- Kernel - mailweb.openeuler.org

[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

[PATCH OLK-6.6 v3 0/4] add redis sockmap sample code
by Zhengchao Shao 08 Dec '23

08 Dec '23

add redis sockmap sample code. Liu Jian (4): cgroup: make cgroup_bpf_prog_attach work when cgroup2 is not mounted net: let sockops can use bpf_get_current_comm() net: add local_skb parameter to identify local tcp connection tools: add sample sockmap code for redis include/linux/cgroup.h | 1 + include/linux/filter.h | 3 + include/linux/skbuff.h | 5 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 8 +- kernel/cgroup/cgroup.c | 24 +++ net/Kconfig | 5 + net/core/filter.c | 13 ++ net/ipv4/tcp_input.c | 6 +- net/ipv4/tcp_output.c | 9 + tools/include/uapi/linux/bpf.h | 1 + tools/netacc/Makefile | 24 +++ tools/netacc/bpf_sockmap.h | 167 +++++++++++++++++++ tools/netacc/net-acc | 35 ++++ tools/netacc/netacc.c | 296 +++++++++++++++++++++++++++++++++ tools/netacc/netaccsockmap.c | 176 ++++++++++++++++++++ 16 files changed, 769 insertions(+), 5 deletions(-) create mode 100644 tools/netacc/Makefile create mode 100644 tools/netacc/bpf_sockmap.h create mode 100755 tools/netacc/net-acc create mode 100644 tools/netacc/netacc.c create mode 100644 tools/netacc/netaccsockmap.c -- 2.34.1

2 5

[PATCH OLK-6.6 v3 0/4] add redis sockmap sample code
by Zhengchao Shao 08 Dec '23

08 Dec '23

add redis sockmap sample code. Liu Jian (4): cgroup: make cgroup_bpf_prog_attach work when cgroup2 is not mounted net: let sockops can use bpf_get_current_comm() net: add local_skb parameter to identify local tcp connection tools: add sample sockmap code for redis include/linux/cgroup.h | 1 + include/linux/filter.h | 3 + include/linux/skbuff.h | 5 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 8 +- kernel/cgroup/cgroup.c | 24 +++ net/Kconfig | 5 + net/core/filter.c | 13 ++ net/ipv4/tcp_input.c | 6 +- net/ipv4/tcp_output.c | 9 + tools/include/uapi/linux/bpf.h | 1 + tools/netacc/Makefile | 24 +++ tools/netacc/bpf_sockmap.h | 167 +++++++++++++++++++ tools/netacc/net-acc | 35 ++++ tools/netacc/netacc.c | 296 +++++++++++++++++++++++++++++++++ tools/netacc/netaccsockmap.c | 176 ++++++++++++++++++++ 16 files changed, 769 insertions(+), 5 deletions(-) create mode 100644 tools/netacc/Makefile create mode 100644 tools/netacc/bpf_sockmap.h create mode 100755 tools/netacc/net-acc create mode 100644 tools/netacc/netacc.c create mode 100644 tools/netacc/netaccsockmap.c -- 2.34.1

2 6

[PATCH openEuler-1.0-LTS v3 0/2] LTS patch backport
by Dong Chenchen 08 Dec '23

08 Dec '23

Dong Chenchen (1): net: fix kabi broken in struct netns_xfrm Eric Dumazet (1): xfrm: fix a data-race in xfrm_gen_index() include/net/netns/xfrm.h | 3 +++ net/xfrm/xfrm_policy.c | 6 ++---- 2 files changed, 5 insertions(+), 4 deletions(-) -- 2.25.1

2 3

[PATCH OLK-6.6 0/7]arm64: add machine check safe support
by Tong Tiangen 08 Dec '23

08 Dec '23

With the increase of memory capacity and density, the probability of memory error also increases. The increasing size and density of server RAM in data centers and clouds have shown increased uncorrectable memory errors. Currently, the kernel has mechanism to recover from hardware memory errors. This patchset provides a new recovery mechanism. For arm64, the hardware memory error handling in do_sea(), which is divided into two cases: 1. If the user state consumed the memory errors, the solution is to kill the user process and isolate the error page. 2. If the kernel state consumed the memory errors, the solution is to panic. For case 2, Undifferentiated panic may not be the optimal choice, as it can be handled better. In some scenarios, we can avoid panic, such as uaccess, if the uaccess fails due to memory error, only the user process will be affected, killing the user process and isolating the user page with hardware memory errors is a better choice. Tong Tiangen (7): uaccess: add generic fallback version of copy_mc_to_user() arm64: add support for machine check error safe arm64: add uaccess to machine check safe mm/hwpoison: return -EFAULT when copy fail in copy_mc_[user]_highpage() arm64: support copy_mc_[user]_highpage() arm64: introduce copy_mc_to_kernel() implementation arm64: add machine check safe sysctl interface Documentation/admin-guide/sysctl/kernel.rst | 14 ++ arch/arm64/Kconfig | 1 + arch/arm64/include/asm/asm-extable.h | 15 ++ arch/arm64/include/asm/assembler.h | 4 + arch/arm64/include/asm/extable.h | 1 + arch/arm64/include/asm/mte.h | 5 + arch/arm64/include/asm/page.h | 10 + arch/arm64/include/asm/string.h | 5 + arch/arm64/include/asm/uaccess.h | 21 ++ arch/arm64/lib/Makefile | 4 +- arch/arm64/lib/copy_from_user.S | 10 +- arch/arm64/lib/copy_mc_page.S | 89 +++++++ arch/arm64/lib/copy_to_user.S | 10 +- arch/arm64/lib/memcpy_mc.S | 257 ++++++++++++++++++++ arch/arm64/lib/mte.S | 27 ++ arch/arm64/mm/copypage.c | 66 ++++- arch/arm64/mm/extable.c | 21 +- arch/arm64/mm/fault.c | 58 ++++- arch/powerpc/include/asm/uaccess.h | 1 + arch/x86/include/asm/uaccess.h | 1 + include/linux/highmem.h | 16 +- include/linux/uaccess.h | 9 + mm/kasan/shadow.c | 12 + mm/khugepaged.c | 4 +- 24 files changed, 635 insertions(+), 26 deletions(-) create mode 100644 arch/arm64/lib/copy_mc_page.S create mode 100644 arch/arm64/lib/memcpy_mc.S -- 2.25.1

2 8

[PATCH OLK-6.6 v3 0/4] add redis sockmap sample code
by Zhengchao Shao 07 Dec '23

07 Dec '23

add redis sockmap sample code. Liu Jian (4): cgroup: make cgroup_bpf_prog_attach work when cgroup2 is not mounted net: let sockops can use bpf_get_current_comm() net: add local_skb parameter to identify local tcp connection tools: add sample sockmap code for redis include/linux/cgroup.h | 1 + include/linux/filter.h | 3 + include/linux/skbuff.h | 5 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 8 +- kernel/cgroup/cgroup.c | 24 +++ net/Kconfig | 5 + net/core/filter.c | 13 ++ net/ipv4/tcp_input.c | 6 +- net/ipv4/tcp_output.c | 9 + tools/include/uapi/linux/bpf.h | 1 + tools/netacc/Makefile | 24 +++ tools/netacc/bpf_sockmap.h | 167 +++++++++++++++++++ tools/netacc/net-acc | 35 ++++ tools/netacc/netacc.c | 296 +++++++++++++++++++++++++++++++++ tools/netacc/netaccsockmap.c | 176 ++++++++++++++++++++ 16 files changed, 769 insertions(+), 5 deletions(-) create mode 100644 tools/netacc/Makefile create mode 100644 tools/netacc/bpf_sockmap.h create mode 100755 tools/netacc/net-acc create mode 100644 tools/netacc/netacc.c create mode 100644 tools/netacc/netaccsockmap.c -- 2.34.1

1 4

[PATCH openEuler-1.0-LTS v2 0/2] LTS patch backport
by Dong Chenchen 07 Dec '23

07 Dec '23

Dong Chenchen (1): net: fix kabi broken in struct netns_xfrm Eric Dumazet (1): xfrm: fix a data-race in xfrm_gen_index() include/net/netns/xfrm.h | 3 +++ net/xfrm/xfrm_policy.c | 6 ++---- 2 files changed, 5 insertions(+), 4 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS 0/2] LTS patch backport
by Dong Chenchen 07 Dec '23

07 Dec '23

Dong Chenchen (1): net: fix kabi broken in struct netns_xfrm Eric Dumazet (1): xfrm: fix a data-race in xfrm_gen_index() include/net/netns/xfrm.h | 1 + net/xfrm/xfrm_policy.c | 6 ++---- 2 files changed, 3 insertions(+), 4 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS v3 00/20] linux-4.19.y inclusion
by Zhang Changzhong 07 Dec '23

07 Dec '23

v2->v3: drop "xfrm: fix a data-race in xfrm_gen_index()" to avoid kabi changes v1->v2: remove redundant patches Chen Yu (1): genirq/matrix: Exclude managed interrupts in irq_matrix_allocated() Christophe JAILLET (1): ACPI: sysfs: Fix create_pnp_modalias() and create_of_modalias() Eric Dumazet (4): tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb tcp_metrics: add missing barriers on delete tcp_metrics: properly set tp->snd_ssthresh in tcp_init_metrics() tcp_metrics: do not create an entry from tcp_init_metrics() Gou Hao (1): ext4: move 'ix' sanity check to corrent position Jan Kara (1): quota: Fix slow quotaoff Jeff Layton (1): overlayfs: set ctime when setting mtime and atime Jorge Sanjuan Garcia (1): mcb: remove is_added flag from mcb_device struct Kuniyuki Iwashima (1): dccp/tcp: Call security_inet_conn_request() after setting IPv6 addresses. Marc Kleine-Budde (3): can: dev: move driver related infrastructure into separate subdir can: dev: can_restart(): don't crash kernel if carrier is OK can: dev: can_restart(): fix race condition between controller restart and netif_carrier_on() Michal Koutný (1): cgroup: Remove duplicates in cgroup v1 tasks file Neal Cardwell (1): tcp: fix excessive TLP and RACK timeouts from HZ rounding Peter Zijlstra (1): sched,idle,rcu: Push rcu_idle deeper into the idle path Reuben Hawkins (1): vfs: fix readahead(2) on block devices Sunil V L (1): ACPI: irq: Fix incorrect return value in acpi_register_gsi() Yan Zhai (1): ipv6: avoid atomic fragment on GSO packets drivers/acpi/device_sysfs.c | 10 ++-- drivers/acpi/irq.c | 7 ++- drivers/cpuidle/cpuidle.c | 12 +++-- drivers/mcb/mcb-core.c | 10 ++-- drivers/mcb/mcb-parse.c | 2 - drivers/net/can/Makefile | 7 +-- drivers/net/can/dev/Makefile | 7 +++ drivers/net/can/{ => dev}/dev.c | 10 ++-- drivers/net/can/{ => dev}/rx-offload.c | 0 fs/ext4/extents.c | 10 ++-- fs/overlayfs/copy_up.c | 2 +- fs/quota/dquot.c | 66 +++++++++++++++----------- include/linux/mcb.h | 1 - include/linux/quota.h | 4 +- include/linux/quotaops.h | 2 +- include/net/tcp.h | 3 ++ kernel/cgroup/cgroup-v1.c | 5 +- kernel/irq/matrix.c | 6 +-- kernel/sched/idle.c | 22 ++++----- mm/readahead.c | 3 +- net/dccp/ipv6.c | 6 +-- net/ipv4/tcp_metrics.c | 15 +++--- net/ipv4/tcp_output.c | 25 +++++++--- net/ipv4/tcp_recovery.c | 2 +- net/ipv6/ip6_output.c | 8 +++- net/ipv6/syncookies.c | 7 +-- 26 files changed, 145 insertions(+), 107 deletions(-) create mode 100644 drivers/net/can/dev/Makefile rename drivers/net/can/{ => dev}/dev.c (99%) rename drivers/net/can/{ => dev}/rx-offload.c (100%) -- 2.34.1

2 21

[PATCH OLK-6.6] arm64: kernel: disable CNP on LINXICORE9100
by Tong Tiangen 07 Dec '23

07 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M8F9 CVE: NA -------------------------------- On Hisilicon LINXICORE9100 cores, sharing tlb entries on two cores when TTBRx.CNP=1 differs from the standard ARM core. This causes issues when tlb entries sharing between CPU cores. Avoid these issues by disabling CNP feature for Hisilicon LINXICORE9100 cores. Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> --- Documentation/arch/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 11 +++++++++++ arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/cputype.h | 2 ++ arch/arm64/kernel/cpu_errata.c | 14 ++++++++++++++ arch/arm64/kernel/cpufeature.c | 3 +++ arch/arm64/tools/cpucaps | 1 + 7 files changed, 34 insertions(+) diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index f47f63bcf67c..bb62e0dbd546 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -203,6 +203,8 @@ stable kernels. | Hisilicon | Hip08 SMMU PMCG | #162001900 | N/A | | | Hip09 SMMU PMCG | | | +----------------+-----------------+-----------------+-----------------------------+ +| Hisilicon | LINXICORE9100 | #162100125 | HISILICON_ERRATUM_162100125 | ++----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | +----------------+-----------------+-----------------+-----------------------------+ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 78f20e632712..5de0d8348cc3 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1158,6 +1158,17 @@ config HISILICON_ERRATUM_161600802 If unsure, say Y. +config HISILICON_ERRATUM_162100125 + bool "Hisilicon erratum 162100125" + default y + help + On Hisilicon LINXICORE9100 cores, sharing tlb entries on two cores when + TTBRx.CNP=1 differs from the standard ARM core. This causes issues when + tlb entries sharing between CPU cores. Avoid these issues by disabling + CNP support for Hisilicon LINXICORE9100 cores. + + 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 8f1a4db8d49b..68d073921996 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -395,6 +395,7 @@ CONFIG_CAVIUM_ERRATUM_30115=y CONFIG_CAVIUM_TX2_ERRATUM_219=y CONFIG_FUJITSU_ERRATUM_010001=y CONFIG_HISILICON_ERRATUM_161600802=y +CONFIG_HISILICON_ERRATUM_162100125=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/cputype.h b/arch/arm64/include/asm/cputype.h index 7c7493cb571f..202588ad92e8 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_LINXICORE9100 0xD02 #define APPLE_CPU_PART_M1_ICESTORM 0x022 #define APPLE_CPU_PART_M1_FIRESTORM 0x023 @@ -180,6 +181,7 @@ #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_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) #define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5706e74c5578..74c4ecc4a980 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -282,6 +282,13 @@ static const struct midr_range cavium_erratum_30115_cpus[] = { }; #endif +#ifdef CONFIG_HISILICON_ERRATUM_162100125 +static const struct midr_range hisilicon_erratum_162100125_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[] = { { @@ -506,6 +513,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .cpu_enable = cpu_enable_trap_ctr_access, }, +#ifdef CONFIG_HISILICON_ERRATUM_162100125 + { + .desc = "Hisilicon erratum 162100125", + .capability = ARM64_WORKAROUND_HISILICON_ERRATUM_162100125, + ERRATA_MIDR_RANGE_LIST(hisilicon_erratum_162100125_cpus), + }, +#endif #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 444a73c2e638..ef4f66b2b6ff 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1624,6 +1624,9 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) return false; + if (cpus_have_const_cap(ARM64_WORKAROUND_HISILICON_ERRATUM_162100125)) + return false; + return has_cpuid_feature(entry, scope); } diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index dea3dc89234b..d85d4a741aed 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -100,3 +100,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_HISILICON_ERRATUM_162100125 -- 2.25.1

2 1

[PATCH v2 OLK-5.10 0/3] Fixed some memory leak issues of the Perf tool
by Junhao He 07 Dec '23

07 Dec '23

Fixed some memory leak issues of the Perf tool: a) ptt: Fix memory leak in lseek failure handling b) ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() c) header: Fix one memory leakage in perf_event__fprintf_event_update Kuan-Wei Chiu (1): perf hisi-ptt: Fix memory leak in lseek failure handling Yicong Yang (2): perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() perf header: Fix one memory leakage in perf_event__fprintf_event_update() tools/perf/util/header.c | 6 ++++-- tools/perf/util/hisi-ptt.c | 5 ++++- 2 files changed, 8 insertions(+), 3 deletions(-) -- 2.33.0

2 4

[PATCH v2 OLK-5.10 0/3] Fixed some memory leak issues of the Perf tool
by Junhao He 07 Dec '23

07 Dec '23

Fixed some memory leak issues of the Perf tool: a) ptt: Fix memory leak in lseek failure handling b) ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() c) header: Fix one memory leakage in perf_event__fprintf_event_update Kuan-Wei Chiu (1): perf hisi-ptt: Fix memory leak in lseek failure handling Yicong Yang (2): perf hisi-ptt: Fix one memory leakage in hisi_ptt_process_auxtrace_event() perf header: Fix one memory leakage in perf_event__fprintf_event_update() tools/perf/util/header.c | 6 ++++-- tools/perf/util/hisi-ptt.c | 5 ++++- 2 files changed, 8 insertions(+), 3 deletions(-) -- 2.33.0

1 3

[PATCH v5 OLK-6.6 0/5] Support Qos Scheduler
by Wenyu Huang 07 Dec '23

07 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 + kernel/sysctl.c | 1 - 12 files changed, 603 insertions(+), 2 deletions(-) -- 2.34.1

3 7

[PATCH OLK-6.6 v2 00/19] Add sharepool support
by Wang Wensheng 07 Dec '23

07 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

1 19

[PATCH OLK-6.6 v3 00/17] arm32/arm64/x86_64: Support basic functions of kernel livepatch
by Zheng Yejian 07 Dec '23

07 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 OLK-5.10] x86/kprobes: Fix the error judgment for debug exceptions
by Li Huafei 07 Dec '23

07 Dec '23

hulk inclusion category: bugfix bugzilla: 188915, https://gitee.com/openeuler/kernel/issues/I7EU4Q -------------------------------- We get the following crash caused by a null pointer access: <SNIP> BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 54 PID: 2469325 Comm: ftracetest Kdump: loaded Tainted: GFS OE 5.10.0+ #12 Hardware name: Huawei RH2288H V3/BC11HGSA0, BIOS 3.35 10/20/2016 RIP: 0010:resume_execution+0x35/0x190 Code: 41 54 55 48 89 fd 53 48 89 f3 48 83 ec 08 4c 8b 6f 60 4c 8b b6 98 00 00 00 48 89 14 24 4c 8b 67 28 4d 89 ef eb 04 49 83 c5 01 <41> 0f b6 7d 00 e8 f1 12 57 00 83 e0 0f 8d 48 ff 83 f9 0a 76 e7 83 RSP: 0018:fffffe16118acec0 EFLAGS: 00010086 RAX: 0000000000000000 RBX: fffffe16118acf58 RCX: 00000000eefdca76 RDX: ffff8f8cffd1f400 RSI: fffffe16118acf58 RDI: ffff8f5500d3c000 RBP: ffff8f5500d3c000 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff970e39c0 R13: 0000000000000000 R14: ffffb55ba0bd7c60 R15: 0000000000000000 FS: 00002aaaaad22740(0000) GS:ffff8f8cffd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000003ac202c003 CR4: 00000000003706e0 DR0: ffffffff98000160 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Call Trace: <#DB> kprobe_debug_handler+0x41/0xd0 exc_debug+0xe5/0x1b0 asm_exc_debug+0x19/0x30 RIP: 0010:copy_from_kernel_nofault.part.0+0x55/0xc0 Code: 85 c0 74 e1 65 48 8b 04 25 40 f0 01 00 83 a8 78 14 00 00 01 48 c7 c0 f2 ff ff ff c3 cc cc cc cc 48 83 fa 03 76 16 31 c0 8b 0e <89> 0f 85 c0 75 d4 48 83 c7 04 48 83 c6 04 48 83 ea 04 48 83 fa 0129711 [200374.683072] RSP: 0018:ffffb55ba0bd7c60 EFLAGS: 00000246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000076207325 RDX: 0000000000000004 RSI: ffffffff98000160 RDI: ffff8f5500c0902c RBP: ffff8f5500c0902c R08: ffffb55ba0bd7bdc R09: 0000000000000001 R10: ffff8f5548a0faf8 R11: 0000000000000000 R12: ffffffff98000160 R13: 0000000000000000 R14: ffff8f560da128c0 R15: 0000000000000000 </#DB> process_fetch_insn+0xfb/0x720 kprobe_trace_func+0x199/0x2c0 ? kernel_clone+0x5/0x2f0 kprobe_dispatcher+0x3d/0x60 aggr_pre_handler+0x40/0x80 ? kernel_clone+0x1/0x2f0 kprobe_ftrace_handler+0x82/0xf0 ? __se_sys_clone+0x65/0x90 ftrace_ops_assist_func+0x86/0x110 ? rcu_nocb_try_bypass+0x1f3/0x370 0xffffffffc07e60c8 ? kernel_clone+0x1/0x2f0 kernel_clone+0x5/0x2f0 <SNIP> The analysis reveals that kprobe and hardware breakpoints conflict in the use of debug exceptions. If we set a hardware breakpoint on a memory address, and at the same time there is a kprobe event that also goes to get the memory of that address, then when kprobe triggers, it will go to read the memory and trigger hardware breakpoint monitoring, at this time, because kprobe handles debug exceptions earlier than hardware breakpoints, it will cause kprobe to incorrectly consider this exception as a kprobe trigger. Kprobe will change the status from KPROBE_HIT_ACTIVE to KPROBE_HIT_SS or KPROBE_REENTER before single-step execution, so if the current status is KPROBE_HIT_ACTIVE, its not a debug exception triggered by kprobe. Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- arch/x86/kernel/kprobes/core.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 5de757099186..352cf0a264d6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -900,7 +900,15 @@ int kprobe_debug_handler(struct pt_regs *regs) struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - if (!cur) + if (!cur || !cur->ainsn.insn) + return 0; + + /* kprobe will change the status from KPROBE_HIT_ACTIVE to + * KPROBE_HIT_SS or KPROBE_REENTER before single-step execution, so + * if the current status is KPROBE_HIT_ACTIVE, its not a debug + * exception triggered by kprobe. + */ + if (kcb->kprobe_status == KPROBE_HIT_ACTIVE) return 0; resume_execution(cur, regs, kcb); -- 2.25.1

2 1

[PATCH OLK-6.6 v2 00/17] arm32/arm64/x86_64: Support basic functions of kernel livepatch
by Zheng Yejian 07 Dec '23

07 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

1 33

[PATCH openEuler-1.0-LTS v2 00/21] linux-4.19.y inclusion
by Zhang Changzhong 07 Dec '23

07 Dec '23

v1->v2: remove redundant patches Chen Yu (1): genirq/matrix: Exclude managed interrupts in irq_matrix_allocated() Christophe JAILLET (1): ACPI: sysfs: Fix create_pnp_modalias() and create_of_modalias() Eric Dumazet (5): xfrm: fix a data-race in xfrm_gen_index() tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb tcp_metrics: add missing barriers on delete tcp_metrics: properly set tp->snd_ssthresh in tcp_init_metrics() tcp_metrics: do not create an entry from tcp_init_metrics() Gou Hao (1): ext4: move 'ix' sanity check to corrent position Jan Kara (1): quota: Fix slow quotaoff Jeff Layton (1): overlayfs: set ctime when setting mtime and atime Jorge Sanjuan Garcia (1): mcb: remove is_added flag from mcb_device struct Kuniyuki Iwashima (1): dccp/tcp: Call security_inet_conn_request() after setting IPv6 addresses. Marc Kleine-Budde (3): can: dev: move driver related infrastructure into separate subdir can: dev: can_restart(): don't crash kernel if carrier is OK can: dev: can_restart(): fix race condition between controller restart and netif_carrier_on() Michal Koutný (1): cgroup: Remove duplicates in cgroup v1 tasks file Neal Cardwell (1): tcp: fix excessive TLP and RACK timeouts from HZ rounding Peter Zijlstra (1): sched,idle,rcu: Push rcu_idle deeper into the idle path Reuben Hawkins (1): vfs: fix readahead(2) on block devices Sunil V L (1): ACPI: irq: Fix incorrect return value in acpi_register_gsi() Yan Zhai (1): ipv6: avoid atomic fragment on GSO packets drivers/acpi/device_sysfs.c | 10 ++-- drivers/acpi/irq.c | 7 ++- drivers/cpuidle/cpuidle.c | 12 +++-- drivers/mcb/mcb-core.c | 10 ++-- drivers/mcb/mcb-parse.c | 2 - drivers/net/can/Makefile | 7 +-- drivers/net/can/dev/Makefile | 7 +++ drivers/net/can/{ => dev}/dev.c | 10 ++-- drivers/net/can/{ => dev}/rx-offload.c | 0 fs/ext4/extents.c | 10 ++-- fs/overlayfs/copy_up.c | 2 +- fs/quota/dquot.c | 66 +++++++++++++++----------- include/linux/mcb.h | 1 - include/linux/quota.h | 4 +- include/linux/quotaops.h | 2 +- include/net/netns/xfrm.h | 1 + include/net/tcp.h | 3 ++ kernel/cgroup/cgroup-v1.c | 5 +- kernel/irq/matrix.c | 6 +-- kernel/sched/idle.c | 22 ++++----- mm/readahead.c | 3 +- net/dccp/ipv6.c | 6 +-- net/ipv4/tcp_metrics.c | 15 +++--- net/ipv4/tcp_output.c | 25 +++++++--- net/ipv4/tcp_recovery.c | 2 +- net/ipv6/ip6_output.c | 8 +++- net/ipv6/syncookies.c | 7 +-- net/xfrm/xfrm_policy.c | 6 +-- 28 files changed, 148 insertions(+), 111 deletions(-) create mode 100644 drivers/net/can/dev/Makefile rename drivers/net/can/{ => dev}/dev.c (99%) rename drivers/net/can/{ => dev}/rx-offload.c (100%) -- 2.34.1

2 22

[PATCH OLK-5.10] iommu/arm-smmu-v3: disable stall for quiet_cd
by Chen Jun 07 Dec '23

07 Dec '23

From: Wenkai Lin <linwenkai6(a)hisilicon.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8MCHF CVE: NA Reference: https://lore.kernel.org/all/20231206005517.46005-1-zhangfei.gao@linaro.org/… -------------------------------- In the stall model, invalid transactions were expected to be stalled and aborted by the IOPF handler. However, when killing a test case with a huge amount of data, the accelerator streamline can not stop until all data is consumed even if the page fault handler reports errors. As a result, the kill may take a long time, about 10 seconds with numerous iopf interrupts. So disable stall for quiet_cd in the non-force stall model, since force stall model (STALL_MODEL==0b10) requires CD.S must be 1. Signed-off-by: Zhangfei Gao <zhangfei.gao(a)linaro.org> Signed-off-by: Wenkai Lin <linwenkai6(a)hisilicon.com> Suggested-by: Jean-Philippe Brucker <jean-philippe(a)linaro.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 ++ 1 file changed, 2 insertions(+) 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 9a71cdb93817..a55c2dab72f8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1277,6 +1277,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, if (!cd) { /* (5) */ val = 0; } else if (cd == &quiet_cd) { /* (4) */ + if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) + val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R); val |= CTXDESC_CD_0_TCR_EPD0; } else if (cd_live) { /* (3) */ val &= ~CTXDESC_CD_0_ASID; -- 2.17.1

2 1

[PATCH 0/5] LoongArch: add cpufreq and ls2k500 bmc support
by Hongchen Zhang 07 Dec '23

07 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 openEuler-1.0-LTS v2 00/21] linux-4.19.y inclusion
by Zhang Changzhong 07 Dec '23

07 Dec '23

v1->v2: remove redundant patches Chen Yu (1): genirq/matrix: Exclude managed interrupts in irq_matrix_allocated() Christophe JAILLET (1): ACPI: sysfs: Fix create_pnp_modalias() and create_of_modalias() Eric Dumazet (5): xfrm: fix a data-race in xfrm_gen_index() tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb tcp_metrics: add missing barriers on delete tcp_metrics: properly set tp->snd_ssthresh in tcp_init_metrics() tcp_metrics: do not create an entry from tcp_init_metrics() Gou Hao (1): ext4: move 'ix' sanity check to corrent position Jan Kara (1): quota: Fix slow quotaoff Jeff Layton (1): overlayfs: set ctime when setting mtime and atime Jorge Sanjuan Garcia (1): mcb: remove is_added flag from mcb_device struct Kuniyuki Iwashima (1): dccp/tcp: Call security_inet_conn_request() after setting IPv6 addresses. Marc Kleine-Budde (3): can: dev: move driver related infrastructure into separate subdir can: dev: can_restart(): don't crash kernel if carrier is OK can: dev: can_restart(): fix race condition between controller restart and netif_carrier_on() Michal Koutný (1): cgroup: Remove duplicates in cgroup v1 tasks file Neal Cardwell (1): tcp: fix excessive TLP and RACK timeouts from HZ rounding Peter Zijlstra (1): sched,idle,rcu: Push rcu_idle deeper into the idle path Reuben Hawkins (1): vfs: fix readahead(2) on block devices Sunil V L (1): ACPI: irq: Fix incorrect return value in acpi_register_gsi() Yan Zhai (1): ipv6: avoid atomic fragment on GSO packets drivers/acpi/device_sysfs.c | 10 ++-- drivers/acpi/irq.c | 7 ++- drivers/cpuidle/cpuidle.c | 12 +++-- drivers/mcb/mcb-core.c | 10 ++-- drivers/mcb/mcb-parse.c | 2 - drivers/net/can/Makefile | 7 +-- drivers/net/can/dev/Makefile | 7 +++ drivers/net/can/{ => dev}/dev.c | 10 ++-- drivers/net/can/{ => dev}/rx-offload.c | 0 fs/ext4/extents.c | 10 ++-- fs/overlayfs/copy_up.c | 2 +- fs/quota/dquot.c | 66 +++++++++++++++----------- include/linux/mcb.h | 1 - include/linux/quota.h | 4 +- include/linux/quotaops.h | 2 +- include/net/netns/xfrm.h | 1 + include/net/tcp.h | 3 ++ kernel/cgroup/cgroup-v1.c | 5 +- kernel/irq/matrix.c | 6 +-- kernel/sched/idle.c | 22 ++++----- mm/readahead.c | 3 +- net/dccp/ipv6.c | 6 +-- net/ipv4/tcp_metrics.c | 15 +++--- net/ipv4/tcp_output.c | 25 +++++++--- net/ipv4/tcp_recovery.c | 2 +- net/ipv6/ip6_output.c | 8 +++- net/ipv6/syncookies.c | 7 +-- net/xfrm/xfrm_policy.c | 6 +-- 28 files changed, 148 insertions(+), 111 deletions(-) create mode 100644 drivers/net/can/dev/Makefile rename drivers/net/can/{ => dev}/dev.c (99%) rename drivers/net/can/{ => dev}/rx-offload.c (100%) -- 2.34.1

1 21

[PATCH OLK-6.6 0/2] arm64: errata: add option to disable cache readunique prefetch on HIP08
by Yang Yingliang 07 Dec '23

07 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

[PATCH openEuler-1.0-LTS] x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs
by liwei 07 Dec '23

07 Dec '23

From: "Borislav Petkov (AMD)" <bp(a)alien8.de> stable inclusion from stable-v4.19.297 commit 05868a16aab502d48a05a9528f23002fbf830335 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MCB5 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… --------------------------- commit f454b18e07f518bcd0c05af17a2239138bff52de upstream. Fix erratum #1485 on Zen4 parts where running with STIBP disabled can cause an #UD exception. The performance impact of the fix is negligible. Reported-by: René Rebe <rene(a)exactcode.de> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Tested-by: René Rebe <rene(a)exactcode.de> Cc: <stable(a)kernel.org> Link: https://lore.kernel.org/r/D99589F4-BC5D-430B-87B2-72C20370CF57@exactcode.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: arch/x86/kernel/cpu/amd.c Signed-off-by: liwei <liwei728(a)huawei.com> --- arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/amd.c | 9 +++++++++ 2 files changed, 13 insertions(+) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 7a115a34f9b2..3948ba5010a2 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -442,6 +442,10 @@ #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +/* Zen4 */ +#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 002aa4bd35cf..9a2257a64562 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -27,6 +27,7 @@ static const int amd_erratum_383[]; static const int amd_erratum_400[]; static const int amd_zenbleed[]; static const int amd_div0[]; +static const int amd_erratum_1485[]; static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); /* @@ -1044,6 +1045,10 @@ static void init_amd(struct cpuinfo_x86 *c) pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); setup_force_cpu_bug(X86_BUG_DIV0); } + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + cpu_has_amd_erratum(c, amd_erratum_1485)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } #ifdef CONFIG_X86_32 @@ -1177,6 +1182,10 @@ static const int amd_zenbleed[] = AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); +static const int amd_erratum_1485[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), + AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); + static const int amd_div0[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); -- 2.25.1

2 1

[PATCH OLK-5.10 0/6] Make the rcache depot scale better
by Zhang Zekun 07 Dec '23

07 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. 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 | 79 +++++++++++++++++++------- include/linux/iova.h | 7 ++- 4 files changed, 63 insertions(+), 34 deletions(-) -- 2.17.1

2 7

[PATCH openEuler-1.0-LTS 00/23] linux-4.19.y inclusion
by Zhang Changzhong 07 Dec '23

07 Dec '23

Chen Yu (1): genirq/matrix: Exclude managed interrupts in irq_matrix_allocated() Christophe JAILLET (1): ACPI: sysfs: Fix create_pnp_modalias() and create_of_modalias() Eric Dumazet (5): xfrm: fix a data-race in xfrm_gen_index() tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb tcp_metrics: add missing barriers on delete tcp_metrics: properly set tp->snd_ssthresh in tcp_init_metrics() tcp_metrics: do not create an entry from tcp_init_metrics() Gou Hao (1): ext4: move 'ix' sanity check to corrent position Jan Kara (1): quota: Fix slow quotaoff Jeff Layton (1): overlayfs: set ctime when setting mtime and atime Jorge Sanjuan Garcia (1): mcb: remove is_added flag from mcb_device struct Kuniyuki Iwashima (1): dccp/tcp: Call security_inet_conn_request() after setting IPv6 addresses. Marc Kleine-Budde (3): can: dev: move driver related infrastructure into separate subdir can: dev: can_restart(): don't crash kernel if carrier is OK can: dev: can_restart(): fix race condition between controller restart and netif_carrier_on() Michal Koutný (1): cgroup: Remove duplicates in cgroup v1 tasks file Neal Cardwell (1): tcp: fix excessive TLP and RACK timeouts from HZ rounding Peter Zijlstra (1): sched,idle,rcu: Push rcu_idle deeper into the idle path Reuben Hawkins (1): vfs: fix readahead(2) on block devices Sunil V L (1): ACPI: irq: Fix incorrect return value in acpi_register_gsi() Thomas Gleixner (1): hrtimers: Push pending hrtimers away from outgoing CPU earlier Yan Zhai (1): ipv6: avoid atomic fragment on GSO packets Yu Liao (1): cpu/hotplug: fix kabi breakage in enum cpuhp_state -- 2.34.1

1 23

[PATCH OLK-6.6 0/2] Open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32
by Jinjie Ruan 07 Dec '23

07 Dec '23

Update script for check & update openeuler_defconfig. And open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32. Jinjie Ruan (2): kconfig: Update script for check & update openeuler_defconfig config: Open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32 arch/arm64/configs/openeuler_defconfig | 14 +++++++++++--- scripts/kconfig/makeconfig.sh | 3 +++ 2 files changed, 14 insertions(+), 3 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6 0/2] Open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32
by Jinjie Ruan 07 Dec '23

07 Dec '23

Update script for check & update openeuler_defconfig. And open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32. Jinjie Ruan (2): kconfig: Update script for check & update openeuler_defconfig config: Open CONFIG_AARCH32_EL0 and close CONFIG_ARM64_ILP32 arch/arm64/configs/openeuler_defconfig | 14 +++++++++++--- scripts/kconfig/makeconfig.sh | 3 +++ 2 files changed, 14 insertions(+), 3 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] support clear free list
by Yu Liao 07 Dec '23

07 Dec '23

support clear free list Yu Liao (2): mm: Add sysctl to clear free list pages config: make CONFIG_CLEAR_FREELIST_PAGE not set by default .../admin-guide/kernel-parameters.txt | 3 + Documentation/admin-guide/sysctl/vm.rst | 13 ++ arch/arm64/configs/openeuler_defconfig | 1 + mm/Kconfig | 13 ++ mm/Makefile | 2 + mm/clear_freelist_page.c | 187 ++++++++++++++++++ 6 files changed, 219 insertions(+) create mode 100644 mm/clear_freelist_page.c -- 2.33.0

2 3

[PATCH OLK-5.10 0/1] iommu/arm-smmu-v3: disable stall for quiet_cd
by Chen Jun 07 Dec '23

07 Dec '23

*** BLURB HERE *** Wenkai Lin (1): iommu/arm-smmu-v3: disable stall for quiet_cd drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.17.1

2 3

答复: openEuler Kernel SIG 双周例会提醒//openEuler Kernel SIG双周例会
by liaotao (C) 07 Dec '23

07 Dec '23

主题：openEuler Kernel SIG双周例会时间：2023年12月8日星期五 14:00-15:45 会议内容： 1. 进展update 2. 议题征集中（新增议题可回复邮件申报，也可直接填至会议看板：https://etherpad.openeuler.org/p/Kernel-meetings） -----原始约会----- 发件人: openEuler conference <public(a)openeuler.org> 发送时间: 2023年12月4日 16:00 收件人: dev@openeuler.org,kernel-discuss@openeuler.org,kernel@openeuler.org 主题: openEuler Kernel SIG双周例会时间: 2023年12月8日星期五 14:00-15:45(UTC+08:00) 北京，重庆，香港特别行政区，乌鲁木齐。地点: 您好！ Kernel SIG 邀请您参加 2023-12-08 14:00 召开的WeLink会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中（新增议题可回复邮件申报，也可直接填至会议看板）会议链接：https://bmeeting.huaweicloud.com:36443/#/j/981980862 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the WeLink conference(auto recording) will be held at 2023-12-08 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中（新增议题可回复邮件申报，也可直接填至会议看板） You can join the meeting at https://bmeeting.huaweicloud.com:36443/#/j/981980862. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()
by Yu Liao 07 Dec '23

07 Dec '23

From: Waiman Long <longman(a)redhat.com> stable inclusion from stable-v4.19.299 commit 55d1e6231a0b98ffcc5eacdae995fa7bd74bf6a0 bugzilla: https://gitee.com/openeuler/kernel/issues/I8MCB5 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ca10d851b9ad0338c19e8e3089e24d565ebfffd7 ] Commit 5c0338c68706 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered") enabled implicit ordered attribute to be added to WQ_UNBOUND workqueues with max_active of 1. This prevented the changing of attributes to these workqueues leading to fix commit 0a94efb5acbb ("workqueue: implicit ordered attribute should be overridable"). However, workqueue_apply_unbound_cpumask() was not updated at that time. So sysfs changes to wq_unbound_cpumask has no effect on WQ_UNBOUND workqueues with implicit ordered attribute. Since not all WQ_UNBOUND workqueues are visible on sysfs, we are not able to make all the necessary cpumask changes even if we iterates all the workqueue cpumasks in sysfs and changing them one by one. Fix this problem by applying the corresponding change made to apply_workqueue_attrs_locked() in the fix commit to workqueue_apply_unbound_cpumask(). Fixes: 5c0338c68706 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered") Signed-off-by: Waiman Long <longman(a)redhat.com> Signed-off-by: Tejun Heo <tj(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: kernel/workqueue.c Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> --- kernel/workqueue.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3ce68188ad0b..0b2eba803e30 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5293,8 +5293,11 @@ static int workqueue_apply_unbound_cpumask(void) if (!(wq->flags & WQ_UNBOUND)) continue; /* creating multiple pwqs breaks ordering guarantee */ - if ((wq->flags & __WQ_ORDERED) && !(wq->flags & __WQ_DYNAMIC)) - continue; + if (!list_empty(&wq->pwqs)) { + if ((wq->flags & __WQ_ORDERED_EXPLICIT) && !(wq->flags & __WQ_DYNAMIC)) + continue; + wq->flags &= ~__WQ_ORDERED; + } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); if (!ctx) { -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] icmp: Fix a data-race around sysctl_icmp_errors_use_inbound_ifaddr.
by Zhengchao Shao 07 Dec '23

07 Dec '23

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v5.19-rc7 commit d2efabce81db7eed1c98fa1a3f203f0edd738ac3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MEXU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- While reading sysctl_icmp_errors_use_inbound_ifaddr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 1c2fb7f93cb2 ("[IPV4]: Sysctl configurable icmp error source address.") Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/sysctl_net_ipv4.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/icmp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a4f838ec7c75..8a39b12611e1 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -710,7 +710,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) -- 2.34.1

2 1

[PATCH OLK-5.10 1/1] iommu/arm-smmu-v3: disable stall for quiet_cd
by Chen Jun 07 Dec '23

07 Dec '23

From: Wenkai Lin <linwenkai6(a)hisilicon.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8MCHF CVE: NA Reference: https://lore.kernel.org/all/20231206005517.46005-1-zhangfei.gao@linaro.org/… -------------------------------- In the stall model, invalid transactions were expected to be stalled and aborted by the IOPF handler. However, when killing a test case with a huge amount of data, the accelerator streamline can not stop until all data is consumed even if the page fault handler reports errors. As a result, the kill may take a long time, about 10 seconds with numerous iopf interrupts. So disable stall for quiet_cd in the non-force stall model, since force stall model (STALL_MODEL==0b10) requires CD.S must be 1. Signed-off-by: Zhangfei Gao <zhangfei.gao(a)linaro.org> Signed-off-by: Wenkai Lin <linwenkai6(a)hisilicon.com> Suggested-by: Jean-Philippe Brucker <jean-philippe(a)linaro.org> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 ++ 1 file changed, 2 insertions(+) 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 9a71cdb93817..a55c2dab72f8 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1277,6 +1277,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid, if (!cd) { /* (5) */ val = 0; } else if (cd == &quiet_cd) { /* (4) */ + if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) + val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R); val |= CTXDESC_CD_0_TCR_EPD0; } else if (cd_live) { /* (3) */ val &= ~CTXDESC_CD_0_ASID; -- 2.17.1

2 2

[PATCH OLK-5.10 0/2] Fixed two memory leak issues of the Perf tool
by Junhao He 07 Dec '23

07 Dec '23

Fixed two memory leak issues of the Perf tool: a) perf hisi-ptt: Fix memory leak in lseek failure handling b) perf header: Fix one memory leakage in perf_event__fprintf_event_update Kuan-Wei Chiu (1): perf hisi-ptt: Fix memory leak in lseek failure handling Yicong Yang (1): perf header: Fix one memory leakage in perf_event__fprintf_event_update() tools/perf/util/header.c | 6 ++++-- tools/perf/util/hisi-ptt.c | 4 +++- 2 files changed, 7 insertions(+), 3 deletions(-) -- 2.33.0

2 3

[PATCH v4 OLK-6.6 0/5] Support Qos Scheduler
by Wenyu Huang 07 Dec '23

07 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 + include/linux/sched/sysctl.h | 5 + init/Kconfig | 12 + kernel/cgroup/cgroup.c | 22 ++ kernel/sched/core.c | 155 +++++++++++ kernel/sched/fair.c | 356 ++++++++++++++++++++++++- kernel/sched/sched.h | 12 + kernel/signal.c | 3 + kernel/sysctl.c | 24 ++ 13 files changed, 610 insertions(+), 1 deletion(-) -- 2.34.1

2 6

[PATCH OLK-5.10 0/1] mbigen/vtimer: isolate mbigen vtimer
by Dongxu Sun 07 Dec '23

07 Dec '23

Dongxu Sun (1): mbigen: vtimer: isolate mbigen vtimer funcs with macro include/clocksource/arm_arch_timer.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) -- 2.33.0

2 2

[PATCH OLK-6.6 00/16] arm32/arm64/x86_64: Support basic livepatch function
by Zheng Yejian 07 Dec '23

07 Dec '23

Port patches from v5.10 to support basic livepatch function on arch arm32/arm64/x86_64. Zheng Yejian (16): 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 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/kernel/Makefile | 1 + arch/arm/kernel/livepatch.c | 256 ++++ 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 | 1231 +++++++++++++++++++- 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 + 45 files changed, 2520 insertions(+), 43 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

1 16

[PATCH openEuler-1.0-LTS] icmp: Fix a data-race around sysctl_icmp_errors_use_inbound_ifaddr.
by Zhengchao Shao 07 Dec '23

07 Dec '23

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v5.19-rc7 commit d2efabce81db7eed1c98fa1a3f203f0edd738ac3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MEXU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- While reading sysctl_icmp_errors_use_inbound_ifaddr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 1c2fb7f93cb2 ("[IPV4]: Sysctl configurable icmp error source address.") Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/sysctl_net_ipv4.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/icmp.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a4f838ec7c75..8a39b12611e1 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -710,7 +710,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 2644e1249a42..1c5abae1e6c7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -578,7 +578,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", -- 2.34.1

2 1

[PATCH OLK-5.10] icmp: Fix a data-race around sysctl_icmp_errors_use_inbound_ifaddr.
by Zhengchao Shao 07 Dec '23

07 Dec '23

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v5.19-rc7 commit d2efabce81db7eed1c98fa1a3f203f0edd738ac3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8MEXU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- While reading sysctl_icmp_errors_use_inbound_ifaddr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 1c2fb7f93cb2 ("[IPV4]: Sysctl configurable icmp error source address.") Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/ipv4/sysctl_net_ipv4.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- net/ipv4/icmp.c | 2 +- net/ipv4/sysctl_net_ipv4.c | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 0bbc047e8f6e..7041f73d5be6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -703,7 +703,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index bd158fdaf547..a013df55e933 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -613,7 +613,9 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP2 00/23] Add error handle for driver
by Li Nan 07 Dec '23

07 Dec '23

And revert redundant patches of nbd to resolve conflict. Christoph Hellwig (9): block: add blk_alloc_disk and blk_cleanup_disk APIs blk-mq: add the blk_mq_alloc_disk APIs loop: use blk_mq_alloc_disk and blk_cleanup_disk loop: fix order of cleaning up the queue and freeing the tagset nbd: use blk_mq_alloc_disk and blk_cleanup_disk block: add a flag to make put_disk on partially initalized disks safer nvme: use blk_mq_alloc_disk brd: convert to blk_alloc_disk/blk_cleanup_disk ubi: use blk_mq_alloc_disk and blk_cleanup_disk Dan Carpenter (1): blk-mq: fix an IS_ERR() vs NULL bug Li Lingfeng (1): nbd: fix uaf in nbd_open Li Nan (1): nbd: Revert redundant patches of nbd first_minor Luis Chamberlain (7): loop: add error handling support for add_disk() nbd: add error handling support for add_disk() nvme: add error handling support for add_disk() block/brd: add error handling support for add_disk() scsi: sd: Add error handling support for add_disk() scsi: sr: Add error handling support for add_disk() mtd/ubi/block: add error handling support for add_disk() Wang Qing (1): nbd: fix order of cleaning up the queue and freeing the tagset Zhong Jinghua (3): scsi: sd: Clean up sdkp if device_add_disk() failed mtd/ubi/block: Fix null pointer dereference issue in error path mtd/ubi/block: Fix uaf problem in ubiblock_cleanup include/linux/blk-mq.h | 12 +++++ include/linux/genhd.h | 23 +++++++++ block/blk-mq.c | 19 ++++++++ block/genhd.c | 42 +++++++++++++++- drivers/block/brd.c | 103 +++++++++++++++++---------------------- drivers/block/loop.c | 26 +++++----- drivers/block/nbd.c | 70 ++++++++++---------------- drivers/mtd/ubi/block.c | 76 ++++++++++++++--------------- drivers/nvme/host/core.c | 41 ++++++++-------- drivers/scsi/sd.c | 8 ++- drivers/scsi/sr.c | 7 ++- 11 files changed, 246 insertions(+), 181 deletions(-) -- 2.39.2

2 24

[OLK-5.10 v2 00/10] A set of patches for openEuler
by Chengchang Tang 07 Dec '23

07 Dec '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Some cleanups. Chengchang Tang (5): RDMA/hns: Replace magic number when fill ADDR to HW RDMA/hns: Remove extra blank line in get_sge_num_from_max_inl_data() RDMA/hns: Remove unused parameters detected by -Wextra RDMA/hns: Refactor mtr find RDMA/hns: Remove useless NULL check in hns_roce_get_netdev() Junxian Huang (2): RDMA/hns: Improve readability of check_bond_support() RDMA/hns: Add more check for bonding-unsupported cases Yangyang Li (1): RDMA/hns: Use macro instead of magic number wenglianfa (2): RDMA/hns: Fix the spin_lock and spin_unlock objects are inconsistent RDMA/hns: Cleanup for debugfs drivers/infiniband/hw/hns/hns_roce_alloc.c | 5 +- drivers/infiniband/hw/hns/hns_roce_bond.c | 107 ++++++++----- drivers/infiniband/hw/hns/hns_roce_cq.c | 11 +- drivers/infiniband/hw/hns/hns_roce_dca.c | 13 +- drivers/infiniband/hw/hns/hns_roce_dca.h | 3 +- drivers/infiniband/hw/hns/hns_roce_debugfs.c | 14 +- drivers/infiniband/hw/hns/hns_roce_debugfs.h | 4 +- drivers/infiniband/hw/hns/hns_roce_device.h | 13 +- drivers/infiniband/hw/hns/hns_roce_hem.c | 13 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 157 +++++++++---------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 12 ++ drivers/infiniband/hw/hns/hns_roce_main.c | 5 +- drivers/infiniband/hw/hns/hns_roce_mr.c | 95 +++++++---- drivers/infiniband/hw/hns/hns_roce_qp.c | 15 +- drivers/infiniband/hw/hns/hns_roce_srq.c | 4 +- 15 files changed, 263 insertions(+), 208 deletions(-) -- 2.30.0

1 10

[PATCH OLK-5.10 0/2] Fixed two memory leak issues of the Perf tool
by Junhao He 07 Dec '23

07 Dec '23

Fixed two memory leak issues of the Perf tool: a) perf hisi-ptt: Fix memory leak in lseek failure handling b) perf header: Fix one memory leakage in perf_event__fprintf_event_update Kuan-Wei Chiu (1): perf hisi-ptt: Fix memory leak in lseek failure handling Yicong Yang (1): perf header: Fix one memory leakage in perf_event__fprintf_event_update() tools/perf/util/header.c | 6 ++++-- tools/perf/util/hisi-ptt.c | 4 +++- 2 files changed, 7 insertions(+), 3 deletions(-) -- 2.33.0

1 2

[src-openEuler/rdma-core-v6 0/4] A seires of bugfix
by Chengchang Tang 07 Dec '23

07 Dec '23

From: Ran Zhou <zhouran10(a)h-partners.com> Correct the retrun of error codes, add pthread spinlock and init judgment and removes a repeated init, fix owner bit when SQ wraps. Chengchang Tang (2): libhns: Fix parent domain unsupported comp mask libhns: Fix owner bit when SQ wraps around in new IO Ran Zhou (1): libhns: Removes a repeated initialization of a spinlock Wenpeng Liang (1): libhns: Add pthread_spin_destroy()/pthread_mutex_destroy() providers/hns/hns_roce_u.c | 61 +++++++++++++++++++++++++++----- providers/hns/hns_roce_u_hw_v2.c | 8 +---- providers/hns/hns_roce_u_verbs.c | 23 +++++++----- 3 files changed, 68 insertions(+), 24 deletions(-) -- 2.30.0

1 4

[PATCH OLK-5.10 0/1] iommu/arm-smmu-v3: disable stall for quiet_cd
by Chen Jun 07 Dec '23

07 Dec '23

In the stall model, invalid transactions were expected to be stalled and aborted by the IOPF handler. *** BLURB HERE *** Wenkai Lin (1): iommu/arm-smmu-v3: disable stall for quiet_cd drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 ++ 1 file changed, 2 insertions(+) -- 2.17.1

1 1

[PATCH openEuler-1.0-LTS 0/2] net: hns: fix fake link up
by Yonglong Liu 06 Dec '23

06 Dec '23

This patch set fix fake link up problem and modify the driver version. Yonglong Liu (2): net: hns: fix fake link up on xge port net: hns: update hns version to 23.12.1 drivers/net/ethernet/hisilicon/hns/hnae.h | 2 +- .../net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 29 +++++++++++++++++++ drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 3 files changed, 31 insertions(+), 2 deletions(-) -- 2.17.1

2 3

[PATCH openEuler-1.0-LTS 0/2] net: hns: fix fake link up
by Yonglong Liu 06 Dec '23

06 Dec '23

This patch set fix fake link up problem and modify the driver version. Yonglong Liu (2): net: hns: fix fake link up on xge port net: hns: update hns version to 23.12.1 drivers/net/ethernet/hisilicon/hns/hnae.h | 2 +- .../net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 29 +++++++++++++++++++ drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +- 3 files changed, 31 insertions(+), 2 deletions(-) -- 2.17.1

2 4

[PATCH OLK-6.6 00/10] kabi: add kabi helper macros and tools
by Jialin Zhang 06 Dec '23

06 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 v3 00/15] Ascend features
by Yuan Can 06 Dec '23

06 Dec '23

Jiankang Chen (1): iort: Read ACPI configure to get streamid. Lijun Fang (2): svm: add support for allocing memory which is within 4G physical address in svm_mmap arm64/ascend: Enable DvPP mmap features for Ascend Platform Navid Emamdoost (1): nbd_genl_status: null check for nla_nest_start Weilong Chen (4): arm64: Add MIDR encoding for HiSilicon Taishan CPUs ACPI / APEI: Notify all ras err to driver cache: Workaround HiSilicon Taishan DC CVAU arm64: Fix conflict for capability when cpu hotplug Xu Qiang (4): serial: amba-pl011: Fix serial port discard interrupt when interrupt signal line of serial port is connected to mbigen. 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 irq-gic-v3: Fix too large cpu_count Zhang Jian (3): mm: export collect_procs() cpu-feature: Enable Taisan IDC feature for Taishan core version iommu: bugfix for missing symbols when build arm_smmu_v3.ko Documentation/arch/arm64/silicon-errata.rst | 2 + arch/alpha/include/uapi/asm/mman.h | 1 + arch/arm64/Kconfig | 38 +++ arch/arm64/include/asm/cache.h | 9 + arch/arm64/include/asm/cputype.h | 2 + arch/arm64/kernel/cpu_errata.c | 34 +++ arch/mips/include/uapi/asm/mman.h | 1 + arch/parisc/include/uapi/asm/mman.h | 1 + arch/powerpc/include/uapi/asm/mman.h | 1 + arch/sparc/include/uapi/asm/mman.h | 1 + arch/xtensa/include/uapi/asm/mman.h | 1 + drivers/acpi/apei/ghes.c | 4 +- drivers/block/nbd.c | 6 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 14 ++ drivers/irqchip/Kconfig | 10 + drivers/irqchip/irq-gic-v3-its.c | 254 +++++++++++++++++++- drivers/irqchip/irq-gic-v3.c | 101 +++++++- drivers/tty/serial/Kconfig | 18 ++ drivers/tty/serial/amba-pl011.c | 66 +++++ fs/hugetlbfs/inode.c | 16 ++ include/linux/irqchip/arm-gic-v3.h | 5 + include/linux/mm.h | 3 + include/linux/mman.h | 64 +++++ include/uapi/asm-generic/mman.h | 1 + mm/memory-failure.c | 3 +- mm/mmap.c | 44 ++++ 26 files changed, 690 insertions(+), 10 deletions(-) -- 2.17.1

2 16

[PATCH OLK-6.6 v2 00/16] *** ASCEND features ***
by Yuan Can 06 Dec '23

06 Dec '23

*** BLURB HERE *** Jiankang Chen (1): iort: Read ACPI configure to get streamid. Lewis Huang (1): drm/amd/display: Change the DMCUB mailbox memory location from FB to inbox Lijun Fang (2): svm: add support for allocing memory which is within 4G physical address in svm_mmap arm64/ascend: Enable DvPP mmap features for Ascend Platform Navid Emamdoost (1): nbd_genl_status: null check for nla_nest_start Weilong Chen (4): arm64: Add MIDR encoding for HiSilicon Taishan CPUs ACPI / APEI: Notify all ras err to driver cache: Workaround HiSilicon Taishan DC CVAU arm64: Fix conflict for capability when cpu hotplug Xu Qiang (4): serial: amba-pl011: Fix serial port discard interrupt when interrupt signal line of serial port is connected to mbigen. 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 irq-gic-v3: Fix too large cpu_count Zhang Jian (3): mm: export collect_procs() cpu-feature: Enable Taisan IDC feature for Taishan core version iommu: bugfix for missing symbols when build arm_smmu_v3.ko -- 2.17.1

2 17

[PATCH OLK-6.6 0/3] cgroupv1 enable writeback
by pkwarcraft＠gmail.com 06 Dec '23

06 Dec '23

From: chenridong <chenridong(a)huawei.com> 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

1 3

[PATCH openEuler-22.03-LTS-SP1 v2 1/6] net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop()
by Dapeng Yu 06 Dec '23

06 Dec '23

From: Florian Fainelli <f.fainelli(a)gmail.com> stable inclusion from stable-v5.10.181 commit e92727ed9e8b6798efc1e7ae44bbe7c44c453670 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8L4MY Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 93e0401e0fc0c54b0ac05b687cd135c2ac38187c ] The call to phy_stop() races with the later call to phy_disconnect(), resulting in concurrent phy_suspend() calls being run from different CPUs. The final call to phy_disconnect() ensures that the PHY is stopped and suspended, too. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Signed-off-by: Florian Fainelli <f.fainelli(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dapeng Yu <dapeng.yu(a)windriver.com> --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 6ee6c34f28f2..52c93701a9e4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3408,7 +3408,6 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); - phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); -- 2.43.0

1 5

[PATCH openEuler-22.03-LTS-SP1 v2 0/6] backport Broadcom NIC driver patches
by Dapeng Yu 06 Dec '23

06 Dec '23

Backport the latest patches from upstream stable branch linux-5.10.y for Broadcom NIC driver. Florian Fainelli (2): net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop() net: bcmgenet: Restore phy_stop() depending upon suspend/close Somnath Kotur (2): bnxt_en: Query default VLAN before VNIC setup on a VF bnxt_en: Implement .set_port / .unset_port UDP tunnel callbacks Sreekanth Reddy (1): bnxt_en: Don't issue AP reset during ethtool's reset operation Tobias Heider (1): Add MODULE_FIRMWARE() for FIRMWARE_TG357766. drivers/net/ethernet/broadcom/bnxt/bnxt.c | 28 ++++++++++++++----- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- .../net/ethernet/broadcom/genet/bcmgenet.c | 9 +++--- drivers/net/ethernet/broadcom/tg3.c | 1 + 4 files changed, 28 insertions(+), 12 deletions(-) -- 2.43.0

1 0

[PATCH OLK-6.6 0/3] cgroupv1 enable writeback
by chenridong 06 Dec '23

06 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

1 3

[PATCH OLK-6.6 0/3] cgroupv1 enable writeback
by chenridong 06 Dec '23

06 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

1 3

[PATCH openEuler-22.03-LTS-SP2 00/23] Add error handle for driver
by Li Nan 06 Dec '23

06 Dec '23

And revert redundant patches of nbd to resolve conflict. Christoph Hellwig (9): block: add blk_alloc_disk and blk_cleanup_disk APIs blk-mq: add the blk_mq_alloc_disk APIs loop: use blk_mq_alloc_disk and blk_cleanup_disk loop: fix order of cleaning up the queue and freeing the tagset nbd: use blk_mq_alloc_disk and blk_cleanup_disk block: add a flag to make put_disk on partially initalized disks safer nvme: use blk_mq_alloc_disk brd: convert to blk_alloc_disk/blk_cleanup_disk ubi: use blk_mq_alloc_disk and blk_cleanup_disk Dan Carpenter (1): blk-mq: fix an IS_ERR() vs NULL bug Li Lingfeng (1): nbd: fix uaf in nbd_open Li Nan (1): nbd: Revert redundant patches of nbd first_minor Luis Chamberlain (7): loop: add error handling support for add_disk() nbd: add error handling support for add_disk() nvme: add error handling support for add_disk() block/brd: add error handling support for add_disk() scsi: sd: Add error handling support for add_disk() scsi: sr: Add error handling support for add_disk() mtd/ubi/block: add error handling support for add_disk() Wang Qing (1): nbd: fix order of cleaning up the queue and freeing the tagset Zhong Jinghua (3): scsi: sd: Clean up sdkp if device_add_disk() failed mtd/ubi/block: Fix null pointer dereference issue in error path mtd/ubi/block: Fix uaf problem in ubiblock_cleanup include/linux/blk-mq.h | 12 +++++ include/linux/genhd.h | 23 +++++++++ block/blk-mq.c | 19 ++++++++ block/genhd.c | 42 +++++++++++++++- drivers/block/brd.c | 103 +++++++++++++++++---------------------- drivers/block/loop.c | 26 +++++----- drivers/block/nbd.c | 70 ++++++++++---------------- drivers/mtd/ubi/block.c | 76 ++++++++++++++--------------- drivers/nvme/host/core.c | 41 ++++++++-------- drivers/scsi/sd.c | 8 ++- drivers/scsi/sr.c | 7 ++- 11 files changed, 246 insertions(+), 181 deletions(-) -- 2.39.2

1 23

[PATCH OLK-5.10 v2] net: txgbe: Fix memleak in txgbe_calc_eeprom_checksum()
by Dapeng Yu 06 Dec '23

06 Dec '23

From: YueHaibing <yuehaibing(a)huawei.com> mainline inclusion from mainline-v6.2-rc1 commit a068d33e542f5d5be2e5de3cf1122c4347d3e2af category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LOJU Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- eeprom_ptrs should be freed before returned. Fixes: 049fe5365324 ("net: txgbe: Add operations to interact with firmware") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Dapeng Yu <dapeng.yu(a)windriver.com> --- v2: * remove lines from commit message to pass format check drivers/net/ethernet/netswift/txgbe/txgbe_hw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c b/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c index 55f98a55f4b6..929f03c42132 100644 --- a/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c @@ -6925,6 +6925,7 @@ s32 txgbe_calc_eeprom_checksum(struct txgbe_hw *hw) eeprom_ptrs); if (status) { DEBUGOUT("Failed to read EEPROM image\n"); + kvfree(eeprom_ptrs); return status; } local_buffer = eeprom_ptrs; -- 2.43.0

2 1

[PATCH OLK-6.6 01/17] mm: export symbol find_get_task_by_vpid
by Yuan Can 06 Dec '23

06 Dec '23

From: Jean-Philippe Brucker <jean-philippe.brucker(a)arm.com> maillist inclusion category: feature bugzilla: 51855 Reference: https://jpbrucker.net/git/linux/commit/?h=sva/2021-03-01&id=176b3454e53ffdd… --------------------------------------------- Userspace drivers implemented with VFIO might want to bind sub-processes to their devices. In a VFIO ioctl, they provide a pid that is used to find a task and its mm. Since VFIO can be built as a module, export the find_get_task_by_vpid symbol. Signed-off-by: Jean-Philippe Brucker <jean-philippe(a)linaro.org> Signed-off-by: Lijun Fang <fanglijun3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(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

3 19

[PATCH OLK-5.10] net: txgbe: Fix memleak in txgbe_calc_eeprom_checksum()
by Dapeng Yu 06 Dec '23

06 Dec '23

From: YueHaibing <yuehaibing(a)huawei.com> mainline inclusion from mainline-v6.2 commit a068d33e542f5d5be2e5de3cf1122c4347d3e2af category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LOJU CVE: NA backport: OLK-5.10, openEuler-22.03-LTS, openEuler-22.03-LTS-SP1, openEuler-22.03-LTS-SP2 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- eeprom_ptrs should be freed before returned. Fixes: 049fe5365324 ("net: txgbe: Add operations to interact with firmware") Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Dapeng Yu <dapeng.yu(a)windriver.com> --- drivers/net/ethernet/netswift/txgbe/txgbe_hw.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c b/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c index 55f98a55f4b6..929f03c42132 100644 --- a/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/netswift/txgbe/txgbe_hw.c @@ -6925,6 +6925,7 @@ s32 txgbe_calc_eeprom_checksum(struct txgbe_hw *hw) eeprom_ptrs); if (status) { DEBUGOUT("Failed to read EEPROM image\n"); + kvfree(eeprom_ptrs); return status; } local_buffer = eeprom_ptrs; -- 2.43.0

2 1

[PATCH OLK-5.10 v2] hinic: ethtool: Allow userspace to set more aggregation params
by Xiongfeng Wang 06 Dec '23

06 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M4TP CVE: NA -------------------------------- Allow userspace to set the following interrupt aggregation params by ethtool: Adaptive RX:on/off rx/tx-usecs rx/tx-usecs-low/high rx/tx-frames rx/tx-frames-low/high Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 26d695684cfb..a271e38d8618 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -2412,6 +2412,9 @@ static const struct ethtool_ops hinic_ethtool_ops = { static const struct ethtool_ops hinicvf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USECS_LOW_HIGH | + ETHTOOL_COALESCE_MAX_FRAMES_LOW_HIGH | ETHTOOL_COALESCE_PKT_RATE_RX_USECS, .get_link_ksettings = hinic_get_link_ksettings, .get_drvinfo = hinic_get_drvinfo, -- 2.20.1

2 1

[PATCH OLK-5.10] hinic: ethtool: Allow userspace to set more aggregation params
by Xiongfeng Wang 06 Dec '23

06 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M4TP CVE: NA -------------------------------- Allow userspace to set the following interrupt aggregation params by ethtool: Adaptive RX:on/off rx/tx-usecs rx/tx-usecs-low/high rx/tx-frames rx/tx-frames-low/high Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 26d695684cfb..b65683b0548e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -2411,8 +2411,12 @@ static const struct ethtool_ops hinic_ethtool_ops = { }; static const struct ethtool_ops hinicvf_ethtool_ops = { - .supported_coalesce_params = ETHTOOL_COALESCE_USECS | - ETHTOOL_COALESCE_PKT_RATE_RX_USECS, + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USECS_LOW_HIGH | + ETHTOOL_COALESCE_MAX_FRAMES_LOW_HIGH | + ETHTOOL_COALESCE_PKT_RATE_RX_USECS, + .get_link_ksettings = hinic_get_link_ksettings, .get_drvinfo = hinic_get_drvinfo, .get_msglevel = hinic_get_msglevel, -- 2.20.1

2 1

[PATCH OLK-5.10] md/raid5: fix miscalculation of 'end_sector' in raid5_read_one_chunk()
by Li Nan 06 Dec '23

06 Dec '23

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-v6.4-rc5 commit 8557dc27126949c702bd3aafe8a7e0b7e4fcb44c category: bugfix bugzilla: 189405, https://gitee.com/openeuler/kernel/issues/I8LZMK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 'end_sector' is compared to 'rdev->recovery_offset', which is offset to rdev, however, commit e82ed3a4fbb5 ("md/raid6: refactor raid5_read_one_chunk") changes the calculation of 'end_sector' to offset to the array. Fix this miscalculation. Fixes: e82ed3a4fbb5 ("md/raid6: refactor raid5_read_one_chunk") Cc: stable(a)vger.kernel.org # v5.12+ Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Song Liu <song(a)kernel.org> Link: https://lore.kernel.org/r/20230524014118.3172781-1-yukuai1@huaweicloud.com Conflict: Commit 2c897e63a100 ("[Backport] md/raid6: refactor raid5_read_one_chunk") missed the space of the previous line. Signed-off-by: Li Nan <linan122(a)huawei.com> --- drivers/md/raid5.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5af25898baad..b4d004b623e7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5408,8 +5408,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) } sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0, - &dd_idx, NULL); - end_sector = bio_end_sector(raid_bio); + &dd_idx, NULL); + end_sector = sector + bio_sectors(raid_bio); rcu_read_lock(); if (r5c_big_stripe_cached(conf, sector)) -- 2.39.2

2 1

[PATCH OLK-5.10 00/27] KVM/arm64: support vtimer/virt_dev irqbypass
by Dongxu Sun 06 Dec '23

06 Dec '23

Dongxu Sun (1): KVM: arm64: update arm64 openeuler_defconfig for CONFIG_VIRT_PLAT_DEV Haibin Wang (2): KVM: arm64: arch_timer: Probe vtimer irqbypass capability KVM: arm64: arch_timer: Rework vcpu init/reset logic Kunkun Jiang (6): mbigen: vtimer mbigen driver support irqchip/gic-v4.1: Detect ITS vtimer interrupt bypass capability irqchip/gic-v4.1: Extend VSGI command to support the new vPPI mbigen: vtimer: add support for MBIX1_CPPI_NEGEDGE_CLR_EN_SETR(CLRR) KVM: arm64: vgic-v3: Clearing pending status of vtimer on guest reset mbigen: Sets the regs related to vtimer irqbypass Zenghui Yu (4): KVM: arm64: GICv4.1: Add direct injection capability to PPI registers KVM: arm64: GICv4.1: Allow non-trapping WFI when using direct vtimer interrupt KVM: arm64: vtimer: Expose HW-based vtimer interrupt in debugfs KVM: arm64: arch_timer: Make vtimer_irqbypass a Distributor attr wanghaibin (14): irqchip/gic-v4.1: Rework get/set_irqchip_state callbacks of GICv4.1-sgi chip irqchip/gic-v4.1: Rework its_alloc_vcpu_sgis() to support vPPI allocation irqchip/gic-v4.1: Probe vtimer irqbypass capability at RD level KVM: arm64: GICv4.1: Inform the HiSilicon vtimer irqbypass capability KVM: arm64: vgic: Add helper for vtimer vppi info register KVM: arm64: GICv4.1: Enable vtimer vPPI irqbypass config KVM: arm64: GICv4.1: Add support for MBIGEN save/restore irqchip/gic-v3-its: Introduce the reserved device ID pools irqchip/gic-v3-its: Alloc/Free device id from pools for virtual devices irqchip/gic-v3-its: Add virt platform devices MSI support virt_plat_dev: Register the virt platform device driver KVM: arm64: Introduce shadow device KVM: arm64: kire: irq routing entry cached the relevant cache data KVM: arm64: sdev: Support virq bypass by INT/VSYNC command arch/arm64/configs/openeuler_defconfig | 1 + arch/arm64/include/asm/kvm_emulate.h | 1 + arch/arm64/kvm/Makefile | 2 +- arch/arm64/kvm/arch_timer.c | 218 +++++++- arch/arm64/kvm/arm.c | 42 ++ arch/arm64/kvm/vgic/shadow_dev.c | 327 ++++++++++++ arch/arm64/kvm/vgic/vgic-debug.c | 2 +- arch/arm64/kvm/vgic/vgic-init.c | 6 + arch/arm64/kvm/vgic/vgic-irqfd.c | 39 ++ arch/arm64/kvm/vgic/vgic-mmio-v3.c | 15 +- arch/arm64/kvm/vgic/vgic-mmio.c | 24 +- arch/arm64/kvm/vgic/vgic-v3.c | 8 + arch/arm64/kvm/vgic/vgic-v4.c | 57 +++ arch/arm64/kvm/vgic/vgic.c | 24 + arch/arm64/kvm/vgic/vgic.h | 11 + drivers/irqchip/irq-gic-phytium-2500-its.c | 2 +- drivers/irqchip/irq-gic-v3-its-platform-msi.c | 39 +- drivers/irqchip/irq-gic-v3-its.c | 277 +++++++++- drivers/irqchip/irq-gic-v3.c | 37 +- drivers/irqchip/irq-gic-v4.c | 23 +- drivers/irqchip/irq-mbigen.c | 472 ++++++++++++++++++ drivers/misc/Kconfig | 9 + drivers/misc/Makefile | 1 + drivers/misc/virt_plat_dev.c | 119 +++++ include/clocksource/arm_arch_timer.h | 15 + include/kvm/arm_arch_timer.h | 13 + include/kvm/arm_vgic.h | 62 +++ include/linux/irqchip/arm-gic-common.h | 3 + include/linux/irqchip/arm-gic-v3.h | 49 +- include/linux/irqchip/arm-gic-v4.h | 6 +- include/linux/kvm_host.h | 9 + include/linux/msi.h | 2 + include/uapi/linux/kvm.h | 9 + virt/kvm/eventfd.c | 8 + 34 files changed, 1869 insertions(+), 63 deletions(-) create mode 100644 arch/arm64/kvm/vgic/shadow_dev.c create mode 100644 drivers/misc/virt_plat_dev.c -- 2.33.0

1 27

[PATCH OLK-6.6 0/3] cgroupv1 enable writeback
by chenridong 05 Dec '23

05 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 5

[PATCH OLK-6.6 v5 0/2] ipvlan: Introduce l2e mode
by Zhengchao Shao 05 Dec '23

05 Dec '23

Inherited features of olk5.10 version. Keefe LIU (2): ipvlan: Introduce l2e mode ipvlan: Introduce local xmit queue for l2e mode drivers/net/Kconfig | 7 + drivers/net/ipvlan/ipvlan.h | 11 ++ drivers/net/ipvlan/ipvlan_core.c | 232 +++++++++++++++++++++++++++++++ drivers/net/ipvlan/ipvlan_main.c | 103 +++++++++++++- include/uapi/linux/if_link.h | 1 + 5 files changed, 352 insertions(+), 2 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6] block: fix inaccurate io_ticks by set 'precise_iostat'
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Zhang Wensheng <zhangwensheng5(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M01Q CVE: NA -------------------------------- After introducing commit 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting"), '%util' accounted by iostat will be over reality data. In fact, the device is quite idle, but iostat may show '%util' as a big number (e.g. 50%). It can produce by fio: fio --name=1 --direct=1 --bs=4k --rw=read --filename=/dev/sda \ --thinktime=4ms --runtime=180 We fix this by using a switch(precise_iostat=1) to control whether or not acconut ioticks precisely. fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting") Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: block/blk-core.c block/blk-merge.c block/genhd.c include/linux/blkdev.h Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- block/blk-core.c | 25 +++++++++++++++++++++++-- block/blk-merge.c | 2 ++ block/blk-mq.c | 4 ++++ block/genhd.c | 2 +- include/linux/blkdev.h | 2 ++ 5 files changed, 32 insertions(+), 3 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index fdf25b8d6e78..16d645532ce9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -61,6 +61,22 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); static DEFINE_IDA(blk_queue_ida); +bool precise_iostat; + +static int __init precise_iostat_setup(char *str) +{ + bool precise; + + if (!strtobool(str, &precise)) { + precise_iostat = precise; + pr_info("precise iostat %d\n", precise_iostat); + } + + return 1; +} +__setup("precise_iostat=", precise_iostat_setup); + + /* * For queue allocation */ @@ -940,9 +956,14 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); - if (unlikely(time_after(now, stamp))) { - if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) + if (unlikely(time_after(now, stamp)) && + likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) { + if (precise_iostat) { + if (end || part_in_flight(part)) + __part_stat_add(part, io_ticks, now - stamp); + } else { __part_stat_add(part, io_ticks, end ? now - stamp : 1); + } } if (part->bd_partno) { part = bdev_whole(part); diff --git a/block/blk-merge.c b/block/blk-merge.c index 65e75efa9bd3..463611c7c944 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -783,6 +783,8 @@ static void blk_account_io_merge_request(struct request *req) if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 6ab7f360ff2a..387528a9f3df 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -994,6 +994,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } @@ -1016,6 +1018,8 @@ static inline void blk_account_io_start(struct request *req) part_stat_lock(); update_io_ticks(req->part, jiffies, false); + if (precise_iostat) + part_stat_local_inc(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/genhd.c b/block/genhd.c index cc32a0c704eb..8cf16dc7e195 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part, } } -static unsigned int part_in_flight(struct block_device *part) +unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eef450f25982..99c2e6aa5e10 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/uuid.h> #include <linux/xarray.h> +extern bool precise_iostat; struct module; struct request_queue; struct elevator_queue; @@ -832,6 +833,7 @@ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); void blk_request_module(dev_t devt); +extern unsigned int part_in_flight(struct block_device *part); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); -- 2.31.1

2 1

[PATCH OLK-6.6 v2 0/2] dm btree spine: show warning if
by Li Lingfeng 05 Dec '23

05 Dec '23

Add extra node_check function declaration back and show warning if node_check failed in node_prep_for_write(). v1->v2: Revert commit 851a8cd3f05b ("dm btree spine: remove extra node_check function declaration") to add extra node_check function declaration back. Fix commit message. Li Lingfeng (1): Revert "dm btree spine: remove extra node_check function declaration" Zhang Xiaoxu (1): dm btree spine: show warning if node_check failed in node_prep_for_write() drivers/md/persistent-data/dm-btree-spine.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.31.1

2 3

[PATCH v2 OLK-5.10 0/7] bring mc support to page eject
by Wupeng Ma 05 Dec '23

05 Dec '23

From: Ma Wupeng <mawupeng1(a)huawei.com> During page eject, machine check safe is enhanced as follow: During soft offline page, page is copied to new page in kernel. If the origin page has UCE, there will lead to kernel panic. In order to solve this problem, use machine check safe to catch this error which can be achieved by using copy_mc_to_kernel to replace copy_page. Signal SIGBUS will be send to user task if this UCE is consumed by this situation to avoid kernel panic. Changelog since v1: - remove unused ret in patch #4 - add a bugfix for page eject Jiaqi Yan (1): mm/hwpoison: introduce copy_mc_highpage Ma Wupeng (6): mm: page_eject: Return right value during removal mm/hwpoison: arm64: introduce copy_mc_highpage mm/hwpoison: introduce copy_mc_highpages mm/hwpoison: add migrate_page_mc_extra() mm: Update PF_COREDUMP_MCS to PF_MCS mm: page_eject: Add mc support during offline page arch/arm64/include/asm/page.h | 1 + arch/arm64/mm/copypage.c | 13 ++++++ drivers/ras/page_eject.c | 10 ++++- fs/coredump.c | 4 +- include/linux/highmem.h | 52 ++++++++++++++++++++++++ include/linux/sched.h | 2 +- lib/iov_iter.c | 2 +- mm/migrate.c | 76 ++++++++++++++++++++++++++++++----- 8 files changed, 145 insertions(+), 15 deletions(-) -- 2.25.1

2 8

[PATCH OLK-6.6 0/2] feature:cgroupv1 enable cgroup writeback
by chenridong 05 Dec '23

05 Dec '23

Lu Jialin (2): cgroup: Add cgroup1_get_from_id() cgroup: support cgroup writeback on cgroupv1 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 | 64 +++++++++++++++++++ mm/backing-dev.c | 117 +++++++++++++++++++++++++++++++++- mm/memcontrol.c | 122 +++++++++++++++++++++++++++++++++++- 10 files changed, 346 insertions(+), 7 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6] block: fix inaccurate io_ticks by set 'precise_iostat'
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Zhang Wensheng <zhangwensheng5(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8M01Q CVE: NA -------------------------------- After introducing commit 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting"), '%util' accounted by iostat will be over reality data. In fact, the device is quite idle, but iostat may show '%util' as a big number (e.g. 50%). It can produce by fio: fio --name=1 --direct=1 --bs=4k --rw=read --filename=/dev/sda \ --thinktime=4ms --runtime=180 We fix this by using a switch(precise_iostat=1) to control whether or not acconut ioticks precisely. fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting") Signed-off-by: Zhang Wensheng <zhangwensheng5(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: block/blk-core.c block/blk-merge.c block/genhd.c include/linux/blkdev.h Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- block/blk-core.c | 25 +++++++++++++++++++++++-- block/blk-merge.c | 2 ++ block/blk-mq.c | 4 ++++ block/genhd.c | 2 +- include/linux/blkdev.h | 2 ++ 5 files changed, 32 insertions(+), 3 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index fdf25b8d6e78..16d645532ce9 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -61,6 +61,22 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert); static DEFINE_IDA(blk_queue_ida); +bool precise_iostat; + +static int __init precise_iostat_setup(char *str) +{ + bool precise; + + if (!strtobool(str, &precise)) { + precise_iostat = precise; + pr_info("precise iostat %d\n", precise_iostat); + } + + return 1; +} +__setup("precise_iostat=", precise_iostat_setup); + + /* * For queue allocation */ @@ -940,9 +956,14 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) unsigned long stamp; again: stamp = READ_ONCE(part->bd_stamp); - if (unlikely(time_after(now, stamp))) { - if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) + if (unlikely(time_after(now, stamp)) && + likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) { + if (precise_iostat) { + if (end || part_in_flight(part)) + __part_stat_add(part, io_ticks, now - stamp); + } else { __part_stat_add(part, io_ticks, end ? now - stamp : 1); + } } if (part->bd_partno) { part = bdev_whole(part); diff --git a/block/blk-merge.c b/block/blk-merge.c index 65e75efa9bd3..463611c7c944 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -783,6 +783,8 @@ static void blk_account_io_merge_request(struct request *req) if (blk_do_io_stat(req)) { part_stat_lock(); part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/blk-mq.c b/block/blk-mq.c index 6ab7f360ff2a..387528a9f3df 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -994,6 +994,8 @@ static inline void blk_account_io_done(struct request *req, u64 now) update_io_ticks(req->part, jiffies, true); part_stat_inc(req->part, ios[sgrp]); part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns); + if (precise_iostat) + part_stat_local_dec(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } @@ -1016,6 +1018,8 @@ static inline void blk_account_io_start(struct request *req) part_stat_lock(); update_io_ticks(req->part, jiffies, false); + if (precise_iostat) + part_stat_local_inc(req->part, in_flight[rq_data_dir(req)]); part_stat_unlock(); } } diff --git a/block/genhd.c b/block/genhd.c index cc32a0c704eb..8cf16dc7e195 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -118,7 +118,7 @@ static void part_stat_read_all(struct block_device *part, } } -static unsigned int part_in_flight(struct block_device *part) +unsigned int part_in_flight(struct block_device *part) { unsigned int inflight = 0; int cpu; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eef450f25982..99c2e6aa5e10 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/uuid.h> #include <linux/xarray.h> +extern bool precise_iostat; struct module; struct request_queue; struct elevator_queue; @@ -832,6 +833,7 @@ dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); void blk_request_module(dev_t devt); +extern unsigned int part_in_flight(struct block_device *part); extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); void submit_bio_noacct(struct bio *bio); -- 2.31.1

1 0

[PATCH OLK-6.6 v5 0/2] ipvlan: Introduce l2e mode
by Zhengchao Shao 05 Dec '23

05 Dec '23

Inherited features of olk5.10 version. Keefe LIU (2): ipvlan: Introduce l2e mode ipvlan: Introduce local xmit queue for l2e mode drivers/net/Kconfig | 7 + drivers/net/ipvlan/ipvlan.h | 11 ++ drivers/net/ipvlan/ipvlan_core.c | 232 +++++++++++++++++++++++++++++++ drivers/net/ipvlan/ipvlan_main.c | 103 +++++++++++++- include/uapi/linux/if_link.h | 1 + 5 files changed, 352 insertions(+), 2 deletions(-) -- 2.34.1

1 2

[PATCH OLK-5.10] md/raid5: fix miscalculation of 'end_sector' in raid5_read_one_chunk()
by Li Nan 05 Dec '23

05 Dec '23

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-v6.4-rc5 commit 8557dc27126949c702bd3aafe8a7e0b7e4fcb44c category: bugfix bugzilla: 189405, https://gitee.com/openeuler/kernel/issues/I8LZMK Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- 'end_sector' is compared to 'rdev->recovery_offset', which is offset to rdev, however, commit e82ed3a4fbb5 ("md/raid6: refactor raid5_read_one_chunk") changes the calculation of 'end_sector' to offset to the array. Fix this miscalculation. Fixes: e82ed3a4fbb5 ("md/raid6: refactor raid5_read_one_chunk") Cc: stable(a)vger.kernel.org # v5.12+ Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Song Liu <song(a)kernel.org> Link: https://lore.kernel.org/r/20230524014118.3172781-1-yukuai1@huaweicloud.com Conflict: Commit 2c897e63a100 ("[Backport] md/raid6: refactor raid5_read_one_chunk") missed the space of the previous line. Signed-off-by: Li Nan <linan122(a)huawei.com> --- drivers/md/raid5.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 5af25898baad..b4d004b623e7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5408,8 +5408,8 @@ static int raid5_read_one_chunk(struct mddev *mddev, struct bio *raid_bio) } sector = raid5_compute_sector(conf, raid_bio->bi_iter.bi_sector, 0, - &dd_idx, NULL); - end_sector = bio_end_sector(raid_bio); + &dd_idx, NULL); + end_sector = sector + bio_sectors(raid_bio); rcu_read_lock(); if (r5c_big_stripe_cached(conf, sector)) -- 2.39.2

1 0

[PATCH OLK-5.10] drivers/perf: hisi: UC PMU support statistics in power saving mode
by Junhao He 05 Dec '23

05 Dec '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LYGD CVE: NA -------------------------------- When the UC enable the power saving mode, the UC power management system will turn off the counters register clock if the PMU is not enabled, and we cannot write values to the counters register. Set the UC PMU enable to turn on the clock, and then restore the UC PMU configuration. Signed-off-by: Junhao He <hejunhao3(a)huawei.com> --- drivers/perf/hisilicon/hisi_uncore_uc_pmu.c | 28 +++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 636fb79647c8..80811c5d8eab 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -287,10 +287,38 @@ static u64 hisi_uc_pmu_read_counter(struct hisi_pmu *uc_pmu, return readq(uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); } +static bool hisi_uc_pmu_get_glb_en_state(struct hisi_pmu *uc_pmu) +{ + u32 val; + + val = readl(uc_pmu->base + HISI_UC_EVENT_CTRL_REG); + return !!FIELD_GET(HISI_UC_EVENT_GLB_EN, val); +} + static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu, struct hw_perf_event *hwc, u64 val) { + bool enable = hisi_uc_pmu_get_glb_en_state(uc_pmu); + + /* + * If the PMU is not enabled, the UC power management system will + * turn off the clock of the counters register and we cannot write + * values to the counters register. Set the UC PMU enable to turn + * on the clock. + */ + if (!enable) + hisi_uc_pmu_start_counters(uc_pmu); + writeq(val, uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); + + /* + * Restore the UC PMU configuration. The Perf schedule will enable PMU + * at appropriate time. + * The irq handler will also call the function to set period. At this + * time, PMU is still enabled and we cannot directly disable the PMU. + */ + if (!enable) + hisi_uc_pmu_stop_counters(uc_pmu); } static void hisi_uc_pmu_enable_counter_int(struct hisi_pmu *uc_pmu, -- 2.33.0

2 1

[PATCH OLK-6.6 V3 00/12] Add SDEI Watchdog Support
by Xiongfeng Wang 05 Dec '23

05 Dec '23

Xiongfeng Wang (12): firmware: arm_sdei: add interrupt binding api firmware: arm_sdei: make 'sdei_api_event_disable/enable' public lockup_detector: init lockup detector after all the init_calls watchdog: add nmi_watchdog support for arm64 based on SDEI sdei_watchdog: clear EOI of the secure timer before kdump sdei_watchdog: set secure timer period base on 'watchdog_thresh' sdei_watchdog: avoid possible false hardlockup init: only move down lockup_detector_init() when sdei_watchdog is enabled kprobes/arm64: Blacklist sdei watchdog callback functions openeuler_defconfig: Enable SDEI Watchdog stop_machine: mask sdei before running the callback arm64: kexec: only clear EOI for SDEI in NMI context arch/arm64/configs/openeuler_defconfig | 3 +- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/machine_kexec.c | 11 ++ arch/arm64/kernel/watchdog_sdei.c | 151 +++++++++++++++++++++++++ drivers/firmware/arm_sdei.c | 26 ++++- include/linux/arm_sdei.h | 5 + include/linux/nmi.h | 8 ++ include/uapi/linux/arm_sdei.h | 2 + init/main.c | 7 +- kernel/stop_machine.c | 10 ++ kernel/watchdog.c | 3 + lib/Kconfig.debug | 9 ++ 12 files changed, 232 insertions(+), 4 deletions(-) create mode 100644 arch/arm64/kernel/watchdog_sdei.c -- 2.20.1

2 13

[PATCH OLK-6.6] exec: Remove redundant check in do_open_execat/uselib
by Zhihao Cheng 05 Dec '23

05 Dec '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LX53 CVE: NA -------------------------------- There is a false positive WARNON happening in execve(2)/uselib(2) syscalls with concurrent noexec-remount. execveat remount do_open_execat(path/bin) do_filp_open path_openat do_open may_open path_noexec() // PASS remount(path->mnt, MS_NOEXEC) WARNON(path_noexec(&file->f_path)) // path_noexec() checks fail Since may_open() has already checked the same conditions, fix it by removing 'S_ISREG' and 'path_noexec' check in do_open_execat()/uselib(2). Fixes: 0fd338b2d2cdf8 ("exec: move path_noexec() check earlier") Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- fs/exec.c | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) diff --git a/fs/exec.c b/fs/exec.c index 6518e33ea813..73b833e8b548 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -142,16 +142,6 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) if (IS_ERR(file)) goto out; - /* - * may_open() has already checked for this, so it should be - * impossible to trip now. But we need to be extra cautious - * and check again at the very end too. - */ - error = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) - goto exit; - error = -ENOEXEC; read_lock(&binfmt_lock); @@ -168,7 +158,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) break; } read_unlock(&binfmt_lock); -exit: + fput(file); out: return error; @@ -925,16 +915,6 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) if (IS_ERR(file)) goto out; - /* - * may_open() has already checked for this, so it should be - * impossible to trip now. But we need to be extra cautious - * and check again at the very end too. - */ - err = -EACCES; - if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || - path_noexec(&file->f_path))) - goto exit; - err = deny_write_access(file); if (err) goto exit; -- 2.31.1

2 1

[OLK-5.10 00/13] crypto: some bugfixs and cleanup
by Weili Qian 05 Dec '23

05 Dec '23

From: JiangShui Yang <yangjiangshui(a)h-partners.com> Chenghai Huang (3): crypto: hisilicon/qm - delete a dbg function vfio/migration - delete a dbg function crypto: hisilicon/sec2 - optimize the error return process JiangShui Yang (1): crypto: hisilicon/qm - increase the maximum waiting timeout interval of the moilbox. Weili Qian (8): crypto: hisilicon/sec2: fix memory use-after-free issue crypto: hisilicon/qm - modify interrupt resource application process crypto: hisilicon/hpre - mask cluster timeout error crypto: hisilicon/qm - support get deivce state crypto: hisilicon/qm - dump important registers values before resetting crypto: hisilicon/qm - remove duplicate configurations crypto: hisilicon/qm - add stop function by hardware crypto: hisilicon/qm - reset device before enabling it Wenkai Lin (1): crypto: hisilicon/qm - add size check in qm set algs Documentation/ABI/testing/debugfs-hisi-hpre | 7 + Documentation/ABI/testing/debugfs-hisi-sec | 7 + Documentation/ABI/testing/debugfs-hisi-zip | 7 + drivers/crypto/hisilicon/debugfs.c | 53 +++ drivers/crypto/hisilicon/hpre/hpre_main.c | 58 ++-- .../hisilicon/migration/acc_vf_migration.c | 3 - drivers/crypto/hisilicon/qm.c | 328 ++++++++++++------ drivers/crypto/hisilicon/sec2/sec.h | 2 - drivers/crypto/hisilicon/sec2/sec_crypto.c | 57 +-- drivers/crypto/hisilicon/sec2/sec_main.c | 23 +- drivers/crypto/hisilicon/zip/zip_main.c | 25 +- include/linux/hisi_acc_qm.h | 5 +- 12 files changed, 362 insertions(+), 213 deletions(-) -- 2.33.0

1 13

[PATCH OLK-6.6] blk-throttle: enable hierarchical throttle in cgroup v1
by Yu Kuai 05 Dec '23

05 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4R7RE CVE: NA ----------------------------------------------- blkio subsytem is not under default hierarchy in cgroup v1 by default, which means configurations will only be effective on current cgroup for io throttle. This patch introduces a new feature that enable default hierarchy for io throttle, which means configurations will be effective on child cgroups. Such feature is disabled by default, and can be enabled by adding "blkcg_global_limit=1" or "blkcg_global_limit=Y" or "blkcg_global_limit=y" in boot cmd. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Tao Hou <houtao1(a)huawei.com> --- block/blk-throttle.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 13e4377a8b28..c3bd159163d7 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -41,6 +41,19 @@ /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; +/* True if global limit is enabled in cgroup v1 */ +static bool global_limit; + +static int __init setup_global_limit(char *str) +{ + if (!strcmp(str, "1") || !strcmp(str, "Y") || !strcmp(str, "y")) + global_limit = true; + + return 1; +} + +__setup("blkcg_global_limit=", setup_global_limit); + #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) /* We measure latency for request size from <= 4k to >= 1M */ @@ -405,7 +418,8 @@ static void throtl_pd_init(struct blkg_policy_data *pd) * regardless of the position of the group in the hierarchy. */ sq->parent_sq = &td->service_queue; - if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent) + if ((cgroup_subsys_on_dfl(io_cgrp_subsys) || global_limit) && + blkg->parent) sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue; tg->td = td; } -- 2.39.2

2 1

[PATCH OLK-5.10 v2 0/2] Two bugfix patch about memcg swap qos
by Liu Shixin 05 Dec '23

05 Dec '23

Two bugfix patch about memcg swap qos. Liu Shixin (2): mm/swap_slots: fix out-of-bounds access of percpu area memcg: fix use-after-free of mm_struct mm/memcontrol.c | 6 ++++++ mm/swap_slots.c | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) -- 2.25.1

2 3

[PATCH OLK-6.6] Revert "dm space maps: don't reset space map allocation cursor when committing"
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Luo Meng <luomeng12(a)huawei.com> hulk inclusion category: bugfix bugzilla: 185894, https://gitee.com/openeuler/kernel/issues/I4SJ8H?from=project-issue CVE: NA ----------------------------------------------- This reverts commit b0d9aeb41d5d5e90601fdf89834eba0a0613291c. This commit b0d9aeb41d5d ("dm space maps: don't reset space map allocation cursor when committing") change the way to find free block. But when use ramdisk(not support discard) for thin-pool,and storage over-commitment. Then constantly create and delete file, can find block in thin-pool, but can't find block in ramdisk. So need revert this patch. Signed-off-by: Luo Meng <luomeng12(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Conflicts: drivers/md/persistent-data/dm-space-map-disk.c commit 2d0f25cbc0d9 ("dm: remove unnecessary braces from single statement blocks") removes some braces; commit d6db294fd819 ("dm space map disk: remove redundant calls to sm_disk_get_nr_free()") removes calls to sm_disk_get_nr_free(). Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- drivers/md/persistent-data/dm-space-map-disk.c | 8 +------- drivers/md/persistent-data/dm-space-map-metadata.c | 9 +-------- 2 files changed, 2 insertions(+), 15 deletions(-) diff --git a/drivers/md/persistent-data/dm-space-map-disk.c b/drivers/md/persistent-data/dm-space-map-disk.c index f4241f54e20e..8d98bdd58db8 100644 --- a/drivers/md/persistent-data/dm-space-map-disk.c +++ b/drivers/md/persistent-data/dm-space-map-disk.c @@ -137,13 +137,6 @@ static int sm_disk_new_block(struct dm_space_map *sm, dm_block_t *b) * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, smd->begin, smd->ll.nr_blocks, b); - if (r == -ENOSPC) - /* - * There's no free block between smd->begin and the end of the metadata device. - * We search before smd->begin in case something has been freed. - */ - r = sm_ll_find_common_free_block(&smd->old_ll, &smd->ll, 0, smd->begin, b); - if (r) return r; @@ -165,6 +158,7 @@ static int sm_disk_commit(struct dm_space_map *sm) return r; memcpy(&smd->old_ll, &smd->ll, sizeof(smd->old_ll)); + smd->begin = 0; smd->nr_allocated_this_transaction = 0; return 0; diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c index 04698fd03e60..b59191649cff 100644 --- a/drivers/md/persistent-data/dm-space-map-metadata.c +++ b/drivers/md/persistent-data/dm-space-map-metadata.c @@ -456,14 +456,6 @@ static int sm_metadata_new_block_(struct dm_space_map *sm, dm_block_t *b) * Any block we allocate has to be free in both the old and current ll. */ r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, smm->begin, smm->ll.nr_blocks, b); - if (r == -ENOSPC) { - /* - * There's no free block between smm->begin and the end of the metadata device. - * We search before smm->begin in case something has been freed. - */ - r = sm_ll_find_common_free_block(&smm->old_ll, &smm->ll, 0, smm->begin, b); - } - if (r) return r; @@ -516,6 +508,7 @@ static int sm_metadata_commit(struct dm_space_map *sm) return r; memcpy(&smm->old_ll, &smm->ll, sizeof(smm->old_ll)); + smm->begin = 0; smm->allocated_this_transaction = 0; return 0; -- 2.31.1

2 1

[OLK-5.10 0/4 v2] A set of patchs for openEuler
by Chengchang Tang 05 Dec '23

05 Dec '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> The first two patches support more netdev speed, the third adds check for resource values and adjusts the invalid ones, and last patch renames the RoCE interrupts. Chengchang Tang (2): RDMA/hns: Fix port active speed RDMA/hns: Rename the interrupts Haoyue Xu (1): RDMA/core:Add support more netdev speed Junxian Huang (1): RDMA/hns: Add check and adjust for function resource values drivers/infiniband/core/verbs.c | 13 ++- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 123 +++++++++++++++++++-- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 37 +++++++ drivers/infiniband/hw/hns/hns_roce_main.c | 7 +- 4 files changed, 168 insertions(+), 12 deletions(-) -- 2.30.0

1 4

[PATCH openEuler-1.0-LTS] regmap: fix NULL deref on lookup
by Zhang Zekun 05 Dec '23

05 Dec '23

From: Johan Hovold <johan+linaro(a)kernel.org> stable inclusion from stable-v4.19.135 commit 7219c6b8fa24ec55a19d7a5ea58fb09151e37950 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LTOI CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------- commit c6df843348d6b71ea986266c12831cb60c2cf325 upstream. Not all regmaps have a name so make sure to check for that to avoid dereferencing a NULL pointer when dev_get_regmap() is used to lookup a named regmap. Fixes: e84861fec32d ("regmap: dev_get_regmap_match(): fix string comparison") Cc: stable(a)vger.kernel.org # 5.8 Cc: Marc Kleine-Budde <mkl(a)pengutronix.de> Signed-off-by: Johan Hovold <johan+linaro(a)kernel.org> Link: https://lore.kernel.org/r/20231006082104.16707-1-johan+linaro@kernel.org Signed-off-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/base/regmap/regmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 6c9f6988bc09..3315bd1ddf30 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1350,7 +1350,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data) /* If the user didn't specify a name match any */ if (data) - return (*r)->name == data; + return (*r)->name && !strcmp((*r)->name, data); else return 1; } -- 2.17.1

2 1

[PATCH OLK-6.6] dm btree spine: show warning if node_check failed in node_prep_for_write()
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5JCAH -------------------------------- The BUG_ON is unneed Since f73e2e70ec48 ("dm btree spine: remove paranoid node_check call in node_prep_for_write()") merged in v5.13. For debug reason, we also want to know the data on disk is corrupted by write or disk fault. So also add check and print some info when data corrupted. Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- drivers/md/persistent-data/dm-btree-spine.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c index 7540383b7cf3..418cac548ce6 100644 --- a/drivers/md/persistent-data/dm-btree-spine.c +++ b/drivers/md/persistent-data/dm-btree-spine.c @@ -27,6 +27,8 @@ static void node_prepare_for_write(struct dm_block_validator *v, h->csum = cpu_to_le32(dm_bm_checksum(&h->flags, block_size - sizeof(__le32), BTREE_CSUM_XOR)); + if (node_check(v, b, 4096)) + DMWARN_LIMIT("%s node_check failed", __func__); } static int node_check(struct dm_block_validator *v, -- 2.31.1

2 1

[PATCH OLK-6.6] loop: Add parm check in loop_control_ioctl
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188586, https://gitee.com/openeuler/kernel/issues/I6TFPJ CVE: NA ---------------------------------------- We found that in loop_control_ioctl, the kernel panic can be easily caused: 1. syscall(__NR_ioctl, r[1], 0x4c80, 0x80000200000ul); Create a loop device 0x80000200000ul. In fact, in the code, it is used as the first_minor number, and the first_minor number is 0. So the created loop device number is 7:0. 2. syscall(__NR_ioctl, r[2], 0x4c80, 0ul); Create a loop device 0x0ul. Since the 7:0 device has been created in 1, add_disk will fail because the major and first_minor numbers are consistent. 3. syscall(__NR_ioctl, r[5], 0x4c81, 0ul); Delete the device that failed to create, the kernel panics. Panic like below: BUG: KASAN: null-ptr-deref in device_del+0xb3/0x840 drivers/base/core.c:3107 Call Trace: kill_device drivers/base/core.c:3079 [inline] device_del+0xb3/0x840 drivers/base/core.c:3107 del_gendisk+0x463/0x5f0 block/genhd.c:971 loop_remove drivers/block/loop.c:2190 [inline] loop_control_ioctl drivers/block/loop.c:2289 [inline] The stack like below: Create loop device: loop_control_ioctl loop_add add_disk device_add_disk bdi_register bdi_register_va device_create device_create_groups_vargs device_add kfree(dev->p); dev->p = NULL; Remove loop device: loop_control_ioctl loop_remove del_gendisk device_del kill_device if (dev->p->dead) // p is null Fix it by adding a check for parm. Fixes: 770fe30a46a1 ("loop: add management interface for on-demand device allocation") Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Conflict: drivers/block/loop.c Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- drivers/block/loop.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 9f2d412fc560..631bc2543d74 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1992,6 +1992,17 @@ static int loop_add(int i) struct gendisk *disk; int err; + /* + * i << part_shift is actually used as the first_minor. + * So here should avoid i << part_shift overflow. + * And, MKDEV() expect that the max bits of + * first_minor is 20. + */ + if (i > 0 && i > MINORMASK >> part_shift) { + err = -EINVAL; + goto out; + } + err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) @@ -2011,7 +2022,8 @@ static int loop_add(int i) if (err == -ENOSPC) err = -EEXIST; } else { - err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); + err = idr_alloc(&loop_index_idr, lo, 0, + (MINORMASK >> part_shift) + 1, GFP_KERNEL); } mutex_unlock(&loop_ctl_mutex); if (err < 0) -- 2.31.1

2 1

[PATCH OLK-6.6 V3 00/12] Add SDEI Watchdog Support
by Xiongfeng Wang 05 Dec '23

05 Dec '23

Xiongfeng Wang (12): firmware: arm_sdei: add interrupt binding api firmware: arm_sdei: make 'sdei_api_event_disable/enable' public lockup_detector: init lockup detector after all the init_calls watchdog: add nmi_watchdog support for arm64 based on SDEI sdei_watchdog: clear EOI of the secure timer before kdump sdei_watchdog: set secure timer period base on 'watchdog_thresh' sdei_watchdog: avoid possible false hardlockup init: only move down lockup_detector_init() when sdei_watchdog is enabled kprobes/arm64: Blacklist sdei watchdog callback functions openeuler_defconfig: Enable SDEI Watchdog stop_machine: mask sdei before running the callback arm64: kexec: only clear EOI for SDEI in NMI context arch/arm64/configs/openeuler_defconfig | 3 +- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/machine_kexec.c | 11 ++ arch/arm64/kernel/watchdog_sdei.c | 151 +++++++++++++++++++++++++ drivers/firmware/arm_sdei.c | 26 ++++- include/linux/arm_sdei.h | 5 + include/linux/nmi.h | 8 ++ include/uapi/linux/arm_sdei.h | 2 + init/main.c | 7 +- kernel/stop_machine.c | 10 ++ kernel/watchdog.c | 3 + lib/Kconfig.debug | 9 ++ 12 files changed, 232 insertions(+), 4 deletions(-) create mode 100644 arch/arm64/kernel/watchdog_sdei.c -- 2.20.1

2 13

[PATCH OLK-6.6] nbd: get config_lock before sock_shutdown
by Li Lingfeng 05 Dec '23

05 Dec '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188799, https://gitee.com/openeuler/kernel/issues/I79QWO CVE: NA ---------------------------------------- Config->socks in sock_shutdown may trigger a UAF problem. The reason is that sock_shutdown does not hold the config_lock, so that nbd_ioctl can release config->socks at this time. T0: NBD_SET_SOCK T1: NBD_DO_IT T0 T1 nbd_ioctl mutex_lock(&nbd->config_lock) // get lock __nbd_ioctl nbd_start_device_ioctl nbd_start_device mutex_unlock(&nbd->config_lock) // relase lock wait_event_interruptible (kill, enter sock_shutdown) sock_shutdown nbd_ioctl mutex_lock(&nbd->config_lock) // get lock __nbd_ioctl nbd_add_socket krealloc kfree(p) //config->socks is NULL nbd_sock *nsock = config->socks // error Fix it by moving config_lock up before sock_shutdown. Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> --- drivers/block/nbd.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 855fdf5c3b4e..9f03cdcb86c7 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1417,13 +1417,18 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd) mutex_unlock(&nbd->config_lock); ret = wait_event_interruptible(config->recv_wq, atomic_read(&config->recv_threads) == 0); + + /* + * recv_work in flush_workqueue will not get this lock, because nbd_open + * will hold nbd->config_refs + */ + mutex_lock(&nbd->config_lock); if (ret) { sock_shutdown(nbd); nbd_clear_que(nbd); } flush_workqueue(nbd->recv_workq); - mutex_lock(&nbd->config_lock); nbd_bdev_reset(nbd); /* user requested, ignore socket errors */ if (test_bit(NBD_RT_DISCONNECT_REQUESTED, &config->runtime_flags)) -- 2.31.1

2 1

[PATCH OLK-5.10] drivers/perf: hisi: Fix some event id for HiSilicon UC pmu
by Junhao He 05 Dec '23

05 Dec '23

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LSBA CVE: NA Reference: https://lore.kernel.org/lkml/20231204110425.20354-1-hejunhao3@huawei.com/ -------------------------------- Some event id of HiSilicon uncore UC PMU driver is incorrect, fix them. Fixes: 312eca95e28d ("drivers/perf: hisi: Add support for HiSilicon UC PMU driver") Signed-off-by: Junhao He <hejunhao3(a)huawei.com> --- drivers/perf/hisilicon/hisi_uncore_uc_pmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 63da05e5831c..636fb79647c8 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -383,8 +383,8 @@ static struct attribute *hisi_uc_pmu_events_attr[] = { HISI_PMU_EVENT_ATTR(cpu_rd, 0x10), HISI_PMU_EVENT_ATTR(cpu_rd64, 0x17), HISI_PMU_EVENT_ATTR(cpu_rs64, 0x19), - HISI_PMU_EVENT_ATTR(cpu_mru, 0x1a), - HISI_PMU_EVENT_ATTR(cycles, 0x9c), + HISI_PMU_EVENT_ATTR(cpu_mru, 0x1c), + HISI_PMU_EVENT_ATTR(cycles, 0x95), HISI_PMU_EVENT_ATTR(spipe_hit, 0xb3), HISI_PMU_EVENT_ATTR(hpipe_hit, 0xdb), HISI_PMU_EVENT_ATTR(cring_rxdat_cnt, 0xfa), -- 2.33.0

2 1

[PATCH openEuler-1.0-LTS v2] net: prevent rewrite of msg_name in sock_sendmsg()
by Lu Wei 05 Dec '23

05 Dec '23

From: Jordan Rife <jrife(a)google.com> stable inclusion from stable-v4.19.297 commit 3d62f2577c7414e5b94e4baad6eb621165960f30 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8EZY4 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 86a7e0b69bd5b812e48a20c66c2161744f3caa16 ] Callers of sock_sendmsg(), and similarly kernel_sendmsg(), in kernel space may observe their value of msg_name change in cases where BPF sendmsg hooks rewrite the send address. This has been confirmed to break NFS mounts running in UDP mode and has the potential to break other systems. This patch: 1) Creates a new function called __sock_sendmsg() with same logic as the old sock_sendmsg() function. 2) Replaces calls to sock_sendmsg() made by __sys_sendto() and __sys_sendmsg() with __sock_sendmsg() to avoid an unnecessary copy, as these system calls are already protected. 3) Modifies sock_sendmsg() so that it makes a copy of msg_name if present before passing it down the stack to insulate callers from changes to the send address. Link: https://lore.kernel.org/netdev/20230912013332.2048422-1-jrife@google.com/ Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Cc: stable(a)vger.kernel.org Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jordan Rife <jrife(a)google.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> conflict: net/socket.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/socket.c | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/net/socket.c b/net/socket.c index 3d3632fe4a34..691dd9fb5d1f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -653,13 +653,30 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) return ret; } -int sock_sendmsg(struct socket *sock, struct msghdr *msg) +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } + +int sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; + + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; +} EXPORT_SYMBOL(sock_sendmsg); /** @@ -963,7 +980,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -1940,7 +1957,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2272,7 +2289,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] fs: don't audit the capability check in simple_xattr_list()
by Zizhi Wo 04 Dec '23

04 Dec '23

From: Ondrej Mosnacek <omosnace(a)redhat.com> mainline inclusion from mainline-v6.2-rc1 commit e7eda157c4071cd1e69f4b1687b0fbe1ae5e6f46 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LQI5?from=project-issue CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The check being unconditional may lead to unwanted denials reported by LSMs when a process has the capability granted by DAC, but denied by an LSM. In the case of SELinux such denials are a problem, since they can't be effectively filtered out via the policy and when not silenced, they produce noise that may hide a true problem or an attack. Checking for the capability only if any trusted xattr is actually present wouldn't really address the issue, since calling listxattr(2) on such node on its own doesn't indicate an explicit attempt to see the trusted xattrs. Additionally, it could potentially leak the presence of trusted xattrs to an unprivileged user if they can check for the denials (e.g. through dmesg). Therefore, it's best (and simplest) to keep the check unconditional and instead use ns_capable_noaudit() that will silence any associated LSM denials. Fixes: 38f38657444d ("xattr: extract simple_xattr code from tmpfs") Reported-by: Martin Pitt <mpitt(a)redhat.com> Suggested-by: Christian Brauner (Microsoft) <brauner(a)kernel.org> Signed-off-by: Ondrej Mosnacek <omosnace(a)redhat.com> Reviewed-by: Christian Brauner (Microsoft) <brauner(a)kernel.org> Reviewed-by: Paul Moore <paul(a)paul-moore.com> Signed-off-by: Christian Brauner (Microsoft) <brauner(a)kernel.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/xattr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xattr.c b/fs/xattr.c index 470ee0af3200..5c3407e18e15 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1012,7 +1012,7 @@ static int xattr_list_one(char **buffer, ssize_t *remaining_size, ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size) { - bool trusted = capable(CAP_SYS_ADMIN); + bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; int err = 0; -- 2.39.2

2 1

[PATCH OLK-6.6 V3 00/12] Add SDEI Watchdog Support
by Xiongfeng Wang 04 Dec '23

04 Dec '23

Xiongfeng Wang (12): firmware: arm_sdei: add interrupt binding api firmware: arm_sdei: make 'sdei_api_event_disable/enable' public lockup_detector: init lockup detector after all the init_calls watchdog: add nmi_watchdog support for arm64 based on SDEI sdei_watchdog: clear EOI of the secure timer before kdump sdei_watchdog: set secure timer period base on 'watchdog_thresh' sdei_watchdog: avoid possible false hardlockup init: only move down lockup_detector_init() when sdei_watchdog is enabled kprobes/arm64: Blacklist sdei watchdog callback functions openeuler_defconfig: Enable SDEI Watchdog stop_machine: mask sdei before running the callback arm64: kexec: only clear EOI for SDEI in NMI context arch/arm64/configs/openeuler_defconfig | 3 +- arch/arm64/kernel/Makefile | 1 + arch/arm64/kernel/machine_kexec.c | 11 ++ arch/arm64/kernel/watchdog_sdei.c | 151 +++++++++++++++++++++++++ drivers/firmware/arm_sdei.c | 26 ++++- include/linux/arm_sdei.h | 5 + include/linux/nmi.h | 8 ++ include/uapi/linux/arm_sdei.h | 2 + init/main.c | 7 +- kernel/stop_machine.c | 10 ++ kernel/watchdog.c | 3 + lib/Kconfig.debug | 9 ++ 12 files changed, 232 insertions(+), 4 deletions(-) create mode 100644 arch/arm64/kernel/watchdog_sdei.c -- 2.20.1

1 12

[PATCH OLK-5.10 0/6] bring mc support to page eject
by Wupeng Ma 04 Dec '23

04 Dec '23

From: Ma Wupeng <mawupeng1(a)huawei.com> During page eject, machine check safe is enhanced as follow: During soft offline page, page is copied to new page in kernel. If the origin page has UCE, there will lead to kernel panic. In order to solve this problem, use machine check safe to catch this error which can be achieved by using copy_mc_to_kernel to replace copy_page. Signal SIGBUS will be send to user task if this UCE is consumed by this situation to avoid kernel panic. Jiaqi Yan (1): mm/hwpoison: introduce copy_mc_highpage Ma Wupeng (5): mm/hwpoison: arm64: introduce copy_mc_highpage mm/hwpoison: introduce copy_mc_highpages mm/hwpoison: add migrate_page_mc_extra() mm: Update PF_COREDUMP_MCS to PF_MCS mm: page_eject: Add mc support during offline page arch/arm64/include/asm/page.h | 1 + arch/arm64/mm/copypage.c | 13 ++++++ drivers/ras/page_eject.c | 5 +++ fs/coredump.c | 4 +- include/linux/highmem.h | 52 +++++++++++++++++++++++ include/linux/sched.h | 2 +- lib/iov_iter.c | 2 +- mm/migrate.c | 77 +++++++++++++++++++++++++++++++---- 8 files changed, 143 insertions(+), 13 deletions(-) -- 2.25.1

2 7

[PATCH OLK-6.6 00/19] Add sharepool support
by Wang Wensheng 04 Dec '23

04 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. 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 | 277 +++ 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 | 3450 ++++++++++++++++++++++++++++++++++++ mm/util.c | 4 + mm/vmalloc.c | 205 ++- 17 files changed, 4204 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-5.10 0/6] bring mc support to page eject
by Wupeng Ma 04 Dec '23

04 Dec '23

From: Ma Wupeng <mawupeng1(a)huawei.com> During page eject, machine check safe is enhanced as follow: During soft offline page, page is copied to new page in kernel. If the origin page has UCE, there will lead to kernel panic. In order to solve this problem, use machine check safe to catch this error which can be achieved by using copy_mc_to_kernel to replace copy_page. Signal SIGBUS will be send to user task if this UCE is consumed by this situation to avoid kernel panic. Jiaqi Yan (1): mm/hwpoison: introduce copy_mc_highpage Ma Wupeng (5): mm/hwpoison: arm64: introduce copy_mc_highpage mm/hwpoison: introduce copy_mc_highpages mm/hwpoison: add migrate_page_mc_extra() mm: Update PF_COREDUMP_MCS to PF_MCS mm: page_eject: Add mc support during offline page arch/arm64/include/asm/page.h | 1 + arch/arm64/mm/copypage.c | 13 ++++++ drivers/ras/page_eject.c | 5 +++ fs/coredump.c | 4 +- include/linux/highmem.h | 52 +++++++++++++++++++++++ include/linux/sched.h | 2 +- lib/iov_iter.c | 2 +- mm/migrate.c | 77 +++++++++++++++++++++++++++++++---- 8 files changed, 143 insertions(+), 13 deletions(-) -- 2.25.1

1 6

[PATCH OLK-5.10 00/15] Some fixes and optimizations for hisi_sas
by Yihang Li 04 Dec '23

04 Dec '23

From: xiabing <xiabing12(a)h-partners.com> This patchset includes some changes for hisi_sas: - Fix NULL pointer issue when removing debugfs. - Directly calling register snapshot instead of workqueue. - Allocate debugfs memory during triggering debugfs dump. - Fix issue that device is not found because .phy_attached is not set. - Replace with standard error code return value. - Check the variable slot before use it. - Clear HISI_SAS_RESET_BIT, release hisi_hba semaphore, unblock the scsi host, clear HISI_SAS_REJECT_CMD_BIT if FLR failed. - Use the correct number of registers when reading register information. - Fix warnings detected by sparse - Handle the NCQ error returned by D2H frame Xiang Chen (1): scsi: hisi_sas: Remove unused variable and check in hisi_sas_send_ata_reset_each_phy() Xingui Yang (3): scsi: hisi_sas: Fix normally completed I/O analysed as failed scsi: hisi_sas: Fix warnings detected by sparse scsi: hisi_sas: Handle the NCQ error returned by D2H frame Yihang Li (11): scsi: hisi_sas: Set debugfs_dir pointer to NULL after removing debugfs scsi: hisi_sas: Directly call register snapshot instead of using workqueue scsi: hisi_sas: Allocate DFX memory during dump trigger scsi: hisi_sas: Remove redundant checks for automatic debugfs dump scsi: hisi_sas: Set .phy_attached before notifing phyup event HISI_PHYE_PHY_UP_PM scsi: hisi_sas: Replace with standard error code return value scsi: hisi_sas: Check before using pointer variables scsi: hisi_sas: Rollback some operations if FLR failed scsi: hisi_sas: Correct the number of global debugfs registers scsi: hisi_sas: Fix the deadlock issue that occurs during automatic dump scsi: hisi_sas: Check whether debugfs is enabled before removing or releasing it drivers/scsi/hisi_sas/hisi_sas.h | 3 +- drivers/scsi/hisi_sas/hisi_sas_main.c | 37 ++++-- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 11 +- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 164 +++++++++++++------------ 4 files changed, 120 insertions(+), 95 deletions(-) -- 2.30.0

1 15

[PATCH OLK-5.10 0/2] Two bugfix patch about memcg swap qos
by Liu Shixin 04 Dec '23

04 Dec '23

Two bugfix patch about memcg swap qos. Liu Shixin (2): mm/swap_slots: fix out-of-bounds access of percpu area memcg: fix use-after-free of mm_struct mm/memcontrol.c | 4 ++++ mm/swap_slots.c | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) -- 2.25.1

2 3

[PATCH OLK-6.6 v4 0/2] ipvlan: Introduce l2e mode
by Zhengchao Shao 04 Dec '23

04 Dec '23

Inherited features of olk5.10 version. Keefe LIU (2): ipvlan: Introduce l2e mode ipvlan: Introduce local xmit queue for l2e mode drivers/net/Kconfig | 7 + drivers/net/ipvlan/ipvlan.h | 11 ++ drivers/net/ipvlan/ipvlan_core.c | 232 +++++++++++++++++++++++++++++++ drivers/net/ipvlan/ipvlan_main.c | 103 +++++++++++++- include/uapi/linux/if_link.h | 3 + 5 files changed, 354 insertions(+), 2 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/5] xfs: fix some misc issue
by Long Li 04 Dec '23

04 Dec '23

This patch set fix some mics xfs issue: Long Li (5): xfs: fix a UAF when inode item push xfs: fix a UAF in xfs_iflush_abort_clean xfs: fix dir3 block read verify fail during log recover 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_buf_item_recover.c | 9 +++------ fs/xfs/xfs_inode_item.c | 8 +++++++- fs/xfs/xfs_trans.c | 2 +- 5 files changed, 18 insertions(+), 9 deletions(-) -- 2.31.1

2 6

[PATCH OLK-5.10] fs: Fix error checking for d_hash_and_lookup()
by Zizhi Wo 04 Dec '23

04 Dec '23

From: Wang Ming <machel(a)vivo.com> mainline inclusion from mainline-v6.6-rc1 commit 0d5a4f8f775ff990142cdc810a84eae078589d27 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LNLY?from=project-issue Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The d_hash_and_lookup() function returns error pointers or NULL. Most incorrect error checks were fixed, but the one in int path_pts() was forgotten. Fixes: eedf265aa003 ("devpts: Make each mount of devpts an independent filesystem.") Signed-off-by: Wang Ming <machel(a)vivo.com> Message-Id: <20230713120555.7025-1-machel(a)vivo.com> Signed-off-by: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namei.c b/fs/namei.c index ff140e2943a0..3588e12d6130 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2647,7 +2647,7 @@ int path_pts(struct path *path) dput(path->dentry); path->dentry = parent; child = d_hash_and_lookup(parent, &this); - if (!child) + if (IS_ERR_OR_NULL(child)) return -ENOENT; path->dentry = child; -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] net: prevent rewrite of msg_name in sock_sendmsg()
by Lu Wei 04 Dec '23

04 Dec '23

From: Jordan Rife <jrife(a)google.com> stable inclusion from stable-v4.19.297 commit 3d62f2577c7414e5b94e4baad6eb621165960f30 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8EZY4 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 86a7e0b69bd5b812e48a20c66c2161744f3caa16 ] Callers of sock_sendmsg(), and similarly kernel_sendmsg(), in kernel space may observe their value of msg_name change in cases where BPF sendmsg hooks rewrite the send address. This has been confirmed to break NFS mounts running in UDP mode and has the potential to break other systems. This patch: 1) Creates a new function called __sock_sendmsg() with same logic as the old sock_sendmsg() function. 2) Replaces calls to sock_sendmsg() made by __sys_sendto() and __sys_sendmsg() with __sock_sendmsg() to avoid an unnecessary copy, as these system calls are already protected. 3) Modifies sock_sendmsg() so that it makes a copy of msg_name if present before passing it down the stack to insulate callers from changes to the send address. Link: https://lore.kernel.org/netdev/20230912013332.2048422-1-jrife@google.com/ Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Cc: stable(a)vger.kernel.org Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jordan Rife <jrife(a)google.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> conflict: net/socket.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/socket.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/net/socket.c b/net/socket.c index 3d3632fe4a34..0cc52ba0b0e2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -637,6 +637,14 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) } EXPORT_SYMBOL(__sock_tx_timestamp); +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); + + return err ?: sock_sendmsg_nosec(sock, msg); +} + /** * sock_sendmsg - send a message through @sock * @sock: socket @@ -655,10 +663,19 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - int err = security_socket_sendmsg(sock, msg, - msg_data_left(msg)); + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; - return err ?: sock_sendmsg_nosec(sock, msg); + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; } EXPORT_SYMBOL(sock_sendmsg); @@ -963,7 +980,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -1940,7 +1957,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2272,7 +2289,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] arm64: errata: add option to disable cache readunique prefetch on HIP08
by Yang Yingliang 04 Dec '23

04 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

[PATCH openEuler-1.0-LTS] mm: don't let userspace spam allocations warnings
by Peng Zhang 04 Dec '23

04 Dec '23

From: Daniel Vetter <daniel.vetter(a)ffwll.ch> mainline inclusion from mainline-v5.0-rc8 commit 6c8fcc096be9d02f478c508052a41a4430506ab3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8LMVO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- memdump_user usually gets fed unchecked userspace input. Blasting a full backtrace into dmesg every time is a bit excessive - I'm not sure on the kernel rule in general, but at least in drm we're trying not to let unpriviledge userspace spam the logs freely. Definitely not entire warning backtraces. It also means more filtering for our CI, because our testsuite exercises these corner cases and so hits these a lot. Link: http://lkml.kernel.org/r/20190220204058.11676-1-daniel.vetter@ffwll.ch Signed-off-by: Daniel Vetter <daniel.vetter(a)intel.com> Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Acked-by: Michal Hocko <mhocko(a)suse.com> Reviewed-by: Kees Cook <keescook(a)chromium.org> Cc: Mike Rapoport <rppt(a)linux.vnet.ibm.com> Cc: Roman Gushchin <guro(a)fb.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Jan Stancek <jstancek(a)redhat.com> Cc: Andrey Ryabinin <aryabinin(a)virtuozzo.com> Cc: "Michael S. Tsirkin" <mst(a)redhat.com> Cc: Huang Ying <ying.huang(a)intel.com> Cc: Bartosz Golaszewski <brgl(a)bgdev.pl> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> --- mm/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/util.c b/mm/util.c index 2b04ff4675d6..3a69fd0a15ca 100644 --- a/mm/util.c +++ b/mm/util.c @@ -160,7 +160,7 @@ void *memdup_user(const void __user *src, size_t len) { void *p; - p = kmalloc_track_caller(len, GFP_USER); + p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); -- 2.25.1

2 1

[PATCH OLK-6.6] mm: Add sysctl to clear free list pages
by Yu Liao 04 Dec '23

04 Dec '23

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I4SK3S CVE: NA -------------------------------- This patch add sysctl to clear pages in free lists of each NUMA node. For each NUMA node, clear each page in the free list, these work is scheduled on a random CPU of the NUMA node. When kasan is enabled and the pages are free, the shadow memory will be filled with 0xFF, writing these free pages will cause UAF, so just disable KASAN for clear freelist. In the case of large memory, the clear freelist will hold zone lock for a long time. As a result, the process may be blocked unless clear freelist thread exit, and causing the system to be reset by the watchdog. Provide a mechanism to stop clear freelist threads when elapsed time exceeds cfp_timeout, which can be set by module_param(). Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> --- .../admin-guide/kernel-parameters.txt | 3 + Documentation/admin-guide/sysctl/vm.rst | 13 ++ mm/Kconfig | 13 ++ mm/Makefile | 2 + mm/clear_freelist_page.c | 187 ++++++++++++++++++ 5 files changed, 218 insertions(+) create mode 100644 mm/clear_freelist_page.c diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 41644336e358..97c91370b01c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -618,6 +618,9 @@ Also note the kernel might malfunction if you disable some critical bits. + clear_freelist + Enable clear_freelist feature. + clk_ignore_unused [CLK] Prevents the clock framework from automatically gating diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 45ba1f4dc004..cc15ea0fc406 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -25,6 +25,7 @@ files can be found in mm/swap.c. Currently, these files are in /proc/sys/vm: - admin_reserve_kbytes +- clear_freelist_pages - compact_memory - compaction_proactiveness - compact_unevictable_allowed @@ -106,6 +107,18 @@ On x86_64 this is about 128MB. Changing this takes effect whenever an application requests memory. +clear_freelist_pages +==================== + +Available only when CONFIG_CLEAR_FREELIST_PAGE is set. When 1 is written to the +file, all pages in free lists will be written with 0. + +Zone lock is held during clear_freelist_pages, if the execution time is too +long, RCU CPU Stall warnings will be print. For each NUMA node, +clear_freelist_pages is performed on a "random" CPU of the NUMA node. +The time consuming is related to the hardware. + + compact_memory ============== diff --git a/mm/Kconfig b/mm/Kconfig index ece4f2847e2b..e652d267e87e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1269,6 +1269,19 @@ config LOCK_MM_AND_FIND_VMA bool depends on !STACK_GROWSUP +config CLEAR_FREELIST_PAGE + bool "Support for clear free list pages" + depends on MMU && SYSCTL + default n + help + Say y here to enable the clear free list pages feature. When + writing to clear_freelist, trigger to clean up the free memory + of the buddy system. + + To enable this feature, kernel parameter "clear_freelist" also + needs to be added. + + source "mm/damon/Kconfig" endmenu diff --git a/mm/Makefile b/mm/Makefile index ec65984e2ade..1dc5d64a54f0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -7,6 +7,7 @@ KASAN_SANITIZE_slab_common.o := n KASAN_SANITIZE_slab.o := n KASAN_SANITIZE_slub.o := n KCSAN_SANITIZE_kmemleak.o := n +KASAN_SANITIZE_clear_freelist_page.o := n # These produce frequent data race reports: most of them are due to races on # the same word but accesses to different bits of that word. Re-enable KCSAN @@ -138,3 +139,4 @@ obj-$(CONFIG_IO_MAPPING) += io-mapping.o obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o +obj-$(CONFIG_CLEAR_FREELIST_PAGE) += clear_freelist_page.o diff --git a/mm/clear_freelist_page.c b/mm/clear_freelist_page.c new file mode 100644 index 000000000000..50b7ec918bfb --- /dev/null +++ b/mm/clear_freelist_page.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for clear free list pages. + */ + +#include <linux/mmzone.h> +#include <linux/mm_types.h> +#include <linux/mm.h> +#include <linux/sysctl.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/workqueue.h> +#include <linux/sched.h> +#include <linux/atomic.h> +#include <linux/nmi.h> +#include <linux/sched/clock.h> +#include <linux/module.h> + +#define CFP_DEFAULT_TIMEOUT 2000 +#define for_each_populated_zone_pgdat(pgdat, zone) \ + for (zone = pgdat->node_zones; \ + zone; \ + zone = next_pgdat_zone(zone)) \ + if (!populated_zone(zone)) \ + ; /* do nothing */ \ + else + +struct pgdat_entry { + struct pglist_data *pgdat; + struct work_struct work; +}; + +static DECLARE_WAIT_QUEUE_HEAD(clear_freelist_wait); +static DEFINE_MUTEX(clear_freelist_lock); +static atomic_t clear_freelist_workers; +static atomic_t clear_pages_num; +static ulong cfp_timeout_ms = CFP_DEFAULT_TIMEOUT; + +/* + * next_pgdat_zone - helper magic for for_each_populated_zone_pgdat() + */ +static struct zone *next_pgdat_zone(struct zone *zone) +{ + pg_data_t *pgdat = zone->zone_pgdat; + + if (zone < pgdat->node_zones + MAX_NR_ZONES - 1) + zone++; + else + zone = NULL; + return zone; +} + +static void clear_pgdat_freelist_pages(struct work_struct *work) +{ + struct pgdat_entry *entry = container_of(work, struct pgdat_entry, work); + u64 cfp_timeout_ns = cfp_timeout_ms * NSEC_PER_MSEC; + struct pglist_data *pgdat = entry->pgdat; + unsigned long flags, order, t; + struct page *page; + struct zone *zone; + u64 start, now; + + start = sched_clock(); + + for_each_populated_zone_pgdat(pgdat, zone) { + spin_lock_irqsave(&zone->lock, flags); + for_each_migratetype_order(order, t) { + list_for_each_entry(page, &zone->free_area[order].free_list[t], lru) { + now = sched_clock(); + if (unlikely(now - start > cfp_timeout_ns)) { + spin_unlock_irqrestore(&zone->lock, flags); + goto out; + } + +#ifdef CONFIG_KMAP_LOCAL + int i; + + /* Clear highmem by clear_highpage() */ + for (i = 0; i < (1 << order); i++) + clear_highpage(page + i); +#else + memset(page_address(page), 0, (1 << order) * PAGE_SIZE); +#endif + touch_nmi_watchdog(); + atomic_add(1 << order, &clear_pages_num); + } + } + spin_unlock_irqrestore(&zone->lock, flags); + + cond_resched(); + } + +out: + kfree(entry); + + if (atomic_dec_and_test(&clear_freelist_workers)) + wake_up(&clear_freelist_wait); +} + +static void init_clear_freelist_work(struct pglist_data *pgdat) +{ + struct pgdat_entry *entry; + + entry = kzalloc(sizeof(struct pgdat_entry), GFP_KERNEL); + if (!entry) + return; + + entry->pgdat = pgdat; + INIT_WORK(&entry->work, clear_pgdat_freelist_pages); + queue_work_node(pgdat->node_id, system_unbound_wq, &entry->work); +} + +static void clear_freelist_pages(void) +{ + struct pglist_data *pgdat; + + mutex_lock(&clear_freelist_lock); + drain_all_pages(NULL); + + for_each_online_pgdat(pgdat) { + atomic_inc(&clear_freelist_workers); + init_clear_freelist_work(pgdat); + } + + wait_event(clear_freelist_wait, atomic_read(&clear_freelist_workers) == 0); + + pr_debug("Cleared pages %d\nFree pages %lu\n", atomic_read(&clear_pages_num), + global_zone_page_state(NR_FREE_PAGES)); + atomic_set(&clear_pages_num, 0); + + mutex_unlock(&clear_freelist_lock); +} + +static int sysctl_clear_freelist_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret; + int val; + + table->data = &val; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (!ret && write) + clear_freelist_pages(); + + return ret; +} + +static struct ctl_table clear_freelist_table[] = { + { + .procname = "clear_freelist_pages", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = &sysctl_clear_freelist_handler, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static struct ctl_table sys_ctl_table[] = { + { + .procname = "vm", + .mode = 0555, + .child = clear_freelist_table, + }, + { } +}; + +static bool clear_freelist_enabled; +static int __init setup_clear_freelist(char *str) +{ + clear_freelist_enabled = true; + return 1; +} +__setup("clear_freelist", setup_clear_freelist); + +static int __init clear_freelist_init(void) +{ + if (clear_freelist_enabled) + register_sysctl_table(sys_ctl_table); + + return 0; +} +module_init(clear_freelist_init); +module_param(cfp_timeout_ms, ulong, 0644); -- 2.33.0

2 1

[PATCH OLK-6.6 0/2] xfs: fix intent item leak during reovery
by Long Li 04 Dec '23

04 Dec '23

This patch set fix intent item leak during reovery when recovery intent fails. Long Li (2): xfs: factor out xfs_defer_pending_abort xfs: abort intent items when recovery intents fail fs/xfs/libxfs/xfs_defer.c | 28 ++++++++++++++++++---------- fs/xfs/libxfs/xfs_defer.h | 2 +- fs/xfs/xfs_log_recover.c | 2 +- 3 files changed, 20 insertions(+), 12 deletions(-) -- 2.31.1

2 3

[PATCH openEuler-22.03-LTS 0/6] backport Broadcom NIC driver patches
by Dapeng Yu 04 Dec '23

04 Dec '23

Backport the latest patches from upstream stable branch linux-5.10.y for Broadcom NIC driver. Florian Fainelli (2): net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop() net: bcmgenet: Restore phy_stop() depending upon suspend/close Somnath Kotur (2): bnxt_en: Query default VLAN before VNIC setup on a VF bnxt_en: Implement .set_port / .unset_port UDP tunnel callbacks Sreekanth Reddy (1): bnxt_en: Don't issue AP reset during ethtool's reset operation Tobias Heider (1): Add MODULE_FIRMWARE() for FIRMWARE_TG357766. drivers/net/ethernet/broadcom/bnxt/bnxt.c | 28 ++++++++++++++----- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- .../net/ethernet/broadcom/genet/bcmgenet.c | 9 +++--- drivers/net/ethernet/broadcom/tg3.c | 1 + 4 files changed, 28 insertions(+), 12 deletions(-) -- 2.43.0

2 1

[PATCH openEuler-22.03-LTS 1/6] net: bcmgenet: Remove phy_stop() from bcmgenet_netif_stop()
by Dapeng Yu 04 Dec '23

04 Dec '23

From: Florian Fainelli <f.fainelli(a)gmail.com> stable inclusion from stable-v5.10.181 commit e92727ed9e8b6798efc1e7ae44bbe7c44c453670 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I8L4MY CVE: NA backport: OLK-5.10, openEuler-22.03-LTS, openEuler-22.03-LTS-SP1, openEuler-22.03-LTS-SP2 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 93e0401e0fc0c54b0ac05b687cd135c2ac38187c ] The call to phy_stop() races with the later call to phy_disconnect(), resulting in concurrent phy_suspend() calls being run from different CPUs. The final call to phy_disconnect() ensures that the PHY is stopped and suspended, too. Fixes: c96e731c93ff ("net: bcmgenet: connect and disconnect from the PHY state machine") Signed-off-by: Florian Fainelli <f.fainelli(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dapeng Yu <dapeng.yu(a)windriver.com> --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 6ee6c34f28f2..52c93701a9e4 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3408,7 +3408,6 @@ static void bcmgenet_netif_stop(struct net_device *dev) /* Disable MAC transmit. TX DMA disabled must be done before this */ umac_enable_set(priv, CMD_TX_EN, false); - phy_stop(dev->phydev); bcmgenet_disable_rx_napi(priv); bcmgenet_intr_disable(priv); -- 2.43.0

1 5

[PATCH OLK-6.6] arm64: errata: add option to disable cache readunique prefetch on HIP08
by Yang Yingliang 04 Dec '23

04 Dec '23

From: Kai Shen <shenkai8(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I3ZFV2 CVE: NA ----------------------------------------------------------- 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'. Signed-off-by: Kai Shen <shenkai8(a)huawei.com> Signed-off-by: Hanjun Guo <guohanjun(a)huawei.com> [XQ: adjusted context] Signed-off-by: Xie XiuQi <xiexiuqi(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/Kconfig | 18 +++++++++++ arch/arm64/kernel/cpu_errata.c | 56 ++++++++++++++++++++++++++++++++++ arch/arm64/tools/cpucaps | 1 + 3 files changed, 75 insertions(+) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 78f20e632712..bbe85ca456c9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1229,6 +1229,24 @@ config SOCIONEXT_SYNQUACER_PREITS If unsure, say Y. +config HISILICON_ERRATUM_HIP08_RU_PREFETCH + bool "HIP08 RU: HiSilicon HIP08 cache readunique might cause performance drop" + default y + help + The HiSilicon HIP08 cache readunique might compromise performance, + use cmdline "readunique_prefetch_disable" to disable RU prefetch. + + If unsure, say Y. + +config HISILICON_HIP08_RU_PREFETCH_DEFAULT_OFF + bool "HIP08 RU: disable HiSilicon HIP08 cache readunique by default" + depends on HISILICON_ERRATUM_HIP08_RU_PREFETCH + default n + help + Disable HiSilicon HIP08 cache readunique by default. + + If unsure, say N. + endmenu # "ARM errata workarounds via the alternatives framework" choice diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 5706e74c5578..6a2ae67e85f7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -13,6 +13,11 @@ #include <asm/cpufeature.h> #include <asm/kvm_asm.h> #include <asm/smp_plat.h> +#ifdef CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH +#include <asm/ptrace.h> +#include <asm/sysreg.h> +#include <linux/smp.h> +#endif static bool __maybe_unused is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope) @@ -121,6 +126,48 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0); } +#ifdef CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH +# ifdef CONFIG_HISILICON_HIP08_RU_PREFETCH_DEFAULT_OFF +static bool readunique_prefetch_enabled; +# else +static bool readunique_prefetch_enabled = true; +# endif +static int __init readunique_prefetch_switch(char *data) +{ + if (!data) + return -EINVAL; + + if (strcmp(data, "off") == 0) + readunique_prefetch_enabled = false; + else if (strcmp(data, "on") == 0) + readunique_prefetch_enabled = true; + else + return -EINVAL; + + return 0; +} +early_param("readunique_prefetch", readunique_prefetch_switch); + +static bool +should_disable_hisi_hip08_ru_prefetch(const struct arm64_cpu_capabilities *entry, int unused) +{ + u64 el; + + if (readunique_prefetch_enabled) + return false; + + el = read_sysreg(CurrentEL); + return el == CurrentEL_EL2; +} + +#define CTLR_HISI_HIP08_RU_PREFETCH (1L << 40) +static void __maybe_unused +hisi_hip08_ru_prefetch_disable(const struct arm64_cpu_capabilities *__unused) +{ + sysreg_clear_set(S3_1_c15_c6_4, 0, CTLR_HISI_HIP08_RU_PREFETCH); +} +#endif + static DEFINE_RAW_SPINLOCK(reg_user_mask_modification); static void __maybe_unused cpu_clear_bf16_from_user_emulation(const struct arm64_cpu_capabilities *__unused) @@ -744,6 +791,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_WORKAROUND_AMPERE_AC03_CPU_38, ERRATA_MIDR_ALL_VERSIONS(MIDR_AMPERE1), }, +#endif +#ifdef CONFIG_HISILICON_ERRATUM_HIP08_RU_PREFETCH + { + .desc = "HiSilicon HIP08 Cache Readunique Prefetch Disable", + .capability = ARM64_WORKAROUND_HISI_HIP08_RU_PREFETCH, + ERRATA_MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + .matches = should_disable_hisi_hip08_ru_prefetch, + .cpu_enable = hisi_hip08_ru_prefetch_disable, + }, #endif { } diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index dea3dc89234b..bbb97036074b 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -100,3 +100,4 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_HISI_HIP08_RU_PREFETCH -- 2.25.1

2 1

[PATCH OLK-5.10 0/3] scsi: scsi_device_gets returns failure
by Li Lingfeng 04 Dec '23

04 Dec '23

If scsi is compiled as a module, scsi_device_gets returns failure when the module is NULL. Li Lingfeng (2): scsi: don't fail if hostt->module is NULL scsi: fix kabi broken in struct Scsi_Host Zhong Jinghua (1): scsi: scsi_device_gets returns failure when the module is NULL. drivers/scsi/hosts.c | 3 +++ drivers/scsi/scsi.c | 6 +++++- include/scsi/scsi_host.h | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) -- 2.31.1

2 4

openEuler Kernel SIG双周例会
by openEuler conference 04 Dec '23

04 Dec '23

您好！ Kernel SIG 邀请您参加 2023-12-08 14:00 召开的WeLink会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中（新增议题可回复邮件申报，也可直接填至会议看板）会议链接：https://bmeeting.huaweicloud.com:36443/#/j/981980862 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the WeLink conference(auto recording) will be held at 2023-12-08 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中（新增议题可回复邮件申报，也可直接填至会议看板） You can join the meeting at https://bmeeting.huaweicloud.com:36443/#/j/981980862. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[openEuler-1.0-LTS] net: prevent rewrite of msg_name in sock_sendmsg()
by Lu Wei 04 Dec '23

04 Dec '23

From: Jordan Rife <jrife(a)google.com> stable inclusion from stable-v4.19.297 commit 3d62f2577c7414e5b94e4baad6eb621165960f30 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8EZY4 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 86a7e0b69bd5b812e48a20c66c2161744f3caa16 ] Callers of sock_sendmsg(), and similarly kernel_sendmsg(), in kernel space may observe their value of msg_name change in cases where BPF sendmsg hooks rewrite the send address. This has been confirmed to break NFS mounts running in UDP mode and has the potential to break other systems. This patch: 1) Creates a new function called __sock_sendmsg() with same logic as the old sock_sendmsg() function. 2) Replaces calls to sock_sendmsg() made by __sys_sendto() and __sys_sendmsg() with __sock_sendmsg() to avoid an unnecessary copy, as these system calls are already protected. 3) Modifies sock_sendmsg() so that it makes a copy of msg_name if present before passing it down the stack to insulate callers from changes to the send address. Link: https://lore.kernel.org/netdev/20230912013332.2048422-1-jrife@google.com/ Fixes: 1cedee13d25a ("bpf: Hooks for sys_sendmsg") Cc: stable(a)vger.kernel.org Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Jordan Rife <jrife(a)google.com> Reviewed-by: Simon Horman <horms(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> conflict: net/socket.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> --- net/socket.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/net/socket.c b/net/socket.c index 3d3632fe4a34..0cc52ba0b0e2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -637,6 +637,14 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) } EXPORT_SYMBOL(__sock_tx_timestamp); +static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) +{ + int err = security_socket_sendmsg(sock, msg, + msg_data_left(msg)); + + return err ?: sock_sendmsg_nosec(sock, msg); +} + /** * sock_sendmsg - send a message through @sock * @sock: socket @@ -655,10 +663,19 @@ static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) int sock_sendmsg(struct socket *sock, struct msghdr *msg) { - int err = security_socket_sendmsg(sock, msg, - msg_data_left(msg)); + struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; + struct sockaddr_storage address; + int ret; - return err ?: sock_sendmsg_nosec(sock, msg); + if (msg->msg_name) { + memcpy(&address, msg->msg_name, msg->msg_namelen); + msg->msg_name = &address; + } + + ret = __sock_sendmsg(sock, msg); + msg->msg_name = save_addr; + + return ret; } EXPORT_SYMBOL(sock_sendmsg); @@ -963,7 +980,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; - res = sock_sendmsg(sock, &msg); + res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } @@ -1940,7 +1957,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; - err = sock_sendmsg(sock, &msg); + err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); @@ -2272,7 +2289,7 @@ static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } - err = sock_sendmsg(sock, msg_sys); + err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. -- 2.34.1

1 0

[PATCH OLK-5.10 0/3] scsi: scsi_device_gets returns failure
by Li Lingfeng 04 Dec '23

04 Dec '23

If scsi is compiled as a module, scsi_device_gets returns failure when the module is NULL. Li Lingfeng (2): scsi: don't fail if hostt->module is NULL scsi: fix kabi broken in struct Scsi_Host Zhong Jinghua (1): scsi: scsi_device_gets returns failure when the module is NULL. drivers/scsi/hosts.c | 3 +++ drivers/scsi/scsi.c | 6 +++++- include/scsi/scsi_host.h | 2 +- 3 files changed, 9 insertions(+), 2 deletions(-) -- 2.31.1

2 5

[PATCH OLK-6.6 0/5] xfs: fix some misc issue
by Long Li 04 Dec '23

04 Dec '23

Long Li (5): xfs: fix a UAF when inode item push xfs: fix a UAF in xfs_iflush_abort_clean xfs: fix dir3 block read verify fail during log recover 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_buf_item_recover.c | 9 +++------ fs/xfs/xfs_inode_item.c | 8 +++++++- fs/xfs/xfs_trans.c | 2 +- 5 files changed, 18 insertions(+), 9 deletions(-) -- 2.31.1

1 5