- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] memcg: support ksm merge any mode per cgroup
by Nanyong Sun 14 Dec '23

14 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8OIQR ---------------------------------------------------------------------- Add control file "memory.ksm" to enable ksm per cgroup. Echo to 1 will set all tasks currently in the cgroup to ksm merge any mode, which means ksm gets enabled for all vma's of a process. Meanwhile echo to 0 will disable ksm for them and unmerge the merged pages. Cat the file will show the above state and ksm related profits of this cgroup. Signed-off-by: Nanyong Sun <sunnanyong(a)huawei.com> --- .../admin-guide/cgroup-v1/memory.rst | 1 + mm/memcontrol.c | 110 +++++++++++++++++- 2 files changed, 109 insertions(+), 2 deletions(-) diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst index ff456871bf4b..3fdb48435e8e 100644 --- a/Documentation/admin-guide/cgroup-v1/memory.rst +++ b/Documentation/admin-guide/cgroup-v1/memory.rst @@ -109,6 +109,7 @@ Brief summary of control files. memory.kmem.tcp.failcnt show the number of tcp buf memory usage hits limits memory.kmem.tcp.max_usage_in_bytes show max tcp buf memory usage recorded + memory.ksm set/show ksm merge any mode ==================================== ========================================== 1. History diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8a881ab21f6c..be37c2dda785 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -73,6 +73,7 @@ #include <linux/uaccess.h> #include <trace/events/vmscan.h> +#include <linux/ksm.h> struct cgroup_subsys memory_cgrp_subsys __read_mostly; EXPORT_SYMBOL(memory_cgrp_subsys); @@ -230,10 +231,15 @@ enum res_type { iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) +static inline bool __task_is_dying(struct task_struct *task) +{ + return tsk_is_oom_victim(task) || fatal_signal_pending(task) || + (task->flags & PF_EXITING); +} + static inline bool task_is_dying(void) { - return tsk_is_oom_victim(current) || fatal_signal_pending(current) || - (current->flags & PF_EXITING); + return __task_is_dying(current); } /* Some nice accessors for the vmpressure. */ @@ -5010,6 +5016,98 @@ static int mem_cgroup_slab_show(struct seq_file *m, void *p) } #endif +#ifdef CONFIG_KSM +static int memcg_set_ksm_for_tasks(struct mem_cgroup *memcg, bool enable) +{ + struct task_struct *task; + struct mm_struct *mm; + struct css_task_iter it; + int ret = 0; + + css_task_iter_start(&memcg->css, CSS_TASK_ITER_PROCS, &it); + while (!ret && (task = css_task_iter_next(&it))) { + if (__task_is_dying(task)) + continue; + + mm = get_task_mm(task); + if (!mm) + continue; + + if (mmap_write_lock_killable(mm)) { + mmput(mm); + continue; + } + + if (enable) + ret = ksm_enable_merge_any(mm); + else + ret = ksm_disable_merge_any(mm); + + mmap_write_unlock(mm); + mmput(mm); + } + css_task_iter_end(&it); + + return ret; +} + +static int memory_ksm_show(struct seq_file *m, void *v) +{ + unsigned long ksm_merging_pages = 0; + unsigned long ksm_rmap_items = 0; + long ksm_process_profits = 0; + unsigned int tasks = 0; + struct task_struct *task; + struct mm_struct *mm; + struct css_task_iter it; + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + css_task_iter_start(&memcg->css, CSS_TASK_ITER_PROCS, &it); + while ((task = css_task_iter_next(&it))) { + mm = get_task_mm(task); + if (!mm) + continue; + + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + tasks++; + + ksm_rmap_items += mm->ksm_rmap_items; + ksm_merging_pages += mm->ksm_merging_pages; + ksm_process_profits += ksm_process_profit(mm); + mmput(mm); + } + css_task_iter_end(&it); + + seq_printf(m, "merge any tasks: %u\n", tasks); + seq_printf(m, "ksm_rmap_items %lu\n", ksm_rmap_items); + seq_printf(m, "ksm_merging_pages %lu\n", ksm_merging_pages); + seq_printf(m, "ksm_process_profits %ld\n", ksm_process_profits); + return 0; +} + +static ssize_t memory_ksm_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + bool enable; + int err; + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + + buf = strstrip(buf); + if (!buf) + return -EINVAL; + + err = kstrtobool(buf, &enable); + if (err) + return err; + + err = memcg_set_ksm_for_tasks(memcg, enable); + if (err) + return err; + + return nbytes; +} +#endif /* CONFIG_KSM */ + static int memory_stat_show(struct seq_file *m, void *v); static struct cftype mem_cgroup_legacy_files[] = { @@ -5138,6 +5236,14 @@ static struct cftype mem_cgroup_legacy_files[] = { .write = mem_cgroup_reset, .read_u64 = mem_cgroup_read_u64, }, +#ifdef CONFIG_KSM + { + .name = "ksm", + .flags = CFTYPE_NOT_ON_ROOT, + .write = memory_ksm_write, + .seq_show = memory_ksm_show, + }, +#endif { }, /* terminate */ }; -- 2.25.1

2 1

[PATCH OLK-6.6 v2] arm64/ascend: Add new enable_oom_killer interface for oom contrl
by Yuan Can 14 Dec '23

14 Dec '23

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------------------------------------------- Support disable oom-killer, and report oom events to bbox vm.enable_oom_killer: 0: disable oom killer 1: enable oom killer (default,compatible with mainline) Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> --- include/linux/oom.h | 24 +++++++++++++++++++ mm/Kconfig | 10 ++++++++ mm/memcontrol.c | 20 ++++++++++++++++ mm/oom_kill.c | 57 +++++++++++++++++++++++++++++++++++++++++++++ mm/util.c | 2 ++ 5 files changed, 113 insertions(+) diff --git a/include/linux/oom.h b/include/linux/oom.h index 7d0c9c48a0c5..b9210e272651 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -112,4 +112,28 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); +#define OOM_TYPE_NOMEM 0 +#define OOM_TYPE_OVERCOMMIT 1 +#define OOM_TYPE_CGROUP 2 + +#ifdef CONFIG_ASCEND_OOM +int register_hisi_oom_notifier(struct notifier_block *nb); +int unregister_hisi_oom_notifier(struct notifier_block *nb); +int oom_type_notifier_call(unsigned int type, struct oom_control *oc); +#else +static inline int register_hisi_oom_notifier(struct notifier_block *nb) +{ + return -EINVAL; +} + +static inline int unregister_hisi_oom_notifier(struct notifier_block *nb) +{ + return -EINVAL; +} + +static inline int oom_type_notifier_call(unsigned int type, struct oom_control *oc) +{ + return -EINVAL; +} +#endif #endif /* _INCLUDE_LINUX_OOM_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 0f68e5bbeb89..48f4aeeaeff9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1302,6 +1302,16 @@ config SHARE_POOL in kernel and user level, which is only enabled for ascend platform. To enable this feature, enable_ascend_share_pool bootarg is needed. +config ASCEND_OOM + bool "Enable support for disable oom killer" + default n + help + In some cases we hopes that the oom will not kill the process when it occurs, + be able to notify the black box to report the event, and be able to trigger + the panic to locate the problem. + vm.enable_oom_killer: + 0: disable oom killer + 1: enable oom killer (default,compatible with mainline) source "mm/damon/Kconfig" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8a881ab21f6c..fec6f37e61da 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1955,6 +1955,7 @@ static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) current->memcg_in_oom = memcg; current->memcg_oom_gfp_mask = mask; current->memcg_oom_order = order; + oom_type_notifier_call(OOM_TYPE_CGROUP, NULL); } return false; } @@ -2019,6 +2020,8 @@ bool mem_cgroup_oom_synchronize(bool handle) if (locked) mem_cgroup_oom_notify(memcg); + oom_type_notifier_call(OOM_TYPE_CGROUP, NULL); + schedule(); mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); @@ -3140,6 +3143,20 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) return ret; } +#ifdef CONFIG_ASCEND_OOM +void hisi_oom_recover(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + memcg = get_mem_cgroup_from_objcg(objcg); + if (!mem_cgroup_is_root(memcg)) + memcg_oom_recover(memcg); + css_put(&memcg->css); +} +#else +static inline void hisi_oom_recover(struct obj_cgroup *objcg) { } +#endif + /** * __memcg_kmem_uncharge_page: uncharge a kmem page * @page: page to uncharge @@ -3156,6 +3173,9 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) objcg = __folio_objcg(folio); obj_cgroup_uncharge_pages(objcg, nr_pages); + + hisi_oom_recover(objcg); + folio->memcg_data = 0; obj_cgroup_put(objcg); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 44bde56ecd02..601ee56cc7d7 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -55,6 +55,7 @@ static int sysctl_panic_on_oom; static int sysctl_oom_kill_allocating_task; static int sysctl_oom_dump_tasks = 1; +static int sysctl_enable_oom_killer = 1; /* * Serializes oom killer invocations (out_of_memory()) from all contexts to @@ -724,6 +725,17 @@ static struct ctl_table vm_oom_kill_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_ASCEND_OOM + { + .procname = "enable_oom_killer", + .data = &sysctl_enable_oom_killer, + .maxlen = sizeof(sysctl_enable_oom_killer), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif {} }; #endif @@ -1073,6 +1085,7 @@ static void check_panic_on_oom(struct oom_control *oc) if (is_sysrq_oom(oc)) return; dump_header(oc, NULL); + oom_type_notifier_call(OOM_TYPE_NOMEM, oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -1091,6 +1104,45 @@ int unregister_oom_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_oom_notifier); +#ifdef CONFIG_ASCEND_OOM +static BLOCKING_NOTIFIER_HEAD(oom_type_notify_list); + +int register_hisi_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&oom_type_notify_list, nb); +} +EXPORT_SYMBOL_GPL(register_hisi_oom_notifier); + +int unregister_hisi_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&oom_type_notify_list, nb); +} +EXPORT_SYMBOL_GPL(unregister_hisi_oom_notifier); + +int oom_type_notifier_call(unsigned int type, struct oom_control *oc) +{ + struct oom_control oc_tmp = { 0 }; + static unsigned long caller_jiffies; + + if (sysctl_enable_oom_killer) + return -EINVAL; + + if (oc) + type = is_memcg_oom(oc) ? OOM_TYPE_CGROUP : OOM_TYPE_NOMEM; + else + oc = &oc_tmp; + + if (printk_timed_ratelimit(&caller_jiffies, 10000)) { + pr_err("OOM_NOTIFIER: oom type %u\n", type); + dump_stack(); + show_mem(); + dump_tasks(oc); + } + + return blocking_notifier_call_chain(&oom_type_notify_list, type, NULL); +} +#endif + /** * out_of_memory - kill the "best" process when we run out of memory * @oc: pointer to struct oom_control @@ -1107,6 +1159,11 @@ bool out_of_memory(struct oom_control *oc) if (oom_killer_disabled) return false; + if (!sysctl_enable_oom_killer) { + oom_type_notifier_call(OOM_TYPE_NOMEM, oc); + return false; + } + if (!is_memcg_oom(oc)) { blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0 && !is_sysrq_oom(oc)) diff --git a/mm/util.c b/mm/util.c index 90250cbc82fe..e41ac8a58eb5 100644 --- a/mm/util.c +++ b/mm/util.c @@ -26,6 +26,7 @@ #include <linux/share_pool.h> #include <linux/uaccess.h> +#include <linux/oom.h> #include "internal.h" #include "swap.h" @@ -981,6 +982,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) error: pr_warn_ratelimited("%s: pid: %d, comm: %s, not enough memory for the allocation\n", __func__, current->pid, current->comm); + oom_type_notifier_call(OOM_TYPE_OVERCOMMIT, NULL); vm_unacct_memory(pages); return -ENOMEM; -- 2.17.1

2 1

[PATCH OLK-6.6 0/8] kaslr: ppc64: Introduce KASLR for PPC64
by GUO Zihua 14 Dec '23

14 Dec '23

This patchset introduces KASLR for PowerPC64 chips. GUO Zihua (2): kaslr: ppc64: Provide correct r5 value for relocated kernel powerpc: kaslr: Fix preserved memory size for int-vectors issue Jason Yan (6): powerpc/fsl_booke/kaslr: refactor kaslr_legal_offset() and kaslr_early_init() powerpc/fsl_booke/64: introduce reloc_kernel_entry() helper powerpc/fsl_booke/64: implement KASLR for fsl_booke64 powerpc/fsl_booke/64: do not clear the BSS for the second pass powerpc/fsl_booke/64: clear the original kernel if randomized powerpc/fsl_booke/kaslr: rename kaslr-booke32.rst to kaslr-booke.rst and add 64bit part Documentation/powerpc/index.rst | 2 +- .../{kaslr-booke32.rst => kaslr-booke.rst} | 35 ++++++- arch/powerpc/Kconfig | 5 +- arch/powerpc/kernel/exceptions-64e.S | 27 ++++++ arch/powerpc/kernel/head_64.S | 22 +++++ arch/powerpc/kernel/prom.c | 8 +- arch/powerpc/kernel/setup_64.c | 3 + arch/powerpc/mm/mmu_decl.h | 25 ++--- arch/powerpc/mm/nohash/kaslr_booke.c | 91 +++++++++++++------ 9 files changed, 169 insertions(+), 49 deletions(-) rename Documentation/powerpc/{kaslr-booke32.rst => kaslr-booke.rst} (59%) -- 2.34.1

2 9

[PATCH OLK-6.6] serial: amba-pl011: Fix serial port discard interrupt when interrupt signal line of serial port is connected to mbigen.
by Yuan Can 14 Dec '23

14 Dec '23

ascend inclusion category: bugfix Bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: N/A --------------------------------------- Hisi when designing ascend chip, connect the serial port interrupt signal lines to mbigen equipment, mbigen write GICD_SETSPI_NSR register trigger the SPI interrupt. This can result in serial port drop interrupts. Signed-off-by: Xu Qiang <xuqiang36(a)huawei.com> Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- drivers/tty/serial/Kconfig | 15 +++++++++++++++ drivers/tty/serial/amba-pl011.c | 17 +++++++++++++++++ 2 files changed, 32 insertions(+) diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index bdc568a4ab66..a2577253f774 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -73,6 +73,21 @@ config SERIAL_AMBA_PL011_CONSOLE your boot loader (lilo or loadlin) about how to pass options to the kernel at boot time.) +config SERIAL_ATTACHED_MBIGEN + bool "Serial port interrupt signal lines connected to the mbigen" + depends on SERIAL_AMBA_PL011=y + depends on ASCEND_FEATURES + default n + help + Say Y here when the interrupt signal line of the serial port is + connected to the mbigne. The mbigen device has the function of + clearing interrupts automatically. However, the interrupt processing + function of the serial port driver may process multiple interrupts + at a time. The mbigen device cannot adapt to this scenario. + As a result, interrupts are lost.Because it maybe discard interrupt. + + If unsure, say N. + config SERIAL_EARLYCON_SEMIHOST bool "Early console using Arm compatible semihosting" depends on ARM64 || ARM || RISCV diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 3dc9b0fcab1c..713e3ef8738f 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1548,6 +1548,18 @@ static void check_apply_cts_event_workaround(struct uart_amba_port *uap) pl011_read(uap, REG_ICR); } +#ifdef CONFIG_SERIAL_ATTACHED_MBIGEN +static bool pl011_enable_hisi_wkrd; +static int __init pl011_check_hisi_workaround_setup(char *str) +{ + pl011_enable_hisi_wkrd = 1; + return 0; +} +__setup("pl011_hisi_wkrd", pl011_check_hisi_workaround_setup); +#else +#define pl011_enable_hisi_wkrd 0 +#endif + static irqreturn_t pl011_int(int irq, void *dev_id) { struct uart_amba_port *uap = dev_id; @@ -1585,6 +1597,11 @@ static irqreturn_t pl011_int(int irq, void *dev_id) handled = 1; } + if (pl011_enable_hisi_wkrd) { + pl011_write(0, uap, REG_IMSC); + pl011_write(uap->im, uap, REG_IMSC); + } + spin_unlock_irqrestore(&uap->port.lock, flags); return IRQ_RETVAL(handled); -- 2.17.1

3 2

[PATCH V2 OLK-6.6 0/6] Add support for hisi HBM devices
by Zhang Zekun 14 Dec '23

14 Dec '23

Add support for HISI HBM device, and HBM ACLS repair. The patch set includes three functionalities. 1. Add support for hbm device hotplug. 2. provide extra information with hbm locality information 3. Add support for HBM acls repair. Zhang Zekun (6): ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information soc: hbmcache: Add support for online and offline the hbm cache soc: hisilicon: hisi_hbmdev: Add hbm acls repair and query methods drivers/acpi/acpi_memhotplug.c | 30 ++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/base/container.c | 3 + drivers/soc/hisilicon/Kconfig | 36 +++ drivers/soc/hisilicon/Makefile | 3 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 435 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 ++ include/linux/acpi.h | 1 + include/linux/memory_hotplug.h | 4 + 11 files changed, 691 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

3 9

[PATCH OLK-6.6] fs/dirty_pages: dump the number of dirty pages for each inode
by Zizhi Wo 14 Dec '23

14 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8OHM4?from=project-issue --------------------------- In order to analyse the IO performance when using buffer IO, it's useful to obtain the number of dirty pages for each inode in the filesystem. This feature depends on 'CONFIG_DIRTY_PAGES'. It creates 2 interfaces by using profs. /proc/dirty/page_threshold to filter result and /proc/dirty/dirty_list to get dirty pages. Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/Kconfig | 13 ++ fs/Makefile | 1 + fs/dirty_pages.c | 275 +++++++++++++++++++++++++ 5 files changed, 291 insertions(+) create mode 100644 fs/dirty_pages.c diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 3781d138c3e3..ce101e7d8fcc 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -6881,6 +6881,7 @@ CONFIG_PROC_PAGE_MONITOR=y CONFIG_PROC_CHILDREN=y CONFIG_KERNFS=y CONFIG_SYSFS=y +CONFIG_DIRTY_PAGES=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_XATTR=y diff --git a/arch/x86/configs/openeuler_defconfig b/arch/x86/configs/openeuler_defconfig index e19bf53c0bd9..76b87ed62579 100644 --- a/arch/x86/configs/openeuler_defconfig +++ b/arch/x86/configs/openeuler_defconfig @@ -8088,6 +8088,7 @@ CONFIG_PROC_PID_ARCH_STATUS=y CONFIG_PROC_CPU_RESCTRL=y CONFIG_KERNFS=y CONFIG_SYSFS=y +CONFIG_DIRTY_PAGES=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_TMPFS_XATTR=y diff --git a/fs/Kconfig b/fs/Kconfig index aa7e03cc1941..a2280cf98729 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -170,6 +170,19 @@ source "fs/proc/Kconfig" source "fs/kernfs/Kconfig" source "fs/sysfs/Kconfig" +config DIRTY_PAGES + bool "Dumps the number of dirty pages of each file" + depends on PROC_FS + default y + help + This config supports the rendering of dirty page data to the user, + which may be useful to analyze the IO performance when using buffer + IO. + + It create 3 interfaces by using procfs. /proc/dirty/buffer_size for + buffer allocation and release; /proc/dirty/page_threshold to filter + result; /proc/dirty/dirty_list to get dirty pages. + config TMPFS bool "Tmpfs virtual memory file system support (former shm fs)" depends on SHMEM diff --git a/fs/Makefile b/fs/Makefile index f9541f40be4e..6246e173e1e4 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -44,6 +44,7 @@ obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o obj-$(CONFIG_NFS_COMMON) += nfs_common/ obj-$(CONFIG_COREDUMP) += coredump.o obj-$(CONFIG_SYSCTL) += drop_caches.o sysctls.o +obj-$(CONFIG_DIRTY_PAGES) += dirty_pages.o obj-$(CONFIG_FHANDLE) += fhandle.o obj-y += iomap/ diff --git a/fs/dirty_pages.c b/fs/dirty_pages.c new file mode 100644 index 000000000000..4edcba2bf1d0 --- /dev/null +++ b/fs/dirty_pages.c @@ -0,0 +1,275 @@ +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/uaccess.h> +#include <linux/pagemap.h> +#include <linux/pagevec.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/proc_fs.h> +#include <linux/kdev_t.h> +#include <linux/vmalloc.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include "internal.h" + +static int buff_limit; /* filter threshold of dirty pages*/ + +static struct proc_dir_entry *dirty_dir; + +/* proc root directory */ +#define DIRTY_ROOT "dirty" +/* proc file to obtain diry pages of each inode */ +#define DIRTY_PAGES "dirty_list" +/* proc file to filter result */ +#define DIRTY_LIMIT "page_threshold" + +static void seq_set_overflow(struct seq_file *m) +{ + m->count = m->size; +} + +static unsigned long dump_dirtypages_inode(struct inode *inode) +{ + struct folio_batch fbatch; + unsigned long nr_dirtys = 0; + unsigned int nr_folios; + pgoff_t index = 0; + + folio_batch_init(&fbatch); + + while (1) { + nr_folios = filemap_get_folios_tag(inode->i_mapping, &index, + (pgoff_t)-1, PAGECACHE_TAG_DIRTY, &fbatch); + if (!nr_folios) + break; + + folio_batch_release(&fbatch); + cond_resched(); + + nr_dirtys += nr_folios; + } + + return nr_dirtys; +} + +static char *inode_filename(struct inode *inode, char *tmpname) +{ + struct dentry *dentry; + char *filename; + + dentry = d_find_alias(inode); + if (!dentry) + return ERR_PTR(-ENOENT); + + tmpname[PATH_MAX-1] = '\0'; + filename = dentry_path_raw(dentry, tmpname, PATH_MAX); + + dput(dentry); + + return filename; +} + +static inline bool is_sb_writable(struct super_block *sb) +{ + if (sb_rdonly(sb)) + return false; + + if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) + return false; + + return true; +} + +/* + * dump_dirtypages_sb - dump the dirty pages of each inode in the sb + * @sb the super block + * @m the seq_file witch is initialized in proc_dpages_open + * + * For each inode in the sb, call dump_dirtypages_pages to get the number + * of dirty pages. And use seq_printf to store the result in the buffer + * if it's not less than the threshold. The inode in unusual state will + * be skipped. + */ +static void dump_dirtypages_sb(struct super_block *sb, struct seq_file *m) +{ + struct inode *inode, *toput_inode = NULL; + unsigned long nr_dirtys; + const char *fstype; + char *filename; + char *tmpname; + int limit = READ_ONCE(buff_limit); + + if (!is_sb_writable(sb)) + return; + + tmpname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!tmpname) + return; + + spin_lock(&sb->s_inode_list_lock); + list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + spin_lock(&inode->i_lock); + + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ + if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || + (inode->i_mapping->nrpages == 0 && !need_resched())) { + spin_unlock(&inode->i_lock); + continue; + } + __iget(inode); + spin_unlock(&inode->i_lock); + spin_unlock(&sb->s_inode_list_lock); + + cond_resched(); + + nr_dirtys = dump_dirtypages_inode(inode); + if (!nr_dirtys || nr_dirtys < limit) + goto skip; + + filename = inode_filename(inode, tmpname); + if (IS_ERR_OR_NULL(filename)) + filename = "unknown"; + + if (sb->s_type && sb->s_type->name) + fstype = sb->s_type->name; + else + fstype = "unknown"; + /* + * seq_printf return nothing, if the buffer is exhausted + * (m->size <= m->count), seq_printf will not store + * anything, just set m->count = m->size and return. In + * that case, log a warn message in buffer to remind users. + */ + if (m->size <= m->count) { + seq_set_overflow(m); + strncpy(m->buf+m->count-12, "terminated\n\0", 12); + iput(inode); + goto done; + } + seq_printf(m, "FSType: %s, Dev ID: %u(%u:%u) ino %lu, dirty pages %lu, path %s\n", + fstype, sb->s_dev, MAJOR(sb->s_dev), + MINOR(sb->s_dev), inode->i_ino, + nr_dirtys, filename); +skip: + iput(toput_inode); + toput_inode = inode; + spin_lock(&sb->s_inode_list_lock); + } + spin_unlock(&sb->s_inode_list_lock); +done: + iput(toput_inode); + kfree(tmpname); +} + +static int proc_dpages_show(struct seq_file *m, void *v) +{ + iterate_supers((void *)dump_dirtypages_sb, (void *)m); + return 0; +} + +static int proc_dpages_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, proc_dpages_show, NULL); +} + +static const struct proc_ops proc_dpages_operations = { + .proc_open = proc_dpages_open, + .proc_read = seq_read, + .proc_release = single_release, +}; + +static int proc_limit_show(struct seq_file *m, void *v) +{ + seq_printf(m, "%d\n", READ_ONCE(buff_limit)); + return 0; +} + +static int proc_limit_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, proc_limit_show, NULL); +} + +static ssize_t write_limit_proc( + struct file *filp, + const char *buf, + size_t count, + loff_t *offp) +{ + char *msg; + int ret = 0; + long temp; + + if (count > PAGE_SIZE) { + ret = -EINVAL; + goto error; + } + + msg = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto error; + } + + if (copy_from_user(msg, buf, count)) { + ret = -EINVAL; + goto free; + } + ret = kstrtol(msg, 10, &temp); + if (ret != 0 || temp < 0 || temp > INT_MAX) { + ret = -EINVAL; + goto free; + } + + WRITE_ONCE(buff_limit, temp); + ret = count; + +free: + kfree(msg); +error: + return ret; +} + +static const struct proc_ops proc_limit_operations = { + .proc_open = proc_limit_open, + .proc_read = seq_read, + .proc_write = write_limit_proc, + .proc_lseek = seq_lseek, + .proc_release = single_release, +}; + +static int __init dpages_proc_init(void) +{ + static struct proc_dir_entry *proc_file; + + dirty_dir = proc_mkdir(DIRTY_ROOT, NULL); + if (!dirty_dir) + goto fail_dir; + + proc_file = proc_create(DIRTY_PAGES, 0440, + dirty_dir, &proc_dpages_operations); + if (!proc_file) + goto fail_pages; + + proc_file = proc_create(DIRTY_LIMIT, 0640, + dirty_dir, &proc_limit_operations); + if (!proc_file) + goto fail_limit; + + return 0; + +fail_limit: + remove_proc_entry(DIRTY_PAGES, dirty_dir); +fail_pages: + remove_proc_entry(DIRTY_ROOT, NULL); +fail_dir: + return -ENOMEM; +} + +subsys_initcall(dpages_proc_init); -- 2.39.2

2 1

[PATCH OLK-6.6 0/2] sync pin memory and pid reserve's code from
by Liu Chao 14 Dec '23

14 Dec '23

euleros inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NXQM ------------------------------ Liu Chao (2): mm: add pin memory method for checkpoint add restore pid: add pid reserve method for checkpoint and recover arch/arm64/configs/openeuler_defconfig | 3 + arch/arm64/kernel/setup.c | 2 + arch/arm64/mm/init.c | 6 + drivers/char/Kconfig | 7 + drivers/char/Makefile | 1 + drivers/char/pin_memory.c | 209 +++++ fs/proc/task_mmu.c | 136 +++ include/linux/page-flags.h | 9 + include/linux/pin_mem.h | 117 +++ include/trace/events/mmflags.h | 9 +- kernel/pid.c | 4 + mm/Kconfig | 19 + mm/Makefile | 1 + mm/huge_memory.c | 64 ++ mm/memory.c | 59 ++ mm/pin_mem.c | 1194 ++++++++++++++++++++++++ mm/rmap.c | 3 +- 17 files changed, 1841 insertions(+), 2 deletions(-) create mode 100644 drivers/char/pin_memory.c create mode 100644 include/linux/pin_mem.h create mode 100644 mm/pin_mem.c -- 2.33.0

2 3

[PATCH OLK-6.6] ACPI / APEI: Notify all ras err to driver
by Yuan Can 14 Dec '23

14 Dec '23

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------------------------------------------- Customization deliver all types error to driver. As the driver need to process the errors in process context. Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 1 + drivers/acpi/apei/Kconfig | 7 +++++++ drivers/acpi/apei/ghes.c | 8 +++++++- 3 files changed, 15 insertions(+), 1 deletion(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 3781d138c3e3..5775069d6844 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -653,6 +653,7 @@ CONFIG_ACPI_HMAT=y CONFIG_HAVE_ACPI_APEI=y CONFIG_ACPI_APEI=y CONFIG_ACPI_APEI_GHES=y +CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR=y CONFIG_ACPI_APEI_PCIEAER=y CONFIG_ACPI_APEI_SEA=y CONFIG_ACPI_APEI_MEMORY_FAILURE=y diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index 6b18f8bc7be3..1dce3ad7c9bd 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -33,6 +33,13 @@ config ACPI_APEI_GHES by firmware to produce more valuable hardware error information for Linux. +config ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR + bool "Notify all ras err to driver" + depends on ARM64 && ACPI_APEI_GHES + default n + help + Deliver all types of error to driver. + config ACPI_APEI_PCIEAER bool "APEI PCIe AER logging/recovering support" depends on ACPI_APEI && PCIEAER diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 63ad0541db38..bf1b9252a8da 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -692,12 +692,18 @@ static bool ghes_do_proc(struct ghes *ghes, queued = ghes_handle_arm_hw_error(gdata, sev); } else { void *err = acpi_hest_get_payload(gdata); - +#ifndef CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR ghes_defer_non_standard_event(gdata, sev); +#endif log_non_standard_event(sec_type, fru_id, fru_text, sec_sev, err, gdata->error_data_length); } + +#ifdef CONFIG_ACPI_APEI_GHES_NOTIFY_ALL_RAS_ERR + /* Customization deliver all types error to driver. */ + ghes_defer_non_standard_event(gdata, sev); +#endif } return queued; -- 2.17.1

2 1

[PATCH OLK-6.6 v2 0/4] xfs: fix some growfs problems
by Long Li 14 Dec '23

14 Dec '23

This patch set fix some growfs problems: Long Li (1): xfs: fix dir3 block read verify fail during log recover Wu Guanghao (1): xfs: fix the problem of mount failure caused by not refreshing mp->m_sb yangerkun (2): xfs: fix mounting failed caused by sequencing problem in the log records xfs: keep growfs sb log item active until ail flush success fs/xfs/libxfs/xfs_log_recover.h | 1 + fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_buf_item.h | 8 +++++++- fs/xfs/xfs_buf_item_recover.c | 36 +++++++++++++++++++++++++++------ fs/xfs/xfs_log_recover.c | 26 +++++++++++++++++++++--- fs/xfs/xfs_trans.c | 8 ++++++++ 6 files changed, 70 insertions(+), 11 deletions(-) -- 2.31.1

2 5

[PATCH OLK-6.6 0/4] xfs: fix some growfs problems
by Long Li 14 Dec '23

14 Dec '23

This patch set fix some growfs problems: Long Li (1): xfs: fix dir3 block read verify fail during log recover Wu Guanghao (1): xfs: fix the problem of mount failure caused by not refreshing mp->m_sb yangerkun (2): xfs: fix mounting failed caused by sequencing problem in the log records xfs: keep growfs sb log item active until ail flush success fs/xfs/libxfs/xfs_log_recover.h | 1 + fs/xfs/xfs_buf_item.c | 2 +- fs/xfs/xfs_buf_item.h | 8 +++++++- fs/xfs/xfs_buf_item_recover.c | 36 +++++++++++++++++++++++++++------ fs/xfs/xfs_log_recover.c | 26 +++++++++++++++++++++--- fs/xfs/xfs_trans.c | 8 ++++++++ 6 files changed, 70 insertions(+), 11 deletions(-) -- 2.31.1

2 5

[PATCH OLK-6.6 0/2] Ascend feature
by Yuan Can 14 Dec '23

14 Dec '23

Ascend init all gicr feature. Xu Qiang (2): irq-gic-v3: Add support to init ts core GICR irq-gic-v3-its: It can't be initialized when the GICR had been cut drivers/irqchip/Kconfig | 7 + drivers/irqchip/irq-gic-v3-its.c | 254 ++++++++++++++++++++++++++++- drivers/irqchip/irq-gic-v3.c | 101 +++++++++++- include/linux/irqchip/arm-gic-v3.h | 5 + 4 files changed, 359 insertions(+), 8 deletions(-) -- 2.17.1

2 3

[PATCH OLK-6.6 1/2] irq-gic-v3: Add support to init ts core GICR
by Yuan Can 14 Dec '23

14 Dec '23

From: Xu Qiang <xuqiang36(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------ For Ascend platform, other NON-OS managed GICRs need be initialized in OS. Signed-off-by: Xu Qiang <xuqiang36(a)huawei.com> --- drivers/irqchip/Kconfig | 7 + drivers/irqchip/irq-gic-v3-its.c | 227 ++++++++++++++++++++++++++++- drivers/irqchip/irq-gic-v3.c | 101 ++++++++++++- include/linux/irqchip/arm-gic-v3.h | 5 + 4 files changed, 332 insertions(+), 8 deletions(-) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index f7149d0f3d45..3ba9ed9e1be1 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -159,6 +159,13 @@ config HISILICON_IRQ_MBIGEN select ARM_GIC_V3 select ARM_GIC_V3_ITS +config ASCEND_INIT_ALL_GICR + bool "Enable init all GICR for Ascend" + depends on ASCEND_FEATURES + depends on ARM_GIC_V3 + depends on ARM_GIC_V3_ITS + default n + config IMGPDC_IRQ bool select GENERIC_IRQ_CHIP diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index a8c89df1a997..b7c5bbd209f3 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -193,6 +193,14 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock); static DEFINE_IDA(its_vpeid_ida); +#ifdef CONFIG_ASCEND_INIT_ALL_GICR +static bool init_all_gicr; +static int nr_gicr; +#else +#define init_all_gicr false +#define nr_gicr 0 +#endif + #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) #define gic_data_rdist_cpu(cpu) (per_cpu_ptr(gic_rdists->rdist, cpu)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) @@ -1558,6 +1566,11 @@ static __maybe_unused u32 its_read_lpi_count(struct irq_data *d, int cpu) static void its_inc_lpi_count(struct irq_data *d, int cpu) { +#ifdef CONFIG_ASCEND_INIT_ALL_GICR + if (cpu >= nr_cpu_ids) + return; +#endif + if (irqd_affinity_is_managed(d)) atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed); else @@ -1566,6 +1579,11 @@ static void its_inc_lpi_count(struct irq_data *d, int cpu) static void its_dec_lpi_count(struct irq_data *d, int cpu) { +#ifdef CONFIG_ASCEND_INIT_ALL_GICR + if (cpu >= nr_cpu_ids) + return; +#endif + if (irqd_affinity_is_managed(d)) atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed); else @@ -1665,6 +1683,26 @@ static int its_select_cpu(struct irq_data *d, return cpu; } +#ifdef CONFIG_ASCEND_INIT_ALL_GICR +static int its_select_cpu_other(const struct cpumask *mask_val) +{ + int cpu; + + if (!init_all_gicr) + return -EINVAL; + + cpu = find_first_bit(cpumask_bits(mask_val), NR_CPUS); + if (cpu >= nr_gicr) + cpu = -EINVAL; + return cpu; +} +#else +static int its_select_cpu_other(const struct cpumask *mask_val) +{ + return -EINVAL; +} +#endif + static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -1686,6 +1724,9 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, cpu = cpumask_pick_least_loaded(d, mask_val); if (cpu < 0 || cpu >= nr_cpu_ids) + cpu = its_select_cpu_other(mask_val); + + if (cpu < 0) goto err; /* don't set the affinity when the target cpu is same as current one */ @@ -2951,8 +2992,12 @@ static int allocate_vpe_l1_table(void) static int its_alloc_collections(struct its_node *its) { int i; + int cpu_nr = nr_cpu_ids; + + if (init_all_gicr) + cpu_nr = CONFIG_NR_CPUS; - its->collections = kcalloc(nr_cpu_ids, sizeof(*its->collections), + its->collections = kcalloc(cpu_nr, sizeof(*its->collections), GFP_KERNEL); if (!its->collections) return -ENOMEM; @@ -3263,6 +3308,186 @@ static void its_cpu_init_collections(void) raw_spin_unlock(&its_lock); } +#ifdef CONFIG_ASCEND_INIT_ALL_GICR +void its_set_gicr_nr(int nr) +{ + nr_gicr = nr; +} + +static int __init its_enable_init_all_gicr(char *str) +{ + init_all_gicr = true; + return 1; +} + +__setup("init_all_gicr", its_enable_init_all_gicr); + +bool its_init_all_gicr(void) +{ + return init_all_gicr; +} + +static void its_cpu_init_lpis_others(void __iomem *rbase, int cpu) +{ + struct page *pend_page; + phys_addr_t paddr; + u64 val, tmp; + + if (!init_all_gicr) + return; + + val = readl_relaxed(rbase + GICR_CTLR); + if ((gic_rdists->flags & RDIST_FLAGS_RD_TABLES_PREALLOCATED) && + (val & GICR_CTLR_ENABLE_LPIS)) { + /* + * Check that we get the same property table on all + * RDs. If we don't, this is hopeless. + */ + paddr = gicr_read_propbaser(rbase + GICR_PROPBASER); + paddr &= GENMASK_ULL(51, 12); + if (WARN_ON(gic_rdists->prop_table_pa != paddr)) + add_taint(TAINT_CRAP, LOCKDEP_STILL_OK); + + paddr = gicr_read_pendbaser(rbase + GICR_PENDBASER); + paddr &= GENMASK_ULL(51, 16); + + WARN_ON(!gic_check_reserved_range(paddr, LPI_PENDBASE_SZ)); + + goto out; + } + + /* If we didn't allocate the pending table yet, do it now */ + pend_page = its_allocate_pending_table(GFP_NOWAIT); + if (!pend_page) { + pr_err("Failed to allocate PENDBASE for GICR:%p\n", rbase); + return; + } + + paddr = page_to_phys(pend_page); + pr_info("GICR:%p using LPI pending table @%pa\n", + rbase, &paddr); + + WARN_ON(gic_reserve_range(paddr, LPI_PENDBASE_SZ)); + + /* Disable LPIs */ + val = readl_relaxed(rbase + GICR_CTLR); + val &= ~GICR_CTLR_ENABLE_LPIS; + writel_relaxed(val, rbase + GICR_CTLR); + + /* + * Make sure any change to the table is observable by the GIC. + */ + dsb(sy); + + /* set PROPBASE */ + val = (gic_rdists->prop_table_pa | + GICR_PROPBASER_InnerShareable | + GICR_PROPBASER_RaWaWb | + ((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK)); + + gicr_write_propbaser(val, rbase + GICR_PROPBASER); + tmp = gicr_read_propbaser(rbase + GICR_PROPBASER); + + if ((tmp ^ val) & GICR_PROPBASER_SHAREABILITY_MASK) { + if (!(tmp & GICR_PROPBASER_SHAREABILITY_MASK)) { + /* + * The HW reports non-shareable, we must + * remove the cacheability attributes as + * well. + */ + val &= ~(GICR_PROPBASER_SHAREABILITY_MASK | + GICR_PROPBASER_CACHEABILITY_MASK); + val |= GICR_PROPBASER_nC; + gicr_write_propbaser(val, rbase + GICR_PROPBASER); + } + pr_info_once("GIC: using cache flushing for LPI property table\n"); + gic_rdists->flags |= RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING; + } + + /* set PENDBASE */ + val = (page_to_phys(pend_page) | + GICR_PENDBASER_InnerShareable | + GICR_PENDBASER_RaWaWb); + + gicr_write_pendbaser(val, rbase + GICR_PENDBASER); + tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER); + + if (!(tmp & GICR_PENDBASER_SHAREABILITY_MASK)) { + /* + * The HW reports non-shareable, we must remove the + * cacheability attributes as well. + */ + val &= ~(GICR_PENDBASER_SHAREABILITY_MASK | + GICR_PENDBASER_CACHEABILITY_MASK); + val |= GICR_PENDBASER_nC; + gicr_write_pendbaser(val, rbase + GICR_PENDBASER); + } + + /* Enable LPIs */ + val = readl_relaxed(rbase + GICR_CTLR); + val |= GICR_CTLR_ENABLE_LPIS; + writel_relaxed(val, rbase + GICR_CTLR); + + /* Make sure the GIC has seen the above */ + dsb(sy); +out: + pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", + cpu, pend_page ? "allocated" : "reserved", &paddr); +} + +static void its_cpu_init_collection_others(void __iomem *rbase, + phys_addr_t phys_base, int cpu) +{ + struct its_node *its; + + if (!init_all_gicr) + return; + + raw_spin_lock(&its_lock); + + list_for_each_entry(its, &its_nodes, entry) { + u64 target; + + /* + * We now have to bind each collection to its target + * redistributor. + */ + if (gic_read_typer(its->base + GITS_TYPER) & GITS_TYPER_PTA) { + /* + * This ITS wants the physical address of the + * redistributor. + */ + target = phys_base; + } else { + /* + * This ITS wants a linear CPU number. + */ + target = gic_read_typer(rbase + GICR_TYPER); + target = GICR_TYPER_CPU_NUMBER(target) << 16; + } + + /* Perform collection mapping */ + its->collections[cpu].target_address = target; + its->collections[cpu].col_id = cpu; + + its_send_mapc(its, &its->collections[cpu], 1); + its_send_invall(its, &its->collections[cpu]); + } + + raw_spin_unlock(&its_lock); +} + +int its_cpu_init_others(void __iomem *base, phys_addr_t phys_base, int cpu) +{ + if (!list_empty(&its_nodes)) { + its_cpu_init_lpis_others(base, cpu); + its_cpu_init_collection_others(base, phys_base, cpu); + } + + return 0; +} +#endif + static struct its_device *its_find_device(struct its_node *its, u32 dev_id) { struct its_device *its_dev = NULL, *tmp; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index f59ac9586b7b..59d5c736be81 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -281,17 +281,11 @@ static u64 __maybe_unused gic_read_iar(void) } #endif -static void gic_enable_redist(bool enable) +static void __gic_enable_redist(void __iomem *rbase, bool enable) { - void __iomem *rbase; u32 count = 1000000; /* 1s! */ u32 val; - if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) - return; - - rbase = gic_data_rdist_rd_base(); - val = readl_relaxed(rbase + GICR_WAKER); if (enable) /* Wake up this CPU redistributor */ @@ -318,6 +312,14 @@ static void gic_enable_redist(bool enable) enable ? "wakeup" : "sleep"); } +static void gic_enable_redist(bool enable) +{ + if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) + return; + + __gic_enable_redist(gic_data_rdist_rd_base(), enable); +} + /* * Routines to disable, enable, EOI and route interrupts */ @@ -1288,6 +1290,89 @@ static void gic_cpu_init(void) gic_cpu_sys_reg_init(); } +#ifdef CONFIG_ASCEND_INIT_ALL_GICR +static int __gic_compute_nr_gicr(struct redist_region *region, void __iomem *ptr) +{ + static int gicr_nr; + + its_set_gicr_nr(++gicr_nr); + + return 1; +} + +static void gic_compute_nr_gicr(void) +{ + gic_iterate_rdists(__gic_compute_nr_gicr); +} + +static int gic_rdist_cpu(void __iomem *ptr, unsigned int cpu) +{ + unsigned long mpidr = cpu_logical_map(cpu); + u64 typer; + u32 aff; + + /* + * Convert affinity to a 32bit value that can be matched to + * GICR_TYPER bits [63:32]. + */ + aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 | + MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | + MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | + MPIDR_AFFINITY_LEVEL(mpidr, 0)); + + typer = gic_read_typer(ptr + GICR_TYPER); + if ((typer >> 32) == aff) + return 0; + + return 1; +} + +static int gic_rdist_cpus(void __iomem *ptr) +{ + unsigned int i; + + for (i = 0; i < nr_cpu_ids; i++) { + if (gic_rdist_cpu(ptr, i) == 0) + return 0; + } + + return 1; +} + +static int gic_cpu_init_other(struct redist_region *region, void __iomem *ptr) +{ + u64 offset; + phys_addr_t phys_base; + static int cpu; + + if (cpu == 0) + cpu = nr_cpu_ids; + + if (gic_rdist_cpus(ptr) == 1) { + offset = ptr - region->redist_base; + phys_base = region->phys_base + offset; + __gic_enable_redist(ptr, true); + if (gic_dist_supports_lpis()) + its_cpu_init_others(ptr, phys_base, cpu); + cpu++; + } + + return 1; +} + +static void gic_cpu_init_others(void) +{ + if (!its_init_all_gicr()) + return; + + gic_iterate_rdists(gic_cpu_init_other); +} +#else +static inline void gic_compute_nr_gicr(void) {} + +static inline void gic_cpu_init_others(void) {} +#endif + #ifdef CONFIG_SMP #define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) @@ -2052,6 +2137,7 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base, gic_data.rdists.has_direct_lpi = true; gic_data.rdists.has_vpend_valid_dirty = true; } + gic_compute_nr_gicr(); if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; @@ -2087,6 +2173,7 @@ static int __init gic_init_bases(phys_addr_t dist_phys_base, } gic_enable_nmi_support(); + gic_cpu_init_others(); return 0; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 728691365464..33e098c70952 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -637,6 +637,11 @@ struct irq_domain; struct fwnode_handle; int __init its_lpi_memreserve_init(void); int its_cpu_init(void); +#ifdef CONFIG_ASCEND_INIT_ALL_GICR +void its_set_gicr_nr(int nr); +bool its_init_all_gicr(void); +int its_cpu_init_others(void __iomem *base, phys_addr_t phys_base, int idx); +#endif int its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *domain); int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent); -- 2.17.1

2 3

[PATCH OLK-6.6] arm64/ascend: Add new enable_oom_killer interface for oom contrl
by Yuan Can 14 Dec '23

14 Dec '23

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------------------------------------------- Support disable oom-killer, and report oom events to bbox vm.enable_oom_killer: 0: disable oom killer 1: enable oom killer (default,compatible with mainline) Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> --- include/linux/oom.h | 24 +++++++++++++++++++ mm/Kconfig | 10 ++++++++ mm/memcontrol.c | 20 ++++++++++++++++ mm/oom_kill.c | 57 +++++++++++++++++++++++++++++++++++++++++++++ mm/util.c | 2 ++ 5 files changed, 113 insertions(+) diff --git a/include/linux/oom.h b/include/linux/oom.h index 7d0c9c48a0c5..b9210e272651 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -112,4 +112,28 @@ extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); +#define OOM_TYPE_NOMEM 0 +#define OOM_TYPE_OVERCOMMIT 1 +#define OOM_TYPE_CGROUP 2 + +#ifdef CONFIG_ASCEND_OOM +int register_hisi_oom_notifier(struct notifier_block *nb); +int unregister_hisi_oom_notifier(struct notifier_block *nb); +int oom_type_notifier_call(unsigned int type, struct oom_control *oc); +#else +static inline int register_hisi_oom_notifier(struct notifier_block *nb) +{ + return -EINVAL; +} + +static inline int unregister_hisi_oom_notifier(struct notifier_block *nb) +{ + return -EINVAL; +} + +static inline int oom_type_notifier_call(unsigned int type, struct oom_control *oc) +{ + return -EINVAL; +} +#endif #endif /* _INCLUDE_LINUX_OOM_H */ diff --git a/mm/Kconfig b/mm/Kconfig index 0f68e5bbeb89..48f4aeeaeff9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1302,6 +1302,16 @@ config SHARE_POOL in kernel and user level, which is only enabled for ascend platform. To enable this feature, enable_ascend_share_pool bootarg is needed. +config ASCEND_OOM + bool "Enable support for disable oom killer" + default n + help + In some cases we hopes that the oom will not kill the process when it occurs, + be able to notify the black box to report the event, and be able to trigger + the panic to locate the problem. + vm.enable_oom_killer: + 0: disable oom killer + 1: enable oom killer (default,compatible with mainline) source "mm/damon/Kconfig" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8a881ab21f6c..fec6f37e61da 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1955,6 +1955,7 @@ static bool mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) current->memcg_in_oom = memcg; current->memcg_oom_gfp_mask = mask; current->memcg_oom_order = order; + oom_type_notifier_call(OOM_TYPE_CGROUP, NULL); } return false; } @@ -2019,6 +2020,8 @@ bool mem_cgroup_oom_synchronize(bool handle) if (locked) mem_cgroup_oom_notify(memcg); + oom_type_notifier_call(OOM_TYPE_CGROUP, NULL); + schedule(); mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); @@ -3140,6 +3143,20 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) return ret; } +#ifdef CONFIG_ASCEND_OOM +void hisi_oom_recover(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + memcg = get_mem_cgroup_from_objcg(objcg); + if (!mem_cgroup_is_root(memcg)) + memcg_oom_recover(memcg); + css_put(&memcg->css); +} +#else +static inline void hisi_oom_recover(struct obj_cgroup *objcg) { } +#endif + /** * __memcg_kmem_uncharge_page: uncharge a kmem page * @page: page to uncharge @@ -3156,6 +3173,9 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) objcg = __folio_objcg(folio); obj_cgroup_uncharge_pages(objcg, nr_pages); + + hisi_oom_recover(objcg); + folio->memcg_data = 0; obj_cgroup_put(objcg); } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 44bde56ecd02..607056d49595 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -55,6 +55,7 @@ static int sysctl_panic_on_oom; static int sysctl_oom_kill_allocating_task; static int sysctl_oom_dump_tasks = 1; +static int sysctl_enable_oom_killer = 1; /* * Serializes oom killer invocations (out_of_memory()) from all contexts to @@ -724,6 +725,17 @@ static struct ctl_table vm_oom_kill_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_ASCEND_OOM + { + .procname = "enable_oom_killer", + .data = &sysctl_enable_oom_killer, + .maxlen = sizeof(sysctl_enable_oom_killer), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif {} }; #endif @@ -1073,6 +1085,7 @@ static void check_panic_on_oom(struct oom_control *oc) if (is_sysrq_oom(oc)) return; dump_header(oc, NULL); + oom_type_notifier_call(0, oc); panic("Out of memory: %s panic_on_oom is enabled\n", sysctl_panic_on_oom == 2 ? "compulsory" : "system-wide"); } @@ -1091,6 +1104,45 @@ int unregister_oom_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_oom_notifier); +#ifdef CONFIG_ASCEND_OOM +static BLOCKING_NOTIFIER_HEAD(oom_type_notify_list); + +int register_hisi_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&oom_type_notify_list, nb); +} +EXPORT_SYMBOL_GPL(register_hisi_oom_notifier); + +int unregister_hisi_oom_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&oom_type_notify_list, nb); +} +EXPORT_SYMBOL_GPL(unregister_hisi_oom_notifier); + +int oom_type_notifier_call(unsigned int type, struct oom_control *oc) +{ + struct oom_control oc_tmp = { 0 }; + static unsigned long caller_jiffies; + + if (sysctl_enable_oom_killer) + return -EINVAL; + + if (oc) + type = is_memcg_oom(oc) ? OOM_TYPE_CGROUP : OOM_TYPE_NOMEM; + else + oc = &oc_tmp; + + if (printk_timed_ratelimit(&caller_jiffies, 10000)) { + pr_err("OOM_NOTIFIER: oom type %u\n", type); + dump_stack(); + show_mem(); + dump_tasks(oc); + } + + return blocking_notifier_call_chain(&oom_type_notify_list, type, NULL); +} +#endif + /** * out_of_memory - kill the "best" process when we run out of memory * @oc: pointer to struct oom_control @@ -1107,6 +1159,11 @@ bool out_of_memory(struct oom_control *oc) if (oom_killer_disabled) return false; + if (!sysctl_enable_oom_killer) { + oom_type_notifier_call(0, oc); + return false; + } + if (!is_memcg_oom(oc)) { blocking_notifier_call_chain(&oom_notify_list, 0, &freed); if (freed > 0 && !is_sysrq_oom(oc)) diff --git a/mm/util.c b/mm/util.c index 90250cbc82fe..e41ac8a58eb5 100644 --- a/mm/util.c +++ b/mm/util.c @@ -26,6 +26,7 @@ #include <linux/share_pool.h> #include <linux/uaccess.h> +#include <linux/oom.h> #include "internal.h" #include "swap.h" @@ -981,6 +982,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) error: pr_warn_ratelimited("%s: pid: %d, comm: %s, not enough memory for the allocation\n", __func__, current->pid, current->comm); + oom_type_notifier_call(OOM_TYPE_OVERCOMMIT, NULL); vm_unacct_memory(pages); return -ENOMEM; -- 2.17.1

2 1

[PATCH OLK-6.6] nbd_genl_status: null check for nla_nest_start
by Yuan Can 14 Dec '23

14 Dec '23

From: Navid Emamdoost <navid.emamdoost(a)gmail.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: CVE-2019-16089 Reference: https://lore.kernel.org/lkml/20190911164013.27364-1-navid.emamdoost@gmail.c… --------------------------- nla_nest_start may fail and return NULL. The check is inserted, and errno is selected based on other call sites within the same source code. Update: removed extra new line. v3 Update: added release reply, thanks to Michal Kubecek for pointing out. Signed-off-by: Navid Emamdoost <navid.emamdoost(a)gmail.com> Reviewed-by: Michal Kubecek <mkubecek(a)suse.cz> --- drivers/block/nbd.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 855fdf5c3b4e..b99c169890d5 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2408,6 +2408,12 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } dev_list = nla_nest_start_noflag(reply, NBD_ATTR_DEVICE_LIST); + if (!dev_list) { + nlmsg_free(reply); + ret = -EMSGSIZE; + goto out; + } + if (index == -1) { ret = idr_for_each(&nbd_index_idr, &status_cb, reply); if (ret) { -- 2.17.1

2 1

[PATCH OLK-5.10] mm/userswap: modify the USWAP registration flag
by Peng Zhang 14 Dec '23

14 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KESX CVE: NA -------------------------------- Modify the USWAP registration flag UFFDIO_REGISTER_MODE_USWAP to reserve more modes. Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- include/uapi/linux/userfaultfd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index b8689050455d..a8a8a58ac029 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -196,7 +196,7 @@ struct uffdio_register { struct uffdio_range range; #define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) #define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) -#define UFFDIO_REGISTER_MODE_USWAP ((__u64)1<<2) +#define UFFDIO_REGISTER_MODE_USWAP ((__u64)1<<10) __u64 mode; /* -- 2.25.1

2 1

[PATCH OLK-6.6] mm: export symbol find_get_task_by_vpid
by Yuan Can 14 Dec '23

14 Dec '23

ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA --------------------------------------------- Export the find_get_task_by_vpid symbol used by Ascend drivers. Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- kernel/pid.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/pid.c b/kernel/pid.c index 6500ef956f2f..383abde0c208 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -437,6 +437,7 @@ struct task_struct *find_get_task_by_vpid(pid_t nr) return task; } +EXPORT_SYMBOL_GPL(find_get_task_by_vpid); struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { -- 2.17.1

2 1

[PATCH OLK-6.6] cache: Workaround HiSilicon Taishan DC CVAU
by Yuan Can 14 Dec '23

14 Dec '23

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------------------------------- Taishan's L1/L2 cache is inclusive, and the data is consistent. Any change of L1 does not require DC operation to brush CL in L1 to L2. It's safe that don't clean data cache by address to point of unification. Without IDC featrue, kernel needs to flush icache as well as dcache, causes performance degradation. The flaw refers to V110/V200 variant 1. Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> --- Documentation/arch/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 9 ++++++ arch/arm64/include/asm/cache.h | 9 ++++++ arch/arm64/include/asm/cputype.h | 2 ++ arch/arm64/kernel/cpu_errata.c | 33 +++++++++++++++++++++ arch/arm64/tools/cpucaps | 1 + 6 files changed, 56 insertions(+) diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index bb62e0dbd546..2beb890aefda 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -205,6 +205,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | LINXICORE9100 | #162100125 | HISILICON_ERRATUM_162100125 | +----------------+-----------------+-----------------+-----------------------------+ +| Hisilicon | TSV{110,200} | #1980005 | HISILICON_ERRATUM_1980005 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 73333648a98c..cd7e351287df 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1170,6 +1170,15 @@ config HISILICON_ERRATUM_162100125 If unsure, say Y. +config HISILICON_ERRATUM_1980005 + bool "Hisilicon erratum IDC support" + default n + help + The HiSilicon TSV100/200 SoC support idc but report wrong value to + kernel. + + If unsure, say N. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index ceb368d33bf4..e0a60e4c8b42 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -112,6 +112,15 @@ int cache_line_size(void); static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void) { u32 ctr = read_cpuid_cachetype(); +#ifdef CONFIG_HISILICON_ERRATUM_1980005 + static const struct midr_range idc_support_list[] = { + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_REV(MIDR_HISI_TSV200, 1, 0), + { /* sentinel */ } + }; + if (is_midr_in_range_list(read_cpuid_id(), idc_support_list)) + ctr |= BIT(CTR_EL0_IDC_SHIFT); +#endif if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) { u64 clidr = read_sysreg(clidr_el1); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 202588ad92e8..c1d6b1a1ac75 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -119,6 +119,7 @@ #define FUJITSU_CPU_PART_A64FX 0x001 #define HISI_CPU_PART_TSV110 0xD01 +#define HISI_CPU_PART_TSV200 0xD02 #define HISI_CPU_PART_LINXICORE9100 0xD02 #define APPLE_CPU_PART_M1_ICESTORM 0x022 @@ -181,6 +182,7 @@ #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX) #define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110) +#define MIDR_HISI_TSV200 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV200) #define MIDR_HISI_LINXICORE9100 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_LINXICORE9100) #define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM) #define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e40b76ac4711..ba786e7ee76e 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -60,6 +60,30 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope) return model == entry->midr_range.model; } +#ifdef CONFIG_HISILICON_ERRATUM_1980005 +static bool +hisilicon_1980005_match(const struct arm64_cpu_capabilities *entry, + int scope) +{ + static const struct midr_range idc_support_list[] = { + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_REV(MIDR_HISI_TSV200, 1, 0), + { /* sentinel */ } + }; + + return is_midr_in_range_list(read_cpuid_id(), idc_support_list); +} + +static void +hisilicon_1980005_enable(const struct arm64_cpu_capabilities *__unused) +{ + __set_bit(ARM64_HAS_CACHE_IDC, system_cpucaps); + arm64_ftr_reg_ctrel0.sys_val |= BIT(CTR_EL0_IDC_SHIFT); + arm64_ftr_reg_ctrel0.strict_mask &= ~BIT(CTR_EL0_IDC_SHIFT); + sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0); +} +#endif + static bool has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry, int scope) @@ -567,6 +591,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100125_cpus), }, #endif +#ifdef CONFIG_HISILICON_ERRATUM_1980005 + { + .desc = "Taishan IDC coherence workaround", + .capability = ARM64_WORKAROUND_HISILICON_1980005, + .matches = hisilicon_1980005_match, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .cpu_enable = hisilicon_1980005_enable, + }, +#endif #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index cb4996edc09f..0b62edb91876 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -102,3 +102,4 @@ WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT WORKAROUND_HISILICON_ERRATUM_162100125 WORKAROUND_HISI_HIP08_RU_PREFETCH +WORKAROUND_HISILICON_1980005 -- 2.17.1

2 1

[PATCH OLK-6.6] iommu/arm-smmu-v3: Add suspend and resume support
by Yuan Can 14 Dec '23

14 Dec '23

ascend inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8NC0E CVE: NA ------------------------------------------------------- Add suspend and resume support for smmuv3. The smmu is stopped when suspending and started when resuming. Signed-off-by: Yuan Can <yuancan(a)huawei.com> --- drivers/iommu/Kconfig | 7 ++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 97 ++++++++++++++++++--- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 2 + 3 files changed, 96 insertions(+), 10 deletions(-) diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 2b12b583ef4b..2ecee01222d4 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -412,6 +412,13 @@ config ARM_SMMU_V3_SVA Say Y here if your system supports SVA extensions such as PCIe PASID and PRI. +config ARM_SMMU_V3_PM + bool "Add arm_smmu_v3 suspend and resume support" + depends on ARM_SMMU_V3 && PM_SLEEP + default n + help + Add support for suspend and resume support for arm smmu v3. + config S390_IOMMU def_bool y if S390 && PCI depends on S390 && PCI diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index bd0a596f9863..4d417b4243eb 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3154,6 +3154,13 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; doorbell &= MSI_CFG0_ADDR_MASK; +#ifdef CONFIG_ARM_SMMU_V3_PM + /* Saves the msg (base addr of msi irq) and restores it during resume */ + desc->msg.address_lo = msg->address_lo; + desc->msg.address_hi = msg->address_hi; + desc->msg.data = msg->data; +#endif + writeq_relaxed(doorbell, smmu->base + cfg[0]); writel_relaxed(msg->data, smmu->base + cfg[1]); writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); @@ -3196,11 +3203,51 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) devm_add_action(dev, arm_smmu_free_msis, dev); } -static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) +#ifdef CONFIG_ARM_SMMU_V3_PM +static void arm_smmu_resume_msis(struct arm_smmu_device *smmu) +{ + struct msi_desc *desc; + struct device *dev = smmu->dev; + + msi_for_each_desc(desc, dev, MSI_DESC_ALL) { + switch (desc->msi_index) { + case EVTQ_MSI_INDEX: + case GERROR_MSI_INDEX: + case PRIQ_MSI_INDEX: { + phys_addr_t *cfg = arm_smmu_msi_cfg[desc->msi_index]; + struct msi_msg *msg = &desc->msg; + phys_addr_t doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; + + doorbell &= MSI_CFG0_ADDR_MASK; + writeq_relaxed(doorbell, smmu->base + cfg[0]); + writel_relaxed(msg->data, smmu->base + cfg[1]); + writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, + smmu->base + cfg[2]); + break; + } + default: + continue; + + } + } +} +#else +static void arm_smmu_resume_msis(struct arm_smmu_device *smmu) +{ +} +#endif + +static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu, bool resume) { int irq, ret; - arm_smmu_setup_msis(smmu); + if (!resume) + arm_smmu_setup_msis(smmu); + else { + /* The irq doesn't need to be re-requested during resume */ + arm_smmu_resume_msis(smmu); + return; + } /* Request interrupt lines */ irq = smmu->evtq.q.irq; @@ -3242,7 +3289,7 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) } } -static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu) +static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu, bool resume) { int ret, irq; u32 irqen_flags = IRQ_CTRL_EVTQ_IRQEN | IRQ_CTRL_GERROR_IRQEN; @@ -3269,7 +3316,7 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu) if (ret < 0) dev_warn(smmu->dev, "failed to enable combined irq\n"); } else - arm_smmu_setup_unique_irqs(smmu); + arm_smmu_setup_unique_irqs(smmu, resume); if (smmu->features & ARM_SMMU_FEAT_PRI) irqen_flags |= IRQ_CTRL_PRIQ_IRQEN; @@ -3294,7 +3341,7 @@ static int arm_smmu_device_disable(struct arm_smmu_device *smmu) return ret; } -static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) +static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool resume) { int ret; u32 reg, enables; @@ -3402,7 +3449,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) } } - ret = arm_smmu_setup_irqs(smmu); + ret = arm_smmu_setup_irqs(smmu, resume); if (ret) { dev_err(smmu->dev, "failed to setup irqs\n"); return ret; @@ -3412,7 +3459,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) enables &= ~(CR0_EVTQEN | CR0_PRIQEN); /* Enable the SMMU interface, or ensure bypass */ - if (!bypass || disable_bypass) { + if (!smmu->bypass || disable_bypass) { enables |= CR0_SMMUEN; } else { ret = arm_smmu_update_gbpa(smmu, 0, GBPA_ABORT); @@ -3767,6 +3814,26 @@ static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start, return devm_ioremap_resource(dev, &res); } +#ifdef CONFIG_ARM_SMMU_V3_PM +static int arm_smmu_suspend(struct device *dev) +{ + /* + * The smmu is powered off and related registers are automatically + * cleared when suspend. No need to do anything. + */ + return 0; +} + +static int arm_smmu_resume(struct device *dev) +{ + struct arm_smmu_device *smmu = dev_get_drvdata(dev); + + arm_smmu_device_reset(smmu, true); + + return 0; +} +#endif + static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu) { struct list_head rmr_list; @@ -3804,7 +3871,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev) resource_size_t ioaddr; struct arm_smmu_device *smmu; struct device *dev = &pdev->dev; - bool bypass; smmu = devm_kzalloc(dev, sizeof(*smmu), GFP_KERNEL); if (!smmu) @@ -3820,7 +3886,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) } /* Set bypass mode according to firmware probing result */ - bypass = !!ret; + smmu->bypass = !!ret; /* Base address */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -3884,7 +3950,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev) arm_smmu_rmr_install_bypass_ste(smmu); /* Reset the device */ - ret = arm_smmu_device_reset(smmu, bypass); + ret = arm_smmu_device_reset(smmu, false); if (ret) return ret; @@ -3928,6 +3994,16 @@ static const struct of_device_id arm_smmu_of_match[] = { }; MODULE_DEVICE_TABLE(of, arm_smmu_of_match); +#ifdef CONFIG_ARM_SMMU_V3_PM +static const struct dev_pm_ops arm_smmu_pm_ops = { + .suspend = arm_smmu_suspend, + .resume = arm_smmu_resume, +}; +#define ARM_SMMU_PM_OPS (&arm_smmu_pm_ops) +#else +#define ARM_SMMU_PM_OPS NULL +#endif + static void arm_smmu_driver_unregister(struct platform_driver *drv) { arm_smmu_sva_notifier_synchronize(); @@ -3939,6 +4015,7 @@ static struct platform_driver arm_smmu_driver = { .name = "arm-smmu-v3", .of_match_table = arm_smmu_of_match, .suppress_bind_attrs = true, + .pm = ARM_SMMU_PM_OPS, }, .probe = arm_smmu_device_probe, .remove_new = arm_smmu_device_remove, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 9915850dd4db..269b6fa705d4 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -682,6 +682,8 @@ struct arm_smmu_device { struct rb_root streams; struct mutex streams_mutex; + + bool bypass; }; struct arm_smmu_stream { -- 2.17.1

2 1

[PATCH OLK-6.6 v6 0/7] memcg reclaim and cgroup kill
by Lu Jialin 14 Dec '23

14 Dec '23

Lu Jialin (7): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low/high} from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland memcg: introduce per-memcg reclaim interface config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 8 +- init/Kconfig | 10 ++ kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 189 ++++++++++++++++++++++++- 8 files changed, 219 insertions(+), 6 deletions(-) -- 2.34.1

2 8

[PATCH v7 OLK-6.6 0/5] Support Qos Scheduler
by Wenyu Huang 14 Dec '23

14 Dec '23

Zhang Qiao (5): sched: Introduce qos scheduler for co-location sched: Throttle qos cfs_rq when current cpu is running online task sched: Support kill boost for offline task sched: Introduce handle priority reversion mechanism sched: Enable qos scheduler config arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/cgroup.h | 4 + include/linux/resume_user_mode.h | 5 + include/linux/sched.h | 11 + init/Kconfig | 12 + kernel/cgroup/cgroup.c | 20 ++ kernel/sched/core.c | 155 ++++++++++ kernel/sched/fair.c | 378 ++++++++++++++++++++++++- kernel/sched/sched.h | 12 + kernel/signal.c | 3 + 11 files changed, 601 insertions(+), 1 deletion(-) -- 2.34.1

2 6

[PATCH OLK-6.6 v5 0/7] memcg reclaim and cgroup kill
by Lu Jialin 13 Dec '23

13 Dec '23

Lu Jialin (7): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low/high} from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland memcg: introduce per-memcg reclaim interface config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 8 +- init/Kconfig | 10 ++ kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 188 ++++++++++++++++++++++++- 8 files changed, 218 insertions(+), 6 deletions(-) -- 2.34.1

2 8

[PATCH OLK-5.10 0/3] md: do not return existing mddevs from mddev_find_or_alloc
by Li Lingfeng 13 Dec '23

13 Dec '23

Do not return existing mddevs from mddev_find_or_alloc. Christoph Hellwig (3): md: factor out a mddev_alloc_unit helper from mddev_find md: refactor mddev_find_or_alloc md: do not return existing mddevs from mddev_find_or_alloc drivers/md/md.c | 139 +++++++++++++++++++++++------------------------- 1 file changed, 67 insertions(+), 72 deletions(-) -- 2.31.1

2 4

[PATCH OLK-6.6 0/8] Spark SQL scenario bpf readahead optimization synchronization to OLK-6.6
by ZhaoLong Wang 13 Dec '23

13 Dec '23

CONFIG: CONFIG_DEBUG_INFO_BTF=y CONFIG_BPF_SYSCALL=y CONFIG_NF_CONNTRACK=y CONFIG_NF_CONNTRACK_MARK=y Hou Tao (5): vfs: add bare tracepoints for vfs read and release fs: add helper fs_file_read_do_trace() xfs: add trace for read and release of regular file ext4: add trace for the read and release of regular file selftests/bpf: add demo for file read pattern detection Yufen Yu (1): readahead: introduce FMODE_CTL_WILLNEED to read first 2MB of file ZhaoLong Wang (2): VFS: Rolling Back the fmode macro definition and structure members selftests/bpf: Update the demo file_read_pattern to run on libbpf 1.0+ fs/ext4/file.c | 4 + fs/read_write.c | 38 +++++ fs/xfs/xfs_file.c | 3 + include/linux/fs.h | 37 +++++ include/trace/events/fs.h | 33 +++++ mm/readahead.c | 40 ++++- tools/testing/selftests/bpf/Makefile | 1 + .../testing/selftests/bpf/file_read_pattern.c | 73 +++++++++ .../bpf/progs/file_read_pattern_prog.c | 138 ++++++++++++++++++ 9 files changed, 366 insertions(+), 1 deletion(-) create mode 100644 include/trace/events/fs.h create mode 100644 tools/testing/selftests/bpf/file_read_pattern.c create mode 100644 tools/testing/selftests/bpf/progs/file_read_pattern_prog.c -- 2.39.2

2 9

[PATCH v7 OLK-6.6 0/5] Support Qos Scheduler
by Wenyu Huang 13 Dec '23

13 Dec '23

Zhang Qiao (5): sched: Introduce qos scheduler for co-location sched: Throttle qos cfs_rq when current cpu is running online task sched: Support kill boost for offline task sched: Introduce handle priority reversion mechanism sched: Enable qos scheduler config arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/cgroup.h | 4 + include/linux/resume_user_mode.h | 5 + include/linux/sched.h | 11 + init/Kconfig | 12 + kernel/cgroup/cgroup.c | 21 ++ kernel/sched/core.c | 155 ++++++++++ kernel/sched/fair.c | 378 ++++++++++++++++++++++++- kernel/sched/sched.h | 12 + kernel/signal.c | 3 + 11 files changed, 602 insertions(+), 1 deletion(-) -- 2.34.1

2 6

[PATCH OLK-5.10] mm/mempolicy: check preferred_node rather than nodes for MPOL_PREFERRED
by Wupeng Ma 13 Dec '23

13 Dec '23

From: Ma Wupeng <mawupeng1(a)huawei.com> Commit b27abaccf8e8 ("mm/mempolicy: add MPOL_PREFERRED_MANY for multiple preferred nodes") add MPOL_PREFERRED_MANY which will return -1 if page node id is not in nodes. However this is useful for linux-v5.15 since commit 269fbe72cded ("mm/mempolicy: use unified 'nodes' for bind/interleave/prefer policies") already unify bind/prefer policies. While this patch does not exists during backport. To fix this, drop checking v.nodes for prefer. Ma Wupeng (1): mm/mempolicy: check preferred_node rather than nodes for MPOL_PREFERRED mm/mempolicy.c | 2 -- 1 file changed, 2 deletions(-) -- 2.25.1

2 2

[PATCH OLK-5.10] locking/osq_lock: Avoid false sharing in optimistic_spin_node
by Zeng Heng 13 Dec '23

13 Dec '23

hulk inclusion category: performance bugzilla: https://gitee.com/openeuler/kernel/issues/I8MV01 -------------------------------- Using the UnixBench test suite, we clearly find that osq_lock() cause extremely high overheads with perf tool in the File Copy items: Overhead Shared Object Symbol 94.25% [kernel] [k] osq_lock 0.74% [kernel] [k] rwsem_spin_on_owner 0.32% [kernel] [k] filemap_get_read_batch In response to this, we conducted an analysis and made some gains: In the prologue of osq_lock(), it set `cpu` member of percpu struct optimistic_spin_node with the local cpu id, after that the value of the percpu struct would never change in fact. Based on that, we can regard the `cpu` member as a constant variable. In the meanwhile, other members of the percpu struct like next, prev and locked are frequently modified by osq_lock() and osq_unlock() which are called by rwsem, mutex and so on. However, that would invalidate the cache of the cpu member on other CPUs. Therefore, we can place padding here and split them into different cache lines to avoid cache misses when the next CPU is spinning to check other node's cpu member by vcpu_is_preempted(). Here provide the UnixBench full-core test result as below: Machine Intel(R) Xeon(R) Gold 6248 CPU, 40 cores, 80 threads Run the command of "./Run -c 80 -i 3" 10 times and take the average. System Benchmarks Index Values Without Patch With Patch Diff Dhrystone 2 using register variables 185876.43 185945.41 0.04% Double-Precision Whetstone 79637.27 79659.29 0.03% Execl Throughput 9909.61 10576.06 6.73% File Copy 1024 bufsize 2000 maxblocks 1723.01 2086.08 21.07% File Copy 256 bufsize 500 maxblocks 1150.24 1338.21 16.34% File Copy 4096 bufsize 8000 maxblocks 3719.19 4011.99 7.87% Pipe Throughput 66184.84 66025.25 -0.24% Pipe-based Context Switching 30606.18 31074.21 1.53% Process Creation 9442.48 9450.77 0.09% Shell Scripts (1 concurrent) 44526.52 46548.54 4.54% Shell Scripts (8 concurrent) 42903.96 45718.56 6.56% System Call Overhead 3645.20 3717.42 1.98% ======== System Benchmarks Index Score 15126.87 15931.29 5.32% Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- include/linux/osq_lock.h | 2 +- kernel/locking/osq_lock.c | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 5581dbd3bd34..deb90ad5f560 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -9,7 +9,7 @@ struct optimistic_spin_node { struct optimistic_spin_node *next, *prev; int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # + 1 value */ + int cpu ____cacheline_aligned; /* encoded CPU # + 1 value */ }; struct optimistic_spin_queue { diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 1de006ed3aa8..4fa8f3b9e2a1 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -96,7 +96,13 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->locked = 0; node->next = NULL; - node->cpu = curr; + /* + * After this cpu member is initialized for the first time, it + * would no longer change in fact. That could avoid cache misses + * when spin and access the cpu member by other CPUs. + */ + if (node->cpu != curr) + node->cpu = curr; /* * We need both ACQUIRE (pairs with corresponding RELEASE in -- 2.25.1

2 1

[PATCH OLK-5.10 0/7] cpumask: cleanup nr_cpu_ids vs nr_cpumask_bits mess
by Lu Jialin 13 Dec '23

13 Dec '23

From: Zheng Zucheng <zhengzucheng(a)huawei.com> cpumask subsystem uses nr_cpu_ids and nr_cpumask_bits interchangeably despite that the variables have different meaning and purpose. It makes some cpumask functions broken. This series cleans that mess and adds new config FORCE_NR_CPUS that allows to optimize cpumask subsystem if the number of CPUs is known at compile-time. After some testing I found build broken when SMP is on and NR_CPUS == 1. This is addressed in a new patch #1, and in the following patch #2 that now declares set_nr_cpu_ids in cpumask.h (was in smp.h). Yury Norov (6): smp: don't declare nr_cpu_ids if NR_CPUS == 1 smp: add set_nr_cpu_ids() lib/cpumask: delete misleading comment lib/cpumask: deprecate nr_cpumask_bits lib/cpumask: add FORCE_NR_CPUS config option powerpc/64: don't refer nr_cpu_ids in asm code when it's undefined Zheng Zucheng (1): config: Add FORCE_NR_CPUS to openeuler_defconfig arch/arm64/configs/openeuler_defconfig | 1 + arch/loongarch/kernel/setup.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/head_64.S | 4 ++++ arch/x86/configs/openeuler_defconfig | 1 + arch/x86/kernel/smpboot.c | 4 ++-- arch/x86/xen/smp_pv.c | 2 +- include/linux/cpumask.h | 22 +++++++++++----------- kernel/smp.c | 6 ++++-- lib/Kconfig | 9 +++++++++ 10 files changed, 35 insertions(+), 18 deletions(-) -- 2.34.1

2 8

[PATCH OLK-6.6] x86/ioapic: add an interface for driver to sync hardware data into memory
by Lin Yujun 13 Dec '23

13 Dec '23

From: Hongbo Yao <yaohongbo(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8NV1E -------------------------------- The default interrupt trigger mode of Pci driver is Level, however, some pci drivers want to change irq trigger mode to edge by writing hardware register directly. In current kernel, this kind of driver needs to sync entry data which has already been reservd in memory. This patch provides an interface for the driver to sync entry data in memory. Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> Signed-off-by: Lin Yujun <linyujun809(a)huawei.com> --- arch/x86/include/asm/io_apic.h | 1 + arch/x86/kernel/apic/io_apic.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e02..435ae723a238 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -174,6 +174,7 @@ extern void clear_IO_APIC(void); extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); +extern void ioapic_sync_hardware_data(int irq); #else /* !CONFIG_X86_IO_APIC */ #define IO_APIC_IRQ(x) 0 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..d256e0b57e94 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1202,6 +1202,31 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +/* + * The function is only provided for Drivers to keep the data value in + * memory consistent with the value of the register, and these drivers + * must use it carefully. + * + * The correct step should be: + * Change register ---> ioapic_sync_hardware_data ---> request_irq + */ +void ioapic_sync_hardware_data(int irq) +{ + struct IO_APIC_route_entry entry; + struct mp_chip_data *data; + struct irq_pin_list *pin_list; + + data = irq_get_chip_data(irq); + for_each_irq_pin(pin_list, data->irq_2_pin) { + entry = ioapic_read_entry(pin_list->apic, pin_list->pin); + data->entry.trigger = entry.trigger; + data->entry.polarity = entry.polarity; + pr_debug("irq[%d] update trigger[%d] polarity[%d]\n", + irq, entry.trigger, entry.polarity); + } +} +EXPORT_SYMBOL(ioapic_sync_hardware_data); + static struct irq_chip ioapic_chip, ioapic_ir_chip; static void __init setup_IO_APIC_irqs(void) -- 2.34.1

2 1

[PATCH OLK-6.6 v4 0/8] memcg reclaim and cgroup kill
by Lu Jialin 13 Dec '23

13 Dec '23

Lu Jialin (8): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland memcg: introduce per-memcg reclaim interface config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +++- init/Kconfig | 10 ++ kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 183 ++++++++++++++++++++++++- 8 files changed, 228 insertions(+), 7 deletions(-) -- 2.34.1

2 9

[PATCH OLK-5.10 0/5] cpumask: cleanup nr_cpu_ids vs nr_cpumask_bits mess
by Lu Jialin 13 Dec '23

13 Dec '23

From: Zheng Zucheng <zhengzucheng(a)huawei.com> cpumask subsystem uses nr_cpu_ids and nr_cpumask_bits interchangeably despite that the variables have different meaning and purpose. It makes some cpumask functions broken. This series cleans that mess and adds new config FORCE_NR_CPUS that allows to optimize cpumask subsystem if the number of CPUs is known at compile-time. After some testing I found build broken when SMP is on and NR_CPUS == 1. This is addressed in a new patch #1, and in the following patch #2 that now declares set_nr_cpu_ids in cpumask.h (was in smp.h). Yury Norov (5): smp: don't declare nr_cpu_ids if NR_CPUS == 1 smp: add set_nr_cpu_ids() lib/cpumask: delete misleading comment lib/cpumask: deprecate nr_cpumask_bits lib/cpumask: add FORCE_NR_CPUS config option arch/loongarch/kernel/setup.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/x86/kernel/smpboot.c | 4 ++-- arch/x86/xen/smp_pv.c | 2 +- include/linux/cpumask.h | 22 +++++++++++----------- kernel/smp.c | 6 ++++-- lib/Kconfig | 9 +++++++++ 7 files changed, 29 insertions(+), 18 deletions(-) -- 2.34.1

2 6

[PATCH OLK-6.6] x86/ioapic: add an interface for driver to sync hardware data into memory
by Lin Yujun 13 Dec '23

13 Dec '23

From: Hongbo Yao <yaohongbo(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8NV1E -------------------------------- The default interrupt trigger mode of Pci driver is Level, however, some pci drivers want to change irq trigger mode to edge by writing hardware register directly. In current kernel, this kind of driver needs to sync entry data which has already been reservd in memory. This patch provides an interface for the driver to sync entry data in memory. Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> Signed-off-by: Lin Yujun <linyujun809(a)huawei.com> --- arch/x86/include/asm/io_apic.h | 1 + arch/x86/kernel/apic/io_apic.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e02..435ae723a238 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -174,6 +174,7 @@ extern void clear_IO_APIC(void); extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); +extern void ioapic_sync_hardware_data(int irq); #else /* !CONFIG_X86_IO_APIC */ #define IO_APIC_IRQ(x) 0 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..d256e0b57e94 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1202,6 +1202,31 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +/* + * The function is only provided for Drivers to keep the data value in + * memory consistent with the value of the register, and these drivers + * must use it carefully. + * + * The correct step should be: + * Change register ---> ioapic_sync_hardware_data ---> request_irq + */ +void ioapic_sync_hardware_data(int irq) +{ + struct IO_APIC_route_entry entry; + struct mp_chip_data *data; + struct irq_pin_list *pin_list; + + data = irq_get_chip_data(irq); + for_each_irq_pin(pin_list, data->irq_2_pin) { + entry = ioapic_read_entry(pin_list->apic, pin_list->pin); + data->entry.trigger = entry.trigger; + data->entry.polarity = entry.polarity; + pr_debug("irq[%d] update trigger[%d] polarity[%d]\n", + irq, entry.trigger, entry.polarity); + } +} +EXPORT_SYMBOL(ioapic_sync_hardware_data); + static struct irq_chip ioapic_chip, ioapic_ir_chip; static void __init setup_IO_APIC_irqs(void) -- 2.34.1

2 1

[PATCH OLK-6.6] ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet
by Zhengchao Shao 13 Dec '23

13 Dec '23

mainline inclusion from mainline-v6.7-rc2 commit e2b706c691905fe78468c361aaabc719d0a496f1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8K0N2 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When I perform the following test operations: 1.ip link add br0 type bridge 2.brctl addif br0 eth0 3.ip addr add 239.0.0.1/32 dev eth0 4.ip addr add 239.0.0.1/32 dev br0 5.ip addr add 224.0.0.1/32 dev br0 6.while ((1)) do ifconfig br0 up ifconfig br0 down done 7.send IGMPv2 query packets to port eth0 continuously. For example, ./mausezahn ethX -c 0 "01 00 5e 00 00 01 00 72 19 88 aa 02 08 00 45 00 00 1c 00 01 00 00 01 02 0e 7f c0 a8 0a b7 e0 00 00 01 11 64 ee 9b 00 00 00 00" The preceding tests may trigger the refcnt uaf issue of the mc list. The stack is as follows: refcount_t: addition on 0; use-after-free. WARNING: CPU: 21 PID: 144 at lib/refcount.c:25 refcount_warn_saturate (lib/refcount.c:25) CPU: 21 PID: 144 Comm: ksoftirqd/21 Kdump: loaded Not tainted 6.7.0-rc1-next-20231117-dirty #80 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:refcount_warn_saturate (lib/refcount.c:25) RSP: 0018:ffffb68f00657910 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff8a00c3bf96c0 RCX: ffff8a07b6160908 RDX: 00000000ffffffd8 RSI: 0000000000000027 RDI: ffff8a07b6160900 RBP: ffff8a00cba36862 R08: 0000000000000000 R09: 00000000ffff7fff R10: ffffb68f006577c0 R11: ffffffffb0fdcdc8 R12: ffff8a00c3bf9680 R13: ffff8a00c3bf96f0 R14: 0000000000000000 R15: ffff8a00d8766e00 FS: 0000000000000000(0000) GS:ffff8a07b6140000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055f10b520b28 CR3: 000000039741a000 CR4: 00000000000006f0 Call Trace: <TASK> igmp_heard_query (net/ipv4/igmp.c:1068) igmp_rcv (net/ipv4/igmp.c:1132) ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205) ip_local_deliver_finish (net/ipv4/ip_input.c:234) __netif_receive_skb_one_core (net/core/dev.c:5529) netif_receive_skb_internal (net/core/dev.c:5729) netif_receive_skb (net/core/dev.c:5788) br_handle_frame_finish (net/bridge/br_input.c:216) nf_hook_bridge_pre (net/bridge/br_input.c:294) __netif_receive_skb_core (net/core/dev.c:5423) __netif_receive_skb_list_core (net/core/dev.c:5606) __netif_receive_skb_list (net/core/dev.c:5674) netif_receive_skb_list_internal (net/core/dev.c:5764) napi_gro_receive (net/core/gro.c:609) e1000_clean_rx_irq (drivers/net/ethernet/intel/e1000/e1000_main.c:4467) e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3805) __napi_poll (net/core/dev.c:6533) net_rx_action (net/core/dev.c:6735) __do_softirq (kernel/softirq.c:554) run_ksoftirqd (kernel/softirq.c:913) smpboot_thread_fn (kernel/smpboot.c:164) kthread (kernel/kthread.c:388) ret_from_fork (arch/x86/kernel/process.c:153) ret_from_fork_asm (arch/x86/entry/entry_64.S:250) </TASK> The root causes are as follows: Thread A Thread B ... netif_receive_skb br_dev_stop ... br_multicast_leave_snoopers ... __ip_mc_dec_group ... __igmp_group_dropped igmp_rcv igmp_stop_timer igmp_heard_query //ref = 1 ip_ma_put igmp_mod_timer refcount_dec_and_test igmp_start_timer //ref = 0 ... refcount_inc //ref increases from 0 When the device receives an IGMPv2 Query message, it starts the timer immediately, regardless of whether the device is running. If the device is down and has left the multicast group, it will cause the mc list refcount uaf issue. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Reviewed-by: Hangbin Liu <liuhangbin(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> --- net/ipv4/igmp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 418e5fb58fd3..d515881d02a6 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = get_random_u32_below(max_delay); im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) -- 2.34.1

2 1

[PATCH OLK-6.6] x86/ioapic: add an interface for driver to sync hardware data into memory
by Lin Yujun 12 Dec '23

12 Dec '23

From: Hongbo Yao <yaohongbo(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8NV1E -------------------------------- The default interrupt trigger mode of Pci driver is Level, however, some pci drivers want to change irq trigger mode to edge by writing hardware register directly. In current kernel, this kind of driver needs to sync entry data which has already been reservd in memory. This patch provides an interface for the driver to sync entry data in memory. Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Lin Yujun <linyujun809(a)huawei.com> --- arch/x86/include/asm/io_apic.h | 1 + arch/x86/kernel/apic/io_apic.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e02..435ae723a238 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -174,6 +174,7 @@ extern void clear_IO_APIC(void); extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); +extern void ioapic_sync_hardware_data(int irq); #else /* !CONFIG_X86_IO_APIC */ #define IO_APIC_IRQ(x) 0 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..d256e0b57e94 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1202,6 +1202,31 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +/* + * The function is only provided for Drivers to keep the data value in + * memory consistent with the value of the register, and these drivers + * must use it carefully. + * + * The correct step should be: + * Change register ---> ioapic_sync_hardware_data ---> request_irq + */ +void ioapic_sync_hardware_data(int irq) +{ + struct IO_APIC_route_entry entry; + struct mp_chip_data *data; + struct irq_pin_list *pin_list; + + data = irq_get_chip_data(irq); + for_each_irq_pin(pin_list, data->irq_2_pin) { + entry = ioapic_read_entry(pin_list->apic, pin_list->pin); + data->entry.trigger = entry.trigger; + data->entry.polarity = entry.polarity; + pr_debug("irq[%d] update trigger[%d] polarity[%d]\n", + irq, entry.trigger, entry.polarity); + } +} +EXPORT_SYMBOL(ioapic_sync_hardware_data); + static struct irq_chip ioapic_chip, ioapic_ir_chip; static void __init setup_IO_APIC_irqs(void) -- 2.34.1

2 1

[PATCH OLK-5.10 0/5] cpumask: cleanup nr_cpu_ids vs nr_cpumask_bits mess
by Lu Jialin 12 Dec '23

12 Dec '23

From: Zheng Zucheng <zhengzucheng(a)huawei.com> Yury Norov (5): mainline inclusion from mainline-v6.1-rc1 commit 53fc190cc6771c5494d782210334d4ebb50c7103 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KQBZ CVE: NA mainline inclusion from mainline-v6.1-rc1 commit 38bef8e57f2149acd2c910a98f57dd6291d2e0ec category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KQBZ CVE: NA mainline inclusion from mainline-v6.1-rc1 commit 7102b3bb070fdf4580a05cbfc5ad3c0691dc4bf9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KQBZ CVE: NA mainline inclusion from mainline-v6.1-rc1 commit aa47a7c215e79a2ade6916f163c5a17b561bce4f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KQBZ CVE: NA mainline inclusion from mainline-v6.1-rc1 commit 6f9c07be9d020489326098801f0661f754c7c865 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8KQBZ CVE: NA arch/loongarch/kernel/setup.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/x86/kernel/smpboot.c | 4 ++-- arch/x86/xen/smp_pv.c | 2 +- include/linux/cpumask.h | 22 +++++++++++----------- kernel/smp.c | 6 ++++-- lib/Kconfig | 9 +++++++++ 7 files changed, 29 insertions(+), 18 deletions(-) -- 2.34.1

2 6

[PATCH OLK-6.6 v5 0/6] Ascend features
by Yuan Can 12 Dec '23

12 Dec '23

Navid Emamdoost (1): nbd_genl_status: null check for nla_nest_start Weilong Chen (2): ACPI / APEI: Notify all ras err to driver arm64/ascend: Add new enable_oom_killer interface for oom contrl Xu Qiang (2): irq-gic-v3: Add support to init ts core GICR irq-gic-v3-its: It can't be initialized when the GICR had been cut Yuan Can (1): ascend: export interfaces required by ascend drivers arch/arm64/configs/openeuler_defconfig | 1 + drivers/acpi/apei/Kconfig | 7 + drivers/acpi/apei/ghes.c | 8 +- drivers/block/nbd.c | 6 + drivers/irqchip/Kconfig | 7 + drivers/irqchip/irq-gic-v3-its.c | 254 ++++++++++++++++++++++++- drivers/irqchip/irq-gic-v3.c | 101 +++++++++- include/linux/irqchip/arm-gic-v3.h | 5 + include/linux/oom.h | 24 +++ kernel/power/autosleep.c | 1 + kernel/workqueue.c | 3 + mm/Kconfig | 10 + mm/memcontrol.c | 20 ++ mm/oom_kill.c | 58 ++++++ mm/util.c | 2 + mm/vmalloc.c | 2 + 16 files changed, 500 insertions(+), 9 deletions(-) -- 2.17.1

2 7

[PATCH OLK-6.6 v2 0/4] xfs: fix some misc issue
by Long Li 12 Dec '23

12 Dec '23

his patch set fix some mics xfs issue: Long Li (4): xfs: fix a UAF when inode item push xfs: fix a UAF in xfs_iflush_abort_clean xfs: don't verify agf length when log recovery xfs: xfs_trans_cancel() path must check for log shutdown fs/xfs/libxfs/xfs_alloc.c | 3 ++- fs/xfs/xfs_buf.c | 5 +++++ fs/xfs/xfs_inode_item.c | 8 +++++++- fs/xfs/xfs_trans.c | 2 +- 4 files changed, 15 insertions(+), 3 deletions(-) -- 2.31.1

2 5

[PATCH OLK-5.10] arm64: cpufeature: Add missing .field_width for system registers
by Wang ShaoBo 12 Dec '23

12 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8NRI6 CVE: NA -------------------------------- This was missed when making specification of a field standard. Fixes: 2ee4c87e5fd2e ("arm64: cpufeature: Always specify and use a field width for capabilities") Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> --- arch/arm64/kernel/cpufeature.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index b13deca20432e..6c07804d94667 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2324,6 +2324,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64PFR0_MPAM_SHIFT, + .field_width = 4, .min_field_value = ID_AA64PFR0_MPAM, }, #endif /* CONFIG_MPAM */ @@ -2605,6 +2606,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, .field_pos = ID_AA64MMFR1_TWED_SHIFT, + .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, }, @@ -2616,6 +2618,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR2_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR2_WFXT_SHIFT, + .field_width = 4, .matches = has_cpuid_feature, .min_field_value = ID_AA64ISAR2_WFXT_SUPPORTED, }, @@ -2626,6 +2629,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_LRCPC_SHIFT, + .field_width = 4, .matches = has_cpuid_feature, .min_field_value = 1, }, @@ -2635,6 +2639,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR1_HPD_SHIFT, + .field_width = 4, .matches = has_cpuid_feature, .min_field_value = 2, }, @@ -2646,6 +2651,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64MMFR1_HPD_SHIFT, + .field_width = 4, .matches = plat_can_use_pbha_stage1, .min_field_value = 2, .cpu_enable = cpu_enable_pbha, -- 2.25.1

2 1

[PATCH OLK-5.10] locking/osq_lock: Avoid false sharing in optimistic_spin_node
by Zeng Heng 12 Dec '23

12 Dec '23

hulk inclusion category: performance bugzilla: https://gitee.com/openeuler/kernel/issues/I8MV01 -------------------------------- In the prologue of osq_lock(), it set `cpu` member of percpu struct optimistic_spin_node with the local cpu id, after that the value is never changed any more. Consequently, we can regard the `cpu` member as a constant variable. In the meanwhile, other members like next, prev and locked are frequently modified by osq_lock() and osq_unlock() which come from rwsem, mutex and so on. So here we can place padding and split them into different cache lines, so that avoid cache misses when a cpu is spinning to check previous node's cpu field by vcpu_is_preempted() in the following. Here provide the UnixBench full-core test result as below: Machine Intel(R) Xeon(R) Gold 6248 CPU, 40 cores, 80 threads Run the command of "./Run -c 80 -i 3" 10 times and take the average. System Benchmarks Index Values Without Patch With Patch Diff Dhrystone 2 using register variables 185876.43 185945.41 0.04% Double-Precision Whetstone 79637.27 79659.29 0.03% Execl Throughput 9909.61 10576.06 6.73% File Copy 1024 bufsize 2000 maxblocks 1723.01 2086.08 21.07% File Copy 256 bufsize 500 maxblocks 1150.24 1338.21 16.34% File Copy 4096 bufsize 8000 maxblocks 3719.19 4011.99 7.87% Pipe Throughput 66184.84 66025.25 -0.24% Pipe-based Context Switching 30606.18 31074.21 1.53% Process Creation 9442.48 9450.77 0.09% Shell Scripts (1 concurrent) 44526.52 46548.54 4.54% Shell Scripts (8 concurrent) 42903.96 45718.56 6.56% System Call Overhead 3645.20 3717.42 1.98% ======== System Benchmarks Index Score 15126.87 15931.29 5.32% Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- include/linux/osq_lock.h | 2 +- kernel/locking/osq_lock.c | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 5581dbd3bd34..deb90ad5f560 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -9,7 +9,7 @@ struct optimistic_spin_node { struct optimistic_spin_node *next, *prev; int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # + 1 value */ + int cpu ____cacheline_aligned; /* encoded CPU # + 1 value */ }; struct optimistic_spin_queue { diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 1de006ed3aa8..1e1a79580e96 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -96,7 +96,13 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->locked = 0; node->next = NULL; - node->cpu = curr; + /* + * After this cpu member is initialized for the first time, it + * would no longer change in fact. That could avoid cache misses + * when spin and access the cpu member by other CPUs. + */ + if (!node->cpu) + node->cpu = curr; /* * We need both ACQUIRE (pairs with corresponding RELEASE in -- 2.25.1

2 1

[PATCH OLK-6.6 0/6] Add support for hisi HBM devices
by Zhang Zekun 12 Dec '23

12 Dec '23

Add support for HISI HBM device, and HBM ACLS repair. The patch set includes three functionalities. 1. Add support for hbm device hotplug. 2. provide extra information with hbm locality information 3. Add support for HBM acls repair. Zhang Zekun (6): ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information soc: hbmcache: Add support for online and offline the hbm cache soc: hisilicon: hisi_hbmdev: Add hbm acls repair and query methods drivers/acpi/acpi_memhotplug.c | 22 ++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/base/container.c | 1 + drivers/soc/hisilicon/Kconfig | 36 +++ drivers/soc/hisilicon/Makefile | 3 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 435 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 ++ include/linux/acpi.h | 2 + include/linux/memory_hotplug.h | 1 + 11 files changed, 679 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

2 7

[PATCH OLK-5.10] KVM: arm64: Translate logic cluster id to physical cluster id when updating lsudvmbm
by chenxiang 12 Dec '23

12 Dec '23

From: Xiang Chen <chenxiang66(a)hisilicon.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8HY1B ---------------------------------------------------------------- For dvmbm feature, MN requires physical cluster id while it is filled with logic cluster id right now. In some situations which physical cluster id is not equal to logic cluster id such as in PG boards, it will cause issues when enabling dvmbm. To avoid the issue, translate logic cluster id to physical cluster id when updating lsudvmbm. Signed-off-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: Cai Jian <caijian11(a)h-partners.com> --- arch/arm64/kvm/hisilicon/hisi_virt.c | 166 +++++++++++++++++++++++++-- 1 file changed, 157 insertions(+), 9 deletions(-) diff --git a/arch/arm64/kvm/hisilicon/hisi_virt.c b/arch/arm64/kvm/hisilicon/hisi_virt.c index 10233b801896..1f4a8e44228e 100644 --- a/arch/arm64/kvm/hisilicon/hisi_virt.c +++ b/arch/arm64/kvm/hisilicon/hisi_virt.c @@ -236,12 +236,113 @@ static int kvm_dvmbm_get_dies_info(struct kvm *kvm, u64 *vm_aff3s, int size) return num; } +#define MAX_CLUSTERS_PER_DIE 8 +#define TB_MN_BASE 0x00C6067f0000 +#define TA_MN_BASE 0x0046067F0000 +#define CHIP_ADDR_OFFSET(_chip) (((((_chip) >> 3) & 0x1) * 0x80000000000) + \ + ((((_chip) >> 2) & 0x1) * (0x100000000000)) + \ + (((_chip) & 0x3) * 0x200000000000)) +#define MAX_PG_CFG_SKITS 4 +#define MAX_PG_CFG_DIES 2 +#define MN_ECO0_OFFSET 0xc00 +#define SOCKET_ID_MASK 0xf8 +#define SOCKET_ID_SHIFT 3 +#define DIE_ID_MASK 0x7 + +static u32 socket_num, die_num; + +static void kvm_get_socket_num(u32 *socket_num) +{ + int socket_id[MAX_PG_CFG_SKITS], cpu; + u32 num = 0; + + for_each_cpu(cpu, cpu_possible_mask) { + bool found = false; + u64 aff3, socket; + int i; + + aff3 = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 3); + /* aff3[7:3]: socket ID */ + socket = (aff3 & SOCKET_ID_MASK) >> SOCKET_ID_SHIFT; + for (i = 0; i < num; i++) { + if (socket_id[i] == socket) { + found = true; + break; + } + } + if (!found) + socket_id[num++] = socket; + } + *socket_num = num; +} + +static void kvm_get_die_num(u32 *die_num) +{ + int die_id[MAX_PG_CFG_DIES], cpu; + u32 num = 0; + + for_each_cpu(cpu, cpu_possible_mask) { + bool found = false; + u64 aff3, die; + int i; + + aff3 = MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 3); + /* aff3[2:0]: die ID */ + die = aff3 & DIE_ID_MASK; + for (i = 0; i < num; i++) { + if (die_id[i] == die) { + found = true; + break; + } + } + if (!found) + die_id[num++] = die; + } + *die_num = num; +} + +static u32 g_pg_cfg[MAX_PG_CFG_SKITS * MAX_PG_CFG_DIES]; + +static u64 kvm_switch_aff2_logic_to_phy(unsigned long pg_cfg, u64 logic_aff2) +{ + u32 pg_num = 0, i, j; + u32 cluster_pg[MAX_CLUSTERS_PER_DIE]; + u32 pg_flag[MAX_CLUSTERS_PER_DIE]; + + for (i = 0; i < MAX_CLUSTERS_PER_DIE; i++) { + if (test_bit(i, &pg_cfg)) + pg_num++; + cluster_pg[i] = i; + pg_flag[i] = 0; + } + + for (i = 0; i < MAX_CLUSTERS_PER_DIE - pg_num; i++) { + if (test_bit(i, &pg_cfg)) { + for (j = 0; j < pg_num; j++) { + u32 cluster_bak = MAX_CLUSTERS_PER_DIE - pg_num + j; + + if (!test_bit(cluster_bak, &pg_cfg) && + !pg_flag[cluster_bak]) { + pg_flag[cluster_bak] = 1; + cluster_pg[i] = cluster_bak; + cluster_pg[cluster_bak] = i; + break; + } + } + } + } + + return cluster_pg[logic_aff2]; +} + static void kvm_update_vm_lsudvmbm(struct kvm *kvm) { - u64 mpidr, aff3, aff2, aff1; + u64 mpidr, aff3, aff2, aff1, phy_aff2; u64 vm_aff3s[DVMBM_MAX_DIES]; u64 val; int cpu, nr_dies; + unsigned long pg_cfg; + u32 socket_id; nr_dies = kvm_dvmbm_get_dies_info(kvm, vm_aff3s, DVMBM_MAX_DIES); if (nr_dies > 2) { @@ -258,8 +359,14 @@ static void kvm_update_vm_lsudvmbm(struct kvm *kvm) mpidr = cpu_logical_map(cpu); aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); aff1 = MPIDR_AFFINITY_LEVEL(mpidr, 1); - - val |= 1ULL << (aff2 * 4 + aff1); + socket_id = (aff3 & SOCKET_ID_MASK) >> SOCKET_ID_SHIFT; + + if ((vm_aff3s[0] & DIE_ID_MASK) == 0x3) /* TB totem */ + pg_cfg = g_pg_cfg[0 + socket_id * die_num] & 0xff; + else /* TA totem */ + pg_cfg = g_pg_cfg[1 + socket_id * die_num] & 0xff; + phy_aff2 = kvm_switch_aff2_logic_to_phy(pg_cfg, aff2); + val |= 1ULL << (phy_aff2 * 4 + aff1); } goto out_update; @@ -268,7 +375,7 @@ static void kvm_update_vm_lsudvmbm(struct kvm *kvm) /* nr_dies == 2 */ val = DVMBM_RANGE_TWO_DIES << DVMBM_RANGE_SHIFT | DVMBM_GRAN_CLUSTER << DVMBM_GRAN_SHIFT | - vm_aff3s[0] << DVMBM_DIE1_SHIFT | + vm_aff3s[0] << DVMBM_DIE1_SHIFT | vm_aff3s[1] << DVMBM_DIE2_SHIFT; /* and fulfill bits [43:0] */ @@ -276,11 +383,23 @@ static void kvm_update_vm_lsudvmbm(struct kvm *kvm) mpidr = cpu_logical_map(cpu); aff3 = MPIDR_AFFINITY_LEVEL(mpidr, 3); aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2); - - if (aff3 == vm_aff3s[0]) - val |= 1ULL << (aff2 + DVMBM_DIE1_CLUSTER_SHIFT); - else - val |= 1ULL << (aff2 + DVMBM_DIE2_CLUSTER_SHIFT); + socket_id = (aff3 & SOCKET_ID_MASK) >> SOCKET_ID_SHIFT; + + if (aff3 == vm_aff3s[0]) { + if ((vm_aff3s[0] & DIE_ID_MASK) == 0x3) /* TB totem */ + pg_cfg = g_pg_cfg[0 + socket_id * die_num] & 0xff; + else /* TA totem */ + pg_cfg = g_pg_cfg[1 + socket_id * die_num] & 0xff; + phy_aff2 = kvm_switch_aff2_logic_to_phy(pg_cfg, aff2); + val |= 1ULL << (phy_aff2 + DVMBM_DIE1_CLUSTER_SHIFT); + } else { + if ((vm_aff3s[1] & DIE_ID_MASK) == 0x3) /* TB totem */ + pg_cfg = g_pg_cfg[0 + socket_id * die_num] & 0xff; + else /* TA totem */ + pg_cfg = g_pg_cfg[1 + socket_id * die_num] & 0xff; + phy_aff2 = kvm_switch_aff2_logic_to_phy(pg_cfg, aff2); + val |= 1ULL << (phy_aff2 + DVMBM_DIE2_CLUSTER_SHIFT); + } } out_update: @@ -357,6 +476,33 @@ void kvm_hisi_dvmbm_put(struct kvm_vcpu *vcpu) */ } +static void kvm_get_pg_cfg(u32 *pg_cfgs) +{ + void __iomem *mn_base; + u32 i, j; + u64 mn_phy_base; + u32 val; + + kvm_get_socket_num(&socket_num); + kvm_get_die_num(&die_num); + for (i = 0; i < socket_num; i++) { + for (j = 0; j < die_num; j++) { + mn_phy_base = (j == 0) ? TB_MN_BASE : TA_MN_BASE; + mn_phy_base += CHIP_ADDR_OFFSET(i); + mn_phy_base += MN_ECO0_OFFSET; + + mn_base = ioremap(mn_phy_base, 4); + if (!mn_base) { + kvm_info("MN base addr ioremap fail\n"); + return; + } + val = readl_relaxed(mn_base); + pg_cfgs[j + i * die_num] = val & 0xff; + iounmap(mn_base); + } + } +} + int kvm_hisi_init_dvmbm(struct kvm *kvm) { if (!kvm_dvmbm_support) @@ -367,6 +513,8 @@ int kvm_hisi_init_dvmbm(struct kvm *kvm) if (!kvm->arch.dvm_cpumask) return -ENOMEM; + kvm_get_pg_cfg(g_pg_cfg); + return 0; } -- 2.30.0

3 3

[PATCH OLK-6.6 v4 0/7] support userswap feature
by Peng Zhang 12 Dec '23

12 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ChangeLog: v3->v4: - define UFFDIO_REGISTER_MODE_USWAP ((__u64)1<<10) rather than ((__u64)1<<3) v2->v3: - update patch 7 commit v1->v2: - enable CONFIG_USERSWAP for openeuler_defconfig ZhangPeng (7): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg mm/userswap: openeuler_defconfig: enable userswap arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 +- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 +++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++ 18 files changed, 747 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

2 8

[PATCH OLK-6.6] amba-pl011: Fix no irq issue due to no IRQ domain found
by Lin Yujun 12 Dec '23

12 Dec '23

From: Lin Ruizhe <linruizhe(a)huawei.com> hulk inclusion category: bugfix bugzilla: 176552 https://gitee.com/openeuler/kernel/issues/I4DDEL ------------------------------------------------- If pl011 interrupt is connected to MBIGEN interrupt controller, because the mbigen initialization is too late, which will lead to no IRQ due to no IRQ domain found, logs is shown below, "irq: no irq domain found for uart0 !" When dev->irq[0] is zero, try to get IRQ by of_irq_get() again, and return -EPROBE_DEFER if the IRQ domain is not yet created. Using deferred probing mechanism to fix the issue. Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Lin ruizhe <linruizhe(a)huawei.com> Signed-off-by: He Ying <heying24(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> conflicts: drivers/tty/serial/amba-pl011.c Signed-off-by: Lin Yujun <linyujun809(a)huawei.com> --- drivers/tty/serial/amba-pl011.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 3dc9b0fcab1c..648f99d4774c 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -2815,10 +2815,20 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id) uap->vendor = vendor; uap->fifosize = vendor->get_fifosize(dev); uap->port.iotype = vendor->access_32b ? UPIO_MEM32 : UPIO_MEM; - uap->port.irq = dev->irq[0]; uap->port.ops = &amba_pl011_pops; uap->port.rs485_config = pl011_rs485_config; uap->port.rs485_supported = pl011_rs485_supported; + + /* if no irq domain found, irq number is 0, try again */ + if (!dev->irq[0] && dev->dev.of_node) { + ret = of_irq_get(dev->dev.of_node, 0); + if (ret < 0) + return ret; + dev->irq[0] = ret; + } + + uap->port.irq = dev->irq[0]; + snprintf(uap->type, sizeof(uap->type), "PL011 rev%u", amba_rev(dev)); if (device_property_read_u32(&dev->dev, "reg-io-width", &val) == 0) { -- 2.34.1

3 2

[PATCH OLK-6.6] x86/ioapic: add an interface for driver to sync hardware data into memory
by Lin Yujun 12 Dec '23

12 Dec '23

From: Hongbo Yao <yaohongbo(a)huawei.com> hulk inclusion category: bugfix bugzilla: 20890, https://gitee.com/openeuler/kernel/issues/I5ZV1W -------------------------------- The default interrupt trigger mode of Pci driver is Level, however, some pci drivers want to change irq trigger mode to edge by writing hardware register directly. In current kernel, this kind of driver needs to sync entry data which has already been reservd in memory. This patch provides an interface for the driver to sync entry data in memory. Signed-off-by: Hongbo Yao <yaohongbo(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Lin Yujun <linyujun809(a)huawei.com> --- arch/x86/include/asm/io_apic.h | 1 + arch/x86/kernel/apic/io_apic.c | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e02..435ae723a238 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -174,6 +174,7 @@ extern void clear_IO_APIC(void); extern void restore_boot_irq_mode(void); extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); extern void print_IO_APICs(void); +extern void ioapic_sync_hardware_data(int irq); #else /* !CONFIG_X86_IO_APIC */ #define IO_APIC_IRQ(x) 0 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..d256e0b57e94 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1202,6 +1202,31 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +/* + * The function is only provided for Drivers to keep the data value in + * memory consistent with the value of the register, and these drivers + * must use it carefully. + * + * The correct step should be: + * Change register ---> ioapic_sync_hardware_data ---> request_irq + */ +void ioapic_sync_hardware_data(int irq) +{ + struct IO_APIC_route_entry entry; + struct mp_chip_data *data; + struct irq_pin_list *pin_list; + + data = irq_get_chip_data(irq); + for_each_irq_pin(pin_list, data->irq_2_pin) { + entry = ioapic_read_entry(pin_list->apic, pin_list->pin); + data->entry.trigger = entry.trigger; + data->entry.polarity = entry.polarity; + pr_debug("irq[%d] update trigger[%d] polarity[%d]\n", + irq, entry.trigger, entry.polarity); + } +} +EXPORT_SYMBOL(ioapic_sync_hardware_data); + static struct irq_chip ioapic_chip, ioapic_ir_chip; static void __init setup_IO_APIC_irqs(void) -- 2.34.1

2 1

[PATCH OLK-6.6 0/9] files cgroup featrue
by chenridong 12 Dec '23

12 Dec '23

Binder Makin (1): cgroups: Resource controller for open files Hou Tao (1): cgroup/files: use task_get_css() to get a valid css during dup_fd() Lu Jialin (3): enable CONFIG_CGROUP_FILES in openeuler_defconfig for x86 and arm64 fs: fix files.usage bug when move tasks fs/filescontrol.c: fix warning:large integer implicitly truncated to unsigned type Yang Yingliang (1): cgroup/files: support boot parameter to control if disable files cgroup Yu Kuai (1): fs/filescontrol: add a switch to enable / disable accounting of open fds Zhang Xiaoxu (2): files_cgroup: fix error pointer when kvm_vm_worker_thread files_cgroup: Fix soft lockup when refcnt overflow. .../admin-guide/kernel-parameters.txt | 7 +- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/Makefile | 1 + fs/file.c | 63 +++- fs/filescontrol.c | 312 ++++++++++++++++++ include/linux/cgroup-defs.h | 8 +- include/linux/cgroup_subsys.h | 6 + include/linux/fdtable.h | 1 + include/linux/filescontrol.h | 40 +++ init/Kconfig | 10 + 11 files changed, 442 insertions(+), 8 deletions(-) create mode 100644 fs/filescontrol.c create mode 100644 include/linux/filescontrol.h -- 2.34.1

2 10

[PATCH OLK-6.6 0/9] files cgroup enble
by chenridong 11 Dec '23

11 Dec '23

Binder Makin (1): cgroups: Resource controller for open files Hou Tao (1): cgroup/files: use task_get_css() to get a valid css during dup_fd() Lu Jialin (3): enable CONFIG_CGROUP_FILES in openeuler_defconfig for x86 and arm64 fs: fix files.usage bug when move tasks fs/filescontrol.c: fix warning:large integer implicitly truncated to unsigned type Yang Yingliang (1): cgroup/files: support boot parameter to control if disable files cgroup Yu Kuai (1): fs/filescontrol: add a switch to enable / disable accounting of open fds Zhang Xiaoxu (2): files_cgroup: fix error pointer when kvm_vm_worker_thread files_cgroup: Fix soft lockup when refcnt overflow. .../admin-guide/kernel-parameters.txt | 7 +- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/Makefile | 1 + fs/file.c | 63 +++- fs/filescontrol.c | 312 ++++++++++++++++++ include/linux/cgroup-defs.h | 8 +- include/linux/cgroup_subsys.h | 6 + include/linux/fdtable.h | 1 + include/linux/filescontrol.h | 40 +++ init/Kconfig | 10 + 11 files changed, 442 insertions(+), 8 deletions(-) create mode 100644 fs/filescontrol.c create mode 100644 include/linux/filescontrol.h -- 2.34.1

2 10

[PATCH openEuler-1.0-LTS] tun: avoid double free in tun_free_netdev
by Ziyang Xuan 11 Dec '23

11 Dec '23

From: George Kennedy <george.kennedy(a)oracle.com> mainline inclusion from mainline-v5.16-rc7 commit 158b515f703e75e7d68289bf4d98c664e1d632df category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8NHAP CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------- Avoid double free in tun_free_netdev() by moving the dev->tstats and tun->security allocs to a new ndo_init routine (tun_net_init()) that will be called by register_netdevice(). ndo_init is paired with the desctructor (tun_free_netdev()), so if there's an error in register_netdevice() the destructor will handle the frees. BUG: KASAN: double-free or invalid-free in selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 CPU: 0 PID: 25750 Comm: syz-executor416 Not tainted 5.16.0-rc2-syzk #1 Hardware name: Red Hat KVM, BIOS Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x89/0xb5 lib/dump_stack.c:106 print_address_description.constprop.9+0x28/0x160 mm/kasan/report.c:247 kasan_report_invalid_free+0x55/0x80 mm/kasan/report.c:372 ____kasan_slab_free mm/kasan/common.c:346 [inline] __kasan_slab_free+0x107/0x120 mm/kasan/common.c:374 kasan_slab_free include/linux/kasan.h:235 [inline] slab_free_hook mm/slub.c:1723 [inline] slab_free_freelist_hook mm/slub.c:1749 [inline] slab_free mm/slub.c:3513 [inline] kfree+0xac/0x2d0 mm/slub.c:4561 selinux_tun_dev_free_security+0x1a/0x20 security/selinux/hooks.c:5605 security_tun_dev_free_security+0x4f/0x90 security/security.c:2342 tun_free_netdev+0xe6/0x150 drivers/net/tun.c:2215 netdev_run_todo+0x4df/0x840 net/core/dev.c:10627 rtnl_unlock+0x13/0x20 net/core/rtnetlink.c:112 __tun_chr_ioctl+0x80c/0x2870 drivers/net/tun.c:3302 tun_chr_ioctl+0x2f/0x40 drivers/net/tun.c:3311 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x19d/0x220 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3a/0x80 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae Reported-by: syzkaller <syzkaller(a)googlegroups.com> Signed-off-by: George Kennedy <george.kennedy(a)oracle.com> Suggested-by: Jakub Kicinski <kuba(a)kernel.org> Link: https://lore.kernel.org/r/1639679132-19884-1-git-send-email-george.kennedy@… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/tun.c Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> --- drivers/net/tun.c | 111 +++++++++++++++++++++++++--------------------- 1 file changed, 60 insertions(+), 51 deletions(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a6b233a01f35..e9b8a68b350a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -248,6 +248,9 @@ struct tun_struct { struct tun_prog __rcu *steering_prog; struct tun_prog __rcu *filter_prog; struct ethtool_link_ksettings link_ksettings; + /* init args */ + struct file *file; + struct ifreq *ifr; }; struct veth { @@ -273,6 +276,9 @@ void *tun_ptr_to_xdp(void *ptr) } EXPORT_SYMBOL(tun_ptr_to_xdp); +static void tun_flow_init(struct tun_struct *tun); +static void tun_flow_uninit(struct tun_struct *tun); + static int tun_napi_receive(struct napi_struct *napi, int budget) { struct tun_file *tfile = container_of(napi, struct tun_file, napi); @@ -1030,6 +1036,49 @@ static int check_filter(struct tap_filter *filter, const struct sk_buff *skb) static const struct ethtool_ops tun_ethtool_ops; +static int tun_net_init(struct net_device *dev) +{ + struct tun_struct *tun = netdev_priv(dev); + struct ifreq *ifr = tun->ifr; + int err; + + tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); + if (!tun->pcpu_stats) + return -ENOMEM; + + spin_lock_init(&tun->lock); + + err = security_tun_dev_alloc_security(&tun->security); + if (err < 0) { + free_percpu(tun->pcpu_stats); + return err; + } + + tun_flow_init(tun); + + dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | + TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + dev->features = dev->hw_features | NETIF_F_LLTX; + dev->vlan_features = dev->features & + ~(NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + tun->flags = (tun->flags & ~TUN_FEATURES) | + (ifr->ifr_flags & TUN_FEATURES); + + INIT_LIST_HEAD(&tun->disabled); + err = tun_attach(tun, tun->file, false, ifr->ifr_flags & IFF_NAPI, + ifr->ifr_flags & IFF_NAPI_FRAGS, false); + if (err < 0) { + tun_flow_uninit(tun); + security_tun_dev_free_security(tun->security); + free_percpu(tun->pcpu_stats); + return err; + } + return 0; +} + /* Net device detach from fd. */ static void tun_net_uninit(struct net_device *dev) { @@ -1260,6 +1309,7 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp) } static const struct net_device_ops tun_netdev_ops = { + .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, @@ -1339,6 +1389,7 @@ static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) } static const struct net_device_ops tap_netdev_ops = { + .ndo_init = tun_net_init, .ndo_uninit = tun_net_uninit, .ndo_open = tun_net_open, .ndo_stop = tun_net_close, @@ -1378,7 +1429,7 @@ static void tun_flow_uninit(struct tun_struct *tun) #define MAX_MTU 65535 /* Initialize net device. */ -static void tun_net_init(struct net_device *dev) +static void tun_net_initialize(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -2633,9 +2684,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!dev) return -ENOMEM; - err = dev_get_valid_name(net, dev, name); - if (err < 0) - goto err_free_dev; dev_net_set(dev, net); dev->rtnl_link_ops = &tun_link_ops; @@ -2654,42 +2702,17 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun->rx_batched = 0; RCU_INIT_POINTER(tun->steering_prog, NULL); - tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); - if (!tun->pcpu_stats) { - err = -ENOMEM; - goto err_free_dev; - } - - spin_lock_init(&tun->lock); - - err = security_tun_dev_alloc_security(&tun->security); - if (err < 0) - goto err_free_stat; - - tun_net_init(dev); - tun_flow_init(tun); - - dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | - TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX; - dev->features = dev->hw_features | NETIF_F_LLTX; - dev->vlan_features = dev->features & - ~(NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX); + tun->ifr = ifr; + tun->file = file; - tun->flags = (tun->flags & ~TUN_FEATURES) | - (ifr->ifr_flags & TUN_FEATURES); - - INIT_LIST_HEAD(&tun->disabled); - err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI, - ifr->ifr_flags & IFF_NAPI_FRAGS, false); - if (err < 0) - goto err_free_flow; + tun_net_initialize(dev); err = register_netdevice(tun->dev); - if (err < 0) - goto err_detach; - /* free_netdev() won't check refcnt, to aovid race + if (err < 0) { + free_netdev(dev); + return err; + } + /* free_netdev() won't check refcnt, to avoid race * with dev_put() we need publish tun after registration. */ rcu_assign_pointer(tfile->tun, tun); @@ -2707,20 +2730,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) strcpy(ifr->ifr_name, tun->dev->name); return 0; - -err_detach: - tun_detach_all(dev); - /* register_netdevice() already called tun_free_netdev() */ - goto err_free_dev; - -err_free_flow: - tun_flow_uninit(tun); - security_tun_dev_free_security(tun->security); -err_free_stat: - free_percpu(tun->pcpu_stats); -err_free_dev: - free_netdev(dev); - return err; } static void tun_get_iff(struct net *net, struct tun_struct *tun, -- 2.25.1

2 1

[PATCH OLK-5.10 v3] smart_grid: cpufreq: clear offline and isolated CPU in warm CPUs
by Yipeng Zou 11 Dec '23

11 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MFO6 CVE: NA ---------------------------------------- When there has some CPU has been offline or isolated, the warm zone CPUs will not clear these CPUs. Because of the warm zone were saluted by a complement of hot zone. So, we need to clear offline and isolated CPUs in every time's warm zone CPUs update. Fixes: 6a00891859d8 ("smart_grid: cpufreq: introduce smart_grid cpufreq control") Signed-off-by: Yipeng Zou <zouyipeng(a)huawei.com> Tested-by: jifa <jifa(a)huawei.com> --- kernel/sched/grid/qos.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/sched/grid/qos.c b/kernel/sched/grid/qos.c index f8c5deffd3ea..7ee3687347ce 100644 --- a/kernel/sched/grid/qos.c +++ b/kernel/sched/grid/qos.c @@ -179,6 +179,7 @@ int sched_grid_zone_update(bool is_locked) raw_spin_lock_irqsave(&sg_zone.lock, flags); cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_HOT]); + cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_WARM]); list_for_each(pos, &sg_zone.af_list_head) { af_pos = list_entry(pos, struct auto_affinity, af_list); @@ -190,10 +191,14 @@ int sched_grid_zone_update(bool is_locked) cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_HOT], &sg_zone.cpus[SMART_GRID_ZONE_HOT], af_pos->ad.domains[af_pos->ad.curr_level]); + /* Update warm zone CPUs to max level first */ + cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + af_pos->ad.domains[af_pos->ad.dcount - 1]); } - cpumask_complement(&sg_zone.cpus[SMART_GRID_ZONE_WARM], - &sg_zone.cpus[SMART_GRID_ZONE_HOT]); + /* Then reset warm zone CPUs without hot zone CPUs */ + cpumask_andnot(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + &sg_zone.cpus[SMART_GRID_ZONE_HOT]); if (!is_locked) raw_spin_unlock_irqrestore(&sg_zone.lock, flags); -- 2.34.1

2 1

[PATCH OLK-6.6 0/9] files cgroup enable
by chenridong 11 Dec '23

11 Dec '23

Binder Makin (1): cgroups: Resource controller for open files Hou Tao (1): cgroup/files: use task_get_css() to get a valid css during dup_fd() Lu Jialin (3): enable CONFIG_CGROUP_FILES in openeuler_defconfig for x86 and arm64 fs: fix files.usage bug when move tasks fs/filescontrol.c: fix warning:large integer implicitly truncated to unsigned type Yang Yingliang (1): cgroup/files: support boot parameter to control if disable files cgroup Yu Kuai (1): fs/filescontrol: add a switch to enable / disable accounting of open fds Zhang Xiaoxu (2): files_cgroup: fix error pointer when kvm_vm_worker_thread files_cgroup: Fix soft lockup when refcnt overflow. .../admin-guide/kernel-parameters.txt | 7 +- arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/Makefile | 1 + fs/file.c | 63 +++- fs/filescontrol.c | 312 ++++++++++++++++++ include/linux/cgroup-defs.h | 8 +- include/linux/cgroup_subsys.h | 6 + include/linux/fdtable.h | 1 + include/linux/filescontrol.h | 40 +++ init/Kconfig | 10 + 11 files changed, 442 insertions(+), 8 deletions(-) create mode 100644 fs/filescontrol.c create mode 100644 include/linux/filescontrol.h -- 2.34.1

2 10

[PATCH OLK-6.6 v4 0/7] Ascend features
by Yuan Can 11 Dec '23

11 Dec '23

Jian Zhang (1): memcontrol: Add oom recover for kmemcg when release buddy hugepage Navid Emamdoost (1): nbd_genl_status: null check for nla_nest_start Weilong Chen (2): ACPI / APEI: Notify all ras err to driver arm64/ascend: Add new enable_oom_killer interface for oom contrl Xu Qiang (2): irq-gic-v3: Add support to init ts core GICR irq-gic-v3-its: It can't be initialized when the GICR had been cut Yuan Can (1): ascend: export interfaces required by ascend drivers arch/arm64/configs/openeuler_defconfig | 1 + drivers/acpi/apei/Kconfig | 7 + drivers/acpi/apei/ghes.c | 8 +- drivers/block/nbd.c | 6 + drivers/irqchip/Kconfig | 10 + drivers/irqchip/irq-gic-v3-its.c | 254 ++++++++++++++++++++++++- drivers/irqchip/irq-gic-v3.c | 101 +++++++++- include/linux/irqchip/arm-gic-v3.h | 5 + include/linux/oom.h | 26 +++ kernel/power/autosleep.c | 1 + kernel/workqueue.c | 3 + mm/Kconfig | 10 + mm/memcontrol.c | 14 ++ mm/oom_kill.c | 58 ++++++ mm/util.c | 2 + mm/vmalloc.c | 2 + 16 files changed, 499 insertions(+), 9 deletions(-) -- 2.17.1

3 10

[PATCH OLK-6.6 0/4] backport nbd bugfix patch
by Li Nan 11 Dec '23

11 Dec '23

Li Nan (4): nbd: fold nbd config initialization into nbd_alloc_config() nbd: factor out a helper to get nbd_config without holding 'config_lock' nbd: fix null-ptr-dereference while accessing 'nbd->config' nbd: pass nbd_sock to nbd_read_reply() instead of index drivers/block/nbd.c | 117 ++++++++++++++++++++++++++++---------------- 1 file changed, 75 insertions(+), 42 deletions(-) -- 2.39.2

2 5

[PATCH OLK-6.6] cgroup: Support iocost for cgroup v1
by Li Nan 11 Dec '23

11 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8ND38 --------------------------- Since iocost can only be used in cgroup v2, add it to v1 now. Signed-off-by: Li Nan <linan122(a)huawei.com> --- block/blk-iocost.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 089fcb9cfce3..d0bdb286632f 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3490,6 +3490,28 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, return ret; } +static struct cftype ioc_legacy_files[] = { + { + .name = "cost.weight", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = ioc_weight_show, + .write = ioc_weight_write, + }, + { + .name = "cost.qos", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = ioc_qos_show, + .write = ioc_qos_write, + }, + { + .name = "cost.model", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = ioc_cost_model_show, + .write = ioc_cost_model_write, + }, + {} +}; + static struct cftype ioc_files[] = { { .name = "weight", @@ -3514,6 +3536,7 @@ static struct cftype ioc_files[] = { static struct blkcg_policy blkcg_policy_iocost = { .dfl_cftypes = ioc_files, + .legacy_cftypes = ioc_legacy_files, .cpd_alloc_fn = ioc_cpd_alloc, .cpd_free_fn = ioc_cpd_free, .pd_alloc_fn = ioc_pd_alloc, -- 2.39.2

2 1

[PATCH OLK-6.6 v2 0/1] Add config isolation for random initialization optimization
by GUO Zihua 11 Dec '23

11 Dec '23

This patch adds config isolating random bootup initialization optimization as it is required for all home-developed patches. v2: Fixed commit message. GUO Zihua (1): random: Added config for random boot optimization arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/char/random.c | 4 ++++ init/Kconfig | 11 +++++++++++ 4 files changed, 17 insertions(+) -- 2.34.1

2 2

[PATCH OLK-6.6 0/3] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (3): cgroup: Add cgroup1_get_from_id() cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 3 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 46 +++++++++- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 289 insertions(+), 9 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/1] Add config isolation for random initialization optimization
by GUO Zihua 11 Dec '23

11 Dec '23

This patch adds config isolating random bootup initialization optimization as it is required for all home-developed patches. GUO Zihua (1): random: Added config for random boot optimization arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + drivers/char/random.c | 4 ++++ init/Kconfig | 11 +++++++++++ 4 files changed, 17 insertions(+) -- 2.34.1

2 2

[PATCH OLK-6.6 v3 0/7] support userswap feature
by Peng Zhang 11 Dec '23

11 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ChangeLog: v2->v3: - update patch 7 commit v1->v2: - enable CONFIG_USERSWAP for openeuler_defconfig ZhangPeng (7): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg mm/userswap: openeuler_defconfig: enable userswap arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 +- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 +++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++ 18 files changed, 747 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

2 16

[PATCH OLK-6.6 v3 0/7] support userswap feature
by Peng Zhang 11 Dec '23

11 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ChangeLog: v2->v3: - update patch 7 commit v1->v2: - enable CONFIG_USERSWAP for openeuler_defconfig ZhangPeng (7): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg mm/userswap: openeuler_defconfig: enable userswap arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 +- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 +++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++ 18 files changed, 747 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

2 9

[PATCH OLK-6.6 v2 0/7] support userswap feature
by Peng Zhang 11 Dec '23

11 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ChangeLog: v1->v2: - enable CONFIG_USERSWAP for openeuler_defconfig ZhangPeng (7): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg mm/userswap: openeuler_defconfig: enable userswap arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 +- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 +++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++ 18 files changed, 747 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

2 16

[PATCH OLK-6.6 0/3] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (3): cgroup: deaggregate __cgroup1_get_from_id for cgroup v1, cgroup_get_from_id for cgrp_dfl_root cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 v3 0/8] memcg reclaim and cgroup kill
by Lu Jialin 11 Dec '23

11 Dec '23

Lu Jialin (8): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland memcg: introduce per-memcg reclaim interface config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +++- init/Kconfig | 10 ++ kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 184 ++++++++++++++++++++++++- 8 files changed, 229 insertions(+), 7 deletions(-) -- 2.34.1

2 9

[PATCH OLK-6.6 0/3] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (3): cgroup: deaggregate __cgroup1_get_from_id for cgroup v1, cgroup_get_from_id for cgrp_dfl_root cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

2 4

[PATCH v2 OLK-6.6 00/10] kabi: add kabi helper macros and tools
by Jialin Zhang 11 Dec '23

11 Dec '23

1. add kabi helper macros 2. add kabi tools: kabideps, kabisyms, check-kabi v1->v2: Move config entries of kabi to "General setup", and make CONFIG_KABI_SIZE_ALIGN_CHECKS depending on CONFIG_KABI_RESERVE. Li Lingfeng (1): kabi: deduplication friendly structs Xie XiuQi (5): kabi: add KABI_SIZE_ALIGN_CHECKS for more stringent kabi checks kabi: enables more stringent kabi checks kabi: add script tools to check kabi symbol kabi: add a tool to generate the kabi reference relationship kabi: add kABI reference checking tool Zheng Zengkai (4): kabi: add kabi helper macros KABI: Add CONFIG_KABI_RESERVE to control KABI padding reserve openeuler_defconfig: Enable CONFIG_KABI_RESERVE for x86 and arm64 kabi: Generalize naming of kabi helper macros arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/kabi.h | 509 +++++++++++++++++++++++++ init/Kconfig | 16 + scripts/check-kabi | 147 +++++++ scripts/kabideps | 161 ++++++++ scripts/kabisyms | 141 +++++++ 7 files changed, 978 insertions(+) create mode 100644 include/linux/kabi.h create mode 100755 scripts/check-kabi create mode 100755 scripts/kabideps create mode 100755 scripts/kabisyms -- 2.25.1

2 11

[PATHC OLK-6.6 v3 0/8] memcg reclaim and cgroup kill
by Lu Jialin 11 Dec '23

11 Dec '23

Lu Jialin (8): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland memcg: introduce per-memcg reclaim interface config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +++- init/Kconfig | 10 ++ kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 184 ++++++++++++++++++++++++- 8 files changed, 229 insertions(+), 7 deletions(-) -- 2.34.1

1 8

[PATCH v6 OLK-6.6 0/5] Support Qos Scheduler
by Wenyu Huang 11 Dec '23

11 Dec '23

Zhang Qiao (5): sched: Introduce qos scheduler for co-location sched: Throttle qos cfs_rq when current cpu is running online task sched: Support kill boost for offline task sched: Introduce handle priority reversion mechanism sched: Enable qos scheduler config arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/cgroup.h | 4 + include/linux/resume_user_mode.h | 5 + include/linux/sched.h | 11 + init/Kconfig | 12 + kernel/cgroup/cgroup.c | 22 ++ kernel/sched/core.c | 155 ++++++++++ kernel/sched/fair.c | 378 ++++++++++++++++++++++++- kernel/sched/sched.h | 12 + kernel/signal.c | 3 + 11 files changed, 603 insertions(+), 1 deletion(-) -- 2.34.1

2 6

[PATCH v2 OLK-5.10] iommu/arm-smmu-v3: Add a SYNC command to avoid broken page table prefetch
by Zhang Zekun 11 Dec '23

11 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8MVBZ CVE: NA ----------------------------------------------- On Hisilicon LINXICORE9100 cores, SMMU pagetable prefetch features may prefetch and use a invalid PTE even the PTE is valid at that time. This will cause the device trigger fake pagefaults. If the SMMU works in terminate mode, transactions which occur fake pagefaults will be aborted, and could result in unexpected errors. To fix this problem, we need to add a SYNC command after smmu has map a iova, then smmu will always try to get the newest PTE. Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- v2: - add a config to explictly set erratum config, no code logic change Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 13 +++++++++++++ arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cpucaps.h | 1 + arch/arm64/kernel/cpu_errata.c | 14 ++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 20 ++++++++++++++++++++ 6 files changed, 51 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index a9441bfebb0d..1f06e18a1859 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -156,6 +156,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | LINXICORE9100 | #162100125 | HISILICON_ERRATUM_162100125 | +----------------+-----------------+-----------------+-----------------------------+ +| Hisilicon | LINXICORE9100 | #162100602 | HISILICON_ERRATUM_162100602 | ++----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | HIP09 | #162102203 | HISILICON_ERRATUM_162102203 | +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c5eca65c27fc..851d24a35e4e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -836,6 +836,19 @@ config HISILICON_ERRATUM_162102203 If unsure, say N. +config HISILICON_ERRATUM_162100602 + bool "Hisilicon erratum 162100602" + depends on ARM_SMMU_V3 + default y + help + On Hisilicon LINXICORE9100 cores, SMMU pagetable prefetch features may + prefetch and use a invalid PTE even the PTE is valid at that time. This + will cause the device trigger fake pagefaults. If the SMMU works in + terminate mode, transactions which occur fake pagefaults will be aborted, + and could result in unexpected errors. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index edcb7911b3ce..261023a908a8 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -404,6 +404,7 @@ CONFIG_HISILICON_ERRATUM_1980005=y CONFIG_HISILICON_ERRATUM_162100801=y CONFIG_HISILICON_ERRATUM_162100125=y CONFIG_HISILICON_ERRATUM_162102203=y +CONFIG_HISILICON_ERRATUM_162100602=y CONFIG_QCOM_FALKOR_ERRATUM_1003=y CONFIG_QCOM_FALKOR_ERRATUM_1009=y CONFIG_QCOM_QDF2400_ERRATUM_0065=y diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index ce9fbf260a3c..0220f10cddd7 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -81,6 +81,7 @@ #define ARM64_HAS_PBHA_STAGE2 73 #define ARM64_SME 74 #define ARM64_SME_FA64 75 +#define ARM64_WORKAROUND_HISILICON_ERRATUM_162100602 76 #define ARM64_NCAPS 80 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 7f175b3aac15..6a3e948d5c2c 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -331,6 +331,13 @@ static const struct midr_range hisilicon_erratum_162100125_cpus[] = { }; #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static const struct midr_range hisilicon_erratum_162100602_cpus[] = { + MIDR_REV(MIDR_HISI_LINXICORE9100, 0, 0), + {}, +}; +#endif + #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 static const struct arm64_cpu_capabilities qcom_erratum_1003_list[] = { { @@ -533,6 +540,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100125_cpus), }, #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + { + .desc = "Hisilicon erratum 162100602", + .capability = ARM64_WORKAROUND_HISILICON_ERRATUM_162100602, + ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100602_cpus), + }, +#endif #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a55c2dab72f8..458151b7fab2 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2941,6 +2941,23 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, gather->pgsize, true, smmu_domain); } +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static void arm_smmu_iotlb_sync_map(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + size_t granule_size; + + if (!cpus_have_const_cap(ARM64_WORKAROUND_HISILICON_ERRATUM_162100602)) + return; + + granule_size = 1 << __ffs(smmu_domain->domain.pgsize_bitmap); + + /* Add a SYNC command to sync io-pgtale to avoid errors in pgtable prefetch*/ + arm_smmu_tlb_inv_range_domain(iova, granule_size, granule_size, true, smmu_domain); +} +#endif + static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -3970,6 +3987,9 @@ static struct iommu_ops arm_smmu_ops = { .unmap = arm_smmu_unmap, .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + .iotlb_sync_map = arm_smmu_iotlb_sync_map, +#endif .iova_to_phys = arm_smmu_iova_to_phys, .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, -- 2.17.1

2 1

[PATCH OLK-6.6 0/2] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (2): cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 v3] config: Open CONFIG_AARCH32_EL0 and keep CONFIG_ARM64_ILP32 closed
by Jinjie Ruan 11 Dec '23

11 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8JVJ3 CVE: NA ------------------------------------------------------------------------- No one currently uses IPL32, keep it closed to simplify the code logic of TASK_SIZE_MAX, thereby improving benchmark performance. For example, all test items of libMicro can be improved by 4.89% on average. Since commit dbece8b041f3 ("arm64: rename COMPAT to AARCH32_EL0"), CONFIG_COMPAT has been renamed to CONFIG_AARCH32_EL0, so open CONFIG_AARCH32_EL0 as what CONFIG_COMPAT used to be. And as commit 880fd21c0a46 ("arm64: set 32-bit compatible TASK_SIZE_MAX to fix U32 libc_write_01 error") said, not set CONFIG_COMPAT_TASK_SIZE by default. Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Liu Chao (CR) <liuchao173(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- v3: - Update the commit subject and message to make it clear. v2: - Do not touch the makeconfig.sh. --- arch/arm64/configs/openeuler_defconfig | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 9d2f717c1f7c..ce5a7aeaeeca 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -449,9 +449,10 @@ CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY=y # CONFIG_RODATA_FULL_DEFAULT_ENABLED is not set # CONFIG_ARM64_SW_TTBR0_PAN is not set CONFIG_ARM64_TAGGED_ADDR_ABI=y -CONFIG_COMPAT=y +CONFIG_AARCH32_EL0=y # CONFIG_KUSER_HELPERS is not set # CONFIG_COMPAT_ALIGNMENT_FIXUPS is not set +# CONFIG_COMPAT_TASK_SIZE is not set CONFIG_ARMV8_DEPRECATED=y CONFIG_SWP_EMULATION=y CONFIG_CP15_BARRIER_EMULATION=y @@ -526,6 +527,8 @@ CONFIG_EFI=y CONFIG_DMI=y # end of Boot options +CONFIG_COMPAT=y + # # Power management options # -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (2): cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] cgroup v1 writeback enable
by chenridong 11 Dec '23

11 Dec '23

Lu Jialin (2): cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/5] LoongArch: add cpufreq and ls2k500 bmc support
by Hongchen Zhang 11 Dec '23

11 Dec '23

Chong Qiao (4): fbdev: add ls2k500sfb driver for ls2k500 bmc. ipmi: add ls2k500 bmc ipmi support. LoongArch: defconfig: enable CONFIG_FB_LS2K500=m. LoongArch: fix ls2k500 bmc not work when installing iso liuyun (1): cpufreq: Add cpufreq driver for LoongArch arch/loongarch/Kconfig | 1 + arch/loongarch/configs/loongson3_defconfig | 5 + arch/loongarch/include/asm/fpu.h | 13 +- drivers/char/ipmi/Makefile | 4 + drivers/char/ipmi/btlock.h | 92 ++ drivers/char/ipmi/ipmi_si.h | 11 + drivers/char/ipmi/ipmi_si_intf.c | 4 + drivers/char/ipmi/ipmi_si_ls2k500.c | 173 +++ drivers/char/ipmi/kcs_bmc_ls2k500.h | 67 + drivers/cpufreq/Kconfig | 11 + drivers/cpufreq/Makefile | 1 + drivers/cpufreq/loongson3-acpi-cpufreq.c | 1527 ++++++++++++++++++++ drivers/gpu/drm/loongson/loongson_module.c | 15 + drivers/video/fbdev/Kconfig | 13 + drivers/video/fbdev/Makefile | 1 + drivers/video/fbdev/ls2k500sfb.c | 792 ++++++++++ 16 files changed, 2729 insertions(+), 1 deletion(-) create mode 100644 drivers/char/ipmi/btlock.h create mode 100644 drivers/char/ipmi/ipmi_si_ls2k500.c create mode 100644 drivers/char/ipmi/kcs_bmc_ls2k500.h create mode 100644 drivers/cpufreq/loongson3-acpi-cpufreq.c create mode 100644 drivers/video/fbdev/ls2k500sfb.c -- 2.33.0

2 6

[PATCH 0/5] LoongArch: add cpufreq and ls2k500 bmc support
by Hongchen Zhang 11 Dec '23

11 Dec '23

Chong Qiao (4): fbdev: add ls2k500sfb driver for ls2k500 bmc. ipmi: add ls2k500 bmc ipmi support. LoongArch: defconfig: enable CONFIG_FB_LS2K500=m. LoongArch: fix ls2k500 bmc not work when installing iso liuyun (1): cpufreq: Add cpufreq driver for LoongArch arch/loongarch/Kconfig | 1 + arch/loongarch/configs/loongson3_defconfig | 5 + arch/loongarch/include/asm/fpu.h | 13 +- drivers/char/ipmi/Makefile | 4 + drivers/char/ipmi/btlock.h | 92 ++ drivers/char/ipmi/ipmi_si.h | 11 + drivers/char/ipmi/ipmi_si_intf.c | 4 + drivers/char/ipmi/ipmi_si_ls2k500.c | 173 +++ drivers/char/ipmi/kcs_bmc_ls2k500.h | 67 + drivers/cpufreq/Kconfig | 11 + drivers/cpufreq/Makefile | 1 + drivers/cpufreq/loongson3-acpi-cpufreq.c | 1527 ++++++++++++++++++++ drivers/gpu/drm/loongson/loongson_module.c | 15 + drivers/video/fbdev/Kconfig | 13 + drivers/video/fbdev/Makefile | 1 + drivers/video/fbdev/ls2k500sfb.c | 792 ++++++++++ 16 files changed, 2729 insertions(+), 1 deletion(-) create mode 100644 drivers/char/ipmi/btlock.h create mode 100644 drivers/char/ipmi/ipmi_si_ls2k500.c create mode 100644 drivers/char/ipmi/kcs_bmc_ls2k500.h create mode 100644 drivers/cpufreq/loongson3-acpi-cpufreq.c create mode 100644 drivers/video/fbdev/ls2k500sfb.c -- 2.33.0

1 5

[PATCH OLK-5.10] smart_grid: cpufreq: clear offline and isolated CPU in warm CPUs
by Yipeng Zou 11 Dec '23

11 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MFO6 CVE: NA ---------------------------------------- When there has some CPU has been offline or isolated, the warm zone CPUs will not clear these CPUs. Because of the warm zone were saluted by a complement of hot zone. So, we need to clear offline and isolated CPUs in every time's warm zone CPUs update. Fixes: 6a00891859d8 ("smart_grid: cpufreq: introduce smart_grid cpufreq control") Signed-off-by: Yipeng Zou <zouyipeng(a)huawei.com> --- kernel/sched/grid/qos.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/sched/grid/qos.c b/kernel/sched/grid/qos.c index f8c5deffd3ea..7ee3687347ce 100644 --- a/kernel/sched/grid/qos.c +++ b/kernel/sched/grid/qos.c @@ -179,6 +179,7 @@ int sched_grid_zone_update(bool is_locked) raw_spin_lock_irqsave(&sg_zone.lock, flags); cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_HOT]); + cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_WARM]); list_for_each(pos, &sg_zone.af_list_head) { af_pos = list_entry(pos, struct auto_affinity, af_list); @@ -190,10 +191,14 @@ int sched_grid_zone_update(bool is_locked) cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_HOT], &sg_zone.cpus[SMART_GRID_ZONE_HOT], af_pos->ad.domains[af_pos->ad.curr_level]); + /* Update warm zone CPUs to max level first */ + cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + af_pos->ad.domains[af_pos->ad.dcount - 1]); } - cpumask_complement(&sg_zone.cpus[SMART_GRID_ZONE_WARM], - &sg_zone.cpus[SMART_GRID_ZONE_HOT]); + /* Then reset warm zone CPUs without hot zone CPUs */ + cpumask_andnot(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + &sg_zone.cpus[SMART_GRID_ZONE_HOT]); if (!is_locked) raw_spin_unlock_irqrestore(&sg_zone.lock, flags); -- 2.34.1

2 1

[PATCH OLK-6.6 0/4]cgroupv1 enable writeback
by chenridong 10 Dec '23

10 Dec '23

Lu Jialin (3): cgroup: Add cgroup1_get_from_id() cgroup: support cgroup writeback on cgroupv1 openeuler_defconfig: enable CONFIG_CGROUP_V1_WRITEBACK in openeuler_defconfig for x86 and arm64 chenridong (1): drop cgroup1_get_from_id, unify cgroup_get_from_id arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + block/blk-cgroup.c | 3 + block/blk-cgroup.h | 3 + include/linux/backing-dev.h | 29 +++++- include/linux/cgroup-defs.h | 2 + include/linux/cgroup.h | 1 + include/linux/memcontrol.h | 5 ++ init/Kconfig | 5 ++ kernel/cgroup/cgroup.c | 28 ++++-- mm/backing-dev.c | 117 ++++++++++++++++++++++++- mm/memcontrol.c | 83 +++++++++++++++++- 12 files changed, 264 insertions(+), 14 deletions(-) -- 2.34.1

3 6

[PATCH V2 OLK-5.10 0/6] Make the rcache depot scale better
by Zhang Zekun 10 Dec '23

10 Dec '23

Recently we have meet a problem when running FIO test. In our kunpeng server with 320 cores, about 80% cpus comes to- 100% usage, and soft lockup appears in the kernel message, which shows it stuck in __alloc_and_insert_iova_range(). Both the call trace and high cpu occupy rate implys that the iova_rcache behaves poorly to alloc iovas. A similar problem has been addressed in early months this year, the solution is just to enlarge the MAX_GLOBAL_MAGS to 128, but it requires to growth with the cpu cores, and it is hard to set a accurate val for a specific machine. So, it is better to use solutions from the linux community, use a list to replace the array of iova_rcache->depot. It will push iova_magazine to depot list when the local cpu_rcache is full, and use schedul_delayed_work() to free it after 100ms. The minimum length of the depot list is the num of online_cpus(). The performance of this patch shows good. This patch set use a lot of timers to record the iova_magazine, and the delay of timers in system may increase when undering heavy work load, but it should not cause problem as timers itself allows a inaccurate delay for a range. v2: - change a comment in patch 5/6, no code change. We need to merge "iommu/iova: change IOVA_MAG_SIZE to 127 to save memory" first to resolve a compile error: error: static assertion failed: "!(sizeof(struct iova_magazine) & (sizeof(struct iova_magazine) - 1))" Feng Tang (1): iommu/iova: change IOVA_MAG_SIZE to 127 to save memory Zhang Zekun (5): Revert "iommu/iova: move IOVA_MAX_GLOBAL_MAGS outside of IOMMU_SUPPORT" Revert "config: enable set the max iova mag size to 128" Revert "iommu/iova: increase the iova_rcache depot max size to 128" iommu/iova: Make the rcache depot scale better iommu/iova: Manage the depot list size arch/arm64/configs/openeuler_defconfig | 1 - drivers/iommu/Kconfig | 10 ---- drivers/iommu/iova.c | 80 +++++++++++++++++++------- include/linux/iova.h | 7 ++- 4 files changed, 64 insertions(+), 34 deletions(-) -- 2.17.1

2 7

[PATCH OLK-5.10] iommu/arm-smmu-v3: Add a SYNC command to avoid broken page table prefetch
by Zhang Zekun 10 Dec '23

10 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8MVBZ CVE: NA ----------------------------------------------- On Hisilicon LINXICORE9100 cores, SMMU pagetable prefetch features may prefetch and use a invalid PTE even the PTE is valid at that time. This will cause the device trigger fake pagefaults. If the SMMU works in terminate mode, transactions which occur fake pagefaults will be aborted, and could result in unexpected errors. To fix this problem, we need to add a SYNC command after smmu has map a iova, then smmu will always try to get the newest PTE. Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 13 +++++++++++++ arch/arm64/include/asm/cpucaps.h | 1 + arch/arm64/kernel/cpu_errata.c | 14 ++++++++++++++ drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 20 ++++++++++++++++++++ 5 files changed, 50 insertions(+) diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index a9441bfebb0d..1f06e18a1859 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -156,6 +156,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | LINXICORE9100 | #162100125 | HISILICON_ERRATUM_162100125 | +----------------+-----------------+-----------------+-----------------------------+ +| Hisilicon | LINXICORE9100 | #162100602 | HISILICON_ERRATUM_162100602 | ++----------------+-----------------+-----------------+-----------------------------+ | Hisilicon | HIP09 | #162102203 | HISILICON_ERRATUM_162102203 | +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c5eca65c27fc..851d24a35e4e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -836,6 +836,19 @@ config HISILICON_ERRATUM_162102203 If unsure, say N. +config HISILICON_ERRATUM_162100602 + bool "Hisilicon erratum 162100602" + depends on ARM_SMMU_V3 + default y + help + On Hisilicon LINXICORE9100 cores, SMMU pagetable prefetch features may + prefetch and use a invalid PTE even the PTE is valid at that time. This + will cause the device trigger fake pagefaults. If the SMMU works in + terminate mode, transactions which occur fake pagefaults will be aborted, + and could result in unexpected errors. + + If unsure, say Y. + config QCOM_FALKOR_ERRATUM_1003 bool "Falkor E1003: Incorrect translation due to ASID change" default y diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index ce9fbf260a3c..0220f10cddd7 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -81,6 +81,7 @@ #define ARM64_HAS_PBHA_STAGE2 73 #define ARM64_SME 74 #define ARM64_SME_FA64 75 +#define ARM64_WORKAROUND_HISILICON_ERRATUM_162100602 76 #define ARM64_NCAPS 80 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 7f175b3aac15..6a3e948d5c2c 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -331,6 +331,13 @@ static const struct midr_range hisilicon_erratum_162100125_cpus[] = { }; #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static const struct midr_range hisilicon_erratum_162100602_cpus[] = { + MIDR_REV(MIDR_HISI_LINXICORE9100, 0, 0), + {}, +}; +#endif + #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 static const struct arm64_cpu_capabilities qcom_erratum_1003_list[] = { { @@ -533,6 +540,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100125_cpus), }, #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + { + .desc = "Hisilicon erratum 162100602", + .capability = ARM64_WORKAROUND_HISILICON_ERRATUM_162100602, + ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100602_cpus), + }, +#endif #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index a55c2dab72f8..458151b7fab2 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -2941,6 +2941,23 @@ static void arm_smmu_iotlb_sync(struct iommu_domain *domain, gather->pgsize, true, smmu_domain); } +#ifdef CONFIG_HISILICON_ERRATUM_162100602 +static void arm_smmu_iotlb_sync_map(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + size_t granule_size; + + if (!cpus_have_const_cap(ARM64_WORKAROUND_HISILICON_ERRATUM_162100602)) + return; + + granule_size = 1 << __ffs(smmu_domain->domain.pgsize_bitmap); + + /* Add a SYNC command to sync io-pgtale to avoid errors in pgtable prefetch*/ + arm_smmu_tlb_inv_range_domain(iova, granule_size, granule_size, true, smmu_domain); +} +#endif + static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { @@ -3970,6 +3987,9 @@ static struct iommu_ops arm_smmu_ops = { .unmap = arm_smmu_unmap, .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, +#ifdef CONFIG_HISILICON_ERRATUM_162100602 + .iotlb_sync_map = arm_smmu_iotlb_sync_map, +#endif .iova_to_phys = arm_smmu_iova_to_phys, .probe_device = arm_smmu_probe_device, .release_device = arm_smmu_release_device, -- 2.17.1

2 1

[PATCH OLK-6.6 0/6] support userswap feature
by Peng Zhang 10 Dec '23

10 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ZhangPeng (6): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 ++- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 ++++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++++++++ 16 files changed, 745 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

2 14

[PATCH OLK-6.6 0/6] support userswap feature
by Peng Zhang 10 Dec '23

10 Dec '23

From: ZhangPeng <zhangpeng362(a)huawei.com> This patch series support userswap feature including registration, unregistration, swap-out and swap-in. Userswap feature depends on CONFIG_USERSWAP and can be enabled by cmdline enable_userswap. We tested the concurrent scenario of multi-threaded page fault and multi-threaded swap-in in the uswap demo;and the remapping in the swap-out phase and the copy-free function in the swap-in phase were ok. During the test, related debugging functions including CONFIG_DEBUG_VM, lockdep, slub debug, kasan and kmemleak are enabled. ZhangPeng (6): mm/userswap: add VM_USWAP and SWP_USERSWAP_ENTRY mm/userswap: add enable_userswap boot option mm/userswap: introduce MREMAP_USWAP_SET_PTE mm/userswap: support userswap via userfaultfd mm/userswap: introduce UFFDIO_COPY_MODE_DIRECT_MAP mm/userswap: provide cpu info in userfault msg fs/proc/task_mmu.c | 3 + fs/userfaultfd.c | 43 ++- include/linux/mm.h | 8 + include/linux/swap.h | 14 +- include/linux/swapops.h | 16 + include/linux/userfaultfd_k.h | 5 + include/linux/userswap.h | 60 ++++ include/trace/events/mmflags.h | 7 + include/uapi/linux/mman.h | 1 + include/uapi/linux/userfaultfd.h | 3 + mm/Kconfig | 10 + mm/Makefile | 1 + mm/memory.c | 8 + mm/mremap.c | 8 +- mm/userfaultfd.c | 12 + mm/userswap.c | 552 +++++++++++++++++++++++++++++++ 16 files changed, 745 insertions(+), 6 deletions(-) create mode 100644 include/linux/userswap.h create mode 100644 mm/userswap.c -- 2.25.1

1 9

[PATCH OLK-6.6 v2 0/8] memcg reclaim and cgroup kill
by Lu Jialin 09 Dec '23

09 Dec '23

Chen Wandun (1): memcg: introduce per-memcg reclaim interface for cgroup v1 Lu Jialin (7): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events{local} from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +- init/Kconfig | 10 + kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 471 +++++++++++++++++-------- 8 files changed, 369 insertions(+), 154 deletions(-) -- 2.34.1

2 9

[PATCH OLK-6.6 v2 0/8] memcg reclaim and cgroup kill
by Lu Jialin 09 Dec '23

09 Dec '23

Chen Wandun (1): memcg: introduce per-memcg reclaim interface for cgroup v1 Lu Jialin (7): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events and memory.events.local from cgroupv2 to cgroupv1 memcg: enable memcg async reclaim memcg: export high_async_ratio to userland config: enable CONFIG_MEMCG_V1_RECLAIM and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +- init/Kconfig | 10 + kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 471 +++++++++++++++++-------- 8 files changed, 369 insertions(+), 154 deletions(-) -- 2.34.1

2 9

[PATCH OLK-6.6 000/134] Backport 6.6.5 LTS Patches
by Zheng Zengkai 09 Dec '23

09 Dec '23

Backport linux-6.6.5 LTS patches from upstream. git cherry-pick v6.6.4..v6.6.5~1 -s No conflicts. Build and boot test passed. Abdul Halim, Mohd Syazwan (1): iommu/vt-d: Add MTL to quirk list to skip TE disabling Adrian Hunter (6): mmc: cqhci: Increase recovery halt timeout mmc: cqhci: Warn of halt or task clear failure mmc: cqhci: Fix task clearing in CQE error recovery mmc: block: Retry commands in CQE error recovery mmc: block: Do not lose cache flush during CQE error recovery mmc: block: Be sure to wait while busy in CQE error recovery Agustin Gutierrez (1): drm/amd/display: Remove power sequencing check Alex Sierra (1): drm/amdgpu: Force order between a read and write to the same address Alvin Lee (2): drm/amd/display: Include udelay when waiting for INBOX0 ACK drm/amd/display: Use DRAM speed from validation for dummy p-state Antonio Borneo (1): pinctrl: stm32: fix array read out of bound Ayush Jain (1): cpufreq/amd-pstate: Only print supported EPP values for performance governor Bragatheswaran Manickavel (1): btrfs: ref-verify: fix memory leaks in btrfs_ref_tree_mod() Brett Creeley (2): vfio/pds: Fix mutex lock->magic != lock warning vfio/pds: Fix possible sleep while in atomic context Camille Cho (1): drm/amd/display: Simplify brightness initialization Candice Li (1): drm/amdgpu: Update EEPROM I2C address for smu v13_0_0 Chen Ni (1): pinctrl: stm32: Add check for devm_kcalloc Christian König (1): dma-buf: fix check in dma_resv_add_fence Christoph Niedermaier (1): cpufreq: imx6q: Don't disable 792 Mhz OPP unnecessarily Claudiu Beznea (6): net: ravb: Check return value of reset_control_deassert() net: ravb: Use pm_runtime_resume_and_get() net: ravb: Make write access to CXR35 first before accessing other EMAC registers net: ravb: Start TX queues after HW initialization succeeded net: ravb: Stop DMA in case of failures on ravb_open() net: ravb: Keep reverse order of operations in ravb_remove() Damien Le Moal (2): scsi: Change SCSI device boolean fields to single bit flags scsi: sd: Fix system start for ATA devices Dan Carpenter (2): media: v4l2-subdev: Fix a 64bit bug wifi: iwlwifi: mvm: fix an error code in iwl_mvm_mld_add_sta() Daniel Mentz (1): iommu: Fix printk arg in of_iommu_get_resv_regions() Dave Airlie (1): nouveau: find the smallest page allocation to cover a buffer alloc. Dave Ertman (1): ice: Fix VF Reset paths when interface in a failed over aggregate David Howells (2): cifs: Fix FALLOC_FL_ZERO_RANGE by setting i_size if EOF moved cifs: Fix FALLOC_FL_INSERT_RANGE by setting i_size after EOF moved David Sterba (1): btrfs: fix 64bit compat send ioctl arguments not initializing version member Dinghao Liu (1): drm/amd/pm: fix a memleak in aldebaran_tables_init Dmitry Antipov (1): uapi: propagate __struct_group() attributes to the container union Elena Salomatkina (1): octeontx2-af: Fix possible buffer overflow Ewan D. Milne (1): nvme: check for valid nvme_identify_ns() before using it Filipe Manana (2): btrfs: fix off-by-one when checking chunk map includes logical address btrfs: make error messages more clear when getting a chunk map Furong Xu (1): net: stmmac: xgmac: Disable FPE MMC interrupts Gaurav Batra (1): powerpc/pseries/iommu: enable_ddw incorrectly returns direct mapping for SR-IOV device Gautham R. Shenoy (1): cpufreq/amd-pstate: Fix the return value of amd_pstate_fast_switch() Geetha sowjanya (1): octeontx2-pf: Fix adding mbox work queue entry when num_vfs > 64 Greg Ungerer (2): net: dsa: mv88e6xxx: fix marvell 6350 switch probing net: dsa: mv88e6xxx: fix marvell 6350 probe crash Gustavo A. R. Silva (1): neighbour: Fix __randomize_layout crash in struct neighbour Hamza Mahfooz (1): drm/amd/display: fix ABM disablement Hans de Goede (1): ACPI: video: Use acpi_video_device for cooling-dev driver data Heiko Carstens (1): s390/cmma: fix handling of swapper_pg_dir and invalid_pg_dir Heiner Kallweit (2): r8169: fix deadlock on RTL8125 in jumbo mtu mode r8169: prevent potential deadlock in rtl8169_close Helge Deller (8): parisc: Mark ex_table entries 32-bit aligned in assembly.h parisc: Mark ex_table entries 32-bit aligned in uaccess.h parisc: Use natural CPU alignment for bug_table parisc: Mark lock_aligned variables 16-byte aligned on SMP parisc: Drop the HP-UX ENOSYM and EREMOTERELEASE error codes parisc: Mark jump_table naturally aligned parisc: Ensure 32-bit alignment on parisc unwind section parisc: Mark altinstructions read-only and 32-bit aligned Hou Tao (1): bpf: Add missed allocation hint for bpf_mem_cache_alloc_flags() Ian Chen (1): drm/amd/display: Refactor edp power control Ilya Bakoulin (1): drm/amd/display: Fix MPCC 1DLUT programming Ioana Ciornei (2): dpaa2-eth: increase the needed headroom to account for alignment dpaa2-eth: recycle the RX buffer only after all processing done Jakub Kicinski (1): ethtool: don't propagate EOPNOTSUPP from dumps Jann Horn (1): btrfs: send: ensure send_fd is writable Jens Axboe (6): io_uring: don't allow discontig pages for IORING_SETUP_NO_MMAP io_uring: free io_buffer_list entries via RCU io_uring: don't guard IORING_OFF_PBUF_RING with SETUP_NO_MMAP io_uring: enable io_mem_alloc/free to be used in other parts io_uring/kbuf: defer release of mapped buffer rings io_uring/kbuf: recycle freed mapped buffer ring entries Jiawen Wu (1): net: libwx: fix memory leak on msix entry Johannes Berg (1): wifi: cfg80211: fix CQM for non-range use John Fastabend (1): bpf, sockmap: af_unix stream sockets need to hold ref for pair sock Juergen Gross (1): x86/xen: fix percpu vcpu_info allocation Kailang Yang (2): ALSA: hda/realtek: Headset Mic VREF to 100% ALSA: hda/realtek: Add supported ALC257 for ChromeOS Kornel Dulęba (1): mmc: sdhci-pci-gli: Disable LPM during initialization Lu Baolu (4): iommu/vt-d: Fix incorrect cache invalidation for mm notification iommu/vt-d: Omit devTLB invalidation requests when TES=0 iommu/vt-d: Disable PCI ATS in legacy passthrough mode iommu/vt-d: Make context clearing consistent with context mapping Lukasz Luba (1): powercap: DTPM: Fix unneeded conversions to micro-Watts Maria Yu (1): pinctrl: avoid reload of p state in list iteration Mario Limonciello (1): drm/amd: Enable PCIe PME from D3 Markus Weippert (1): bcache: revert replacing IS_ERR_OR_NULL with IS_ERR Michael Roth (1): efi/unaccepted: Fix off-by-one when checking for overlapping ranges Mikulas Patocka (1): dm-verity: align struct dm_verity_fec_io properly Namjae Jeon (1): ksmbd: fix possible deadlock in smb2_open Nicholas Kazlauskas (2): drm/amd/display: Remove min_dst_y_next_start check for Z8 drm/amd/display: Update min Z8 residency time to 2100 for DCN314 Nicholas Piggin (1): KVM: PPC: Book3S HV: Fix KVM_RUN clobbering FP/VEC user registers Oldřich Jedlička (1): wifi: mac80211: do not pass AP_VLAN vif pointer to drivers during flush Paulo Alcantara (2): smb: client: fix missing mode bits for SMB symlinks smb: client: report correct st_size for SMB and NFS symlinks Peter Wang (1): scsi: ufs: core: Clear cmd if abort succeeds in MCQ mode Prike Liang (1): drm/amdgpu: correct the amdgpu runtime dereference usage count Qu Wenruo (2): btrfs: add dmesg output for first mount and last unmount of a filesystem btrfs: free the allocated memory if btrfs_alloc_page_array() fails Ritesh Harjani (IBM) (1): ext2: Fix ki_pos update for DIO buffered-io fallback case Robin Murphy (1): iommu: Avoid more races around device probe Sean Christopherson (1): vfio: Drop vfio_file_iommu_group() stub to fudge around a KVM wart Sherry Wang (1): drm/amd/display: refactor ILR to make it work Stanislav Fomichev (1): netdevsim: Don't accept device bound programs Subbaraya Sundeep (1): octeontx2-pf: Restore TC ingress police rules when interface is up Swapnil Patel (1): drm/amd/display: Reduce default backlight min from 5 nits to 1 nits Takashi Iwai (2): leds: class: Don't expose color sysfs entry ALSA: hda: Disable power-save on KONTRON SinglePC Tim Huang (1): drm/amdgpu: fix memory overflow in the IB test Timothy Pearson (1): powerpc: Don't clobber f0/vs0 during fp|altivec register save Tvrtko Ursulin (1): drm/i915/gsc: Mark internal GSC engine with reserved uabi class Ville Syrjälä (1): drm/i915: Also check for VGA converter in eDP probe Wenchao Chen (1): mmc: sdhci-sprd: Fix vqmmc not shutting down after the card was pulled Willem de Bruijn (4): selftests/net: ipsec: fix constant out of range selftests/net: fix a char signedness issue selftests/net: unix: fix unused variable compiler warning selftests/net: mptcp: fix uninitialized variable warnings Wu Bo (2): dm verity: initialize fec io before freeing it dm verity: don't perform FEC for failed readahead IO Wyes Karny (1): cpufreq/amd-pstate: Fix scaling_min_freq and scaling_max_freq update Yang Yingliang (2): firewire: core: fix possible memory leak in create_units() drm/panel: nt36523: fix return value check in nt36523_probe() Yoshihiro Shimoda (4): net: rswitch: Fix type of ret in rswitch_start_xmit() net: rswitch: Fix return value in rswitch_start_xmit() net: rswitch: Fix missing dev_kfree_skb_any() in error path ravb: Fix races between ravb_tx_timeout_work() and net related ops Zhengchao Shao (1): ipv4: igmp: fix refcnt uaf issue when receiving igmp query packet Zhongwei (1): drm/amd/display: force toggle rate wa for first link training for a retimer xiazhengqiao (1): drm/panel: starry-2081101qfh032011-53g: Fine tune the panel power sequence Documentation/ABI/testing/sysfs-class-led | 9 - arch/parisc/include/asm/alternative.h | 9 +- arch/parisc/include/asm/assembly.h | 1 + arch/parisc/include/asm/bug.h | 30 ++-- arch/parisc/include/asm/jump_label.h | 8 +- arch/parisc/include/asm/ldcw.h | 2 +- arch/parisc/include/asm/uaccess.h | 1 + arch/parisc/include/uapi/asm/errno.h | 2 - arch/parisc/kernel/vmlinux.lds.S | 1 + arch/powerpc/kernel/fpu.S | 13 ++ arch/powerpc/kernel/process.c | 6 +- arch/powerpc/kernel/vector.S | 2 + arch/powerpc/platforms/pseries/iommu.c | 8 +- arch/s390/mm/page-states.c | 6 + arch/x86/xen/enlighten.c | 6 +- arch/x86/xen/xen-ops.h | 2 +- drivers/acpi/acpi_video.c | 14 +- drivers/acpi/scan.c | 7 +- drivers/ata/libata-scsi.c | 9 +- drivers/cpufreq/amd-pstate.c | 71 ++++++-- drivers/cpufreq/imx6q-cpufreq.c | 2 +- drivers/dma-buf/dma-resv.c | 2 +- drivers/firewire/core-device.c | 11 +- drivers/firewire/sbp2.c | 6 +- drivers/firmware/efi/unaccepted_memory.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 9 +- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 + .../gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 6 + drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 10 +- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 4 +- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 8 +- drivers/gpu/drm/amd/display/dc/core/dc.c | 21 +++ drivers/gpu/drm/amd/display/dc/dc.h | 5 +- drivers/gpu/drm/amd/display/dc/dc_stream.h | 1 - drivers/gpu/drm/amd/display/dc/dc_types.h | 4 - .../display/dc/dce110/dce110_hw_sequencer.c | 2 +- .../drm/amd/display/dc/dcn314/dcn314_hwseq.c | 3 +- .../amd/display/dc/dcn314/dcn314_resource.c | 2 +- .../drm/amd/display/dc/dcn32/dcn32_hwseq.c | 6 +- .../drm/amd/display/dc/dml/dcn20/dcn20_fpu.c | 15 +- .../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 3 +- drivers/gpu/drm/amd/display/dc/inc/link.h | 1 + .../drm/amd/display/dc/link/link_detection.c | 8 +- .../gpu/drm/amd/display/dc/link/link_dpms.c | 11 +- .../drm/amd/display/dc/link/link_factory.c | 1 + .../dc/link/protocols/link_dp_capability.c | 14 +- .../display/dc/link/protocols/link_dp_phy.c | 3 +- .../link_dp_training_fixed_vs_pe_retimer.c | 6 +- .../link/protocols/link_edp_panel_control.c | 62 +++++-- .../link/protocols/link_edp_panel_control.h | 4 +- .../gpu/drm/amd/display/dmub/src/dmub_srv.c | 1 + .../include/asic_reg/gc/gc_11_0_0_offset.h | 2 + .../drm/amd/pm/swsmu/smu13/aldebaran_ppt.c | 5 +- drivers/gpu/drm/i915/display/intel_dp.c | 28 ++- drivers/gpu/drm/i915/gt/intel_engine_user.c | 39 ++-- drivers/gpu/drm/nouveau/nouveau_bo.c | 5 +- .../gpu/drm/panel/panel-boe-tv101wum-nl6.c | 1 + drivers/gpu/drm/panel/panel-novatek-nt36523.c | 4 +- drivers/iommu/intel/dmar.c | 18 ++ drivers/iommu/intel/iommu.c | 9 +- drivers/iommu/intel/svm.c | 26 +++ drivers/iommu/iommu.c | 20 +-- drivers/iommu/of_iommu.c | 14 +- drivers/leds/led-class.c | 14 -- drivers/md/bcache/btree.c | 2 +- drivers/md/dm-verity-fec.c | 3 +- drivers/md/dm-verity-target.c | 7 +- drivers/md/dm-verity.h | 6 - drivers/mmc/core/block.c | 2 + drivers/mmc/core/core.c | 9 +- drivers/mmc/host/cqhci-core.c | 44 ++--- drivers/mmc/host/sdhci-pci-gli.c | 54 +++--- drivers/mmc/host/sdhci-sprd.c | 25 +++ drivers/net/dsa/mv88e6xxx/chip.c | 26 ++- .../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 16 +- .../net/ethernet/freescale/dpaa2/dpaa2-eth.h | 2 +- drivers/net/ethernet/intel/ice/ice_lag.c | 122 +++++++------ drivers/net/ethernet/intel/ice/ice_lag.h | 1 + drivers/net/ethernet/intel/ice/ice_vf_lib.c | 20 +++ drivers/net/ethernet/intel/ice/ice_virtchnl.c | 25 +++ .../ethernet/marvell/octeontx2/af/rvu_nix.c | 4 +- .../ethernet/marvell/octeontx2/nic/cn10k.c | 3 + .../marvell/octeontx2/nic/otx2_common.h | 2 + .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 9 +- .../ethernet/marvell/octeontx2/nic/otx2_tc.c | 120 ++++++++++--- drivers/net/ethernet/realtek/r8169_main.c | 9 +- drivers/net/ethernet/renesas/ravb_main.c | 69 ++++--- drivers/net/ethernet/renesas/rswitch.c | 22 ++- .../net/ethernet/stmicro/stmmac/mmc_core.c | 4 + drivers/net/ethernet/wangxun/libwx/wx_lib.c | 2 +- drivers/net/netdevsim/bpf.c | 4 +- .../net/wireless/intel/iwlwifi/mvm/mld-sta.c | 4 +- drivers/nvme/host/core.c | 9 + drivers/pinctrl/core.c | 6 +- drivers/pinctrl/stm32/pinctrl-stm32.c | 13 +- drivers/powercap/dtpm_cpu.c | 6 +- drivers/powercap/dtpm_devfreq.c | 11 +- drivers/scsi/sd.c | 9 +- drivers/ufs/core/ufshcd.c | 13 ++ drivers/vfio/pci/pds/pci_drv.c | 4 +- drivers/vfio/pci/pds/vfio_dev.c | 30 +++- drivers/vfio/pci/pds/vfio_dev.h | 2 +- fs/btrfs/disk-io.c | 1 + fs/btrfs/extent_io.c | 11 +- fs/btrfs/ioctl.c | 1 + fs/btrfs/ref-verify.c | 2 + fs/btrfs/send.c | 2 +- fs/btrfs/super.c | 5 +- fs/btrfs/volumes.c | 9 +- fs/ext2/file.c | 1 - fs/smb/client/inode.c | 4 +- fs/smb/client/smb2ops.c | 13 +- fs/smb/server/smb2pdu.c | 47 +++-- fs/smb/server/smbacl.c | 7 +- fs/smb/server/smbacl.h | 2 +- fs/smb/server/vfs.c | 68 ++++--- fs/smb/server/vfs.h | 10 +- include/linux/amd-pstate.h | 4 + include/linux/dma-fence.h | 15 ++ include/linux/io_uring_types.h | 3 + include/linux/iommu.h | 1 + include/linux/skmsg.h | 1 + include/linux/vfio.h | 8 +- include/net/af_unix.h | 1 + include/net/neighbour.h | 2 +- include/scsi/scsi_device.h | 12 +- include/uapi/linux/stddef.h | 2 +- include/uapi/linux/v4l2-subdev.h | 2 +- io_uring/io_uring.c | 59 +++--- io_uring/io_uring.h | 3 + io_uring/kbuf.c | 169 +++++++++++++++--- io_uring/kbuf.h | 5 + kernel/bpf/memalloc.c | 2 + lib/errname.c | 6 - net/core/skmsg.c | 2 + net/ethtool/netlink.c | 1 + net/ipv4/igmp.c | 6 +- net/mac80211/driver-ops.h | 9 +- net/unix/af_unix.c | 2 - net/unix/unix_bpf.c | 5 + net/wireless/core.h | 1 + net/wireless/nl80211.c | 50 ++++-- sound/pci/hda/hda_intel.c | 2 + sound/pci/hda/patch_realtek.c | 12 ++ tools/arch/parisc/include/uapi/asm/errno.h | 2 - .../testing/selftests/net/af_unix/diag_uid.c | 1 - tools/testing/selftests/net/cmsg_sender.c | 2 +- tools/testing/selftests/net/ipsec.c | 4 +- .../selftests/net/mptcp/mptcp_connect.c | 11 +- tools/testing/selftests/net/mptcp/mptcp_inq.c | 11 +- 152 files changed, 1331 insertions(+), 622 deletions(-) -- 2.20.1

2 135

[PATCH OLK-6.6 000/112] Backport 6.6.4 LTS Patches
by Zheng Zengkai 09 Dec '23

09 Dec '23

Backport linux-6.6.4 LTS patches from upstream. git cherry-pick v6.6.3..v6.6.4~1 -s No conflicts. Build and boot test passed. Abel Wu (1): sched/eevdf: Fix vruntime adjustment on reweight Alex Elder (1): net: ipa: fix one GSI register field width Alexander Stein (1): usb: dwc3: Fix default mode initialization Andrzej Hajda (1): drm/i915: do not clean GT table on error path Ani Sinha (1): hv/hv_kvp_daemon: Some small fixes for handling NM keyfiles Arseniy Krasnov (1): vsock/test: fix SEQPACKET message bounds test Asuna Yang (1): USB: serial: option: add Luat Air72*U series products Badhri Jagan Sridharan (2): usb: typec: tcpm: Fix sink caps op current check usb: typec: tcpm: Skip hard reset when in error recovery Bjorn Andersson (1): drm/msm/dpu: Add missing safe_lut_tbl in sc8280xp catalog Charles Mirabile (1): io_uring/fs: consider link->flags when getting path for LINKAT Charles Yi (1): HID: fix HID device resource race between HID core and debugging support Chen Ni (1): ata: pata_isapnp: Add missing error check for devm_ioport_map() Christoph Hellwig (3): filemap: add a per-mapping stable writes flag block: update the stable_writes flag in bdev_add nvmet: nul-terminate the NQNs passed in the connect command Chuck Lever (3): NFSD: Fix "start of NFS reply" pointer passed to nfsd_cache_update() NFSD: Fix checksum mismatches in the duplicate reply cache libfs: getdents() should return 0 after reaching EOD Coly Li (2): bcache: replace a mistaken IS_ERR() by IS_ERR_OR_NULL() in btree_gc_coalesce() bcache: check return value from btree_node_alloc_replacement() Cong Yang (1): drm/panel: boe-tv101wum-nl6: Fine tune Himax83102-j02 panel HFP and HBP D. Wythe (1): net/smc: avoid data corruption caused by decline Daniel Borkmann (2): net, vrf: Move dstats structure to core net: Move {l,t,d}stats allocation to core and convert veth & vrf David Howells (6): rxrpc: Fix RTT determination to use any ACK as a source rxrpc: Defer the response to a PING ACK until we've parsed it afs: Fix afs_server_list to be cleaned up with RCU afs: Make error on cell lookup failure consistent with OpenAFS afs: Return ENOENT if no cell DNS record can be found afs: Fix file locking on R/O volumes to operate in local mode David Woodhouse (2): PM: tools: Fix sleepgraph syntax error ACPI: processor_idle: use raw_safe_halt() in acpi_idle_play_dead() Eric Dumazet (1): wireguard: use DEV_STATS_INC() Fang Xiang (1): irqchip/gic-v3-its: Flush ITS tables correctly in non-coherent GIC designs Florent Revest (1): mm: add a NO_INHERIT flag to the PR_SET_MDWE prctl Gerd Bayer (1): s390/ism: ism driver implies smc protocol Gil Fine (1): thunderbolt: Set lane bonding bit only for downstream port Haiyang Zhang (2): hv_netvsc: fix race of netvsc and VF register_netdevice hv_netvsc: Fix race of register_netdevice_notifier and VF register Hannes Reinecke (1): nvme: blank out authentication fabrics options if not configured Hans de Goede (3): ACPI: video: Use acpi_device_fix_up_power_children() ACPI: resource: Skip IRQ override on ASUS ExpertBook B1402CVA ACPI: PM: Add acpi_device_fix_up_power_children() function Harshit Mogalapalli (3): platform/x86: hp-bioscfg: Simplify return check in hp_add_other_attributes() platform/x86: hp-bioscfg: move mutex_lock() down in hp_add_other_attributes() platform/x86: hp-bioscfg: Fix error handling in hp_add_other_attributes() Helge Deller (1): prctl: Disable prctl(PR_SET_MDWE) on parisc Ivan Vecera (1): i40e: Fix adding unsupported cloud filters Jacek Lawrynowicz (1): accel/ivpu/37xx: Fix hangs related to MMIO reset Jan Höppner (1): s390/dasd: protect device queue against concurrent access Jann Horn (1): tls: fix NULL deref on tls_sw_splice_eof() with empty record Jiawen Wu (1): net: wangxun: fix kernel panic due to null pointer Johan Hovold (8): USB: dwc3: qcom: fix resource leaks on probe deferral USB: dwc3: qcom: fix ACPI platform device leak Revert "usb: phy: add usb phy notify port status API" Revert "phy: realtek: usb: Add driver for the Realtek SoC USB 3.0 PHY" Revert "phy: realtek: usb: Add driver for the Realtek SoC USB 2.0 PHY" USB: xhci-plat: fix legacy PHY double init USB: dwc3: qcom: fix software node leak on probe errors USB: dwc3: qcom: fix wakeup after probe deferral Jonas Karlman (1): drm/rockchip: vop: Fix color for RGB888/BGR888 format on VOP full Jonathan Marek (1): drm/msm/dsi: use the correct VREG_CTRL_1 value for 4nm cphy Jose Ignacio Tornos Martinez (1): net: usb: ax88179_178a: fix failed operations during ax88179_reset Keisuke Nishimura (1): sched/fair: Fix the decision for load balance Keith Busch (2): swiotlb-xen: provide the "max_mapping_size" method io_uring: fix off-by one bvec index Kunwu Chan (1): ipv4: Correct/silence an endian warning in __ip_do_redirect Lech Perczak (1): USB: serial: option: don't claim interface 4 for ZTE MF290 Long Li (1): hv_netvsc: Mark VF as slave before exposing it to user-mode Lorenzo Bianconi (1): net: veth: fix ethtool stats reporting Marek Vasut (2): drm/panel: simple: Fix Innolux G101ICE-L01 bus flags drm/panel: simple: Fix Innolux G101ICE-L01 timings Mark Brown (1): kselftest/arm64: Fix output formatting for za-fork Mikhail Zaslonko (1): s390/ipl: add missing IPL_TYPE_ECKD_DUMP case to ipl_init() Mikulas Patocka (1): dm-delay: fix a race between delay_presuspend and delay_bio Ming Lei (1): blk-cgroup: avoid to warn !rcu_read_lock_held() in blkg_lookup() Mingzhe Zou (3): bcache: fixup multi-threaded bch_sectors_dirty_init() wake-up race bcache: fixup init dirty data errors bcache: fixup lock c->root error Niklas Neronin (1): usb: config: fix iteration issue in 'usb_get_bos_descriptor()' Oliver Neukum (1): USB: dwc2: write HCINT with INTMASK applied Pawel Laszczak (1): usb: cdnsp: Fix deadlock issue during using NCM gadget Peilin Ye (2): bpf: Fix dev's rx stats for bpf_redirect_peer traffic veth: Use tstats per-CPU traffic counters Peter Zijlstra (1): lockdep: Fix block chain corruption Puliang Lu (1): USB: serial: option: fix FM101R-GL defines Raju Rangoju (3): amd-xgbe: handle corner-case during sfp hotplug amd-xgbe: handle the corner-case during tx completion amd-xgbe: propagate the correct speed and duplex status Rand Deeb (1): bcache: prevent potential division by zero error Ricardo Ribalda (1): usb: dwc3: set the dma max_seg_size Samuel Holland (1): net: axienet: Fix check for partial TX checksum Shyam Prasad N (3): cifs: distribute channels across interfaces based on speed cifs: account for primary channel in the interface list cifs: fix leak of iface for primary channel Shyam Sundar S K (1): platform/x86/amd/pmc: adjust getting DRAM size behavior Song Liu (1): md: fix bi_status reporting in md_end_clone_io Stanislaw Gruszka (1): accel/ivpu: Do not initialize parameters on power up Stefan Berger (1): fs: Pass AT_GETATTR_NOSEC flag to getattr interface function Stefan Binding (1): ALSA: hda/realtek: Add quirks for ASUS 2024 Zenbooks Stefan Eichenberger (2): dt-bindings: usb: microchip,usb5744: Add second supply usb: misc: onboard-hub: add support for Microchip USB5744 Stefano Stabellini (1): arm/xen: fix xen_vcpu_info allocation alignment Stuart Hayhurst (1): platform/x86: ideapad-laptop: Set max_brightness before using it Suman Ghosh (2): octeontx2-pf: Fix memory leak during interface down octeontx2-pf: Fix ntuple rule creation to direct packet to VF with higher Rx queue than its PF Thomas Zimmermann (1): drm/ast: Disconnect BMC if physical connector is connected Victor Fragoso (1): USB: serial: option: add Fibocom L7xx modules Vitalii Torshyn (1): ALSA: hda: ASUS UM5302LA: Added quirks for cs35L41/10431A83 on i2c bus Will Deacon (1): arm64: mm: Fix "rodata=on" when CONFIG_RODATA_FULL_DEFAULT_ENABLED=y Xuxin Xiong (1): drm/panel: auo,b101uan08.3: Fine tune the panel power sequence .../bindings/usb/microchip,usb5744.yaml | 7 +- arch/arm/xen/enlighten.c | 3 +- arch/arm64/include/asm/setup.h | 17 +- arch/arm64/mm/pageattr.c | 7 +- arch/s390/kernel/ipl.c | 1 + block/bdev.c | 2 + block/blk-cgroup.h | 2 - drivers/accel/ivpu/ivpu_hw_37xx.c | 54 +- drivers/accel/ivpu/ivpu_hw_40xx.c | 8 +- drivers/acpi/acpi_video.c | 2 +- drivers/acpi/device_pm.c | 13 + drivers/acpi/processor_idle.c | 2 +- drivers/acpi/resource.c | 7 + drivers/ata/pata_isapnp.c | 3 + drivers/gpu/drm/ast/ast_drv.h | 13 +- drivers/gpu/drm/ast/ast_mode.c | 62 +- drivers/gpu/drm/i915/gt/intel_gt.c | 11 - drivers/gpu/drm/i915/i915_driver.c | 4 +- .../msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h | 1 + drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c | 2 +- .../gpu/drm/panel/panel-boe-tv101wum-nl6.c | 9 +- drivers/gpu/drm/panel/panel-simple.c | 13 +- drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 14 +- drivers/hid/hid-core.c | 12 +- drivers/hid/hid-debug.c | 3 + drivers/irqchip/irq-gic-v3-its.c | 16 +- drivers/md/bcache/btree.c | 4 +- drivers/md/bcache/sysfs.c | 2 +- drivers/md/bcache/writeback.c | 22 +- drivers/md/dm-delay.c | 17 +- drivers/md/md.c | 3 +- drivers/net/ethernet/amd/xgbe/xgbe-drv.c | 14 + drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 11 +- drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 14 +- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 16 +- .../marvell/octeontx2/nic/otx2_flows.c | 20 +- .../ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 + drivers/net/ethernet/wangxun/libwx/wx_hw.c | 8 +- drivers/net/ethernet/wangxun/ngbe/ngbe_main.c | 4 +- .../net/ethernet/wangxun/txgbe/txgbe_main.c | 4 +- .../net/ethernet/xilinx/xilinx_axienet_main.c | 2 +- drivers/net/hyperv/netvsc_drv.c | 66 +- drivers/net/ipa/reg/gsi_reg-v5.0.c | 2 +- drivers/net/usb/ax88179_178a.c | 4 +- drivers/net/veth.c | 46 +- drivers/net/vrf.c | 38 +- drivers/net/wireguard/device.c | 4 +- drivers/net/wireguard/receive.c | 12 +- drivers/net/wireguard/send.c | 3 +- drivers/nvme/host/fabrics.c | 2 + drivers/nvme/target/fabrics-cmd.c | 4 + drivers/phy/Kconfig | 1 - drivers/phy/Makefile | 1 - drivers/phy/realtek/Kconfig | 32 - drivers/phy/realtek/Makefile | 3 - drivers/phy/realtek/phy-rtk-usb2.c | 1325 ----------------- drivers/phy/realtek/phy-rtk-usb3.c | 761 ---------- drivers/platform/x86/amd/pmc/pmc.c | 31 +- drivers/platform/x86/hp/hp-bioscfg/bioscfg.c | 24 +- drivers/platform/x86/ideapad-laptop.c | 11 +- drivers/s390/block/dasd.c | 24 +- drivers/s390/net/Kconfig | 3 +- drivers/s390/net/ism_drv.c | 93 +- drivers/thunderbolt/switch.c | 2 +- drivers/usb/cdns3/cdnsp-ring.c | 3 + drivers/usb/core/config.c | 3 +- drivers/usb/core/hub.c | 23 - drivers/usb/dwc2/hcd_intr.c | 15 +- drivers/usb/dwc3/core.c | 2 + drivers/usb/dwc3/drd.c | 2 +- drivers/usb/dwc3/dwc3-qcom.c | 65 +- drivers/usb/host/xhci-plat.c | 50 +- drivers/usb/misc/onboard_usb_hub.c | 2 + drivers/usb/misc/onboard_usb_hub.h | 7 + drivers/usb/serial/option.c | 11 +- drivers/usb/typec/tcpm/tcpm.c | 12 +- drivers/xen/swiotlb-xen.c | 1 + fs/afs/dynroot.c | 4 +- fs/afs/internal.h | 1 + fs/afs/server_list.c | 2 +- fs/afs/super.c | 2 + fs/afs/vl_rotate.c | 10 + fs/ecryptfs/inode.c | 12 +- fs/inode.c | 2 + fs/libfs.c | 14 +- fs/nfsd/cache.h | 4 +- fs/nfsd/nfscache.c | 64 +- fs/nfsd/nfssvc.c | 14 +- fs/overlayfs/inode.c | 10 +- fs/overlayfs/overlayfs.h | 8 + fs/smb/client/cifs_debug.c | 16 + fs/smb/client/cifsglob.h | 2 + fs/smb/client/connect.c | 6 + fs/smb/client/sess.c | 112 +- fs/smb/client/smb2ops.c | 6 + fs/stat.c | 6 +- include/acpi/acpi_bus.h | 1 + include/linux/hid.h | 3 + include/linux/netdevice.h | 30 +- include/linux/pagemap.h | 17 + include/linux/sched/coredump.h | 10 + include/linux/usb/phy.h | 13 - include/trace/events/rxrpc.h | 2 +- include/uapi/linux/fcntl.h | 3 + include/uapi/linux/prctl.h | 1 + io_uring/fs.c | 2 +- io_uring/rsrc.c | 2 +- kernel/fork.c | 2 +- kernel/locking/lockdep.c | 3 +- kernel/sched/fair.c | 161 +- kernel/sys.c | 36 +- mm/page-writeback.c | 2 +- net/core/dev.c | 57 +- net/core/filter.c | 1 + net/ipv4/route.c | 2 +- net/rxrpc/input.c | 61 +- net/smc/af_smc.c | 8 +- net/tls/tls_sw.c | 3 + sound/pci/hda/patch_realtek.c | 10 + tools/hv/hv_kvp_daemon.c | 20 +- tools/hv/hv_set_ifconfig.sh | 4 +- tools/include/uapi/linux/prctl.h | 1 + tools/power/pm-graph/sleepgraph.py | 2 +- tools/testing/selftests/arm64/fp/za-fork.c | 2 +- tools/testing/vsock/vsock_test.c | 19 +- 125 files changed, 1207 insertions(+), 2685 deletions(-) delete mode 100644 drivers/phy/realtek/Kconfig delete mode 100644 drivers/phy/realtek/Makefile delete mode 100644 drivers/phy/realtek/phy-rtk-usb2.c delete mode 100644 drivers/phy/realtek/phy-rtk-usb3.c -- 2.20.1

2 113

[PATCH OLK-5.10] smart_grid: cpufreq: clear offline and isolated CPU in warm CPUs
by Yipeng Zou 09 Dec '23

09 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MFO6 CVE: NA ---------------------------------------- When there has some CPU has been offline or isolated, the warm zone CPUs will not clear these CPUs. Because of the warm zone were saluted by a complement of hot zone. So, we need to clear offline and isolated CPUs in every time's warm zone CPUs update. Fixes: 6a00891859d8 ("smart_grid: cpufreq: introduce smart_grid cpufreq control") Signed-off-by: Yipeng Zou <zouyipeng(a)huawei.com> --- drivers/cpufreq/cpufreq.c | 7 ++++++- kernel/sched/grid/qos.c | 9 +++++++-- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 574c9584923f..a262eab3e771 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -29,6 +29,9 @@ #include <linux/syscore_ops.h> #include <linux/tick.h> #include <trace/events/power.h> +#ifdef CONFIG_QOS_SCHED_SMART_GRID +#include <linux/sched/isolation.h> +#endif static LIST_HEAD(cpufreq_policy_list); @@ -2827,7 +2830,9 @@ static void smart_grid_work_handler(struct work_struct *work) continue; for_each_cpu(cpu, sched_grid_zone_cpumask(gov_index)) { - if (cpu_is_offline(cpu)) + /* bypass offline and isolated CPU */ + if (housekeeping_test_cpu(cpu, HK_FLAG_DOMAIN) || + cpu_is_offline(cpu)) continue; policy = cpufreq_cpu_acquire(cpu); diff --git a/kernel/sched/grid/qos.c b/kernel/sched/grid/qos.c index f8c5deffd3ea..7ee3687347ce 100644 --- a/kernel/sched/grid/qos.c +++ b/kernel/sched/grid/qos.c @@ -179,6 +179,7 @@ int sched_grid_zone_update(bool is_locked) raw_spin_lock_irqsave(&sg_zone.lock, flags); cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_HOT]); + cpumask_clear(&sg_zone.cpus[SMART_GRID_ZONE_WARM]); list_for_each(pos, &sg_zone.af_list_head) { af_pos = list_entry(pos, struct auto_affinity, af_list); @@ -190,10 +191,14 @@ int sched_grid_zone_update(bool is_locked) cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_HOT], &sg_zone.cpus[SMART_GRID_ZONE_HOT], af_pos->ad.domains[af_pos->ad.curr_level]); + /* Update warm zone CPUs to max level first */ + cpumask_or(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + af_pos->ad.domains[af_pos->ad.dcount - 1]); } - cpumask_complement(&sg_zone.cpus[SMART_GRID_ZONE_WARM], - &sg_zone.cpus[SMART_GRID_ZONE_HOT]); + /* Then reset warm zone CPUs without hot zone CPUs */ + cpumask_andnot(&sg_zone.cpus[SMART_GRID_ZONE_WARM], &sg_zone.cpus[SMART_GRID_ZONE_WARM], + &sg_zone.cpus[SMART_GRID_ZONE_HOT]); if (!is_locked) raw_spin_unlock_irqrestore(&sg_zone.lock, flags); -- 2.34.1

2 1

[PATCH OLK-6.6 v2] kasan: fix the compilation error for memcpy_mcs()
by Tong Tiangen 09 Dec '23

09 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MWHA CVE: NA -------------------------------- check_memory_region() has been renamed kasan_check_range() in commit f00748bfa024 ("kasan: prefix global functions with kasan_"). Therefore, a compilation error occurs when check_memory_region() is called in memcpy_mcs() in file mm/kasan/shadow.c, this patch fix this issue. Fixes: 23ca830ebbef ("arm64: introduce copy_mc_to_kernel() implementation") Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> --- mm/kasan/shadow.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index ffaf2df1ed6e..9372f0c6f7ec 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -83,9 +83,9 @@ void *memcpy(void *dest, const void *src, size_t len) #undef memcpy_mcs int memcpy_mcs(void *dest, const void *src, size_t len) { - if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) || - !check_memory_region((unsigned long)dest, len, true, _RET_IP_)) - return (unsigned long)len; + if (!kasan_check_range(src, len, false, _RET_IP_) || + !kasan_check_range(dest, len, true, _RET_IP_)) + return (int)len; return __memcpy_mcs(dest, src, len); } -- 2.25.1

2 1

[PATCH OLK-6.6] kasan: fix the compilation error for memcpy_mcs()
by Tong Tiangen 08 Dec '23

08 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MWHA CVE: NA -------------------------------- Fix the compilation error when CONFIG_KASAN=y: error: implicit declaration of function ‘check_memory_region’; Fixes: 23ca830ebbef ("arm64: introduce copy_mc_to_kernel() implementation") Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> --- mm/kasan/shadow.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index ffaf2df1ed6e..9372f0c6f7ec 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -83,9 +83,9 @@ void *memcpy(void *dest, const void *src, size_t len) #undef memcpy_mcs int memcpy_mcs(void *dest, const void *src, size_t len) { - if (!check_memory_region((unsigned long)src, len, false, _RET_IP_) || - !check_memory_region((unsigned long)dest, len, true, _RET_IP_)) - return (unsigned long)len; + if (!kasan_check_range(src, len, false, _RET_IP_) || + !kasan_check_range(dest, len, true, _RET_IP_)) + return (int)len; return __memcpy_mcs(dest, src, len); } -- 2.25.1

2 1

[PATCH OLK-6.6 v2] config: Open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32
by Jinjie Ruan 08 Dec '23

08 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8JVJ3 CVE: NA ------------------------------------------------------------------------- No one currently uses IPL32, close it to simplify the code logic of TASK_SIZE_MAX, thereby improving benchmark performance. For example, all test items of libMicro can be improved by 4.89% on average. Since commit 7f6675f0e994 ("arm64: rename COMPAT to AARCH32_EL0"), CONFIG_COMPAT has been renamed to CONFIG_AARCH32_EL0, so open CONFIG_AARCH32_EL0 as what CONFIG_COMPAT used to be. Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Reviewed-by: Liu Chao (CR) <liuchao173(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- arch/arm64/configs/openeuler_defconfig | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index 9d2f717c1f7c..ce5a7aeaeeca 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -449,9 +449,10 @@ CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY=y # CONFIG_RODATA_FULL_DEFAULT_ENABLED is not set # CONFIG_ARM64_SW_TTBR0_PAN is not set CONFIG_ARM64_TAGGED_ADDR_ABI=y -CONFIG_COMPAT=y +CONFIG_AARCH32_EL0=y # CONFIG_KUSER_HELPERS is not set # CONFIG_COMPAT_ALIGNMENT_FIXUPS is not set +# CONFIG_COMPAT_TASK_SIZE is not set CONFIG_ARMV8_DEPRECATED=y CONFIG_SWP_EMULATION=y CONFIG_CP15_BARRIER_EMULATION=y @@ -526,6 +527,8 @@ CONFIG_EFI=y CONFIG_DMI=y # end of Boot options +CONFIG_COMPAT=y + # # Power management options # -- 2.34.1

2 1

[PATCH OLK-6.6 0/3] improve gettimeofday() performance in user space
by Yang Yingliang 08 Dec '23

08 Dec '23

Don't trap kernel to read the counter register, do this in userspace to improve performance. Yang Yingliang (3): arm64: arch_timer: Disable CNTVCT_EL0 trap if workaround is enabled vdso: do cntvct workaround in the VDSO arm64: arch_timer: disable CONFIG_ARM_ARCH_TIMER_WORKAROUND_IN_USERSPACE arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/vdso/gettimeofday.h | 32 ++++++++++++++++++++++ drivers/clocksource/Kconfig | 5 ++++ drivers/clocksource/arm_arch_timer.c | 27 ++++++++++++++++++ include/linux/clocksource.h | 4 +++ include/vdso/datapage.h | 8 +++++- kernel/time/vsyscall.c | 16 +++++++++++ 7 files changed, 92 insertions(+), 1 deletion(-) -- 2.25.1

2 4

[PATCH OLK-5.10] locking/osq_lock: Avoid false sharing in optimistic_spin_node
by Zeng Heng 08 Dec '23

08 Dec '23

hulk inclusion category: performance bugzilla: https://gitee.com/openeuler/kernel/issues/I8MV01 -------------------------------- In the prologue of osq_lock(), it set `cpu` member of percpu struct optimistic_spin_node with the local cpu id, after that the value is never changed any more. Consequently, we can regard the `cpu` member as a constant variable. In the meanwhile, other members like next, prev and locked are frequently modified by osq_lock() and osq_unlock() which come from rwsem, mutex and so on. So here we can place padding and locate them at different cache lines, so that avoid cache misses when access optimistic_spin_node.cpu field by other CPUs from the node list. Here provide the UnixBench full-core test result as below: Machine Intel(R) Xeon(R) Gold 6248 CPU, 40 cores, 80 threads Run the command of "./Run -c 80 -i 3" 10 times and take the average. System Benchmarks Index Values Without Patch With Patch Diff Dhrystone 2 using register variables 185876.43 185945.41 0.04% Double-Precision Whetstone 79637.27 79659.29 0.03% Execl Throughput 9909.61 10576.06 6.73% File Copy 1024 bufsize 2000 maxblocks 1723.01 2086.08 21.07% File Copy 256 bufsize 500 maxblocks 1150.24 1338.21 16.34% File Copy 4096 bufsize 8000 maxblocks 3719.19 4011.99 7.87% Pipe Throughput 66184.84 66025.25 -0.24% Pipe-based Context Switching 30606.18 31074.21 1.53% Process Creation 9442.48 9450.77 0.09% Shell Scripts (1 concurrent) 44526.52 46548.54 4.54% Shell Scripts (8 concurrent) 42903.96 45718.56 6.56% System Call Overhead 3645.20 3717.42 1.98% ======== System Benchmarks Index Score 15126.87 15931.29 5.32% Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- include/linux/osq_lock.h | 2 +- kernel/locking/osq_lock.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h index 5581dbd3bd34..deb90ad5f560 100644 --- a/include/linux/osq_lock.h +++ b/include/linux/osq_lock.h @@ -9,7 +9,7 @@ struct optimistic_spin_node { struct optimistic_spin_node *next, *prev; int locked; /* 1 if lock acquired */ - int cpu; /* encoded CPU # + 1 value */ + int cpu ____cacheline_aligned; /* encoded CPU # + 1 value */ }; struct optimistic_spin_queue { diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 1de006ed3aa8..f7e7b76f6274 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -96,7 +96,8 @@ bool osq_lock(struct optimistic_spin_queue *lock) node->locked = 0; node->next = NULL; - node->cpu = curr; + if (!node->cpu) + node->cpu = curr; /* * We need both ACQUIRE (pairs with corresponding RELEASE in -- 2.25.1

2 1

[PATCH OLK-6.6 v3 00/19] Add sharepool support v3
by Wang Wensheng 08 Dec '23

08 Dec '23

This patch series migrates share pool features from OLK-5.10 to OLK-6.6. We don't want to do this work patch by patch since there are hundreds of patches in OLK-5.10 including bugfix and small features generation. Instead we just take the final version and split it into a few small patches, each of which contains one feature at the final version. The share pool features is a big feature, it is mainly used to share user virtual memory for different processes in the same group. It could be used by this steps: Process A create a new group which is owned by process A. Process A add process B to the group. Process A add process C to the same group. Process B alloc a new memory VA, and write something in it. The VA was send to the process C by IPC, then process C got it. The process C access the VA and got the data directly. The process A could add more processes in the group to share the memory. Fix the memory by use the free function or exit the group. The new features is enabled both by CONFIG_SHARE_POOL and the enable_ascend_share_pool bootarg, it would not affect anything if disabled. v1->v2: Delete some unused code. v2->v3: Rename several function. Wang Wensheng (19): mm/hugetlb: Introduce hugetlb_insert_hugepage_pte[_by_pa] mm/vmalloc: Extend vmalloc usage about hugepage mm: Extend mmap assocated functions to accept mm_struct mm/sharepool: Add base framework for share_pool mm/sharepool: Add sp_area management code mm/sharepool: Reserve the va space for share_pool mm/sharepool: Implement mg_sp_make_share_u2k() mm/sharepool: Implement mg_sp_unshare_kva mm/sharepool: Implement mg_sp_walk_page_range() mm/sharepool: Implement mg_sp_free() mm/sharepool: Implement mg_sp_alloc() mm/sharepool: Implement mg_sp_make_share_k2u() mm/sharepool: Implement mg_sp_group_add_task() mm/sharepool: Implement mg_sp_group_id_by_pid() mm/sharepool: Implement mg_sp_id_of_current() mm/sharepool: Implement mg_sp_config_dvpp_range() mm/sharepool: Add proc interfaces to show sp info mm/sharepool: support fork() and exit() to handle the mm mm/sharepool: Protect the va reserved for sharepool include/linux/hugetlb.h | 32 + include/linux/mempolicy.h | 11 + include/linux/mm.h | 17 + include/linux/mm_types.h | 6 + include/linux/share_pool.h | 267 +++ include/linux/vmalloc.h | 18 + kernel/fork.c | 3 + mm/Kconfig | 34 + mm/Makefile | 1 + mm/gup.c | 23 +- mm/hugetlb.c | 80 + mm/mempolicy.c | 12 +- mm/mmap.c | 50 +- mm/mremap.c | 4 + mm/share_pool.c | 3448 ++++++++++++++++++++++++++++++++++++ mm/util.c | 4 + mm/vmalloc.c | 205 ++- 17 files changed, 4194 insertions(+), 21 deletions(-) create mode 100644 include/linux/share_pool.h create mode 100644 mm/share_pool.c -- 2.17.1

2 20

[PATCH OLK-5.10] roh/core: Synchronously update the mac address of
by Ke Chen 08 Dec '23

08 Dec '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MTN4 ----------------------------------------------------------------------- In ROH mode, when the IP address of a VLAN device changes, we need to change the MAC address of the VLAN device to maintain the mapping between the IP address, EID, and MAC address. In this way, the ARP fast response in ROH mode can take effect. Fixes:55901e4aae1e("roh/core: Add support for inetaddr notifier in roh/core") Signed-off-by: Ke Chen <chenke54(a)huawei.com> Reviewed-by: Gang Zhang <gang.zhang(a)huawei.com> --- drivers/roh/core/core.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/drivers/roh/core/core.c b/drivers/roh/core/core.c index 1b8041004be3..9b867f2cc2d5 100644 --- a/drivers/roh/core/core.c +++ b/drivers/roh/core/core.c @@ -3,6 +3,7 @@ #include <linux/pci.h> #include <linux/inetdevice.h> +#include <linux/if_vlan.h> #include "core_priv.h" #include "core.h" @@ -245,12 +246,26 @@ static int roh_ipv4_event(struct notifier_block *this, unsigned long event, void struct in_ifaddr *ifa = ptr; struct roh_device *device; struct net_device *ndev; + struct sockaddr s_addr; struct sockaddr_in in; int ret; + if (event != NETDEV_UP) + return NOTIFY_DONE; + device = container_of(this, struct roh_device, nb); ndev = ifa->ifa_dev->dev; - if (device->netdev != ndev || event != NETDEV_UP) + + if (is_vlan_dev(ndev)) { + if (vlan_dev_real_dev(ndev) == device->netdev) { + s_addr.sa_family = ndev->type; + u64_to_ether_addr(be32_to_cpu(ifa->ifa_address) & 0xffffff, s_addr.sa_data); + dev_set_mac_address(ndev, &s_addr, NULL); + } + return NOTIFY_DONE; + } + + if (device->netdev != ndev) return NOTIFY_DONE; in.sin_addr.s_addr = ifa->ifa_address; -- 2.30.0

2 1

[PATCH OLK-6.6 1/1] ARM: Add unwinding annotations to __loop.*delay functions
by Xu Kuohai 08 Dec '23

08 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MTBB CVE: NA -------------------------------- The unwind directives can't handle nested function entries, so only the outermost function __loop_udelay is annotated, and the inner nested entries share the same unwind info with __loop_udelay. Signed-off-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/arm/lib/delay-loop.S | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S index 3ac05177d097..3ba37ce6dbb0 100644 --- a/arch/arm/lib/delay-loop.S +++ b/arch/arm/lib/delay-loop.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/delay.h> +#include <asm/unwind.h> #ifdef CONFIG_ARCH_RPC .arch armv4 @@ -25,6 +26,7 @@ */ ENTRY(__loop_udelay) +UNWIND(.fnstart) ldr r2, .LC1 mul r0, r2, r0 @ r0 = delay_us * UDELAY_MULT ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0xfffffaf0 @@ -58,6 +60,7 @@ ENTRY(__loop_delay) #endif bhi __loop_delay ret lr -ENDPROC(__loop_udelay) -ENDPROC(__loop_const_udelay) ENDPROC(__loop_delay) +ENDPROC(__loop_const_udelay) +UNWIND(.fnend) +ENDPROC(__loop_udelay) -- 2.30.2

2 2

[PATCH OLK-6.6 1/1] ARM: Add unwinding annotations to __loop.*delay functions
by Xu Kuohai 08 Dec '23

08 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MTBB CVE: NA -------------------------------- The unwind directives can't handle nested function entries, so only the outermost function __loop_udelay is annotated, and the inner nested entries share the same unwind info with __loop_udelay. Signed-off-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Yang Jihong <yangjihong1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/arm/lib/delay-loop.S | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/arm/lib/delay-loop.S b/arch/arm/lib/delay-loop.S index 3ac05177d097..3ba37ce6dbb0 100644 --- a/arch/arm/lib/delay-loop.S +++ b/arch/arm/lib/delay-loop.S @@ -7,6 +7,7 @@ #include <linux/linkage.h> #include <asm/assembler.h> #include <asm/delay.h> +#include <asm/unwind.h> #ifdef CONFIG_ARCH_RPC .arch armv4 @@ -25,6 +26,7 @@ */ ENTRY(__loop_udelay) +UNWIND(.fnstart) ldr r2, .LC1 mul r0, r2, r0 @ r0 = delay_us * UDELAY_MULT ENTRY(__loop_const_udelay) @ 0 <= r0 <= 0xfffffaf0 @@ -58,6 +60,7 @@ ENTRY(__loop_delay) #endif bhi __loop_delay ret lr -ENDPROC(__loop_udelay) -ENDPROC(__loop_const_udelay) ENDPROC(__loop_delay) +ENDPROC(__loop_const_udelay) +UNWIND(.fnend) +ENDPROC(__loop_udelay) -- 2.30.2

2 1

[PATCH 0/5] LoongArch: add cpufreq and ls2k500 bmc support
by Hongchen Zhang 08 Dec '23

08 Dec '23

Chong Qiao (4): fbdev: add ls2k500sfb driver for ls2k500 bmc. ipmi: add ls2k500 bmc ipmi support. LoongArch: defconfig: enable CONFIG_FB_LS2K500=m. LoongArch: fix ls2k500 bmc not work when installing iso liuyun (1): cpufreq: Add cpufreq driver for LoongArch arch/loongarch/Kconfig | 1 + arch/loongarch/configs/loongson3_defconfig | 5 + arch/loongarch/include/asm/fpu.h | 13 +- drivers/char/ipmi/Makefile | 4 + drivers/char/ipmi/btlock.h | 92 ++ drivers/char/ipmi/ipmi_si.h | 11 + drivers/char/ipmi/ipmi_si_intf.c | 4 + drivers/char/ipmi/ipmi_si_ls2k500.c | 173 +++ drivers/char/ipmi/kcs_bmc_ls2k500.h | 67 + drivers/cpufreq/Kconfig | 11 + drivers/cpufreq/Makefile | 1 + drivers/cpufreq/loongson3-acpi-cpufreq.c | 1527 ++++++++++++++++++++ drivers/gpu/drm/loongson/loongson_module.c | 15 + drivers/video/fbdev/Kconfig | 13 + drivers/video/fbdev/Makefile | 1 + drivers/video/fbdev/ls2k500sfb.c | 792 ++++++++++ 16 files changed, 2729 insertions(+), 1 deletion(-) create mode 100644 drivers/char/ipmi/btlock.h create mode 100644 drivers/char/ipmi/ipmi_si_ls2k500.c create mode 100644 drivers/char/ipmi/kcs_bmc_ls2k500.h create mode 100644 drivers/cpufreq/loongson3-acpi-cpufreq.c create mode 100644 drivers/video/fbdev/ls2k500sfb.c -- 2.33.0

1 5

[PATCH OLK-5.10] module: Expose module_init_layout_section()
by Zhao Wenhui 08 Dec '23

08 Dec '23

From: James Morse <james.morse(a)arm.com> stable inclusion from stable-v5.10.194 commit ecd62c85120dc74b07c5ccd1532de121e81a4dba category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I83LMD Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 2abcc4b5a64a65a2d2287ba0be5c2871c1552416 upstream. module_init_layout_section() choses whether the core module loader considers a section as init or not. This affects the placement of the exit section when module unloading is disabled. This code will never run, so it can be free()d once the module has been initialised. arm and arm64 need to count the number of PLTs they need before applying relocations based on the section name. The init PLTs are stored separately so they can be free()d. arm and arm64 both use within_module_init() to decide which list of PLTs to use when applying the relocation. Because within_module_init()'s behaviour changes when module unloading is disabled, both architecture would need to take this into account when counting the PLTs. Today neither architecture does this, meaning when module unloading is disabled there are insufficient PLTs in the init section to load some modules, resulting in warnings: | WARNING: CPU: 2 PID: 51 at arch/arm64/kernel/module-plts.c:99 module_emit_plt_entry+0x184/0x1cc | Modules linked in: crct10dif_common | CPU: 2 PID: 51 Comm: modprobe Not tainted 6.5.0-rc4-yocto-standard-dirty #15208 | Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015 | pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) | pc : module_emit_plt_entry+0x184/0x1cc | lr : module_emit_plt_entry+0x94/0x1cc | sp : ffffffc0803bba60 [...] | Call trace: | module_emit_plt_entry+0x184/0x1cc | apply_relocate_add+0x2bc/0x8e4 | load_module+0xe34/0x1bd4 | init_module_from_file+0x84/0xc0 | __arm64_sys_finit_module+0x1b8/0x27c | invoke_syscall.constprop.0+0x5c/0x104 | do_el0_svc+0x58/0x160 | el0_svc+0x38/0x110 | el0t_64_sync_handler+0xc0/0xc4 | el0t_64_sync+0x190/0x194 Instead of duplicating module_init_layout_section()s logic, expose it. Reported-by: Adam Johnston <adam.johnston(a)arm.com> Fixes: 055f23b74b20 ("module: check for exit sections in layout_sections() instead of module_init_section()") Cc: stable(a)vger.kernel.org Signed-off-by: James Morse <james.morse(a)arm.com> Signed-off-by: Luis Chamberlain <mcgrof(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhao Wenhui <zhaowenhui8(a)huawei.com> --- include/linux/moduleloader.h | 5 +++++ kernel/module.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 2d835b7dc918..0b4541cb4c74 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -39,6 +39,11 @@ bool module_init_section(const char *name); */ bool module_exit_section(const char *name); +/* Describes whether within_module_init() will consider this an init section + * or not. This behaviour changes with CONFIG_MODULE_UNLOAD. + */ +bool module_init_layout_section(const char *sname); + /* * Apply the given relocation to the (simplified) ELF. Return -error * or 0. diff --git a/kernel/module.c b/kernel/module.c index 23c5349a54ea..e978debc93df 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2301,7 +2301,7 @@ void *__symbol_get(const char *symbol) } EXPORT_SYMBOL_GPL(__symbol_get); -static bool module_init_layout_section(const char *sname) +bool module_init_layout_section(const char *sname) { #ifndef CONFIG_MODULE_UNLOAD if (module_exit_section(sname)) -- 2.34.1

2 1

[PATCH OLK-6.6 00/10] kabi: add kabi helper macros and tools
by Jialin Zhang 08 Dec '23

08 Dec '23

1. add kabi helper macros 2. add kabi tools: kabideps, kabisyms, check-kabi Li Lingfeng (1): kabi: deduplication friendly structs Xie XiuQi (5): kabi: add KABI_SIZE_ALIGN_CHECKS for more stringent kabi checks kabi: enables more stringent kabi checks kabi: add script tools to check kabi symbol kabi: add a tool to generate the kabi reference relationship kabi: add kABI reference checking tool Zheng Zengkai (4): kabi: add kabi helper macros KABI: Add CONFIG_KABI_RESERVE to control KABI padding reserve openeuler_defconfig: Enable CONFIG_KABI_RESERVE for x86 and arm64 kabi: Generalize naming of kabi helper macros Kconfig | 15 + arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/kabi.h | 509 +++++++++++++++++++++++++ scripts/check-kabi | 147 +++++++ scripts/kabideps | 161 ++++++++ scripts/kabisyms | 141 +++++++ 7 files changed, 977 insertions(+) create mode 100644 include/linux/kabi.h create mode 100755 scripts/check-kabi create mode 100755 scripts/kabideps create mode 100755 scripts/kabisyms -- 2.25.1

2 11

[PATCH OLK-6.6 0/8] memcg_qos and memcg_async_reclaim
by Lu Jialin 08 Dec '23

08 Dec '23

Lu Jialin (8): cgroup: Export cgroup.kill from cgroupv2 to cgroupv1 memcg: Export memcg.{min/low} from cgroupv2 to cgroupv1 memcg: Export memcg.high from cgroupv2 to cgroupv1 memcg: Export memory.events and memory.events.local from cgroupv2 to cgroupv1 memcg: Fix inconsistent oom event behavior for OOM_MEMCG_KILL memcg: enable memcg async reclaim memcg: export high_async_ratio to userland Kconfig: Introduce CONFIG_MEMCG_V1_THRESHOLD_QOS and CONFIG_CGROUP_V1_KILL arch/arm64/configs/openeuler_defconfig | 2 + arch/x86/configs/openeuler_defconfig | 2 + include/linux/memcontrol.h | 24 +- init/Kconfig | 11 + kernel/cgroup/cgroup-internal.h | 3 + kernel/cgroup/cgroup-v1.c | 7 + kernel/cgroup/cgroup.c | 4 +- mm/memcontrol.c | 378 ++++++++++++++++++------- 8 files changed, 319 insertions(+), 112 deletions(-) -- 2.34.1

3 10

[PATCH OLK-6.6 0/5] block: Add config option to not allow
by Li Lingfeng 08 Dec '23

08 Dec '23

This feature is controlled by both CONFIG_BLK_DEV_WRITE_MOUNTED and cmdline parameters bdev_allow_write_mounted, and bdev_allow_write_mounted has a higher priority. Jan Kara (5): block: Add config option to not allow writing to mounted devices btrfs: Do not restrict writes to btrfs devices fs: Block writes to mounted block devices xfs: Block writes to log device ext4: Block writes to journal device block/Kconfig | 20 +++++++++++ block/bdev.c | 75 ++++++++++++++++++++++++++++++++++++++- fs/btrfs/super.c | 2 ++ fs/ext4/super.c | 5 +-- fs/xfs/xfs_super.c | 5 +-- include/linux/blk_types.h | 1 + include/linux/blkdev.h | 5 ++- 7 files changed, 107 insertions(+), 6 deletions(-) -- 2.31.1

2 6

[PATCH OLK-6.6 v2 00/19] Add sharepool support
by Wang Wensheng 08 Dec '23

08 Dec '23

This patch series migrates share pool features from OLK-5.10 to OLK-6.6. We don't want to do this work patch by patch since there are hundreds of patches in OLK-5.10 including bugfix and small features generation. Instead we just take the final version and split it into a few small patches, each of which contains one feature at the final version. The share pool features is a big feature, it is mainly used to share user virtual memory for different processes in the same group. It could be used by this steps: Process A create a new group which is owned by process A. Process A add process B to the group. Process A add process C to the same group. Process B alloc a new memory VA, and write something in it. The VA was send to the process C by IPC, then process C got it. The process C access the VA and got the data directly. The process A could add more processes in the group to share the memory. Fix the memory by use the free function or exit the group. The new features is enabled both by CONFIG_SHARE_POOL and the enable_ascend_share_pool bootarg, it would not affect anything if disabled. v1->v2: Delete some unused code. Wang Wensheng (19): mm/hugetlb: Introduce hugetlb_insert_hugepage_pte[_by_pa] mm/vmalloc: Extend vmalloc usage about hugepage mm: Extend mmap assocated functions to accept mm_struct mm/sharepool: Add base framework for share_pool mm/sharepool: Add sp_area management code mm/sharepool: Reserve the va space for share_pool mm/sharepool: Implement mg_sp_make_share_u2k() mm/sharepool: Implement mg_sp_unshare_kva mm/sharepool: Implement mg_sp_walk_page_range() mm/sharepool: Implement mg_sp_free() mm/sharepool: Implement mg_sp_alloc() mm/sharepool: Implement mg_sp_make_share_k2u() mm/sharepool: Implement mg_sp_group_add_task() mm/sharepool: Implement mg_sp_group_id_by_pid() mm/sharepool: Implement mg_sp_id_of_current() mm/sharepool: Implement mg_sp_config_dvpp_range() mm/sharepool: Add proc interfaces to show sp info mm/sharepool: support fork() and exit() to handle the mm mm/sharepool: Protect the va reserved for sharepool include/linux/hugetlb.h | 32 + include/linux/mempolicy.h | 11 + include/linux/mm.h | 17 + include/linux/mm_types.h | 6 + include/linux/share_pool.h | 267 +++ include/linux/vmalloc.h | 18 + kernel/fork.c | 3 + mm/Kconfig | 34 + mm/Makefile | 1 + mm/gup.c | 23 +- mm/hugetlb.c | 78 + mm/mempolicy.c | 12 +- mm/mmap.c | 50 +- mm/mremap.c | 4 + mm/share_pool.c | 3448 ++++++++++++++++++++++++++++++++++++ mm/util.c | 4 + mm/vmalloc.c | 205 ++- 17 files changed, 4192 insertions(+), 21 deletions(-) create mode 100644 include/linux/share_pool.h create mode 100644 mm/share_pool.c -- 2.17.1

3 22

[PATCH OLK-6.6 0/2] arm64: errata: add option to disable cache readunique prefetch on HIP08
by Yang Yingliang 08 Dec '23

08 Dec '23

Random performance decreases appear on cases of Hackbench which test pipe or socket communication among multi-threads on Hisi HIP08 SoC. Cache sharing which caused by the change of the data layout and the cache readunique prefetch mechanism both lead to this problem. Readunique mechanism which may caused by store operation will invalid cachelines on other cores during data fetching stage which can cause cacheline invalidation happens frequently in a sharing data access situation. Disable cache readunique prefetch can trackle this problem. Test cases are like: for i in 20;do echo "--------pipe thread num=$i----------" for j in $(seq 1 10);do ./hackbench -pipe $i thread 1000 done done We disable readunique prefetch only in el2 for in el1 disabling readunique prefetch may cause panic due to lack of related priority which often be set in BIOS. Introduce CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH and disable RU prefetch using boot cmdline 'readunique_prefetch=off'. Kai Shen (1): arm64: errata: add option to disable cache readunique prefetch on HIP08 Xie XiuQi (1): arm64: errata: enable HISILICON_ERRATUM_HIP08_RU_PREFETCH arch/arm64/Kconfig | 18 +++++++++ arch/arm64/configs/openeuler_defconfig | 2 + arch/arm64/kernel/cpu_errata.c | 56 ++++++++++++++++++++++++++ arch/arm64/tools/cpucaps | 1 + 4 files changed, 77 insertions(+) -- 2.25.1

2 3

[src-openEuler/rdma-core 1/1] libhns: Fix missing DB when compiler does not support SVE
by Chengchang Tang 08 Dec '23

08 Dec '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8I94Q ---------------------------------------------------------------------- Currently, if compiler does not support SVE, hns_roce_sve_write512() will be a empty function, which means that this doorbell will be missed when HNS_ROCE_QP_CAP_SVE_DIRECT_WQE is set in qp flag. This patch ensures that driver will at least generate the DB regardless of whether SVE DWQE is supported or not. Fixes: 7b1f5c5654c2 ("libhns: Add support for SVE Direct WQE function") Signed-off-by: Chengchang Tang <tangchengchang(a)huawei.com> Signed-off-by: Ran Zhou <zhouran10(a)h-partners.com> --- providers/hns/hns_roce_u_hw_v2.c | 33 +++++++++++++------------------- 1 file changed, 13 insertions(+), 20 deletions(-) diff --git a/providers/hns/hns_roce_u_hw_v2.c b/providers/hns/hns_roce_u_hw_v2.c index acbc854..be4c9f3 100644 --- a/providers/hns/hns_roce_u_hw_v2.c +++ b/providers/hns/hns_roce_u_hw_v2.c @@ -318,26 +318,22 @@ static void hns_roce_update_sq_db(struct hns_roce_context *ctx, hns_roce_write64(ctx, qp->sq.db_reg, (__le32 *)&sq_db); } -static void hns_roce_write512(uint64_t *dest, uint64_t *val) +static void hns_roce_qp_write512(struct hns_roce_qp *qp, uint64_t *val) { - mmio_memcpy_x64(dest, val, sizeof(struct hns_roce_rc_sq_wqe)); -} + uint64_t *dest = qp->sq.db_reg; #if defined(HNS_SVE) -static void hns_roce_sve_write512(uint64_t *dest, uint64_t *val) -{ - asm volatile( - "ldr z0, [%0]\n" - "str z0, [%1]\n" - ::"r" (val), "r"(dest):"cc", "memory" - ); -} -#else -static void hns_roce_sve_write512(uint64_t *dest, uint64_t *val) -{ - return; -} + if (qp->flags & HNS_ROCE_QP_CAP_SVE_DIRECT_WQE) { + asm volatile( + "ldr z0, [%0]\n" + "str z0, [%1]\n" + ::"r" (val), "r"(dest):"cc", "memory" + ); + return; + } #endif + mmio_memcpy_x64(dest, val, sizeof(struct hns_roce_rc_sq_wqe)); +} static void hns_roce_write_dwqe(struct hns_roce_qp *qp, void *wqe) { @@ -355,10 +351,7 @@ static void hns_roce_write_dwqe(struct hns_roce_qp *qp, void *wqe) hr_reg_write(rc_sq_wqe, RCWQE_DB_SL_H, qp->sl >> HNS_ROCE_SL_SHIFT); hr_reg_write(rc_sq_wqe, RCWQE_WQE_IDX, qp->sq.head); - if (qp->flags & HNS_ROCE_QP_CAP_SVE_DIRECT_WQE) - hns_roce_sve_write512(qp->sq.db_reg, wqe); - else - hns_roce_write512(qp->sq.db_reg, wqe); + hns_roce_qp_write512(qp, wqe); } static void update_cq_db(struct hns_roce_context *ctx, struct hns_roce_cq *cq) -- 2.30.0

1 0

[PATCH OLK-6.6 v4 00/17] arm32/arm64/x86_64: Support basic functions of kernel livepatch
by Zheng Yejian 08 Dec '23

08 Dec '23

Port patches from v5.10 to support basic functions of kernel livepatch on arch arm32/arm64/x86_64. Zheng Yejian (17): livepatch/core: Allow implementation without ftrace livepatch/core: Reuse common codes in the solution without ftrace Revert "x86/insn: Make insn_complete() static" livepatch/x86: Support livepatch without ftrace livepatch/core: Restrict livepatch patched/unpatched when plant kprobe livepatch/core: Support load and unload hooks livepatch: samples: Adapt livepatch-sample for solution without ftrace livepatch/core: Support jump_label livepatch: Fix crash when access the global variable in hook livepatch: Fix patching functions which have static_call livepatch/core: Avoid conflict with static {call,key} livepatch/arm64: Support livepatch without ftrace livepatch/core: Revert module_enable_ro and module_disable_ro livepatch: Enable livepatch configs in openeuler_defconfig arm/module: Use plt section indices for relocations livepatch/core: Add support for arm for klp relocation livepatch/arm: Support livepatch without ftrace Documentation/filesystems/proc.rst | 2 +- arch/arm/Kconfig | 3 + arch/arm/include/asm/livepatch.h | 51 + arch/arm/include/asm/module.h | 4 +- arch/arm/kernel/Makefile | 1 + arch/arm/kernel/ftrace.c | 4 +- arch/arm/kernel/livepatch.c | 256 ++++ arch/arm/kernel/module-plts.c | 22 +- arch/arm/kernel/module.c | 4 +- arch/arm64/Kconfig | 3 + arch/arm64/configs/openeuler_defconfig | 12 + arch/arm64/include/asm/livepatch.h | 48 + arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/livepatch.c | 225 ++++ arch/powerpc/Kconfig | 4 +- arch/s390/Kconfig | 2 +- arch/s390/configs/debug_defconfig | 1 + arch/s390/configs/defconfig | 1 + arch/x86/Kconfig | 3 +- arch/x86/configs/openeuler_defconfig | 12 +- arch/x86/include/asm/insn.h | 7 + arch/x86/include/asm/livepatch.h | 33 + arch/x86/kernel/Makefile | 1 + arch/x86/kernel/livepatch.c | 289 +++++ arch/x86/kernel/module.c | 2 +- arch/x86/lib/insn.c | 7 - include/linux/jump_label.h | 10 + include/linux/livepatch.h | 97 +- include/linux/livepatch_sched.h | 6 +- include/linux/module.h | 33 + include/linux/moduleloader.h | 4 +- include/linux/static_call.h | 6 + kernel/jump_label.c | 22 + kernel/livepatch/Kconfig | 78 +- kernel/livepatch/Makefile | 3 +- kernel/livepatch/core.c | 1245 +++++++++++++++++++- kernel/livepatch/core.h | 4 + kernel/module/main.c | 10 +- kernel/module/strict_rwx.c | 17 + kernel/static_call_inline.c | 20 + lib/Kconfig.debug | 2 +- samples/livepatch/Makefile | 2 + samples/livepatch/livepatch-sample.c | 36 + tools/arch/x86/include/asm/insn.h | 7 + tools/arch/x86/lib/insn.c | 7 - tools/testing/selftests/bpf/config.aarch64 | 1 + tools/testing/selftests/bpf/config.s390x | 1 + tools/testing/selftests/livepatch/README | 1 + tools/testing/selftests/livepatch/config | 1 + 49 files changed, 2555 insertions(+), 56 deletions(-) create mode 100644 arch/arm/include/asm/livepatch.h create mode 100644 arch/arm/kernel/livepatch.c create mode 100644 arch/arm64/include/asm/livepatch.h create mode 100644 arch/arm64/kernel/livepatch.c create mode 100644 arch/x86/include/asm/livepatch.h create mode 100644 arch/x86/kernel/livepatch.c -- 2.25.1

2 18

[PATCH v3 OLK-5.10 0/2] Fixed some memory leak issues of the Perf tool
by Junhao He 08 Dec '23

08 Dec '23

Fixed some memory leak issues of the Perf record of ptt: a) ptt: Fix memory leak in lseek failure handling b) ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() Kuan-Wei Chiu (1): perf hisi-ptt: Fix memory leak in lseek failure handling Yicong Yang (1): perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() tools/perf/util/hisi-ptt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.33.0

2 3