_serialize(void) +{ + struct luo_session_header *sh = &luo_session_global.outgoing; + struct luo_session *session; + int i = 0; + int err; + + guard(rwsem_write)(&sh->rwsem); + list_for_each_entry(session, &sh->list, list) { + err = luo_session_freeze_one(session, &sh->ser[i]); + if (err) + goto err_undo; + + strscpy(sh->ser[i].name, session->name, + sizeof(sh->ser[i].name)); + i++; + } + sh->header_ser->count = sh->count; + + return 0; + +err_undo: + list_for_each_entry_continue_reverse(session, &sh->list, list) { + i--; + luo_session_unfreeze_one(session, &sh->ser[i]); + memset(sh->ser[i].name, 0, sizeof(sh->ser[i].name)); + } + + return err; +} + +/** + * luo_session_quiesce - Ensure no active sessions exist and lock session lists. + * + * Acquires exclusive write locks on both incoming and outgoing session lists. + * It then validates no sessions exist in either list. + * + * This mechanism is used during file handler un/registration to ensure that no + * sessions are currently using the handler, and no new sessions can be created + * while un/registration is in progress. + * + * This prevents registering new handlers while sessions are active or + * while deserialization is in progress. + * + * Return: + * true - System is quiescent (0 sessions) and locked. + * false - Active sessions exist. The locks are released internally. + */ +bool luo_session_quiesce(void) +{ + down_write(&luo_session_global.incoming.rwsem); + down_write(&luo_session_global.outgoing.rwsem); + + if (luo_session_global.incoming.count || + luo_session_global.outgoing.count) { + up_write(&luo_session_global.outgoing.rwsem); + up_write(&luo_session_global.incoming.rwsem); + return false; + } + + return true; +} + +/** + * luo_session_resume - Unlock session lists and resume normal activity. + * + * Releases the exclusive locks acquired by a successful call to + * luo_session_quiesce(). + */ +void luo_session_resume(void) +{ + up_write(&luo_session_global.outgoing.rwsem); + up_write(&luo_session_global.incoming.rwsem); +} diff --git a/kernel/module/main.c b/kernel/module/main.c index 7b3ec2fa6e7c..710ee30b3bea 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -954,7 +954,7 @@ size_t module_flags_taint(unsigned long taints, char *buf) int i; for (i = 0; i < TAINT_FLAGS_COUNT; i++) { - if (taint_flags[i].module && test_bit(i, &taints)) + if (test_bit(i, &taints)) buf[l++] = taint_flags[i].c_true; } diff --git a/kernel/panic.c b/kernel/panic.c index b2f2470af7e5..0d52210a9e2b 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -401,7 +401,7 @@ static void panic_trigger_all_cpu_backtrace(void) */ static void panic_other_cpus_shutdown(bool crash_kexec) { - if (panic_print & SYS_INFO_ALL_CPU_BT) + if (panic_print & SYS_INFO_ALL_BT) panic_trigger_all_cpu_backtrace(); /* @@ -628,38 +628,40 @@ void panic(const char *fmt, ...) } EXPORT_SYMBOL(panic); -#define TAINT_FLAG(taint, _c_true, _c_false, _module) \ +#define TAINT_FLAG(taint, _c_true, _c_false) \ [ TAINT_##taint ] = { \ .c_true = _c_true, .c_false = _c_false, \ - .module = _module, \ .desc = #taint, \ } /* - * TAINT_FORCED_RMMOD could be a per-module flag but the module - * is being removed anyway. + * NOTE: if you modify the taint_flags or TAINT_FLAGS_COUNT, + * please also modify tools/debugging/kernel-chktaint and + * Documentation/admin-guide/tainted-kernels.rst, including its + * small shell script that prints the TAINT_FLAGS_COUNT bits of + * /proc/sys/kernel/tainted. */ const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = { - TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G', true), - TAINT_FLAG(FORCED_MODULE, 'F', ' ', true), - TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' ', false), - TAINT_FLAG(FORCED_RMMOD, 'R', ' ', false), - TAINT_FLAG(MACHINE_CHECK, 'M', ' ', false), - TAINT_FLAG(BAD_PAGE, 'B', ' ', false), - TAINT_FLAG(USER, 'U', ' ', false), - TAINT_FLAG(DIE, 'D', ' ', false), - TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' ', false), - TAINT_FLAG(WARN, 'W', ' ', false), - TAINT_FLAG(CRAP, 'C', ' ', true), - TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' ', false), - TAINT_FLAG(OOT_MODULE, 'O', ' ', true), - TAINT_FLAG(UNSIGNED_MODULE, 'E', ' ', true), - TAINT_FLAG(SOFTLOCKUP, 'L', ' ', false), - TAINT_FLAG(LIVEPATCH, 'K', ' ', true), - TAINT_FLAG(AUX, 'X', ' ', true), - TAINT_FLAG(RANDSTRUCT, 'T', ' ', true), - TAINT_FLAG(TEST, 'N', ' ', true), - TAINT_FLAG(FWCTL, 'J', ' ', true), + TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G'), + TAINT_FLAG(FORCED_MODULE, 'F', ' '), + TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' '), + TAINT_FLAG(FORCED_RMMOD, 'R', ' '), + TAINT_FLAG(MACHINE_CHECK, 'M', ' '), + TAINT_FLAG(BAD_PAGE, 'B', ' '), + TAINT_FLAG(USER, 'U', ' '), + TAINT_FLAG(DIE, 'D', ' '), + TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' '), + TAINT_FLAG(WARN, 'W', ' '), + TAINT_FLAG(CRAP, 'C', ' '), + TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' '), + TAINT_FLAG(OOT_MODULE, 'O', ' '), + TAINT_FLAG(UNSIGNED_MODULE, 'E', ' '), + TAINT_FLAG(SOFTLOCKUP, 'L', ' '), + TAINT_FLAG(LIVEPATCH, 'K', ' '), + TAINT_FLAG(AUX, 'X', ' '), + TAINT_FLAG(RANDSTRUCT, 'T', ' '), + TAINT_FLAG(TEST, 'N', ' '), + TAINT_FLAG(FWCTL, 'J', ' '), }; #undef TAINT_FLAG diff --git a/kernel/resource.c b/kernel/resource.c index b9fa2a4ce089..e4e9bac12e6e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -341,6 +341,8 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, struct resource *res) { + /* Skip children until we find a top level range that matches */ + bool skip_children = true; struct resource *p; if (!res) @@ -351,7 +353,7 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, read_lock(&resource_lock); - for_each_resource(&iomem_resource, p, false) { + for_each_resource(&iomem_resource, p, skip_children) { /* If we passed the resource we are looking for, stop */ if (p->start > end) { p = NULL; @@ -362,6 +364,12 @@ static int find_next_iomem_res(resource_size_t start, resource_size_t end, if (p->end < start) continue; + /* + * We found a top level range that matches what we are looking + * for. Time to start checking children too. + */ + skip_children = false; + /* Found a match, break */ if (is_type_match(p, flags, desc)) break; diff --git a/kernel/scs.c b/kernel/scs.c index d7809affe740..772488afd5b9 100644 --- a/kernel/scs.c +++ b/kernel/scs.c @@ -135,7 +135,7 @@ static void scs_check_usage(struct task_struct *tsk) if (!IS_ENABLED(CONFIG_DEBUG_STACK_USAGE)) return; - for (p = task_scs(tsk); p < __scs_magic(tsk); ++p) { + for (p = task_scs(tsk); p < __scs_magic(task_scs(tsk)); ++p) { if (!READ_ONCE_NOCHECK(*p)) break; used += sizeof(*p); diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c index e066d31d08f8..fe9bf8db1922 100644 --- a/kernel/vmcore_info.c +++ b/kernel/vmcore_info.c @@ -31,6 +31,13 @@ u32 *vmcoreinfo_note; /* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ static unsigned char *vmcoreinfo_data_safecopy; +struct hwerr_info { + atomic_t count; + time64_t timestamp; +}; + +static struct hwerr_info hwerr_data[HWERR_RECOV_MAX]; + Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) { @@ -118,6 +125,16 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void) } EXPORT_SYMBOL(paddr_vmcoreinfo_note); +void hwerr_log_error_type(enum hwerr_error_type src) +{ + if (src < 0 || src >= HWERR_RECOV_MAX) + return; + + atomic_inc(&hwerr_data[src].count); + WRITE_ONCE(hwerr_data[src].timestamp, ktime_get_real_seconds()); +} +EXPORT_SYMBOL_GPL(hwerr_log_error_type); + static int __init crash_save_vmcoreinfo_init(void) { vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index a567600cf3ed..0685e3a8aa0a 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -65,6 +66,13 @@ int __read_mostly sysctl_hardlockup_all_cpu_backtrace; unsigned int __read_mostly hardlockup_panic = IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC); +/* + * bitmasks to control what kinds of system info to be printed when + * hard lockup is detected, it could be task, memory, lock etc. + * Refer include/linux/sys_info.h for detailed bit definition. + */ +static unsigned long hardlockup_si_mask; + #ifdef CONFIG_SYSFS static unsigned int hardlockup_count; @@ -178,11 +186,15 @@ static void watchdog_hardlockup_kick(void) void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) { + int hardlockup_all_cpu_backtrace; + if (per_cpu(watchdog_hardlockup_touched, cpu)) { per_cpu(watchdog_hardlockup_touched, cpu) = false; return; } + hardlockup_all_cpu_backtrace = (hardlockup_si_mask & SYS_INFO_ALL_BT) ? + 1 : sysctl_hardlockup_all_cpu_backtrace; /* * Check for a hardlockup by making sure the CPU's timer * interrupt is incrementing. The timer interrupt should have @@ -214,7 +226,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) * Prevent multiple hard-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ - if (sysctl_hardlockup_all_cpu_backtrace) { + if (hardlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn)) return; } @@ -243,12 +255,13 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) trigger_single_cpu_backtrace(cpu); } - if (sysctl_hardlockup_all_cpu_backtrace) { + if (hardlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(cpu); if (!hardlockup_panic) clear_bit_unlock(0, &hard_lockup_nmi_warn); } + sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); @@ -339,6 +352,13 @@ static void lockup_detector_update_enable(void) int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif +/* + * bitmasks to control what kinds of system info to be printed when + * soft lockup is detected, it could be task, memory, lock etc. + * Refer include/linux/sys_info.h for detailed bit definition. + */ +static unsigned long softlockup_si_mask; + static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ @@ -755,7 +775,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int duration; - int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + int softlockup_all_cpu_backtrace; unsigned long flags; if (!watchdog_enabled) @@ -767,6 +787,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) if (panic_in_progress()) return HRTIMER_NORESTART; + softlockup_all_cpu_backtrace = (softlockup_si_mask & SYS_INFO_ALL_BT) ? + 1 : sysctl_softlockup_all_cpu_backtrace; + watchdog_hardlockup_kick(); /* kick the softlockup detector */ @@ -855,6 +878,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); + sys_info(softlockup_si_mask & ~SYS_INFO_ALL_BT); if (softlockup_panic) panic("softlockup: hung tasks"); } @@ -1206,6 +1230,13 @@ static const struct ctl_table watchdog_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "softlockup_sys_info", + .data = &softlockup_si_mask, + .maxlen = sizeof(softlockup_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, #ifdef CONFIG_SMP { .procname = "softlockup_all_cpu_backtrace", @@ -1228,6 +1259,13 @@ static const struct ctl_table watchdog_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "hardlockup_sys_info", + .data = &hardlockup_si_mask, + .maxlen = sizeof(hardlockup_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, #ifdef CONFIG_SMP { .procname = "hardlockup_all_cpu_backtrace", diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c2654075377e..ba36939fda79 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -342,8 +342,7 @@ config DEBUG_INFO_COMPRESSED_ZLIB depends on $(cc-option,-gz=zlib) depends on $(ld-option,--compress-debug-sections=zlib) help - Compress the debug information using zlib. Requires GCC 5.0+ or Clang - 5.0+, binutils 2.26+, and zlib. + Compress the debug information using zlib. Users of dpkg-deb via debian/rules may find an increase in size of their debug .deb packages with this config set, due to the @@ -493,23 +492,23 @@ config DEBUG_SECTION_MISMATCH bool "Enable full Section mismatch analysis" depends on CC_IS_GCC help - The section mismatch analysis checks if there are illegal - references from one section to another section. - During linktime or runtime, some sections are dropped; - any use of code/data previously in these sections would - most likely result in an oops. - In the code, functions and variables are annotated with - __init,, etc. (see the full list in include/linux/init.h), - which results in the code/data being placed in specific sections. + The section mismatch analysis checks if there are illegal references + from one section to another. During linktime or runtime, some + sections are dropped; any use of code/data previously in these + sections would most likely result in an oops. + + In the code, functions and variables are annotated with __init, + __initdata, and so on (see the full list in include/linux/init.h). + This directs the toolchain to place code/data in specific sections. + The section mismatch analysis is always performed after a full - kernel build, and enabling this option causes the following - additional step to occur: - - Add the option -fno-inline-functions-called-once to gcc commands. - When inlining a function annotated with __init in a non-init - function, we would lose the section information and thus - the analysis would not catch the illegal reference. - This option tells gcc to inline less (but it does result in - a larger kernel). + kernel build, and enabling this option causes the option + -fno-inline-functions-called-once to be added to gcc commands. + + However, when inlining a function annotated with __init in + a non-init function, we would lose the section information and thus + the analysis would not catch the illegal reference. This option + tells gcc to inline less (but it does result in a larger kernel). config SECTION_MISMATCH_WARN_ONLY bool "Make section mismatch errors non-fatal" @@ -1260,12 +1259,13 @@ config DEFAULT_HUNG_TASK_TIMEOUT Keeping the default should be fine in most cases. config BOOTPARAM_HUNG_TASK_PANIC - bool "Panic (Reboot) On Hung Tasks" + int "Number of hung tasks to trigger kernel panic" depends on DETECT_HUNG_TASK + default 0 help - Say Y here to enable the kernel to panic on "hung tasks", - which are bugs that cause the kernel to leave a task stuck - in uninterruptible "D" state. + When set to a non-zero value, a kernel panic will be triggered + if the number of hung tasks found during a single scan reaches + this value. The panic can be used in combination with panic_timeout, to cause the system to reboot automatically after a @@ -2817,8 +2817,25 @@ config CMDLINE_KUNIT_TEST If unsure, say N. +config BASE64_KUNIT + tristate "KUnit test for base64 decoding and encoding" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + This builds the base64 unit tests. + + The tests cover the encoding and decoding logic of Base64 functions + in the kernel. + In addition to correctness checks, simple performance benchmarks + for both encoding and decoding are also included. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + config BITS_TEST - tristate "KUnit test for bits.h" if !KUNIT_ALL_TESTS + tristate "KUnit test for bit functions and macros" if !KUNIT_ALL_TESTS depends on KUNIT default KUNIT_ALL_TESTS help diff --git a/lib/base64.c b/lib/base64.c index b736a7a431c5..41961a444028 100644 --- a/lib/base64.c +++ b/lib/base64.c @@ -1,12 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* - * base64.c - RFC4648-compliant base64 encoding + * base64.c - Base64 with support for multiple variants * * Copyright (c) 2020 Hannes Reinecke, SUSE * * Based on the base64url routines from fs/crypto/fname.c - * (which are using the URL-safe base64 encoding), - * modified to use the standard coding table from RFC4648 section 4. + * (which are using the URL-safe Base64 encoding), + * modified to support multiple Base64 variants. */ #include @@ -15,89 +15,170 @@ #include #include -static const char base64_table[65] = - "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; +static const char base64_tables[][65] = { + [BASE64_STD] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/", + [BASE64_URLSAFE] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_", + [BASE64_IMAP] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,", +}; +/* + * Initialize the base64 reverse mapping for a single character + * This macro maps a character to its corresponding base64 value, + * returning -1 if the character is invalid. + * char 'A'-'Z' maps to 0-25, 'a'-'z' maps to 26-51, '0'-'9' maps to 52-61, + * ch_62 maps to 62, ch_63 maps to 63, and other characters return -1 + */ +#define INIT_1(v, ch_62, ch_63) \ + [v] = (v) >= 'A' && (v) <= 'Z' ? (v) - 'A' \ + : (v) >= 'a' && (v) <= 'z' ? (v) - 'a' + 26 \ + : (v) >= '0' && (v) <= '9' ? (v) - '0' + 52 \ + : (v) == (ch_62) ? 62 : (v) == (ch_63) ? 63 : -1 + +/* + * Recursive macros to generate multiple Base64 reverse mapping table entries. + * Each macro generates a sequence of entries in the lookup table: + * INIT_2 generates 2 entries, INIT_4 generates 4, INIT_8 generates 8, and so on up to INIT_32. + */ +#define INIT_2(v, ...) INIT_1(v, __VA_ARGS__), INIT_1((v) + 1, __VA_ARGS__) +#define INIT_4(v, ...) INIT_2(v, __VA_ARGS__), INIT_2((v) + 2, __VA_ARGS__) +#define INIT_8(v, ...) INIT_4(v, __VA_ARGS__), INIT_4((v) + 4, __VA_ARGS__) +#define INIT_16(v, ...) INIT_8(v, __VA_ARGS__), INIT_8((v) + 8, __VA_ARGS__) +#define INIT_32(v, ...) INIT_16(v, __VA_ARGS__), INIT_16((v) + 16, __VA_ARGS__) + +#define BASE64_REV_INIT(ch_62, ch_63) { \ + [0 ... 0x1f] = -1, \ + INIT_32(0x20, ch_62, ch_63), \ + INIT_32(0x40, ch_62, ch_63), \ + INIT_32(0x60, ch_62, ch_63), \ + [0x80 ... 0xff] = -1 } + +static const s8 base64_rev_maps[][256] = { + [BASE64_STD] = BASE64_REV_INIT('+', '/'), + [BASE64_URLSAFE] = BASE64_REV_INIT('-', '_'), + [BASE64_IMAP] = BASE64_REV_INIT('+', ',') +}; + +#undef BASE64_REV_INIT +#undef INIT_32 +#undef INIT_16 +#undef INIT_8 +#undef INIT_4 +#undef INIT_2 +#undef INIT_1 /** - * base64_encode() - base64-encode some binary data + * base64_encode() - Base64-encode some binary data * @src: the binary data to encode * @srclen: the length of @src in bytes - * @dst: (output) the base64-encoded string. Not NUL-terminated. + * @dst: (output) the Base64-encoded string. Not NUL-terminated. + * @padding: whether to append '=' padding characters + * @variant: which base64 variant to use * - * Encodes data using base64 encoding, i.e. the "Base 64 Encoding" specified - * by RFC 4648, including the '='-padding. + * Encodes data using the selected Base64 variant. * - * Return: the length of the resulting base64-encoded string in bytes. + * Return: the length of the resulting Base64-encoded string in bytes. */ -int base64_encode(const u8 *src, int srclen, char *dst) +int base64_encode(const u8 *src, int srclen, char *dst, bool padding, enum base64_variant variant) { u32 ac = 0; - int bits = 0; - int i; char *cp = dst; + const char *base64_table = base64_tables[variant]; - for (i = 0; i < srclen; i++) { - ac = (ac << 8) | src[i]; - bits += 8; - do { - bits -= 6; - *cp++ = base64_table[(ac >> bits) & 0x3f]; - } while (bits >= 6); + while (srclen >= 3) { + ac = src[0] << 16 | src[1] << 8 | src[2]; + *cp++ = base64_table[ac >> 18]; + *cp++ = base64_table[(ac >> 12) & 0x3f]; + *cp++ = base64_table[(ac >> 6) & 0x3f]; + *cp++ = base64_table[ac & 0x3f]; + + src += 3; + srclen -= 3; } - if (bits) { - *cp++ = base64_table[(ac << (6 - bits)) & 0x3f]; - bits -= 6; - } - while (bits < 0) { - *cp++ = '='; - bits += 2; + + switch (srclen) { + case 2: + ac = src[0] << 16 | src[1] << 8; + *cp++ = base64_table[ac >> 18]; + *cp++ = base64_table[(ac >> 12) & 0x3f]; + *cp++ = base64_table[(ac >> 6) & 0x3f]; + if (padding) + *cp++ = '='; + break; + case 1: + ac = src[0] << 16; + *cp++ = base64_table[ac >> 18]; + *cp++ = base64_table[(ac >> 12) & 0x3f]; + if (padding) { + *cp++ = '='; + *cp++ = '='; + } + break; } return cp - dst; } EXPORT_SYMBOL_GPL(base64_encode); /** - * base64_decode() - base64-decode a string + * base64_decode() - Base64-decode a string * @src: the string to decode. Doesn't need to be NUL-terminated. * @srclen: the length of @src in bytes * @dst: (output) the decoded binary data + * @padding: whether to append '=' padding characters + * @variant: which base64 variant to use * - * Decodes a string using base64 encoding, i.e. the "Base 64 Encoding" - * specified by RFC 4648, including the '='-padding. - * - * This implementation hasn't been optimized for performance. + * Decodes a string using the selected Base64 variant. * * Return: the length of the resulting decoded binary data in bytes, - * or -1 if the string isn't a valid base64 string. + * or -1 if the string isn't a valid Base64 string. */ -int base64_decode(const char *src, int srclen, u8 *dst) +int base64_decode(const char *src, int srclen, u8 *dst, bool padding, enum base64_variant variant) { - u32 ac = 0; - int bits = 0; - int i; u8 *bp = dst; + s8 input[4]; + s32 val; + const u8 *s = (const u8 *)src; + const s8 *base64_rev_tables = base64_rev_maps[variant]; - for (i = 0; i < srclen; i++) { - const char *p = strchr(base64_table, src[i]); + while (srclen >= 4) { + input[0] = base64_rev_tables[s[0]]; + input[1] = base64_rev_tables[s[1]]; + input[2] = base64_rev_tables[s[2]]; + input[3] = base64_rev_tables[s[3]]; - if (src[i] == '=') { - ac = (ac << 6); - bits += 6; - if (bits >= 8) - bits -= 8; - continue; - } - if (p == NULL || src[i] == 0) - return -1; - ac = (ac << 6) | (p - base64_table); - bits += 6; - if (bits >= 8) { - bits -= 8; - *bp++ = (u8)(ac >> bits); + val = input[0] << 18 | input[1] << 12 | input[2] << 6 | input[3]; + + if (unlikely(val < 0)) { + if (!padding || srclen != 4 || s[3] != '=') + return -1; + padding = 0; + srclen = s[2] == '=' ? 2 : 3; + break; } + + *bp++ = val >> 16; + *bp++ = val >> 8; + *bp++ = val; + + s += 4; + srclen -= 4; } - if (ac & ((1 << bits) - 1)) + + if (likely(!srclen)) + return bp - dst; + if (padding || srclen == 1) return -1; + + val = (base64_rev_tables[s[0]] << 12) | (base64_rev_tables[s[1]] << 6); + *bp++ = val >> 10; + + if (srclen == 2) { + if (val & 0x800003ff) + return -1; + } else { + val |= base64_rev_tables[s[2]]; + if (val & 0x80000003) + return -1; + *bp++ = val >> 2; + } return bp - dst; } EXPORT_SYMBOL_GPL(base64_decode); diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 5a007952f7f2..7d7892e57a01 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -95,6 +95,7 @@ static const struct { unsigned flag:8; char opt_char; } opt_array[] = { { _DPRINTK_FLAGS_INCL_SOURCENAME, 's' }, { _DPRINTK_FLAGS_INCL_LINENO, 'l' }, { _DPRINTK_FLAGS_INCL_TID, 't' }, + { _DPRINTK_FLAGS_INCL_STACK, 'd' }, { _DPRINTK_FLAGS_NONE, '_' }, }; diff --git a/lib/math/div64.c b/lib/math/div64.c index bf77b9843175..d1e92ea24fce 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -177,94 +177,157 @@ EXPORT_SYMBOL(div64_s64); * Iterative div/mod for use when dividend is not expected to be much * bigger than divisor. */ +#ifndef iter_div_u64_rem u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) { return __iter_div_u64_rem(dividend, divisor, remainder); } EXPORT_SYMBOL(iter_div_u64_rem); +#endif -#ifndef mul_u64_u64_div_u64 -u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c) +#if !defined(mul_u64_add_u64_div_u64) || defined(test_mul_u64_add_u64_div_u64) + +#define mul_add(a, b, c) add_u64_u32(mul_u32_u32(a, b), c) + +#if defined(__SIZEOF_INT128__) && !defined(test_mul_u64_add_u64_div_u64) +static inline u64 mul_u64_u64_add_u64(u64 *p_lo, u64 a, u64 b, u64 c) { - if (ilog2(a) + ilog2(b) <= 62) - return div64_u64(a * b, c); - -#if defined(__SIZEOF_INT128__) - /* native 64x64=128 bits multiplication */ - u128 prod = (u128)a * b; - u64 n_lo = prod, n_hi = prod >> 64; + u128 prod = (u128)a * b + c; + *p_lo = prod; + return prod >> 64; +} #else - - /* perform a 64x64=128 bits multiplication manually */ - u32 a_lo = a, a_hi = a >> 32, b_lo = b, b_hi = b >> 32; +static inline u64 mul_u64_u64_add_u64(u64 *p_lo, u64 a, u64 b, u64 c) +{ + /* perform a 64x64=128 bits multiplication in 32bit chunks */ u64 x, y, z; - x = (u64)a_lo * b_lo; - y = (u64)a_lo * b_hi + (u32)(x >> 32); - z = (u64)a_hi * b_hi + (u32)(y >> 32); - y = (u64)a_hi * b_lo + (u32)y; - z += (u32)(y >> 32); - x = (y << 32) + (u32)x; - - u64 n_lo = x, n_hi = z; - -#endif - - /* make sure c is not zero, trigger runtime exception otherwise */ - if (unlikely(c == 0)) { - unsigned long zero = 0; - - OPTIMIZER_HIDE_VAR(zero); - return ~0UL/zero; - } - - int shift = __builtin_ctzll(c); - - /* try reducing the fraction in case the dividend becomes <= 64 bits */ - if ((n_hi >> shift) == 0) { - u64 n = shift ? (n_lo >> shift) | (n_hi << (64 - shift)) : n_lo; - - return div64_u64(n, c >> shift); - /* - * The remainder value if needed would be: - * res = div64_u64_rem(n, c >> shift, &rem); - * rem = (rem << shift) + (n_lo - (n << shift)); - */ - } - - if (n_hi >= c) { - /* overflow: result is unrepresentable in a u64 */ - return -1; - } - - /* Do the full 128 by 64 bits division */ - - shift = __builtin_clzll(c); - c <<= shift; - - int p = 64 + shift; - u64 res = 0; - bool carry; - - do { - carry = n_hi >> 63; - shift = carry ? 1 : __builtin_clzll(n_hi); - if (p < shift) - break; - p -= shift; - n_hi <<= shift; - n_hi |= n_lo >> (64 - shift); - n_lo <<= shift; - if (carry || (n_hi >= c)) { - n_hi -= c; - res |= 1ULL << p; - } - } while (n_hi); - /* The remainder value if needed would be n_hi << p */ - - return res; + /* Since (x-1)(x-1) + 2(x-1) == x.x - 1 two u32 can be added to a u64 */ + x = mul_add(a, b, c); + y = mul_add(a, b >> 32, c >> 32); + y = add_u64_u32(y, x >> 32); + z = mul_add(a >> 32, b >> 32, y >> 32); + y = mul_add(a >> 32, b, y); + *p_lo = (y << 32) + (u32)x; + return add_u64_u32(z, y >> 32); } -EXPORT_SYMBOL(mul_u64_u64_div_u64); +#endif + +#ifndef BITS_PER_ITER +#define BITS_PER_ITER (__LONG_WIDTH__ >= 64 ? 32 : 16) +#endif + +#if BITS_PER_ITER == 32 +#define mul_u64_long_add_u64(p_lo, a, b, c) mul_u64_u64_add_u64(p_lo, a, b, c) +#define add_u64_long(a, b) ((a) + (b)) +#else +#undef BITS_PER_ITER +#define BITS_PER_ITER 16 +static inline u32 mul_u64_long_add_u64(u64 *p_lo, u64 a, u32 b, u64 c) +{ + u64 n_lo = mul_add(a, b, c); + u64 n_med = mul_add(a >> 32, b, c >> 32); + + n_med = add_u64_u32(n_med, n_lo >> 32); + *p_lo = n_med << 32 | (u32)n_lo; + return n_med >> 32; +} + +#define add_u64_long(a, b) add_u64_u32(a, b) +#endif + +u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d) +{ + unsigned long d_msig, q_digit; + unsigned int reps, d_z_hi; + u64 quotient, n_lo, n_hi; + u32 overflow; + + n_hi = mul_u64_u64_add_u64(&n_lo, a, b, c); + + if (!n_hi) + return div64_u64(n_lo, d); + + if (unlikely(n_hi >= d)) { + /* trigger runtime exception if divisor is zero */ + if (d == 0) { + unsigned long zero = 0; + + OPTIMIZER_HIDE_VAR(zero); + return ~0UL/zero; + } + /* overflow: result is unrepresentable in a u64 */ + return ~0ULL; + } + + /* Left align the divisor, shifting the dividend to match */ + d_z_hi = __builtin_clzll(d); + if (d_z_hi) { + d <<= d_z_hi; + n_hi = n_hi << d_z_hi | n_lo >> (64 - d_z_hi); + n_lo <<= d_z_hi; + } + + reps = 64 / BITS_PER_ITER; + /* Optimise loop count for small dividends */ + if (!(u32)(n_hi >> 32)) { + reps -= 32 / BITS_PER_ITER; + n_hi = n_hi << 32 | n_lo >> 32; + n_lo <<= 32; + } +#if BITS_PER_ITER == 16 + if (!(u32)(n_hi >> 48)) { + reps--; + n_hi = add_u64_u32(n_hi << 16, n_lo >> 48); + n_lo <<= 16; + } +#endif + + /* Invert the dividend so we can use add instead of subtract. */ + n_lo = ~n_lo; + n_hi = ~n_hi; + + /* + * Get the most significant BITS_PER_ITER bits of the divisor. + * This is used to get a low 'guestimate' of the quotient digit. + */ + d_msig = (d >> (64 - BITS_PER_ITER)) + 1; + + /* + * Now do a 'long division' with BITS_PER_ITER bit 'digits'. + * The 'guess' quotient digit can be low and BITS_PER_ITER+1 bits. + * The worst case is dividing ~0 by 0x8000 which requires two subtracts. + */ + quotient = 0; + while (reps--) { + q_digit = (unsigned long)(~n_hi >> (64 - 2 * BITS_PER_ITER)) / d_msig; + /* Shift 'n' left to align with the product q_digit * d */ + overflow = n_hi >> (64 - BITS_PER_ITER); + n_hi = add_u64_u32(n_hi << BITS_PER_ITER, n_lo >> (64 - BITS_PER_ITER)); + n_lo <<= BITS_PER_ITER; + /* Add product to negated divisor */ + overflow += mul_u64_long_add_u64(&n_hi, d, q_digit, n_hi); + /* Adjust for the q_digit 'guestimate' being low */ + while (overflow < 0xffffffff >> (32 - BITS_PER_ITER)) { + q_digit++; + n_hi += d; + overflow += n_hi < d; + } + quotient = add_u64_long(quotient << BITS_PER_ITER, q_digit); + } + + /* + * The above only ensures the remainder doesn't overflow, + * it can still be possible to add (aka subtract) another copy + * of the divisor. + */ + if ((n_hi + d) > n_hi) + quotient++; + return quotient; +} +#if !defined(test_mul_u64_add_u64_div_u64) +EXPORT_SYMBOL(mul_u64_add_u64_div_u64); +#endif #endif diff --git a/lib/math/test_mul_u64_u64_div_u64.c b/lib/math/test_mul_u64_u64_div_u64.c index 58d058de4e73..338d014f0c73 100644 --- a/lib/math/test_mul_u64_u64_div_u64.c +++ b/lib/math/test_mul_u64_u64_div_u64.c @@ -10,80 +10,141 @@ #include #include -typedef struct { u64 a; u64 b; u64 c; u64 result; } test_params; +typedef struct { u64 a; u64 b; u64 d; u64 result; uint round_up;} test_params; static test_params test_values[] = { /* this contains many edge values followed by a couple random values */ -{ 0xb, 0x7, 0x3, 0x19 }, -{ 0xffff0000, 0xffff0000, 0xf, 0x1110eeef00000000 }, -{ 0xffffffff, 0xffffffff, 0x1, 0xfffffffe00000001 }, -{ 0xffffffff, 0xffffffff, 0x2, 0x7fffffff00000000 }, -{ 0x1ffffffff, 0xffffffff, 0x2, 0xfffffffe80000000 }, -{ 0x1ffffffff, 0xffffffff, 0x3, 0xaaaaaaa9aaaaaaab }, -{ 0x1ffffffff, 0x1ffffffff, 0x4, 0xffffffff00000000 }, -{ 0xffff000000000000, 0xffff000000000000, 0xffff000000000001, 0xfffeffffffffffff }, -{ 0x3333333333333333, 0x3333333333333333, 0x5555555555555555, 0x1eb851eb851eb851 }, -{ 0x7fffffffffffffff, 0x2, 0x3, 0x5555555555555554 }, -{ 0xffffffffffffffff, 0x2, 0x8000000000000000, 0x3 }, -{ 0xffffffffffffffff, 0x2, 0xc000000000000000, 0x2 }, -{ 0xffffffffffffffff, 0x4000000000000004, 0x8000000000000000, 0x8000000000000007 }, -{ 0xffffffffffffffff, 0x4000000000000001, 0x8000000000000000, 0x8000000000000001 }, -{ 0xffffffffffffffff, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000001 }, -{ 0xfffffffffffffffe, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000000 }, -{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffe, 0x8000000000000001 }, -{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffd, 0x8000000000000002 }, -{ 0x7fffffffffffffff, 0xffffffffffffffff, 0xc000000000000000, 0xaaaaaaaaaaaaaaa8 }, -{ 0xffffffffffffffff, 0x7fffffffffffffff, 0xa000000000000000, 0xccccccccccccccca }, -{ 0xffffffffffffffff, 0x7fffffffffffffff, 0x9000000000000000, 0xe38e38e38e38e38b }, -{ 0x7fffffffffffffff, 0x7fffffffffffffff, 0x5000000000000000, 0xccccccccccccccc9 }, -{ 0xffffffffffffffff, 0xfffffffffffffffe, 0xffffffffffffffff, 0xfffffffffffffffe }, -{ 0xe6102d256d7ea3ae, 0x70a77d0be4c31201, 0xd63ec35ab3220357, 0x78f8bf8cc86c6e18 }, -{ 0xf53bae05cb86c6e1, 0x3847b32d2f8d32e0, 0xcfd4f55a647f403c, 0x42687f79d8998d35 }, -{ 0x9951c5498f941092, 0x1f8c8bfdf287a251, 0xa3c8dc5f81ea3fe2, 0x1d887cb25900091f }, -{ 0x374fee9daa1bb2bb, 0x0d0bfbff7b8ae3ef, 0xc169337bd42d5179, 0x03bb2dbaffcbb961 }, -{ 0xeac0d03ac10eeaf0, 0x89be05dfa162ed9b, 0x92bb1679a41f0e4b, 0xdc5f5cc9e270d216 }, +{ 0xb, 0x7, 0x3, 0x19, 1 }, +{ 0xffff0000, 0xffff0000, 0xf, 0x1110eeef00000000, 0 }, +{ 0xffffffff, 0xffffffff, 0x1, 0xfffffffe00000001, 0 }, +{ 0xffffffff, 0xffffffff, 0x2, 0x7fffffff00000000, 1 }, +{ 0x1ffffffff, 0xffffffff, 0x2, 0xfffffffe80000000, 1 }, +{ 0x1ffffffff, 0xffffffff, 0x3, 0xaaaaaaa9aaaaaaab, 0 }, +{ 0x1ffffffff, 0x1ffffffff, 0x4, 0xffffffff00000000, 1 }, +{ 0xffff000000000000, 0xffff000000000000, 0xffff000000000001, 0xfffeffffffffffff, 1 }, +{ 0x3333333333333333, 0x3333333333333333, 0x5555555555555555, 0x1eb851eb851eb851, 1 }, +{ 0x7fffffffffffffff, 0x2, 0x3, 0x5555555555555554, 1 }, +{ 0xffffffffffffffff, 0x2, 0x8000000000000000, 0x3, 1 }, +{ 0xffffffffffffffff, 0x2, 0xc000000000000000, 0x2, 1 }, +{ 0xffffffffffffffff, 0x4000000000000004, 0x8000000000000000, 0x8000000000000007, 1 }, +{ 0xffffffffffffffff, 0x4000000000000001, 0x8000000000000000, 0x8000000000000001, 1 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000001, 0 }, +{ 0xfffffffffffffffe, 0x8000000000000001, 0xffffffffffffffff, 0x8000000000000000, 1 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffe, 0x8000000000000001, 1 }, +{ 0xffffffffffffffff, 0x8000000000000001, 0xfffffffffffffffd, 0x8000000000000002, 1 }, +{ 0x7fffffffffffffff, 0xffffffffffffffff, 0xc000000000000000, 0xaaaaaaaaaaaaaaa8, 1 }, +{ 0xffffffffffffffff, 0x7fffffffffffffff, 0xa000000000000000, 0xccccccccccccccca, 1 }, +{ 0xffffffffffffffff, 0x7fffffffffffffff, 0x9000000000000000, 0xe38e38e38e38e38b, 1 }, +{ 0x7fffffffffffffff, 0x7fffffffffffffff, 0x5000000000000000, 0xccccccccccccccc9, 1 }, +{ 0xffffffffffffffff, 0xfffffffffffffffe, 0xffffffffffffffff, 0xfffffffffffffffe, 0 }, +{ 0xe6102d256d7ea3ae, 0x70a77d0be4c31201, 0xd63ec35ab3220357, 0x78f8bf8cc86c6e18, 1 }, +{ 0xf53bae05cb86c6e1, 0x3847b32d2f8d32e0, 0xcfd4f55a647f403c, 0x42687f79d8998d35, 1 }, +{ 0x9951c5498f941092, 0x1f8c8bfdf287a251, 0xa3c8dc5f81ea3fe2, 0x1d887cb25900091f, 1 }, +{ 0x374fee9daa1bb2bb, 0x0d0bfbff7b8ae3ef, 0xc169337bd42d5179, 0x03bb2dbaffcbb961, 1 }, +{ 0xeac0d03ac10eeaf0, 0x89be05dfa162ed9b, 0x92bb1679a41f0e4b, 0xdc5f5cc9e270d216, 1 }, }; /* * The above table can be verified with the following shell script: - * - * #!/bin/sh - * sed -ne 's/^{ \+\(.*\), \+\(.*\), \+\(.*\), \+\(.*\) },$/\1 \2 \3 \4/p' \ - * lib/math/test_mul_u64_u64_div_u64.c | - * while read a b c r; do - * expected=$( printf "obase=16; ibase=16; %X * %X / %X\n" $a $b $c | bc ) - * given=$( printf "%X\n" $r ) - * if [ "$expected" = "$given" ]; then - * echo "$a * $b / $c = $r OK" - * else - * echo "$a * $b / $c = $r is wrong" >&2 - * echo "should be equivalent to 0x$expected" >&2 - * exit 1 - * fi - * done + +#!/bin/sh +sed -ne 's/^{ \+\(.*\), \+\(.*\), \+\(.*\), \+\(.*\), \+\(.*\) },$/\1 \2 \3 \4 \5/p' \ + lib/math/test_mul_u64_u64_div_u64.c | +while read a b d r e; do + expected=$( printf "obase=16; ibase=16; %X * %X / %X\n" $a $b $d | bc ) + given=$( printf "%X\n" $r ) + if [ "$expected" = "$given" ]; then + echo "$a * $b / $d = $r OK" + else + echo "$a * $b / $d = $r is wrong" >&2 + echo "should be equivalent to 0x$expected" >&2 + exit 1 + fi + expected=$( printf "obase=16; ibase=16; (%X * %X + %X) / %X\n" $a $b $((d-1)) $d | bc ) + given=$( printf "%X\n" $((r + e)) ) + if [ "$expected" = "$given" ]; then + echo "$a * $b +/ $d = $(printf '%#x' $((r + e))) OK" + else + echo "$a * $b +/ $d = $(printf '%#x' $((r + e))) is wrong" >&2 + echo "should be equivalent to 0x$expected" >&2 + exit 1 + fi +done + */ -static int __init test_init(void) +static u64 test_mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d); +#if __LONG_WIDTH__ >= 64 +#define TEST_32BIT_DIV +static u64 test_mul_u64_add_u64_div_u64_32bit(u64 a, u64 b, u64 c, u64 d); +#endif + +static int __init test_run(unsigned int fn_no, const char *fn_name) { + u64 start_time; + int errors = 0; + int tests = 0; int i; - pr_info("Starting mul_u64_u64_div_u64() test\n"); + start_time = ktime_get_ns(); for (i = 0; i < ARRAY_SIZE(test_values); i++) { u64 a = test_values[i].a; u64 b = test_values[i].b; - u64 c = test_values[i].c; + u64 d = test_values[i].d; u64 expected_result = test_values[i].result; - u64 result = mul_u64_u64_div_u64(a, b, c); + u64 result, result_up; + + switch (fn_no) { + default: + result = mul_u64_u64_div_u64(a, b, d); + result_up = mul_u64_u64_div_u64_roundup(a, b, d); + break; + case 1: + result = test_mul_u64_add_u64_div_u64(a, b, 0, d); + result_up = test_mul_u64_add_u64_div_u64(a, b, d - 1, d); + break; +#ifdef TEST_32BIT_DIV + case 2: + result = test_mul_u64_add_u64_div_u64_32bit(a, b, 0, d); + result_up = test_mul_u64_add_u64_div_u64_32bit(a, b, d - 1, d); + break; +#endif + } + + tests += 2; if (result != expected_result) { - pr_err("ERROR: 0x%016llx * 0x%016llx / 0x%016llx\n", a, b, c); + pr_err("ERROR: 0x%016llx * 0x%016llx / 0x%016llx\n", a, b, d); pr_err("ERROR: expected result: %016llx\n", expected_result); pr_err("ERROR: obtained result: %016llx\n", result); + errors++; + } + expected_result += test_values[i].round_up; + if (result_up != expected_result) { + pr_err("ERROR: 0x%016llx * 0x%016llx +/ 0x%016llx\n", a, b, d); + pr_err("ERROR: expected result: %016llx\n", expected_result); + pr_err("ERROR: obtained result: %016llx\n", result_up); + errors++; } } - pr_info("Completed mul_u64_u64_div_u64() test\n"); + pr_info("Completed %s() test, %d tests, %d errors, %llu ns\n", + fn_name, tests, errors, ktime_get_ns() - start_time); + return errors; +} + +static int __init test_init(void) +{ + pr_info("Starting mul_u64_u64_div_u64() test\n"); + if (test_run(0, "mul_u64_u64_div_u64")) + return -EINVAL; + if (test_run(1, "test_mul_u64_u64_div_u64")) + return -EINVAL; +#ifdef TEST_32BIT_DIV + if (test_run(2, "test_mul_u64_u64_div_u64_32bit")) + return -EINVAL; +#endif return 0; } @@ -91,6 +152,36 @@ static void __exit test_exit(void) { } +/* Compile the generic mul_u64_add_u64_div_u64() code */ +#undef __div64_32 +#define __div64_32 __div64_32 +#define div_s64_rem div_s64_rem +#define div64_u64_rem div64_u64_rem +#define div64_u64 div64_u64 +#define div64_s64 div64_s64 +#define iter_div_u64_rem iter_div_u64_rem + +#undef mul_u64_add_u64_div_u64 +#define mul_u64_add_u64_div_u64 test_mul_u64_add_u64_div_u64 +#define test_mul_u64_add_u64_div_u64 test_mul_u64_add_u64_div_u64 + +#include "div64.c" + +#ifdef TEST_32BIT_DIV +/* Recompile the generic code for 32bit long */ +#undef test_mul_u64_add_u64_div_u64 +#define test_mul_u64_add_u64_div_u64 test_mul_u64_add_u64_div_u64_32bit +#undef BITS_PER_ITER +#define BITS_PER_ITER 16 + +#define mul_u64_u64_add_u64 mul_u64_u64_add_u64_32bit +#undef mul_u64_long_add_u64 +#undef add_u64_long +#undef mul_add + +#include "div64.c" +#endif + module_init(test_init); module_exit(test_exit); diff --git a/lib/plist.c b/lib/plist.c index 330febb4bd7d..ba677c31e8f3 100644 --- a/lib/plist.c +++ b/lib/plist.c @@ -47,8 +47,8 @@ static void plist_check_list(struct list_head *top) plist_check_prev_next(top, prev, next); while (next != top) { - WRITE_ONCE(prev, next); - WRITE_ONCE(next, prev->next); + prev = next; + next = prev->next; plist_check_prev_next(top, prev, next); } } diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 859c251b23ce..e2d65d3b1c35 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -27,7 +27,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). - * Changing two values seperately could be inconsistent + * Changing two values separately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); diff --git a/lib/rbtree.c b/lib/rbtree.c index 5114eda6309c..18d42bcf4ec9 100644 --- a/lib/rbtree.c +++ b/lib/rbtree.c @@ -460,35 +460,6 @@ void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, } EXPORT_SYMBOL(__rb_insert_augmented); -/* - * This function returns the first node (in sort order) of the tree. - */ -struct rb_node *rb_first(const struct rb_root *root) -{ - struct rb_node *n; - - n = root->rb_node; - if (!n) - return NULL; - while (n->rb_left) - n = n->rb_left; - return n; -} -EXPORT_SYMBOL(rb_first); - -struct rb_node *rb_last(const struct rb_root *root) -{ - struct rb_node *n; - - n = root->rb_node; - if (!n) - return NULL; - while (n->rb_right) - n = n->rb_right; - return n; -} -EXPORT_SYMBOL(rb_last); - struct rb_node *rb_next(const struct rb_node *node) { struct rb_node *parent; diff --git a/lib/sys_info.c b/lib/sys_info.c index 496f9151c9b6..f32a06ec9ed4 100644 --- a/lib/sys_info.c +++ b/lib/sys_info.c @@ -1,31 +1,35 @@ // SPDX-License-Identifier: GPL-2.0-only -#include +#include +#include +#include #include +#include #include #include -#include #include +#include +#include +#include #include -struct sys_info_name { - unsigned long bit; - const char *name; +static const char * const si_names[] = { + [ilog2(SYS_INFO_TASKS)] = "tasks", + [ilog2(SYS_INFO_MEM)] = "mem", + [ilog2(SYS_INFO_TIMERS)] = "timers", + [ilog2(SYS_INFO_LOCKS)] = "locks", + [ilog2(SYS_INFO_FTRACE)] = "ftrace", + [ilog2(SYS_INFO_PANIC_CONSOLE_REPLAY)] = "", + [ilog2(SYS_INFO_ALL_BT)] = "all_bt", + [ilog2(SYS_INFO_BLOCKED_TASKS)] = "blocked_tasks", }; /* - * When 'si_names' gets updated, please make sure the 'sys_info_avail' - * below is updated accordingly. + * Default kernel sys_info mask. + * If a kernel module calls sys_info() with "parameter == 0", then + * this mask will be used. */ -static const struct sys_info_name si_names[] = { - { SYS_INFO_TASKS, "tasks" }, - { SYS_INFO_MEM, "mem" }, - { SYS_INFO_TIMERS, "timers" }, - { SYS_INFO_LOCKS, "locks" }, - { SYS_INFO_FTRACE, "ftrace" }, - { SYS_INFO_ALL_CPU_BT, "all_bt" }, - { SYS_INFO_BLOCKED_TASKS, "blocked_tasks" }, -}; +static unsigned long kernel_si_mask; /* Expecting string like "xxx_sys_info=tasks,mem,timers,locks,ftrace,..." */ unsigned long sys_info_parse_param(char *str) @@ -36,12 +40,9 @@ unsigned long sys_info_parse_param(char *str) s = str; while ((name = strsep(&s, ",")) && *name) { - for (i = 0; i < ARRAY_SIZE(si_names); i++) { - if (!strcmp(name, si_names[i].name)) { - si_bits |= si_names[i].bit; - break; - } - } + i = match_string(si_names, ARRAY_SIZE(si_names), name); + if (i >= 0) + __set_bit(i, &si_bits); } return si_bits; @@ -49,56 +50,93 @@ unsigned long sys_info_parse_param(char *str) #ifdef CONFIG_SYSCTL -static const char sys_info_avail[] __maybe_unused = "tasks,mem,timers,locks,ftrace,all_bt,blocked_tasks"; +static int sys_info_write_handler(const struct ctl_table *table, + void *buffer, size_t *lenp, loff_t *ppos, + unsigned long *si_bits_global) +{ + unsigned long si_bits; + int ret; + + ret = proc_dostring(table, 1, buffer, lenp, ppos); + if (ret) + return ret; + + si_bits = sys_info_parse_param(table->data); + + /* The access to the global value is not synchronized. */ + WRITE_ONCE(*si_bits_global, si_bits); + + return 0; +} + +static int sys_info_read_handler(const struct ctl_table *table, + void *buffer, size_t *lenp, loff_t *ppos, + unsigned long *si_bits_global) +{ + unsigned long si_bits; + unsigned int len = 0; + char *delim = ""; + unsigned int i; + + /* The access to the global value is not synchronized. */ + si_bits = READ_ONCE(*si_bits_global); + + for_each_set_bit(i, &si_bits, ARRAY_SIZE(si_names)) { + if (*si_names[i]) { + len += scnprintf(table->data + len, table->maxlen - len, + "%s%s", delim, si_names[i]); + delim = ","; + } + } + + return proc_dostring(table, 0, buffer, lenp, ppos); +} int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - char names[sizeof(sys_info_avail)]; struct ctl_table table; - unsigned long *si_bits_global; + unsigned int i; + size_t maxlen; - si_bits_global = ro_table->data; + maxlen = 0; + for (i = 0; i < ARRAY_SIZE(si_names); i++) + maxlen += strlen(si_names[i]) + 1; - if (write) { - unsigned long si_bits; - int ret; + char *names __free(kfree) = kzalloc(maxlen, GFP_KERNEL); + if (!names) + return -ENOMEM; - table = *ro_table; - table.data = names; - table.maxlen = sizeof(names); - ret = proc_dostring(&table, write, buffer, lenp, ppos); - if (ret) - return ret; + table = *ro_table; + table.data = names; + table.maxlen = maxlen; - si_bits = sys_info_parse_param(names); - /* The access to the global value is not synchronized. */ - WRITE_ONCE(*si_bits_global, si_bits); - return 0; - } else { - /* for 'read' operation */ - char *delim = ""; - int i, len = 0; - - names[0] = '\0'; - for (i = 0; i < ARRAY_SIZE(si_names); i++) { - if (*si_bits_global & si_names[i].bit) { - len += scnprintf(names + len, sizeof(names) - len, - "%s%s", delim, si_names[i].name); - delim = ","; - } - } - - table = *ro_table; - table.data = names; - table.maxlen = sizeof(names); - return proc_dostring(&table, write, buffer, lenp, ppos); - } + if (write) + return sys_info_write_handler(&table, buffer, lenp, ppos, ro_table->data); + else + return sys_info_read_handler(&table, buffer, lenp, ppos, ro_table->data); } + +static const struct ctl_table sys_info_sysctls[] = { + { + .procname = "kernel_sys_info", + .data = &kernel_si_mask, + .maxlen = sizeof(kernel_si_mask), + .mode = 0644, + .proc_handler = sysctl_sys_info_handler, + }, +}; + +static int __init sys_info_sysctl_init(void) +{ + register_sysctl_init("kernel", sys_info_sysctls); + return 0; +} +subsys_initcall(sys_info_sysctl_init); #endif -void sys_info(unsigned long si_mask) +static void __sys_info(unsigned long si_mask) { if (si_mask & SYS_INFO_TASKS) show_state(); @@ -115,9 +153,14 @@ void sys_info(unsigned long si_mask) if (si_mask & SYS_INFO_FTRACE) ftrace_dump(DUMP_ALL); - if (si_mask & SYS_INFO_ALL_CPU_BT) + if (si_mask & SYS_INFO_ALL_BT) trigger_all_cpu_backtrace(); if (si_mask & SYS_INFO_BLOCKED_TASKS) show_state_filter(TASK_UNINTERRUPTIBLE); } + +void sys_info(unsigned long si_mask) +{ + __sys_info(si_mask ? : kernel_si_mask); +} diff --git a/lib/test_kho.c b/lib/test_kho.c index fff018e5548d..47de56280795 100644 --- a/lib/test_kho.c +++ b/lib/test_kho.c @@ -33,44 +33,28 @@ struct kho_test_state { unsigned int nr_folios; struct folio **folios; phys_addr_t *folios_info; + struct kho_vmalloc folios_info_phys; + int nr_folios_preserved; struct folio *fdt; __wsum csum; }; static struct kho_test_state kho_test_state; -static int kho_test_notifier(struct notifier_block *self, unsigned long cmd, - void *v) +static void kho_test_unpreserve_data(struct kho_test_state *state) { - struct kho_test_state *state = &kho_test_state; - struct kho_serialization *ser = v; - int err = 0; + for (int i = 0; i < state->nr_folios_preserved; i++) + kho_unpreserve_folio(state->folios[i]); - switch (cmd) { - case KEXEC_KHO_ABORT: - return NOTIFY_DONE; - case KEXEC_KHO_FINALIZE: - /* Handled below */ - break; - default: - return NOTIFY_BAD; - } - - err |= kho_preserve_folio(state->fdt); - err |= kho_add_subtree(ser, KHO_TEST_FDT, folio_address(state->fdt)); - - return err ? NOTIFY_BAD : NOTIFY_DONE; + kho_unpreserve_vmalloc(&state->folios_info_phys); + vfree(state->folios_info); } -static struct notifier_block kho_test_nb = { - .notifier_call = kho_test_notifier, -}; - -static int kho_test_save_data(struct kho_test_state *state, void *fdt) +static int kho_test_preserve_data(struct kho_test_state *state) { - phys_addr_t *folios_info __free(kvfree) = NULL; struct kho_vmalloc folios_info_phys; - int err = 0; + phys_addr_t *folios_info; + int err; folios_info = vmalloc_array(state->nr_folios, sizeof(*folios_info)); if (!folios_info) @@ -78,62 +62,98 @@ static int kho_test_save_data(struct kho_test_state *state, void *fdt) err = kho_preserve_vmalloc(folios_info, &folios_info_phys); if (err) - return err; + goto err_free_info; + + state->folios_info_phys = folios_info_phys; + state->folios_info = folios_info; for (int i = 0; i < state->nr_folios; i++) { struct folio *folio = state->folios[i]; unsigned int order = folio_order(folio); folios_info[i] = virt_to_phys(folio_address(folio)) | order; - err = kho_preserve_folio(folio); if (err) - break; + goto err_unpreserve; + state->nr_folios_preserved++; } + return 0; + +err_unpreserve: + /* + * kho_test_unpreserve_data frees folio_info, bail out immediately to + * avoid double free + */ + kho_test_unpreserve_data(state); + return err; + +err_free_info: + vfree(folios_info); + return err; +} + +static int kho_test_prepare_fdt(struct kho_test_state *state, ssize_t fdt_size) +{ + const char compatible[] = KHO_TEST_COMPAT; + unsigned int magic = KHO_TEST_MAGIC; + void *fdt = folio_address(state->fdt); + int err; + + err = fdt_create(fdt, fdt_size); + err |= fdt_finish_reservemap(fdt); + err |= fdt_begin_node(fdt, ""); + err |= fdt_property(fdt, "compatible", compatible, sizeof(compatible)); + err |= fdt_property(fdt, "magic", &magic, sizeof(magic)); + err |= fdt_begin_node(fdt, "data"); err |= fdt_property(fdt, "nr_folios", &state->nr_folios, sizeof(state->nr_folios)); - err |= fdt_property(fdt, "folios_info", &folios_info_phys, - sizeof(folios_info_phys)); + err |= fdt_property(fdt, "folios_info", &state->folios_info_phys, + sizeof(state->folios_info_phys)); err |= fdt_property(fdt, "csum", &state->csum, sizeof(state->csum)); err |= fdt_end_node(fdt); - if (!err) - state->folios_info = no_free_ptr(folios_info); + err |= fdt_end_node(fdt); + err |= fdt_finish(fdt); return err; } -static int kho_test_prepare_fdt(struct kho_test_state *state) +static int kho_test_preserve(struct kho_test_state *state) { - const char compatible[] = KHO_TEST_COMPAT; - unsigned int magic = KHO_TEST_MAGIC; ssize_t fdt_size; - int err = 0; - void *fdt; + int err; fdt_size = state->nr_folios * sizeof(phys_addr_t) + PAGE_SIZE; state->fdt = folio_alloc(GFP_KERNEL, get_order(fdt_size)); if (!state->fdt) return -ENOMEM; - fdt = folio_address(state->fdt); - - err |= fdt_create(fdt, fdt_size); - err |= fdt_finish_reservemap(fdt); - - err |= fdt_begin_node(fdt, ""); - err |= fdt_property(fdt, "compatible", compatible, sizeof(compatible)); - err |= fdt_property(fdt, "magic", &magic, sizeof(magic)); - err |= kho_test_save_data(state, fdt); - err |= fdt_end_node(fdt); - - err |= fdt_finish(fdt); - + err = kho_preserve_folio(state->fdt); if (err) - folio_put(state->fdt); + goto err_free_fdt; + err = kho_test_preserve_data(state); + if (err) + goto err_unpreserve_fdt; + + err = kho_test_prepare_fdt(state, fdt_size); + if (err) + goto err_unpreserve_data; + + err = kho_add_subtree(KHO_TEST_FDT, folio_address(state->fdt)); + if (err) + goto err_unpreserve_data; + + return 0; + +err_unpreserve_data: + kho_test_unpreserve_data(state); +err_unpreserve_fdt: + kho_unpreserve_folio(state->fdt); +err_free_fdt: + folio_put(state->fdt); return err; } @@ -199,18 +219,12 @@ static int kho_test_save(void) if (err) goto err_free_folios; - err = kho_test_prepare_fdt(state); + err = kho_test_preserve(state); if (err) goto err_free_folios; - err = register_kho_notifier(&kho_test_nb); - if (err) - goto err_free_fdt; - return 0; -err_free_fdt: - folio_put(state->fdt); err_free_folios: kvfree(folios); return err; @@ -292,7 +306,6 @@ static int kho_test_restore(phys_addr_t fdt_phys) if (err) return err; - pr_info("KHO restore succeeded\n"); return 0; } @@ -305,8 +318,15 @@ static int __init kho_test_init(void) return 0; err = kho_retrieve_subtree(KHO_TEST_FDT, &fdt_phys); - if (!err) - return kho_test_restore(fdt_phys); + if (!err) { + err = kho_test_restore(fdt_phys); + if (err) + pr_err("KHO restore failed\n"); + else + pr_info("KHO restore succeeded\n"); + + return err; + } if (err != -ENOENT) { pr_warn("failed to retrieve %s FDT: %d\n", KHO_TEST_FDT, err); @@ -329,7 +349,7 @@ static void kho_test_cleanup(void) static void __exit kho_test_exit(void) { - unregister_kho_notifier(&kho_test_nb); + kho_remove_subtree(folio_address(kho_test_state.fdt)); kho_test_cleanup(); } module_exit(kho_test_exit); diff --git a/lib/tests/Makefile b/lib/tests/Makefile index f7460831cfdd..601dba4b7d96 100644 --- a/lib/tests/Makefile +++ b/lib/tests/Makefile @@ -4,6 +4,7 @@ # KUnit tests CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN) +obj-$(CONFIG_BASE64_KUNIT) += base64_kunit.o obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o obj-$(CONFIG_BITS_TEST) += test_bits.o obj-$(CONFIG_BLACKHOLE_DEV_KUNIT_TEST) += blackhole_dev_kunit.o diff --git a/lib/tests/base64_kunit.c b/lib/tests/base64_kunit.c new file mode 100644 index 000000000000..f7252070c359 --- /dev/null +++ b/lib/tests/base64_kunit.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * base64_kunit_test.c - KUnit tests for base64 encoding and decoding functions + * + * Copyright (c) 2025, Guan-Chun Wu <409411716@gms.tku.edu.tw> + */ + +#include +#include + +/* ---------- Benchmark helpers ---------- */ +static u64 bench_encode_ns(const u8 *data, int len, char *dst, int reps, + enum base64_variant variant) +{ + u64 t0, t1; + + t0 = ktime_get_ns(); + for (int i = 0; i < reps; i++) + base64_encode(data, len, dst, true, variant); + t1 = ktime_get_ns(); + + return div64_u64(t1 - t0, (u64)reps); +} + +static u64 bench_decode_ns(const char *data, int len, u8 *dst, int reps, + enum base64_variant variant) +{ + u64 t0, t1; + + t0 = ktime_get_ns(); + for (int i = 0; i < reps; i++) + base64_decode(data, len, dst, true, variant); + t1 = ktime_get_ns(); + + return div64_u64(t1 - t0, (u64)reps); +} + +static void run_perf_and_check(struct kunit *test, const char *label, int size, + enum base64_variant variant) +{ + const int reps = 1000; + size_t outlen = DIV_ROUND_UP(size, 3) * 4; + u8 *in = kmalloc(size, GFP_KERNEL); + char *enc = kmalloc(outlen, GFP_KERNEL); + u8 *decoded = kmalloc(size, GFP_KERNEL); + + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, in); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, enc); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, decoded); + + get_random_bytes(in, size); + int enc_len = base64_encode(in, size, enc, true, variant); + int dec_len = base64_decode(enc, enc_len, decoded, true, variant); + + /* correctness sanity check */ + KUNIT_EXPECT_EQ(test, dec_len, size); + KUNIT_EXPECT_MEMEQ(test, decoded, in, size); + + /* benchmark encode */ + + u64 t1 = bench_encode_ns(in, size, enc, reps, variant); + + kunit_info(test, "[%s] encode run : %lluns", label, t1); + + u64 t2 = bench_decode_ns(enc, enc_len, decoded, reps, variant); + + kunit_info(test, "[%s] decode run : %lluns", label, t2); + + kfree(in); + kfree(enc); + kfree(decoded); +} + +static void base64_performance_tests(struct kunit *test) +{ + /* run on STD variant only */ + run_perf_and_check(test, "64B", 64, BASE64_STD); + run_perf_and_check(test, "1KB", 1024, BASE64_STD); +} + +/* ---------- Helpers for encode ---------- */ +static void expect_encode_ok(struct kunit *test, const u8 *src, int srclen, + const char *expected, bool padding, + enum base64_variant variant) +{ + char buf[128]; + int encoded_len = base64_encode(src, srclen, buf, padding, variant); + + buf[encoded_len] = '\0'; + + KUNIT_EXPECT_EQ(test, encoded_len, strlen(expected)); + KUNIT_EXPECT_STREQ(test, buf, expected); +} + +/* ---------- Helpers for decode ---------- */ +static void expect_decode_ok(struct kunit *test, const char *src, + const u8 *expected, int expected_len, bool padding, + enum base64_variant variant) +{ + u8 buf[128]; + int decoded_len = base64_decode(src, strlen(src), buf, padding, variant); + + KUNIT_EXPECT_EQ(test, decoded_len, expected_len); + KUNIT_EXPECT_MEMEQ(test, buf, expected, expected_len); +} + +static void expect_decode_err(struct kunit *test, const char *src, + int srclen, bool padding, + enum base64_variant variant) +{ + u8 buf[64]; + int decoded_len = base64_decode(src, srclen, buf, padding, variant); + + KUNIT_EXPECT_EQ(test, decoded_len, -1); +} + +/* ---------- Encode Tests ---------- */ +static void base64_std_encode_tests(struct kunit *test) +{ + /* With padding */ + expect_encode_ok(test, (const u8 *)"", 0, "", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"f", 1, "Zg==", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"fo", 2, "Zm8=", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foo", 3, "Zm9v", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foob", 4, "Zm9vYg==", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"fooba", 5, "Zm9vYmE=", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foobar", 6, "Zm9vYmFy", true, BASE64_STD); + + /* Extra cases with padding */ + expect_encode_ok(test, (const u8 *)"Hello, world!", 13, "SGVsbG8sIHdvcmxkIQ==", + true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"ABCDEFGHIJKLMNOPQRSTUVWXYZ", 26, + "QUJDREVGR0hJSktMTU5PUFFSU1RVVldYWVo=", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"abcdefghijklmnopqrstuvwxyz", 26, + "YWJjZGVmZ2hpamtsbW5vcHFyc3R1dnd4eXo=", true, BASE64_STD); + expect_encode_ok(test, (const u8 *)"0123456789+/", 12, "MDEyMzQ1Njc4OSsv", + true, BASE64_STD); + + /* Without padding */ + expect_encode_ok(test, (const u8 *)"", 0, "", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"f", 1, "Zg", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"fo", 2, "Zm8", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foo", 3, "Zm9v", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foob", 4, "Zm9vYg", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"fooba", 5, "Zm9vYmE", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"foobar", 6, "Zm9vYmFy", false, BASE64_STD); + + /* Extra cases without padding */ + expect_encode_ok(test, (const u8 *)"Hello, world!", 13, "SGVsbG8sIHdvcmxkIQ", + false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"ABCDEFGHIJKLMNOPQRSTUVWXYZ", 26, + "QUJDREVGR0hJSktMTU5PUFFSU1RVVldYWVo", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"abcdefghijklmnopqrstuvwxyz", 26, + "YWJjZGVmZ2hpamtsbW5vcHFyc3R1dnd4eXo", false, BASE64_STD); + expect_encode_ok(test, (const u8 *)"0123456789+/", 12, "MDEyMzQ1Njc4OSsv", + false, BASE64_STD); +} + +/* ---------- Decode Tests ---------- */ +static void base64_std_decode_tests(struct kunit *test) +{ + /* -------- With padding --------*/ + expect_decode_ok(test, "", (const u8 *)"", 0, true, BASE64_STD); + expect_decode_ok(test, "Zg==", (const u8 *)"f", 1, true, BASE64_STD); + expect_decode_ok(test, "Zm8=", (const u8 *)"fo", 2, true, BASE64_STD); + expect_decode_ok(test, "Zm9v", (const u8 *)"foo", 3, true, BASE64_STD); + expect_decode_ok(test, "Zm9vYg==", (const u8 *)"foob", 4, true, BASE64_STD); + expect_decode_ok(test, "Zm9vYmE=", (const u8 *)"fooba", 5, true, BASE64_STD); + expect_decode_ok(test, "Zm9vYmFy", (const u8 *)"foobar", 6, true, BASE64_STD); + expect_decode_ok(test, "SGVsbG8sIHdvcmxkIQ==", (const u8 *)"Hello, world!", 13, + true, BASE64_STD); + expect_decode_ok(test, "QUJDREVGR0hJSktMTU5PUFFSU1RVVldYWVo=", + (const u8 *)"ABCDEFGHIJKLMNOPQRSTUVWXYZ", 26, true, BASE64_STD); + expect_decode_ok(test, "YWJjZGVmZ2hpamtsbW5vcHFyc3R1dnd4eXo=", + (const u8 *)"abcdefghijklmnopqrstuvwxyz", 26, true, BASE64_STD); + + /* Error cases */ + expect_decode_err(test, "Zg=!", 4, true, BASE64_STD); + expect_decode_err(test, "Zm$=", 4, true, BASE64_STD); + expect_decode_err(test, "Z===", 4, true, BASE64_STD); + expect_decode_err(test, "Zg", 2, true, BASE64_STD); + expect_decode_err(test, "Zm9v====", 8, true, BASE64_STD); + expect_decode_err(test, "Zm==A", 5, true, BASE64_STD); + + { + char with_nul[4] = { 'Z', 'g', '\0', '=' }; + + expect_decode_err(test, with_nul, 4, true, BASE64_STD); + } + + /* -------- Without padding --------*/ + expect_decode_ok(test, "", (const u8 *)"", 0, false, BASE64_STD); + expect_decode_ok(test, "Zg", (const u8 *)"f", 1, false, BASE64_STD); + expect_decode_ok(test, "Zm8", (const u8 *)"fo", 2, false, BASE64_STD); + expect_decode_ok(test, "Zm9v", (const u8 *)"foo", 3, false, BASE64_STD); + expect_decode_ok(test, "Zm9vYg", (const u8 *)"foob", 4, false, BASE64_STD); + expect_decode_ok(test, "Zm9vYmE", (const u8 *)"fooba", 5, false, BASE64_STD); + expect_decode_ok(test, "Zm9vYmFy", (const u8 *)"foobar", 6, false, BASE64_STD); + expect_decode_ok(test, "TWFu", (const u8 *)"Man", 3, false, BASE64_STD); + expect_decode_ok(test, "SGVsbG8sIHdvcmxkIQ", (const u8 *)"Hello, world!", 13, + false, BASE64_STD); + expect_decode_ok(test, "QUJDREVGR0hJSktMTU5PUFFSU1RVVldYWVo", + (const u8 *)"ABCDEFGHIJKLMNOPQRSTUVWXYZ", 26, false, BASE64_STD); + expect_decode_ok(test, "YWJjZGVmZ2hpamtsbW5vcHFyc3R1dnd4eXo", + (const u8 *)"abcdefghijklmnopqrstuvwxyz", 26, false, BASE64_STD); + expect_decode_ok(test, "MDEyMzQ1Njc4OSsv", (const u8 *)"0123456789+/", 12, + false, BASE64_STD); + + /* Error cases */ + expect_decode_err(test, "Zg=!", 4, false, BASE64_STD); + expect_decode_err(test, "Zm$=", 4, false, BASE64_STD); + expect_decode_err(test, "Z===", 4, false, BASE64_STD); + expect_decode_err(test, "Zg=", 3, false, BASE64_STD); + expect_decode_err(test, "Zm9v====", 8, false, BASE64_STD); + expect_decode_err(test, "Zm==v", 4, false, BASE64_STD); + + { + char with_nul[4] = { 'Z', 'g', '\0', '=' }; + + expect_decode_err(test, with_nul, 4, false, BASE64_STD); + } +} + +/* ---------- Variant tests (URLSAFE / IMAP) ---------- */ +static void base64_variant_tests(struct kunit *test) +{ + const u8 sample1[] = { 0x00, 0xfb, 0xff, 0x7f, 0x80 }; + char std_buf[128], url_buf[128], imap_buf[128]; + u8 back[128]; + int n_std, n_url, n_imap, m; + int i; + + n_std = base64_encode(sample1, sizeof(sample1), std_buf, false, BASE64_STD); + n_url = base64_encode(sample1, sizeof(sample1), url_buf, false, BASE64_URLSAFE); + std_buf[n_std] = '\0'; + url_buf[n_url] = '\0'; + + for (i = 0; i < n_std; i++) { + if (std_buf[i] == '+') + std_buf[i] = '-'; + else if (std_buf[i] == '/') + std_buf[i] = '_'; + } + KUNIT_EXPECT_STREQ(test, std_buf, url_buf); + + m = base64_decode(url_buf, n_url, back, false, BASE64_URLSAFE); + KUNIT_EXPECT_EQ(test, m, (int)sizeof(sample1)); + KUNIT_EXPECT_MEMEQ(test, back, sample1, sizeof(sample1)); + + n_std = base64_encode(sample1, sizeof(sample1), std_buf, false, BASE64_STD); + n_imap = base64_encode(sample1, sizeof(sample1), imap_buf, false, BASE64_IMAP); + std_buf[n_std] = '\0'; + imap_buf[n_imap] = '\0'; + + for (i = 0; i < n_std; i++) + if (std_buf[i] == '/') + std_buf[i] = ','; + KUNIT_EXPECT_STREQ(test, std_buf, imap_buf); + + m = base64_decode(imap_buf, n_imap, back, false, BASE64_IMAP); + KUNIT_EXPECT_EQ(test, m, (int)sizeof(sample1)); + KUNIT_EXPECT_MEMEQ(test, back, sample1, sizeof(sample1)); + + { + const char *bad = "Zg=="; + u8 tmp[8]; + + m = base64_decode(bad, strlen(bad), tmp, false, BASE64_URLSAFE); + KUNIT_EXPECT_EQ(test, m, -1); + + m = base64_decode(bad, strlen(bad), tmp, false, BASE64_IMAP); + KUNIT_EXPECT_EQ(test, m, -1); + } +} + +/* ---------- Test registration ---------- */ +static struct kunit_case base64_test_cases[] = { + KUNIT_CASE(base64_performance_tests), + KUNIT_CASE(base64_std_encode_tests), + KUNIT_CASE(base64_std_decode_tests), + KUNIT_CASE(base64_variant_tests), + {} +}; + +static struct kunit_suite base64_test_suite = { + .name = "base64", + .test_cases = base64_test_cases, +}; + +kunit_test_suite(base64_test_suite); + +MODULE_AUTHOR("Guan-Chun Wu <409411716@gms.tku.edu.tw>"); +MODULE_DESCRIPTION("KUnit tests for Base64 encoding/decoding, including performance checks"); +MODULE_LICENSE("GPL"); diff --git a/lib/usercopy.c b/lib/usercopy.c index 7b17b83c8042..b00a3a957de6 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -12,7 +12,7 @@ /* out-of-line parts */ -#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST) +#if !defined(INLINE_COPY_FROM_USER) unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n) { return _inline_copy_from_user(to, from, n); @@ -20,7 +20,7 @@ unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n EXPORT_SYMBOL(_copy_from_user); #endif -#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST) +#if !defined(INLINE_COPY_TO_USER) unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { return _inline_copy_to_user(to, from, n); diff --git a/lib/xxhash.c b/lib/xxhash.c index cf629766f376..4125b3e3cf7f 100644 --- a/lib/xxhash.c +++ b/lib/xxhash.c @@ -73,21 +73,6 @@ static const uint64_t PRIME64_3 = 1609587929392839161ULL; static const uint64_t PRIME64_4 = 9650029242287828579ULL; static const uint64_t PRIME64_5 = 2870177450012600261ULL; -/*-************************** - * Utils - ***************************/ -void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src) -{ - memcpy(dst, src, sizeof(*dst)); -} -EXPORT_SYMBOL(xxh32_copy_state); - -void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src) -{ - memcpy(dst, src, sizeof(*dst)); -} -EXPORT_SYMBOL(xxh64_copy_state); - /*-*************************** * Simple Hash Functions ****************************/ @@ -239,20 +224,6 @@ EXPORT_SYMBOL(xxh64); /*-************************************************** * Advanced Hash Functions ***************************************************/ -void xxh32_reset(struct xxh32_state *statePtr, const uint32_t seed) -{ - /* use a local state for memcpy() to avoid strict-aliasing warnings */ - struct xxh32_state state; - - memset(&state, 0, sizeof(state)); - state.v1 = seed + PRIME32_1 + PRIME32_2; - state.v2 = seed + PRIME32_2; - state.v3 = seed + 0; - state.v4 = seed - PRIME32_1; - memcpy(statePtr, &state, sizeof(state)); -} -EXPORT_SYMBOL(xxh32_reset); - void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed) { /* use a local state for memcpy() to avoid strict-aliasing warnings */ diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c index 8237db17eee3..610d58d947ab 100644 --- a/lib/xz/xz_dec_bcj.c +++ b/lib/xz/xz_dec_bcj.c @@ -20,7 +20,6 @@ struct xz_dec_bcj { enum { BCJ_X86 = 4, /* x86 or x86-64 */ BCJ_POWERPC = 5, /* Big endian only */ - BCJ_IA64 = 6, /* Big or little endian */ BCJ_ARM = 7, /* Little endian only */ BCJ_ARMTHUMB = 8, /* Little endian only */ BCJ_SPARC = 9, /* Big or little endian */ @@ -180,92 +179,6 @@ static size_t bcj_powerpc(struct xz_dec_bcj *s, uint8_t *buf, size_t size) } #endif -#ifdef XZ_DEC_IA64 -static size_t bcj_ia64(struct xz_dec_bcj *s, uint8_t *buf, size_t size) -{ - static const uint8_t branch_table[32] = { - 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, - 4, 4, 6, 6, 0, 0, 7, 7, - 4, 4, 0, 0, 4, 4, 0, 0 - }; - - /* - * The local variables take a little bit stack space, but it's less - * than what LZMA2 decoder takes, so it doesn't make sense to reduce - * stack usage here without doing that for the LZMA2 decoder too. - */ - - /* Loop counters */ - size_t i; - size_t j; - - /* Instruction slot (0, 1, or 2) in the 128-bit instruction word */ - uint32_t slot; - - /* Bitwise offset of the instruction indicated by slot */ - uint32_t bit_pos; - - /* bit_pos split into byte and bit parts */ - uint32_t byte_pos; - uint32_t bit_res; - - /* Address part of an instruction */ - uint32_t addr; - - /* Mask used to detect which instructions to convert */ - uint32_t mask; - - /* 41-bit instruction stored somewhere in the lowest 48 bits */ - uint64_t instr; - - /* Instruction normalized with bit_res for easier manipulation */ - uint64_t norm; - - size &= ~(size_t)15; - - for (i = 0; i < size; i += 16) { - mask = branch_table[buf[i] & 0x1F]; - for (slot = 0, bit_pos = 5; slot < 3; ++slot, bit_pos += 41) { - if (((mask >> slot) & 1) == 0) - continue; - - byte_pos = bit_pos >> 3; - bit_res = bit_pos & 7; - instr = 0; - for (j = 0; j < 6; ++j) - instr |= (uint64_t)(buf[i + j + byte_pos]) - << (8 * j); - - norm = instr >> bit_res; - - if (((norm >> 37) & 0x0F) == 0x05 - && ((norm >> 9) & 0x07) == 0) { - addr = (norm >> 13) & 0x0FFFFF; - addr |= ((uint32_t)(norm >> 36) & 1) << 20; - addr <<= 4; - addr -= s->pos + (uint32_t)i; - addr >>= 4; - - norm &= ~((uint64_t)0x8FFFFF << 13); - norm |= (uint64_t)(addr & 0x0FFFFF) << 13; - norm |= (uint64_t)(addr & 0x100000) - << (36 - 20); - - instr &= (1 << bit_res) - 1; - instr |= norm << bit_res; - - for (j = 0; j < 6; j++) - buf[i + j + byte_pos] - = (uint8_t)(instr >> (8 * j)); - } - } - } - - return i; -} -#endif - #ifdef XZ_DEC_ARM static size_t bcj_arm(struct xz_dec_bcj *s, uint8_t *buf, size_t size) { @@ -509,11 +422,6 @@ static void bcj_apply(struct xz_dec_bcj *s, filtered = bcj_powerpc(s, buf, size); break; #endif -#ifdef XZ_DEC_IA64 - case BCJ_IA64: - filtered = bcj_ia64(s, buf, size); - break; -#endif #ifdef XZ_DEC_ARM case BCJ_ARM: filtered = bcj_arm(s, buf, size); @@ -699,9 +607,6 @@ enum xz_ret xz_dec_bcj_reset(struct xz_dec_bcj *s, uint8_t id) #ifdef XZ_DEC_POWERPC case BCJ_POWERPC: #endif -#ifdef XZ_DEC_IA64 - case BCJ_IA64: -#endif #ifdef XZ_DEC_ARM case BCJ_ARM: #endif diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index 8409784b1639..6775078f3cce 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -24,9 +24,6 @@ # ifdef CONFIG_XZ_DEC_POWERPC # define XZ_DEC_POWERPC # endif -# ifdef CONFIG_XZ_DEC_IA64 -# define XZ_DEC_IA64 -# endif # ifdef CONFIG_XZ_DEC_ARM # define XZ_DEC_ARM # endif @@ -103,7 +100,6 @@ */ #ifndef XZ_DEC_BCJ # if defined(XZ_DEC_X86) || defined(XZ_DEC_POWERPC) \ - || defined(XZ_DEC_IA64) \ || defined(XZ_DEC_ARM) || defined(XZ_DEC_ARMTHUMB) \ || defined(XZ_DEC_SPARC) || defined(XZ_DEC_ARM64) \ || defined(XZ_DEC_RISCV) diff --git a/mm/Makefile b/mm/Makefile index 00ceb2418b64..2d0570a16e5b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -100,6 +100,7 @@ obj-$(CONFIG_NUMA) += memory-tiers.o obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o obj-$(CONFIG_PAGE_COUNTER) += page_counter.o +obj-$(CONFIG_LIVEUPDATE) += memfd_luo.o obj-$(CONFIG_MEMCG_V1) += memcontrol-v1.o obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o ifdef CONFIG_SWAP diff --git a/mm/internal.h b/mm/internal.h index 89790def1bae..e430da900430 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1582,6 +1582,12 @@ void __meminit __init_page_from_nid(unsigned long pfn, int nid); unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); +int shmem_add_to_page_cache(struct folio *folio, + struct address_space *mapping, + pgoff_t index, void *expected, gfp_t gfp); +int shmem_inode_acct_blocks(struct inode *inode, long pages); +bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped); + #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) diff --git a/mm/memblock.c b/mm/memblock.c index f0f2dc66e9a2..905d06b16348 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2445,60 +2445,59 @@ int reserve_mem_release_by_name(const char *name) #define MEMBLOCK_KHO_FDT "memblock" #define MEMBLOCK_KHO_NODE_COMPATIBLE "memblock-v1" #define RESERVE_MEM_KHO_NODE_COMPATIBLE "reserve-mem-v1" -static struct page *kho_fdt; -static int reserve_mem_kho_finalize(struct kho_serialization *ser) +static int __init reserved_mem_preserve(void) { - int err = 0, i; + unsigned int nr_preserved = 0; + int err; - for (i = 0; i < reserved_mem_count; i++) { + for (unsigned int i = 0; i < reserved_mem_count; i++, nr_preserved++) { struct reserve_mem_table *map = &reserved_mem_table[i]; struct page *page = phys_to_page(map->start); unsigned int nr_pages = map->size >> PAGE_SHIFT; - err |= kho_preserve_pages(page, nr_pages); + err = kho_preserve_pages(page, nr_pages); + if (err) + goto err_unpreserve; } - err |= kho_preserve_folio(page_folio(kho_fdt)); - err |= kho_add_subtree(ser, MEMBLOCK_KHO_FDT, page_to_virt(kho_fdt)); + return 0; - return notifier_from_errno(err); -} +err_unpreserve: + for (unsigned int i = 0; i < nr_preserved; i++) { + struct reserve_mem_table *map = &reserved_mem_table[i]; + struct page *page = phys_to_page(map->start); + unsigned int nr_pages = map->size >> PAGE_SHIFT; -static int reserve_mem_kho_notifier(struct notifier_block *self, - unsigned long cmd, void *v) -{ - switch (cmd) { - case KEXEC_KHO_FINALIZE: - return reserve_mem_kho_finalize((struct kho_serialization *)v); - case KEXEC_KHO_ABORT: - return NOTIFY_DONE; - default: - return NOTIFY_BAD; + kho_unpreserve_pages(page, nr_pages); } -} -static struct notifier_block reserve_mem_kho_nb = { - .notifier_call = reserve_mem_kho_notifier, -}; + return err; +} static int __init prepare_kho_fdt(void) { - int err = 0, i; + struct page *fdt_page; void *fdt; + int err; - kho_fdt = alloc_page(GFP_KERNEL); - if (!kho_fdt) - return -ENOMEM; + fdt_page = alloc_page(GFP_KERNEL); + if (!fdt_page) { + err = -ENOMEM; + goto err_report; + } - fdt = page_to_virt(kho_fdt); + fdt = page_to_virt(fdt_page); + err = kho_preserve_pages(fdt_page, 1); + if (err) + goto err_free_fdt; err |= fdt_create(fdt, PAGE_SIZE); err |= fdt_finish_reservemap(fdt); - err |= fdt_begin_node(fdt, ""); err |= fdt_property_string(fdt, "compatible", MEMBLOCK_KHO_NODE_COMPATIBLE); - for (i = 0; i < reserved_mem_count; i++) { + + for (unsigned int i = 0; !err && i < reserved_mem_count; i++) { struct reserve_mem_table *map = &reserved_mem_table[i]; err |= fdt_begin_node(fdt, map->name); @@ -2508,14 +2507,29 @@ static int __init prepare_kho_fdt(void) err |= fdt_end_node(fdt); } err |= fdt_end_node(fdt); - err |= fdt_finish(fdt); - if (err) { - pr_err("failed to prepare memblock FDT for KHO: %d\n", err); - put_page(kho_fdt); - kho_fdt = NULL; - } + if (err) + goto err_unpreserve_fdt; + + err = kho_add_subtree(MEMBLOCK_KHO_FDT, fdt); + if (err) + goto err_unpreserve_fdt; + + err = reserved_mem_preserve(); + if (err) + goto err_remove_subtree; + + return 0; + +err_remove_subtree: + kho_remove_subtree(fdt); +err_unpreserve_fdt: + kho_unpreserve_pages(fdt_page, 1); +err_free_fdt: + put_page(fdt_page); +err_report: + pr_err("failed to prepare memblock FDT for KHO: %d\n", err); return err; } @@ -2530,13 +2544,6 @@ static int __init reserve_mem_init(void) err = prepare_kho_fdt(); if (err) return err; - - err = register_kho_notifier(&reserve_mem_kho_nb); - if (err) { - put_page(kho_fdt); - kho_fdt = NULL; - } - return err; } late_initcall(reserve_mem_init); diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c new file mode 100644 index 000000000000..4f6ba63b4310 --- /dev/null +++ b/mm/memfd_luo.c @@ -0,0 +1,516 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + * + * Copyright (C) 2025 Amazon.com Inc. or its affiliates. + * Pratyush Yadav + */ + +/** + * DOC: Memfd Preservation via LUO + * + * Overview + * ======== + * + * Memory file descriptors (memfd) can be preserved over a kexec using the Live + * Update Orchestrator (LUO) file preservation. This allows userspace to + * transfer its memory contents to the next kernel after a kexec. + * + * The preservation is not intended to be transparent. Only select properties of + * the file are preserved. All others are reset to default. The preserved + * properties are described below. + * + * .. note:: + * The LUO API is not stabilized yet, so the preserved properties of a memfd + * are also not stable and are subject to backwards incompatible changes. + * + * .. note:: + * Currently a memfd backed by Hugetlb is not supported. Memfds created + * with ``MFD_HUGETLB`` will be rejected. + * + * Preserved Properties + * ==================== + * + * The following properties of the memfd are preserved across kexec: + * + * File Contents + * All data stored in the file is preserved. + * + * File Size + * The size of the file is preserved. Holes in the file are filled by + * allocating pages for them during preservation. + * + * File Position + * The current file position is preserved, allowing applications to continue + * reading/writing from their last position. + * + * File Status Flags + * memfds are always opened with ``O_RDWR`` and ``O_LARGEFILE``. This property + * is maintained. + * + * Non-Preserved Properties + * ======================== + * + * All properties which are not preserved must be assumed to be reset to + * default. This section describes some of those properties which may be more of + * note. + * + * ``FD_CLOEXEC`` flag + * A memfd can be created with the ``MFD_CLOEXEC`` flag that sets the + * ``FD_CLOEXEC`` on the file. This flag is not preserved and must be set + * again after restore via ``fcntl()``. + * + * Seals + * File seals are not preserved. The file is unsealed on restore and if + * needed, must be sealed again via ``fcntl()``. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +static int memfd_luo_preserve_folios(struct file *file, + struct kho_vmalloc *kho_vmalloc, + struct memfd_luo_folio_ser **out_folios_ser, + u64 *nr_foliosp) +{ + struct inode *inode = file_inode(file); + struct memfd_luo_folio_ser *folios_ser; + unsigned int max_folios; + long i, size, nr_pinned; + struct folio **folios; + int err = -EINVAL; + pgoff_t offset; + u64 nr_folios; + + size = i_size_read(inode); + /* + * If the file has zero size, then the folios and nr_folios properties + * are not set. + */ + if (!size) { + *nr_foliosp = 0; + *out_folios_ser = NULL; + memset(kho_vmalloc, 0, sizeof(*kho_vmalloc)); + return 0; + } + + /* + * Guess the number of folios based on inode size. Real number might end + * up being smaller if there are higher order folios. + */ + max_folios = PAGE_ALIGN(size) / PAGE_SIZE; + folios = kvmalloc_array(max_folios, sizeof(*folios), GFP_KERNEL); + if (!folios) + return -ENOMEM; + + /* + * Pin the folios so they don't move around behind our back. This also + * ensures none of the folios are in CMA -- which ensures they don't + * fall in KHO scratch memory. It also moves swapped out folios back to + * memory. + * + * A side effect of doing this is that it allocates a folio for all + * indices in the file. This might waste memory on sparse memfds. If + * that is really a problem in the future, we can have a + * memfd_pin_folios() variant that does not allocate a page on empty + * slots. + */ + nr_pinned = memfd_pin_folios(file, 0, size - 1, folios, max_folios, + &offset); + if (nr_pinned < 0) { + err = nr_pinned; + pr_err("failed to pin folios: %d\n", err); + goto err_free_folios; + } + nr_folios = nr_pinned; + + folios_ser = vcalloc(nr_folios, sizeof(*folios_ser)); + if (!folios_ser) { + err = -ENOMEM; + goto err_unpin; + } + + for (i = 0; i < nr_folios; i++) { + struct memfd_luo_folio_ser *pfolio = &folios_ser[i]; + struct folio *folio = folios[i]; + unsigned int flags = 0; + + err = kho_preserve_folio(folio); + if (err) + goto err_unpreserve; + + if (folio_test_dirty(folio)) + flags |= MEMFD_LUO_FOLIO_DIRTY; + if (folio_test_uptodate(folio)) + flags |= MEMFD_LUO_FOLIO_UPTODATE; + + pfolio->pfn = folio_pfn(folio); + pfolio->flags = flags; + pfolio->index = folio->index; + } + + err = kho_preserve_vmalloc(folios_ser, kho_vmalloc); + if (err) + goto err_unpreserve; + + kvfree(folios); + *nr_foliosp = nr_folios; + *out_folios_ser = folios_ser; + + /* + * Note: folios_ser is purposely not freed here. It is preserved + * memory (via KHO). In the 'unpreserve' path, we use the vmap pointer + * that is passed via private_data. + */ + return 0; + +err_unpreserve: + for (i = i - 1; i >= 0; i--) + kho_unpreserve_folio(folios[i]); + vfree(folios_ser); +err_unpin: + unpin_folios(folios, nr_folios); +err_free_folios: + kvfree(folios); + + return err; +} + +static void memfd_luo_unpreserve_folios(struct kho_vmalloc *kho_vmalloc, + struct memfd_luo_folio_ser *folios_ser, + u64 nr_folios) +{ + long i; + + if (!nr_folios) + return; + + kho_unpreserve_vmalloc(kho_vmalloc); + + for (i = 0; i < nr_folios; i++) { + const struct memfd_luo_folio_ser *pfolio = &folios_ser[i]; + struct folio *folio; + + if (!pfolio->pfn) + continue; + + folio = pfn_folio(pfolio->pfn); + + kho_unpreserve_folio(folio); + unpin_folio(folio); + } + + vfree(folios_ser); +} + +static int memfd_luo_preserve(struct liveupdate_file_op_args *args) +{ + struct inode *inode = file_inode(args->file); + struct memfd_luo_folio_ser *folios_ser; + struct memfd_luo_ser *ser; + u64 nr_folios; + int err = 0; + + inode_lock(inode); + shmem_freeze(inode, true); + + /* Allocate the main serialization structure in preserved memory */ + ser = kho_alloc_preserve(sizeof(*ser)); + if (IS_ERR(ser)) { + err = PTR_ERR(ser); + goto err_unlock; + } + + ser->pos = args->file->f_pos; + ser->size = i_size_read(inode); + + err = memfd_luo_preserve_folios(args->file, &ser->folios, + &folios_ser, &nr_folios); + if (err) + goto err_free_ser; + + ser->nr_folios = nr_folios; + inode_unlock(inode); + + args->private_data = folios_ser; + args->serialized_data = virt_to_phys(ser); + + return 0; + +err_free_ser: + kho_unpreserve_free(ser); +err_unlock: + shmem_freeze(inode, false); + inode_unlock(inode); + return err; +} + +static int memfd_luo_freeze(struct liveupdate_file_op_args *args) +{ + struct memfd_luo_ser *ser; + + if (WARN_ON_ONCE(!args->serialized_data)) + return -EINVAL; + + ser = phys_to_virt(args->serialized_data); + + /* + * The pos might have changed since prepare. Everything else stays the + * same. + */ + ser->pos = args->file->f_pos; + + return 0; +} + +static void memfd_luo_unpreserve(struct liveupdate_file_op_args *args) +{ + struct inode *inode = file_inode(args->file); + struct memfd_luo_ser *ser; + + if (WARN_ON_ONCE(!args->serialized_data)) + return; + + inode_lock(inode); + shmem_freeze(inode, false); + + ser = phys_to_virt(args->serialized_data); + + memfd_luo_unpreserve_folios(&ser->folios, args->private_data, + ser->nr_folios); + + kho_unpreserve_free(ser); + inode_unlock(inode); +} + +static void memfd_luo_discard_folios(const struct memfd_luo_folio_ser *folios_ser, + u64 nr_folios) +{ + u64 i; + + for (i = 0; i < nr_folios; i++) { + const struct memfd_luo_folio_ser *pfolio = &folios_ser[i]; + struct folio *folio; + phys_addr_t phys; + + if (!pfolio->pfn) + continue; + + phys = PFN_PHYS(pfolio->pfn); + folio = kho_restore_folio(phys); + if (!folio) { + pr_warn_ratelimited("Unable to restore folio at physical address: %llx\n", + phys); + continue; + } + + folio_put(folio); + } +} + +static void memfd_luo_finish(struct liveupdate_file_op_args *args) +{ + struct memfd_luo_folio_ser *folios_ser; + struct memfd_luo_ser *ser; + + if (args->retrieved) + return; + + ser = phys_to_virt(args->serialized_data); + if (!ser) + return; + + if (ser->nr_folios) { + folios_ser = kho_restore_vmalloc(&ser->folios); + if (!folios_ser) + goto out; + + memfd_luo_discard_folios(folios_ser, ser->nr_folios); + vfree(folios_ser); + } + +out: + kho_restore_free(ser); +} + +static int memfd_luo_retrieve_folios(struct file *file, + struct memfd_luo_folio_ser *folios_ser, + u64 nr_folios) +{ + struct inode *inode = file_inode(file); + struct address_space *mapping = inode->i_mapping; + struct folio *folio; + int err = -EIO; + long i; + + for (i = 0; i < nr_folios; i++) { + const struct memfd_luo_folio_ser *pfolio = &folios_ser[i]; + phys_addr_t phys; + u64 index; + int flags; + + if (!pfolio->pfn) + continue; + + phys = PFN_PHYS(pfolio->pfn); + folio = kho_restore_folio(phys); + if (!folio) { + pr_err("Unable to restore folio at physical address: %llx\n", + phys); + goto put_folios; + } + index = pfolio->index; + flags = pfolio->flags; + + /* Set up the folio for insertion. */ + __folio_set_locked(folio); + __folio_set_swapbacked(folio); + + err = mem_cgroup_charge(folio, NULL, mapping_gfp_mask(mapping)); + if (err) { + pr_err("shmem: failed to charge folio index %ld: %d\n", + i, err); + goto unlock_folio; + } + + err = shmem_add_to_page_cache(folio, mapping, index, NULL, + mapping_gfp_mask(mapping)); + if (err) { + pr_err("shmem: failed to add to page cache folio index %ld: %d\n", + i, err); + goto unlock_folio; + } + + if (flags & MEMFD_LUO_FOLIO_UPTODATE) + folio_mark_uptodate(folio); + if (flags & MEMFD_LUO_FOLIO_DIRTY) + folio_mark_dirty(folio); + + err = shmem_inode_acct_blocks(inode, 1); + if (err) { + pr_err("shmem: failed to account folio index %ld: %d\n", + i, err); + goto unlock_folio; + } + + shmem_recalc_inode(inode, 1, 0); + folio_add_lru(folio); + folio_unlock(folio); + folio_put(folio); + } + + return 0; + +unlock_folio: + folio_unlock(folio); + folio_put(folio); +put_folios: + /* + * Note: don't free the folios already added to the file. They will be + * freed when the file is freed. Free the ones not added yet here. + */ + for (long j = i + 1; j < nr_folios; j++) { + const struct memfd_luo_folio_ser *pfolio = &folios_ser[j]; + + folio = kho_restore_folio(pfolio->pfn); + if (folio) + folio_put(folio); + } + + return err; +} + +static int memfd_luo_retrieve(struct liveupdate_file_op_args *args) +{ + struct memfd_luo_folio_ser *folios_ser; + struct memfd_luo_ser *ser; + struct file *file; + int err; + + ser = phys_to_virt(args->serialized_data); + if (!ser) + return -EINVAL; + + file = shmem_file_setup("", 0, VM_NORESERVE); + + if (IS_ERR(file)) { + pr_err("failed to setup file: %pe\n", file); + return PTR_ERR(file); + } + + vfs_setpos(file, ser->pos, MAX_LFS_FILESIZE); + file->f_inode->i_size = ser->size; + + if (ser->nr_folios) { + folios_ser = kho_restore_vmalloc(&ser->folios); + if (!folios_ser) { + err = -EINVAL; + goto put_file; + } + + err = memfd_luo_retrieve_folios(file, folios_ser, ser->nr_folios); + vfree(folios_ser); + if (err) + goto put_file; + } + + args->file = file; + kho_restore_free(ser); + + return 0; + +put_file: + fput(file); + + return err; +} + +static bool memfd_luo_can_preserve(struct liveupdate_file_handler *handler, + struct file *file) +{ + struct inode *inode = file_inode(file); + + return shmem_file(file) && !inode->i_nlink; +} + +static const struct liveupdate_file_ops memfd_luo_file_ops = { + .freeze = memfd_luo_freeze, + .finish = memfd_luo_finish, + .retrieve = memfd_luo_retrieve, + .preserve = memfd_luo_preserve, + .unpreserve = memfd_luo_unpreserve, + .can_preserve = memfd_luo_can_preserve, + .owner = THIS_MODULE, +}; + +static struct liveupdate_file_handler memfd_luo_handler = { + .ops = &memfd_luo_file_ops, + .compatible = MEMFD_LUO_FH_COMPATIBLE, +}; + +static int __init memfd_luo_init(void) +{ + int err = liveupdate_register_file_handler(&memfd_luo_handler); + + if (err && err != -EOPNOTSUPP) { + pr_err("Could not register luo filesystem handler: %pe\n", + ERR_PTR(err)); + + return err; + } + + return 0; +} +late_initcall(memfd_luo_init); diff --git a/mm/shmem.c b/mm/shmem.c index d578d8e765d7..3f194c9842a8 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -174,20 +174,20 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_NORESERVE) ? + return (flags & SHMEM_F_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { - if (!(flags & VM_NORESERVE)) + if (!(flags & SHMEM_F_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { - if (!(flags & VM_NORESERVE)) { + if (!(flags & SHMEM_F_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); @@ -205,7 +205,7 @@ static inline int shmem_reacct_size(unsigned long flags, */ static inline int shmem_acct_blocks(unsigned long flags, long pages) { - if (!(flags & VM_NORESERVE)) + if (!(flags & SHMEM_F_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, @@ -214,11 +214,11 @@ static inline int shmem_acct_blocks(unsigned long flags, long pages) static inline void shmem_unacct_blocks(unsigned long flags, long pages) { - if (flags & VM_NORESERVE) + if (flags & SHMEM_F_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } -static int shmem_inode_acct_blocks(struct inode *inode, long pages) +int shmem_inode_acct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); @@ -434,7 +434,7 @@ static void shmem_free_inode(struct super_block *sb, size_t freed_ispace) * * Return: true if swapped was incremented from 0, for shmem_writeout(). */ -static bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped) +bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped) { struct shmem_inode_info *info = SHMEM_I(inode); bool first_swapped = false; @@ -878,9 +878,9 @@ static void shmem_update_stats(struct folio *folio, int nr_pages) /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ -static int shmem_add_to_page_cache(struct folio *folio, - struct address_space *mapping, - pgoff_t index, void *expected, gfp_t gfp) +int shmem_add_to_page_cache(struct folio *folio, + struct address_space *mapping, + pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); unsigned long nr = folio_nr_pages(folio); @@ -1314,6 +1314,8 @@ static int shmem_setattr(struct mnt_idmap *idmap, return -EPERM; if (newsize != oldsize) { + if (info->flags & SHMEM_F_MAPPING_FROZEN) + return -EPERM; error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) @@ -1568,7 +1570,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug, int nr_pages; bool split = false; - if ((info->flags & VM_LOCKED) || sbinfo->noswap) + if ((info->flags & SHMEM_F_LOCKED) || sbinfo->noswap) goto redirty; if (!total_swap_pages) @@ -2926,15 +2928,15 @@ int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) * ipc_lock_object() when called from shmctl_do_lock(), * no serialization needed when called from shm_destroy(). */ - if (lock && !(info->flags & VM_LOCKED)) { + if (lock && !(info->flags & SHMEM_F_LOCKED)) { if (!user_shm_lock(inode->i_size, ucounts)) goto out_nomem; - info->flags |= VM_LOCKED; + info->flags |= SHMEM_F_LOCKED; mapping_set_unevictable(file->f_mapping); } - if (!lock && (info->flags & VM_LOCKED) && ucounts) { + if (!lock && (info->flags & SHMEM_F_LOCKED) && ucounts) { user_shm_unlock(inode->i_size, ucounts); - info->flags &= ~VM_LOCKED; + info->flags &= ~SHMEM_F_LOCKED; mapping_clear_unevictable(file->f_mapping); } retval = 0; @@ -3079,7 +3081,7 @@ static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, spin_lock_init(&info->lock); atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; - info->flags = flags & VM_NORESERVE; + info->flags = (flags & VM_NORESERVE) ? SHMEM_F_NORESERVE : 0; info->i_crtime = inode_get_mtime(inode); info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; @@ -3306,6 +3308,10 @@ shmem_write_begin(const struct kiocb *iocb, struct address_space *mapping, return -EPERM; } + if (unlikely((info->flags & SHMEM_F_MAPPING_FROZEN) && + pos + len > inode->i_size)) + return -EPERM; + ret = shmem_get_folio(inode, index, pos + len, &folio, SGP_WRITE); if (ret) return ret; @@ -3679,6 +3685,11 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, inode_lock(inode); + if (info->flags & SHMEM_F_MAPPING_FROZEN) { + error = -EPERM; + goto out; + } + if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); @@ -5799,8 +5810,10 @@ static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, /* common code */ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, - loff_t size, unsigned long flags, unsigned int i_flags) + loff_t size, unsigned long vm_flags, + unsigned int i_flags) { + unsigned long flags = (vm_flags & VM_NORESERVE) ? SHMEM_F_NORESERVE : 0; struct inode *inode; struct file *res; @@ -5817,7 +5830,7 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, return ERR_PTR(-ENOMEM); inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL, - S_IFREG | S_IRWXUGO, 0, flags); + S_IFREG | S_IRWXUGO, 0, vm_flags); if (IS_ERR(inode)) { shmem_unacct_size(flags, size); return ERR_CAST(inode); diff --git a/rust/helpers/rbtree.c b/rust/helpers/rbtree.c index 6d404b84a9b5..2a0eabbb4160 100644 --- a/rust/helpers/rbtree.c +++ b/rust/helpers/rbtree.c @@ -7,3 +7,13 @@ void rust_helper_rb_link_node(struct rb_node *node, struct rb_node *parent, { rb_link_node(node, parent, rb_link); } + +struct rb_node *rust_helper_rb_first(const struct rb_root *root) +{ + return rb_first(root); +} + +struct rb_node *rust_helper_rb_last(const struct rb_root *root) +{ + return rb_last(root); +} diff --git a/rust/helpers/uaccess.c b/rust/helpers/uaccess.c index f49076f813cd..4629b2d15529 100644 --- a/rust/helpers/uaccess.c +++ b/rust/helpers/uaccess.c @@ -13,3 +13,15 @@ unsigned long rust_helper_copy_to_user(void __user *to, const void *from, { return copy_to_user(to, from, n); } + +#ifdef INLINE_COPY_FROM_USER +unsigned long rust_helper__copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return _inline_copy_from_user(to, from, n); +} + +unsigned long rust_helper__copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return _inline_copy_to_user(to, from, n); +} +#endif diff --git a/samples/Kconfig b/samples/Kconfig index 6e072a5f1ed8..5bc7c9e5a59e 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -23,11 +23,11 @@ config SAMPLE_TRACE_CUSTOM_EVENTS This builds the custom trace event example module. config SAMPLE_TRACE_PRINTK - tristate "Build trace_printk module - tests various trace_printk formats" + tristate "Build trace_printk module - tests various trace_printk formats" depends on EVENT_TRACING && m help - This builds a module that calls trace_printk() and can be used to - test various trace_printk() calls from a module. + This builds a module that calls trace_printk() and can be used to + test various trace_printk() calls from a module. config SAMPLE_FTRACE_DIRECT tristate "Build register_ftrace_direct() example" @@ -54,11 +54,11 @@ config SAMPLE_FTRACE_OPS measures the time taken to invoke one function a number of times. config SAMPLE_TRACE_ARRAY - tristate "Build sample module for kernel access to Ftrace instances" + tristate "Build sample module for kernel access to Ftrace instances" depends on EVENT_TRACING && m help - This builds a module that demonstrates the use of various APIs to - access Ftrace instances from within the kernel. + This builds a module that demonstrates the use of various APIs to + access Ftrace instances from within the kernel. config SAMPLE_KOBJECT tristate "Build kobject examples" @@ -290,11 +290,11 @@ config SAMPLE_CORESIGHT_SYSCFG configurations and easily load them into the system at runtime. config SAMPLE_KMEMLEAK - tristate "Simple test for the kernel memory leak detector" - depends on DEBUG_KMEMLEAK && m - help - Build a sample program which have explicitly leaks memory to test - kmemleak + tristate "Simple test for the kernel memory leak detector" + depends on DEBUG_KMEMLEAK && m + help + Build a sample program which have explicitly leaks memory to test + kmemleak. config SAMPLE_CGROUP bool "Build cgroup sample code" diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile index 6554b73a75c8..9256ca5d762b 100644 --- a/samples/vfs/Makefile +++ b/samples/vfs/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only userprogs-always-y += test-fsmount test-statx mountinfo test-list-all-mounts +userccflags += -I $(srctree)/tools/testing/selftests/ userccflags += -I usr/include diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 92669904eecc..d58ca9655ab7 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -860,6 +860,10 @@ our %deprecated_apis = ( "kunmap" => "kunmap_local", "kmap_atomic" => "kmap_local_page", "kunmap_atomic" => "kunmap_local", + #These should be enough to drive away new IDR users + "DEFINE_IDR" => "DEFINE_XARRAY", + "idr_init" => "xa_init", + "idr_init_base" => "xa_init_flags" ); #Create a search pattern for all these strings to speed up a loop below @@ -3345,6 +3349,13 @@ sub process { } } +# Check for auto-generated unhandled placeholder text (mostly for cover letters) + if (($in_commit_log || $in_header_lines) && + $rawline =~ /(?:SUBJECT|BLURB) HERE/) { + ERROR("PLACEHOLDER_USE", + "Placeholder text detected\n" . $herecurr); + } + # Check for git id commit length and improperly formed commit descriptions # A correctly formed commit description is: # commit ("Complete commit subject") diff --git a/scripts/gdb/linux/bpf.py b/scripts/gdb/linux/bpf.py new file mode 100644 index 000000000000..1870534ef6f9 --- /dev/null +++ b/scripts/gdb/linux/bpf.py @@ -0,0 +1,253 @@ +# SPDX-License-Identifier: GPL-2.0 + +import json +import subprocess +import tempfile + +import gdb + +from linux import constants, lists, radixtree, utils + + +if constants.LX_CONFIG_BPF and constants.LX_CONFIG_BPF_JIT: + bpf_ksym_type = utils.CachedType("struct bpf_ksym") +if constants.LX_CONFIG_BPF_SYSCALL: + bpf_prog_type = utils.CachedType("struct bpf_prog") + + +def get_ksym_name(ksym): + name = ksym["name"].bytes + end = name.find(b"\x00") + if end != -1: + name = name[:end] + return name.decode() + + +def list_ksyms(): + if not (constants.LX_CONFIG_BPF and constants.LX_CONFIG_BPF_JIT): + return [] + bpf_kallsyms = gdb.parse_and_eval("&bpf_kallsyms") + bpf_ksym_ptr_type = bpf_ksym_type.get_type().pointer() + return list(lists.list_for_each_entry(bpf_kallsyms, + bpf_ksym_ptr_type, + "lnode")) + + +class KsymAddBreakpoint(gdb.Breakpoint): + def __init__(self, monitor): + super(KsymAddBreakpoint, self).__init__("bpf_ksym_add", internal=True) + self.silent = True + self.monitor = monitor + + def stop(self): + self.monitor.add(gdb.parse_and_eval("ksym")) + return False + + +class KsymRemoveBreakpoint(gdb.Breakpoint): + def __init__(self, monitor): + super(KsymRemoveBreakpoint, self).__init__("bpf_ksym_del", + internal=True) + self.silent = True + self.monitor = monitor + + def stop(self): + self.monitor.remove(gdb.parse_and_eval("ksym")) + return False + + +class KsymMonitor: + def __init__(self, add, remove): + self.add = add + self.remove = remove + + self.add_bp = KsymAddBreakpoint(self) + self.remove_bp = KsymRemoveBreakpoint(self) + + self.notify_initial() + + def notify_initial(self): + for ksym in list_ksyms(): + self.add(ksym) + + def delete(self): + self.add_bp.delete() + self.remove_bp.delete() + + +def list_progs(): + if not constants.LX_CONFIG_BPF_SYSCALL: + return [] + idr_rt = gdb.parse_and_eval("&prog_idr.idr_rt") + bpf_prog_ptr_type = bpf_prog_type.get_type().pointer() + progs = [] + for _, slot in radixtree.for_each_slot(idr_rt): + prog = slot.dereference().cast(bpf_prog_ptr_type) + progs.append(prog) + # Subprogs are not registered in prog_idr, fetch them manually. + # func[0] is the current prog. + aux = prog["aux"] + func = aux["func"] + real_func_cnt = int(aux["real_func_cnt"]) + for i in range(1, real_func_cnt): + progs.append(func[i]) + return progs + + +class ProgAddBreakpoint(gdb.Breakpoint): + def __init__(self, monitor): + super(ProgAddBreakpoint, self).__init__("bpf_prog_kallsyms_add", + internal=True) + self.silent = True + self.monitor = monitor + + def stop(self): + self.monitor.add(gdb.parse_and_eval("fp")) + return False + + +class ProgRemoveBreakpoint(gdb.Breakpoint): + def __init__(self, monitor): + super(ProgRemoveBreakpoint, self).__init__("bpf_prog_free_id", + internal=True) + self.silent = True + self.monitor = monitor + + def stop(self): + self.monitor.remove(gdb.parse_and_eval("prog")) + return False + + +class ProgMonitor: + def __init__(self, add, remove): + self.add = add + self.remove = remove + + self.add_bp = ProgAddBreakpoint(self) + self.remove_bp = ProgRemoveBreakpoint(self) + + self.notify_initial() + + def notify_initial(self): + for prog in list_progs(): + self.add(prog) + + def delete(self): + self.add_bp.delete() + self.remove_bp.delete() + + +def btf_str_by_offset(btf, offset): + while offset < btf["start_str_off"]: + btf = btf["base_btf"] + + offset -= btf["start_str_off"] + if offset < btf["hdr"]["str_len"]: + return (btf["strings"] + offset).string() + + return None + + +def bpf_line_info_line_num(line_col): + return line_col >> 10 + + +def bpf_line_info_line_col(line_col): + return line_col & 0x3ff + + +class LInfoIter: + def __init__(self, prog): + # See bpf_prog_get_file_line() for details. + self.pos = 0 + self.nr_linfo = 0 + + if prog is None: + return + + self.bpf_func = int(prog["bpf_func"]) + aux = prog["aux"] + self.btf = aux["btf"] + linfo_idx = aux["linfo_idx"] + self.nr_linfo = int(aux["nr_linfo"]) - linfo_idx + if self.nr_linfo == 0: + return + + linfo_ptr = aux["linfo"] + tpe = linfo_ptr.type.target().array(self.nr_linfo).pointer() + self.linfo = (linfo_ptr + linfo_idx).cast(tpe).dereference() + jited_linfo_ptr = aux["jited_linfo"] + tpe = jited_linfo_ptr.type.target().array(self.nr_linfo).pointer() + self.jited_linfo = (jited_linfo_ptr + linfo_idx).cast(tpe).dereference() + + self.filenos = {} + + def get_code_off(self): + if self.pos >= self.nr_linfo: + return -1 + return self.jited_linfo[self.pos] - self.bpf_func + + def advance(self): + self.pos += 1 + + def get_fileno(self): + file_name_off = int(self.linfo[self.pos]["file_name_off"]) + fileno = self.filenos.get(file_name_off) + if fileno is not None: + return fileno, None + file_name = btf_str_by_offset(self.btf, file_name_off) + fileno = len(self.filenos) + 1 + self.filenos[file_name_off] = fileno + return fileno, file_name + + def get_line_col(self): + line_col = int(self.linfo[self.pos]["line_col"]) + return bpf_line_info_line_num(line_col), \ + bpf_line_info_line_col(line_col) + + +def generate_debug_obj(ksym, prog): + name = get_ksym_name(ksym) + # Avoid read_memory(); it throws bogus gdb.MemoryError in some contexts. + start = ksym["start"] + code = start.cast(gdb.lookup_type("unsigned char") + .array(int(ksym["end"]) - int(start)) + .pointer()).dereference().bytes + linfo_iter = LInfoIter(prog) + + result = tempfile.NamedTemporaryFile(suffix=".o", mode="wb") + try: + with tempfile.NamedTemporaryFile(suffix=".s", mode="w") as src: + # ".loc" does not apply to ".byte"s, only to ".insn"s, but since + # this needs to work for all architectures, the latter are not an + # option. Ask the assembler to apply ".loc"s to labels as well, + # and generate dummy labels after each ".loc". + src.write(".loc_mark_labels 1\n") + + src.write(".globl {}\n".format(name)) + src.write(".type {},@function\n".format(name)) + src.write("{}:\n".format(name)) + for code_off, code_byte in enumerate(code): + if linfo_iter.get_code_off() == code_off: + fileno, file_name = linfo_iter.get_fileno() + if file_name is not None: + src.write(".file {} {}\n".format( + fileno, json.dumps(file_name))) + line, col = linfo_iter.get_line_col() + src.write(".loc {} {} {}\n".format(fileno, line, col)) + src.write("0:\n") + linfo_iter.advance() + src.write(".byte {}\n".format(code_byte)) + src.write(".size {},{}\n".format(name, len(code))) + src.flush() + + try: + subprocess.check_call(["as", "-c", src.name, "-o", result.name]) + except FileNotFoundError: + # "as" is not installed. + result.close() + return None + return result + except: + result.close() + raise diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index c3886739a028..6d475540c6ba 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -170,3 +170,6 @@ LX_CONFIG(CONFIG_PAGE_OWNER) LX_CONFIG(CONFIG_SLUB_DEBUG) LX_CONFIG(CONFIG_SLAB_FREELIST_HARDENED) LX_CONFIG(CONFIG_MMU) +LX_CONFIG(CONFIG_BPF) +LX_CONFIG(CONFIG_BPF_JIT) +LX_CONFIG(CONFIG_BPF_SYSCALL) diff --git a/scripts/gdb/linux/radixtree.py b/scripts/gdb/linux/radixtree.py index 074543ac763d..bc2954e45c32 100644 --- a/scripts/gdb/linux/radixtree.py +++ b/scripts/gdb/linux/radixtree.py @@ -30,13 +30,16 @@ def entry_to_node(node): def node_maxindex(node): return (constants.LX_RADIX_TREE_MAP_SIZE << node['shift']) - 1 -def lookup(root, index): +def resolve_root(root): + if root.type == radix_tree_root_type.get_type(): + return root if root.type == radix_tree_root_type.get_type().pointer(): - node = root.dereference() - elif root.type != radix_tree_root_type.get_type(): - raise gdb.GdbError("must be {} not {}" - .format(radix_tree_root_type.get_type(), root.type)) + return root.dereference() + raise gdb.GdbError("must be {} not {}" + .format(radix_tree_root_type.get_type(), root.type)) +def lookup(root, index): + root = resolve_root(root) node = root['xa_head'] if node == 0: return None @@ -71,14 +74,120 @@ def lookup(root, index): return node -class LxRadixTree(gdb.Function): +def descend(parent, index): + offset = (index >> int(parent["shift"])) & constants.LX_RADIX_TREE_MAP_MASK + return offset, parent["slots"][offset] + +def load_root(root): + node = root["xa_head"] + nodep = node + + if is_internal_node(node): + node = entry_to_node(node) + maxindex = node_maxindex(node) + return int(node["shift"]) + constants.LX_RADIX_TREE_MAP_SHIFT, \ + nodep, maxindex + + return 0, nodep, 0 + +class RadixTreeIter: + def __init__(self, start): + self.index = 0 + self.next_index = start + self.node = None + +def xa_mk_internal(v): + return (v << 2) | 2 + +LX_XA_RETRY_ENTRY = xa_mk_internal(256) +LX_RADIX_TREE_RETRY = LX_XA_RETRY_ENTRY + +def next_chunk(root, iter): + mask = (1 << (utils.get_ulong_type().sizeof * 8)) - 1 + + index = iter.next_index + if index == 0 and iter.index != 0: + return None + + restart = True + while restart: + restart = False + + _, child, maxindex = load_root(root) + if index > maxindex: + return None + if not child: + return None + + if not is_internal_node(child): + iter.index = index + iter.next_index = (maxindex + 1) & mask + iter.node = None + return root["xa_head"].address + + while True: + node = entry_to_node(child) + offset, child = descend(node, index) + + if not child: + while True: + offset += 1 + if offset >= constants.LX_RADIX_TREE_MAP_SIZE: + break + slot = node["slots"][offset] + if slot: + break + index &= ~node_maxindex(node) + index = (index + (offset << int(node["shift"]))) & mask + if index == 0: + return None + if offset == constants.LX_RADIX_TREE_MAP_SIZE: + restart = True + break + child = node["slots"][offset] + + if not child: + restart = True + break + if child == LX_XA_RETRY_ENTRY: + break + if not node["shift"] or not is_internal_node(child): + break + + iter.index = (index & ~node_maxindex(node)) | offset + iter.next_index = ((index | node_maxindex(node)) + 1) & mask + iter.node = node + + return node["slots"][offset].address + +def next_slot(slot, iter): + mask = (1 << (utils.get_ulong_type().sizeof * 8)) - 1 + for _ in range(iter.next_index - iter.index - 1): + slot += 1 + iter.index = (iter.index + 1) & mask + if slot.dereference(): + return slot + return None + +def for_each_slot(root, start=0): + iter = RadixTreeIter(start) + slot = None + while True: + if not slot: + slot = next_chunk(root, iter) + if not slot: + break + yield iter.index, slot + slot = next_slot(slot, iter) + +class LxRadixTreeLookup(gdb.Function): """ Lookup and return a node from a RadixTree. $lx_radix_tree_lookup(root_node [, index]): Return the node at the given index. If index is omitted, the root node is dereference and returned.""" def __init__(self): - super(LxRadixTree, self).__init__("lx_radix_tree_lookup") + super(LxRadixTreeLookup, self).__init__("lx_radix_tree_lookup") def invoke(self, root, index=0): result = lookup(root, index) @@ -87,4 +196,20 @@ If index is omitted, the root node is dereference and returned.""" return result +class LxRadixTree(gdb.Command): + """Show all values stored in a RadixTree.""" + + def __init__(self): + super(LxRadixTree, self).__init__("lx-radix-tree", gdb.COMMAND_DATA, + gdb.COMPLETE_NONE) + + def invoke(self, argument, from_tty): + args = gdb.string_to_argv(argument) + if len(args) != 1: + raise gdb.GdbError("Usage: lx-radix-tree ROOT") + root = gdb.parse_and_eval(args[0]) + for index, slot in for_each_slot(root): + gdb.write("[{}] = {}\n".format(index, slot.dereference())) + LxRadixTree() +LxRadixTreeLookup() diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 6edb99221675..d4308b726183 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -11,13 +11,14 @@ # This work is licensed under the terms of the GNU GPL version 2. # +import atexit import gdb import os import re import struct from itertools import count -from linux import modules, utils, constants +from linux import bpf, constants, modules, utils if hasattr(gdb, 'Breakpoint'): @@ -114,17 +115,27 @@ class LxSymbols(gdb.Command): The kernel (vmlinux) is taken from the current working directly. Modules (.ko) are scanned recursively, starting in the same directory. Optionally, the module search path can be extended by a space separated list of paths passed to the -lx-symbols command.""" +lx-symbols command. + +When the -bpf flag is specified, symbols from the currently loaded BPF programs +are loaded as well.""" module_paths = [] module_files = [] module_files_updated = False loaded_modules = [] breakpoint = None + bpf_prog_monitor = None + bpf_ksym_monitor = None + bpf_progs = {} + # The remove-symbol-file command, even when invoked with -a, requires the + # respective object file to exist, so keep them around. + bpf_debug_objs = {} def __init__(self): super(LxSymbols, self).__init__("lx-symbols", gdb.COMMAND_FILES, gdb.COMPLETE_FILENAME) + atexit.register(self.cleanup_bpf) def _update_module_files(self): self.module_files = [] @@ -197,6 +208,51 @@ lx-symbols command.""" else: gdb.write("no module object found for '{0}'\n".format(module_name)) + def add_bpf_prog(self, prog): + if prog["jited"]: + self.bpf_progs[int(prog["bpf_func"])] = prog + + def remove_bpf_prog(self, prog): + self.bpf_progs.pop(int(prog["bpf_func"]), None) + + def add_bpf_ksym(self, ksym): + addr = int(ksym["start"]) + name = bpf.get_ksym_name(ksym) + with utils.pagination_off(): + gdb.write("loading @{addr}: {name}\n".format( + addr=hex(addr), name=name)) + debug_obj = bpf.generate_debug_obj(ksym, self.bpf_progs.get(addr)) + if debug_obj is None: + return + try: + cmdline = "add-symbol-file {obj} {addr}".format( + obj=debug_obj.name, addr=hex(addr)) + gdb.execute(cmdline, to_string=True) + except: + debug_obj.close() + raise + self.bpf_debug_objs[addr] = debug_obj + + def remove_bpf_ksym(self, ksym): + addr = int(ksym["start"]) + debug_obj = self.bpf_debug_objs.pop(addr, None) + if debug_obj is None: + return + try: + name = bpf.get_ksym_name(ksym) + gdb.write("unloading @{addr}: {name}\n".format( + addr=hex(addr), name=name)) + cmdline = "remove-symbol-file {path}".format(path=debug_obj.name) + gdb.execute(cmdline, to_string=True) + finally: + debug_obj.close() + + def cleanup_bpf(self): + self.bpf_progs = {} + while len(self.bpf_debug_objs) > 0: + self.bpf_debug_objs.popitem()[1].close() + + def load_all_symbols(self): gdb.write("loading vmlinux\n") @@ -224,34 +280,59 @@ lx-symbols command.""" else: [self.load_module_symbols(module) for module in module_list] + self.cleanup_bpf() + if self.bpf_prog_monitor is not None: + self.bpf_prog_monitor.notify_initial() + if self.bpf_ksym_monitor is not None: + self.bpf_ksym_monitor.notify_initial() + for saved_state in saved_states: saved_state['breakpoint'].enabled = saved_state['enabled'] def invoke(self, arg, from_tty): skip_decompressor() - self.module_paths = [os.path.abspath(os.path.expanduser(p)) - for p in arg.split()] + monitor_bpf = False + self.module_paths = [] + for p in arg.split(): + if p == "-bpf": + monitor_bpf = True + else: + p.append(os.path.abspath(os.path.expanduser(p))) self.module_paths.append(os.getcwd()) + if self.breakpoint is not None: + self.breakpoint.delete() + self.breakpoint = None + if self.bpf_prog_monitor is not None: + self.bpf_prog_monitor.delete() + self.bpf_prog_monitor = None + if self.bpf_ksym_monitor is not None: + self.bpf_ksym_monitor.delete() + self.bpf_ksym_monitor = None + # enforce update self.module_files = [] self.module_files_updated = False self.load_all_symbols() - if not modules.has_modules(): + if not hasattr(gdb, 'Breakpoint'): + gdb.write("Note: symbol update on module and BPF loading not " + "supported with this gdb version\n") return - if hasattr(gdb, 'Breakpoint'): - if self.breakpoint is not None: - self.breakpoint.delete() - self.breakpoint = None + if modules.has_modules(): self.breakpoint = LoadModuleBreakpoint( "kernel/module/main.c:do_init_module", self) - else: - gdb.write("Note: symbol update on module loading not supported " - "with this gdb version\n") + + if monitor_bpf: + if constants.LX_CONFIG_BPF_SYSCALL: + self.bpf_prog_monitor = bpf.ProgMonitor(self.add_bpf_prog, + self.remove_bpf_prog) + if constants.LX_CONFIG_BPF and constants.LX_CONFIG_BPF_JIT: + self.bpf_ksym_monitor = bpf.KsymMonitor(self.add_bpf_ksym, + self.remove_bpf_ksym) LxSymbols() diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c46ebdb9b8ef..56e44a98d6a5 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -54,6 +54,7 @@ TARGETS += kvm TARGETS += landlock TARGETS += lib TARGETS += livepatch +TARGETS += liveupdate TARGETS += lkdtm TARGETS += lsm TARGETS += membarrier diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c index 87c044fb9293..421adbdc299d 100644 --- a/tools/testing/selftests/acct/acct_syscall.c +++ b/tools/testing/selftests/acct/acct_syscall.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(void) { diff --git a/tools/testing/selftests/alsa/conf.c b/tools/testing/selftests/alsa/conf.c index dc7f40e68dee..317212078e36 100644 --- a/tools/testing/selftests/alsa/conf.c +++ b/tools/testing/selftests/alsa/conf.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "alsa-local.h" #define SYSFS_ROOT "/sys" diff --git a/tools/testing/selftests/alsa/mixer-test.c b/tools/testing/selftests/alsa/mixer-test.c index e113dafa5c24..d4f845c32804 100644 --- a/tools/testing/selftests/alsa/mixer-test.c +++ b/tools/testing/selftests/alsa/mixer-test.c @@ -25,7 +25,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "alsa-local.h" #define TESTS_PER_CONTROL 7 diff --git a/tools/testing/selftests/alsa/pcm-test.c b/tools/testing/selftests/alsa/pcm-test.c index ce92548670c8..ee04ccef7d7c 100644 --- a/tools/testing/selftests/alsa/pcm-test.c +++ b/tools/testing/selftests/alsa/pcm-test.c @@ -17,7 +17,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "alsa-local.h" typedef struct timespec timestamp_t; diff --git a/tools/testing/selftests/alsa/test-pcmtest-driver.c b/tools/testing/selftests/alsa/test-pcmtest-driver.c index ca81afa4ee90..95065ef3b441 100644 --- a/tools/testing/selftests/alsa/test-pcmtest-driver.c +++ b/tools/testing/selftests/alsa/test-pcmtest-driver.c @@ -7,7 +7,7 @@ */ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define CH_NUM 4 diff --git a/tools/testing/selftests/alsa/utimer-test.c b/tools/testing/selftests/alsa/utimer-test.c index 37964f311a33..c45cb226bd8f 100644 --- a/tools/testing/selftests/alsa/utimer-test.c +++ b/tools/testing/selftests/alsa/utimer-test.c @@ -6,7 +6,7 @@ * * Author: Ivan Orlov */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 3b96d090c5eb..c41640f18e4e 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -19,7 +19,7 @@ #include -#include "../../kselftest.h" +#include "kselftest.h" #define TESTS_PER_HWCAP 3 diff --git a/tools/testing/selftests/arm64/abi/ptrace.c b/tools/testing/selftests/arm64/abi/ptrace.c index b51d21f78cf9..0e46ac21c81d 100644 --- a/tools/testing/selftests/arm64/abi/ptrace.c +++ b/tools/testing/selftests/arm64/abi/ptrace.c @@ -18,7 +18,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #define EXPECTED_TESTS 11 diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index 5ec9a18ec802..b67e3e26fa6d 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -16,7 +16,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "syscall-abi.h" diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c index 0114108ab25f..22c584b78be5 100644 --- a/tools/testing/selftests/arm64/fp/fp-ptrace.c +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -27,7 +27,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "fp-ptrace.h" diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c index 9349aa630c84..65e01aba96ff 100644 --- a/tools/testing/selftests/arm64/fp/fp-stress.c +++ b/tools/testing/selftests/arm64/fp/fp-stress.c @@ -24,7 +24,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #define MAX_VLS 16 diff --git a/tools/testing/selftests/arm64/fp/sve-probe-vls.c b/tools/testing/selftests/arm64/fp/sve-probe-vls.c index a24eca7a4ecb..df0c1b6eb114 100644 --- a/tools/testing/selftests/arm64/fp/sve-probe-vls.c +++ b/tools/testing/selftests/arm64/fp/sve-probe-vls.c @@ -12,7 +12,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "rdvl.h" int main(int argc, char **argv) diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index f44d44618575..28f6b996c5e2 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -19,7 +19,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" /* and don't like each other, so: */ #ifndef NT_ARM_SVE diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c index 2d75d342eeb9..8dd932fdcdc4 100644 --- a/tools/testing/selftests/arm64/fp/vec-syscfg.c +++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c @@ -19,7 +19,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "rdvl.h" #define ARCH_MIN_VL SVE_VL_MIN diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c index 08c777f87ea2..787eed22d059 100644 --- a/tools/testing/selftests/arm64/fp/za-ptrace.c +++ b/tools/testing/selftests/arm64/fp/za-ptrace.c @@ -18,7 +18,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" /* and don't like each other, so: */ #ifndef NT_ARM_ZA diff --git a/tools/testing/selftests/arm64/fp/zt-ptrace.c b/tools/testing/selftests/arm64/fp/zt-ptrace.c index a7f34040fbf1..f3fa49fd0fbd 100644 --- a/tools/testing/selftests/arm64/fp/zt-ptrace.c +++ b/tools/testing/selftests/arm64/fp/zt-ptrace.c @@ -18,7 +18,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" /* and don't like each other, so: */ #ifndef NT_ARM_ZA diff --git a/tools/testing/selftests/arm64/gcs/gcs-stress.c b/tools/testing/selftests/arm64/gcs/gcs-stress.c index cf316d78ea97..86d8cd42aee7 100644 --- a/tools/testing/selftests/arm64/gcs/gcs-stress.c +++ b/tools/testing/selftests/arm64/gcs/gcs-stress.c @@ -24,7 +24,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" struct child_data { char *name, *output; diff --git a/tools/testing/selftests/arm64/pauth/pac.c b/tools/testing/selftests/arm64/pauth/pac.c index 6d21b2fc758d..67d138057707 100644 --- a/tools/testing/selftests/arm64/pauth/pac.c +++ b/tools/testing/selftests/arm64/pauth/pac.c @@ -10,7 +10,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "helper.h" #define PAC_COLLISION_ATTEMPTS 1000 diff --git a/tools/testing/selftests/arm64/tags/tags_test.c b/tools/testing/selftests/arm64/tags/tags_test.c index 8ae26e496c89..375ab47f0edb 100644 --- a/tools/testing/selftests/arm64/tags/tags_test.c +++ b/tools/testing/selftests/arm64/tags/tags_test.c @@ -6,7 +6,7 @@ #include #include #include -#include "../../kselftest.h" +#include "kselftest.h" #define SHIFT_TAG(tag) ((uint64_t)(tag) << 56) #define SET_TAG(ptr, tag) (((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \ diff --git a/tools/testing/selftests/bpf/xskxceiver.c b/tools/testing/selftests/bpf/xskxceiver.c index 9234a58b0a97..05b3cebc5ca9 100644 --- a/tools/testing/selftests/bpf/xskxceiver.c +++ b/tools/testing/selftests/bpf/xskxceiver.c @@ -96,7 +96,7 @@ #include "xskxceiver.h" #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "xsk_xdp_common.h" #include diff --git a/tools/testing/selftests/breakpoints/breakpoint_test.c b/tools/testing/selftests/breakpoints/breakpoint_test.c index d46962a24724..1159d81890c2 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define COUNT_ISN_BPS 4 #define COUNT_WPS 4 diff --git a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c index e7041816085a..5fc0f37f3fd4 100644 --- a/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c +++ b/tools/testing/selftests/breakpoints/breakpoint_test_arm64.c @@ -26,7 +26,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static volatile uint8_t var[96] __attribute__((__aligned__(32))); diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c index 8d233ac95696..ca2aaab9e4ca 100644 --- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c +++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c @@ -19,7 +19,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" void child(int cpu) { diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index ab838bcb9ec5..542cd09cb443 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define NR_TESTS 9 diff --git a/tools/testing/selftests/capabilities/test_execve.c b/tools/testing/selftests/capabilities/test_execve.c index 47bad7ddc5bc..46fc8d46b6e6 100644 --- a/tools/testing/selftests/capabilities/test_execve.c +++ b/tools/testing/selftests/capabilities/test_execve.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static int nerrs; static pid_t mpid; /* main() pid is used to avoid duplicate test counts */ diff --git a/tools/testing/selftests/capabilities/validate_cap.c b/tools/testing/selftests/capabilities/validate_cap.c index 65f2a1c89239..cef1d9937b9f 100644 --- a/tools/testing/selftests/capabilities/validate_cap.c +++ b/tools/testing/selftests/capabilities/validate_cap.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 19) # define HAVE_GETAUXVAL diff --git a/tools/testing/selftests/cgroup/test_core.c b/tools/testing/selftests/cgroup/test_core.c index 1d778c8b7764..102262555a59 100644 --- a/tools/testing/selftests/cgroup/test_core.c +++ b/tools/testing/selftests/cgroup/test_core.c @@ -17,7 +17,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" static bool nsdelegate; diff --git a/tools/testing/selftests/cgroup/test_cpu.c b/tools/testing/selftests/cgroup/test_cpu.c index b1b30e82dd7c..c83f05438d7c 100644 --- a/tools/testing/selftests/cgroup/test_cpu.c +++ b/tools/testing/selftests/cgroup/test_cpu.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" enum hog_clock_type { diff --git a/tools/testing/selftests/cgroup/test_cpuset.c b/tools/testing/selftests/cgroup/test_cpuset.c index 8086d2ea394f..c5cf8b56ceb8 100644 --- a/tools/testing/selftests/cgroup/test_cpuset.c +++ b/tools/testing/selftests/cgroup/test_cpuset.c @@ -3,7 +3,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" static int idle_process_fn(const char *cgroup, void *arg) diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 465cdad2bfca..97fae92c8387 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" #define DEBUG diff --git a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c index 856f9508ea56..f451aa449be6 100644 --- a/tools/testing/selftests/cgroup/test_hugetlb_memcg.c +++ b/tools/testing/selftests/cgroup/test_hugetlb_memcg.c @@ -7,7 +7,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" #define ADDR ((void *)(0x0UL)) diff --git a/tools/testing/selftests/cgroup/test_kill.c b/tools/testing/selftests/cgroup/test_kill.c index ed590b150a17..c8c9d306925b 100644 --- a/tools/testing/selftests/cgroup/test_kill.c +++ b/tools/testing/selftests/cgroup/test_kill.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "../pidfd/pidfd.h" #include "cgroup_util.h" diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index d4c4a514ee43..ca38525484e3 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index b117325c0439..4e1647568c5b 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" static bool has_localevents; diff --git a/tools/testing/selftests/cgroup/test_pids.c b/tools/testing/selftests/cgroup/test_pids.c index d8a1d1cd5007..9a387c815d2c 100644 --- a/tools/testing/selftests/cgroup/test_pids.c +++ b/tools/testing/selftests/cgroup/test_pids.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" static int run_success(const char *cgroup, void *arg) diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 86a8930b47e3..64ebc3f3f203 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -10,7 +10,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "cgroup_util.h" static int read_int(const char *path, size_t *value) diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e61f07973ce5..289e0c7c1f09 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "clone3_selftests.h" enum test_mode { diff --git a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c index 3c196fa86c99..e82281efa273 100644 --- a/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c +++ b/tools/testing/selftests/clone3/clone3_cap_checkpoint_restore.c @@ -24,7 +24,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "clone3_selftests.h" static void child_exit(int ret) diff --git a/tools/testing/selftests/clone3/clone3_clear_sighand.c b/tools/testing/selftests/clone3/clone3_clear_sighand.c index ce0426786828..de0c9d62015d 100644 --- a/tools/testing/selftests/clone3/clone3_clear_sighand.c +++ b/tools/testing/selftests/clone3/clone3_clear_sighand.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "clone3_selftests.h" static void nop_handler(int signo) diff --git a/tools/testing/selftests/clone3/clone3_selftests.h b/tools/testing/selftests/clone3/clone3_selftests.h index eeca8005723f..a0593e8950f0 100644 --- a/tools/testing/selftests/clone3/clone3_selftests.h +++ b/tools/testing/selftests/clone3/clone3_selftests.h @@ -11,7 +11,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) diff --git a/tools/testing/selftests/clone3/clone3_set_tid.c b/tools/testing/selftests/clone3/clone3_set_tid.c index bfb0da2b4fdd..5c944aee6b41 100644 --- a/tools/testing/selftests/clone3/clone3_set_tid.c +++ b/tools/testing/selftests/clone3/clone3_set_tid.c @@ -20,7 +20,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "clone3_selftests.h" #define MAX_PID_NS_LEVEL 32 diff --git a/tools/testing/selftests/connector/proc_filter.c b/tools/testing/selftests/connector/proc_filter.c index 4a825b997666..36c11467a8f1 100644 --- a/tools/testing/selftests/connector/proc_filter.c +++ b/tools/testing/selftests/connector/proc_filter.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define NL_MESSAGE_SIZE (sizeof(struct nlmsghdr) + sizeof(struct cn_msg) + \ sizeof(struct proc_input)) diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index e0d9851fe1c9..f14eca63f20c 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../clone3/clone3_selftests.h" diff --git a/tools/testing/selftests/core/unshare_test.c b/tools/testing/selftests/core/unshare_test.c index 7fec9dfb1b0e..ffce75a6c228 100644 --- a/tools/testing/selftests/core/unshare_test.c +++ b/tools/testing/selftests/core/unshare_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../clone3/clone3_selftests.h" TEST(unshare_EMFILE) diff --git a/tools/testing/selftests/coredump/stackdump_test.c b/tools/testing/selftests/coredump/stackdump_test.c index c2e895bcc160..1ec88937a1c2 100644 --- a/tools/testing/selftests/coredump/stackdump_test.c +++ b/tools/testing/selftests/coredump/stackdump_test.c @@ -19,7 +19,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../filesystems/wrappers.h" #include "../pidfd/pidfd.h" diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index 5d0a809dc2df..fc9694fc4e89 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -15,7 +15,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define DEVPATH "/dev/dma_heap" diff --git a/tools/testing/selftests/drivers/dma-buf/udmabuf.c b/tools/testing/selftests/drivers/dma-buf/udmabuf.c index 77aa2897e79f..d78aec662586 100644 --- a/tools/testing/selftests/drivers/dma-buf/udmabuf.c +++ b/tools/testing/selftests/drivers/dma-buf/udmabuf.c @@ -16,7 +16,7 @@ #include #include #include -#include "../../kselftest.h" +#include "kselftest.h" #define TEST_PREFIX "drivers/dma-buf/udmabuf" #define NUM_PAGES 4 diff --git a/tools/testing/selftests/drivers/net/gro.c b/tools/testing/selftests/drivers/net/gro.c index 995b492f5bcb..e894037d2e3e 100644 --- a/tools/testing/selftests/drivers/net/gro.c +++ b/tools/testing/selftests/drivers/net/gro.c @@ -57,7 +57,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "../../net/lib/ksft.h" #define DPORT 8000 diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.c b/tools/testing/selftests/drivers/net/hw/toeplitz.c index a4d04438c313..d23b3b0c20a3 100644 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.c +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.c @@ -55,7 +55,7 @@ #include #include "ethtool-user.h" -#include "../../../kselftest.h" +#include "kselftest.h" #include "../../../net/lib/ksft.h" #define TOEPLITZ_KEY_MIN_LEN 40 diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c index 3aad311574c4..e6a37214aa46 100644 --- a/tools/testing/selftests/drivers/ntsync/ntsync.c +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -12,7 +12,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" static int read_sem_state(int sem, __u32 *count, __u32 *max) { diff --git a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c index 7ee7492138c6..14df9aa07308 100644 --- a/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c +++ b/tools/testing/selftests/drivers/s390x/uvdevice/test_uvdevice.c @@ -14,7 +14,7 @@ #include -#include "../../../kselftest_harness.h" +#include "kselftest_harness.h" #define UV_PATH "/dev/uv" #define BUFFER_SIZE 0x200 diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c index 55bce47e56b7..f2397e75aa7c 100644 --- a/tools/testing/selftests/exec/check-exec.c +++ b/tools/testing/selftests/exec/check-exec.c @@ -30,7 +30,7 @@ #define _ASM_GENERIC_FCNTL_H #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static int sys_execveat(int dirfd, const char *pathname, char *const argv[], char *const envp[], int flags) diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c index 8fb7395fd35b..d37c068ed5fe 100644 --- a/tools/testing/selftests/exec/execveat.c +++ b/tools/testing/selftests/exec/execveat.c @@ -21,7 +21,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define TESTS_EXPECTED 54 #define TEST_NAME_LEN (PATH_MAX * 4) diff --git a/tools/testing/selftests/exec/load_address.c b/tools/testing/selftests/exec/load_address.c index 8257fddba8c8..55fd3732f029 100644 --- a/tools/testing/selftests/exec/load_address.c +++ b/tools/testing/selftests/exec/load_address.c @@ -6,7 +6,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" struct Statistics { unsigned long long load_address; diff --git a/tools/testing/selftests/exec/non-regular.c b/tools/testing/selftests/exec/non-regular.c index cd3a34aca93e..14ac36487df5 100644 --- a/tools/testing/selftests/exec/non-regular.c +++ b/tools/testing/selftests/exec/non-regular.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" /* Remove a file, ignoring the result if it didn't exist. */ void rm(struct __test_metadata *_metadata, const char *pathname, diff --git a/tools/testing/selftests/exec/null-argv.c b/tools/testing/selftests/exec/null-argv.c index c19726e710d1..4940aee5bb38 100644 --- a/tools/testing/selftests/exec/null-argv.c +++ b/tools/testing/selftests/exec/null-argv.c @@ -5,7 +5,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define FORK(exec) \ do { \ diff --git a/tools/testing/selftests/exec/recursion-depth.c b/tools/testing/selftests/exec/recursion-depth.c index 438c8ff2fd26..7b5c4f6d1928 100644 --- a/tools/testing/selftests/exec/recursion-depth.c +++ b/tools/testing/selftests/exec/recursion-depth.c @@ -23,7 +23,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(void) { diff --git a/tools/testing/selftests/fchmodat2/fchmodat2_test.c b/tools/testing/selftests/fchmodat2/fchmodat2_test.c index e0319417124d..e397339495f6 100644 --- a/tools/testing/selftests/fchmodat2/fchmodat2_test.c +++ b/tools/testing/selftests/fchmodat2/fchmodat2_test.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int sys_fchmodat2(int dfd, const char *filename, mode_t mode, int flags) { diff --git a/tools/testing/selftests/filelock/ofdlocks.c b/tools/testing/selftests/filelock/ofdlocks.c index a55b79810ab2..ff8d47fc373a 100644 --- a/tools/testing/selftests/filelock/ofdlocks.c +++ b/tools/testing/selftests/filelock/ofdlocks.c @@ -6,7 +6,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" static int lock_set(int fd, struct flock *fl) { diff --git a/tools/testing/selftests/filesystems/anon_inode_test.c b/tools/testing/selftests/filesystems/anon_inode_test.c index 73e0a4d4fb2f..94c6c81c2301 100644 --- a/tools/testing/selftests/filesystems/anon_inode_test.c +++ b/tools/testing/selftests/filesystems/anon_inode_test.c @@ -6,7 +6,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "wrappers.h" TEST(anon_inode_no_chown) diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c index 39a68078a79b..a1a79a6fef17 100644 --- a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -21,7 +21,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define DEFAULT_THREADS 4 diff --git a/tools/testing/selftests/filesystems/devpts_pts.c b/tools/testing/selftests/filesystems/devpts_pts.c index b1fc9b916ace..54fea349204e 100644 --- a/tools/testing/selftests/filesystems/devpts_pts.c +++ b/tools/testing/selftests/filesystems/devpts_pts.c @@ -11,7 +11,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" static bool terminal_dup2(int duplicate, int original) { diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 65ede506305c..8bc57a2ef966 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -11,7 +11,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" struct epoll_mtcontext { diff --git a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c index 72d51ad0ee0e..1b48f267157d 100644 --- a/tools/testing/selftests/filesystems/eventfd/eventfd_test.c +++ b/tools/testing/selftests/filesystems/eventfd/eventfd_test.c @@ -11,7 +11,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define EVENTFD_TEST_ITERATIONS 100000UL diff --git a/tools/testing/selftests/filesystems/fclog.c b/tools/testing/selftests/filesystems/fclog.c index 912a8b755c3b..551c4a0f395a 100644 --- a/tools/testing/selftests/filesystems/fclog.c +++ b/tools/testing/selftests/filesystems/fclog.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define ASSERT_ERRNO(expected, _t, seen) \ __EXPECT(expected, #expected, \ diff --git a/tools/testing/selftests/filesystems/file_stressor.c b/tools/testing/selftests/filesystems/file_stressor.c index 01dd89f8e52f..141badd671a9 100644 --- a/tools/testing/selftests/filesystems/file_stressor.c +++ b/tools/testing/selftests/filesystems/file_stressor.c @@ -12,7 +12,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include diff --git a/tools/testing/selftests/filesystems/fuse/fusectl_test.c b/tools/testing/selftests/filesystems/fuse/fusectl_test.c index 8d124d1cacb2..0d1d012c35ed 100644 --- a/tools/testing/selftests/filesystems/fuse/fusectl_test.c +++ b/tools/testing/selftests/filesystems/fuse/fusectl_test.c @@ -17,7 +17,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define FUSECTL_MOUNTPOINT "/sys/fs/fuse/connections" #define FUSE_MOUNTPOINT "/tmp/fuse_mnt_XXXXXX" diff --git a/tools/testing/selftests/filesystems/kernfs_test.c b/tools/testing/selftests/filesystems/kernfs_test.c index 16538b3b318e..84c2b910a60d 100644 --- a/tools/testing/selftests/filesystems/kernfs_test.c +++ b/tools/testing/selftests/filesystems/kernfs_test.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "wrappers.h" TEST(kernfs_listxattr) diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index e4b7c2b457ee..6381af6a40e3 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -19,7 +19,7 @@ typedef struct { #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "../statmount/statmount.h" #include "../utils.h" diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index 9f57ca46e3af..320ee25dc8a5 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -19,7 +19,7 @@ typedef struct { #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "../statmount/statmount.h" #include "../utils.h" diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c index a3d8015897e9..61e55dfbf121 100644 --- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -12,7 +12,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define MNT_NS_COUNT 11 #define MNT_NS_LAST_INDEX 10 diff --git a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c index 31db54b00e64..8924cea6aa4b 100644 --- a/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c +++ b/tools/testing/selftests/filesystems/overlayfs/dev_in_maps.c @@ -15,7 +15,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #include "log.h" #include "../wrappers.h" diff --git a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c index dc0449fa628f..3c0b93183348 100644 --- a/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c +++ b/tools/testing/selftests/filesystems/overlayfs/set_layers_via_fds.c @@ -12,7 +12,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "../../pidfd/pidfd.h" #include "log.h" #include "../utils.h" diff --git a/tools/testing/selftests/filesystems/statmount/listmount_test.c b/tools/testing/selftests/filesystems/statmount/listmount_test.c index 15f0834f7557..8bc82f38c42f 100644 --- a/tools/testing/selftests/filesystems/statmount/listmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/listmount_test.c @@ -11,7 +11,7 @@ #include #include "statmount.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef LISTMOUNT_REVERSE #define LISTMOUNT_REVERSE (1 << 0) /* List later mounts first */ diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index f048042e53e9..6e53430423d2 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -13,7 +13,7 @@ #include #include "statmount.h" -#include "../../kselftest.h" +#include "kselftest.h" static const char *const known_fs[] = { "9p", "adfs", "affs", "afs", "aio", "anon_inodefs", "apparmorfs", diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c index 605a3fa16bf7..d56d4103182f 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test_ns.c @@ -15,7 +15,7 @@ #include "statmount.h" #include "../utils.h" -#include "../../kselftest.h" +#include "kselftest.h" #define NSID_PASS 0 #define NSID_FAIL 1 diff --git a/tools/testing/selftests/filesystems/utils.c b/tools/testing/selftests/filesystems/utils.c index a0c64f415a7f..c9dd5412b37b 100644 --- a/tools/testing/selftests/filesystems/utils.c +++ b/tools/testing/selftests/filesystems/utils.c @@ -20,7 +20,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "wrappers.h" #include "utils.h" diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c index d037a3f10ee8..ab8555752137 100644 --- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c +++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c @@ -18,7 +18,7 @@ #include "futextest.h" #include "futex2test.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define MAX_THREADS 64 diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c index 3b7b5851f290..e8079d7c65e8 100644 --- a/tools/testing/selftests/futex/functional/futex_priv_hash.c +++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c @@ -14,7 +14,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define MAX_THREADS 64 diff --git a/tools/testing/selftests/futex/functional/futex_requeue.c b/tools/testing/selftests/futex/functional/futex_requeue.c index 69e2555b6039..35d4be23db5d 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue.c +++ b/tools/testing/selftests/futex/functional/futex_requeue.c @@ -9,7 +9,7 @@ #include #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define timeout_ns 30000000 #define WAKE_WAIT_US 10000 diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi.c b/tools/testing/selftests/futex/functional/futex_requeue_pi.c index f299d75848cd..46d2858e15a8 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi.c @@ -29,7 +29,7 @@ #include "atomic.h" #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define MAX_WAKE_ITERS 1000 #define THREAD_MAX 10 diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c index 77135a22a583..f686e605359c 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_mismatched_ops.c @@ -25,7 +25,7 @@ #include #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" futex_t f1 = FUTEX_INITIALIZER; futex_t f2 = FUTEX_INITIALIZER; diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c index e34ee0f9ebcc..a18ccae73eb1 100644 --- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c +++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c @@ -27,7 +27,7 @@ #include "atomic.h" #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define DELAY_US 100 diff --git a/tools/testing/selftests/futex/functional/futex_wait.c b/tools/testing/selftests/futex/functional/futex_wait.c index 152ca4612886..0e69c53524c1 100644 --- a/tools/testing/selftests/futex/functional/futex_wait.c +++ b/tools/testing/selftests/futex/functional/futex_wait.c @@ -11,7 +11,7 @@ #include #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define timeout_ns 30000000 #define WAKE_WAIT_US 10000 diff --git a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c index 8952ebda14ab..2a749f9b14eb 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c +++ b/tools/testing/selftests/futex/functional/futex_wait_private_mapped_file.c @@ -28,7 +28,7 @@ #include #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define PAGE_SZ 4096 diff --git a/tools/testing/selftests/futex/functional/futex_wait_timeout.c b/tools/testing/selftests/futex/functional/futex_wait_timeout.c index 0c8766aced2e..674dd13af421 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_timeout.c +++ b/tools/testing/selftests/futex/functional/futex_wait_timeout.c @@ -19,7 +19,7 @@ #include "futextest.h" #include "futex2test.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" static long timeout_ns = 100000; /* 100us default timeout */ static futex_t futex_pi; diff --git a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c index ce2301500d83..b07d68a67f31 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c +++ b/tools/testing/selftests/futex/functional/futex_wait_uninitialized_heap.c @@ -30,7 +30,7 @@ #include #include "futextest.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define WAIT_US 5000000 diff --git a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c index 36b7a54a4085..9ff936ecf164 100644 --- a/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c +++ b/tools/testing/selftests/futex/functional/futex_wait_wouldblock.c @@ -24,7 +24,7 @@ #include "futextest.h" #include "futex2test.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define timeout_ns 100000 diff --git a/tools/testing/selftests/futex/functional/futex_waitv.c b/tools/testing/selftests/futex/functional/futex_waitv.c index c684b10eb76e..d60876164d4b 100644 --- a/tools/testing/selftests/futex/functional/futex_waitv.c +++ b/tools/testing/selftests/futex/functional/futex_waitv.c @@ -18,7 +18,7 @@ #include "futextest.h" #include "futex2test.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define WAKE_WAIT_US 10000 #define NR_FUTEXES 30 diff --git a/tools/testing/selftests/hid/hid_common.h b/tools/testing/selftests/hid/hid_common.h index 8085519c47cb..e3b267446fa0 100644 --- a/tools/testing/selftests/hid/hid_common.h +++ b/tools/testing/selftests/hid/hid_common.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2022-2024 Red Hat */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c index a8acf3996973..953b63e5aa6a 100644 --- a/tools/testing/selftests/intel_pstate/aperf.c +++ b/tools/testing/selftests/intel_pstate/aperf.c @@ -11,7 +11,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MSEC_PER_SEC 1000L #define NSEC_PER_MSEC 1000000L diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 0a0ff6f7926d..5502751d500c 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -11,7 +11,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../../../../drivers/iommu/iommufd/iommufd_test.h" /* Hack to make assertions more readable */ diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index 5e36aeeb9901..e107379d185c 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MAX_MSG_SIZE 32 diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index f4a15cbdd5ea..adfcf50b1264 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -23,7 +23,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define TEST_SCANCODES 10 #define SYSFS_PATH_MAX 256 diff --git a/tools/testing/selftests/kcmp/kcmp_test.c b/tools/testing/selftests/kcmp/kcmp_test.c index d7a8e321bb16..79aa438b7479 100644 --- a/tools/testing/selftests/kcmp/kcmp_test.c +++ b/tools/testing/selftests/kcmp/kcmp_test.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static long sys_kcmp(int pid1, int pid2, int type, unsigned long fd1, unsigned long fd2) { diff --git a/tools/testing/selftests/kho/vmtest.sh b/tools/testing/selftests/kho/vmtest.sh index 3f6c17166846..49fdac8e8b15 100755 --- a/tools/testing/selftests/kho/vmtest.sh +++ b/tools/testing/selftests/kho/vmtest.sh @@ -59,6 +59,7 @@ function build_kernel() { tee "$kconfig" > "$kho_config" < #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 9acecae36f51..230b75f6015b 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -17,7 +17,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "wrappers.h" #define TMP_DIR "tmp" diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index a448fae57831..f02cc8a2e4ae 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -199,6 +199,9 @@ clean: $(if $(TEST_GEN_MODS_DIR),clean_mods_dir) # Build with _GNU_SOURCE by default CFLAGS += -D_GNU_SOURCE= +# Additional include paths needed by kselftest.h and local headers +CFLAGS += -I${top_srcdir}/tools/testing/selftests + # Enables to extend CFLAGS and LDFLAGS from command line, e.g. # make USERCFLAGS=-Werror USERLDFLAGS=-static CFLAGS += $(USERCFLAGS) diff --git a/tools/testing/selftests/liveupdate/.gitignore b/tools/testing/selftests/liveupdate/.gitignore new file mode 100644 index 000000000000..661827083ab6 --- /dev/null +++ b/tools/testing/selftests/liveupdate/.gitignore @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only +* +!/**/ +!*.c +!*.h +!*.sh +!.gitignore +!config +!Makefile diff --git a/tools/testing/selftests/liveupdate/Makefile b/tools/testing/selftests/liveupdate/Makefile new file mode 100644 index 000000000000..080754787ede --- /dev/null +++ b/tools/testing/selftests/liveupdate/Makefile @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: GPL-2.0-only + +LIB_C += luo_test_utils.c + +TEST_GEN_PROGS += liveupdate + +TEST_GEN_PROGS_EXTENDED += luo_kexec_simple +TEST_GEN_PROGS_EXTENDED += luo_multi_session + +TEST_FILES += do_kexec.sh + +include ../lib.mk + +CFLAGS += $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -Wno-unused-function +CFLAGS += -MD + +LIB_O := $(patsubst %.c, $(OUTPUT)/%.o, $(LIB_C)) +TEST_O := $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_O += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) + +TEST_DEP_FILES := $(patsubst %.o, %.d, $(LIB_O)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(TEST_O)) +-include $(TEST_DEP_FILES) + +$(LIB_O): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/%: %.o $(LIB_O) + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIB_O) $(LDLIBS) -o $@ + +EXTRA_CLEAN += $(LIB_O) +EXTRA_CLEAN += $(TEST_O) +EXTRA_CLEAN += $(TEST_DEP_FILES) diff --git a/tools/testing/selftests/liveupdate/config b/tools/testing/selftests/liveupdate/config new file mode 100644 index 000000000000..91d03f9a6a39 --- /dev/null +++ b/tools/testing/selftests/liveupdate/config @@ -0,0 +1,11 @@ +CONFIG_BLK_DEV_INITRD=y +CONFIG_KEXEC_FILE=y +CONFIG_KEXEC_HANDOVER=y +CONFIG_KEXEC_HANDOVER_ENABLE_DEFAULT=y +CONFIG_KEXEC_HANDOVER_DEBUGFS=y +CONFIG_KEXEC_HANDOVER_DEBUG=y +CONFIG_LIVEUPDATE=y +CONFIG_LIVEUPDATE_TEST=y +CONFIG_MEMFD_CREATE=y +CONFIG_TMPFS=y +CONFIG_SHMEM=y diff --git a/tools/testing/selftests/liveupdate/do_kexec.sh b/tools/testing/selftests/liveupdate/do_kexec.sh new file mode 100755 index 000000000000..3c7c6cafbef8 --- /dev/null +++ b/tools/testing/selftests/liveupdate/do_kexec.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +set -e + +# Use $KERNEL and $INITRAMFS to pass custom Kernel and optional initramfs + +KERNEL="${KERNEL:-/boot/bzImage}" +set -- -l -s --reuse-cmdline "$KERNEL" + +INITRAMFS="${INITRAMFS:-/boot/initramfs}" +if [ -f "$INITRAMFS" ]; then + set -- "$@" --initrd="$INITRAMFS" +fi + +kexec "$@" +kexec -e diff --git a/tools/testing/selftests/liveupdate/liveupdate.c b/tools/testing/selftests/liveupdate/liveupdate.c new file mode 100644 index 000000000000..c2878e3d5ef9 --- /dev/null +++ b/tools/testing/selftests/liveupdate/liveupdate.c @@ -0,0 +1,348 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +/* + * Selftests for the Live Update Orchestrator. + * This test suite verifies the functionality and behavior of the + * /dev/liveupdate character device and its session management capabilities. + * + * Tests include: + * - Device access: basic open/close, and enforcement of exclusive access. + * - Session management: creation of unique sessions, and duplicate name detection. + * - Resource preservation: successfully preserving individual and multiple memfds, + * verifying contents remain accessible. + * - Complex multi-session scenarios involving mixed empty and populated files. + */ + +#include +#include +#include +#include +#include + +#include + +#include "../kselftest.h" +#include "../kselftest_harness.h" + +#define LIVEUPDATE_DEV "/dev/liveupdate" + +FIXTURE(liveupdate_device) { + int fd1; + int fd2; +}; + +FIXTURE_SETUP(liveupdate_device) +{ + self->fd1 = -1; + self->fd2 = -1; +} + +FIXTURE_TEARDOWN(liveupdate_device) +{ + if (self->fd1 >= 0) + close(self->fd1); + if (self->fd2 >= 0) + close(self->fd2); +} + +/* + * Test Case: Basic Open and Close + * + * Verifies that the /dev/liveupdate device can be opened and subsequently + * closed without errors. Skips if the device does not exist. + */ +TEST_F(liveupdate_device, basic_open_close) +{ + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist.", LIVEUPDATE_DEV); + + ASSERT_GE(self->fd1, 0); + ASSERT_EQ(close(self->fd1), 0); + self->fd1 = -1; +} + +/* + * Test Case: Exclusive Open Enforcement + * + * Verifies that the /dev/liveupdate device can only be opened by one process + * at a time. It checks that a second attempt to open the device fails with + * the EBUSY error code. + */ +TEST_F(liveupdate_device, exclusive_open) +{ + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist.", LIVEUPDATE_DEV); + + ASSERT_GE(self->fd1, 0); + self->fd2 = open(LIVEUPDATE_DEV, O_RDWR); + EXPECT_LT(self->fd2, 0); + EXPECT_EQ(errno, EBUSY); +} + +/* Helper function to create a LUO session via ioctl. */ +static int create_session(int lu_fd, const char *name) +{ + struct liveupdate_ioctl_create_session args = {}; + + args.size = sizeof(args); + strncpy((char *)args.name, name, sizeof(args.name) - 1); + + if (ioctl(lu_fd, LIVEUPDATE_IOCTL_CREATE_SESSION, &args)) + return -errno; + + return args.fd; +} + +/* + * Test Case: Create Duplicate Session + * + * Verifies that attempting to create two sessions with the same name fails + * on the second attempt with EEXIST. + */ +TEST_F(liveupdate_device, create_duplicate_session) +{ + int session_fd1, session_fd2; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + + ASSERT_GE(self->fd1, 0); + + session_fd1 = create_session(self->fd1, "duplicate-session-test"); + ASSERT_GE(session_fd1, 0); + + session_fd2 = create_session(self->fd1, "duplicate-session-test"); + EXPECT_LT(session_fd2, 0); + EXPECT_EQ(-session_fd2, EEXIST); + + ASSERT_EQ(close(session_fd1), 0); +} + +/* + * Test Case: Create Distinct Sessions + * + * Verifies that creating two sessions with different names succeeds. + */ +TEST_F(liveupdate_device, create_distinct_sessions) +{ + int session_fd1, session_fd2; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + + ASSERT_GE(self->fd1, 0); + + session_fd1 = create_session(self->fd1, "distinct-session-1"); + ASSERT_GE(session_fd1, 0); + + session_fd2 = create_session(self->fd1, "distinct-session-2"); + ASSERT_GE(session_fd2, 0); + + ASSERT_EQ(close(session_fd1), 0); + ASSERT_EQ(close(session_fd2), 0); +} + +static int preserve_fd(int session_fd, int fd_to_preserve, __u64 token) +{ + struct liveupdate_session_preserve_fd args = {}; + + args.size = sizeof(args); + args.fd = fd_to_preserve; + args.token = token; + + if (ioctl(session_fd, LIVEUPDATE_SESSION_PRESERVE_FD, &args)) + return -errno; + + return 0; +} + +/* + * Test Case: Preserve MemFD + * + * Verifies that a valid memfd can be successfully preserved in a session and + * that its contents remain intact after the preservation call. + */ +TEST_F(liveupdate_device, preserve_memfd) +{ + const char *test_str = "hello liveupdate"; + char read_buf[64] = {}; + int session_fd, mem_fd; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + ASSERT_GE(self->fd1, 0); + + session_fd = create_session(self->fd1, "preserve-memfd-test"); + ASSERT_GE(session_fd, 0); + + mem_fd = memfd_create("test-memfd", 0); + ASSERT_GE(mem_fd, 0); + + ASSERT_EQ(write(mem_fd, test_str, strlen(test_str)), strlen(test_str)); + ASSERT_EQ(preserve_fd(session_fd, mem_fd, 0x1234), 0); + ASSERT_EQ(close(session_fd), 0); + + ASSERT_EQ(lseek(mem_fd, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd, read_buf, sizeof(read_buf)), strlen(test_str)); + ASSERT_STREQ(read_buf, test_str); + ASSERT_EQ(close(mem_fd), 0); +} + +/* + * Test Case: Preserve Multiple MemFDs + * + * Verifies that multiple memfds can be preserved in a single session, + * each with a unique token, and that their contents remain distinct and + * correct after preservation. + */ +TEST_F(liveupdate_device, preserve_multiple_memfds) +{ + const char *test_str1 = "data for memfd one"; + const char *test_str2 = "data for memfd two"; + char read_buf[64] = {}; + int session_fd, mem_fd1, mem_fd2; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + ASSERT_GE(self->fd1, 0); + + session_fd = create_session(self->fd1, "preserve-multi-memfd-test"); + ASSERT_GE(session_fd, 0); + + mem_fd1 = memfd_create("test-memfd-1", 0); + ASSERT_GE(mem_fd1, 0); + mem_fd2 = memfd_create("test-memfd-2", 0); + ASSERT_GE(mem_fd2, 0); + + ASSERT_EQ(write(mem_fd1, test_str1, strlen(test_str1)), strlen(test_str1)); + ASSERT_EQ(write(mem_fd2, test_str2, strlen(test_str2)), strlen(test_str2)); + + ASSERT_EQ(preserve_fd(session_fd, mem_fd1, 0xAAAA), 0); + ASSERT_EQ(preserve_fd(session_fd, mem_fd2, 0xBBBB), 0); + + memset(read_buf, 0, sizeof(read_buf)); + ASSERT_EQ(lseek(mem_fd1, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd1, read_buf, sizeof(read_buf)), strlen(test_str1)); + ASSERT_STREQ(read_buf, test_str1); + + memset(read_buf, 0, sizeof(read_buf)); + ASSERT_EQ(lseek(mem_fd2, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd2, read_buf, sizeof(read_buf)), strlen(test_str2)); + ASSERT_STREQ(read_buf, test_str2); + + ASSERT_EQ(close(mem_fd1), 0); + ASSERT_EQ(close(mem_fd2), 0); + ASSERT_EQ(close(session_fd), 0); +} + +/* + * Test Case: Preserve Complex Scenario + * + * Verifies a more complex scenario with multiple sessions and a mix of empty + * and non-empty memfds distributed across them. + */ +TEST_F(liveupdate_device, preserve_complex_scenario) +{ + const char *data1 = "data for session 1"; + const char *data2 = "data for session 2"; + char read_buf[64] = {}; + int session_fd1, session_fd2; + int mem_fd_data1, mem_fd_empty1, mem_fd_data2, mem_fd_empty2; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + ASSERT_GE(self->fd1, 0); + + session_fd1 = create_session(self->fd1, "complex-session-1"); + ASSERT_GE(session_fd1, 0); + session_fd2 = create_session(self->fd1, "complex-session-2"); + ASSERT_GE(session_fd2, 0); + + mem_fd_data1 = memfd_create("data1", 0); + ASSERT_GE(mem_fd_data1, 0); + ASSERT_EQ(write(mem_fd_data1, data1, strlen(data1)), strlen(data1)); + + mem_fd_empty1 = memfd_create("empty1", 0); + ASSERT_GE(mem_fd_empty1, 0); + + mem_fd_data2 = memfd_create("data2", 0); + ASSERT_GE(mem_fd_data2, 0); + ASSERT_EQ(write(mem_fd_data2, data2, strlen(data2)), strlen(data2)); + + mem_fd_empty2 = memfd_create("empty2", 0); + ASSERT_GE(mem_fd_empty2, 0); + + ASSERT_EQ(preserve_fd(session_fd1, mem_fd_data1, 0x1111), 0); + ASSERT_EQ(preserve_fd(session_fd1, mem_fd_empty1, 0x2222), 0); + ASSERT_EQ(preserve_fd(session_fd2, mem_fd_data2, 0x3333), 0); + ASSERT_EQ(preserve_fd(session_fd2, mem_fd_empty2, 0x4444), 0); + + ASSERT_EQ(lseek(mem_fd_data1, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd_data1, read_buf, sizeof(read_buf)), strlen(data1)); + ASSERT_STREQ(read_buf, data1); + + memset(read_buf, 0, sizeof(read_buf)); + ASSERT_EQ(lseek(mem_fd_data2, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd_data2, read_buf, sizeof(read_buf)), strlen(data2)); + ASSERT_STREQ(read_buf, data2); + + ASSERT_EQ(lseek(mem_fd_empty1, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd_empty1, read_buf, sizeof(read_buf)), 0); + + ASSERT_EQ(lseek(mem_fd_empty2, 0, SEEK_SET), 0); + ASSERT_EQ(read(mem_fd_empty2, read_buf, sizeof(read_buf)), 0); + + ASSERT_EQ(close(mem_fd_data1), 0); + ASSERT_EQ(close(mem_fd_empty1), 0); + ASSERT_EQ(close(mem_fd_data2), 0); + ASSERT_EQ(close(mem_fd_empty2), 0); + ASSERT_EQ(close(session_fd1), 0); + ASSERT_EQ(close(session_fd2), 0); +} + +/* + * Test Case: Preserve Unsupported File Descriptor + * + * Verifies that attempting to preserve a file descriptor that does not have + * a registered Live Update handler fails gracefully. + * Uses /dev/null as a representative of a file type (character device) + * that is not supported by the orchestrator. + */ +TEST_F(liveupdate_device, preserve_unsupported_fd) +{ + int session_fd, unsupported_fd; + int ret; + + self->fd1 = open(LIVEUPDATE_DEV, O_RDWR); + if (self->fd1 < 0 && errno == ENOENT) + SKIP(return, "%s does not exist", LIVEUPDATE_DEV); + ASSERT_GE(self->fd1, 0); + + session_fd = create_session(self->fd1, "unsupported-fd-test"); + ASSERT_GE(session_fd, 0); + + unsupported_fd = open("/dev/null", O_RDWR); + ASSERT_GE(unsupported_fd, 0); + + ret = preserve_fd(session_fd, unsupported_fd, 0xDEAD); + EXPECT_EQ(ret, -ENOENT); + + ASSERT_EQ(close(unsupported_fd), 0); + ASSERT_EQ(close(session_fd), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/liveupdate/luo_kexec_simple.c b/tools/testing/selftests/liveupdate/luo_kexec_simple.c new file mode 100644 index 000000000000..d7ac1f3dc4cb --- /dev/null +++ b/tools/testing/selftests/liveupdate/luo_kexec_simple.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + * + * A simple selftest to validate the end-to-end lifecycle of a LUO session + * across a single kexec reboot. + */ + +#include "luo_test_utils.h" + +#define TEST_SESSION_NAME "test-session" +#define TEST_MEMFD_TOKEN 0x1A +#define TEST_MEMFD_DATA "hello kexec world" + +/* Constants for the state-tracking mechanism, specific to this test file. */ +#define STATE_SESSION_NAME "kexec_simple_state" +#define STATE_MEMFD_TOKEN 999 + +/* Stage 1: Executed before the kexec reboot. */ +static void run_stage_1(int luo_fd) +{ + int session_fd; + + ksft_print_msg("[STAGE 1] Starting pre-kexec setup...\n"); + + ksft_print_msg("[STAGE 1] Creating state file for next stage (2)...\n"); + create_state_file(luo_fd, STATE_SESSION_NAME, STATE_MEMFD_TOKEN, 2); + + ksft_print_msg("[STAGE 1] Creating session '%s' and preserving memfd...\n", + TEST_SESSION_NAME); + session_fd = luo_create_session(luo_fd, TEST_SESSION_NAME); + if (session_fd < 0) + fail_exit("luo_create_session for '%s'", TEST_SESSION_NAME); + + if (create_and_preserve_memfd(session_fd, TEST_MEMFD_TOKEN, + TEST_MEMFD_DATA) < 0) { + fail_exit("create_and_preserve_memfd for token %#x", + TEST_MEMFD_TOKEN); + } + + close(luo_fd); + daemonize_and_wait(); +} + +/* Stage 2: Executed after the kexec reboot. */ +static void run_stage_2(int luo_fd, int state_session_fd) +{ + int session_fd, mfd, stage; + + ksft_print_msg("[STAGE 2] Starting post-kexec verification...\n"); + + restore_and_read_stage(state_session_fd, STATE_MEMFD_TOKEN, &stage); + if (stage != 2) + fail_exit("Expected stage 2, but state file contains %d", stage); + + ksft_print_msg("[STAGE 2] Retrieving session '%s'...\n", TEST_SESSION_NAME); + session_fd = luo_retrieve_session(luo_fd, TEST_SESSION_NAME); + if (session_fd < 0) + fail_exit("luo_retrieve_session for '%s'", TEST_SESSION_NAME); + + ksft_print_msg("[STAGE 2] Restoring and verifying memfd (token %#x)...\n", + TEST_MEMFD_TOKEN); + mfd = restore_and_verify_memfd(session_fd, TEST_MEMFD_TOKEN, + TEST_MEMFD_DATA); + if (mfd < 0) + fail_exit("restore_and_verify_memfd for token %#x", TEST_MEMFD_TOKEN); + close(mfd); + + ksft_print_msg("[STAGE 2] Test data verified successfully.\n"); + ksft_print_msg("[STAGE 2] Finalizing test session...\n"); + if (luo_session_finish(session_fd) < 0) + fail_exit("luo_session_finish for test session"); + close(session_fd); + + ksft_print_msg("[STAGE 2] Finalizing state session...\n"); + if (luo_session_finish(state_session_fd) < 0) + fail_exit("luo_session_finish for state session"); + close(state_session_fd); + + ksft_print_msg("\n--- SIMPLE KEXEC TEST PASSED ---\n"); +} + +int main(int argc, char *argv[]) +{ + return luo_test(argc, argv, STATE_SESSION_NAME, + run_stage_1, run_stage_2); +} diff --git a/tools/testing/selftests/liveupdate/luo_multi_session.c b/tools/testing/selftests/liveupdate/luo_multi_session.c new file mode 100644 index 000000000000..0ee2d795beef --- /dev/null +++ b/tools/testing/selftests/liveupdate/luo_multi_session.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + * + * A selftest to validate the end-to-end lifecycle of multiple LUO sessions + * across a kexec reboot, including empty sessions and sessions with multiple + * files. + */ + +#include "luo_test_utils.h" + +#define SESSION_EMPTY_1 "multi-test-empty-1" +#define SESSION_EMPTY_2 "multi-test-empty-2" +#define SESSION_FILES_1 "multi-test-files-1" +#define SESSION_FILES_2 "multi-test-files-2" + +#define MFD1_TOKEN 0x1001 +#define MFD2_TOKEN 0x2002 +#define MFD3_TOKEN 0x3003 + +#define MFD1_DATA "Data for session files 1" +#define MFD2_DATA "First file for session files 2" +#define MFD3_DATA "Second file for session files 2" + +#define STATE_SESSION_NAME "kexec_multi_state" +#define STATE_MEMFD_TOKEN 998 + +/* Stage 1: Executed before the kexec reboot. */ +static void run_stage_1(int luo_fd) +{ + int s_empty1_fd, s_empty2_fd, s_files1_fd, s_files2_fd; + + ksft_print_msg("[STAGE 1] Starting pre-kexec setup for multi-session test...\n"); + + ksft_print_msg("[STAGE 1] Creating state file for next stage (2)...\n"); + create_state_file(luo_fd, STATE_SESSION_NAME, STATE_MEMFD_TOKEN, 2); + + ksft_print_msg("[STAGE 1] Creating empty sessions '%s' and '%s'...\n", + SESSION_EMPTY_1, SESSION_EMPTY_2); + s_empty1_fd = luo_create_session(luo_fd, SESSION_EMPTY_1); + if (s_empty1_fd < 0) + fail_exit("luo_create_session for '%s'", SESSION_EMPTY_1); + + s_empty2_fd = luo_create_session(luo_fd, SESSION_EMPTY_2); + if (s_empty2_fd < 0) + fail_exit("luo_create_session for '%s'", SESSION_EMPTY_2); + + ksft_print_msg("[STAGE 1] Creating session '%s' with one memfd...\n", + SESSION_FILES_1); + + s_files1_fd = luo_create_session(luo_fd, SESSION_FILES_1); + if (s_files1_fd < 0) + fail_exit("luo_create_session for '%s'", SESSION_FILES_1); + if (create_and_preserve_memfd(s_files1_fd, MFD1_TOKEN, MFD1_DATA) < 0) { + fail_exit("create_and_preserve_memfd for token %#x", + MFD1_TOKEN); + } + + ksft_print_msg("[STAGE 1] Creating session '%s' with two memfds...\n", + SESSION_FILES_2); + + s_files2_fd = luo_create_session(luo_fd, SESSION_FILES_2); + if (s_files2_fd < 0) + fail_exit("luo_create_session for '%s'", SESSION_FILES_2); + if (create_and_preserve_memfd(s_files2_fd, MFD2_TOKEN, MFD2_DATA) < 0) { + fail_exit("create_and_preserve_memfd for token %#x", + MFD2_TOKEN); + } + if (create_and_preserve_memfd(s_files2_fd, MFD3_TOKEN, MFD3_DATA) < 0) { + fail_exit("create_and_preserve_memfd for token %#x", + MFD3_TOKEN); + } + + close(luo_fd); + daemonize_and_wait(); +} + +/* Stage 2: Executed after the kexec reboot. */ +static void run_stage_2(int luo_fd, int state_session_fd) +{ + int s_empty1_fd, s_empty2_fd, s_files1_fd, s_files2_fd; + int mfd1, mfd2, mfd3, stage; + + ksft_print_msg("[STAGE 2] Starting post-kexec verification...\n"); + + restore_and_read_stage(state_session_fd, STATE_MEMFD_TOKEN, &stage); + if (stage != 2) { + fail_exit("Expected stage 2, but state file contains %d", + stage); + } + + ksft_print_msg("[STAGE 2] Retrieving all sessions...\n"); + s_empty1_fd = luo_retrieve_session(luo_fd, SESSION_EMPTY_1); + if (s_empty1_fd < 0) + fail_exit("luo_retrieve_session for '%s'", SESSION_EMPTY_1); + + s_empty2_fd = luo_retrieve_session(luo_fd, SESSION_EMPTY_2); + if (s_empty2_fd < 0) + fail_exit("luo_retrieve_session for '%s'", SESSION_EMPTY_2); + + s_files1_fd = luo_retrieve_session(luo_fd, SESSION_FILES_1); + if (s_files1_fd < 0) + fail_exit("luo_retrieve_session for '%s'", SESSION_FILES_1); + + s_files2_fd = luo_retrieve_session(luo_fd, SESSION_FILES_2); + if (s_files2_fd < 0) + fail_exit("luo_retrieve_session for '%s'", SESSION_FILES_2); + + ksft_print_msg("[STAGE 2] Verifying contents of session '%s'...\n", + SESSION_FILES_1); + mfd1 = restore_and_verify_memfd(s_files1_fd, MFD1_TOKEN, MFD1_DATA); + if (mfd1 < 0) + fail_exit("restore_and_verify_memfd for token %#x", MFD1_TOKEN); + close(mfd1); + + ksft_print_msg("[STAGE 2] Verifying contents of session '%s'...\n", + SESSION_FILES_2); + + mfd2 = restore_and_verify_memfd(s_files2_fd, MFD2_TOKEN, MFD2_DATA); + if (mfd2 < 0) + fail_exit("restore_and_verify_memfd for token %#x", MFD2_TOKEN); + close(mfd2); + + mfd3 = restore_and_verify_memfd(s_files2_fd, MFD3_TOKEN, MFD3_DATA); + if (mfd3 < 0) + fail_exit("restore_and_verify_memfd for token %#x", MFD3_TOKEN); + close(mfd3); + + ksft_print_msg("[STAGE 2] Test data verified successfully.\n"); + + ksft_print_msg("[STAGE 2] Finalizing all test sessions...\n"); + if (luo_session_finish(s_empty1_fd) < 0) + fail_exit("luo_session_finish for '%s'", SESSION_EMPTY_1); + close(s_empty1_fd); + + if (luo_session_finish(s_empty2_fd) < 0) + fail_exit("luo_session_finish for '%s'", SESSION_EMPTY_2); + close(s_empty2_fd); + + if (luo_session_finish(s_files1_fd) < 0) + fail_exit("luo_session_finish for '%s'", SESSION_FILES_1); + close(s_files1_fd); + + if (luo_session_finish(s_files2_fd) < 0) + fail_exit("luo_session_finish for '%s'", SESSION_FILES_2); + close(s_files2_fd); + + ksft_print_msg("[STAGE 2] Finalizing state session...\n"); + if (luo_session_finish(state_session_fd) < 0) + fail_exit("luo_session_finish for state session"); + close(state_session_fd); + + ksft_print_msg("\n--- MULTI-SESSION KEXEC TEST PASSED ---\n"); +} + +int main(int argc, char *argv[]) +{ + return luo_test(argc, argv, STATE_SESSION_NAME, + run_stage_1, run_stage_2); +} diff --git a/tools/testing/selftests/liveupdate/luo_test_utils.c b/tools/testing/selftests/liveupdate/luo_test_utils.c new file mode 100644 index 000000000000..3c8721c505df --- /dev/null +++ b/tools/testing/selftests/liveupdate/luo_test_utils.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0-only + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + */ + +#define _GNU_SOURCE + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "luo_test_utils.h" + +int luo_open_device(void) +{ + return open(LUO_DEVICE, O_RDWR); +} + +int luo_create_session(int luo_fd, const char *name) +{ + struct liveupdate_ioctl_create_session arg = { .size = sizeof(arg) }; + + snprintf((char *)arg.name, LIVEUPDATE_SESSION_NAME_LENGTH, "%.*s", + LIVEUPDATE_SESSION_NAME_LENGTH - 1, name); + + if (ioctl(luo_fd, LIVEUPDATE_IOCTL_CREATE_SESSION, &arg) < 0) + return -errno; + + return arg.fd; +} + +int luo_retrieve_session(int luo_fd, const char *name) +{ + struct liveupdate_ioctl_retrieve_session arg = { .size = sizeof(arg) }; + + snprintf((char *)arg.name, LIVEUPDATE_SESSION_NAME_LENGTH, "%.*s", + LIVEUPDATE_SESSION_NAME_LENGTH - 1, name); + + if (ioctl(luo_fd, LIVEUPDATE_IOCTL_RETRIEVE_SESSION, &arg) < 0) + return -errno; + + return arg.fd; +} + +int create_and_preserve_memfd(int session_fd, int token, const char *data) +{ + struct liveupdate_session_preserve_fd arg = { .size = sizeof(arg) }; + long page_size = sysconf(_SC_PAGE_SIZE); + void *map = MAP_FAILED; + int mfd = -1, ret = -1; + + mfd = memfd_create("test_mfd", 0); + if (mfd < 0) + return -errno; + + if (ftruncate(mfd, page_size) != 0) + goto out; + + map = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, mfd, 0); + if (map == MAP_FAILED) + goto out; + + snprintf(map, page_size, "%s", data); + munmap(map, page_size); + + arg.fd = mfd; + arg.token = token; + if (ioctl(session_fd, LIVEUPDATE_SESSION_PRESERVE_FD, &arg) < 0) + goto out; + + ret = 0; +out: + if (ret != 0 && errno != 0) + ret = -errno; + if (mfd >= 0) + close(mfd); + return ret; +} + +int restore_and_verify_memfd(int session_fd, int token, + const char *expected_data) +{ + struct liveupdate_session_retrieve_fd arg = { .size = sizeof(arg) }; + long page_size = sysconf(_SC_PAGE_SIZE); + void *map = MAP_FAILED; + int mfd = -1, ret = -1; + + arg.token = token; + if (ioctl(session_fd, LIVEUPDATE_SESSION_RETRIEVE_FD, &arg) < 0) + return -errno; + mfd = arg.fd; + + map = mmap(NULL, page_size, PROT_READ, MAP_SHARED, mfd, 0); + if (map == MAP_FAILED) + goto out; + + if (expected_data && strcmp(expected_data, map) != 0) { + ksft_print_msg("Data mismatch! Expected '%s', Got '%s'\n", + expected_data, (char *)map); + ret = -EINVAL; + goto out_munmap; + } + + ret = mfd; +out_munmap: + munmap(map, page_size); +out: + if (ret < 0 && errno != 0) + ret = -errno; + if (ret < 0 && mfd >= 0) + close(mfd); + return ret; +} + +int luo_session_finish(int session_fd) +{ + struct liveupdate_session_finish arg = { .size = sizeof(arg) }; + + if (ioctl(session_fd, LIVEUPDATE_SESSION_FINISH, &arg) < 0) + return -errno; + + return 0; +} + +void create_state_file(int luo_fd, const char *session_name, int token, + int next_stage) +{ + char buf[32]; + int state_session_fd; + + state_session_fd = luo_create_session(luo_fd, session_name); + if (state_session_fd < 0) + fail_exit("luo_create_session for state tracking"); + + snprintf(buf, sizeof(buf), "%d", next_stage); + if (create_and_preserve_memfd(state_session_fd, token, buf) < 0) + fail_exit("create_and_preserve_memfd for state tracking"); + + /* + * DO NOT close session FD, otherwise it is going to be unpreserved + */ +} + +void restore_and_read_stage(int state_session_fd, int token, int *stage) +{ + char buf[32] = {0}; + int mfd; + + mfd = restore_and_verify_memfd(state_session_fd, token, NULL); + if (mfd < 0) + fail_exit("failed to restore state memfd"); + + if (read(mfd, buf, sizeof(buf) - 1) < 0) + fail_exit("failed to read state mfd"); + + *stage = atoi(buf); + + close(mfd); +} + +void daemonize_and_wait(void) +{ + pid_t pid; + + ksft_print_msg("[STAGE 1] Forking persistent child to hold sessions...\n"); + + pid = fork(); + if (pid < 0) + fail_exit("fork failed"); + + if (pid > 0) { + ksft_print_msg("[STAGE 1] Child PID: %d. Resources are pinned.\n", pid); + ksft_print_msg("[STAGE 1] You may now perform kexec reboot.\n"); + exit(EXIT_SUCCESS); + } + + /* Detach from terminal so closing the window doesn't kill us */ + if (setsid() < 0) + fail_exit("setsid failed"); + + close(STDIN_FILENO); + close(STDOUT_FILENO); + close(STDERR_FILENO); + + /* Change dir to root to avoid locking filesystems */ + if (chdir("/") < 0) + exit(EXIT_FAILURE); + + while (1) + sleep(60); +} + +static int parse_stage_args(int argc, char *argv[]) +{ + static struct option long_options[] = { + {"stage", required_argument, 0, 's'}, + {0, 0, 0, 0} + }; + int option_index = 0; + int stage = 1; + int opt; + + optind = 1; + while ((opt = getopt_long(argc, argv, "s:", long_options, &option_index)) != -1) { + switch (opt) { + case 's': + stage = atoi(optarg); + if (stage != 1 && stage != 2) + fail_exit("Invalid stage argument"); + break; + default: + fail_exit("Unknown argument"); + } + } + return stage; +} + +int luo_test(int argc, char *argv[], + const char *state_session_name, + luo_test_stage1_fn stage1, + luo_test_stage2_fn stage2) +{ + int target_stage = parse_stage_args(argc, argv); + int luo_fd = luo_open_device(); + int state_session_fd; + int detected_stage; + + if (luo_fd < 0) { + ksft_exit_skip("Failed to open %s. Is the luo module loaded?\n", + LUO_DEVICE); + } + + state_session_fd = luo_retrieve_session(luo_fd, state_session_name); + if (state_session_fd == -ENOENT) + detected_stage = 1; + else if (state_session_fd >= 0) + detected_stage = 2; + else + fail_exit("Failed to check for state session"); + + if (target_stage != detected_stage) { + ksft_exit_fail_msg("Stage mismatch Requested --stage %d, but system is in stage %d.\n" + "(State session %s: %s)\n", + target_stage, detected_stage, state_session_name, + (detected_stage == 2) ? "EXISTS" : "MISSING"); + } + + if (target_stage == 1) + stage1(luo_fd); + else + stage2(luo_fd, state_session_fd); + + return 0; +} diff --git a/tools/testing/selftests/liveupdate/luo_test_utils.h b/tools/testing/selftests/liveupdate/luo_test_utils.h new file mode 100644 index 000000000000..90099bf49577 --- /dev/null +++ b/tools/testing/selftests/liveupdate/luo_test_utils.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2025, Google LLC. + * Pasha Tatashin + * + * Utility functions for LUO kselftests. + */ + +#ifndef LUO_TEST_UTILS_H +#define LUO_TEST_UTILS_H + +#include +#include +#include +#include "../kselftest.h" + +#define LUO_DEVICE "/dev/liveupdate" + +#define fail_exit(fmt, ...) \ + ksft_exit_fail_msg("[%s:%d] " fmt " (errno: %s)\n", \ + __func__, __LINE__, ##__VA_ARGS__, strerror(errno)) + +int luo_open_device(void); +int luo_create_session(int luo_fd, const char *name); +int luo_retrieve_session(int luo_fd, const char *name); +int luo_session_finish(int session_fd); + +int create_and_preserve_memfd(int session_fd, int token, const char *data); +int restore_and_verify_memfd(int session_fd, int token, const char *expected_data); + +void create_state_file(int luo_fd, const char *session_name, int token, + int next_stage); +void restore_and_read_stage(int state_session_fd, int token, int *stage); + +void daemonize_and_wait(void); + +typedef void (*luo_test_stage1_fn)(int luo_fd); +typedef void (*luo_test_stage2_fn)(int luo_fd, int state_session_fd); + +int luo_test(int argc, char *argv[], const char *state_session_name, + luo_test_stage1_fn stage1, luo_test_stage2_fn stage2); + +#endif /* LUO_TEST_UTILS_H */ diff --git a/tools/testing/selftests/lsm/lsm_get_self_attr_test.c b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c index df215e4aa63f..60caf8528f81 100644 --- a/tools/testing/selftests/lsm/lsm_get_self_attr_test.c +++ b/tools/testing/selftests/lsm/lsm_get_self_attr_test.c @@ -13,7 +13,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "common.h" static struct lsm_ctx *next_ctx(struct lsm_ctx *ctxp) diff --git a/tools/testing/selftests/lsm/lsm_list_modules_test.c b/tools/testing/selftests/lsm/lsm_list_modules_test.c index 1cc8a977c711..54d59044ace1 100644 --- a/tools/testing/selftests/lsm/lsm_list_modules_test.c +++ b/tools/testing/selftests/lsm/lsm_list_modules_test.c @@ -12,7 +12,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "common.h" TEST(size_null_lsm_list_modules) diff --git a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c index 732e89fe99c0..dcb6f8aa772e 100644 --- a/tools/testing/selftests/lsm/lsm_set_self_attr_test.c +++ b/tools/testing/selftests/lsm/lsm_set_self_attr_test.c @@ -12,7 +12,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "common.h" TEST(ctx_null_lsm_set_self_attr) diff --git a/tools/testing/selftests/media_tests/media_device_open.c b/tools/testing/selftests/media_tests/media_device_open.c index 93183a37b133..4396bf2273a4 100644 --- a/tools/testing/selftests/media_tests/media_device_open.c +++ b/tools/testing/selftests/media_tests/media_device_open.c @@ -34,7 +34,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(int argc, char **argv) { diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c index 4b9953359e40..6e4a8090a0eb 100644 --- a/tools/testing/selftests/media_tests/media_device_test.c +++ b/tools/testing/selftests/media_tests/media_device_test.c @@ -39,7 +39,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(int argc, char **argv) { diff --git a/tools/testing/selftests/membarrier/membarrier_test_impl.h b/tools/testing/selftests/membarrier/membarrier_test_impl.h index af89855adb7b..f6d7c44b2288 100644 --- a/tools/testing/selftests/membarrier/membarrier_test_impl.h +++ b/tools/testing/selftests/membarrier/membarrier_test_impl.h @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static int registrations; diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index 17ed3e9917ca..cdd022c1c497 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -15,8 +15,8 @@ #include #include -#include "../kselftest.h" -#include "../kselftest_harness.h" +#include "kselftest.h" +#include "kselftest_harness.h" /* Default test file size: 4MB */ #define MB (1UL << 20) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 9bc4591c7b16..30209c40b697 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MAP_SIZE_MB 100 #define MAP_SIZE (MAP_SIZE_MB * 1024 * 1024) diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 6560c26f47d1..accfd198dbda 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -27,7 +27,7 @@ #endif /* LOCAL_CONFIG_HAVE_LIBURING */ #include "../../../../mm/gup_test.h" -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #include "thp_settings.h" diff --git a/tools/testing/selftests/mm/droppable.c b/tools/testing/selftests/mm/droppable.c index f3d9ecf96890..44940f75c461 100644 --- a/tools/testing/selftests/mm/droppable.c +++ b/tools/testing/selftests/mm/droppable.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(int argc, char *argv[]) { diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index 795bf3f39f44..dbd21d66d383 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later #define _GNU_SOURCE -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include /* Force the import of the tools version. */ #include #include diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c index 268dadb8ce43..6279893a0adc 100644 --- a/tools/testing/selftests/mm/gup_longterm.c +++ b/tools/testing/selftests/mm/gup_longterm.c @@ -27,7 +27,7 @@ #endif /* LOCAL_CONFIG_HAVE_LIBURING */ #include "../../../../mm/gup_test.h" -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" static size_t pagesize; diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index 40c1538a17b4..fb8f9ae49efa 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -12,7 +12,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define MB (1UL << 20) diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 5a1525f72daa..e8328c89d855 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -10,7 +10,7 @@ * bugs. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include diff --git a/tools/testing/selftests/mm/hugepage-mmap.c b/tools/testing/selftests/mm/hugepage-mmap.c index 3b1b532f1cbb..d543419de040 100644 --- a/tools/testing/selftests/mm/hugepage-mmap.c +++ b/tools/testing/selftests/mm/hugepage-mmap.c @@ -15,7 +15,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c index 2bd1dac75c3f..b8f7d92e5a35 100644 --- a/tools/testing/selftests/mm/hugepage-mremap.c +++ b/tools/testing/selftests/mm/hugepage-mremap.c @@ -24,7 +24,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define DEFAULT_LENGTH_MB 10UL diff --git a/tools/testing/selftests/mm/hugetlb-madvise.c b/tools/testing/selftests/mm/hugetlb-madvise.c index c5940c0595be..05d9d2805ae4 100644 --- a/tools/testing/selftests/mm/hugetlb-madvise.c +++ b/tools/testing/selftests/mm/hugetlb-madvise.c @@ -19,7 +19,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define MIN_FREE_PAGES 20 #define NR_HUGE_PAGES 10 /* common number of pages to map/allocate */ diff --git a/tools/testing/selftests/mm/hugetlb-read-hwpoison.c b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c index ba6cc6f9cabc..46230462ad48 100644 --- a/tools/testing/selftests/mm/hugetlb-read-hwpoison.c +++ b/tools/testing/selftests/mm/hugetlb-read-hwpoison.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define PREFIX " ... " #define ERROR_PREFIX " !!! " diff --git a/tools/testing/selftests/mm/hugetlb-soft-offline.c b/tools/testing/selftests/mm/hugetlb-soft-offline.c index f086f0e04756..a8bc02688085 100644 --- a/tools/testing/selftests/mm/hugetlb-soft-offline.c +++ b/tools/testing/selftests/mm/hugetlb-soft-offline.c @@ -24,7 +24,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef MADV_SOFT_OFFLINE #define MADV_SOFT_OFFLINE 101 diff --git a/tools/testing/selftests/mm/hugetlb_dio.c b/tools/testing/selftests/mm/hugetlb_dio.c index db63abe5ee5e..9ac62eb4c97d 100644 --- a/tools/testing/selftests/mm/hugetlb_dio.c +++ b/tools/testing/selftests/mm/hugetlb_dio.c @@ -18,7 +18,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" void run_dio_using_hugetlb(unsigned int start_off, unsigned int end_off) { diff --git a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c index e2640529dbb2..b4b257775b74 100644 --- a/tools/testing/selftests/mm/hugetlb_fault_after_madv.c +++ b/tools/testing/selftests/mm/hugetlb_fault_after_madv.c @@ -9,7 +9,7 @@ #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define INLOOP_ITER 100 diff --git a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c index 8f122a0f0828..efd774b41389 100644 --- a/tools/testing/selftests/mm/hugetlb_madv_vs_map.c +++ b/tools/testing/selftests/mm/hugetlb_madv_vs_map.c @@ -25,7 +25,7 @@ #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define INLOOP_ITER 100 diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c index 95afa5cfc062..8d874c4754f3 100644 --- a/tools/testing/selftests/mm/ksm_functional_tests.c +++ b/tools/testing/selftests/mm/ksm_functional_tests.c @@ -21,7 +21,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define KiB 1024u diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index b77462b5c240..a0b48b839d54 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -12,7 +12,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include #include "vm_util.h" #include "thp_settings.h" diff --git a/tools/testing/selftests/mm/madv_populate.c b/tools/testing/selftests/mm/madv_populate.c index d8d11bc67ddc..88050e0f829a 100644 --- a/tools/testing/selftests/mm/madv_populate.c +++ b/tools/testing/selftests/mm/madv_populate.c @@ -17,7 +17,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" /* diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index 1e9980b8993c..11241edde7fe 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -12,7 +12,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" static void dump_maps(void) { diff --git a/tools/testing/selftests/mm/map_hugetlb.c b/tools/testing/selftests/mm/map_hugetlb.c index b47399feab53..aa409107611b 100644 --- a/tools/testing/selftests/mm/map_hugetlb.c +++ b/tools/testing/selftests/mm/map_hugetlb.c @@ -11,7 +11,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define LENGTH (256UL*1024*1024) #define PROTECTION (PROT_READ | PROT_WRITE) diff --git a/tools/testing/selftests/mm/map_populate.c b/tools/testing/selftests/mm/map_populate.c index 9df2636c829b..712327f4e932 100644 --- a/tools/testing/selftests/mm/map_populate.c +++ b/tools/testing/selftests/mm/map_populate.c @@ -16,7 +16,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" diff --git a/tools/testing/selftests/mm/mdwe_test.c b/tools/testing/selftests/mm/mdwe_test.c index 200bedcdc32e..647779653da0 100644 --- a/tools/testing/selftests/mm/mdwe_test.c +++ b/tools/testing/selftests/mm/mdwe_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef __aarch64__ # define PROT_BTI 0 diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 9a0597310a76..aac4f795c327 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -22,7 +22,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define fail(fmt, ...) ksft_test_result_fail(fmt, ##__VA_ARGS__) #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__) diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c index cc4253f47f10..363c1033cc7d 100644 --- a/tools/testing/selftests/mm/merge.c +++ b/tools/testing/selftests/mm/merge.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later #define _GNU_SOURCE -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index ea945eebec2f..ee24b88c2b24 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -4,7 +4,7 @@ * paths in the kernel. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "thp_settings.h" #include diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 09feeb453646..68dd447a5454 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -22,7 +22,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" static size_t pagesize; diff --git a/tools/testing/selftests/mm/mlock-random-test.c b/tools/testing/selftests/mm/mlock-random-test.c index b8d7e966f44c..9d349c151360 100644 --- a/tools/testing/selftests/mm/mlock-random-test.c +++ b/tools/testing/selftests/mm/mlock-random-test.c @@ -13,7 +13,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "mlock2.h" #define CHUNK_UNIT (128 * 1024) diff --git a/tools/testing/selftests/mm/mlock2-tests.c b/tools/testing/selftests/mm/mlock2-tests.c index 3e90ff37e336..b474f2b20def 100644 --- a/tools/testing/selftests/mm/mlock2-tests.c +++ b/tools/testing/selftests/mm/mlock2-tests.c @@ -7,7 +7,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "mlock2.h" struct vm_boundaries { diff --git a/tools/testing/selftests/mm/mrelease_test.c b/tools/testing/selftests/mm/mrelease_test.c index 100370a7111d..64e8d00ae944 100644 --- a/tools/testing/selftests/mm/mrelease_test.c +++ b/tools/testing/selftests/mm/mrelease_test.c @@ -12,7 +12,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #define MB(x) (x << 20) #define MAX_SIZE_MB 1024 diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index 1d75084b9ca5..a4f75d836733 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" unsigned long page_size; char *page_buffer; diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5f073504e0b1..308576437228 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define EXPECT_SUCCESS 0 #define EXPECT_FAILURE 1 diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index 005f29c86484..faad4833366a 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -8,7 +8,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include #include #include diff --git a/tools/testing/selftests/mm/on-fault-limit.c b/tools/testing/selftests/mm/on-fault-limit.c index 431c1277d83a..fc4117453c84 100644 --- a/tools/testing/selftests/mm/on-fault-limit.c +++ b/tools/testing/selftests/mm/on-fault-limit.c @@ -5,7 +5,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" static void test_limit(void) { diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 4fc8e578ec7c..2cb5441f29c7 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -8,7 +8,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #include #include #include diff --git a/tools/testing/selftests/mm/pfnmap.c b/tools/testing/selftests/mm/pfnmap.c index 88659f0a90ea..f546dfb10cae 100644 --- a/tools/testing/selftests/mm/pfnmap.c +++ b/tools/testing/selftests/mm/pfnmap.c @@ -22,7 +22,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "vm_util.h" static sigjmp_buf sigjmp_buf_env; diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index fa15f006fa68..7c29f075e40b 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" /* Define some kernel-like types */ typedef __u8 u8; diff --git a/tools/testing/selftests/mm/prctl_thp_disable.c b/tools/testing/selftests/mm/prctl_thp_disable.c index 84b4a4b345af..ca27200596a4 100644 --- a/tools/testing/selftests/mm/prctl_thp_disable.c +++ b/tools/testing/selftests/mm/prctl_thp_disable.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "thp_settings.h" #include "vm_util.h" diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c index 471cae8427f1..cd4610baf5d7 100644 --- a/tools/testing/selftests/mm/process_madv.c +++ b/tools/testing/selftests/mm/process_madv.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later #define _GNU_SOURCE -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/mm/rmap.c b/tools/testing/selftests/mm/rmap.c index 13f7bccfd0a9..53f2058b0ef2 100644 --- a/tools/testing/selftests/mm/rmap.c +++ b/tools/testing/selftests/mm/rmap.c @@ -5,7 +5,7 @@ * Author(s): Wei Yang */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index c3a9585de98c..59c0dbe99a9b 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #include "thp_settings.h" diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index 743af3c05190..40799f3f0213 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -20,7 +20,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" uint64_t pagesize; unsigned int pageshift; diff --git a/tools/testing/selftests/mm/thuge-gen.c b/tools/testing/selftests/mm/thuge-gen.c index 4f5e290ff1a6..77813d34dcc2 100644 --- a/tools/testing/selftests/mm/thuge-gen.c +++ b/tools/testing/selftests/mm/thuge-gen.c @@ -27,7 +27,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" #if !defined(MAP_HUGETLB) #define MAP_HUGETLB 0x40000 diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c index 68201192e37c..bcad47c09518 100644 --- a/tools/testing/selftests/mm/transhuge-stress.c +++ b/tools/testing/selftests/mm/transhuge-stress.c @@ -16,7 +16,7 @@ #include #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" int backing_fd = -1; int mmap_flags = MAP_ANONYMOUS | MAP_NORESERVE | MAP_PRIVATE; diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index 37d3ca55905f..844a85ab31eb 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -35,7 +35,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define UFFD_FLAGS (O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY) diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c index 4e4a591cf527..17186d4a4147 100644 --- a/tools/testing/selftests/mm/uffd-wp-mremap.c +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -7,7 +7,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "thp_settings.h" #include "uffd-common.h" diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c index 306eba825107..02f290a69132 100644 --- a/tools/testing/selftests/mm/va_high_addr_switch.c +++ b/tools/testing/selftests/mm/va_high_addr_switch.c @@ -10,7 +10,7 @@ #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" /* * The hint addr value is used to allocate addresses diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 81b33d8f78f4..4f0923825ed7 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -16,7 +16,7 @@ #include #include "vm_util.h" -#include "../kselftest.h" +#include "kselftest.h" /* * Maximum address range mapped with a single mmap() diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 605cb58ea5c3..d954bf91afd5 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -9,7 +9,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vm_util.h" #define PMD_SIZE_FILE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size" diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index a8abdf414d46..6ad32b1830f1 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -6,7 +6,7 @@ #include #include /* ffsl() */ #include /* _SC_PAGESIZE */ -#include "../kselftest.h" +#include "kselftest.h" #include #define BIT_ULL(nr) (1ULL << (nr)) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index a688871a98eb..7aec3ae82a44 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -21,7 +21,7 @@ #include #include "../filesystems/wrappers.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef CLONE_NEWNS #define CLONE_NEWNS 0x00020000 diff --git a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c index bcf51d785a37..12434415ec36 100644 --- a/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c +++ b/tools/testing/selftests/move_mount_set_group/move_mount_set_group_test.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef CLONE_NEWNS #define CLONE_NEWNS 0x00020000 diff --git a/tools/testing/selftests/mqueue/mq_open_tests.c b/tools/testing/selftests/mqueue/mq_open_tests.c index 9403ac01ba11..b16029c40c0f 100644 --- a/tools/testing/selftests/mqueue/mq_open_tests.c +++ b/tools/testing/selftests/mqueue/mq_open_tests.c @@ -33,7 +33,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static char *usage = "Usage:\n" diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c index fb898850867c..303c46eebd94 100644 --- a/tools/testing/selftests/mqueue/mq_perf_tests.c +++ b/tools/testing/selftests/mqueue/mq_perf_tests.c @@ -40,7 +40,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static char *usage = "Usage:\n" diff --git a/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c b/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c index 0d2af30c3bf5..cb0ca6ed7ebe 100644 --- a/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c +++ b/tools/testing/selftests/mseal_system_mappings/sysmap_is_sealed.c @@ -11,8 +11,8 @@ #include #include -#include "../kselftest.h" -#include "../kselftest_harness.h" +#include "kselftest.h" +#include "kselftest_harness.h" #define VMFLAGS "VmFlags:" #define MSEAL_FLAGS "sl" diff --git a/tools/testing/selftests/namespaces/file_handle_test.c b/tools/testing/selftests/namespaces/file_handle_test.c index f1bc5773f552..064b41ad96b2 100644 --- a/tools/testing/selftests/namespaces/file_handle_test.c +++ b/tools/testing/selftests/namespaces/file_handle_test.c @@ -14,7 +14,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef FD_NSFS_ROOT #define FD_NSFS_ROOT -10003 /* Root of the nsfs filesystem */ diff --git a/tools/testing/selftests/namespaces/init_ino_test.c b/tools/testing/selftests/namespaces/init_ino_test.c index 5b6993c3740b..e4394a2fa0a9 100644 --- a/tools/testing/selftests/namespaces/init_ino_test.c +++ b/tools/testing/selftests/namespaces/init_ino_test.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" struct ns_info { const char *name; diff --git a/tools/testing/selftests/namespaces/nsid_test.c b/tools/testing/selftests/namespaces/nsid_test.c index 527ade0a8673..b4a14c6693a5 100644 --- a/tools/testing/selftests/namespaces/nsid_test.c +++ b/tools/testing/selftests/namespaces/nsid_test.c @@ -20,7 +20,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" /* Fixture for tests that create child processes */ FIXTURE(nsid) { diff --git a/tools/testing/selftests/nci/nci_dev.c b/tools/testing/selftests/nci/nci_dev.c index 6dec59d64083..312f84ee0444 100644 --- a/tools/testing/selftests/nci/nci_dev.c +++ b/tools/testing/selftests/nci/nci_dev.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) #define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c index 79a3dd75590e..da7d50cedee6 100644 --- a/tools/testing/selftests/net/af_unix/diag_uid.c +++ b/tools/testing/selftests/net/af_unix/diag_uid.c @@ -14,7 +14,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(diag_uid) { diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c index b5f474969917..1b499d56656c 100644 --- a/tools/testing/selftests/net/af_unix/msg_oob.c +++ b/tools/testing/selftests/net/af_unix/msg_oob.c @@ -11,7 +11,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define BUF_SZ 32 diff --git a/tools/testing/selftests/net/af_unix/scm_inq.c b/tools/testing/selftests/net/af_unix/scm_inq.c index fc467714387e..3a86be9bda17 100644 --- a/tools/testing/selftests/net/af_unix/scm_inq.c +++ b/tools/testing/selftests/net/af_unix/scm_inq.c @@ -6,7 +6,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define NR_CHUNKS 100 #define MSG_LEN 256 diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index ef2921988e5f..2c18b92a2603 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -16,7 +16,7 @@ #include #include "../../pidfd/pidfd.h" -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) #define log_err(MSG, ...) \ diff --git a/tools/testing/selftests/net/af_unix/scm_rights.c b/tools/testing/selftests/net/af_unix/scm_rights.c index 914f99d153ce..d82a79c21c17 100644 --- a/tools/testing/selftests/net/af_unix/scm_rights.c +++ b/tools/testing/selftests/net/af_unix/scm_rights.c @@ -10,7 +10,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(scm_rights) { diff --git a/tools/testing/selftests/net/af_unix/unix_connect.c b/tools/testing/selftests/net/af_unix/unix_connect.c index d799fd8f5c7c..870ca96fa8ea 100644 --- a/tools/testing/selftests/net/af_unix/unix_connect.c +++ b/tools/testing/selftests/net/af_unix/unix_connect.c @@ -10,7 +10,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(unix_connect) { diff --git a/tools/testing/selftests/net/bind_timewait.c b/tools/testing/selftests/net/bind_timewait.c index cb9fdf51ea59..40126f9b901e 100644 --- a/tools/testing/selftests/net/bind_timewait.c +++ b/tools/testing/selftests/net/bind_timewait.c @@ -4,7 +4,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(bind_timewait) { diff --git a/tools/testing/selftests/net/bind_wildcard.c b/tools/testing/selftests/net/bind_wildcard.c index b7b54d646b93..7d11548b2c61 100644 --- a/tools/testing/selftests/net/bind_wildcard.c +++ b/tools/testing/selftests/net/bind_wildcard.c @@ -4,7 +4,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const __u32 in4addr_any = INADDR_ANY; static const __u32 in4addr_loopback = INADDR_LOOPBACK; diff --git a/tools/testing/selftests/net/can/test_raw_filter.c b/tools/testing/selftests/net/can/test_raw_filter.c index 4101c36390fd..bb8ae8854273 100644 --- a/tools/testing/selftests/net/can/test_raw_filter.c +++ b/tools/testing/selftests/net/can/test_raw_filter.c @@ -19,7 +19,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define ID 0x123 diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index ded9b925865e..67a72b1a2f3d 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" enum { ERN_SUCCESS = 0, diff --git a/tools/testing/selftests/net/epoll_busy_poll.c b/tools/testing/selftests/net/epoll_busy_poll.c index 16e457c2f877..adf8dd0b5e0b 100644 --- a/tools/testing/selftests/net/epoll_busy_poll.c +++ b/tools/testing/selftests/net/epoll_busy_poll.c @@ -23,7 +23,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" /* if the headers haven't been updated, we need to define some things */ #if !defined(EPOLL_IOC_TYPE) diff --git a/tools/testing/selftests/net/ip_local_port_range.c b/tools/testing/selftests/net/ip_local_port_range.c index 29451d2244b7..e6834a6cfc8f 100644 --- a/tools/testing/selftests/net/ip_local_port_range.c +++ b/tools/testing/selftests/net/ip_local_port_range.c @@ -10,7 +10,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef IP_LOCAL_PORT_RANGE #define IP_LOCAL_PORT_RANGE 51 diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index 9b44a091802c..0ccf484b1d9d 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -34,7 +34,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define printk(fmt, ...) \ ksft_print_msg("%d[%u] " fmt "\n", getpid(), __LINE__, ##__VA_ARGS__) diff --git a/tools/testing/selftests/net/ipv6_fragmentation.c b/tools/testing/selftests/net/ipv6_fragmentation.c index 267ef62b5c72..672c9fe086a7 100644 --- a/tools/testing/selftests/net/ipv6_fragmentation.c +++ b/tools/testing/selftests/net/ipv6_fragmentation.c @@ -34,7 +34,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MTU 1500 #define LARGER_THAN_MTU 8192 diff --git a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c index 5f827e10717d..5cecb8a1bc94 100644 --- a/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c +++ b/tools/testing/selftests/net/netfilter/conntrack_dump_flush.c @@ -10,7 +10,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define TEST_ZONE_ID 123 #define NF_CT_DEFAULT_ZONE_ID 0 diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 679b6c77ace7..51129c564d0a 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c index 0a5226196a2e..0f3babf19fd0 100644 --- a/tools/testing/selftests/net/ovpn/ovpn-cli.c +++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c @@ -32,7 +32,7 @@ #include -#include "../../kselftest.h" +#include "kselftest.h" /* defines to make checkpatch happy */ #define strscpy strncpy diff --git a/tools/testing/selftests/net/proc_net_pktgen.c b/tools/testing/selftests/net/proc_net_pktgen.c index 69444fb29577..fab3b5c2e25d 100644 --- a/tools/testing/selftests/net/proc_net_pktgen.c +++ b/tools/testing/selftests/net/proc_net_pktgen.c @@ -10,7 +10,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char ctrl_cmd_stop[] = "stop"; static const char ctrl_cmd_start[] = "start"; diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c index 84c524357075..ab8d8b7e6cb0 100644 --- a/tools/testing/selftests/net/psock_fanout.c +++ b/tools/testing/selftests/net/psock_fanout.c @@ -54,7 +54,7 @@ #include #include "psock_lib.h" -#include "../kselftest.h" +#include "kselftest.h" #define RING_NUM_FRAMES 20 diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 2938045c5cf9..7caf3135448d 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -46,7 +46,7 @@ #include "psock_lib.h" -#include "../kselftest.h" +#include "kselftest.h" #ifndef bug_on # define bug_on(cond) assert(!(cond)) diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c index 7b9bf8a7bbe1..5aad27a0d13a 100644 --- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c +++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c @@ -22,7 +22,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" struct reuse_opts { int reuseaddr[2]; diff --git a/tools/testing/selftests/net/reuseport_bpf.c b/tools/testing/selftests/net/reuseport_bpf.c index 65aea27d761c..b6634d6da3d6 100644 --- a/tools/testing/selftests/net/reuseport_bpf.c +++ b/tools/testing/selftests/net/reuseport_bpf.c @@ -24,7 +24,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" struct test_params { int recv_family; diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c index c9ba36aa688e..2ffd957ffb15 100644 --- a/tools/testing/selftests/net/reuseport_bpf_numa.c +++ b/tools/testing/selftests/net/reuseport_bpf_numa.c @@ -23,7 +23,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static const int PORT = 8888; diff --git a/tools/testing/selftests/net/rxtimestamp.c b/tools/testing/selftests/net/rxtimestamp.c index 16ac4df55fdb..b81ed0352d6c 100644 --- a/tools/testing/selftests/net/rxtimestamp.c +++ b/tools/testing/selftests/net/rxtimestamp.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" struct options { int so_timestamp; diff --git a/tools/testing/selftests/net/sk_so_peek_off.c b/tools/testing/selftests/net/sk_so_peek_off.c index d87dd8d8d491..2a3f5c604f52 100644 --- a/tools/testing/selftests/net/sk_so_peek_off.c +++ b/tools/testing/selftests/net/sk_so_peek_off.c @@ -8,7 +8,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" static char *afstr(int af, int proto) { diff --git a/tools/testing/selftests/net/so_incoming_cpu.c b/tools/testing/selftests/net/so_incoming_cpu.c index e9fa14e10732..4740701f1a9a 100644 --- a/tools/testing/selftests/net/so_incoming_cpu.c +++ b/tools/testing/selftests/net/so_incoming_cpu.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(so_incoming_cpu) { diff --git a/tools/testing/selftests/net/socket.c b/tools/testing/selftests/net/socket.c index be1080003c61..9e270548dad8 100644 --- a/tools/testing/selftests/net/socket.c +++ b/tools/testing/selftests/net/socket.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" struct socket_testcase { int domain; diff --git a/tools/testing/selftests/net/tap.c b/tools/testing/selftests/net/tap.c index 247c3b3ac1c9..9ec1c9b50e77 100644 --- a/tools/testing/selftests/net/tap.c +++ b/tools/testing/selftests/net/tap.c @@ -17,7 +17,7 @@ #include #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char param_dev_tap_name[] = "xmacvtap0"; static const char param_dev_dummy_name[] = "xdummy0"; diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index a27cc03c9fbd..49aec2922a31 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -9,7 +9,7 @@ * Can't be included in the header: it defines static variables which * will be unique to every object. Let's include it only once here. */ -#include "../../../kselftest.h" +#include "kselftest.h" /* Prevent overriding of one thread's output by another */ static pthread_mutex_t ksft_print_lock = PTHREAD_MUTEX_INITIALIZER; diff --git a/tools/testing/selftests/net/tcp_fastopen_backup_key.c b/tools/testing/selftests/net/tcp_fastopen_backup_key.c index c1cb0c75156a..4b3f9b5e50fe 100644 --- a/tools/testing/selftests/net/tcp_fastopen_backup_key.c +++ b/tools/testing/selftests/net/tcp_fastopen_backup_key.c @@ -26,7 +26,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef TCP_FASTOPEN_KEY #define TCP_FASTOPEN_KEY 33 diff --git a/tools/testing/selftests/net/tcp_port_share.c b/tools/testing/selftests/net/tcp_port_share.c index 4c39d599dfce..6146b62610df 100644 --- a/tools/testing/selftests/net/tcp_port_share.c +++ b/tools/testing/selftests/net/tcp_port_share.c @@ -10,7 +10,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define DST_PORT 30000 #define SRC_PORT 40000 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index da1b50b30719..a3ef4b57eb5f 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -21,7 +21,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define TLS_PAYLOAD_MAX_LEN 16384 #define SOL_TLS 282 diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index fa83918b62d1..0efc67b0357a 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static int tun_attach(int fd, char *dev) { diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index 477392715a9a..86d80cce55b4 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -25,7 +25,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef ETH_MAX_MTU #define ETH_MAX_MTU 0xFFFFU diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index 7056340b9339..510e60602511 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -12,7 +12,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define ARRAY_LEN(X) (sizeof (X) / sizeof (*(X))) #define BUILD_BUG_ON(e) ((void)(sizeof(struct { int:(-!!(e)); }))) diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 5790ab446527..0e161ef9e9e4 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "helpers.h" /* diff --git a/tools/testing/selftests/openat2/rename_attack_test.c b/tools/testing/selftests/openat2/rename_attack_test.c index 0a770728b436..aa5699e45729 100644 --- a/tools/testing/selftests/openat2/rename_attack_test.c +++ b/tools/testing/selftests/openat2/rename_attack_test.c @@ -22,7 +22,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "helpers.h" /* Construct a test directory with the following structure: diff --git a/tools/testing/selftests/openat2/resolve_test.c b/tools/testing/selftests/openat2/resolve_test.c index bbafad440893..a76ef15ceb90 100644 --- a/tools/testing/selftests/openat2/resolve_test.c +++ b/tools/testing/selftests/openat2/resolve_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "helpers.h" /* diff --git a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c index cd9075444c32..23aac6f97061 100644 --- a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c +++ b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c @@ -20,7 +20,7 @@ #include "../../../../include/uapi/linux/pcitest.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define pci_ep_ioctl(cmd, arg) \ ({ \ diff --git a/tools/testing/selftests/perf_events/mmap.c b/tools/testing/selftests/perf_events/mmap.c index ea0427aac1f9..d1fa8ec58987 100644 --- a/tools/testing/selftests/perf_events/mmap.c +++ b/tools/testing/selftests/perf_events/mmap.c @@ -14,7 +14,7 @@ #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define RB_SIZE 0x3000 #define AUX_SIZE 0x10000 diff --git a/tools/testing/selftests/perf_events/remove_on_exec.c b/tools/testing/selftests/perf_events/remove_on_exec.c index 5814611a1dc7..89e7b06835df 100644 --- a/tools/testing/selftests/perf_events/remove_on_exec.c +++ b/tools/testing/selftests/perf_events/remove_on_exec.c @@ -30,7 +30,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static volatile int signal_count; diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index d1d8483ac628..b5cf8355345d 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -31,7 +31,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define NUM_THREADS 5 diff --git a/tools/testing/selftests/perf_events/watermark_signal.c b/tools/testing/selftests/perf_events/watermark_signal.c index b3a72f0ac522..0f64b9b17081 100644 --- a/tools/testing/selftests/perf_events/watermark_signal.c +++ b/tools/testing/selftests/perf_events/watermark_signal.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static int sigio_count; diff --git a/tools/testing/selftests/pid_namespace/pid_max.c b/tools/testing/selftests/pid_namespace/pid_max.c index 96f274f0582b..c9519e7385b6 100644 --- a/tools/testing/selftests/pid_namespace/pid_max.c +++ b/tools/testing/selftests/pid_namespace/pid_max.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../pidfd/pidfd.h" #define __STACK_SIZE (8 * 1024 * 1024) diff --git a/tools/testing/selftests/pid_namespace/regression_enomem.c b/tools/testing/selftests/pid_namespace/regression_enomem.c index 7d84097ad45c..059e7ec5b4fd 100644 --- a/tools/testing/selftests/pid_namespace/regression_enomem.c +++ b/tools/testing/selftests/pid_namespace/regression_enomem.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../pidfd/pidfd.h" /* diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index d60f10a873bb..9085c1a3c005 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -25,7 +25,7 @@ #undef SCHED_FLAG_KEEP_ALL #undef SCHED_FLAG_UTIL_CLAMP -#include "../kselftest.h" +#include "kselftest.h" #include "../clone3/clone3_selftests.h" #ifndef FD_PIDFS_ROOT diff --git a/tools/testing/selftests/pidfd/pidfd_bind_mount.c b/tools/testing/selftests/pidfd/pidfd_bind_mount.c index c094aeb1c620..1fdf49939524 100644 --- a/tools/testing/selftests/pidfd/pidfd_bind_mount.c +++ b/tools/testing/selftests/pidfd/pidfd_bind_mount.c @@ -14,7 +14,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../filesystems/wrappers.h" FIXTURE(pidfd_bind_mount) { diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index f718aac75068..9935e9471c77 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -16,7 +16,7 @@ #include #include "pidfd.h" -#include "../kselftest.h" +#include "kselftest.h" struct error { int code; diff --git a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c index 6bd2e9c9565b..68918734dcf3 100644 --- a/tools/testing/selftests/pidfd/pidfd_file_handle_test.c +++ b/tools/testing/selftests/pidfd/pidfd_file_handle_test.c @@ -20,7 +20,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(file_handle) { diff --git a/tools/testing/selftests/pidfd/pidfd_getfd_test.c b/tools/testing/selftests/pidfd/pidfd_getfd_test.c index cd51d547b751..ea45b37001b0 100644 --- a/tools/testing/selftests/pidfd/pidfd_getfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_getfd_test.c @@ -19,7 +19,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" /* * UNKNOWN_FD is an fd number that should never exist in the child, as it is diff --git a/tools/testing/selftests/pidfd/pidfd_info_test.c b/tools/testing/selftests/pidfd/pidfd_info_test.c index cb5430a2fd75..6571e04acd88 100644 --- a/tools/testing/selftests/pidfd/pidfd_info_test.c +++ b/tools/testing/selftests/pidfd/pidfd_info_test.c @@ -21,7 +21,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(pidfd_info) { diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c index cd3de40e4977..318e6f09c8e0 100644 --- a/tools/testing/selftests/pidfd/pidfd_open_test.c +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -20,7 +20,7 @@ #include #include "pidfd.h" -#include "../kselftest.h" +#include "kselftest.h" static int safe_int(const char *numstr, int *converted) { diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c index 55d74a50358f..232304f818c7 100644 --- a/tools/testing/selftests/pidfd/pidfd_poll_test.c +++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c @@ -14,7 +14,7 @@ #include #include "pidfd.h" -#include "../kselftest.h" +#include "kselftest.h" static bool timeout; diff --git a/tools/testing/selftests/pidfd/pidfd_setattr_test.c b/tools/testing/selftests/pidfd/pidfd_setattr_test.c index d7de05edc4b3..e8562a2992f3 100644 --- a/tools/testing/selftests/pidfd/pidfd_setattr_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setattr_test.c @@ -22,7 +22,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(pidfs_setattr) { diff --git a/tools/testing/selftests/pidfd/pidfd_setns_test.c b/tools/testing/selftests/pidfd/pidfd_setns_test.c index e6a079b3d5e2..107edecff224 100644 --- a/tools/testing/selftests/pidfd/pidfd_setns_test.c +++ b/tools/testing/selftests/pidfd/pidfd_setns_test.c @@ -18,7 +18,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" enum { PIDFD_NS_USER, diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index fcd85cad9f18..932cbd8caa77 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -20,7 +20,7 @@ #include #include "pidfd.h" -#include "../kselftest.h" +#include "kselftest.h" #define str(s) _str(s) #define _str(s) #s diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 1e2d49751cde..4bf702d62c1c 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -17,7 +17,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) diff --git a/tools/testing/selftests/pidfd/pidfd_xattr_test.c b/tools/testing/selftests/pidfd/pidfd_xattr_test.c index 5cf7bb0e4bf2..fd57511af7e4 100644 --- a/tools/testing/selftests/pidfd/pidfd_xattr_test.c +++ b/tools/testing/selftests/pidfd/pidfd_xattr_test.c @@ -22,7 +22,7 @@ #include #include "pidfd.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" FIXTURE(pidfs_xattr) { diff --git a/tools/testing/selftests/prctl/set-anon-vma-name-test.c b/tools/testing/selftests/prctl/set-anon-vma-name-test.c index 4275cb256dce..ac6721b184a6 100644 --- a/tools/testing/selftests/prctl/set-anon-vma-name-test.c +++ b/tools/testing/selftests/prctl/set-anon-vma-name-test.c @@ -10,7 +10,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define AREA_SIZE 1024 diff --git a/tools/testing/selftests/prctl/set-process-name.c b/tools/testing/selftests/prctl/set-process-name.c index 562f707ba771..3f7b146d36df 100644 --- a/tools/testing/selftests/prctl/set-process-name.c +++ b/tools/testing/selftests/prctl/set-process-name.c @@ -7,7 +7,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define CHANGE_NAME "changename" #define EMPTY_NAME "" diff --git a/tools/testing/selftests/proc/proc-maps-race.c b/tools/testing/selftests/proc/proc-maps-race.c index a546475db550..a734553718da 100644 --- a/tools/testing/selftests/proc/proc-maps-race.c +++ b/tools/testing/selftests/proc/proc-maps-race.c @@ -23,7 +23,7 @@ * */ #define _GNU_SOURCE -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 978cbcb3eb11..4e6a3e53f975 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -51,7 +51,7 @@ #define __maybe_unused __attribute__((__unused__)) #endif -#include "../kselftest.h" +#include "kselftest.h" static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { diff --git a/tools/testing/selftests/proc/proc-pidns.c b/tools/testing/selftests/proc/proc-pidns.c index 52500597f951..25b9a2933c45 100644 --- a/tools/testing/selftests/proc/proc-pidns.c +++ b/tools/testing/selftests/proc/proc-pidns.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define ASSERT_ERRNO(expected, _t, seen) \ __EXPECT(expected, #expected, \ diff --git a/tools/testing/selftests/ptrace/get_set_sud.c b/tools/testing/selftests/ptrace/get_set_sud.c index 5297b10d25c3..2e619c7599bb 100644 --- a/tools/testing/selftests/ptrace/get_set_sud.c +++ b/tools/testing/selftests/ptrace/get_set_sud.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define _GNU_SOURCE -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/ptrace/get_syscall_info.c b/tools/testing/selftests/ptrace/get_syscall_info.c index 5bcd1c7b5be6..3f5c3a9fdaba 100644 --- a/tools/testing/selftests/ptrace/get_syscall_info.c +++ b/tools/testing/selftests/ptrace/get_syscall_info.c @@ -7,7 +7,7 @@ * matches userspace expectations. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/ptrace/set_syscall_info.c b/tools/testing/selftests/ptrace/set_syscall_info.c index 4198248ef874..1cc411a41cd6 100644 --- a/tools/testing/selftests/ptrace/set_syscall_info.c +++ b/tools/testing/selftests/ptrace/set_syscall_info.c @@ -7,7 +7,7 @@ * matches userspace expectations. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/ptrace/vmaccess.c b/tools/testing/selftests/ptrace/vmaccess.c index 4db327b44586..3801b5831527 100644 --- a/tools/testing/selftests/ptrace/vmaccess.c +++ b/tools/testing/selftests/ptrace/vmaccess.c @@ -7,7 +7,7 @@ * when de_thread is blocked with ->cred_guard_mutex held. */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include #include #include diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index cd3adfc14969..3c51bdac2dfa 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -23,7 +23,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MB (1024 * 1024) #define RESCTRL_PATH "/sys/fs/resctrl" diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index a58f520f2f41..f24677737066 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -17,7 +17,7 @@ #include #include "../user_events/user_events_selftests.h" /* share tracefs setup */ -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define TRACEFS_ROOT "/sys/kernel/tracing" diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index 059d2e87eb1f..2d540af7b558 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -9,7 +9,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #ifndef PR_PMLEN_SHIFT #define PR_PMLEN_SHIFT 24 diff --git a/tools/testing/selftests/riscv/hwprobe/cbo.c b/tools/testing/selftests/riscv/hwprobe/cbo.c index 6d99726aceac..f254b2edd6ce 100644 --- a/tools/testing/selftests/riscv/hwprobe/cbo.c +++ b/tools/testing/selftests/riscv/hwprobe/cbo.c @@ -18,7 +18,7 @@ #include #include "hwprobe.h" -#include "../../kselftest.h" +#include "kselftest.h" #define MK_CBO(fn) le32_bswap((uint32_t)(fn) << 20 | 10 << 15 | 2 << 12 | 0 << 7 | 15) #define MK_PREFETCH(fn) \ diff --git a/tools/testing/selftests/riscv/hwprobe/hwprobe.c b/tools/testing/selftests/riscv/hwprobe/hwprobe.c index fd73c87804f3..54c435af9923 100644 --- a/tools/testing/selftests/riscv/hwprobe/hwprobe.c +++ b/tools/testing/selftests/riscv/hwprobe/hwprobe.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include "hwprobe.h" -#include "../../kselftest.h" +#include "kselftest.h" int main(int argc, char **argv) { diff --git a/tools/testing/selftests/riscv/hwprobe/which-cpus.c b/tools/testing/selftests/riscv/hwprobe/which-cpus.c index 82c121412dfc..3ab53067e8dd 100644 --- a/tools/testing/selftests/riscv/hwprobe/which-cpus.c +++ b/tools/testing/selftests/riscv/hwprobe/which-cpus.c @@ -14,7 +14,7 @@ #include #include "hwprobe.h" -#include "../../kselftest.h" +#include "kselftest.h" static void help(void) { diff --git a/tools/testing/selftests/riscv/mm/mmap_bottomup.c b/tools/testing/selftests/riscv/mm/mmap_bottomup.c index f9ccae50349b..461a65c9be00 100644 --- a/tools/testing/selftests/riscv/mm/mmap_bottomup.c +++ b/tools/testing/selftests/riscv/mm/mmap_bottomup.c @@ -2,7 +2,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" TEST(infinite_rlimit) { diff --git a/tools/testing/selftests/riscv/mm/mmap_default.c b/tools/testing/selftests/riscv/mm/mmap_default.c index 3f53b6ecc326..58db7d172af2 100644 --- a/tools/testing/selftests/riscv/mm/mmap_default.c +++ b/tools/testing/selftests/riscv/mm/mmap_default.c @@ -2,7 +2,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" TEST(default_rlimit) { diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h index 75918d15919f..266a6becdeba 100644 --- a/tools/testing/selftests/riscv/mm/mmap_test.h +++ b/tools/testing/selftests/riscv/mm/mmap_test.h @@ -5,7 +5,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define TOP_DOWN 0 #define BOTTOM_UP 1 diff --git a/tools/testing/selftests/riscv/sigreturn/sigreturn.c b/tools/testing/selftests/riscv/sigreturn/sigreturn.c index ed351a1cb917..e10873d95fed 100644 --- a/tools/testing/selftests/riscv/sigreturn/sigreturn.c +++ b/tools/testing/selftests/riscv/sigreturn/sigreturn.c @@ -4,7 +4,7 @@ #include #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #define RISCV_V_MAGIC 0x53465457 #define DEFAULT_VALUE 2 diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c index be9e1d18ad29..5fd2382e15a2 100644 --- a/tools/testing/selftests/riscv/vector/v_initval.c +++ b/tools/testing/selftests/riscv/vector/v_initval.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "v_helpers.h" #define NEXT_PROGRAM "./v_exec_initval_nolibc" diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 62fbb17a0556..d607af3900c1 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -6,7 +6,7 @@ #include #include -#include "../../kselftest_harness.h" +#include "kselftest_harness.h" #include "v_helpers.h" #define NEXT_PROGRAM "./vstate_exec_nolibc" diff --git a/tools/testing/selftests/rseq/basic_percpu_ops_test.c b/tools/testing/selftests/rseq/basic_percpu_ops_test.c index 2348d2c20d0a..1193612bf327 100644 --- a/tools/testing/selftests/rseq/basic_percpu_ops_test.c +++ b/tools/testing/selftests/rseq/basic_percpu_ops_test.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "rseq.h" #ifdef BUILDOPT_RSEQ_PERCPU_MM_CID diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index dcac5cbe7933..a736727b83c1 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -33,7 +33,7 @@ #include -#include "../kselftest.h" +#include "kselftest.h" #include "rseq.h" /* diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c index be175c0e6ae3..8047d9879039 100644 --- a/tools/testing/selftests/rtc/rtctest.c +++ b/tools/testing/selftests/rtc/rtctest.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define NUM_UIE 3 #define ALARM_DELTA 3 diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index 5822e25e0217..ea4068cdefd6 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -20,7 +20,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" unsigned long long timing(clockid_t clk_id, unsigned long long samples) { diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 874f17763536..32e2d4df397b 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -54,7 +54,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "../clone3/clone3_selftests.h" /* Attempt to de-conflict with the selftests tree. */ diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index 9820b3809c69..13b84e54ce38 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -18,7 +18,7 @@ #include #include #include "defines.h" -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "main.h" static const uint64_t MAGIC = 0x1122334455667788ULL; diff --git a/tools/testing/selftests/signal/mangle_uc_sigmask.c b/tools/testing/selftests/signal/mangle_uc_sigmask.c index b79ab92178a8..11dbc14bbc8e 100644 --- a/tools/testing/selftests/signal/mangle_uc_sigmask.c +++ b/tools/testing/selftests/signal/mangle_uc_sigmask.c @@ -39,7 +39,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" void handler_verify_ucontext(int signo, siginfo_t *info, void *uc) { diff --git a/tools/testing/selftests/signal/sas.c b/tools/testing/selftests/signal/sas.c index 07227fab1cc9..306b996ab365 100644 --- a/tools/testing/selftests/signal/sas.c +++ b/tools/testing/selftests/signal/sas.c @@ -19,7 +19,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "current_stack_pointer.h" #ifndef SS_AUTODISARM diff --git a/tools/testing/selftests/sparc64/drivers/adi-test.c b/tools/testing/selftests/sparc64/drivers/adi-test.c index 84e5d9fd20b0..b986714e7a52 100644 --- a/tools/testing/selftests/sparc64/drivers/adi-test.c +++ b/tools/testing/selftests/sparc64/drivers/adi-test.c @@ -16,7 +16,7 @@ #include #include -#include "../../kselftest.h" +#include "kselftest.h" #define DEBUG_LEVEL_1_BIT (0x0001) #define DEBUG_LEVEL_2_BIT (0x0002) diff --git a/tools/testing/selftests/sync/sync_test.c b/tools/testing/selftests/sync/sync_test.c index 93db5aa246a3..2b44e5d88b63 100644 --- a/tools/testing/selftests/sync/sync_test.c +++ b/tools/testing/selftests/sync/sync_test.c @@ -34,7 +34,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "synctest.h" static int run_test(int (*test)(void), char *name) diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c index 2eb2c06303f2..b855c6000287 100644 --- a/tools/testing/selftests/syscall_user_dispatch/sud_test.c +++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #ifndef PR_SET_SYSCALL_USER_DISPATCH # define PR_SET_SYSCALL_USER_DISPATCH 59 diff --git a/tools/testing/selftests/tdx/tdx_guest_test.c b/tools/testing/selftests/tdx/tdx_guest_test.c index 81d8cb88ea1a..dfaefa685519 100644 --- a/tools/testing/selftests/tdx/tdx_guest_test.c +++ b/tools/testing/selftests/tdx/tdx_guest_test.c @@ -13,7 +13,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define TDX_GUEST_DEVNAME "/dev/tdx_guest" #define HEX_DUMP_SIZE 8 diff --git a/tools/testing/selftests/timens/timens.h b/tools/testing/selftests/timens/timens.h index d4fc52d47146..7ca4b46ca61d 100644 --- a/tools/testing/selftests/timens/timens.h +++ b/tools/testing/selftests/timens/timens.h @@ -7,7 +7,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef CLONE_NEWTIME # define CLONE_NEWTIME 0x00000080 diff --git a/tools/testing/selftests/timers/adjtick.c b/tools/testing/selftests/timers/adjtick.c index 777d9494b683..5b3ef708d6e9 100644 --- a/tools/testing/selftests/timers/adjtick.c +++ b/tools/testing/selftests/timers/adjtick.c @@ -24,7 +24,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MILLION 1000000 diff --git a/tools/testing/selftests/timers/alarmtimer-suspend.c b/tools/testing/selftests/timers/alarmtimer-suspend.c index a9ef76ea6051..aa66c805f6a4 100644 --- a/tools/testing/selftests/timers/alarmtimer-suspend.c +++ b/tools/testing/selftests/timers/alarmtimer-suspend.c @@ -30,7 +30,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define UNREASONABLE_LAT (NSEC_PER_SEC * 5) /* hopefully we resume in 5 secs */ diff --git a/tools/testing/selftests/timers/change_skew.c b/tools/testing/selftests/timers/change_skew.c index 18e794a46c23..387fda10fcd8 100644 --- a/tools/testing/selftests/timers/change_skew.c +++ b/tools/testing/selftests/timers/change_skew.c @@ -28,7 +28,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int change_skew_test(int ppm) { diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c index 83faa4e354e3..db62a764c29e 100644 --- a/tools/testing/selftests/timers/clocksource-switch.c +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -34,7 +34,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int get_clocksources(char list[][30]) diff --git a/tools/testing/selftests/timers/freq-step.c b/tools/testing/selftests/timers/freq-step.c index 73b636f89fdc..cfa46dafe3e8 100644 --- a/tools/testing/selftests/timers/freq-step.c +++ b/tools/testing/selftests/timers/freq-step.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define SAMPLES 100 #define SAMPLE_READINGS 10 diff --git a/tools/testing/selftests/timers/inconsistency-check.c b/tools/testing/selftests/timers/inconsistency-check.c index 9d1573769d55..e53e63e18683 100644 --- a/tools/testing/selftests/timers/inconsistency-check.c +++ b/tools/testing/selftests/timers/inconsistency-check.c @@ -29,7 +29,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/leap-a-day.c b/tools/testing/selftests/timers/leap-a-day.c index 04004a7c0934..3568cfb3e815 100644 --- a/tools/testing/selftests/timers/leap-a-day.c +++ b/tools/testing/selftests/timers/leap-a-day.c @@ -49,7 +49,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define CLOCK_TAI 11 diff --git a/tools/testing/selftests/timers/leapcrash.c b/tools/testing/selftests/timers/leapcrash.c index 8fd065eec904..c2d3bccb52f2 100644 --- a/tools/testing/selftests/timers/leapcrash.c +++ b/tools/testing/selftests/timers/leapcrash.c @@ -22,7 +22,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" /* clear NTP time_status & time_state */ int clear_time_state(void) diff --git a/tools/testing/selftests/timers/mqueue-lat.c b/tools/testing/selftests/timers/mqueue-lat.c index 63de2334a291..c0d9368e4fca 100644 --- a/tools/testing/selftests/timers/mqueue-lat.c +++ b/tools/testing/selftests/timers/mqueue-lat.c @@ -30,7 +30,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define TARGET_TIMEOUT 100000000 /* 100ms in nanoseconds */ diff --git a/tools/testing/selftests/timers/nanosleep.c b/tools/testing/selftests/timers/nanosleep.c index 10badae13ebe..a054680b3372 100644 --- a/tools/testing/selftests/timers/nanosleep.c +++ b/tools/testing/selftests/timers/nanosleep.c @@ -28,7 +28,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/nsleep-lat.c b/tools/testing/selftests/timers/nsleep-lat.c index de23dc0c9f97..a7ba1eb1e21b 100644 --- a/tools/testing/selftests/timers/nsleep-lat.c +++ b/tools/testing/selftests/timers/nsleep-lat.c @@ -25,7 +25,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define UNRESONABLE_LATENCY 40000000 /* 40ms in nanosecs */ diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index a563c438ac79..38512623622a 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -20,7 +20,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define DELAY 2 diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 957f7cd29cb1..a7bae7d80916 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -26,7 +26,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ diff --git a/tools/testing/selftests/timers/rtcpie.c b/tools/testing/selftests/timers/rtcpie.c index 7c07edd0d450..4ba42d198b7e 100644 --- a/tools/testing/selftests/timers/rtcpie.c +++ b/tools/testing/selftests/timers/rtcpie.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" /* * This expects the new RTC class driver framework, working with diff --git a/tools/testing/selftests/timers/set-2038.c b/tools/testing/selftests/timers/set-2038.c index ed244315e11c..ecc171de4728 100644 --- a/tools/testing/selftests/timers/set-2038.c +++ b/tools/testing/selftests/timers/set-2038.c @@ -28,7 +28,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define KTIME_MAX ((long long)~((unsigned long long)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) diff --git a/tools/testing/selftests/timers/set-tai.c b/tools/testing/selftests/timers/set-tai.c index 5b67462efcd6..e283c04284af 100644 --- a/tools/testing/selftests/timers/set-tai.c +++ b/tools/testing/selftests/timers/set-tai.c @@ -23,7 +23,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int set_tai(int offset) { diff --git a/tools/testing/selftests/timers/set-timer-lat.c b/tools/testing/selftests/timers/set-timer-lat.c index 9d8437c13929..44d2e3614fa5 100644 --- a/tools/testing/selftests/timers/set-timer-lat.c +++ b/tools/testing/selftests/timers/set-timer-lat.c @@ -29,7 +29,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" /* CLOCK_HWSPECIFIC == CLOCK_SGI_CYCLE (Deprecated) */ #define CLOCK_HWSPECIFIC 10 diff --git a/tools/testing/selftests/timers/set-tz.c b/tools/testing/selftests/timers/set-tz.c index 20daaf1782b7..334f36c0eda6 100644 --- a/tools/testing/selftests/timers/set-tz.c +++ b/tools/testing/selftests/timers/set-tz.c @@ -23,7 +23,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int set_tz(int min, int dst) { diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index 46c391d7f45d..53ee5d710ff4 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -34,7 +34,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(int argc, char **argv) { diff --git a/tools/testing/selftests/timers/threadtest.c b/tools/testing/selftests/timers/threadtest.c index d5564bbf0e50..60b8b21bf782 100644 --- a/tools/testing/selftests/timers/threadtest.c +++ b/tools/testing/selftests/timers/threadtest.c @@ -21,7 +21,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" /* serializes shared list access */ pthread_mutex_t list_lock = PTHREAD_MUTEX_INITIALIZER; diff --git a/tools/testing/selftests/timers/valid-adjtimex.c b/tools/testing/selftests/timers/valid-adjtimex.c index 6b7801055ad1..e1e56d3097d6 100644 --- a/tools/testing/selftests/timers/valid-adjtimex.c +++ b/tools/testing/selftests/timers/valid-adjtimex.c @@ -30,7 +30,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define ADJ_SETOFFSET 0x0100 diff --git a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c index 02ecfe687dc2..5cb4e404a2bd 100644 --- a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c +++ b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c @@ -23,7 +23,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" int main(void) { diff --git a/tools/testing/selftests/tty/tty_tstamp_update.c b/tools/testing/selftests/tty/tty_tstamp_update.c index 9e1a40f5db17..bc3291dcd18b 100644 --- a/tools/testing/selftests/tty/tty_tstamp_update.c +++ b/tools/testing/selftests/tty/tty_tstamp_update.c @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #define MIN_TTY_PATH_LEN 8 diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c index dbe55f3a66f4..974b076f9235 100644 --- a/tools/testing/selftests/uevent/uevent_filtering.c +++ b/tools/testing/selftests/uevent/uevent_filtering.c @@ -19,7 +19,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #define __DEV_FULL "/sys/devices/virtual/mem/full/uevent" #define __UEVENT_BUFFER_SIZE (2048 * 2) diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 7288a05136ba..85892b3b719c 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -20,7 +20,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "user_events_selftests.h" const char *data_file = "/sys/kernel/tracing/user_events_data"; diff --git a/tools/testing/selftests/user_events/dyn_test.c b/tools/testing/selftests/user_events/dyn_test.c index 54c9412f8dee..78e3c33f4015 100644 --- a/tools/testing/selftests/user_events/dyn_test.c +++ b/tools/testing/selftests/user_events/dyn_test.c @@ -14,7 +14,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "user_events_selftests.h" const char *dyn_file = "/sys/kernel/tracing/dynamic_events"; diff --git a/tools/testing/selftests/user_events/ftrace_test.c b/tools/testing/selftests/user_events/ftrace_test.c index 0bb46793dcd4..decce06b9ba8 100644 --- a/tools/testing/selftests/user_events/ftrace_test.c +++ b/tools/testing/selftests/user_events/ftrace_test.c @@ -15,7 +15,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "user_events_selftests.h" const char *data_file = "/sys/kernel/tracing/user_events_data"; diff --git a/tools/testing/selftests/user_events/perf_test.c b/tools/testing/selftests/user_events/perf_test.c index 68625362add2..cafec0e52eb3 100644 --- a/tools/testing/selftests/user_events/perf_test.c +++ b/tools/testing/selftests/user_events/perf_test.c @@ -16,7 +16,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" #include "user_events_selftests.h" const char *data_file = "/sys/kernel/tracing/user_events_data"; diff --git a/tools/testing/selftests/user_events/user_events_selftests.h b/tools/testing/selftests/user_events/user_events_selftests.h index e1c3c063c031..3b5d37e46f8a 100644 --- a/tools/testing/selftests/user_events/user_events_selftests.h +++ b/tools/testing/selftests/user_events/user_events_selftests.h @@ -9,7 +9,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" static inline void tracefs_unmount(void) { diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 238d609a457a..c620317eaeea 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "vdso_config.h" #include "vdso_call.h" #include "parse_vdso.h" diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c index 0aad682b12c8..9a5c9c05e09c 100644 --- a/tools/testing/selftests/vDSO/vdso_test_chacha.c +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -10,7 +10,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #if defined(__aarch64__) static bool cpu_has_capabilities(void) diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index da651cf53c6c..055af95aa552 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -21,7 +21,7 @@ #include "vdso_config.h" #include "vdso_call.h" -#include "../kselftest.h" +#include "kselftest.h" static const char **name; diff --git a/tools/testing/selftests/vDSO/vdso_test_getcpu.c b/tools/testing/selftests/vDSO/vdso_test_getcpu.c index cdeaed45fb26..bea8ad54da11 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getcpu.c +++ b/tools/testing/selftests/vDSO/vdso_test_getcpu.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" #include "vdso_call.h" diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c index dd1132508a0d..ef402001e898 100644 --- a/tools/testing/selftests/vDSO/vdso_test_getrandom.c +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -23,7 +23,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" #include "vdso_call.h" diff --git a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c index 9ce795b806f0..912edadad92c 100644 --- a/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c +++ b/tools/testing/selftests/vDSO/vdso_test_gettimeofday.c @@ -16,7 +16,7 @@ #include #endif -#include "../kselftest.h" +#include "kselftest.h" #include "parse_vdso.h" #include "vdso_config.h" #include "vdso_call.h" diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_device.c b/tools/testing/selftests/vfio/lib/vfio_pci_device.c index 13fdb4b0b10f..8e34b9bfc96b 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_device.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_device.c @@ -19,7 +19,7 @@ #include #include -#include "../../../kselftest.h" +#include "kselftest.h" #include #define PCI_SYSFS_PATH "/sys/bus/pci/devices" diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c index ca0e25efbfa1..6827f4a6febe 100644 --- a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c +++ b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "../../../kselftest.h" +#include "kselftest.h" #include #ifdef __x86_64__ diff --git a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c index 5397822c3dd4..16eba2ecca47 100644 --- a/tools/testing/selftests/vfio/vfio_dma_mapping_test.c +++ b/tools/testing/selftests/vfio/vfio_dma_mapping_test.c @@ -12,7 +12,7 @@ #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char *device_bdf; diff --git a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c index caf1c6291f3d..17017ed3beac 100644 --- a/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c +++ b/tools/testing/selftests/vfio/vfio_iommufd_setup_test.c @@ -11,7 +11,7 @@ #include #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char iommu_dev_path[] = "/dev/iommu"; static const char *cdev_path; diff --git a/tools/testing/selftests/vfio/vfio_pci_device_test.c b/tools/testing/selftests/vfio/vfio_pci_device_test.c index ecbb669b3765..7c0fe8ce3a61 100644 --- a/tools/testing/selftests/vfio/vfio_pci_device_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_device_test.c @@ -12,7 +12,7 @@ #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char *device_bdf; diff --git a/tools/testing/selftests/vfio/vfio_pci_driver_test.c b/tools/testing/selftests/vfio/vfio_pci_driver_test.c index f0ca8310d6a8..afa0480ddd9b 100644 --- a/tools/testing/selftests/vfio/vfio_pci_driver_test.c +++ b/tools/testing/selftests/vfio/vfio_pci_driver_test.c @@ -7,7 +7,7 @@ #include -#include "../kselftest_harness.h" +#include "kselftest_harness.h" static const char *device_bdf; diff --git a/tools/testing/selftests/wireguard/qemu/kernel.config b/tools/testing/selftests/wireguard/qemu/kernel.config index 936b18be07cf..0504c11c2de6 100644 --- a/tools/testing/selftests/wireguard/qemu/kernel.config +++ b/tools/testing/selftests/wireguard/qemu/kernel.config @@ -81,7 +81,7 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DETECT_HUNG_TASK=y CONFIG_BOOTPARAM_HARDLOCKUP_PANIC=y CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y -CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=1 CONFIG_PANIC_TIMEOUT=-1 CONFIG_STACKTRACE=y CONFIG_EARLY_PRINTK=y diff --git a/tools/testing/selftests/x86/corrupt_xstate_header.c b/tools/testing/selftests/x86/corrupt_xstate_header.c index 93a89a5997ca..f4d67b050275 100644 --- a/tools/testing/selftests/x86/corrupt_xstate_header.c +++ b/tools/testing/selftests/x86/corrupt_xstate_header.c @@ -17,7 +17,7 @@ #include #include -#include "../kselftest.h" /* For __cpuid_count() */ +#include "kselftest.h" /* For __cpuid_count() */ #include "helpers.h" static inline int xsave_enabled(void) diff --git a/tools/testing/selftests/x86/helpers.h b/tools/testing/selftests/x86/helpers.h index 6deaad035161..4c747a1278d9 100644 --- a/tools/testing/selftests/x86/helpers.h +++ b/tools/testing/selftests/x86/helpers.h @@ -7,7 +7,7 @@ #include -#include "../kselftest.h" +#include "kselftest.h" static inline unsigned long get_eflags(void) { diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0873b0e5f48b..1919fa6daec0 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -18,7 +18,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" #ifndef __x86_64__ # error This test is 64-bit only diff --git a/tools/testing/selftests/x86/syscall_numbering.c b/tools/testing/selftests/x86/syscall_numbering.c index 41c42b7b54a6..ca0eca7b9dce 100644 --- a/tools/testing/selftests/x86/syscall_numbering.c +++ b/tools/testing/selftests/x86/syscall_numbering.c @@ -25,7 +25,7 @@ #include #include -#include "../kselftest.h" +#include "kselftest.h" /* Common system call numbers */ #define SYS_READ 0 diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c index 94bee6e0c813..a5edf6c5f17e 100644 --- a/tools/testing/selftests/x86/test_mremap_vdso.c +++ b/tools/testing/selftests/x86/test_mremap_vdso.c @@ -20,7 +20,7 @@ #include #include #include -#include "../kselftest.h" +#include "kselftest.h" #define PAGE_SIZE 4096 diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c index 918eaec8bfbe..f1c3df642352 100644 --- a/tools/testing/selftests/x86/test_vsyscall.c +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -21,7 +21,7 @@ #include #include "helpers.h" -#include "../kselftest.h" +#include "kselftest.h" #ifdef __x86_64__ #define TOTAL_TESTS 13 diff --git a/tools/testing/selftests/x86/xstate.h b/tools/testing/selftests/x86/xstate.h index e91e3092b5d2..6ee816e7625a 100644 --- a/tools/testing/selftests/x86/xstate.h +++ b/tools/testing/selftests/x86/xstate.h @@ -4,7 +4,7 @@ #include -#include "../kselftest.h" +#include "kselftest.h" #define XSAVE_HDR_OFFSET 512 #define XSAVE_HDR_SIZE 64