diff options
43 files changed, 244 insertions, 156 deletions
@@ -28,6 +28,7 @@ Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> Alexander Mikhalitsyn <alexander@mihalicyn.com> <alexander.mikhalitsyn@virtuozzo.com> Alexander Mikhalitsyn <alexander@mihalicyn.com> <aleksandr.mikhalitsyn@canonical.com> Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com> +Alexandre Ghiti <alex@ghiti.fr> <alexandre.ghiti@canonical.com> Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> @@ -121,7 +122,7 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> -Dikshita Agarwal <dikshita@qti.qualcomm.com> <dikshita@codeaurora.org> +Dikshita Agarwal <quic_dikshita@quicinc.com> <dikshita@codeaurora.org> Dmitry Baryshkov <dbaryshkov@gmail.com> Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]> Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com> @@ -194,6 +195,7 @@ Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com> Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com> Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com> Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com> +Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@tuni.fi> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst index 50b690f7f663..68abc089d6dd 100644 --- a/Documentation/driver-api/vfio.rst +++ b/Documentation/driver-api/vfio.rst @@ -242,7 +242,7 @@ group and can access them as follows:: VFIO User API ------------------------------------------------------------------------------- -Please see include/linux/vfio.h for complete API documentation. +Please see include/uapi/linux/vfio.h for complete API documentation. VFIO bus driver API ------------------------------------------------------------------------------- diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index c53f30251a66..f3b344f0c0a4 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1222,7 +1222,7 @@ defined: return -ECHILD and it will be called again in ref-walk mode. -``_weak_revalidate`` +``d_weak_revalidate`` called when the VFS needs to revalidate a "jumped" dentry. This is called when a path-walk ends at dentry that was not acquired by doing a lookup in the parent directory. This includes "/", diff --git a/Documentation/maintainer/rebasing-and-merging.rst b/Documentation/maintainer/rebasing-and-merging.rst index 09f988e7fa71..85800ce95ae5 100644 --- a/Documentation/maintainer/rebasing-and-merging.rst +++ b/Documentation/maintainer/rebasing-and-merging.rst @@ -213,11 +213,7 @@ point rather than some random spot. If your upstream-bound branch has emptied entirely into the mainline during the merge window, you can pull it forward with a command like:: - git merge v5.2-rc1^0 - -The "^0" will cause Git to do a fast-forward merge (which should be -possible in this situation), thus avoiding the addition of a spurious merge -commit. + git merge --ff-only v5.2-rc1 The guidelines laid out above are just that: guidelines. There will always be situations that call out for a different solution, and these guidelines diff --git a/Documentation/mm/hugetlbfs_reserv.rst b/Documentation/mm/hugetlbfs_reserv.rst index 3d05d64de9b4..d9c2b0f01dcd 100644 --- a/Documentation/mm/hugetlbfs_reserv.rst +++ b/Documentation/mm/hugetlbfs_reserv.rst @@ -5,10 +5,10 @@ Hugetlbfs Reservation Overview ======== -Huge pages as described at Documentation/mm/hugetlbpage.rst are typically -preallocated for application use. These huge pages are instantiated in a -task's address space at page fault time if the VMA indicates huge pages are -to be used. If no huge page exists at page fault time, the task is sent +Huge pages as described at Documentation/admin-guide/mm/hugetlbpage.rst are +typically preallocated for application use. These huge pages are instantiated +in a task's address space at page fault time if the VMA indicates huge pages +are to be used. If no huge page exists at page fault time, the task is sent a SIGBUS and often dies an unhappy death. Shortly after huge page support was added, it was determined that it would be better to detect a shortage of huge pages at mmap() time. The idea is that if there were not enough diff --git a/Documentation/mm/physical_memory.rst b/Documentation/mm/physical_memory.rst index f9d7ea4b9dca..1bc888d36ea1 100644 --- a/Documentation/mm/physical_memory.rst +++ b/Documentation/mm/physical_memory.rst @@ -66,7 +66,7 @@ one of the types described below. also populated on boot using one of ``kernelcore``, ``movablecore`` and ``movable_node`` kernel command line parameters. See Documentation/mm/page_migration.rst and - Documentation/admin-guide/mm/memory_hotplug.rst for additional details. + Documentation/admin-guide/mm/memory-hotplug.rst for additional details. * ``ZONE_DEVICE`` represents memory residing on devices such as PMEM and GPU. It has different characteristics than RAM zone types and it exists to provide diff --git a/Documentation/process/programming-language.rst b/Documentation/process/programming-language.rst index 5fc9160ca1fa..bc56dee6d0bc 100644 --- a/Documentation/process/programming-language.rst +++ b/Documentation/process/programming-language.rst @@ -12,10 +12,6 @@ under ``-std=gnu11`` [gcc-c-dialect-options]_: the GNU dialect of ISO C11. This dialect contains many extensions to the language [gnu-extensions]_, and many of them are used within the kernel as a matter of course. -There is some support for compiling the kernel with ``icc`` [icc]_ for several -of the architectures, although at the time of writing it is not completed, -requiring third-party patches. - Attributes ---------- @@ -35,12 +31,28 @@ in order to feature detect which ones can be used and/or to shorten the code. Please refer to ``include/linux/compiler_attributes.h`` for more information. +Rust +---- + +The kernel has experimental support for the Rust programming language +[rust-language]_ under ``CONFIG_RUST``. It is compiled with ``rustc`` [rustc]_ +under ``--edition=2021`` [rust-editions]_. Editions are a way to introduce +small changes to the language that are not backwards compatible. + +On top of that, some unstable features [rust-unstable-features]_ are used in +the kernel. Unstable features may change in the future, thus it is an important +goal to reach a point where only stable features are used. + +Please refer to Documentation/rust/index.rst for more information. + .. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards .. [gcc] https://gcc.gnu.org .. [clang] https://clang.llvm.org -.. [icc] https://software.intel.com/en-us/c-compilers .. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html .. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html .. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html .. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf - +.. [rust-language] https://www.rust-lang.org +.. [rustc] https://doc.rust-lang.org/rustc/ +.. [rust-editions] https://doc.rust-lang.org/edition-guide/editions/ +.. [rust-unstable-features] https://github.com/Rust-for-Linux/linux/issues/2 diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index eac7167dce83..69ce64e03c70 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -320,7 +320,7 @@ for their time. Code review is a tiring and time-consuming process, and reviewers sometimes get grumpy. Even in that case, though, respond politely and address the problems they have pointed out. When sending a next version, add a ``patch changelog`` to the cover letter or to individual patches -explaining difference aganst previous submission (see +explaining difference against previous submission (see :ref:`the_canonical_patch_format`). See Documentation/process/email-clients.rst for recommendations on email diff --git a/Documentation/scheduler/sched-capacity.rst b/Documentation/scheduler/sched-capacity.rst index 8e2b8538bc2b..e2c1cf743158 100644 --- a/Documentation/scheduler/sched-capacity.rst +++ b/Documentation/scheduler/sched-capacity.rst @@ -258,7 +258,7 @@ Linux cannot currently figure out CPU capacity on its own, this information thus needs to be handed to it. Architectures must define arch_scale_cpu_capacity() for that purpose. -The arm and arm64 architectures directly map this to the arch_topology driver +The arm, arm64, and RISC-V architectures directly map this to the arch_topology driver CPU scaling data, which is derived from the capacity-dmips-mhz CPU binding; see Documentation/devicetree/bindings/cpu/cpu-capacity.txt. diff --git a/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst b/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst index c1fa35315d8b..b7a0544224ad 100644 --- a/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst +++ b/Documentation/translations/zh_CN/mm/hugetlbfs_reserv.rst @@ -15,7 +15,8 @@ Hugetlbfs 预留 概述 ==== -Documentation/mm/hugetlbpage.rst 中描述的巨页通常是预先分配给应用程序使用的。如果VMA指 +Documentation/admin-guide/mm/hugetlbpage.rst +中描述的巨页通常是预先分配给应用程序使用的 。如果VMA指 示要使用巨页,这些巨页会在缺页异常时被实例化到任务的地址空间。如果在缺页异常 时没有巨页存在,任务就会被发送一个SIGBUS,并经常不高兴地死去。在加入巨页支 持后不久,人们决定,在mmap()时检测巨页的短缺情况会更好。这个想法是,如果 diff --git a/Documentation/translations/zh_CN/scheduler/sched-capacity.rst b/Documentation/translations/zh_CN/scheduler/sched-capacity.rst index e07ffdd391d3..8cba135dcd1a 100644 --- a/Documentation/translations/zh_CN/scheduler/sched-capacity.rst +++ b/Documentation/translations/zh_CN/scheduler/sched-capacity.rst @@ -231,7 +231,7 @@ CFS调度类基于实体负载跟踪机制(Per-Entity Load Tracking, PELT) 当前,Linux无法凭自身算出CPU算力,因此必须要有把这个信息传递给Linux的方式。每个架构必须为此 定义arch_scale_cpu_capacity()函数。 -arm和arm64架构直接把这个信息映射到arch_topology驱动的CPU scaling数据中(译注:参考 +arm、arm64和RISC-V架构直接把这个信息映射到arch_topology驱动的CPU scaling数据中(译注:参考 arch_topology.h的percpu变量cpu_scale),它是从capacity-dmips-mhz CPU binding中衍生计算 出来的。参见Documentation/devicetree/bindings/cpu/cpu-capacity.txt。 diff --git a/MAINTAINERS b/MAINTAINERS index ec57c42ed544..a3b14ec33830 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17990,7 +17990,7 @@ F: Documentation/devicetree/bindings/spi/microchip,mpfs-spi.yaml F: Documentation/devicetree/bindings/usb/microchip,mpfs-musb.yaml F: arch/riscv/boot/dts/microchip/ F: drivers/char/hw_random/mpfs-rng.c -F: drivers/clk/microchip/clk-mpfs.c +F: drivers/clk/microchip/clk-mpfs*.c F: drivers/i2c/busses/i2c-microchip-corei2c.c F: drivers/mailbox/mailbox-mpfs.c F: drivers/pci/controller/pcie-microchip-host.c diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 1265ad519249..fb4f1e01b64a 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -136,10 +136,12 @@ SYM_TYPED_FUNC_START(ftrace_stub) RET SYM_FUNC_END(ftrace_stub) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_TYPED_FUNC_START(ftrace_stub_graph) CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub_graph) +#endif #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index b6c5bf69a2b2..1eef05bb1f99 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -91,7 +91,7 @@ config COMMON_CLK_RK808 config COMMON_CLK_HI655X tristate "Clock driver for Hi655x" if EXPERT depends on (MFD_HI655X_PMIC || COMPILE_TEST) - depends on REGMAP + select REGMAP default MFD_HI655X_PMIC help This driver supports the hi655x PMIC clock. This diff --git a/drivers/clk/bcm/clk-bcm2835-aux.c b/drivers/clk/bcm/clk-bcm2835-aux.c index 290a2846a86b..0fafa5cba442 100644 --- a/drivers/clk/bcm/clk-bcm2835-aux.c +++ b/drivers/clk/bcm/clk-bcm2835-aux.c @@ -69,4 +69,3 @@ builtin_platform_driver(bcm2835_aux_clk_driver); MODULE_AUTHOR("Eric Anholt <eric@anholt.net>"); MODULE_DESCRIPTION("BCM2835 auxiliary peripheral clock driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index e74fe6219d14..8dc476ef5bf9 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -2350,4 +2350,3 @@ builtin_platform_driver(bcm2835_clk_driver); MODULE_AUTHOR("Eric Anholt <eric@anholt.net>"); MODULE_DESCRIPTION("BCM2835 clock driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/clk/clk-fixed-mmio.c b/drivers/clk/clk-fixed-mmio.c index 5225d17d6b3f..8609fca29cc4 100644 --- a/drivers/clk/clk-fixed-mmio.c +++ b/drivers/clk/clk-fixed-mmio.c @@ -99,4 +99,3 @@ module_platform_driver(of_fixed_mmio_clk_driver); MODULE_AUTHOR("Jan Kotas <jank@cadence.com>"); MODULE_DESCRIPTION("Memory Mapped IO Fixed clock driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/clk/clk-fsl-sai.c b/drivers/clk/clk-fsl-sai.c index 6238fcea0467..ee5baf993ff2 100644 --- a/drivers/clk/clk-fsl-sai.c +++ b/drivers/clk/clk-fsl-sai.c @@ -88,5 +88,4 @@ module_platform_driver(fsl_sai_clk_driver); MODULE_DESCRIPTION("Freescale SAI bitclock-as-a-clock driver"); MODULE_AUTHOR("Michael Walle <michael@walle.cc>"); -MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:fsl-sai-clk"); diff --git a/drivers/clk/clk-k210.c b/drivers/clk/clk-k210.c index 67a7cb3503c3..4eed667eddaf 100644 --- a/drivers/clk/clk-k210.c +++ b/drivers/clk/clk-k210.c @@ -495,7 +495,7 @@ static unsigned long k210_pll_get_rate(struct clk_hw *hw, f = FIELD_GET(K210_PLL_CLKF, reg) + 1; od = FIELD_GET(K210_PLL_CLKOD, reg) + 1; - return (u64)parent_rate * f / (r * od); + return div_u64((u64)parent_rate * f, r * od); } static const struct clk_ops k210_pll_ops = { diff --git a/drivers/clk/hisilicon/clk-hi3559a.c b/drivers/clk/hisilicon/clk-hi3559a.c index 9ea1a80acbe8..8036bd8cbb0a 100644 --- a/drivers/clk/hisilicon/clk-hi3559a.c +++ b/drivers/clk/hisilicon/clk-hi3559a.c @@ -841,5 +841,4 @@ static void __exit hi3559av100_crg_exit(void) module_exit(hi3559av100_crg_exit); -MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("HiSilicon Hi3559AV100 CRG Driver"); diff --git a/drivers/clk/microchip/clk-mpfs-ccc.c b/drivers/clk/microchip/clk-mpfs-ccc.c index 0ddc73e07be4..bce61c45e967 100644 --- a/drivers/clk/microchip/clk-mpfs-ccc.c +++ b/drivers/clk/microchip/clk-mpfs-ccc.c @@ -291,4 +291,3 @@ module_exit(clk_ccc_exit); MODULE_DESCRIPTION("Microchip PolarFire SoC Clock Conditioning Circuitry Driver"); MODULE_AUTHOR("Conor Dooley <conor.dooley@microchip.com>"); -MODULE_LICENSE("GPL"); diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 058fbe28107e..25fc4120b618 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -96,6 +96,7 @@ struct mlx5_vdpa_dev { struct mlx5_control_vq cvq; struct workqueue_struct *wq; unsigned int group2asid[MLX5_VDPA_NUMVQ_GROUPS]; + bool suspended; }; int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 3a0e721aef05..520646ae7fa0 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2438,7 +2438,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, if (err) goto err_mr; - if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK) || mvdev->suspended) goto err_mr; restore_channels_info(ndev); @@ -2606,6 +2606,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; + ndev->mvdev.suspended = false; ndev->cur_num_vqs = 0; ndev->mvdev.cvq.received_desc = 0; ndev->mvdev.cvq.completed_desc = 0; @@ -2852,6 +2853,8 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) struct mlx5_vdpa_virtqueue *mvq; int i; + mlx5_vdpa_info(mvdev, "suspending device\n"); + down_write(&ndev->reslock); ndev->nb_registered = false; mlx5_notifier_unregister(mvdev->mdev, &ndev->nb); @@ -2861,6 +2864,7 @@ static int mlx5_vdpa_suspend(struct vdpa_device *vdev) suspend_vq(ndev, mvq); } mlx5_vdpa_cvq_suspend(mvdev); + mvdev->suspended = true; up_write(&ndev->reslock); return 0; } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 6a0a65814626..eea23c630f7c 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -68,6 +68,17 @@ static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx) (uintptr_t)vq->device_addr); vq->vring.last_avail_idx = last_avail_idx; + + /* + * Since vdpa_sim does not support receive inflight descriptors as a + * destination of a migration, let's set both avail_idx and used_idx + * the same at vq start. This is how vhost-user works in a + * VHOST_SET_VRING_BASE call. + * + * Although the simple fix is to set last_used_idx at + * vdpasim_set_vq_state, it would be reset at vdpasim_queue_ready. + */ + vq->vring.last_used_idx = last_avail_idx; vq->vring.notify = vdpasim_vq_notify; } diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index 8fe267ca3e76..281287fae89f 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -645,8 +645,8 @@ static void vp_vdpa_remove(struct pci_dev *pdev) struct virtio_pci_modern_device *mdev = NULL; mdev = vp_vdpa_mgtdev->mdev; - vp_modern_remove(mdev); vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev); + vp_modern_remove(mdev); kfree(vp_vdpa_mgtdev->mgtdev.id_table); kfree(mdev); kfree(vp_vdpa_mgtdev); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index dc12dbd5b43b..7be9d9d8f01c 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1169,6 +1169,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) err_attach: iommu_domain_free(v->domain); + v->domain = NULL; return ret; } @@ -1213,6 +1214,7 @@ static void vhost_vdpa_cleanup(struct vhost_vdpa *v) vhost_vdpa_remove_as(v, asid); } + vhost_vdpa_free_domain(v); vhost_dev_cleanup(&v->vdev); kfree(v->vdev.vqs); } @@ -1285,7 +1287,6 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep) vhost_vdpa_clean_irq(v); vhost_vdpa_reset(v); vhost_dev_stop(&v->vdev); - vhost_vdpa_free_domain(v); vhost_vdpa_config_put(v); vhost_vdpa_cleanup(v); mutex_unlock(&d->mutex); diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1d65f6ef00ca..0394505fdce3 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1977,11 +1977,26 @@ int ocfs2_write_end_nolock(struct address_space *mapping, } if (unlikely(copied < len) && wc->w_target_page) { + loff_t new_isize; + if (!PageUptodate(wc->w_target_page)) copied = 0; - ocfs2_zero_new_buffers(wc->w_target_page, start+copied, - start+len); + new_isize = max_t(loff_t, i_size_read(inode), pos + copied); + if (new_isize > page_offset(wc->w_target_page)) + ocfs2_zero_new_buffers(wc->w_target_page, start+copied, + start+len); + else { + /* + * When page is fully beyond new isize (data copy + * failed), do not bother zeroing the page. Invalidate + * it instead so that writeback does not get confused + * put page & buffer dirty bits into inconsistent + * state. + */ + block_invalidate_folio(page_folio(wc->w_target_page), + 0, PAGE_SIZE); + } } if (wc->w_target_page) flush_dcache_page(wc->w_target_page); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..6f3175f0678a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1363,7 +1363,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index e299f29375bb..6811e43c1b5c 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -242,12 +242,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -260,9 +259,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ diff --git a/kernel/compat.c b/kernel/compat.c index 55551989d9da..fb50f29d9b36 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -152,7 +152,7 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, if (len & (sizeof(compat_ulong_t)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index af017e038b48..488655f2319f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8414,14 +8414,14 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, if (len & (sizeof(unsigned long)-1)) return -EINVAL; - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; ret = sched_getaffinity(pid, mask); if (ret == 0) { unsigned int retlen = min(len, cpumask_size()); - if (copy_to_user(user_mask_ptr, mask, retlen)) + if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen)) ret = -EFAULT; else ret = retlen; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 29baa97d0d53..9b2803c7a18f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1564,7 +1564,8 @@ static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) key.flags = end; /* overload flags, as it is unsigned long */ for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || + if (pg->index == 0 || + end < pg->records[0].ip || start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) continue; rec = bsearch(&key, pg->records, pg->index, diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 89877a18f933..486cca3c2b75 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1331,6 +1331,9 @@ static const char *hist_field_name(struct hist_field *field, { const char *field_name = ""; + if (WARN_ON_ONCE(!field)) + return field_name; + if (level > 1) return field_name; @@ -4235,6 +4238,15 @@ static int __create_val_field(struct hist_trigger_data *hist_data, goto out; } + /* Some types cannot be a value */ + if (hist_field->flags & (HIST_FIELD_FL_GRAPH | HIST_FIELD_FL_PERCENT | + HIST_FIELD_FL_BUCKET | HIST_FIELD_FL_LOG2 | + HIST_FIELD_FL_SYM | HIST_FIELD_FL_SYM_OFFSET | + HIST_FIELD_FL_SYSCALL | HIST_FIELD_FL_STACKTRACE)) { + hist_err(file->tr, HIST_ERR_BAD_FIELD_MODIFIER, errpos(field_str)); + ret = -EINVAL; + } + hist_data->fields[val_idx] = hist_field; ++hist_data->n_vals; diff --git a/lib/zstd/common/zstd_deps.h b/lib/zstd/common/zstd_deps.h index 7a5bf44839c9..f06df065dec0 100644 --- a/lib/zstd/common/zstd_deps.h +++ b/lib/zstd/common/zstd_deps.h @@ -84,7 +84,7 @@ static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) { #include <linux/kernel.h> -#define assert(x) WARN_ON((x)) +#define assert(x) WARN_ON(!(x)) #endif /* ZSTD_DEPS_ASSERT */ #endif /* ZSTD_DEPS_NEED_ASSERT */ diff --git a/lib/zstd/decompress/huf_decompress.c b/lib/zstd/decompress/huf_decompress.c index 89b269a641c7..60958afebc41 100644 --- a/lib/zstd/decompress/huf_decompress.c +++ b/lib/zstd/decompress/huf_decompress.c @@ -985,7 +985,7 @@ static void HUF_fillDTableX2Level2(HUF_DEltX2* DTable, U32 targetLog, const U32 static void HUF_fillDTableX2(HUF_DEltX2* DTable, const U32 targetLog, const sortedSymbol_t* sortedList, - const U32* rankStart, rankVal_t rankValOrigin, const U32 maxWeight, + const U32* rankStart, rankValCol_t *rankValOrigin, const U32 maxWeight, const U32 nbBitsBaseline) { U32* const rankVal = rankValOrigin[0]; diff --git a/lib/zstd/decompress/zstd_decompress.c b/lib/zstd/decompress/zstd_decompress.c index b9b935a9f5c0..6b3177c94711 100644 --- a/lib/zstd/decompress/zstd_decompress.c +++ b/lib/zstd/decompress/zstd_decompress.c @@ -798,7 +798,7 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity, if (srcSize == 0) return 0; RETURN_ERROR(dstBuffer_null, ""); } - ZSTD_memcpy(dst, src, srcSize); + ZSTD_memmove(dst, src, srcSize); return srcSize; } @@ -858,6 +858,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, /* Loop on each block */ while (1) { + BYTE* oBlockEnd = oend; size_t decodedSize; blockProperties_t blockProperties; size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSrcSize, &blockProperties); @@ -867,16 +868,34 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, remainingSrcSize -= ZSTD_blockHeaderSize; RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong, ""); + if (ip >= op && ip < oBlockEnd) { + /* We are decompressing in-place. Limit the output pointer so that we + * don't overwrite the block that we are currently reading. This will + * fail decompression if the input & output pointers aren't spaced + * far enough apart. + * + * This is important to set, even when the pointers are far enough + * apart, because ZSTD_decompressBlock_internal() can decide to store + * literals in the output buffer, after the block it is decompressing. + * Since we don't want anything to overwrite our input, we have to tell + * ZSTD_decompressBlock_internal to never write past ip. + * + * See ZSTD_allocateLiteralsBuffer() for reference. + */ + oBlockEnd = op + (ip - op); + } + switch(blockProperties.blockType) { case bt_compressed: - decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oend-op), ip, cBlockSize, /* frame */ 1, not_streaming); + decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oBlockEnd-op), ip, cBlockSize, /* frame */ 1, not_streaming); break; case bt_raw : + /* Use oend instead of oBlockEnd because this function is safe to overlap. It uses memmove. */ decodedSize = ZSTD_copyRawBlock(op, (size_t)(oend-op), ip, cBlockSize); break; case bt_rle : - decodedSize = ZSTD_setRleBlock(op, (size_t)(oend-op), *ip, blockProperties.origSize); + decodedSize = ZSTD_setRleBlock(op, (size_t)(oBlockEnd-op), *ip, blockProperties.origSize); break; case bt_reserved : default: diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 6c655d9b5639..dd9c33fbe805 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -130,7 +130,6 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz) accessed = false; else accessed = true; - folio_put(folio); goto out; } @@ -144,10 +143,10 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz) if (need_lock) folio_unlock(folio); - folio_put(folio); out: *folio_sz = folio_size(folio); + folio_put(folio); return accessed; } @@ -281,8 +280,8 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate( folio_mark_accessed(folio); else folio_deactivate(folio); - folio_put(folio); applied += folio_nr_pages(folio); + folio_put(folio); } return applied * PAGE_SIZE; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4fc43859e59a..032fb0ef9cd1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2037,7 +2037,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; - pmd_t _pmd; + pmd_t _pmd, old_pmd; int i; /* @@ -2048,7 +2048,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, * * See Documentation/mm/mmu_notifier.rst */ - pmdp_huge_clear_flush(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); @@ -2057,6 +2057,8 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pte_t *pte, entry; entry = pfn_pte(my_zero_pfn(haddr), vma->vm_page_prot); entry = pte_mkspecial(entry); + if (pmd_uffd_wp(old_pmd)) + entry = pte_mkuffd_wp(entry); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte_none(*pte)); set_pte_at(mm, haddr, pte, entry); diff --git a/mm/migrate.c b/mm/migrate.c index 98f1c11197a8..db3f154446af 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1112,9 +1112,8 @@ static void migrate_folio_done(struct folio *src, /* Obtain the lock on page, remove all ptes. */ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page, unsigned long private, struct folio *src, - struct folio **dstp, int force, bool avoid_force_lock, - enum migrate_mode mode, enum migrate_reason reason, - struct list_head *ret) + struct folio **dstp, enum migrate_mode mode, + enum migrate_reason reason, struct list_head *ret) { struct folio *dst; int rc = -EAGAIN; @@ -1144,7 +1143,7 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page dst->private = NULL; if (!folio_trylock(src)) { - if (!force || mode == MIGRATE_ASYNC) + if (mode == MIGRATE_ASYNC) goto out; /* @@ -1163,17 +1162,6 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page if (current->flags & PF_MEMALLOC) goto out; - /* - * We have locked some folios and are going to wait to lock - * this folio. To avoid a potential deadlock, let's bail - * out and not do that. The locked folios will be moved and - * unlocked, then we can wait to lock this folio. - */ - if (avoid_force_lock) { - rc = -EDEADLOCK; - goto out; - } - folio_lock(src); } locked = true; @@ -1193,8 +1181,6 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page rc = -EBUSY; goto out; } - if (!force) - goto out; folio_wait_writeback(src); } @@ -1253,7 +1239,7 @@ static int migrate_folio_unmap(new_page_t get_new_page, free_page_t put_new_page /* Establish migration ptes */ VM_BUG_ON_FOLIO(folio_test_anon(src) && !folio_test_ksm(src) && !anon_vma, src); - try_to_migrate(src, TTU_BATCH_FLUSH); + try_to_migrate(src, mode == MIGRATE_ASYNC ? TTU_BATCH_FLUSH : 0); page_was_mapped = 1; } @@ -1267,7 +1253,7 @@ out: * A folio that has not been unmapped will be restored to * right list unless we want to retry. */ - if (rc == -EAGAIN || rc == -EDEADLOCK) + if (rc == -EAGAIN) ret = NULL; migrate_folio_undo_src(src, page_was_mapped, anon_vma, locked, ret); @@ -1508,6 +1494,9 @@ static inline int try_split_folio(struct folio *folio, struct list_head *split_f #define NR_MAX_BATCHED_MIGRATION 512 #endif #define NR_MAX_MIGRATE_PAGES_RETRY 10 +#define NR_MAX_MIGRATE_ASYNC_RETRY 3 +#define NR_MAX_MIGRATE_SYNC_RETRY \ + (NR_MAX_MIGRATE_PAGES_RETRY - NR_MAX_MIGRATE_ASYNC_RETRY) struct migrate_pages_stats { int nr_succeeded; /* Normal and large folios migrated successfully, in @@ -1618,13 +1607,19 @@ static int migrate_hugetlbs(struct list_head *from, new_page_t get_new_page, /* * migrate_pages_batch() first unmaps folios in the from list as many as * possible, then move the unmapped folios. + * + * We only batch migration if mode == MIGRATE_ASYNC to avoid to wait a + * lock or bit when we have locked more than one folio. Which may cause + * deadlock (e.g., for loop device). So, if mode != MIGRATE_ASYNC, the + * length of the from list must be <= 1. */ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page, free_page_t put_new_page, unsigned long private, enum migrate_mode mode, int reason, struct list_head *ret_folios, - struct migrate_pages_stats *stats) + struct list_head *split_folios, struct migrate_pages_stats *stats, + int nr_pass) { - int retry; + int retry = 1; int large_retry = 1; int thp_retry = 1; int nr_failed = 0; @@ -1634,21 +1629,15 @@ static int migrate_pages_batch(struct list_head *from, new_page_t get_new_page, bool is_large = false; bool is_thp = false; struct folio *folio, *folio2, *dst = NULL, *dst2; - int rc, rc_saved, nr_pages; - LIST_HEAD(split_folios); + int rc, rc_saved = 0, nr_pages; LIST_HEAD(unmap_folios); LIST_HEAD(dst_folios); bool nosplit = (reason == MR_NUMA_MISPLACED); - bool no_split_folio_counting = false; - bool avoid_force_lock; -retry: - rc_saved = 0; - avoid_force_lock = false; - retry = 1; - for (pass = 0; - pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry); - pass++) { + VM_WARN_ON_ONCE(mode != MIGRATE_ASYNC && + !list_empty(from) && !list_is_singular(from)); + + for (pass = 0; pass < nr_pass && (retry || large_retry); pass++) { retry = 0; large_retry = 0; thp_retry = 0; @@ -1679,7 +1668,7 @@ retry: if (!thp_migration_supported() && is_thp) { nr_large_failed++; stats->nr_thp_failed++; - if (!try_split_folio(folio, &split_folios)) { + if (!try_split_folio(folio, split_folios)) { stats->nr_thp_split++; continue; } @@ -1689,15 +1678,13 @@ retry: } rc = migrate_folio_unmap(get_new_page, put_new_page, private, - folio, &dst, pass > 2, avoid_force_lock, - mode, reason, ret_folios); + folio, &dst, mode, reason, ret_folios); /* * The rules are: * Success: folio will be freed * Unmap: folio will be put on unmap_folios list, * dst folio put on dst_folios list * -EAGAIN: stay on the from list - * -EDEADLOCK: stay on the from list * -ENOMEM: stay on the from list * Other errno: put on ret_folios list */ @@ -1712,7 +1699,7 @@ retry: stats->nr_thp_failed += is_thp; /* Large folio NUMA faulting doesn't split to retry. */ if (!nosplit) { - int ret = try_split_folio(folio, &split_folios); + int ret = try_split_folio(folio, split_folios); if (!ret) { stats->nr_thp_split += is_thp; @@ -1729,18 +1716,11 @@ retry: break; } } - } else if (!no_split_folio_counting) { + } else { nr_failed++; } stats->nr_failed_pages += nr_pages + nr_retry_pages; - /* - * There might be some split folios of fail-to-migrate large - * folios left in split_folios list. Move them to ret_folios - * list so that they could be put back to the right list by - * the caller otherwise the folio refcnt will be leaked. - */ - list_splice_init(&split_folios, ret_folios); /* nr_failed isn't updated for not used */ nr_large_failed += large_retry; stats->nr_thp_failed += thp_retry; @@ -1749,19 +1729,11 @@ retry: goto out; else goto move; - case -EDEADLOCK: - /* - * The folio cannot be locked for potential deadlock. - * Go move (and unlock) all locked folios. Then we can - * try again. - */ - rc_saved = rc; - goto move; case -EAGAIN: if (is_large) { large_retry++; thp_retry += is_thp; - } else if (!no_split_folio_counting) { + } else { retry++; } nr_retry_pages += nr_pages; @@ -1771,11 +1743,6 @@ retry: stats->nr_thp_succeeded += is_thp; break; case MIGRATEPAGE_UNMAP: - /* - * We have locked some folios, don't force lock - * to avoid deadlock. - */ - avoid_force_lock = true; list_move_tail(&folio->lru, &unmap_folios); list_add_tail(&dst->lru, &dst_folios); break; @@ -1789,7 +1756,7 @@ retry: if (is_large) { nr_large_failed++; stats->nr_thp_failed += is_thp; - } else if (!no_split_folio_counting) { + } else { nr_failed++; } @@ -1807,9 +1774,7 @@ move: try_to_unmap_flush(); retry = 1; - for (pass = 0; - pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry); - pass++) { + for (pass = 0; pass < nr_pass && (retry || large_retry); pass++) { retry = 0; large_retry = 0; thp_retry = 0; @@ -1838,7 +1803,7 @@ move: if (is_large) { large_retry++; thp_retry += is_thp; - } else if (!no_split_folio_counting) { + } else { retry++; } nr_retry_pages += nr_pages; @@ -1851,7 +1816,7 @@ move: if (is_large) { nr_large_failed++; stats->nr_thp_failed += is_thp; - } else if (!no_split_folio_counting) { + } else { nr_failed++; } @@ -1888,30 +1853,52 @@ out: dst2 = list_next_entry(dst, lru); } - /* - * Try to migrate split folios of fail-to-migrate large folios, no - * nr_failed counting in this round, since all split folios of a - * large folio is counted as 1 failure in the first round. - */ - if (rc >= 0 && !list_empty(&split_folios)) { - /* - * Move non-migrated folios (after NR_MAX_MIGRATE_PAGES_RETRY - * retries) to ret_folios to avoid migrating them again. - */ - list_splice_init(from, ret_folios); - list_splice_init(&split_folios, from); - no_split_folio_counting = true; - goto retry; - } + return rc; +} +static int migrate_pages_sync(struct list_head *from, new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason, struct list_head *ret_folios, + struct list_head *split_folios, struct migrate_pages_stats *stats) +{ + int rc, nr_failed = 0; + LIST_HEAD(folios); + struct migrate_pages_stats astats; + + memset(&astats, 0, sizeof(astats)); + /* Try to migrate in batch with MIGRATE_ASYNC mode firstly */ + rc = migrate_pages_batch(from, get_new_page, put_new_page, private, MIGRATE_ASYNC, + reason, &folios, split_folios, &astats, + NR_MAX_MIGRATE_ASYNC_RETRY); + stats->nr_succeeded += astats.nr_succeeded; + stats->nr_thp_succeeded += astats.nr_thp_succeeded; + stats->nr_thp_split += astats.nr_thp_split; + if (rc < 0) { + stats->nr_failed_pages += astats.nr_failed_pages; + stats->nr_thp_failed += astats.nr_thp_failed; + list_splice_tail(&folios, ret_folios); + return rc; + } + stats->nr_thp_failed += astats.nr_thp_split; + nr_failed += astats.nr_thp_split; /* - * We have unlocked all locked folios, so we can force lock now, let's - * try again. + * Fall back to migrate all failed folios one by one synchronously. All + * failed folios except split THPs will be retried, so their failure + * isn't counted */ - if (rc == -EDEADLOCK) - goto retry; + list_splice_tail_init(&folios, from); + while (!list_empty(from)) { + list_move(from->next, &folios); + rc = migrate_pages_batch(&folios, get_new_page, put_new_page, + private, mode, reason, ret_folios, + split_folios, stats, NR_MAX_MIGRATE_SYNC_RETRY); + list_splice_tail_init(&folios, ret_folios); + if (rc < 0) + return rc; + nr_failed += rc; + } - return rc; + return nr_failed; } /* @@ -1949,6 +1936,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, struct folio *folio, *folio2; LIST_HEAD(folios); LIST_HEAD(ret_folios); + LIST_HEAD(split_folios); struct migrate_pages_stats stats; trace_mm_migrate_pages_start(mode, reason); @@ -1959,6 +1947,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page, mode, reason, &stats, &ret_folios); if (rc_gather < 0) goto out; + again: nr_pages = 0; list_for_each_entry_safe(folio, folio2, from, lru) { @@ -1969,20 +1958,36 @@ again: } nr_pages += folio_nr_pages(folio); - if (nr_pages > NR_MAX_BATCHED_MIGRATION) + if (nr_pages >= NR_MAX_BATCHED_MIGRATION) break; } - if (nr_pages > NR_MAX_BATCHED_MIGRATION) - list_cut_before(&folios, from, &folio->lru); + if (nr_pages >= NR_MAX_BATCHED_MIGRATION) + list_cut_before(&folios, from, &folio2->lru); else list_splice_init(from, &folios); - rc = migrate_pages_batch(&folios, get_new_page, put_new_page, private, - mode, reason, &ret_folios, &stats); + if (mode == MIGRATE_ASYNC) + rc = migrate_pages_batch(&folios, get_new_page, put_new_page, private, + mode, reason, &ret_folios, &split_folios, &stats, + NR_MAX_MIGRATE_PAGES_RETRY); + else + rc = migrate_pages_sync(&folios, get_new_page, put_new_page, private, + mode, reason, &ret_folios, &split_folios, &stats); list_splice_tail_init(&folios, &ret_folios); if (rc < 0) { rc_gather = rc; + list_splice_tail(&split_folios, &ret_folios); goto out; } + if (!list_empty(&split_folios)) { + /* + * Failure isn't counted since all split folios of a large folio + * is counted as 1 failure already. And, we only try to migrate + * with minimal effort, force MIGRATE_ASYNC mode and retry once. + */ + migrate_pages_batch(&split_folios, get_new_page, put_new_page, private, + MIGRATE_ASYNC, reason, &ret_folios, NULL, &stats, 1); + list_splice_tail_init(&split_folios, &ret_folios); + } rc_gather += rc; if (!list_empty(from)) goto again; diff --git a/mm/mincore.c b/mm/mincore.c index cd69b9db0081..d359650b0f75 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -33,7 +33,7 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, * Hugepages under user process are always in RAM and never * swapped out, but theoretically it needs to be checked. */ - present = pte && !huge_pte_none(huge_ptep_get(pte)); + present = pte && !huge_pte_none_mostly(huge_ptep_get(pte)); for (; addr != end; vec++, addr += PAGE_SIZE) *vec = present; walk->private = vec; diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile index 5fd1424db37d..c382f579fe94 100644 --- a/tools/testing/selftests/amd-pstate/Makefile +++ b/tools/testing/selftests/amd-pstate/Makefile @@ -4,10 +4,15 @@ # No binaries, but make sure arg-less "make" doesn't trigger "run_tests" all: -uname_M := $(shell uname -m 2>/dev/null || echo not) -ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +ARCH ?= $(shell uname -m 2>/dev/null || echo not) +ARCH := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -TEST_PROGS := run.sh -TEST_FILES := basic.sh tbench.sh gitsource.sh +ifeq (x86,$(ARCH)) +TEST_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py +TEST_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py +endif + +TEST_PROGS += run.sh +TEST_FILES += basic.sh tbench.sh gitsource.sh include ../lib.mk diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index f7900e75d230..05400462c779 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -10,12 +10,14 @@ endif CLANG_TARGET_FLAGS_arm := arm-linux-gnueabi CLANG_TARGET_FLAGS_arm64 := aarch64-linux-gnu CLANG_TARGET_FLAGS_hexagon := hexagon-linux-musl +CLANG_TARGET_FLAGS_i386 := i386-linux-gnu CLANG_TARGET_FLAGS_m68k := m68k-linux-gnu CLANG_TARGET_FLAGS_mips := mipsel-linux-gnu CLANG_TARGET_FLAGS_powerpc := powerpc64le-linux-gnu CLANG_TARGET_FLAGS_riscv := riscv64-linux-gnu CLANG_TARGET_FLAGS_s390 := s390x-linux-gnu CLANG_TARGET_FLAGS_x86 := x86_64-linux-gnu +CLANG_TARGET_FLAGS_x86_64 := x86_64-linux-gnu CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) ifeq ($(CROSS_COMPILE),) diff --git a/tools/virtio/.gitignore b/tools/virtio/.gitignore index 075588c4da08..9934d48d9a55 100644 --- a/tools/virtio/.gitignore +++ b/tools/virtio/.gitignore @@ -2,3 +2,4 @@ *.d virtio_test vringh_test +virtio-trace/trace-agent |