- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] HID: core: Correctly handle ReportSize being zero
by Yang Yingliang 18 Jan '21

18 Jan '21

From: Marc Zyngier <maz(a)kernel.org> stable inclusion from linux-4.19.144 commit abae259fdccc5e41ff302dd80a2b944ce385c970 CVE: CVE-2020-0465 -------------------------------- commit bce1305c0ece3dc549663605e567655dd701752c upstream. It appears that a ReportSize value of zero is legal, even if a bit non-sensical. Most of the HID code seems to handle that gracefully, except when computing the total size in bytes. When fed as input to memset, this leads to some funky outcomes. Detect the corner case and correctly compute the size. Cc: stable(a)vger.kernel.org Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Benjamin Tissoires <benjamin.tissoires(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/hid/hid-core.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3a359716fb38..3178580db7fa 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1419,6 +1419,17 @@ static void hid_output_field(const struct hid_device *hid, } } +/* + * Compute the size of a report. + */ +static size_t hid_compute_report_size(struct hid_report *report) +{ + if (report->size) + return ((report->size - 1) >> 3) + 1; + + return 0; +} + /* * Create a report. 'data' has to be allocated using * hid_alloc_report_buf() so that it has proper size. @@ -1431,7 +1442,7 @@ void hid_output_report(struct hid_report *report, __u8 *data) if (report->id > 0) *data++ = report->id; - memset(data, 0, ((report->size - 1) >> 3) + 1); + memset(data, 0, hid_compute_report_size(report)); for (n = 0; n < report->maxfield; n++) hid_output_field(report->device, report->field[n], data); } @@ -1558,7 +1569,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, csize--; } - rsize = ((report->size - 1) >> 3) + 1; + rsize = hid_compute_report_size(report); if (rsize > HID_MAX_BUFFER_SIZE) rsize = HID_MAX_BUFFER_SIZE; -- 2.25.1

1 0

[PATCH kernel-4.19 1/2] ascend: share pool: optimize the big lock for memory processing
by Yang Yingliang 18 Jan '21

18 Jan '21

From: Ding Tianhong <dingtianhong(a)huawei.com> ascend inclusion category: feature bugzilla: NA CVE: NA ------------------------------------------------- The sp_mutex is used to protect all critical path for share pool, it has serious affected the performance of the the memory alloc and release interface when there is a lot of process in the same memory group, it will serious break the scailability of the system, so add a new read semaphore lock to instead of the big lock for allocation and release critical path. The scailability has been greatly improved by this modification. Show the test result: number of process: alloc 4M avg time: Before the patch: 1 32us 3 96us 10 330us after the patch: 1 32us 3 40us 10 60us v2: fix some conflicts and clean some code. Signed-off-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/share_pool.h | 5 ++ kernel/fork.c | 4 +- mm/share_pool.c | 170 ++++++++++++++++++++----------------- 3 files changed, 100 insertions(+), 79 deletions(-) diff --git a/include/linux/share_pool.h b/include/linux/share_pool.h index 70b841d0eb8e..f2d17cb85fa5 100644 --- a/include/linux/share_pool.h +++ b/include/linux/share_pool.h @@ -93,6 +93,8 @@ struct sp_group { unsigned long dvpp_va_start; unsigned long dvpp_size; atomic_t use_count; + /* protect the group internal elements */ + struct rw_semaphore rw_lock; }; struct sp_walk_data { @@ -238,6 +240,8 @@ extern void *vmalloc_hugepage_user(unsigned long size); extern void *buff_vzalloc_user(unsigned long size); extern void *buff_vzalloc_hugepage_user(unsigned long size); +void sp_exit_mm(struct mm_struct *mm); + #else static inline int sp_group_add_task(int pid, int spg_id) @@ -400,6 +404,7 @@ static inline void *buff_vzalloc_hugepage_user(unsigned long size) { return NULL; } + #endif #endif /* LINUX_SHARE_POOL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index d1d8ac083c80..61496b70cfb8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1055,8 +1055,6 @@ static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); - sp_group_exit(mm); - uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); @@ -1084,6 +1082,8 @@ void mmput(struct mm_struct *mm) { might_sleep(); + sp_group_exit(mm); + if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } diff --git a/mm/share_pool.c b/mm/share_pool.c index e326c95104da..27792a641401 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -197,6 +197,16 @@ static bool host_svm_sp_enable = false; int sysctl_share_pool_hugepage_enable = 1; +static void free_sp_group(struct sp_group *spg); + +static bool sp_group_get(struct sp_group *spg) +{ + if (spg_valid(spg) && atomic_inc_not_zero(&spg->use_count)) + return true; + + return false; +} + static unsigned long spa_size(struct sp_area *spa) { return spa->real_size; @@ -337,7 +347,9 @@ static struct sp_group *__sp_find_spg(int pid, int spg_id) put_task_struct(tsk); } else { + mutex_lock(&sp_mutex); spg = idr_find(&sp_group_idr, spg_id); + mutex_unlock(&sp_mutex); } return spg; @@ -392,6 +404,8 @@ static struct sp_group *find_or_alloc_sp_group(int spg_id) INIT_LIST_HEAD(&spg->procs); INIT_LIST_HEAD(&spg->spa_list); + init_rwsem(&spg->rw_lock); + ret = idr_alloc(&sp_group_idr, spg, spg_id, spg_id+1, GFP_KERNEL); if (ret < 0) { @@ -422,9 +436,8 @@ static struct sp_group *find_or_alloc_sp_group(int spg_id) goto out_fput; } } else { - if (!spg_valid(spg)) + if (!sp_group_get(spg)) return ERR_PTR(-ENODEV); - atomic_inc(&spg->use_count); } return spg; @@ -607,6 +620,8 @@ int sp_group_add_task(int pid, int spg_id) } mm->sp_group = spg; + + down_write(&spg->rw_lock); /* We reactive the spg even the spg exists already. */ spg->is_alive = true; list_add_tail(&mm->sp_node, &spg->procs); @@ -675,11 +690,14 @@ int sp_group_add_task(int pid, int spg_id) mm->sp_group = NULL; } + up_write(&spg->rw_lock); out_drop_group: if (unlikely(ret)) __sp_group_drop_locked(spg); out_put_mm: - mmput(mm); + /* No need to put the mm if the sp group add this mm success.*/ + if (unlikely(ret)) + mmput(mm); out_put_task: put_task_struct(tsk); out_unlock: @@ -712,44 +730,12 @@ static void spg_exit_unlock(bool unlock) mutex_unlock(&sp_mutex); } -/* - * Do cleanup when a process exits. - */ -void sp_group_exit(struct mm_struct *mm) -{ - bool is_alive = true; - bool unlock; - - /* - * Nothing to do if this thread group doesn't belong to any sp_group. - * No need to protect this check with lock because we can add a task - * to a group if !PF_EXITING. - */ - if (!mm->sp_group) - return; - - spg_exit_lock(&unlock); - if (list_is_singular(&mm->sp_group->procs)) - is_alive = mm->sp_group->is_alive = false; - list_del(&mm->sp_node); - spg_exit_unlock(unlock); - - /* - * To avoid calling this with sp_mutex held, we first mark the - * sp_group as dead and then send the notification and then do - * the real cleanup in sp_group_post_exit(). - */ - if (!is_alive) - blocking_notifier_call_chain(&sp_notifier_chain, 0, - mm->sp_group); -} - void sp_group_post_exit(struct mm_struct *mm) { struct sp_proc_stat *stat; bool unlock; - if (!mm->sp_group) + if (!enable_ascend_share_pool || !mm->sp_group) return; spg_exit_lock(&unlock); @@ -1139,8 +1125,6 @@ static void sp_munmap(struct mm_struct *mm, unsigned long addr, { int err; - if (!mmget_not_zero(mm)) - return; down_write(&mm->mmap_sem); err = do_munmap(mm, addr, size, NULL); @@ -1150,7 +1134,6 @@ static void sp_munmap(struct mm_struct *mm, unsigned long addr, } up_write(&mm->mmap_sem); - mmput(mm); } /* The caller must hold sp_mutex. */ @@ -1183,8 +1166,6 @@ int sp_free(unsigned long addr) check_interrupt_context(); - mutex_lock(&sp_mutex); - /* * Access control: a share pool addr can only be freed by another task * in the same spg or a kthread (such as buff_module_guard_work) @@ -1217,6 +1198,8 @@ int sp_free(unsigned long addr) sp_dump_stack(); + down_read(&spa->spg->rw_lock); + __sp_free(spa->spg, spa->va_start, spa_size(spa), NULL); /* Free the memory of the backing shmem or hugetlbfs */ @@ -1226,6 +1209,9 @@ int sp_free(unsigned long addr) if (ret) pr_err("share pool: sp free fallocate failed: %d\n", ret); + up_read(&spa->spg->rw_lock); + + mutex_lock(&sp_mutex); /* pointer stat may be invalid because of kthread buff_module_guard_work */ if (current->mm == NULL) { kthread_stat.alloc_size -= spa->real_size; @@ -1236,12 +1222,11 @@ int sp_free(unsigned long addr) else BUG(); } + mutex_unlock(&sp_mutex); drop_spa: __sp_area_drop(spa); out: - mutex_unlock(&sp_mutex); - sp_try_to_compact(); return ret; } @@ -1317,9 +1302,7 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) if (sp_flags & SP_HUGEPAGE_ONLY) sp_flags |= SP_HUGEPAGE; - mutex_lock(&sp_mutex); spg = __sp_find_spg(current->pid, SPG_ID_DEFAULT); - mutex_unlock(&sp_mutex); if (!spg) { /* DVPP pass through scene: first call sp_alloc() */ /* mdc scene hack */ if (enable_mdc_default_group) @@ -1336,14 +1319,16 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) ret); return ERR_PTR(ret); } - mutex_lock(&sp_mutex); spg = current->mm->sp_group; } else { /* other scenes */ - mutex_lock(&sp_mutex); if (spg_id != SPG_ID_DEFAULT) { + mutex_lock(&sp_mutex); /* the caller should be a member of the sp group */ - if (spg != idr_find(&sp_group_idr, spg_id)) + if (spg != idr_find(&sp_group_idr, spg_id)) { + mutex_unlock(&sp_mutex); goto out; + } + mutex_unlock(&sp_mutex); } } @@ -1352,6 +1337,7 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) goto out; } + down_read(&spg->rw_lock); if (sp_flags & SP_HUGEPAGE) { file = spg->file_hugetlb; size_aligned = ALIGN(size, PMD_SIZE); @@ -1376,31 +1362,25 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) unsigned long populate = 0; struct vm_area_struct *vma; - if (!mmget_not_zero(mm)) - continue; - down_write(&mm->mmap_sem); mmap_addr = sp_mmap(mm, file, spa, &populate); if (IS_ERR_VALUE(mmap_addr)) { up_write(&mm->mmap_sem); p = (void *)mmap_addr; __sp_free(spg, sp_addr, size_aligned, mm); - mmput(mm); pr_err("share pool: allocation sp mmap failed, ret %ld\n", mmap_addr); goto out; } - p =(void *)mmap_addr; /* success */ + p = (void *)mmap_addr; /* success */ if (populate == 0) { up_write(&mm->mmap_sem); - mmput(mm); continue; } vma = find_vma(mm, sp_addr); if (unlikely(!vma)) { up_write(&mm->mmap_sem); - mmput(mm); pr_err("share pool: allocation failed due to find %pK vma failure\n", (void *)sp_addr); p = ERR_PTR(-EINVAL); @@ -1461,24 +1441,22 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) size_aligned = ALIGN(size, PAGE_SIZE); sp_flags &= ~SP_HUGEPAGE; __sp_area_drop(spa); - mmput(mm); goto try_again; } } - - mmput(mm); break; } - mmput(mm); } +out: + up_read(&spg->rw_lock); + + mutex_lock(&sp_mutex); if (!IS_ERR(p)) { stat = idr_find(&sp_stat_idr, current->mm->sp_stat_id); if (stat) stat->alloc_size += size_aligned; } - -out: mutex_unlock(&sp_mutex); /* this will free spa if mmap failed */ @@ -1556,10 +1534,6 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, } } - if (!mmget_not_zero(mm)) { - ret_addr = -ESPGMMEXIT; - goto put_file; - } down_write(&mm->mmap_sem); ret_addr = sp_mmap(mm, file, spa, &populate); @@ -1604,8 +1578,7 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, put_mm: up_write(&mm->mmap_sem); - mmput(mm); -put_file: + if (!spa->spg && file) fput(file); @@ -1769,10 +1742,12 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, */ stat = sp_init_proc_stat(tsk, mm); if (IS_ERR(stat)) { + mutex_unlock(&sp_mutex); uva = stat; pr_err("share pool: init proc stat failed, ret %lx\n", PTR_ERR(stat)); goto out_unlock; } + mutex_unlock(&sp_mutex); spg = __sp_find_spg(pid, SPG_ID_DEFAULT); if (spg == NULL) { @@ -1794,6 +1769,7 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, } if (!vmalloc_area_set_flag(spa, kva_aligned, VM_SHAREPOOL)) { + up_read(&spg->rw_lock); pr_err("share pool: %s: the kva %pK is not valid\n", __func__, (void *)kva_aligned); goto out_drop_spa; } @@ -1808,12 +1784,14 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, goto out_unlock; } + down_read(&spg->rw_lock); if (enable_share_k2u_spg) spa = sp_alloc_area(size_aligned, sp_flags, spg, SPA_TYPE_K2SPG); else spa = sp_alloc_area(size_aligned, sp_flags, NULL, SPA_TYPE_K2TASK); if (IS_ERR(spa)) { + up_read(&spg->rw_lock); if (printk_ratelimit()) pr_err("share pool: k2u(spg) failed due to alloc spa failure " "(potential no enough virtual memory when -75): %ld\n", @@ -1831,14 +1809,18 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, uva = sp_make_share_kva_to_spg(kva_aligned, spa, spg); else uva = sp_make_share_kva_to_task(kva_aligned, spa, mm); + + up_read(&spg->rw_lock); } else { /* group is dead, return -ENODEV */ pr_err("share pool: failed to make k2u, sp group is dead\n"); } if (!IS_ERR(uva)) { + mutex_lock(&sp_mutex); uva = uva + (kva - kva_aligned); stat->k2u_size += size_aligned; + mutex_unlock(&sp_mutex); } else { /* associate vma and spa */ if (!vmalloc_area_clr_flag(spa, kva_aligned, VM_SHAREPOOL)) @@ -1849,7 +1831,6 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, out_drop_spa: __sp_area_drop(spa); out_unlock: - mutex_unlock(&sp_mutex); mmput(mm); out_put_task: put_task_struct(tsk); @@ -2144,7 +2125,6 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp unsigned int page_size; struct sp_proc_stat *stat; - mutex_lock(&sp_mutex); /* * at first we guess it's a hugepage addr * we can tolerate at most PMD_SIZE or PAGE_SIZE which is matched in k2u @@ -2157,7 +2137,7 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp if (printk_ratelimit()) pr_err("share pool: invalid input uva %pK in unshare uva\n", (void *)uva); - goto out_unlock; + goto out; } } @@ -2259,10 +2239,14 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp goto out_drop_area; } + down_read(&spa->spg->rw_lock); __sp_free(spa->spg, uva_aligned, size_aligned, NULL); + up_read(&spa->spg->rw_lock); } sp_dump_stack(); + + mutex_lock(&sp_mutex); /* pointer stat may be invalid because of kthread buff_module_guard_work */ if (current->mm == NULL) { kthread_stat.k2u_size -= spa->real_size; @@ -2273,6 +2257,7 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp else WARN(1, "share_pool: %s: null process stat\n", __func__); } + mutex_unlock(&sp_mutex); out_clr_flag: /* deassociate vma and spa */ @@ -2281,8 +2266,7 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp out_drop_area: __sp_area_drop(spa); -out_unlock: - mutex_unlock(&sp_mutex); +out: return ret; } @@ -2446,7 +2430,7 @@ bool sp_config_dvpp_range(size_t start, size_t size, int device_id, int pid) check_interrupt_context(); if (device_id < 0 || device_id >= MAX_DEVID || pid < 0 || size <= 0 || - size> MMAP_SHARE_POOL_16G_SIZE) + size > MMAP_SHARE_POOL_16G_SIZE) return false; mutex_lock(&sp_mutex); @@ -2468,9 +2452,10 @@ EXPORT_SYMBOL_GPL(sp_config_dvpp_range); /* Check whether the address belongs to the share pool. */ bool is_sharepool_addr(unsigned long addr) { - if (host_svm_sp_enable == false) - return addr >= MMAP_SHARE_POOL_START && addr < (MMAP_SHARE_POOL_16G_START + MMAP_SHARE_POOL_16G_SIZE); - return addr >= MMAP_SHARE_POOL_START && addr < MMAP_SHARE_POOL_END; + if (host_svm_sp_enable == false) + return addr >= MMAP_SHARE_POOL_START && addr < (MMAP_SHARE_POOL_16G_START + MMAP_SHARE_POOL_16G_SIZE); + + return addr >= MMAP_SHARE_POOL_START && addr < MMAP_SHARE_POOL_END; } EXPORT_SYMBOL_GPL(is_sharepool_addr); @@ -2515,7 +2500,8 @@ int proc_sp_group_state(struct seq_file *m, struct pid_namespace *ns, return 0; } -static void rb_spa_stat_show(struct seq_file *seq) { +static void rb_spa_stat_show(struct seq_file *seq) +{ struct rb_node *node; struct sp_area *spa; @@ -2814,6 +2800,36 @@ vm_fault_t sharepool_no_page(struct mm_struct *mm, } EXPORT_SYMBOL(sharepool_no_page); +#define MM_WOULD_FREE 2 + +void sp_group_exit(struct mm_struct *mm) +{ + struct sp_group *spg = NULL; + bool is_alive = true, unlock; + + if (!enable_ascend_share_pool) + return; + + spg = mm->sp_group; + + /* If the mm_users is 2, it means that the mm is ready to be freed + because the last owner of this mm is in exiting process. + */ + if (spg_valid(spg) && atomic_read(&mm->mm_users) == MM_WOULD_FREE) { + spg_exit_lock(&unlock); + down_write(&spg->rw_lock); + if (list_is_singular(&spg->procs)) + is_alive = spg->is_alive = false; + list_del(&mm->sp_node); + up_write(&spg->rw_lock); + if (!is_alive) + blocking_notifier_call_chain(&sp_notifier_chain, 0, + mm->sp_group); + atomic_dec(&mm->mm_users); + spg_exit_unlock(unlock); + } +} + struct page *sp_alloc_pages(struct vm_struct *area, gfp_t mask, unsigned int page_order, int node) { -- 2.25.1

1 1

[PATCH kernel-4.19 1/5] share_pool: Remove redundant null pointer check
by Yang Yingliang 14 Jan '21

14 Jan '21

From: Tang Yizhou <tangyizhou(a)huawei.com> ascend inclusion category: bugfix bugzilla: 46925 CVE: NA ------------------------------------------------- __sp_area_drop_locked() checks null pointer of spa, so remove null pointer checks before calling __sp_area_drop_locked(). Reported-by: Cui Bixuan <cuibixuan(a)huawei.com> Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 4316625defac..2cfac4642e0b 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -443,8 +443,7 @@ static void sp_munmap_task_areas(struct mm_struct *mm, struct list_head *stop) if (&spa->link == stop) break; - if (prev) - __sp_area_drop_locked(prev); + __sp_area_drop_locked(prev); prev = spa; atomic_inc(&spa->use_count); @@ -459,8 +458,7 @@ static void sp_munmap_task_areas(struct mm_struct *mm, struct list_head *stop) spin_lock(&sp_area_lock); } - if (prev) - __sp_area_drop_locked(prev); + __sp_area_drop_locked(prev); spin_unlock(&sp_area_lock); } @@ -607,8 +605,7 @@ int sp_group_add_task(int pid, int spg_id) struct file *file = spa_file(spa); unsigned long addr; - if (prev) - __sp_area_drop_locked(prev); + __sp_area_drop_locked(prev); prev = spa; atomic_inc(&spa->use_count); @@ -651,8 +648,7 @@ int sp_group_add_task(int pid, int spg_id) spin_lock(&sp_area_lock); } - if (prev) - __sp_area_drop_locked(prev); + __sp_area_drop_locked(prev); spin_unlock(&sp_area_lock); if (unlikely(ret)) { -- 2.25.1

1 4

[PATCH kernel-4.19 00/78] backport stable-4.19.167
by Yang Yingliang 14 Jan '21

14 Jan '21

Adrian Hunter (1): scsi: ufs-pci: Ensure UFS device is in PowerDown mode for suspend-to-disk ->poweroff() Alexey Dobriyan (2): proc: change ->nlink under proc_subdir_lock proc: fix lookup in /proc/net subdirectories after setns(2) Antoine Tenart (4): net-sysfs: take the rtnl lock when storing xps_cpus net-sysfs: take the rtnl lock when accessing xps_cpus_map and num_tc net-sysfs: take the rtnl lock when storing xps_rxqs net-sysfs: take the rtnl lock when accessing xps_rxqs_map and num_tc Ard Biesheuvel (1): crypto: ecdh - avoid buffer overflow in ecdh_set_secret() Arnd Bergmann (1): usb: gadget: select CONFIG_CRC32 Bard Liao (1): Revert "device property: Keep secondary firmware node secondary by type" Bart Van Assche (2): scsi: ide: Do not set the RQF_PREEMPT flag for sense requests scsi: scsi_transport_spi: Set RQF_PM for domain validation commands Bean Huo (1): scsi: ufs: Fix wrong print message in dev_err() Bjørn Mork (2): net: usb: qmi_wwan: add Quectel EM160R-GL USB: serial: option: add Quectel EM160R-GL Chandana Kishori Chiluveru (1): usb: gadget: configfs: Preserve function ordering after bind failure Christophe JAILLET (1): staging: mt7621-dma: Fix a resource leak in an error handling path Cong Wang (1): erspan: fix version 1 check in gre_parse_header() Dan Carpenter (1): atm: idt77252: call pci_disable_device() on error path Dan Williams (1): x86/mm: Fix leak of pmd ptlock Daniel Palmer (1): USB: serial: option: add LongSung M5710 module support David Disseldorp (1): scsi: target: Fix XCOPY NAA identifier lookup Dexuan Cui (1): video: hyperv_fb: Fix the mmap() regression for v5.4.y and older Dinghao Liu (1): net: ethernet: Fix memleak in ethoc_probe Dominique Martinet (1): kbuild: don't hardcode depmod path Eddie Hung (1): usb: gadget: configfs: Fix use-after-free issue with udc_name Filipe Manana (1): btrfs: send: fix wrong file path when there is an inode with a pending rmdir Florian Fainelli (1): net: systemport: set dev->max_mtu to UMAC_MAX_MTU_SIZE Florian Westphal (1): netfilter: xt_RATEEST: reject non-null terminated string from userspace Greg Kroah-Hartman (1): Linux 4.19.167 Grygorii Strashko (1): net: ethernet: ti: cpts: fix ethtool output when no ptp_clock registered Guillaume Nault (1): ipv4: Ignore ECN bits for fib lookups in fib_compute_spec_dst() Hans de Goede (1): Bluetooth: revert: hci_h5: close serdev device and free hu in h5_close Heiner Kallweit (1): r8169: work around power-saving bug on some chip versions Huang Shijie (1): lib/genalloc: fix the overflow when size is too big Jeff Dike (1): virtio_net: Fix recursive call to cpus_read_lock() Jerome Brunet (1): usb: gadget: f_uac2: reset wMaxPacketSize Johan Hovold (4): USB: serial: iuu_phoenix: fix DMA from stack USB: yurex: fix control-URB timeout handling USB: usblp: fix DMA to stack USB: serial: keyspan_pda: remove unused variable John Wang (1): net/ncsi: Use real net-device for response handler Kailang Yang (1): ALSA: hda/realtek - Fix speaker volume control on Lenovo C940 Linus Torvalds (1): depmod: handle the case of /sbin/depmod without /sbin in PATH Manish Chopra (1): qede: fix offload for IPIP tunnel packets Manish Narani (1): usb: gadget: u_ether: Fix MTU size mismatch with RX packet size Michael Grzeschik (1): USB: xhci: fix U1/U2 handling for hardware with XHCI_INTEL_HOST quirk set Paolo Bonzini (1): KVM: x86: fix shift out of bounds reported by UBSAN Randy Dunlap (2): net: sched: prevent invalid Scell_log shift count usb: usbip: vhci_hcd: protect shift size Rasmus Villemoes (2): ethernet: ucc_geth: fix use-after-free in ucc_geth_remove() ethernet: ucc_geth: set dev->max_mtu to 1518 Roger Pau Monne (1): xen/pvh: correctly setup the PV EFI interface for dom0 Roland Dreier (1): CDC-NCM: remove "connected" log message Sean Young (1): USB: cdc-acm: blacklist another IR Droid device Serge Semin (1): usb: dwc3: ulpi: Use VStsDone to detect PHY regs access completion Sriharsha Allenki (1): usb: gadget: Fix spinlock lockup on usb_function_deactivate Stefan Chulski (3): net: mvpp2: Add TCAM entry to drop flow control pause frames net: mvpp2: prs: fix PPPoE with ipv6 packet parse net: mvpp2: Fix GoP port 3 Networking Complex Control configurations Subash Abhinov Kasiviswanathan (1): netfilter: x_tables: Update remaining dereference to RCU Sylwester Dziedziuch (1): i40e: Fix Error I40E_AQ_RC_EINVAL when removing VFs Takashi Iwai (2): ALSA: usb-audio: Fix UBSAN warnings for MIDI jacks ALSA: hda/via: Fix runtime PM for Clevo W35xSS Tetsuo Handa (1): USB: cdc-wdm: Fix use after free in service_outstanding_interrupt(). Thinh Nguyen (1): usb: uas: Add PNY USB Portable SSD to unusual_uas Vasily Averin (1): netfilter: ipset: fix shift-out-of-bounds in htable_bits() Xie He (1): net: hdlc_ppp: Fix issues when mod_timer is called while timer is running Yang Yingliang (1): USB: gadget: legacy: fix return error code in acm_ms_bind() Ying-Tsun Huang (1): x86/mtrr: Correct the range check before performing MTRR type lookups Yu Kuai (1): usb: chipidea: ci_hdrc_imx: add missing put_device() call in usbmisc_get_init_data() Yunfeng Ye (1): workqueue: Kick a worker based on the actual activation of delayed works Yunjian Wang (3): tun: fix return value when the number of iovs exceeds MAX_SKB_FRAGS net: hns: fix return value check in __lb_other_process() vhost_net: fix ubuf refcount incorrectly when sendmsg fails Zqiang (1): usb: gadget: function: printer: Fix a memory leak for interface descriptor bo liu (1): ALSA: hda/conexant: add a new hda codec CX11970 taehyun.cho (1): usb: gadget: enable super speed plus Makefile | 4 +- arch/x86/kernel/cpu/mtrr/generic.c | 6 +- arch/x86/kvm/mmu.h | 2 +- arch/x86/mm/pgtable.c | 2 + arch/x86/xen/efi.c | 12 +- arch/x86/xen/enlighten_pv.c | 2 +- arch/x86/xen/enlighten_pvh.c | 4 + arch/x86/xen/xen-ops.h | 4 +- crypto/ecdh.c | 3 +- drivers/atm/idt77252.c | 2 +- drivers/base/core.c | 2 +- drivers/bluetooth/hci_h5.c | 8 +- drivers/ide/ide-atapi.c | 1 - drivers/ide/ide-io.c | 5 - drivers/net/ethernet/broadcom/bcmsysport.c | 1 + drivers/net/ethernet/ethoc.c | 3 +- drivers/net/ethernet/freescale/ucc_geth.c | 3 +- .../net/ethernet/hisilicon/hns/hns_ethtool.c | 4 + drivers/net/ethernet/intel/i40e/i40e.h | 3 + drivers/net/ethernet/intel/i40e/i40e_main.c | 10 ++ .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 4 +- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- .../net/ethernet/marvell/mvpp2/mvpp2_prs.c | 38 +++++- .../net/ethernet/marvell/mvpp2/mvpp2_prs.h | 2 +- drivers/net/ethernet/qlogic/qede/qede_fp.c | 5 + drivers/net/ethernet/realtek/r8169.c | 6 +- drivers/net/ethernet/ti/cpts.c | 2 + drivers/net/tun.c | 2 +- drivers/net/usb/cdc_ncm.c | 3 - drivers/net/usb/qmi_wwan.c | 1 + drivers/net/virtio_net.c | 12 +- drivers/net/wan/hdlc_ppp.c | 7 ++ drivers/scsi/scsi_transport_spi.c | 27 ++-- drivers/scsi/ufs/ufshcd-pci.c | 34 ++++- drivers/scsi/ufs/ufshcd.c | 2 +- drivers/staging/mt7621-dma/mtk-hsdma.c | 4 +- drivers/target/target_core_xcopy.c | 119 ++++++++++-------- drivers/target/target_core_xcopy.h | 1 + drivers/usb/chipidea/ci_hdrc_imx.c | 6 +- drivers/usb/class/cdc-acm.c | 4 + drivers/usb/class/cdc-wdm.c | 16 ++- drivers/usb/class/usblp.c | 21 +++- drivers/usb/dwc3/core.h | 1 + drivers/usb/dwc3/ulpi.c | 2 +- drivers/usb/gadget/Kconfig | 2 + drivers/usb/gadget/composite.c | 10 +- drivers/usb/gadget/configfs.c | 19 ++- drivers/usb/gadget/function/f_printer.c | 1 + drivers/usb/gadget/function/f_uac2.c | 69 +++++++--- drivers/usb/gadget/function/u_ether.c | 9 +- drivers/usb/gadget/legacy/acm_ms.c | 4 +- drivers/usb/host/xhci.c | 24 ++-- drivers/usb/misc/yurex.c | 3 + drivers/usb/serial/iuu_phoenix.c | 20 ++- drivers/usb/serial/keyspan_pda.c | 2 - drivers/usb/serial/option.c | 3 + drivers/usb/storage/unusual_uas.h | 7 ++ drivers/usb/usbip/vhci_hcd.c | 2 + drivers/vhost/net.c | 6 +- drivers/video/fbdev/hyperv_fb.c | 6 +- fs/btrfs/send.c | 49 +++++--- fs/proc/generic.c | 55 +++++--- fs/proc/internal.h | 7 ++ fs/proc/proc_net.c | 16 --- include/linux/proc_fs.h | 8 +- include/net/red.h | 4 +- kernel/workqueue.c | 13 +- lib/genalloc.c | 25 ++-- net/core/net-sysfs.c | 65 ++++++++-- net/ipv4/fib_frontend.c | 2 +- net/ipv4/gre_demux.c | 2 +- net/ipv4/netfilter/arp_tables.c | 2 +- net/ipv4/netfilter/ip_tables.c | 2 +- net/ipv6/netfilter/ip6_tables.c | 2 +- net/ncsi/ncsi-rsp.c | 2 +- net/netfilter/ipset/ip_set_hash_gen.h | 20 +-- net/netfilter/xt_RATEEST.c | 3 + net/sched/sch_choke.c | 2 +- net/sched/sch_gred.c | 2 +- net/sched/sch_red.c | 2 +- net/sched/sch_sfq.c | 2 +- scripts/depmod.sh | 2 + sound/pci/hda/hda_intel.c | 2 - sound/pci/hda/patch_conexant.c | 1 + sound/pci/hda/patch_realtek.c | 6 + sound/pci/hda/patch_via.c | 13 ++ sound/usb/midi.c | 4 + 87 files changed, 624 insertions(+), 278 deletions(-) -- 2.25.1

1 78

[PATCH kernel-4.19 0/8] backport stable-4.19.166
by Yang Yingliang 11 Jan '21

11 Jan '21

Felix Fietkau (1): Revert "mtd: spinand: Fix OOB read" Greg Kroah-Hartman (1): Linux 4.19.166 Jonathan Cameron (2): iio:imu:bmi160: Fix alignment and data leak issues iio:magnetometer:mag3110: Fix alignment and data leak issues. Josh Poimboeuf (1): kdev_t: always inline major/minor helper functions Tudor Ambarus (1): dmaengine: at_hdmac: Substitute kzalloc with kmalloc Yu Kuai (2): dmaengine: at_hdmac: add missing put_device() call in at_dma_xlate() dmaengine: at_hdmac: add missing kfree() call in at_dma_xlate() Makefile | 2 +- drivers/dma/at_hdmac.c | 11 ++++++++--- drivers/iio/imu/bmi160/bmi160_core.c | 13 +++++++++---- drivers/iio/magnetometer/mag3110.c | 13 +++++++++---- drivers/mtd/nand/spi/core.c | 4 ---- include/linux/kdev_t.h | 22 +++++++++++----------- 6 files changed, 38 insertions(+), 27 deletions(-) -- 2.25.1

1 8

[PATCH kernel-4.19 1/5] arm64/ascend: mm: Fix hugetlb check node error
by Yang Yingliang 11 Jan '21

11 Jan '21

From: Fang Lijun <fanglijun3(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- The vm_flags will changed by MAP_CHECKNODE, so we must use it for output argument. Fixes: 66bd45db2b03 ("arm64/ascend: mm: Fix arm32 compile warnings") Signed-off-by: Fang Lijun <fanglijun3(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/mman.h | 7 ++++--- mm/mmap.c | 2 +- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/include/linux/mman.h b/include/linux/mman.h index d35d984c058c..a8ea591faed7 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -76,15 +76,16 @@ static inline int dvpp_mmap_zone(unsigned long addr) { return 0; } #ifdef CONFIG_COHERENT_DEVICE #define CHECKNODE_BITS 48 #define CHECKNODE_MASK (~((_AC(1, UL) << CHECKNODE_BITS) - 1)) -static inline void set_vm_checknode(vm_flags_t vm_flags, unsigned long flags) +static inline void set_vm_checknode(vm_flags_t *vm_flags, unsigned long flags) { if (is_set_cdmmask()) - vm_flags |= VM_CHECKNODE | ((((flags >> MAP_HUGE_SHIFT) & + *vm_flags |= VM_CHECKNODE | ((((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK) << CHECKNODE_BITS) & CHECKNODE_MASK); } #else #define CHECKNODE_BITS (0) -static inline void set_vm_checknode(vm_flags_t vm_flags, unsigned long flags) {} +static inline void set_vm_checknode(vm_flags_t *vm_flags, unsigned long flags) +{} #endif /* diff --git a/mm/mmap.c b/mm/mmap.c index 9dfef56dd0e8..e0399b087430 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1579,7 +1579,7 @@ unsigned long __do_mmap(struct mm_struct *mm, struct file *file, * hugetlbfs file mmap will use it to check node */ if (flags & MAP_CHECKNODE) - set_vm_checknode(vm_flags, flags); + set_vm_checknode(&vm_flags, flags); addr = __mmap_region(mm, file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && -- 2.25.1

1 4

openEuler kernel sig meeting
by openEuler conference 11 Jan '21

11 Jan '21

2 1

[PATCH openEuler-1.0-LTS] HID: core: Sanitize event code and type when mapping input
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Marc Zyngier <maz(a)kernel.org> stable inclusion from linux-4.19.144 commit a47b8511d90528c77346597e2012100dfc28cd8c CVE: CVE-2020-0465 -------------------------------- commit 35556bed836f8dc07ac55f69c8d17dce3e7f0e25 upstream. When calling into hid_map_usage(), the passed event code is blindly stored as is, even if it doesn't fit in the associated bitmap. This event code can come from a variety of sources, including devices masquerading as input devices, only a bit more "programmable". Instead of taking the event code at face value, check that it actually fits the corresponding bitmap, and if it doesn't: - spit out a warning so that we know which device is acting up - NULLify the bitmap pointer so that we catch unexpected uses Code paths that can make use of untrusted inputs can now check that the mapping was indeed correct and bail out if not. Cc: stable(a)vger.kernel.org Signed-off-by: Marc Zyngier <maz(a)kernel.org> Signed-off-by: Benjamin Tissoires <benjamin.tissoires(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/hid/hid-input.c | 4 ++++ drivers/hid/hid-multitouch.c | 2 ++ include/linux/hid.h | 42 +++++++++++++++++++++++++----------- 3 files changed, 35 insertions(+), 13 deletions(-) diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index dbb0cbe65fc9..0062b37ef98f 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1125,6 +1125,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel } mapped: + /* Mapping failed, bail out */ + if (!bit) + return; + if (device->driver->input_mapped && device->driver->input_mapped(device, hidinput, field, usage, &bit, &max) < 0) { diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index f9167d0e095c..dfb2548e0052 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -841,6 +841,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, code = BTN_0 + ((usage->hid - 1) & HID_USAGE); hid_map_usage(hi, usage, bit, max, EV_KEY, code); + if (!*bit) + return -1; input_set_capability(hi->input, EV_KEY, code); return 1; diff --git a/include/linux/hid.h b/include/linux/hid.h index 8b3e5e8a72fb..bbbe6c0e0e26 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -956,34 +956,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type + * + * The value pointed to by @bit will be set to NULL if either @type is + * an unhandled event type, or if @c is out of range for @type. This + * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, - __u8 type, __u16 c) + __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; - - usage->type = type; - usage->code = c; + unsigned long *bmap = NULL; + unsigned int limit = 0; switch (type) { case EV_ABS: - *bit = input->absbit; - *max = ABS_MAX; + bmap = input->absbit; + limit = ABS_MAX; break; case EV_REL: - *bit = input->relbit; - *max = REL_MAX; + bmap = input->relbit; + limit = REL_MAX; break; case EV_KEY: - *bit = input->keybit; - *max = KEY_MAX; + bmap = input->keybit; + limit = KEY_MAX; break; case EV_LED: - *bit = input->ledbit; - *max = LED_MAX; + bmap = input->ledbit; + limit = LED_MAX; break; } + + if (unlikely(c > limit || !bmap)) { + pr_warn_ratelimited("%s: Invalid code %d type %d\n", + input->name, c, type); + *bit = NULL; + return; + } + + usage->type = type; + usage->code = c; + *max = limit; + *bit = bmap; } /** @@ -997,7 +1012,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); - clear_bit(c, *bit); + if (*bit) + clear_bit(usage->code, *bit); } /** -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] cfg80211: add missing policy for NL80211_ATTR_STATUS_CODE
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Sergey Matyukevich <sergey.matyukevich.os(a)quantenna.com> stable inclusion from linux-4.19.108 commit 0fb31bd53a5e27394916758173eb748c5e0dbd47 CVE: CVE-2020-27068 -------------------------------- [ Upstream commit ea75080110a4c1fa011b0a73cb8f42227143ee3e ] The nl80211_policy is missing for NL80211_ATTR_STATUS_CODE attribute. As a result, for strictly validated commands, it's assumed to not be supported. Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os(a)quantenna.com> Link: https://lore.kernel.org/r/20200213131608.10541-2-sergey.matyukevich.os@quan… Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- net/wireless/nl80211.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5075fd293feb..de9580f13914 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -323,6 +323,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG }, [NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG }, [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] speakup: Reject setting the speakup line discipline outside of speakup
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Samuel Thibault <samuel.thibault(a)ens-lyon.org> mainline inclusion from mainline-v5.10-rc7 commit f0992098cadb4c9c6a00703b66cafe604e178fea category: bugfix bugzilla: NA CVE: CVE-2020-27830 -------------------------------- Speakup exposing a line discipline allows userland to try to use it, while it is deemed to be useless, and thus uselessly exposes potential bugs. One of them is simply that in such a case if the line sends data, spk_ttyio_receive_buf2 is called and crashes since spk_ttyio_synth is NULL. This change restricts the use of the speakup line discipline to speakup drivers, thus avoiding such kind of issues altogether. Cc: stable(a)vger.kernel.org Reported-by: Shisong Qin <qinshisong1205(a)gmail.com> Signed-off-by: Samuel Thibault <samuel.thibault(a)ens-lyon.org> Tested-by: Shisong Qin <qinshisong1205(a)gmail.com> Link: https://lore.kernel.org/r/20201129193523.hm3f6n5xrn6fiyyc@function Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/accessibility/speakup/spk_ttyio.c [yyl: spk_ttyio.c is in drivers/staging/speakup/ in kernel-4.19] Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/staging/speakup/spk_ttyio.c | 36 ++++++++++++++++++----------- 1 file changed, 23 insertions(+), 13 deletions(-) diff --git a/drivers/staging/speakup/spk_ttyio.c b/drivers/staging/speakup/spk_ttyio.c index 6c754ddf1257..8bc7db55daeb 100644 --- a/drivers/staging/speakup/spk_ttyio.c +++ b/drivers/staging/speakup/spk_ttyio.c @@ -47,27 +47,21 @@ static int spk_ttyio_ldisc_open(struct tty_struct *tty) { struct spk_ldisc_data *ldisc_data; + if (tty != speakup_tty) + /* Somebody tried to use this line discipline outside speakup */ + return -ENODEV; + if (tty->ops->write == NULL) return -EOPNOTSUPP; - mutex_lock(&speakup_tty_mutex); - if (speakup_tty) { - mutex_unlock(&speakup_tty_mutex); - return -EBUSY; - } - speakup_tty = tty; ldisc_data = kmalloc(sizeof(struct spk_ldisc_data), GFP_KERNEL); - if (!ldisc_data) { - speakup_tty = NULL; - mutex_unlock(&speakup_tty_mutex); + if (!ldisc_data) return -ENOMEM; - } sema_init(&ldisc_data->sem, 0); ldisc_data->buf_free = true; - speakup_tty->disc_data = ldisc_data; - mutex_unlock(&speakup_tty_mutex); + tty->disc_data = ldisc_data; return 0; } @@ -187,9 +181,25 @@ static int spk_ttyio_initialise_ldisc(struct spk_synth *synth) tty_unlock(tty); + mutex_lock(&speakup_tty_mutex); + speakup_tty = tty; ret = tty_set_ldisc(tty, N_SPEAKUP); if (ret) - pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + speakup_tty = NULL; + mutex_unlock(&speakup_tty_mutex); + + if (!ret) + /* Success */ + return 0; + + pr_err("speakup: Failed to set N_SPEAKUP on tty\n"); + + tty_lock(tty); + if (tty->ops->close) + tty->ops->close(tty, NULL); + tty_unlock(tty); + + tty_kclose(tty); return ret; } -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] tty: Fix ->pgrp locking in tiocspgrp()
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Jann Horn <jannh(a)google.com> mainline inclusion from mainline-v5.10-rc7 commit 54ffccbf053b5b6ca4f6e45094b942fab92a25fc category: bugfix bugzilla: NA CVE: CVE-2020-29661 -------------------------------- tiocspgrp() takes two tty_struct pointers: One to the tty that userspace passed to ioctl() (`tty`) and one to the TTY being changed (`real_tty`). These pointers are different when ioctl() is called with a master fd. To properly lock real_tty->pgrp, we must take real_tty->ctrl_lock. This bug makes it possible for racing ioctl(TIOCSPGRP, ...) calls on both sides of a PTY pair to corrupt the refcount of `struct pid`, leading to use-after-free errors. Fixes: 47f86834bbd4 ("redo locking of tty->pgrp") CC: stable(a)kernel.org Signed-off-by: Jann Horn <jannh(a)google.com> Reviewed-by: Jiri Slaby <jirislaby(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/tty/tty_jobctrl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c index c4ecd66fafef..a42dec3c95d0 100644 --- a/drivers/tty/tty_jobctrl.c +++ b/drivers/tty/tty_jobctrl.c @@ -494,10 +494,10 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t if (session_of_pgrp(pgrp) != task_session(current)) goto out_unlock; retval = 0; - spin_lock_irq(&tty->ctrl_lock); + spin_lock_irq(&real_tty->ctrl_lock); put_pid(real_tty->pgrp); real_tty->pgrp = get_pid(pgrp); - spin_unlock_irq(&tty->ctrl_lock); + spin_unlock_irq(&real_tty->ctrl_lock); out_unlock: rcu_read_unlock(); return retval; -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] ALSA: rawmidi: Fix racy buffer resize under concurrent accesses
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from linux-4.19.124 commit a507658fdb2ad8ca282b0eb42f2a40b805deb1e6 CVE: CVE-2020-27786 -------------------------------- commit c1f6e3c818dd734c30f6a7eeebf232ba2cf3181d upstream. The rawmidi core allows user to resize the runtime buffer via ioctl, and this may lead to UAF when performed during concurrent reads or writes: the read/write functions unlock the runtime lock temporarily during copying form/to user-space, and that's the race window. This patch fixes the hole by introducing a reference counter for the runtime buffer read/write access and returns -EBUSY error when the resize is performed concurrently against read/write. Note that the ref count field is a simple integer instead of refcount_t here, since the all contexts accessing the buffer is basically protected with a spinlock, hence we need no expensive atomic ops. Also, note that this busy check is needed only against read / write functions, and not in receive/transmit callbacks; the race can happen only at the spinlock hole mentioned in the above, while the whole function is protected for receive / transmit callbacks. Reported-by: butt3rflyh4ck <butterflyhuangxx(a)gmail.com> Cc: <stable(a)vger.kernel.org> Link: https://lore.kernel.org/r/CAFcO6XMWpUVK_yzzCpp8_XP7+=oUpQvuBeCbMffEDkpe8jWr… Link: https://lore.kernel.org/r/s5heerw3r5z.wl-tiwai@suse.de Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/sound/rawmidi.h | 1 + sound/core/rawmidi.c | 31 +++++++++++++++++++++++++++---- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 6665cb29e1a2..7a908a81cef4 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -76,6 +76,7 @@ struct snd_rawmidi_runtime { size_t avail_min; /* min avail for wakeup */ size_t avail; /* max used buffer for wakeup */ size_t xruns; /* over/underruns counter */ + int buffer_ref; /* buffer reference count */ /* misc */ spinlock_t lock; wait_queue_head_t sleep; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index a52d6d16efc4..9b26973fe697 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -112,6 +112,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work) runtime->event(runtime->substream); } +/* buffer refcount management: call with runtime->lock held */ +static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref++; +} + +static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref--; +} + static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime; @@ -661,6 +672,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); + if (runtime->buffer_ref) { + spin_unlock_irq(&runtime->lock); + kvfree(newbuf); + return -EBUSY; + } oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; @@ -960,8 +976,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; unsigned long appl_ptr; + int err = 0; spin_lock_irqsave(&runtime->lock, flags); + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -980,16 +998,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + appl_ptr, count1)) { - return result > 0 ? result : -EFAULT; - } + runtime->buffer + appl_ptr, count1)) + err = -EFAULT; spin_lock_irqsave(&runtime->lock, flags); + if (err) + goto out; } result += count1; count -= count1; } + out: + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); - return result; + return result > 0 ? result : err; } long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream, @@ -1261,6 +1282,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, return -EAGAIN; } } + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail > 0) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1292,6 +1314,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } __end: count1 = runtime->avail < runtime->buffer_size; + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); if (count1) snd_rawmidi_output_trigger(substream, 1); -- 2.25.1

1 0

[PATCH kernel-4.19 1/5] Kconfig: disable KTASK by default
by Yang Yingliang 08 Jan '21

08 Jan '21

hulk inclusion category: bugfix bugzilla: 46923 CVE: NA ---------------------------------------------- Enable KTASK in vfio, if the BAR size of some straight through equipment device is too large, it will cause guest crash on booting. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index 6880b55901bb..71b09d998413 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -352,7 +352,7 @@ config AUDIT_TREE config KTASK bool "Multithread CPU-intensive kernel work" depends on SMP - default y + default n help Parallelize CPU-intensive kernel work. This feature is designed for big machines that can take advantage of their extra CPUs to speed up -- 2.25.1

1 4

[PATCH kernel-4.19 01/33] irqchip/gic-v3: Fix compiling error on ARM32 with GICv3
by Yang Yingliang 08 Jan '21

08 Jan '21

From: Wei Li <liwei391(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------------------------- /builds/1mHAjaH6WFVPAq6OVOJsJsJKHA2/drivers/irqchip/irq-gic-v3.c: In function 'gic_cpu_init': /builds/1mHAjaH6WFVPAq6OVOJsJsJKHA2/drivers/irqchip/irq-gic-v3.c:888:3: error: implicit declaration of function 'ipi_set_nmi_prio' [-Werror=implicit-function-declaration] 888 | ipi_set_nmi_prio(rbase, GICD_INT_NMI_PRI); | ^~~~~~~~~~~~~~~~ On ARM32, ipi_set_nmi_prio() is not implmented as CONFIG_ARM64_PSEUDO_NMI is not supported. Skip setting the NMI priority of SGIs when initializing. Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/irqchip/irq-gic-v3.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6bb787ba1764..14e9c1a5627b 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -884,8 +884,10 @@ static void gic_cpu_init(void) gic_cpu_config(rbase, gic_redist_wait_for_rwp); +#ifdef CONFIG_ARM64_PSEUDO_NMI if (gic_supports_nmi()) ipi_set_nmi_prio(rbase, GICD_INT_NMI_PRI); +#endif /* initialise system registers */ gic_cpu_sys_reg_init(); -- 2.25.1

1 32

[PATCH kernel-4.19 00/30] backport stable-4.19.165
by Yang Yingliang 08 Jan '21

08 Jan '21

Anant Thazhemadam (2): Bluetooth: hci_h5: close serdev device and free hu in h5_close misc: vmw_vmci: fix kernel info-leak by initializing dbells in vmci_ctx_get_chkpt_doorbells() Boqun Feng (1): fcntl: Fix potential deadlock in send_sig{io, urg}() Christophe Leroy (1): powerpc/bitops: Fix possible undefined behaviour with fls() and fls64() Damien Le Moal (1): null_blk: Fix zone size initialization Dinghao Liu (1): rtc: sun6i: Fix memleak in sun6i_rtc_clk_init Eric Auger (1): vfio/pci: Move dummy_resources_list init in vfio_pci_probe() Eric Biggers (4): fscrypt: add fscrypt_is_nokey_name() ext4: prevent creating duplicate encrypted filenames f2fs: prevent creating duplicate encrypted filenames ubifs: prevent creating duplicate encrypted filenames Greg Kroah-Hartman (1): Linux 4.19.165 Hyeongseok Kim (1): dm verity: skip verity work if I/O error when system is shutting down Jan Kara (2): ext4: don't remount read-only with errors=continue on reboot quota: Don't overflow quota file offsets Jessica Yu (1): module: delay kobject uevent until after module init call Johan Hovold (1): of: fix linker-section match-table corruption Kevin Vigor (1): md/raid10: initialize r10_bio->read_slot before use. Mauro Carvalho Chehab (1): media: gp8psk: initialize stats at power control logic Miroslav Benes (1): module: set MODULE_STATE_GOING state when a module fails to load Paolo Bonzini (2): KVM: SVM: relax conditions for allowing MSR_IA32_SPEC_CTRL accesses KVM: x86: reinstate vendor-agnostic check on SPEC_CTRL cpuid bits Petr Vorel (1): uapi: move constants from <linux/kernel.h> to <linux/const.h> Qinglang Miao (1): powerpc: sysdev: add missing iounmap() on error in mpic_msgr_probe() Rustam Kovhaev (1): reiserfs: add check for an invalid ih_entry_count Souptick Joarder (1): xen/gntdev.c: Mark pages as dirty Takashi Iwai (3): ALSA: seq: Use bool for snd_seq_queue internal flags ALSA: rawmidi: Access runtime->avail always in spinlock ALSA: pcm: Clear the full allocated memory at hw_params Trond Myklebust (1): NFSv4: Fix a pNFS layout related use-after-free race when freeing the inode Makefile | 2 +- arch/powerpc/include/asm/bitops.h | 23 +++++++++++- arch/powerpc/sysdev/mpic_msgr.c | 2 +- arch/x86/kvm/cpuid.h | 14 +++++++ arch/x86/kvm/svm.c | 9 ++--- arch/x86/kvm/vmx.c | 6 +-- drivers/block/null_blk_zoned.c | 20 ++++++---- drivers/bluetooth/hci_h5.c | 8 +++- drivers/md/dm-verity-target.c | 12 +++++- drivers/md/raid10.c | 3 +- drivers/media/usb/dvb-usb/gp8psk.c | 2 +- drivers/misc/vmw_vmci/vmci_context.c | 2 +- drivers/rtc/rtc-sun6i.c | 8 ++-- drivers/vfio/pci/vfio_pci.c | 3 +- drivers/xen/gntdev.c | 17 ++++++--- fs/crypto/hooks.c | 10 ++--- fs/ext4/namei.c | 3 ++ fs/ext4/super.c | 15 +++----- fs/f2fs/f2fs.h | 2 + fs/fcntl.c | 10 +++-- fs/nfs/nfs4super.c | 2 +- fs/nfs/pnfs.c | 33 ++++++++++++++++- fs/nfs/pnfs.h | 5 +++ fs/quota/quota_tree.c | 8 ++-- fs/reiserfs/stree.c | 6 +++ fs/ubifs/dir.c | 17 +++++++-- include/linux/fscrypt_notsupp.h | 5 +++ include/linux/fscrypt_supp.h | 29 +++++++++++++++ include/linux/of.h | 1 + include/uapi/linux/const.h | 5 +++ include/uapi/linux/ethtool.h | 2 +- include/uapi/linux/kernel.h | 9 +---- include/uapi/linux/lightnvm.h | 2 +- include/uapi/linux/mroute6.h | 2 +- include/uapi/linux/netfilter/x_tables.h | 2 +- include/uapi/linux/netlink.h | 2 +- include/uapi/linux/sysctl.h | 2 +- kernel/module.c | 6 ++- sound/core/pcm_native.c | 9 ++++- sound/core/rawmidi.c | 49 ++++++++++++++++++------- sound/core/seq/seq_queue.h | 8 ++-- 41 files changed, 274 insertions(+), 101 deletions(-) -- 2.25.1

1 30

[PATCH] hifc: remove unnecessary __init specifier
by Zhengyuan Liu 04 Jan '21

04 Jan '21

hulk inclusion category: bugfix bugzilla: NA CVE: NA The specifier of __init added to hrd_flashProbe() isn't appropriate. It can cause following building warning: WARNING: drivers/mtd/hisilicon/sfc/hi-sfc.o(.text.unlikely+0x38c): Section mismatch in reference from the \ function flash_map_init() to the function .init.text:hrd_flashProbe() The function flash_map_init() references the function __init hrd_flashProbe(). This is often because flash_map_init lacks a __init annotation or the annotation of hrd_flashProbe is wrong. Fixes: 25d711e7ffb7 ("drivers: add sfc driver to hulk") Signed-off-by: Zhengyuan Liu <liuzhengyuan(a)tj.kylinos.cn> --- drivers/mtd/hisilicon/sfc/hrd_sfc_driver.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/mtd/hisilicon/sfc/hrd_sfc_driver.c b/drivers/mtd/hisilicon/sfc/hrd_sfc_driver.c index 23254e325a85..69fb1b306f0d 100644 --- a/drivers/mtd/hisilicon/sfc/hrd_sfc_driver.c +++ b/drivers/mtd/hisilicon/sfc/hrd_sfc_driver.c @@ -87,8 +87,8 @@ static int _hrd_flashProbe(const char **mtdDrv, struct map_info *map, return HRD_ERR; } -static int __init hrd_flashProbe(const char **mtdDrv, struct map_info *map, - struct resource *sfc_regres, struct mtd_info **mtd) +static int hrd_flashProbe(const char **mtdDrv, struct map_info *map, + struct resource *sfc_regres, struct mtd_info **mtd) { int ret; -- 2.20.1

3 2

[PATCH kernel-4.19 v2] mmap: fix a compiling error for 'MAP_PA32BIT'
by Bixuan Cui 04 Jan '21

04 Jan '21

From: Zhengyuan Liu <liuzhengyuan(a)tj.kylinos.cn> hulk inclusion category: bugfix bugzilla: NA CVE: NA MAP_PA32BIT was defined in uapi/asm-generic/mman.h, that was not automatically included by mm/mmap.c when building on platforms such as mips, and result in following compiling error: mm/mmap.c: In function ‘do_mmap’: mm/mmap.c:1450:14: error: ‘MAP_PA32BIT’ undeclared (first use in this function); did you mean ‘MAP_32BIT’? if (flags & MAP_PA32BIT) ^~~~~~~~~~~ MAP_32BIT mm/mmap.c:1450:14: note: each undeclared identifier is reported only once for each function it appears in make[1]: *** [scripts/Makefile.build:303: mm/mmap.o] Error 1 Fixes: e138253f2b82 ("svm: add support for allocing memory which is within 4G physical address in svm_mmap") Signed-off-by: Zhengyuan Liu <liuzhengyuan(a)tj.kylinos.cn> Signed-off-by: Bixuan Cui <cuibixuan(a)huawei.com> --- arch/alpha/include/uapi/asm/mman.h | 1 + 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 + 6 files changed, 6 insertions(+) diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index f9d4e6b6d4bd..b3acfc00c8ec 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -33,6 +33,7 @@ #define MAP_STACK 0x80000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x100000 /* create a huge page mapping */ #define MAP_FIXED_NOREPLACE 0x200000/* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ #define MS_ASYNC 1 /* sync memory asynchronously */ #define MS_SYNC 2 /* synchronous memory sync */ diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 3035ca499cd8..72a00c746e78 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -51,6 +51,7 @@ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ /* * Flags for msync diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 870fbf8c7088..9e989d649e85 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -27,6 +27,7 @@ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ #define MS_SYNC 1 /* synchronous memory sync */ #define MS_ASYNC 2 /* sync memory asynchronously */ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 65065ce32814..95f884ada96f 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -29,6 +29,7 @@ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ /* Override any generic PKEY permission defines */ #define PKEY_DISABLE_EXECUTE 0x4 diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h index f6f99ec65bb3..0d1881b8f30d 100644 --- a/arch/sparc/include/uapi/asm/mman.h +++ b/arch/sparc/include/uapi/asm/mman.h @@ -26,6 +26,7 @@ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ #define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x40000 /* create a huge page mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ #endif /* _UAPI__SPARC_MMAN_H__ */ diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 58f29a9d895d..f584a590bb00 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -58,6 +58,7 @@ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_PA32BIT 0x400000 /* physical address is within 4G */ #ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED # define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be * uninitialized */ -- 2.17.1

3 2

[PATCH kernel-4.19 01/12] memcg/ascend: Check sysctl oom config for memcg oom
by Yang Yingliang 04 Jan '21

04 Jan '21

From: Zhou Guanghui <zhouguanghui1(a)huawei.com> ascend inclusion category: feature bugzilla: NA CVE: NA -------------------------------------------------- If memcg oom_kill_disable is false(enable oom killer), and sysctl enable_oom_killer is also false(disable oom killer), the memory allocated for this memcg will exceed the limit. This means that the memcg cannot limit the memory usage. Therefore, ensure that sysctl enable_oom_killer is not false. Otherwise, wait for memory resources. Signed-off-by: Zhou Guanghui <zhouguanghui1(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/memcontrol.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6ad8fafcdf87..aa8f6f75eea1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1942,7 +1942,11 @@ bool mem_cgroup_oom_synchronize(bool handle) if (locked) mem_cgroup_oom_notify(memcg); - if (locked && !memcg->oom_kill_disable) { + if (locked && +#ifdef CONFIG_ASCEND_OOM + sysctl_enable_oom_killer != 0 && +#endif + !memcg->oom_kill_disable) { mem_cgroup_unmark_under_oom(memcg); finish_wait(&memcg_oom_waitq, &owait.wait); mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask, -- 2.25.1

1 11

[PATCH kernel-4.19 00/59] MPAM series
by Yang Yingliang 04 Jan '21

04 Jan '21

本次MPAM特性合入59个补丁，主要包括： 1）MPAM 对外sysfs功能增强； 2）适配后续社区版本，适配兼容MPAM协议； 3）代码框架整体重构，拓展对SMMU io的支持； 4）支持鲲鹏930全套MPAM能力； James Morse (10): arm64/mpam: Add mpam driver discovery phase and kbuild boiler plate cacheinfo: Provide a helper to find a cacheinfo leaf arm64/mpam: Probe supported partid/pmg ranges from devices arm64/mpam: Supplement MPAM MSC register layout definitions arm64/mpam: Probe the features resctrl supports arm64/mpam: Reset controls when CPUs come online arm64/mpam: Summarize feature support during mpam_enable() arm64/mpam: resctrl: Re-synchronise resctrl's view of online CPUs drivers: base: cacheinfo: Add helper to search cacheinfo by of_node arm64/mpam: Enabling registering and logging error interrupts Wang ShaoBo (49): arm64/mpam: Preparing for MPAM refactoring arm64/mpam: Add helper for getting mpam sysprops arm64/mpam: Allocate mpam component configuration arrays arm64/mpam: Pick MPAM resources and events for resctrl_res exported arm64/mpam: Init resctrl resources' info from resctrl_res selected arm64/mpam: resctrl: Handle cpuhp and resctrl_dom allocation arm64/mpam: Implement helpers for handling configuration and monitoring arm64/mpam: Migrate old MSCs' discovery process to new branch arm64/mpam: Add helper for getting MSCs' configuration arm64/mpam: Probe partid,pmg and feature capabilities' ranges from classes arm64/mpam: resctrl: Rebuild configuration and monitoring pipeline arm64/mpam: resctrl: Append schemata CDP definitions arm64/mpam: resctrl: Supplement cdpl2,cdpl3 for mount options arm64/mpam: resctrl: Add helpers for init and destroy schemata list arm64/mpam: resctrl: Use resctrl_group_init_alloc() to init schema list arm64/mpam: resctrl: Write and read schemata by schema_list arm64/mpam: Support cdp in mpam_sched_in() arm64/mpam: resctrl: Update resources reset process arm64/mpam: resctrl: Update closid alloc and free process with bitmap arm64/mpam: resctrl: Move ctrlmon sysfile write/read function to mpam_ctrlmon.c arm64/mpam: Support cdp on allocating monitors arm64/mpam: resctrl: Support cdp on monitoring data arm64/mpam: Clean up header files and rearrange declarations arm64/mpam: resctrl: Remove ctrlmon sysfile arm64/mpam: resctrl: Remove unnecessary CONFIG_ARM64 arm64/mpam: Implement intpartid narrowing process arm64/mpam: Using software-defined id for rdtgroup instead of 32-bit integer arm64/mpam: resctrl: collect child mon group's monitor data arm64/mpam: resctrl: Support cpus' monitoring for mon group arm64/mpam: resctrl: Support priority and hardlimit(Memory bandwidth) configuration arm64/mpam: Store intpri and dspri for mpam device reset arm64/mpam: Squash default priority from mpam device to class arm64/mpam: Restore extend ctrls' max width for checking schemata input arm64/mpam: Re-plan intpartid narrowing process arm64/mpam: Add hook-events id for ctrl features arm64/mpam: Integrate monitor data for Memory Bandwidth if cdp enabled arm64/mpam: Fix MPAM_ESR intPARTID_range error arm64/mpam: Separate internal and downstream priority event arm64/mpam: Remap reqpartid,pmg to rmid and intpartid to closid arm64/mpam: Add wait queue for monitor alloc and free arm64/mpam: Add resctrl_ctrl_feature structure to manage ctrl features arm64/mpam: resctrl: Export resource's properties to info directory arm64/mpam: Split header files into suitable location arm64/mpam: resctrl: Add rmid file in resctrl sysfs arm64/mpam: Filter schema control type with ctrl features arm64/mpam: Simplify mpamid cdp mapping process arm64/mpam: Set per-cpu's closid to none zero for cdp ACPI/MPAM: Use acpi_map_pxm_to_node() to get node id for memory node arm64/mpam: Supplement additional useful ctrl features for mount options arch/arm64/include/asm/mpam.h | 324 +--- arch/arm64/include/asm/mpam_resource.h | 129 -- arch/arm64/include/asm/mpam_sched.h | 8 - arch/arm64/include/asm/resctrl.h | 489 +++++- arch/arm64/kernel/Makefile | 2 +- arch/arm64/kernel/mpam.c | 1494 ---------------- arch/arm64/kernel/mpam/Makefile | 3 + arch/arm64/kernel/mpam/mpam_ctrlmon.c | 957 ++++++++++ arch/arm64/kernel/mpam/mpam_device.c | 1706 ++++++++++++++++++ arch/arm64/kernel/mpam/mpam_device.h | 140 ++ arch/arm64/kernel/mpam/mpam_internal.h | 345 ++++ arch/arm64/kernel/mpam/mpam_mon.c | 331 ++++ arch/arm64/kernel/mpam/mpam_resctrl.c | 2221 ++++++++++++++++++++++++ arch/arm64/kernel/mpam/mpam_resource.h | 228 +++ arch/arm64/kernel/mpam/mpam_setup.c | 597 +++++++ arch/arm64/kernel/mpam_ctrlmon.c | 619 ------- arch/arm64/kernel/mpam_mon.c | 121 -- drivers/acpi/arm64/mpam.c | 87 +- drivers/base/cacheinfo.c | 38 + fs/resctrlfs.c | 410 +++-- include/linux/arm_mpam.h | 118 ++ include/linux/cacheinfo.h | 36 + include/linux/resctrlfs.h | 30 - 23 files changed, 7473 insertions(+), 2960 deletions(-) delete mode 100644 arch/arm64/include/asm/mpam_resource.h delete mode 100644 arch/arm64/kernel/mpam.c create mode 100644 arch/arm64/kernel/mpam/Makefile create mode 100644 arch/arm64/kernel/mpam/mpam_ctrlmon.c create mode 100644 arch/arm64/kernel/mpam/mpam_device.c create mode 100644 arch/arm64/kernel/mpam/mpam_device.h create mode 100644 arch/arm64/kernel/mpam/mpam_internal.h create mode 100644 arch/arm64/kernel/mpam/mpam_mon.c create mode 100644 arch/arm64/kernel/mpam/mpam_resctrl.c create mode 100644 arch/arm64/kernel/mpam/mpam_resource.h create mode 100644 arch/arm64/kernel/mpam/mpam_setup.c delete mode 100644 arch/arm64/kernel/mpam_ctrlmon.c delete mode 100644 arch/arm64/kernel/mpam_mon.c create mode 100644 include/linux/arm_mpam.h -- 2.25.1

1 59

[PATCH 01/10] vfio: allow external user to get vfio group from device
by Yang Yingliang 04 Jan '21

04 Jan '21

From: Yan Zhao <yan.y.zhao(a)intel.com> mainline inclusion from mainline-v5.6-rc7 commit c0560f51cf77472f4ed113539b0a02ca6cda7961 category: Common features bugzilla: 46841 CVE: NA ------------------------------------------------- external user calls vfio_group_get_external_user_from_dev() with a device pointer to get the VFIO group associated with this device. The VFIO group is checked to be vialbe and have IOMMU set. Then container user counter is increased and VFIO group reference is hold to prevent the VFIO group from disposal before external user exits. when the external user finishes using of the VFIO group, it calls vfio_group_put_external_user() to dereference the VFIO group and the container user counter. Suggested-by: Alex Williamson <alex.williamson(a)redhat.com> Signed-off-by: Yan Zhao <yan.y.zhao(a)intel.com> Signed-off-by: Alex Williamson <alex.williamson(a)redhat.com> Signed-off-by: Xiaoyang Xu <xuxiaoyang2(a)huawei.com> Reviewed-by: Xiangyou Xie <xiexiangyou(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/vfio/vfio.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/vfio.h | 2 ++ 2 files changed, 40 insertions(+) diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 7a386fb30bf1..34a293318a39 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1759,6 +1759,44 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) } EXPORT_SYMBOL_GPL(vfio_group_get_external_user); +/** + * External user API, exported by symbols to be linked dynamically. + * The external user passes in a device pointer + * to verify that: + * - A VFIO group is assiciated with the device; + * - IOMMU is set for the group. + * If both checks passed, vfio_group_get_external_user_from_dev() + * increments the container user counter to prevent the VFIO group + * from disposal before external user exits and returns the pointer + * to the VFIO group. + * + * When the external user finishes using the VFIO group, it calls + * vfio_group_put_external_user() to release the VFIO group and + * decrement the container user counter. + * + * @dev [in] : device + * Return error PTR or pointer to VFIO group. + */ + +struct vfio_group *vfio_group_get_external_user_from_dev(struct device *dev) +{ + struct vfio_group *group; + int ret; + + group = vfio_group_get_from_dev(dev); + if (!group) + return ERR_PTR(-ENODEV); + + ret = vfio_group_add_container_user(group); + if (ret) { + vfio_group_put(group); + return ERR_PTR(ret); + } + + return group; +} +EXPORT_SYMBOL_GPL(vfio_group_get_external_user_from_dev); + void vfio_group_put_external_user(struct vfio_group *group) { vfio_group_try_dissolve_container(group); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 66741ab087c1..a1e8943b7be3 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device + *dev); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); -- 2.25.1

1 9

[PATCH kernel-4.19 000/337] backport stable-4.19.164
by Yang Yingliang 04 Jan '21

04 Jan '21

Alan Stern (1): media: gspca: Fix memory leak in probe Alexander Sverdlin (1): serial: 8250_omap: Avoid FIFO corruption caused by MDR1 access Alexandre Belloni (1): ARM: dts: at91: at91sam9rl: fix ADC triggers Alexey Kardashevskiy (1): serial_core: Check for port state when tty is in error state Amadej Kastelic (1): ALSA: usb-audio: Add VID to support native DSD reproduction on FiiO devices Anant Thazhemadam (1): Bluetooth: hci_h5: fix memory leak in h5_close Andy Lutomirski (1): x86/membarrier: Get rid of a dubious optimization Andy Shevchenko (2): pinctrl: merrifield: Set default bias in case no particular value given pinctrl: baytrail: Avoid clearing debounce value when turning it off Anmol Karn (1): Bluetooth: Fix null pointer dereference in hci_event_packet() Ansuel Smith (1): PCI: qcom: Add missing reset for ipq806x Anton Ivanov (3): um: Monitor error events in IRQ controller um: tty: Fix handling of close in tty lines um: chan_xterm: Fix fd leak Antti Palosaari (1): media: msi2500: assign SPI bus number dynamically Ard Biesheuvel (2): ARM: p2v: fix handling of LPAE translation in BE mode crypto: ecdh - avoid unaligned accesses in ecdh_set_secret() Arnd Bergmann (7): kbuild: avoid static_assert for genksyms scsi: megaraid_sas: Check user-provided offsets RDMa/mthca: Work around -Wenum-conversion warning seq_buf: Avoid type mismatch for seq_buf_init watchdog: coh901327: add COMMON_CLK dependency Input: cyapa_gen6 - fix out-of-bounds stack access platform/x86: mlx-platform: remove an unused variable Artem Lapkin (1): arm64: dts: meson: fix spi-max-frequency on Khadas VIM2 Arvind Sankar (3): x86/mm/mem_encrypt: Fix definition of PMD_FLAGS_DEC_WP compiler.h: fix barrier_data() on clang x86/mm/ident_map: Check for errors from ident_pud_init() Athira Rajeev (1): powerpc/perf: Exclude kernel samples while counting events in user space. Baruch Siach (1): gpio: mvebu: fix potential user-after-free on probe Bean Huo (1): mmc: block: Fixup condition for CMD13 polling for RPMB requests Bharat Gooty (1): PCI: iproc: Fix out-of-bound array accesses Bjorn Andersson (1): slimbus: qcom-ngd-ctrl: Avoid sending power requests without QMI Bjorn Helgaas (1): PCI: Bounds-check command-line resource alignment requests Björn Töpel (1): ixgbe: avoid premature Rx buffer reuse Bob Pearson (1): RDMA/rxe: Compute PSN windows correctly Bongsu Jeon (1): nfc: s3fwrn5: Release the nfc firmware Borislav Petkov (1): EDAC/amd64: Fix PCI component registration Bui Quang Minh (1): USB: dummy-hcd: Fix uninitialized array use in init() Calum Mackay (1): lockd: don't use interval-based rebinding over TCP Can Guo (1): scsi: ufs: Make sure clk scaling happens only when HBA is runtime ACTIVE Carlos Garnacho (1): platform/x86: intel-vbtn: Allow switch events on Acer Switch Alpha 12 Cezary Rojewski (1): ASoC: pcm: DRAIN support reactivation Chen-Yu Tsai (2): arm64: dts: rockchip: Set dr_mode to "host" for OTG on rk3328-roc-cc arm64: dts: rockchip: Fix UART pull-ups on rk3328 Cheng Lin (1): nfs_common: need lock during iterate through the list Chris Chiu (4): Input: i8042 - add Acer laptops to the i8042 reset list ALSA: hda/realtek - Enable headset mic of ASUS X430UN with ALC256 ALSA: hda/realtek - Enable headset mic of ASUS Q524UQK with ALC255 ALSA: hda/realtek: Apply jack fixup for Quanta NL3 Chris Packham (1): ARM: dts: Remove non-existent i2c1 from 98dx3236 Christophe JAILLET (5): ath10k: Fix an error handling path ath10k: Release some resources in an error handling path net: bcmgenet: Fix a resource leak in an error handling path in the probe functin net: allwinner: Fix some resources leak in the error handling path of the probe and in the remove function clk: s2mps11: Fix a resource leak in error handling paths in the probe function Christophe Leroy (4): crypto: talitos - Endianess in current_desc_hdr() crypto: talitos - Fix return type of current_desc_hdr() powerpc/feature: Fix CPU_FTRS_ALWAYS by removing CPU_FTRS_GENERIC_32 powerpc/xmon: Change printk() to pr_cont() Chuhong Yuan (1): ASoC: jz4740-i2s: add missed checks for clk_get() Chunguang Xu (1): ext4: fix a memory leak of ext4_free_data Chunyan Zhang (1): gpio: eic-sprd: break loop when getting NULL device resource Claudiu Beznea (1): ARM: dts: at91: sama5d2: map securam as device Coiby Xu (1): pinctrl: amd: remove debounce filter setting in IRQ type setting Colin Ian King (3): crypto: inside-secure - Fix sizeof() mismatch media: tm6000: Fix sizeof() mismatches PCI: Fix overflow in command-line resource alignment requests Connor McAdams (1): ALSA: hda/ca0132 - Change Input Source enum strings. Cristian Birsan (2): ARM: dts: at91: sama5d4_xplained: add pincontrol for USB Host ARM: dts: at91: sama5d3_xplained: add pincontrol for USB Host Dae R. Jeong (1): md: fix a warning caused by a race between concurrent md_ioctl()s Dan Carpenter (6): scsi: be2iscsi: Revert "Fix a theoretical leak in beiscsi_create_eqs()" soc: renesas: rmobile-sysc: Fix some leaks in rmobile_init_pm_domains() media: max2175: fix max2175_set_csm_mode() error code media: saa7146: fix array overflow in vidioc_s_audio() ASoC: wm_adsp: remove "ctl" from list on error in wm_adsp_create_control() qlcnic: Fix error code in probe Dan Williams (1): libnvdimm/namespace: Fix reaping of invalidated block-window-namespace labels Daniel Scally (1): Revert "ACPI / resources: Use AE_CTRL_TERMINATE to terminate resources walks" Daniel T. Lee (1): samples: bpf: Fix lwt_len_hist reusing previous BPF map David Hildenbrand (2): powerpc/powernv/memtrace: Don't leak kernel memory to user space powerpc/powernv/memtrace: Fix crashing the kernel when enabling concurrently David Jander (1): Input: ads7846 - fix race that causes missing releases David Woodhouse (1): x86/apic: Fix x2apic enablement without interrupt remapping Deepak R Varma (1): drm/tegra: replace idr_init() by idr_init_base() Dmitry Baryshkov (1): drm/msm/dsi_pll_10nm: restore VCO rate during restore_state Dmitry Osipenko (1): clk: tegra: Fix duplicated SE clock entry Dmitry Torokhov (3): Input: cm109 - do not stomp on control URB Input: ads7846 - fix unaligned access on 7845 Input: cros_ec_keyb - send 'scancodes' in addition to key events Dongdong Wang (1): lwt: Disable BH too in run_lwt_bpf() Douglas Anderson (1): soc: qcom: geni: More properly switch to DMA mode Dwaipayan Ray (1): checkpatch: fix unescaped left brace Eric Biggers (1): crypto: af_alg - avoid undefined behavior accessing salg_name Eric Dumazet (2): mac80211: mesh: fix mesh_pathtbl_init() error path tcp: select sane initial rcvq_space.space for big MSS Evan Green (1): soc: qcom: smp2p: Safely acquire spinlock without IRQs Fabio Estevam (1): usb: chipidea: ci_hdrc_imx: Pass DISABLE_DEVICE_STREAMING flag to imx6ul Fangrui Song (2): x86/lib: Change .weak to SYM_FUNC_START_WEAK for arch/x86/lib/mem*_64.S arm64: Change .weak to SYM_FUNC_START_WEAK_PI for arch/arm64/lib/mem*.S Fugang Duan (2): net: stmmac: free tx skb buffer in stmmac_resume() net: stmmac: delete the eee_ctrl_timer after napi disabled Geert Uytterhoeven (1): clk: renesas: r9a06g032: Drop __packed for portability Greg Kroah-Hartman (1): Linux 4.19.164 Guenter Roeck (1): watchdog: sirfsoc: Add missing dependency on HAS_IOMEM H. Nikolaus Schaller (1): ARM: dts: pandaboard: fix pinmux for gpio user button of Pandaboard ES Hans de Goede (3): platform/x86: thinkpad_acpi: Do not report SW_TABLET_MODE on Yoga 11e platform/x86: thinkpad_acpi: Add BAT1 is primary battery quirk for Thinkpad Yoga 11e 4th gen power: supply: axp288_charger: Fix HP Pavilion x2 10 DMI matching Hao Si (1): soc: fsl: dpio: Get the cpumask through cpumask_of(cpu) Hui Wang (1): ACPI: PNP: compare the string length in the matching_id() Ian Abbott (1): staging: comedi: mf6x4: Fix AI end-of-conversion detection Icenowy Zheng (1): ARM: dts: sun8i: v3s: fix GIC node memory range Jack Pham (1): usb: gadget: f_fs: Re-use SS descriptors for SuperSpeedPlus Jack Xu (1): crypto: qat - fix status check in qat_hal_put_rel_rd_xfer() James Morse (1): x86/resctrl: Remove unused struct mbm_state::chunks_bw James Smart (2): scsi: lpfc: Fix invalid sleeping context in lpfc_sli4_nvmet_alloc() scsi: lpfc: Re-fix use after free in lpfc_rq_buf_free() Jan Kara (2): quota: Sanity-check quota file headers on load ext4: fix deadlock with fs freezing and EA inodes Jason Gunthorpe (1): vfio-pci: Use io_remap_pfn_range() for PCI IO memory Jernej Skrabec (1): clk: sunxi-ng: Make sure divider tables have sentinel Jerome Brunet (1): ASoC: meson: fix COMPILE_TEST error Jing Xiangfeng (3): staging: gasket: interrupt: fix the missed eventfd_ctx_put() in gasket_interrupt.c HSI: omap_ssi: Don't jump to free ID in ssi_add_controller() memstick: r592: Fix error return in r592_probe() Joel Stanley (1): ARM: dts: aspeed: s2600wf: Fix VGA memory region location Johan Hovold (9): USB: serial: option: add interface-number sanity check to flag handling USB: serial: mos7720: fix parallel-port state restore USB: serial: digi_acceleport: fix write-wakeup deadlocks USB: serial: keyspan_pda: fix dropped unthrottle interrupts USB: serial: keyspan_pda: fix write deadlock USB: serial: keyspan_pda: fix stalled writes USB: serial: keyspan_pda: fix write-wakeup use-after-free USB: serial: keyspan_pda: fix tx-unthrottle use-after-free USB: serial: keyspan_pda: fix write unthrottling Johannes Berg (2): iwlwifi: pcie: limit memory read spin time mac80211: don't set set TDLS STA bandwidth wider than possible Johannes Thumshirn (1): block: factor out requeue handling from dispatch code Jonathan Cameron (4): iio:light:rpr0521: Fix timestamp alignment and prevent data leak. iio:light:st_uvis25: Fix timestamp alignment and prevent data leak. iio:pressure:mpl3115: Force alignment of buffer iio:imu:bmi160: Fix too large a buffer. Jordan Niethe (1): powerpc/64: Set up a kernel stack for secondaries before cpu_restore() Jubin Zhong (1): PCI: Fix pci_slot_release() NULL pointer dereference Julian Sax (1): HID: i2c-hid: add Vero K147 to descriptor override Kamal Heib (2): RDMA/bnxt_re: Set queue pair state when being queried RDMA/cxgb4: Validate the number of CQEs Keita Suzuki (1): media: siano: fix memory leak of debugfs members in smsdvb_hotplug Keqian Zhu (1): clocksource/drivers/arm_arch_timer: Correct fault programming of CNTKCTL_EL1.EVNTI Krzysztof Kozlowski (4): ARM: dts: exynos: fix roles of USB 3.0 ports on Odroid XU ARM: dts: exynos: fix USB 3.0 VBUS control and over-current pins on Exynos5410 ARM: dts: exynos: fix USB 3.0 pins supply being turned off on Odroid XU drm/tve200: Fix handling of platform_get_irq() error Leo Yan (2): perf cs-etm: Change tuple from traceID-CPU# to traceID-metadata perf cs-etm: Move definition of 'traceid_list' global variable from header file Leon Romanovsky (2): RDMA/cm: Fix an attempt to use non-valid pointer when cleaning timewait net/mlx5: Properly convey driver version to firmware Li Jun (1): xhci: Give USB2 ports time to enter U3 in bus suspend Lingling Xu (2): watchdog: sprd: remove watchdog disable from resume fail path watchdog: sprd: check busy bit before new loading rather than after that Lokesh Vutla (1): pwm: lp3943: Dynamically allocate PWM chip base Luc Van Oostenryck (1): xsk: Fix xsk_poll()'s return type Luis Henriques (1): ceph: fix race in concurrent __ceph_remove_cap invocations Lukas Wunner (8): spi: bcm2835aux: Fix use-after-free on unbind media: netup_unidvb: Don't leak SPI master in probe error path spi: spi-sh: Fix use-after-free on unbind spi: davinci: Fix use-after-free on unbind spi: pic32: Don't leak DMA channels in probe error path spi: rb4xx: Don't leak SPI master in probe error path spi: sc18is602: Don't leak SPI master in probe error path spi: st-ssc4: Fix unbalanced pm_runtime_disable() in probe error path Manivannan Sadhasivam (1): watchdog: qcom: Avoid context switch in restart handler Mao Jinlong (1): coresight: tmc-etr: Check if page is valid before dma_map_page() Marc Zyngier (3): genirq/irqdomain: Don't try to free an interrupt that has no mapping irqchip/alpine-msi: Fix freeing of interrupts on allocation error path KVM: arm64: Introduce handling of AArch32 TTBCR2 traps Marek Szyprowski (1): extcon: max77693: Fix modalias string Mark Rutland (1): arm64: syscall: exit userspace before unmasking exceptions Markus Reichl (1): arm64: dts: rockchip: Assign a fixed index to mmc devices on rk3399 boards. Martin Blumenstingl (1): net: stmmac: dwmac-meson8b: fix mask definition of the m250_sel mux Martin Wilck (1): scsi: core: Fix VPD LUN ID designator priorities Masahiro Yamada (1): kconfig: fix return value of do_error_if() Masami Hiramatsu (1): x86/kprobes: Restore BTF if the single-stepping is cancelled Mathieu Desnoyers (1): powerpc: Fix incorrect stw{, ux, u, x} instructions in __set_pte_at Max Verevkin (1): platform/x86: intel-vbtn: Support for tablet mode on HP Pavilion 13 x360 PC Michael Ellerman (1): powerpc: Drop -me200 addition to build flags Miquel Raynal (1): mtd: spinand: Fix OOB read Moshe Shemesh (2): net/mlx4_en: Avoid scheduling restart task if it is already running net/mlx4_en: Handle TX error CQE Nathan Chancellor (2): spi: bcm2835aux: Restore err assignment in bcm2835aux_spi_probe crypto: crypto4xx - Replace bitwise OR with logical OR in crypto4xx_build_pd Nathan Lynch (2): powerpc/pseries/hibernation: drop pseries_suspend_begin() from suspend ops powerpc/pseries/hibernation: remove redundant cacheinfo update Neal Cardwell (1): tcp: fix cwnd-limited bug for TSO deferral where we send nothing Necip Fazil Yildiran (1): MIPS: BCM47XX: fix kconfig dependency bug for BCM47XX_BCMA NeilBrown (1): NFS: switch nfsiod to be an UNBOUND workqueue. Nicholas Piggin (1): kernel/cpu: add arch override for clear_tasks_mm_cpumask() mm handling Nick Desaulniers (1): Kbuild: do not emit debug info for assembly with LLVM_IAS=1 Nicolas Boichat (1): soc: mediatek: Check if power domains can be powered on at boot time Nicolas Ferre (1): ARM: dts: at91: sama5d2: fix CAN message ram offset and size Nicolin Chen (1): soc/tegra: fuse: Fix index bug in get_process_id Nuno Sá (1): iio: buffer: Fix demux update Oleksandr Andrushchenko (1): drm/xen-front: Fix misused IS_ERR_OR_NULL checks Oleksij Rempel (1): Input: ads7846 - fix integer overflow on Rt calculation Olga Kornievskaia (1): NFSv4.2: condition READDIR's mask for security label based on LSM state Oliver Neukum (2): USB: add RESET_RESUME quirk for Snapscan 1212 USB: UAS: introduce a quirk to set no_write_same Pali Rohár (5): cpufreq: highbank: Add missing MODULE_DEVICE_TABLE cpufreq: mediatek: Add missing MODULE_DEVICE_TABLE cpufreq: st: Add missing MODULE_DEVICE_TABLE cpufreq: loongson1: Add missing MODULE_ALIAS cpufreq: scpi: Add missing MODULE_ALIAS Paul Kocialkowski (1): ARM: sunxi: Add machine match for the Allwinner V3 SoC Paul Moore (1): selinux: fix inode_doinit_with_dentry() LABEL_INVALID error handling Paweł Chmiel (2): arm64: dts: exynos: Include common syscon restart/poweroff for Exynos7 arm64: dts: exynos: Correct psci compatible used on Exynos7 Peilin Ye (1): Bluetooth: Fix slab-out-of-bounds read in hci_le_direct_adv_report_evt() Peng Liu (1): sched/deadline: Fix sched_dl_global_validate() Philipp Rudo (1): s390/kexec_file: fix diag308 subcode when loading crash kernel Praveenkumar I (1): mtd: rawnand: qcom: Fix DMA sync on FLASH_STATUS register read Qinglang Miao (11): drm/tegra: sor: Disable clocks on error in tegra_sor_init() spi: bcm63xx-hsspi: fix missing clk_disable_unprepare() on error in bcm63xx_hsspi_resume media: solo6x10: fix missing snd_card_free in error handling case memstick: fix a double-free bug in memstick_check cw1200: fix missing destroy_workqueue() on error in cw1200_init_common mips: cdmm: fix use-after-free in mips_cdmm_bus_discover platform/x86: dell-smbios-base: Fix error return code in dell_smbios_init dm ioctl: fix error return code in target_message scsi: qedi: Fix missing destroy_workqueue() on error in __qedi_probe spi: mt7621: fix missing clk_disable_unprepare() on error in mt7621_spi_probe iio: adc: rockchip_saradc: fix missing clk_disable_unprepare() on error in rockchip_saradc_resume Rafael J. Wysocki (1): PM: ACPI: PCI: Drop acpi_pm_set_bridge_wakeup() Rakesh Pillai (1): ath10k: Fix the parsing error in service available event Randy Dunlap (1): scsi: bnx2i: Requires MMU Richard Weinberger (1): ubifs: wbuf: Don't leak kernel memory to flash Roberto Sassu (1): ima: Don't modify file descriptor mode on the fly Sakari Ailus (5): media: ipu3-cio2: Remove traces of returned buffers media: ipu3-cio2: Return actual subdev format media: ipu3-cio2: Serialise access to pad format media: ipu3-cio2: Validate mbus format in setting subdev format media: ipu3-cio2: Make the field on subdev format V4L2_FIELD_NONE Sami Tolvanen (1): arm64: lse: fix LSE atomics with LLVM's integrated assembler Sara Sharon (2): iwlwifi: mvm: fix kernel panic in case of assert during CSA cfg80211: initialize rekey_data Sean Young (1): media: sunxi-cir: ensure IR is handled when it is continuous Sebastian Andrzej Siewior (1): orinoco: Move context allocation after processing the skb Serge Hallyn (1): fix namespaced fscaps when !CONFIG_SECURITY Sergej Bauer (1): lan743x: fix for potential NULL pointer dereference with bare card Simon Beginn (1): Input: goodix - add upside-down quirk for Teclast X98 Pro tablet Sreekanth Reddy (1): scsi: mpt3sas: Increase IOCInit request timeout to 30s Stefan Haberland (4): s390/dasd: fix hanging device offline processing s390/dasd: prevent inconsistent LCU device data s390/dasd: fix list corruption of pavgroup group list s390/dasd: fix list corruption of lcu list Steve French (2): SMB3: avoid confusing warning message on mount to Azure SMB3.1.1: do not log warning message if server doesn't populate salt Steven Rostedt (VMware) (1): ktest.pl: If size of log is too big to email, email error message Subash Abhinov Kasiviswanathan (1): netfilter: x_tables: Switch synchronization to RCU Sven Eckelmann (3): vxlan: Add needed_headroom for lower device vxlan: Copy needed_tailroom from lowerdev mtd: parser: cmdline: Fix parsing of part-names with colons Sven Schnelle (1): s390/smp: perform initial CPU reset also for SMT siblings Takashi Iwai (7): ALSA: usb-audio: Fix potential out-of-bounds shift ALSA: usb-audio: Fix control 'access overflow' errors from chmap ALSA: pcm: oss: Fix potential out-of-bounds shift ALSA: hda: Fix regressions on clear and reconfig sysfs ALSA: pcm: oss: Fix a few more UBSAN fixes ALSA: hda/realtek: Add quirk for MSI-GP73 ALSA: usb-audio: Disable sample read check if firmware doesn't give back Terry Zhou (1): clk: mvebu: a3700: fix the XTAL MODE pin to MPP1_9 Thomas Gleixner (4): x86/apic/vector: Fix ordering in vector assignment USB: sisusbvga: Make console support depend on BROKEN dm table: Remove BUG_ON(in_interrupt()) sched: Reenable interrupts in do_sched_yield() Tianyue Ren (1): selinux: fix error initialization in inode_doinit_with_dentry() Timo Witte (1): platform/x86: acer-wmi: add automatic keyboard background light toggle key as KEY_LIGHTS_TOGGLE Toke Høiland-Jørgensen (1): selftests/bpf/test_offload.py: Reset ethtool features after failed setting Tom Rix (1): drm/gma500: fix double free of gma_connector Trond Myklebust (1): SUNRPC: xprt_load_transport() needs to support the netid "rdma6" Tsuchiya Yuto (1): mwifiex: fix mwifiex_shutdown_sw() causing sw reset failure Tyrel Datwyler (1): powerpc/rtas: Fix typo of ibm,open-errinjct in RTAS filter Uwe Kleine-König (2): spi: fix resource leak for drivers without .remove callback pwm: zx: Add missing cleanup in error path Vadim Pasternak (3): platform/x86: mlx-platform: Remove PSU EEPROM from default platform configuration platform/x86: mlx-platform: Remove PSU EEPROM from MSN274x platform configuration platform/x86: mlx-platform: Fix item counter assignment for MSN2700, MSN24xx systems Vincent Stehlé (2): powerpc/ps3: use dma_mapping_error() net: korina: fix return value Vincenzo Frascino (1): arm64: lse: Fix LSE atomics with LLVM Vineet Gupta (1): ARC: stack unwinding: don't assume non-current task is sleeping Wang Wensheng (1): watchdog: Fix potential dereferencing of null pointer Will McVicker (2): USB: gadget: f_midi: setup SuperSpeed Plus descriptors USB: gadget: f_rndis: fix bitrate for SuperSpeed and above Xiaochen Shen (1): x86/resctrl: Fix incorrect local bandwidth when mba_sc is enabled Xin Xiong (1): drm: fix drm_dp_mst_port refcount leaks in drm_dp_mst_allocate_vcpi Yang Yingliang (4): video: fbdev: atmel_lcdfb: fix return error code in atmel_lcdfb_of_init() drm/omap: dmm_tiler: fix return error code in omap_dmm_probe() usb/max3421: fix return error code in max3421_probe() speakup: fix uninitialized flush_lock Yangtao Li (1): pinctrl: sunxi: Always call chained_irq_{enter, exit} in sunxi_pinctrl_irq_handler Yu Kuai (3): media: mtk-vcodec: add missing put_device() call in mtk_vcodec_release_dec_pm() clocksource/drivers/cadence_ttc: Fix memory leak in ttc_setup_clockevent() pinctrl: falcon: add missing put_device() call in pinctrl_falcon_probe() Zhang Changzhong (3): net: bridge: vlan: fix error return code in __vlan_add() scsi: fnic: Fix error return code in fnic_probe() bus: fsl-mc: fix error return code in fsl_mc_object_allocate() Zhang Qilong (20): can: softing: softing_netdev_open(): fix error handling spi: img-spfi: fix reference leak in img_spfi_resume spi: spi-ti-qspi: fix reference leak in ti_qspi_setup spi: tegra20-slink: fix reference leak in slink ops of tegra20 spi: tegra20-sflash: fix reference leak in tegra_sflash_resume spi: tegra114: fix reference leak in tegra spi ops ASoC: wm8998: Fix PM disable depth imbalance on error ASoC: arizona: Fix a wrong free in wm8997_probe staging: greybus: codecs: Fix reference counter leak in error handling spi: mxs: fix reference leak in mxs_spi_probe crypto: omap-aes - Fix PM disable depth imbalance in omap_aes_probe soc: ti: knav_qmss: fix reference leak in knav_queue_probe soc: ti: Fix reference imbalance in knav_dma_probe Input: omap4-keypad - fix runtime PM error handling power: supply: bq24190_charger: fix reference leak scsi: pm80xx: Fix error return in pm8001_pci_probe() usb: ehci-omap: Fix PM disable depth umbalance in ehci_hcd_omap_probe usb: oxu210hp-hcd: Fix memory leak in oxu_create libnvdimm/label: Return -ENXIO for no slot in __blk_label_update clk: ti: Fix memleak in ti_fapll_synth_setup Zhao Heming (2): md/cluster: block reshape with remote resync job md/cluster: fix deadlock when node is doing resync job Zhe Li (1): jffs2: Fix GC exit abnormally Zheng Zengkai (1): perf record: Fix memory leak when using '--user-regs=?' to list registers Zhihao Cheng (2): drivers: soc: ti: knav_qmss_queue: Fix error return code in knav_queue_probe dmaengine: mv_xor_v2: Fix error return code in mv_xor_v2_probe() Zwane Mwaikambo (1): drm/dp_aux_dev: check aux_dev before use in drm_dp_aux_dev_get_by_minor() kazuo ito (1): nfsd: Fix message level for normal termination taehyun.cho (1): USB: gadget: f_acm: add support for SuperSpeed Plus .../admin-guide/kernel-parameters.txt | 1 + Makefile | 5 +- arch/arc/kernel/stacktrace.c | 23 ++-- arch/arm/boot/dts/armada-xp-98dx3236.dtsi | 5 - .../arm/boot/dts/aspeed-bmc-intel-s2600wf.dts | 4 +- arch/arm/boot/dts/at91-sama5d3_xplained.dts | 7 + arch/arm/boot/dts/at91-sama5d4_xplained.dts | 7 + arch/arm/boot/dts/at91sam9rl.dtsi | 19 +-- arch/arm/boot/dts/exynos5410-odroidxu.dts | 6 +- arch/arm/boot/dts/exynos5410-pinctrl.dtsi | 28 ++++ arch/arm/boot/dts/exynos5410.dtsi | 4 + arch/arm/boot/dts/omap4-panda-es.dts | 2 +- arch/arm/boot/dts/sama5d2.dtsi | 7 +- arch/arm/boot/dts/sun8i-v3s.dtsi | 2 +- arch/arm/kernel/head.S | 6 +- arch/arm/mach-shmobile/pm-rmobile.c | 1 + arch/arm/mach-sunxi/sunxi.c | 1 + .../dts/amlogic/meson-gxm-khadas-vim2.dts | 2 +- arch/arm64/boot/dts/exynos/exynos7.dtsi | 12 +- .../arm64/boot/dts/rockchip/rk3328-roc-cc.dts | 1 + arch/arm64/boot/dts/rockchip/rk3328.dtsi | 16 +-- arch/arm64/boot/dts/rockchip/rk3399.dtsi | 3 + arch/arm64/include/asm/atomic_lse.h | 76 ++++++++--- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/include/asm/lse.h | 6 +- arch/arm64/kernel/syscall.c | 2 +- arch/arm64/kvm/sys_regs.c | 1 + arch/arm64/lib/memcpy.S | 3 +- arch/arm64/lib/memmove.S | 3 +- arch/arm64/lib/memset.S | 3 +- arch/mips/bcm47xx/Kconfig | 1 + arch/powerpc/Makefile | 1 - arch/powerpc/include/asm/book3s/32/pgtable.h | 4 +- arch/powerpc/include/asm/cputable.h | 5 - arch/powerpc/include/asm/nohash/pgtable.h | 4 +- arch/powerpc/kernel/head_64.S | 8 +- arch/powerpc/kernel/rtas.c | 2 +- arch/powerpc/kernel/setup-common.c | 4 +- arch/powerpc/perf/core-book3s.c | 10 ++ arch/powerpc/platforms/powernv/memtrace.c | 44 +++++- arch/powerpc/platforms/pseries/suspend.c | 4 - arch/powerpc/xmon/nonstdio.c | 2 +- arch/s390/kernel/smp.c | 18 +-- arch/s390/purgatory/head.S | 9 +- arch/um/drivers/chan_user.c | 4 +- arch/um/drivers/xterm.c | 5 + arch/um/os-Linux/irq.c | 2 +- arch/x86/include/asm/apic.h | 1 + arch/x86/include/asm/pgtable_types.h | 1 + arch/x86/include/asm/sync_core.h | 9 +- arch/x86/kernel/apic/apic.c | 14 +- arch/x86/kernel/apic/vector.c | 24 ++-- arch/x86/kernel/apic/x2apic_phys.c | 9 ++ arch/x86/kernel/cpu/intel_rdt.h | 2 - arch/x86/kernel/cpu/intel_rdt_monitor.c | 7 +- arch/x86/kernel/kprobes/core.c | 5 + arch/x86/lib/memcpy_64.S | 6 +- arch/x86/lib/memmove_64.S | 4 +- arch/x86/lib/memset_64.S | 6 +- arch/x86/mm/ident_map.c | 12 +- arch/x86/mm/mem_encrypt_identity.c | 4 +- arch/x86/mm/tlb.c | 10 +- block/blk-mq.c | 29 ++-- crypto/af_alg.c | 10 +- crypto/ecdh.c | 9 +- drivers/acpi/acpi_pnp.c | 3 + drivers/acpi/device_pm.c | 41 ++---- drivers/acpi/resource.c | 2 +- drivers/bluetooth/hci_h5.c | 3 + drivers/bus/fsl-mc/fsl-mc-allocator.c | 4 +- drivers/bus/mips_cdmm.c | 4 +- drivers/clk/clk-s2mps11.c | 1 + drivers/clk/mvebu/armada-37xx-xtal.c | 4 +- drivers/clk/renesas/r9a06g032-clocks.c | 2 +- drivers/clk/sunxi-ng/ccu-sun50i-a64.c | 1 + drivers/clk/sunxi-ng/ccu-sun8i-h3.c | 1 + drivers/clk/tegra/clk-id.h | 1 + drivers/clk/tegra/clk-tegra-periph.c | 2 +- drivers/clk/ti/fapll.c | 11 +- drivers/clocksource/arm_arch_timer.c | 23 +++- drivers/clocksource/cadence_ttc_timer.c | 18 +-- drivers/cpufreq/highbank-cpufreq.c | 7 + drivers/cpufreq/loongson1-cpufreq.c | 1 + drivers/cpufreq/mediatek-cpufreq.c | 1 + drivers/cpufreq/scpi-cpufreq.c | 1 + drivers/cpufreq/sti-cpufreq.c | 7 + drivers/crypto/amcc/crypto4xx_core.c | 2 +- drivers/crypto/inside-secure/safexcel.c | 2 +- drivers/crypto/omap-aes.c | 3 +- drivers/crypto/qat/qat_common/qat_hal.c | 2 +- drivers/crypto/talitos.c | 10 +- drivers/dma/mv_xor_v2.c | 4 +- drivers/edac/amd64_edac.c | 26 ++-- drivers/extcon/extcon-max77693.c | 2 +- drivers/gpio/gpio-eic-sprd.c | 2 +- drivers/gpio/gpio-mvebu.c | 16 ++- drivers/gpu/drm/drm_dp_aux_dev.c | 2 +- drivers/gpu/drm/drm_dp_mst_topology.c | 7 +- drivers/gpu/drm/gma500/cdv_intel_dp.c | 2 +- drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c | 8 ++ drivers/gpu/drm/omapdrm/omap_dmm_tiler.c | 1 + drivers/gpu/drm/tegra/drm.c | 2 +- drivers/gpu/drm/tegra/sor.c | 10 +- drivers/gpu/drm/tve200/tve200_drv.c | 4 +- drivers/gpu/drm/xen/xen_drm_front.c | 2 +- drivers/gpu/drm/xen/xen_drm_front_gem.c | 8 +- drivers/gpu/drm/xen/xen_drm_front_kms.c | 2 +- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 8 ++ drivers/hsi/controllers/omap_ssi_core.c | 2 +- .../hwtracing/coresight/coresight-tmc-etr.c | 2 + drivers/iio/adc/rockchip_saradc.c | 2 +- drivers/iio/imu/bmi160/bmi160_core.c | 4 +- drivers/iio/industrialio-buffer.c | 6 +- drivers/iio/light/rpr0521.c | 17 ++- drivers/iio/light/st_uvis25.h | 5 + drivers/iio/light/st_uvis25_core.c | 8 +- drivers/iio/pressure/mpl3115.c | 9 +- drivers/infiniband/core/cm.c | 2 + drivers/infiniband/hw/bnxt_re/ib_verbs.c | 1 + drivers/infiniband/hw/cxgb4/cq.c | 3 + drivers/infiniband/hw/mthca/mthca_cq.c | 2 +- drivers/infiniband/hw/mthca/mthca_dev.h | 1 - drivers/infiniband/sw/rxe/rxe_req.c | 3 +- drivers/input/keyboard/cros_ec_keyb.c | 1 + drivers/input/keyboard/omap4-keypad.c | 89 ++++++++----- drivers/input/misc/cm109.c | 7 +- drivers/input/mouse/cyapa_gen6.c | 2 +- drivers/input/serio/i8042-x86ia64io.h | 42 ++++++ drivers/input/touchscreen/ads7846.c | 52 +++++--- drivers/input/touchscreen/goodix.c | 12 ++ drivers/irqchip/irq-alpine-msi.c | 3 +- drivers/md/dm-ioctl.c | 1 + drivers/md/dm-table.c | 6 - drivers/md/md-cluster.c | 67 ++++++---- drivers/md/md.c | 21 ++- drivers/media/common/siano/smsdvb-main.c | 5 +- drivers/media/i2c/max2175.c | 2 +- drivers/media/pci/intel/ipu3/ipu3-cio2.c | 62 +++++---- drivers/media/pci/intel/ipu3/ipu3-cio2.h | 1 + .../media/pci/netup_unidvb/netup_unidvb_spi.c | 5 +- drivers/media/pci/saa7146/mxb.c | 19 +-- drivers/media/pci/solo6x10/solo6x10-g723.c | 2 +- .../platform/mtk-vcodec/mtk_vcodec_dec_pm.c | 1 + drivers/media/rc/sunxi-cir.c | 2 + drivers/media/usb/gspca/gspca.c | 1 + drivers/media/usb/msi2500/msi2500.c | 2 +- drivers/media/usb/tm6000/tm6000-video.c | 5 +- drivers/memstick/core/memstick.c | 1 - drivers/memstick/host/r592.c | 12 +- drivers/mmc/core/block.c | 2 +- drivers/mtd/cmdlinepart.c | 14 +- drivers/mtd/nand/raw/qcom_nandc.c | 2 + drivers/mtd/nand/spi/core.c | 4 + drivers/net/can/softing/softing_main.c | 9 +- drivers/net/ethernet/allwinner/sun4i-emac.c | 7 +- .../net/ethernet/broadcom/genet/bcmgenet.c | 4 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 24 +++- drivers/net/ethernet/korina.c | 2 +- .../net/ethernet/mellanox/mlx4/en_netdev.c | 21 ++- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 40 +++++- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 12 +- .../net/ethernet/mellanox/mlx5/core/main.c | 6 +- .../net/ethernet/microchip/lan743x_ethtool.c | 9 +- .../net/ethernet/qlogic/qlcnic/qlcnic_main.c | 1 + .../ethernet/stmicro/stmmac/dwmac-meson8b.c | 6 +- .../net/ethernet/stmicro/stmmac/stmmac_main.c | 27 +++- drivers/net/vxlan.c | 3 + drivers/net/wireless/ath/ath10k/usb.c | 7 +- drivers/net/wireless/ath/ath10k/wmi-tlv.c | 4 +- drivers/net/wireless/ath/ath10k/wmi.c | 9 +- drivers/net/wireless/ath/ath10k/wmi.h | 1 + .../net/wireless/intel/iwlwifi/mvm/mac80211.c | 2 +- .../net/wireless/intel/iwlwifi/pcie/trans.c | 36 +++-- .../wireless/intersil/orinoco/orinoco_usb.c | 14 +- drivers/net/wireless/marvell/mwifiex/main.c | 2 + drivers/net/wireless/st/cw1200/main.c | 2 + drivers/nfc/s3fwrn5/firmware.c | 4 +- drivers/nvdimm/label.c | 13 +- drivers/pci/controller/dwc/pcie-qcom.c | 12 ++ drivers/pci/controller/pcie-iproc.c | 10 +- drivers/pci/pci-acpi.c | 4 +- drivers/pci/pci.c | 14 +- drivers/pci/slot.c | 6 +- drivers/pinctrl/intel/pinctrl-baytrail.c | 8 +- drivers/pinctrl/intel/pinctrl-merrifield.c | 8 ++ drivers/pinctrl/pinctrl-amd.c | 7 - drivers/pinctrl/pinctrl-falcon.c | 14 +- drivers/pinctrl/sunxi/pinctrl-sunxi.c | 6 +- drivers/platform/x86/acer-wmi.c | 1 + drivers/platform/x86/dell-smbios-base.c | 1 + drivers/platform/x86/intel-vbtn.c | 12 ++ drivers/platform/x86/mlx-platform.c | 27 +--- drivers/platform/x86/thinkpad_acpi.c | 10 +- drivers/power/supply/axp288_charger.c | 28 ++-- drivers/power/supply/bq24190_charger.c | 20 ++- drivers/ps3/ps3stor_lib.c | 2 +- drivers/pwm/pwm-lp3943.c | 1 + drivers/pwm/pwm-zx.c | 1 + drivers/s390/block/dasd_alias.c | 22 ++- drivers/scsi/be2iscsi/be_main.c | 4 +- drivers/scsi/bnx2i/Kconfig | 1 + drivers/scsi/fnic/fnic_main.c | 1 + drivers/scsi/lpfc/lpfc_mem.c | 6 +- drivers/scsi/lpfc/lpfc_sli.c | 10 +- drivers/scsi/megaraid/megaraid_sas_base.c | 16 ++- drivers/scsi/mpt3sas/mpt3sas_base.c | 2 +- drivers/scsi/pm8001/pm8001_init.c | 3 +- drivers/scsi/qedi/qedi_main.c | 4 +- drivers/scsi/scsi_lib.c | 126 ++++++++++++------ drivers/scsi/ufs/ufshcd.c | 7 + drivers/slimbus/qcom-ngd-ctrl.c | 6 + drivers/soc/fsl/dpio/dpio-driver.c | 5 +- drivers/soc/mediatek/mtk-scpsys.c | 5 +- drivers/soc/qcom/qcom-geni-se.c | 17 ++- drivers/soc/qcom/smp2p.c | 5 +- drivers/soc/tegra/fuse/speedo-tegra210.c | 2 +- drivers/soc/ti/knav_dma.c | 13 +- drivers/soc/ti/knav_qmss_queue.c | 4 +- drivers/spi/spi-bcm2835aux.c | 17 +-- drivers/spi/spi-bcm63xx-hsspi.c | 4 +- drivers/spi/spi-davinci.c | 2 +- drivers/spi/spi-img-spfi.c | 4 +- drivers/spi/spi-mxs.c | 1 + drivers/spi/spi-pic32.c | 1 + drivers/spi/spi-rb4xx.c | 2 +- drivers/spi/spi-sc18is602.c | 13 +- drivers/spi/spi-sh.c | 13 +- drivers/spi/spi-st-ssc4.c | 5 +- drivers/spi/spi-tegra114.c | 2 + drivers/spi/spi-tegra20-sflash.c | 1 + drivers/spi/spi-tegra20-slink.c | 2 + drivers/spi/spi-ti-qspi.c | 1 + drivers/spi/spi.c | 19 +-- drivers/staging/comedi/drivers/mf6x4.c | 3 +- drivers/staging/gasket/gasket_interrupt.c | 15 ++- drivers/staging/greybus/audio_codec.c | 2 + drivers/staging/mt7621-spi/spi-mt7621.c | 2 + drivers/staging/speakup/speakup_dectlk.c | 2 +- drivers/tty/serial/8250/8250_omap.c | 5 - drivers/tty/serial/serial_core.c | 4 + drivers/usb/chipidea/ci_hdrc_imx.c | 3 +- drivers/usb/core/quirks.c | 3 + drivers/usb/gadget/function/f_acm.c | 2 +- drivers/usb/gadget/function/f_fs.c | 5 +- drivers/usb/gadget/function/f_midi.c | 6 + drivers/usb/gadget/function/f_rndis.c | 4 +- drivers/usb/gadget/udc/dummy_hcd.c | 2 +- drivers/usb/host/ehci-omap.c | 1 + drivers/usb/host/max3421-hcd.c | 3 +- drivers/usb/host/oxu210hp-hcd.c | 4 +- drivers/usb/host/xhci-hub.c | 4 + drivers/usb/misc/sisusbvga/Kconfig | 2 +- drivers/usb/serial/digi_acceleport.c | 45 ++----- drivers/usb/serial/keyspan_pda.c | 63 +++++---- drivers/usb/serial/mos7720.c | 2 + drivers/usb/serial/option.c | 23 +++- drivers/usb/storage/uas.c | 3 + drivers/usb/storage/unusual_uas.h | 7 +- drivers/usb/storage/usb.c | 3 + drivers/vfio/pci/vfio_pci.c | 4 +- drivers/video/fbdev/atmel_lcdfb.c | 2 +- drivers/watchdog/Kconfig | 3 +- drivers/watchdog/qcom-wdt.c | 2 +- drivers/watchdog/sprd_wdt.c | 34 +++-- drivers/watchdog/watchdog_core.c | 22 +-- fs/ceph/caps.c | 11 +- fs/cifs/smb2ops.c | 3 +- fs/cifs/smb2pdu.c | 7 +- fs/cifs/smb2pdu.h | 14 +- fs/ext4/inode.c | 19 ++- fs/ext4/mballoc.c | 1 + fs/jffs2/readinode.c | 16 +++ fs/lockd/host.c | 20 +-- fs/nfs/inode.c | 2 +- fs/nfs/nfs4proc.c | 10 +- fs/nfs_common/grace.c | 6 +- fs/nfsd/nfssvc.c | 3 +- fs/quota/quota_v2.c | 19 +++ fs/ubifs/io.c | 13 +- include/acpi/acpi_bus.h | 5 - include/linux/build_bug.h | 5 + include/linux/compiler-clang.h | 1 - include/linux/compiler-gcc.h | 19 --- include/linux/compiler.h | 18 ++- include/linux/netfilter/x_tables.h | 5 +- include/linux/security.h | 2 +- include/linux/seq_buf.h | 2 +- include/linux/sunrpc/xprt.h | 1 + include/linux/trace_seq.h | 4 +- include/linux/usb_usual.h | 2 + include/uapi/linux/if_alg.h | 16 +++ kernel/cpu.c | 6 +- kernel/irq/irqdomain.c | 11 +- kernel/sched/core.c | 6 +- kernel/sched/deadline.c | 5 +- kernel/sched/sched.h | 42 +++--- net/bluetooth/hci_event.c | 17 ++- net/bridge/br_vlan.c | 4 +- net/core/lwt_bpf.c | 8 +- net/ipv4/netfilter/arp_tables.c | 14 +- net/ipv4/netfilter/ip_tables.c | 14 +- net/ipv4/tcp_input.c | 3 +- net/ipv4/tcp_output.c | 9 +- net/ipv6/netfilter/ip6_tables.c | 14 +- net/mac80211/mesh_pathtbl.c | 4 +- net/mac80211/vht.c | 14 +- net/netfilter/x_tables.c | 49 +++---- net/sunrpc/xprt.c | 65 ++++++--- net/sunrpc/xprtrdma/module.c | 1 + net/sunrpc/xprtrdma/transport.c | 1 + net/sunrpc/xprtsock.c | 4 + net/wireless/nl80211.c | 2 +- net/xdp/xsk.c | 8 +- samples/bpf/lwt_len_hist.sh | 2 + samples/bpf/test_lwt_bpf.sh | 0 scripts/checkpatch.pl | 2 +- scripts/kconfig/preprocess.c | 2 +- security/integrity/ima/ima_crypto.c | 20 +-- security/selinux/hooks.c | 16 ++- sound/core/oss/pcm_oss.c | 28 ++-- sound/pci/hda/hda_codec.c | 2 +- sound/pci/hda/hda_sysfs.c | 2 +- sound/pci/hda/patch_ca0132.c | 2 +- sound/pci/hda/patch_realtek.c | 4 + sound/soc/codecs/wm8997.c | 2 + sound/soc/codecs/wm8998.c | 4 +- sound/soc/codecs/wm_adsp.c | 5 +- sound/soc/jz4740/jz4740-i2s.c | 4 + sound/soc/meson/Kconfig | 2 +- sound/soc/soc-pcm.c | 2 + sound/usb/clock.c | 6 + sound/usb/format.c | 2 + sound/usb/quirks.c | 1 + sound/usb/stream.c | 6 +- .../perf/util/cs-etm-decoder/cs-etm-decoder.c | 8 +- tools/perf/util/cs-etm.c | 29 +++- tools/perf/util/cs-etm.h | 10 +- tools/perf/util/parse-regs-options.c | 2 +- tools/testing/ktest/ktest.pl | 7 +- tools/testing/selftests/bpf/test_offload.py | 1 + 340 files changed, 2021 insertions(+), 1084 deletions(-) mode change 100644 => 100755 samples/bpf/lwt_len_hist.sh mode change 100644 => 100755 samples/bpf/test_lwt_bpf.sh -- 2.25.1

1 337

[PATCH v2 1/1 openEuler-1.0-LTS] fork: add pid recover method for checkpoint and recover
by hejingxian 31 Dec '20

31 Dec '20

From: hejingxian <hejingxian(a)huawei.com> Date: Thu, 31 Dec 2020 20:18:56 +0800 Subject: [PATCH v2 1/1 openEuler-1.0-LTS] fork: add pid recover method for checkpoint and recover We record the pid of dump task in the reserved memory, and reserve the pids before init task start. In the recover process, set the fork_pid of the recovery task before call fork(). And then the fork_pid will be used to alloc pid. /proc/sys/kernel/ns_last_pid can also be used to fork child task with assigned pid. However, when there exist many tasks need to recover at the same time, we will fail to recover pids by using /proc/sys/kernel/ns_last_pid. Signed-off-by: Jingxian He <hejingxian(a)huawei.com> --- drivers/char/pin_memory.c | 24 +++++++++++++++++++++- include/linux/pin_mem.h | 6 ++++++ include/linux/sched.h | 9 +++++++++ init/init_task.c | 3 +++ kernel/pid.c | 33 ++++++++++++++++++++++++++++++ mm/Kconfig | 7 +++++++ mm/pin_mem.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 132 insertions(+), 1 deletion(-) diff --git a/drivers/char/pin_memory.c b/drivers/char/pin_memory.c index a0464e1..2c65de7 100644 --- a/drivers/char/pin_memory.c +++ b/drivers/char/pin_memory.c @@ -36,9 +36,12 @@ struct pin_mem_area_set { #define _SET_PIN_MEM_AREA 1 #define _CLEAR_PIN_MEM_AREA 2 #define _REMAP_PIN_MEM_AREA 3 +#define _SET_FORK_PID 4 + #define SET_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _SET_PIN_MEM_AREA, struct pin_mem_area_set) #define CLEAR_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _CLEAR_PIN_MEM_AREA, int) #define REMAP_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _REMAP_PIN_MEM_AREA, int) +#define SET_FORK_PID _IOW(PIN_MEM_MAGIC, _SET_FORK_PID, int) static int set_pin_mem(struct pin_mem_area_set *pmas) { @@ -136,13 +139,29 @@ static int pin_mem_remap(unsigned long arg) return -EFAULT; } +static int set_fork_pid(unsigned long arg) +{ + int pid; + struct page_map_info * pmi = NULL; + void __user *buf = (void __user *)arg; + + if (!access_ok(buf, sizeof(int))) + goto fault; + if (copy_from_user(&pid, buf, sizeof(int))) + goto fault; + current->fork_pid = pid; + return 0; +fault: + return -EFAULT; +} + static long pin_memory_ioctl(struct file *file, unsigned cmd, unsigned long arg) { long ret = 0; if (_IOC_TYPE(cmd) != PIN_MEM_MAGIC) return -EINVAL; - if (_IOC_NR(cmd) > _REMAP_PIN_MEM_AREA) + if (_IOC_NR(cmd) > _SET_FORK_PID) return -EINVAL; switch (cmd) { @@ -155,6 +174,9 @@ static long pin_memory_ioctl(struct file *file, unsigned cmd, unsigned long arg) case REMAP_PIN_MEM_AREA: ret = pin_mem_remap(arg); break; + case SET_FORK_PID: + ret = set_fork_pid(arg); + break; default: return -EINVAL; } diff --git a/include/linux/pin_mem.h b/include/linux/pin_mem.h index 997ddb8..f47dab4 100644 --- a/include/linux/pin_mem.h +++ b/include/linux/pin_mem.h @@ -58,5 +58,11 @@ extern vm_fault_t do_anon_huge_page_remap(struct vm_area_struct *vma, unsigned l #endif extern void init_reserve_page_map(unsigned long map_addr, unsigned long map_size); +#ifdef CONFIG_PID_RECOVER +extern bool is_need_reserve_pids(void); +extern void reserve_pids(struct idr *idr, int pid_max); +extern void free_reserved_pid(struct idr *idr, int pid); +#endif + #endif /* CONFIG_PIN_MEMORY */ #endif /* _LINUX_PIN_MEMORY_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index ced2d7f..3d23e46 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1220,7 +1220,16 @@ struct task_struct { KABI_RESERVE(1) KABI_RESERVE(2) #endif +#ifdef CONFIG_PID_RECOVER +#ifndef __GENKSYMS__ + int fork_pid; + int reserve; +#else KABI_RESERVE(3) +#endif +#else + KABI_RESERVE(3) +#endif KABI_RESERVE(4) KABI_RESERVE(5) KABI_RESERVE(6) diff --git a/init/init_task.c b/init/init_task.c index 5aebe3b..0334ad8 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -179,6 +179,9 @@ struct task_struct init_task #ifdef CONFIG_SECURITY .security = NULL, #endif +#ifdef CONFIG_PID_RECOVER + .fork_pid = 0, +#endif }; EXPORT_SYMBOL(init_task); diff --git a/kernel/pid.c b/kernel/pid.c index bfdcd16..5d02591 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -41,6 +41,9 @@ #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/kmemleak.h> +#ifdef CONFIG_PID_RECOVER +#include <linux/pin_mem.h> +#endif struct pid init_struct_pid = { .count = ATOMIC_INIT(1), @@ -185,6 +188,31 @@ struct pid *alloc_pid(struct pid_namespace *ns) if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; +#ifdef CONFIG_PID_RECOVER + if (!current->fork_pid) { + /* + * Store a null pointer so find_pid_ns does not find + * a partially initialized PID (see below). + */ + nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, + tmp->pid_max, + GFP_ATOMIC); + } else { + /* Try to use fork_pid to alloc pid, and change to use the default way after fail. */ + test_pid_reserved_and_free(&tmp->idr, current->fork_pid); + pid_min = current->fork_pid; + current->fork_pid = 0; + nr = idr_alloc(&tmp->idr, NULL, pid_min, + tmp->pid_max, + GFP_ATOMIC); + pr_debug("Alloc pid by fork_pid ret: %d.", nr); + if (nr < 0) + nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, + tmp->pid_max, + GFP_ATOMIC); + } +#else + /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). @@ -192,6 +220,7 @@ struct pid *alloc_pid(struct pid_namespace *ns) nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, tmp->pid_max, GFP_ATOMIC); +#endif spin_unlock_irq(&pidmap_lock); idr_preload_end(); @@ -500,6 +529,10 @@ void __init pid_idr_init(void) init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); +#ifdef CONFIG_PID_RECOVER + if (is_need_reserve_pids()) + reserve_pids(&init_pid_ns.idr, pid_max); +#endif hdr = register_sysctl_paths(pid_kern_path, pid_ctl_table); kmemleak_not_leak(hdr); diff --git a/mm/Kconfig b/mm/Kconfig index 31fa670..9ac20da 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -794,4 +794,11 @@ config PIN_MEMORY help Say y here to enable the pin memory feature for checkpoint and restore. + +config PID_RECOVER + bool "Support for pid recover" + depends on PIN_MEMORY + help + Say y here to enable the pid recover feature for checkpoint + and restore. endmenu diff --git a/mm/pin_mem.c b/mm/pin_mem.c index 89af938..2f77e86 100644 --- a/mm/pin_mem.c +++ b/mm/pin_mem.c @@ -688,4 +688,55 @@ vm_fault_t reserve_kernel_space_mem(unsigned long start_addr, unsigned int pages } EXPORT_SYMBOL_GPL(reserve_kernel_space_mem); +#ifdef CONFIG_PID_RECOVER +struct idr *reserve_idr; + +/* test if there exist pin memory tasks */ +bool is_need_reserve_pids(void) +{ + return (pin_pid_num > 0); +} + +void free_reserved_pid(struct idr *idr, int pid) +{ + unsigned int index; + struct page_map_info *pmi; + + if (!max_pin_pid_num || idr != reserve_idr) + return; + + for (index = 0; index < pin_pid_num; index++) { + pmi = &(user_space_reserve_start[index]); + if (pmi->pid == pid && pmi->pid_reserved) { + idr_remove(idr, pid); + return; + } + } +} + +/* reserve pids for check point tasks which pinned memory */ +void reserve_pids(struct idr *idr, int pid_max) +{ + int alloc_pid; + unsigned int index; + struct page_map_info *pmi; + + if (!max_pin_pid_num) + return; + reserve_idr = idr; + for (index = 0; index < pin_pid_num; index++) { + pmi = &(user_space_reserve_start[index]); + pmi->pid_reserved = true; + alloc_pid = idr_alloc(idr, NULL, pmi->pid, pid_max, GFP_ATOMIC); + if (alloc_pid != pmi->pid) { + if (alloc_pid > 0) + idr_remove(idr, alloc_pid); + pr_warn("Reserve pid (%d) fail, real pid is %d.\n", alloc_pid, pmi->pid); + pmi->pid_reserved = false; + continue; + } + } + return; +} +#endif /* CONFIG_PID_RECOVER */ #endif /* CONFIG_PIN_MEMORY */ -- 1.8.3.1

1 0

[PATCH v1 1/1 openEuler-1.0-LTS] fork: add pid recover method for checkpoint and recover
by hejingxian 31 Dec '20

31 Dec '20

From: hejingxian <hejingxian(a)huawei.com> Date: Thu, 10 Dec 2020 20:35:00 +0800 Subject: [PATCH v1 1/1 openEuler-1.0-LTS] fork: add pid recover method for checkpoint and recover We record the pid of dump task in the reserved memory, and reserve the pids before init task start. In the recover process, set the fork_pid of the recovery task before call fork(). And then the fork_pid will be used to alloc pid. /proc/sys/kernel/ns_last_pid can also be used to fork child task with assigned pid. However, when there exist many tasks need to recover at the same time, we will fail to recover pids by using /proc/sys/kernel/ns_last_pid. Signed-off-by: Jingxian He <hejingxian(a)huawei.com> --- drivers/char/pin_memory.c | 24 +++++++++++++++++++++- include/linux/pin_mem.h | 6 ++++++ include/linux/sched.h | 4 ++++ init/init_task.c | 3 +++ kernel/pid.c | 27 ++++++++++++++++++++++++- mm/Kconfig | 7 +++++++ mm/pin_mem.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 120 insertions(+), 2 deletions(-) diff --git a/drivers/char/pin_memory.c b/drivers/char/pin_memory.c index a0464e1..2c65de7 100644 --- a/drivers/char/pin_memory.c +++ b/drivers/char/pin_memory.c @@ -36,9 +36,12 @@ struct pin_mem_area_set { #define _SET_PIN_MEM_AREA 1 #define _CLEAR_PIN_MEM_AREA 2 #define _REMAP_PIN_MEM_AREA 3 +#define _SET_FORK_PID 4 + #define SET_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _SET_PIN_MEM_AREA, struct pin_mem_area_set) #define CLEAR_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _CLEAR_PIN_MEM_AREA, int) #define REMAP_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _REMAP_PIN_MEM_AREA, int) +#define SET_FORK_PID _IOW(PIN_MEM_MAGIC, _SET_FORK_PID, int) static int set_pin_mem(struct pin_mem_area_set *pmas) { @@ -136,13 +139,29 @@ static int pin_mem_remap(unsigned long arg) return -EFAULT; } +static int set_fork_pid(unsigned long arg) +{ + int pid; + struct page_map_info * pmi = NULL; + void __user *buf = (void __user *)arg; + + if (!access_ok(buf, sizeof(int))) + goto fault; + if (copy_from_user(&pid, buf, sizeof(int))) + goto fault; + current->fork_pid = pid; + return 0; +fault: + return -EFAULT; +} + static long pin_memory_ioctl(struct file *file, unsigned cmd, unsigned long arg) { long ret = 0; if (_IOC_TYPE(cmd) != PIN_MEM_MAGIC) return -EINVAL; - if (_IOC_NR(cmd) > _REMAP_PIN_MEM_AREA) + if (_IOC_NR(cmd) > _SET_FORK_PID) return -EINVAL; switch (cmd) { @@ -155,6 +174,9 @@ static long pin_memory_ioctl(struct file *file, unsigned cmd, unsigned long arg) case REMAP_PIN_MEM_AREA: ret = pin_mem_remap(arg); break; + case SET_FORK_PID: + ret = set_fork_pid(arg); + break; default: return -EINVAL; } diff --git a/include/linux/pin_mem.h b/include/linux/pin_mem.h index 0ca44ac..4162043 100644 --- a/include/linux/pin_mem.h +++ b/include/linux/pin_mem.h @@ -58,5 +58,11 @@ extern vm_fault_t do_anon_huge_page_remap(struct vm_area_struct *vma, unsigned l #endif extern void init_reserve_page_map(unsigned long map_addr, unsigned long map_size); +#ifdef CONFIG_PID_RECOVER +extern bool is_need_reserve_pids(void); +extern void reserve_pids(struct idr *idr, int pid_max); +extern void free_reserved_pid(struct idr *idr, int pid); +#endif + #endif /* CONFIG_PIN_MEMORY */ #endif /* _LINUX_PIN_MEMORY_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 716ad1d..f6b1560 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1281,6 +1281,10 @@ struct task_struct { unsigned long prev_lowest_stack; #endif +#ifdef CONFIG_PID_RECOVER + int fork_pid; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/init/init_task.c b/init/init_task.c index 9e5cbe5..40cd98f 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -181,6 +181,9 @@ struct task_struct init_task #ifdef CONFIG_SECURITY .security = NULL, #endif +#ifdef CONFIG_PID_RECOVER + .fork_pid = 0, +#endif }; EXPORT_SYMBOL(init_task); diff --git a/kernel/pid.c b/kernel/pid.c index 2278e24..dc93f7a 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -42,6 +42,9 @@ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> +#ifdef CONFIG_PID_RECOVER +#include <linux/pin_mem.h> +#endif struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), @@ -208,8 +211,26 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); - +#ifdef CONFIG_PID_RECOVER + if (current->fork_pid) { + int pid_min; + /* Try to free the reserved fork_pid, and then use it to alloc pid. */ + free_reserved_pid(&tmp->idr, current->fork_pid); + pid_min = current->fork_pid; + current->fork_pid = 0; + nr = idr_alloc(&tmp->idr, NULL, pid_min, + pid_min + 1, + GFP_ATOMIC); + /* + * If ENOSPC is returned it means that the PID is + * alreay in use. Return EEXIST in that case. + */ + if (nr == -ENOSPC) + nr = -EEXIST; + } else if (tid) { +#else if (tid) { +#endif nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* @@ -577,4 +598,8 @@ void __init pid_idr_init(void) init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); +#ifdef CONFIG_PID_RECOVER + if (is_need_reserve_pids()) + reserve_pids(&init_pid_ns.idr, pid_max); +#endif } diff --git a/mm/Kconfig b/mm/Kconfig index c2dd088..847e8e4 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -745,4 +745,11 @@ config PIN_MEMORY help Say y here to enable the pin memory feature for checkpoint and restore. + +config PID_RECOVER + bool "Support for pid recover" + depends on PIN_MEMORY + help + Say y here to enable the pid recover feature for checkpoint + and restore. endmenu diff --git a/mm/pin_mem.c b/mm/pin_mem.c index ca3f23a..9426874 100644 --- a/mm/pin_mem.c +++ b/mm/pin_mem.c @@ -688,4 +688,55 @@ vm_fault_t reserve_kernel_space_mem(unsigned long start_addr, unsigned int pages } EXPORT_SYMBOL_GPL(reserve_kernel_space_mem); +#ifdef CONFIG_PID_RECOVER +struct idr *reserve_idr; + +/* test if there exist pin memory tasks */ +bool is_need_reserve_pids(void) +{ + return (pin_pid_num > 0); +} + +void free_reserved_pid(struct idr *idr, int pid) +{ + unsigned int index; + struct page_map_info *pmi; + + if (!max_pin_pid_num || idr != reserve_idr) + return; + + for (index = 0; index < pin_pid_num; index++) { + pmi = &(user_space_reserve_start[index]); + if (pmi->pid == pid && pmi->pid_reserved) { + idr_remove(idr, pid); + return; + } + } +} + +/* reserve pids for check point tasks which pinned memory */ +void reserve_pids(struct idr *idr, int pid_max) +{ + int alloc_pid; + unsigned int index; + struct page_map_info *pmi; + + if (!max_pin_pid_num) + return; + reserve_idr = idr; + for (index = 0; index < pin_pid_num; index++) { + pmi = &(user_space_reserve_start[index]); + pmi->pid_reserved = true; + alloc_pid = idr_alloc(idr, NULL, pmi->pid, pid_max, GFP_ATOMIC); + if (alloc_pid != pmi->pid) { + if (alloc_pid > 0) + idr_remove(idr, alloc_pid); + pr_warn("Reserve pid (%d) fail, real pid is %d.\n", alloc_pid, pmi->pid); + pmi->pid_reserved = false; + continue; + } + } + return; +} +#endif /* CONFIG_PID_RECOVER */ #endif /* CONFIG_PIN_MEMORY */ -- 1.8.3.1

2 1

[PATCH v1 0/1 openEuler-1.0-LTS] mm: add pin memory method for checkpoint add restore
by hejingxian 31 Dec '20

31 Dec '20

From: hejingxian <hejingxian(a)huawei.com> Date: Thu, 10 Dec 2020 20:31:15 +0800 Subject: [PATCH v1 0/1 openEuler-1.0-LTS] mm: add pin memory method for checkpoint add restore We can use the checkpoint and restore in userspace(criu) method to dump and restore tasks when updating the kernel. Currently, criu needs dump all memory data of tasks to files. When the memory size is very large(larger than 1G), the cost time of the dumping data will be very long(more than 1 min). We can pin the memory data of tasks and collect the corresponding physical pages mapping info in checkpoint process, and remap the physical pages to restore tasks after kernel is updated. The pin memory area info is saved in the reserve memblock named nvwa_res_first, which can keep usable in the kernel update process. The pin memory driver provides the following ioctl command for criu: 1) SET_PIN_MEM_AREA: set pin memory area, which can be remap to the restore task. 2) CLEAR_PIN_MEM_AREA: clear the pin memory area info, which enable user reset the pin data. 3) REMAP_PIN_MEM_AREA: remap the pages of the pin memory to the restore task. Signed-off-by: Jingxian He <hejingxian(a)huawei.com> --- arch/arm64/kernel/setup.c | 7 + arch/arm64/mm/init.c | 62 +++- drivers/char/Kconfig | 7 + drivers/char/Makefile | 1 + drivers/char/pin_memory.c | 198 +++++++++++++ include/linux/crash_core.h | 5 + include/linux/pin_mem.h | 62 ++++ kernel/crash_core.c | 11 + mm/Kconfig | 6 + mm/Makefile | 1 + mm/huge_memory.c | 61 ++++ mm/memory.c | 68 +++++ mm/pin_mem.c | 691 +++++++++++++++++++++++++++++++++++++++++++++ 13 files changed, 1179 insertions(+), 1 deletion(-) create mode 100644 drivers/char/pin_memory.c create mode 100644 include/linux/pin_mem.h create mode 100644 mm/pin_mem.c diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 56f6645..40751ed 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -50,6 +50,9 @@ #include <asm/efi.h> #include <asm/xen/hypervisor.h> #include <asm/mmu_context.h> +#ifdef CONFIG_PIN_MEMORY +#include <linux/pin_memory.h> +#endif static int num_standard_resources; static struct resource *standard_resources; @@ -243,6 +246,10 @@ static void __init request_standard_resources(void) crashk_res.end <= res->end) request_resource(res, &crashk_res); #endif +#ifdef CONFIG_PIN_MEMORY + if (pin_memory_resource.end) + insert_resource(&iomem_resource, &pin_memory_resource); +#endif } } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index b65dffd..dee3192 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -41,7 +41,9 @@ #include <linux/sizes.h> #include <asm/tlb.h> #include <asm/alternative.h> - +#ifdef CONFIG_PIN_MEMORY +#include <linux/pin_memory.h> +#endif #define ARM64_ZONE_DMA_BITS 30 /* @@ -68,6 +70,16 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init; static phys_addr_t arm64_dma32_phys_limit __ro_after_init; +#ifdef CONFIG_PIN_MEMORY +struct resource pin_memory_resource = { + .name = "Pin memory maps", + .start = 0, + .end = 0, + .flags = IORESOURCE_MEM, + .desc = IORES_DESC_PIN_MEM_MAPS +}; +#endif + #ifdef CONFIG_KEXEC_CORE /* * reserve_crashkernel() - reserves memory for crash kernel @@ -129,6 +141,47 @@ static void __init reserve_crashkernel(void) } #endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_PIN_MEMORY +static void __init reserve_pin_memory_res(void) +{ + unsigned long long mem_start, mem_len; + int ret; + + ret = parse_pin_memory(boot_command_line, memblock_phys_mem_size(), + &mem_len, &mem_start); + if (ret || !mem_len) + return; + + mem_len = PAGE_ALIGN(mem_len); + + if (!memblock_is_region_memory(mem_start, mem_len)) { + pr_warn("cannot reserve for pin memory: region is not memory!\n"); + return; + } + + if (memblock_is_region_reserved(mem_start, mem_len)) { + pr_warn("cannot reserve for pin memory: region overlaps reserved memory!\n"); + return; + } + + if (!IS_ALIGNED(mem_start, SZ_2M)) { + pr_warn("cannot reserve for pin memory: base address is not 2MB aligned\n"); + return; + } + + memblock_reserve(mem_start, mem_len); + pr_debug("pin memory resource reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + mem_start, mem_start + mem_len, mem_len >> 20); + + pin_memory_resource.start = mem_start; + pin_memory_resource.end = mem_start + mem_len - 1; +} +#else +static void __init reserve_pin_memory_res(void) +{ +} +#endif /* CONFIG_PIN_MEMORY */ + #ifdef CONFIG_CRASH_DUMP static int __init early_init_dt_scan_elfcorehdr(unsigned long node, const char *uname, int depth, void *data) @@ -452,6 +505,8 @@ void __init arm64_memblock_init(void) reserve_crashkernel(); + reserve_pin_memory_res(); + reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; @@ -573,6 +628,11 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ memblock_free_all(); +#ifdef CONFIG_PIN_MEMORY + /* pre alloc the pages for pin memory */ + init_reserve_page_map((unsigned long)pin_memory_resource.start, + (unsigned long)(pin_memory_resource.end - pin_memory_resource.start)); +#endif mem_init_print_info(NULL); /* diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index 26956c0..73af2f0 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -560,3 +560,10 @@ config RANDOM_TRUST_BOOTLOADER booloader is trustworthy so it will be added to the kernel's entropy pool. Otherwise, say N here so it will be regarded as device input that only mixes the entropy pool. + +config PIN_MEMORY_DEV + bool "/dev/pinmem character device" + depends PIN_MEMORY + default n + help + pin memory driver diff --git a/drivers/char/Makefile b/drivers/char/Makefile index 7c5ea6f..1941642 100644 --- a/drivers/char/Makefile +++ b/drivers/char/Makefile @@ -52,3 +52,4 @@ js-rtc-y = rtc.o obj-$(CONFIG_XILLYBUS) += xillybus/ obj-$(CONFIG_POWERNV_OP_PANEL) += powernv-op-panel.o obj-$(CONFIG_ADI) += adi.o +obj-$(CONFIG_PIN_MEMORY_DEV) += pin_memory.o diff --git a/drivers/char/pin_memory.c b/drivers/char/pin_memory.c new file mode 100644 index 00000000..a0464e1 --- /dev/null +++ b/drivers/char/pin_memory.c @@ -0,0 +1,198 @@ +/* + * Copyright @ Huawei Technologies Co., Ltd. 2020-2020. ALL rights reserved. + * Description: Euler pin memory driver + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/kprobes.h> +#include <linux/spinlock.h> +#include <linux/workqueue.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/miscdevice.h> +#include <linux/fs.h> +#include <linux/mm_types.h> +#include <asm/processor.h> +#include <uapi/asm-generic/ioctl.h> +#include <uapi/asm-generic/mman-common.h> +#include <uapi/asm/setup.h> +#include <linux/pin_mem.h> +#include <linux/sched/mm.h> + +#define MAX_PIN_MEM_AREA_NUM 16 +struct _pin_mem_area { + unsigned long virt_start; + unsigned long virt_end; +}; + +struct pin_mem_area_set { + unsigned int pid; + unsigned int area_num; + struct _pin_mem_area mem_area[MAX_PIN_MEM_AREA_NUM]; +}; + +#define PIN_MEM_MAGIC 0x59 +#define _SET_PIN_MEM_AREA 1 +#define _CLEAR_PIN_MEM_AREA 2 +#define _REMAP_PIN_MEM_AREA 3 +#define SET_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _SET_PIN_MEM_AREA, struct pin_mem_area_set) +#define CLEAR_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _CLEAR_PIN_MEM_AREA, int) +#define REMAP_PIN_MEM_AREA _IOW(PIN_MEM_MAGIC, _REMAP_PIN_MEM_AREA, int) + +static int set_pin_mem(struct pin_mem_area_set *pmas) +{ + int i; + int ret = 0; + struct _pin_mem_area *pma; + struct mm_struct *mm; + struct task_struct *task; + struct pid *pid_s; + + pid_s = find_get_pid(pmas->pid); + if (!pid_s) { + pr_warn("Get pid struct fail:%d.\n", pmas->pid); + goto fail; + } + rcu_read_lock(); + task = pid_task(pid_s, PIDTYPE_PID); + if (!task) { + pr_warn("Get task struct fail:%d.\n", pmas->pid); + goto fail; + } + mm = get_task_mm(task); + for (i = 0; i < pmas->area_num; i++) { + pma = &(pmas->mem_area[i]); + ret = pin_mem_area(task, mm, pma->virt_start, pma->virt_end); + if (ret) { + mmput(mm); + goto fail; + } + } + mmput(mm); + rcu_read_unlock(); + return ret; + +fail: + rcu_read_unlock(); + return -EFAULT; +} + +static int set_pin_mem_area(unsigned long arg) +{ + struct pin_mem_area_set pmas; + void __user *buf = (void __user *)arg; + + if (!access_ok(buf, sizeof(pmas))) + return -EFAULT; + if (copy_from_user(&pmas, buf, sizeof(pmas))) + return -EINVAL; + if (pmas.area_num > MAX_PIN_MEM_AREA_NUM) { + pr_warn("Input area_num is too large.\n"); + return -EINVAL; + } + + return set_pin_mem(&pmas); +} + +static int pin_mem_remap(unsigned long arg) +{ + int pid; + struct task_struct *task; + struct mm_struct *mm; + vm_fault_t ret; + void __user *buf = (void __user *)arg; + struct pid *pid_s; + + if (!access_ok(buf, sizeof(int))) + return -EINVAL; + if (copy_from_user(&pid, buf, sizeof(int))) + return -EINVAL; + + pid_s = find_get_pid(pid); + if (!pid_s) { + pr_warn("Get pid struct fail:%d.\n", pid); + return -EINVAL; + } + rcu_read_lock(); + task = pid_task(pid_s, PIDTYPE_PID); + if (!task) { + pr_warn("Get task struct fail:%d.\n", pid); + goto fault; + } + mm = get_task_mm(task); + ret = do_mem_remap(pid, mm); + if (ret) { + pr_warn("Handle pin memory remap fail.\n"); + mmput(mm); + goto fault; + } + mmput(mm); + rcu_read_unlock(); + return 0; + +fault: + rcu_read_unlock(); + return -EFAULT; +} + +static long pin_memory_ioctl(struct file *file, unsigned cmd, unsigned long arg) +{ + long ret = 0; + + if (_IOC_TYPE(cmd) != PIN_MEM_MAGIC) + return -EINVAL; + if (_IOC_NR(cmd) > _REMAP_PIN_MEM_AREA) + return -EINVAL; + + switch (cmd) { + case SET_PIN_MEM_AREA: + ret = set_pin_mem_area(arg); + break; + case CLEAR_PIN_MEM_AREA: + clear_pin_memory_record(); + break; + case REMAP_PIN_MEM_AREA: + ret = pin_mem_remap(arg); + break; + default: + return -EINVAL; + } + return ret; +} + +static const struct file_operations pin_memory_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = pin_memory_ioctl, + .compat_ioctl = pin_memory_ioctl, +}; + +static struct miscdevice pin_memory_miscdev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "pinmem", + .fops = &pin_memory_fops, +}; + +static int pin_memory_init(void) +{ + int err = misc_register(&pin_memory_miscdev); + if (!err) { + pr_info("pin_memory init\n"); + } else { + pr_warn("pin_memory init failed!\n"); + } + return err; +} + +static void pin_memory_exit(void) +{ + misc_deregister(&pin_memory_miscdev); + pr_info("pin_memory ko exists!\n"); +} + +module_init(pin_memory_init); +module_exit(pin_memory_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Euler"); +MODULE_DESCRIPTION("pin memory"); diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 525510a..5baf40d 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -75,4 +75,9 @@ int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, int parse_crashkernel_low(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); +#ifdef CONFIG_PIN_MEMORY +int __init parse_pin_memory(char *cmdline, unsigned long long system_ram, + unsigned long long *pin_size, unsigned long long *pin_base); +#endif + #endif /* LINUX_CRASH_CORE_H */ diff --git a/include/linux/pin_mem.h b/include/linux/pin_mem.h new file mode 100644 index 00000000..0ca44ac --- /dev/null +++ b/include/linux/pin_mem.h @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2020. Huawei Technologies Co., Ltd. All rights reserved. + * Provide the pin memory method for check point and restore task. + */ +#ifndef _LINUX_PIN_MEMORY_H +#define _LINUX_PIN_MEMORY_H + +#ifdef CONFIG_PIN_MEMORY +#include <linux/errno.h> +#include <linux/kabi.h> +#include <linux/mm_types.h> +#include <linux/err.h> +#ifdef CONFIG_ARM64 +#include <linux/ioport.h> +#endif + +#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) + +#define COLLECT_PAGES_FINISH 0 +#define COLLECT_PAGES_NEED_CONTINUE 1 +#define COLLECT_PAGES_FAIL -1 + +#define COMPOUND_PAD_MASK 0xffffffff +#define COMPOUND_PAD_START 0x88 +#define COMPOUND_PAD_DELTA 0x40 +#define LIST_POISON4 0xdead000000000400 + +#define next_pme(pme) ((unsigned long *)(pme + 1) + pme->nr_pages) + +struct page_map_entry { + unsigned long virt_addr; + unsigned int nr_pages; + unsigned int is_huge_page; + unsigned long phy_addr_array[0]; +}; + +struct page_map_info { + int pid; + int pid_reserved; + unsigned int entry_num; + struct page_map_entry *pme; +}; + +extern struct page_map_info *get_page_map_info(int pid); +extern struct page_map_info *create_page_map_info(int pid); +extern vm_fault_t do_mem_remap(int pid, struct mm_struct *mm); +extern vm_fault_t do_anon_page_remap(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, struct page *page); +extern void clear_pin_memory_record(void); +extern int pin_mem_area(struct task_struct *task, struct mm_struct *mm, + unsigned long start_addr, unsigned long end_addr); +extern vm_fault_t do_anon_huge_page_remap(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, struct page *page); + +/* reserve space for pin memory*/ +#ifdef CONFIG_ARM64 +extern struct resource pin_memory_resource; +#endif +extern void init_reserve_page_map(unsigned long map_addr, unsigned long map_size); + +#endif /* CONFIG_PIN_MEMORY */ +#endif /* _LINUX_PIN_MEMORY_H */ diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 9f1557b..7512696 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -292,6 +292,17 @@ int __init parse_crashkernel_low(char *cmdline, "crashkernel=", suffix_tbl[SUFFIX_LOW]); } +#ifdef CONFIG_PIN_MEMORY +int __init parse_pin_memory(char *cmdline, + unsigned long long system_ram, + unsigned long long *pin_size, + unsigned long long *pin_base) +{ + return __parse_crashkernel(cmdline, system_ram, pin_size, pin_base, + "pinmemory=", NULL); +} +#endif + Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len) { diff --git a/mm/Kconfig b/mm/Kconfig index ab80933..c2dd088 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -739,4 +739,10 @@ config ARCH_HAS_HUGEPD config MAPPING_DIRTY_HELPERS bool +config PIN_MEMORY + bool "Support for pin memory" + depends on CHECKPOINT_RESTORE + help + Say y here to enable the pin memory feature for checkpoint + and restore. endmenu diff --git a/mm/Makefile b/mm/Makefile index 1937cc2..7e1984e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -108,3 +108,4 @@ obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o +obj-$(CONFIG_PIN_MEMORY) += pin_mem.o diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a880932..93dc582 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3083,4 +3083,65 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } + +#ifdef CONFIG_PIN_MEMORY +vm_fault_t do_anon_huge_page_remap(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, struct page *page) +{ + gfp_t gfp; + pgtable_t pgtable; + spinlock_t *ptl; + pmd_t entry; + vm_fault_t ret = 0; + struct mem_cgroup *memcg; + + if (unlikely(anon_vma_prepare(vma))) + return VM_FAULT_OOM; + if (unlikely(khugepaged_enter(vma, vma->vm_flags))) + return VM_FAULT_OOM; + gfp = alloc_hugepage_direct_gfpmask(vma); + prep_transhuge_page(page); + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) { + put_page(page); + count_vm_event(THP_FAULT_FALLBACK); + return VM_FAULT_FALLBACK; + } + pgtable = pte_alloc_one(vma->vm_mm, address); + if (unlikely(!pgtable)) { + ret = VM_FAULT_OOM; + goto release; + } + __SetPageUptodate(page); + ptl = pmd_lock(vma->vm_mm, pmd); + if (unlikely(!pmd_none(*pmd))) { + goto unlock_release; + } else { + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock_release; + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + page_add_new_anon_rmap(page, vma, address, true); + mem_cgroup_commit_charge(page, memcg, false, true); + lru_cache_add_active_or_unevictable(page, vma); + pgtable_trans_huge_deposit(vma->vm_mm, pmd, pgtable); + set_pmd_at(vma->vm_mm, address, pmd, entry); + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm_inc_nr_ptes(vma->vm_mm); + spin_unlock(ptl); + count_vm_event(THP_FAULT_ALLOC); + } + + return 0; +unlock_release: + spin_unlock(ptl); +release: + if (pgtable) + pte_free(vma->vm_mm, pgtable); + mem_cgroup_cancel_charge(page, memcg, true); + put_page(page); + return ret; +} +#endif + #endif diff --git a/mm/memory.c b/mm/memory.c index 45442d9..dd416fd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4799,4 +4799,72 @@ void ptlock_free(struct page *page) { kmem_cache_free(page_ptl_cachep, page->ptl); } + +#ifdef CONFIG_PIN_MEMORY +vm_fault_t do_anon_page_remap(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, struct page *page) +{ + struct mem_cgroup *memcg; + pte_t entry; + spinlock_t *ptl; + pte_t *pte; + vm_fault_t ret = 0; + + if (pte_alloc(vma->vm_mm, pmd, address)) + return VM_FAULT_OOM; + + /* See the comment in pte_alloc_one_map() */ + if (unlikely(pmd_trans_unstable(pmd))) + return 0; + + /* Allocate our own private page. */ + if (unlikely(anon_vma_prepare(vma))) + goto oom; + + if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg, + false)) + goto oom_free_page; + + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceeding stores to the page contents become visible before + * the set_pte_at() write. + */ + __SetPageUptodate(page); + + entry = mk_pte(page, vma->vm_page_prot); + if (vma->vm_flags & VM_WRITE) + entry = pte_mkwrite(pte_mkdirty(entry)); + pte = pte_offset_map_lock(vma->vm_mm, pmd, address, + &ptl); + if (!pte_none(*pte)) { + ret = VM_FAULT_FALLBACK; + goto release; + } + + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); + page_add_new_anon_rmap(page, vma, address, false); + mem_cgroup_commit_charge(page, memcg, false, false); + lru_cache_add_active_or_unevictable(page, vma); + + set_pte_at(vma->vm_mm, address, pte, entry); + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, address, pte); +unlock: + pte_unmap_unlock(pte, ptl); + return ret; +release: + mem_cgroup_cancel_charge(page, memcg, false); + put_page(page); + goto unlock; +oom_free_page: + put_page(page); +oom: + return VM_FAULT_OOM; +} +#endif + #endif diff --git a/mm/pin_mem.c b/mm/pin_mem.c new file mode 100644 index 00000000..ca3f23a --- /dev/null +++ b/mm/pin_mem.c @@ -0,0 +1,691 @@ +/* + * Copyright (C) 2020. Huawei Technologies Co., Ltd. All rights reserved. + * Provide the pin memory method for check point and restore task. + */ +#ifdef CONFIG_PIN_MEMORY +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/sched/cputime.h> +#include <linux/tick.h> +#include <asm/uaccess.h> +#include <linux/mm.h> +#include <linux/pin_mem.h> +#include <linux/idr.h> +#include <linux/page-isolation.h> +#include <linux/sched/mm.h> +#include <linux/ctype.h> + +#define MAX_PIN_PID_NUM 128 +static DEFINE_SPINLOCK(page_map_entry_lock); + +unsigned int pin_pid_num; +static unsigned int *pin_pid_num_addr; +static unsigned long __page_map_entry_start; +static unsigned long page_map_entry_end; +static struct page_map_info *user_space_reserve_start; +static struct page_map_entry *page_map_entry_start; +unsigned int max_pin_pid_num __read_mostly; + +static int __init setup_max_pin_pid_num(char *str) +{ + int ret = 1; + + if (!str) + goto out; + + ret = kstrtouint(str, 10, &max_pin_pid_num); +out: + if (ret) { + pr_warn("Unable to parse max pin pid num.\n"); + } else { + if (max_pin_pid_num > MAX_PIN_PID_NUM) { + max_pin_pid_num = 0; + pr_warn("Input max_pin_pid_num is too large.\n"); + } + } + return ret; +} +early_param("max_pin_pid_num", setup_max_pin_pid_num); + +struct page_map_info *create_page_map_info(int pid) +{ + struct page_map_info *new; + + if (!user_space_reserve_start) + return NULL; + + if (pin_pid_num >= max_pin_pid_num) { + pr_warn("Pin pid num too large than max_pin_pid_num, fail create: %d!", pid); + return NULL; + } + new = (struct page_map_info *)(user_space_reserve_start + pin_pid_num); + new->pid = pid; + new->pme = NULL; + new->entry_num = 0; + new->pid_reserved = false; + (*pin_pid_num_addr)++; + pin_pid_num++; + return new; +} +EXPORT_SYMBOL_GPL(create_page_map_info); + +struct page_map_info *get_page_map_info(int pid) +{ + int i; + + if (!user_space_reserve_start) + return NULL; + + for (i = 0; i < pin_pid_num; i++) { + if (user_space_reserve_start[i].pid == pid) { + return &(user_space_reserve_start[i]); + } + } + return NULL; +} +EXPORT_SYMBOL_GPL(get_page_map_info); + +static struct page *find_head_page(struct page *page) +{ + struct page *p = page; + + while (!PageBuddy(p)) { + if (PageLRU(p)) + return NULL; + p--; + } + return p; +} + +static void spilt_page_area_left(struct zone *zone, struct free_area *area, struct page *page, + unsigned long size, int order) +{ + unsigned long cur_size = 1 << order; + unsigned long total_size = 0; + struct page *tmp; + unsigned long tmp_size = size; + + while (size && cur_size > size) { + cur_size >>= 1; + order--; + area--; + if (cur_size <= size) { + list_add(&page[total_size].lru, &area->free_list[MIGRATE_MOVABLE]); + atomic_set(&(page[total_size]._mapcount), PAGE_BUDDY_MAPCOUNT_VALUE); + set_page_private(&page[total_size], order); + set_pageblock_migratetype(&page[total_size], MIGRATE_MOVABLE); + area->nr_free++; + total_size += cur_size; + size -= cur_size; + } + } +} + +static void spilt_page_area_right(struct zone *zone, struct free_area *area, struct page *page, + unsigned long size, int order) +{ + unsigned long cur_size = 1 << order; + struct page *right_page, *head_page; + unsigned long tmp_size = size; + + right_page = page + size; + while (size && cur_size > size) { + cur_size >>= 1; + order--; + area--; + if (cur_size <= size) { + head_page = right_page - cur_size; + list_add(&head_page->lru, &area->free_list[MIGRATE_MOVABLE]); + atomic_set(&(head_page->_mapcount), PAGE_BUDDY_MAPCOUNT_VALUE); + set_page_private(head_page, order); + set_pageblock_migratetype(head_page, MIGRATE_MOVABLE); + area->nr_free++; + size -= cur_size; + right_page = head_page; + } + } +} + +void reserve_page_from_buddy(unsigned long nr_pages, struct page *page) +{ + unsigned int current_order; + struct page *page_end; + struct free_area *area; + struct zone *zone; + struct page *head_page; + + head_page = find_head_page(page); + if (!head_page) { + pr_warn("Find page head fail."); + return; + } + current_order = head_page->private; + page_end = head_page + (1 << current_order); + zone = page_zone(head_page); + area = &(zone->free_area[current_order]); + list_del(&head_page->lru); + atomic_set(&head_page->_mapcount, -1); + set_page_private(head_page, 0); + area->nr_free--; + if (head_page != page) + spilt_page_area_left(zone, area, head_page, + (unsigned long)(page - head_page), current_order); + page = page + nr_pages; + if (page < page_end) { + spilt_page_area_right(zone, area, page, + (unsigned long)(page_end - page), current_order); + } else if (page > page_end) { + pr_warn("Find page end smaller than page."); + } +} + +static inline void reserve_user_normal_pages(struct page *page) +{ + if (!atomic_read(&page->_refcount)) { + atomic_inc(&page->_refcount); + reserve_page_from_buddy(1, page); + } else { + pr_warn("Page %pK refcount %d large than zero, no need reserve.\n", + page, page->_refcount.counter); + } +} + +static void init_huge_pmd_pages(struct page *head_page) +{ + int i = 0; + struct page *page = head_page; + unsigned long *temp; + unsigned long compound_pad = COMPOUND_PAD_START; + + __set_bit(PG_head, &page->flags); + __set_bit(PG_active, &page->flags); + atomic_set(&page->_refcount, 1); + page++; + i++; + page->compound_head = (unsigned long)head_page + 1; + page->_compound_pad_2 = (unsigned long)head_page & COMPOUND_PAD_MASK; + temp = (unsigned long *)(&(page->_compound_pad_2)); + temp[1] = LIST_POISON4; + page->compound_dtor = HUGETLB_PAGE_DTOR + 1; + page->compound_order = HPAGE_PMD_ORDER; + page++; + i++; + page->compound_head = (unsigned long)head_page + 1; + page->_compound_pad_2 = (unsigned long)head_page + compound_pad; + i++; + INIT_LIST_HEAD(&(page->deferred_list)); + for (; i < HPAGE_PMD_NR; i++) { + page = head_page + i; + page->compound_head = (unsigned long)head_page + 1; + compound_pad += COMPOUND_PAD_DELTA; + page->_compound_pad_2 = (unsigned long)head_page + compound_pad; + temp = (unsigned long *)(&(page->_compound_pad_2)); + temp[1] = LIST_POISON4; + } +} + +static void reserve_user_huge_pmd_pages(struct page *page) +{ + struct page *head_page; + + if (!atomic_read(&page->_refcount)) { + atomic_inc(&page->_refcount); + head_page = find_head_page(page); + reserve_page_from_buddy((1 << HPAGE_PMD_ORDER), page); + init_huge_pmd_pages(page); + } else { + pr_warn("Page %pK refcount %d large than zero, no need reserve.\n", + page, page->_refcount.counter); + } +} + +static void reserve_user_space_map_pages(void) +{ + struct page_map_info *pmi; + struct page_map_entry *pme; + unsigned int i, j, index; + struct page *page; + unsigned long flags; + unsigned long page_size; + int err = 0; + unsigned long phy_addr; + + if (!user_space_reserve_start) + return; + spin_lock_irqsave(&page_map_entry_lock, flags); + for (index = 0; index < pin_pid_num; index++) { + pmi = &(user_space_reserve_start[index]); + pme = pmi->pme; + + for (i = 0; i < pmi->entry_num; i++) { + err = 0; + for (j = 0; j < pme->nr_pages; j++) { + phy_addr = pme->phy_addr_array[j]; + if (!phy_addr) + continue; + page = phys_to_page(phy_addr); + if (atomic_read(&page->_refcount)) { + pme->phy_addr_array[j] = 0; + page_size = pme->is_huge_page ? HPAGE_PMD_SIZE : PAGE_SIZE; + continue; + } + if (!pme->is_huge_page) { + reserve_user_normal_pages(page); + } else { + reserve_user_huge_pmd_pages(page); + } + } + pme = (struct page_map_entry *)next_pme(pme); + if (err) + err_phy_num++; + } + page_size = pme->is_huge_page ? HPAGE_PMD_SIZE : PAGE_SIZE; + } + spin_unlock(&page_map_entry_lock); +} + + +/* The whole page map entry collect process must be Sequentially. + The user_space_reserve_start points to the first page map info for + the first dump task. And the page_map_entry_start points to + the first page map entry of the first dump vma. */ +static void init_page_map_info(unsigned int *map_addr) +{ + unsigned long map_len = pin_memory_resource.end - pin_memory_resource.start; + + if (user_space_reserve_start || !max_pin_pid_num) + return; + pin_pid_num = *map_addr; + pin_pid_num_addr = map_addr; + user_space_reserve_start = + (struct kup_page_map_info *)(map_addr + 1); + page_map_entry_start = + (struct page_map_entry *)(user_space_reserve_start + max_pin_pid_num); + page_map_entry_end = (unsigned long)map_addr + map_len; + if (pin_pid_num > 0) + reserve_user_space_map_pages(); +} + +int collect_pmd_huge_pages(struct task_struct *task, + unsigned long start_addr, unsigned long end_addr, struct page_map_entry *pme) +{ + long res; + int index = 0; + unsigned long start = start_addr; + struct page *temp_page; + + while (start < end_addr) { + temp_page = NULL; + res = get_user_pages_remote(task, task->mm, start, 1, + FOLL_TOUCH|FOLL_GET, &temp_page, NULL, NULL); + if (!res) { + pr_warn("Get huge page for addr(%lx) fail.", start); + return COLLECT_PAGES_FAIL; + } + if (PageHead(temp_page)) { + start += HPAGE_PMD_SIZE; + pme->phy_addr_array[index] = page_to_phys(temp_page); + index++; + } else { + pme->nr_pages = index; + atomic_dec(&((temp_page)->_refcount)); + return COLLECT_PAGES_NEED_CONTINUE; + } + } + pme->nr_pages = index; + return COLLECT_PAGES_FINISH; +} + +int collect_normal_pages(struct task_struct *task, + unsigned long start_addr, unsigned long end_addr, struct page_map_entry *pme) +{ + int res; + unsigned long next; + unsigned long i, nr_pages; + struct page *tmp_page; + unsigned long *phy_addr_array = pme->phy_addr_array; + struct page **page_array = (struct page **)pme->phy_addr_array; + + next = (start_addr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE; + next = (next > end_addr) ? end_addr : next; + pme->nr_pages = 0; + while (start_addr < next) { + nr_pages = (next - start_addr) / PAGE_SIZE; + res = get_user_pages_remote(task, task->mm, start_addr, 1, + FOLL_TOUCH|FOLL_GET, &tmp_page, NULL, NULL); + if (!res) { + pr_warn("Get user pages of %lx fail.\n", start_addr); + return COLLECT_PAGES_FAIL; + } + if (PageHead(tmp_page)) { + atomic_dec(&(tmp_page->_refcount)); + return COLLECT_PAGES_NEED_CONTINUE; + } + atomic_dec(&(tmp_page->_refcount)); + if (PageTail(tmp_page)) { + start_addr = next; + pme->virt_addr = start_addr; + next = (next + HPAGE_PMD_SIZE) > end_addr ? end_addr : (next + HPAGE_PMD_SIZE); + continue; + } + res = get_user_pages_remote(task, task->mm, start_addr, nr_pages, + FOLL_TOUCH|FOLL_GET, page_array, NULL, NULL); + if (!res) { + pr_warn("Get user pages of %lx fail.\n", start_addr); + return COLLECT_PAGES_FAIL; + } + for (i = 0; i < nr_pages; i++) { + phy_addr_array[i] = page_to_phys(page_array[i]); + } + pme->nr_pages += nr_pages; + page_array += nr_pages; + phy_addr_array += nr_pages; + start_addr = next; + next = (next + HPAGE_PMD_SIZE) > end_addr ? end_addr : (next + HPAGE_PMD_SIZE); + } + return COLLECT_PAGES_FINISH; +} + +/* Users make sure that the pin memory belongs to anonymous vma. */ +int pin_mem_area(struct task_struct *task, struct mm_struct *mm, + unsigned long start_addr, unsigned long end_addr) +{ + int pid, ret; + int is_huge_page = false; + unsigned int page_size; + unsigned long nr_pages, flags; + struct page_map_entry *pme; + struct page_map_info *pmi; + struct vm_area_struct *vma; + unsigned long i; + struct page *tmp_page; + + if (!page_map_entry_start + || !task || !mm + || start_addr >= end_addr) + return -EFAULT; + + pid = task->pid; + spin_lock_irqsave(&page_map_entry_lock, flags); + nr_pages = ((end_addr - start_addr) / PAGE_SIZE); + if ((unsigned long)page_map_entry_start + nr_pages * sizeof(struct page *) + >= page_map_entry_end) { + pr_warn("Page map entry use up!\n"); + ret = -EFAULT; + goto finish; + } + vma = find_extend_vma(mm, start_addr); + if (!vma) { + pr_warn("Find no match vma!\n"); + ret = -EFAULT; + goto finish; + } + if (start_addr == (start_addr & HPAGE_PMD_MASK) && + transparent_hugepage_enabled(vma)) { + page_size = HPAGE_PMD_SIZE; + is_huge_page = true; + } else { + page_size = PAGE_SIZE; + } + pme = page_map_entry_start; + pme->virt_addr = start_addr; + pme->is_huge_page = is_huge_page; + memset(pme->phy_addr_array, 0, nr_pages * sizeof(unsigned long)); + down_write(&mm->mmap_sem); + if (!is_huge_page) { + ret = collect_normal_pages(task, start_addr, end_addr, pme); + if (!pme->nr_pages) { + if (ret == COLLECT_PAGES_FINISH) { + ret = 0; + up_write(&mm->mmap_sem); + goto finish; + } + pme->is_huge_page = true; + page_size = HPAGE_PMD_SIZE; + ret = collect_pmd_huge_pages(task, pme->virt_addr, end_addr, pme); + } + } else { + ret = collect_pmd_huge_pages(task, start_addr, end_addr, pme); + if (!pme->nr_pages) { + if (ret == COLLECT_PAGES_FINISH) { + ret = 0; + up_write(&mm->mmap_sem); + goto finish; + } + pme->is_huge_page = false; + page_size = PAGE_SIZE; + ret = collect_normal_pages(task, pme->virt_addr, end_addr, pme); + } + } + up_write(&mm->mmap_sem); + if (ret == COLLECT_PAGES_FAIL) { + ret = -EFAULT; + goto finish; + } + + /* check for zero pages */ + for (i = 0; i < pme->nr_pages; i++) { + tmp_page = phys_to_page(pme->phy_addr_array[i]); + if (!pme->is_huge_page) { + if (page_to_pfn(tmp_page) == my_zero_pfn(pme->virt_addr + i * PAGE_SIZE)) + pme->phy_addr_array[i] = 0; + } else if (is_huge_zero_page(tmp_page)) + pme->phy_addr_array[i] = 0; + } + + page_map_entry_start = (struct page_map_entry *)(next_pme(pme)); + pmi = get_page_map_info(pid); + if (!pmi) + pmi = create_page_map_info(pid); + if (!pmi) { + pr_warn("Create page map info fail for pid: %d!\n", pid); + ret = -EFAULT; + goto finish; + } + if (!pmi->pme) + pmi->pme = pme; + pmi->entry_num++; + spin_unlock_irqrestore(&page_map_entry_lock, flags); + if (ret == COLLECT_PAGES_NEED_CONTINUE) { + ret = pin_mem_area(task, mm, pme->virt_addr + pme->nr_pages * page_size, end_addr); + } + return ret; +finish: + spin_unlock_irqrestore(&page_map_entry_lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(pin_mem_area); + +vm_fault_t remap_normal_pages(struct mm_struct *mm, struct vm_area_struct *vma, + struct page_map_entry *pme) +{ + int ret; + unsigned int j; + pgd_t *pgd; + p4d_t *p4d; + pmd_t *pmd; + pud_t *pud; + struct page *page; + unsigned long address; + unsigned long phy_addr; + + for (j = 0; j < pme->nr_pages; j++) { + address = pme->virt_addr + j * PAGE_SIZE; + phy_addr = pme->phy_addr_array[j]; + if (!phy_addr) + continue; + page = phys_to_page(phy_addr); + if (page->flags & (1 << PG_reserved)) + page->flags -= (1 << PG_reserved); + if (page_to_pfn(page) == my_zero_pfn(address)) { + pme->phy_addr_array[j] = 0; + continue; + } + page->mapping = NULL; + pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return VM_FAULT_OOM; + pmd = pmd_alloc(mm, pud, address); + if (!pmd) + return VM_FAULT_OOM; + ret = do_anon_page_remap(vma, address, pmd, page); + if (ret == VM_FAULT_OOM) + return ret; + } + return 0; +} + +vm_fault_t remap_huge_pmd_pages(struct mm_struct *mm, struct vm_area_struct *vma, + struct page_map_entry *pme) +{ + int ret; + unsigned int j; + pgd_t *pgd; + p4d_t *p4d; + pmd_t *pmd; + pud_t *pud; + struct page *page; + unsigned long address; + unsigned long phy_addr; + + for (j = 0; j < pme->nr_pages; j++) { + address = pme->virt_addr + j * HPAGE_PMD_SIZE; + phy_addr = pme->phy_addr_array[j]; + if (!phy_addr) + continue; + page = phys_to_page(phy_addr); + if (page->flags & (1 << PG_reserved)) + page->flags -= (1 << PG_reserved); + if (is_huge_zero_page(page)) { + pme->phy_addr_array[j] = 0; + continue; + } + pgd = pgd_offset(mm, address); + p4d = p4d_alloc(mm, pgd, address); + if (!p4d) + return VM_FAULT_OOM; + pud = pud_alloc(mm, p4d, address); + if (!pud) + return VM_FAULT_OOM; + pmd = pmd_alloc(mm, pud, address); + if (!pmd) + return VM_FAULT_OOM; + ret = do_anon_huge_page_remap(vma, address, pmd, page); + if (ret == VM_FAULT_OOM) + return ret; + } + return 0; +} + +vm_fault_t do_mem_remap(int pid, struct mm_struct *mm) +{ + unsigned int i = 0; + vm_fault_t ret = 0; + struct vm_area_struct *vma; + struct page_map_info *pmi; + struct page_map_entry *pme; + + pmi = get_page_map_info(pid); + if (!pmi) + return -EFAULT; + down_write(&mm->mmap_sem); + pme = pmi->pme; + vma = mm->mmap; + while ((i < pmi->entry_num) && (vma != NULL)) { + if (pme->virt_addr >= vma->vm_start && pme->virt_addr < vma->vm_end) { + i++; + if (!vma_is_anonymous(vma)) { + pme = (struct page_map_entry *)(next_pme(pme)); + continue; + } + if (!pme->is_huge_page) { + ret = remap_normal_pages(mm, vma, pme); + if (ret < 0) + goto out; + } else { + ret = remap_huge_pmd_pages(mm, vma, pme); + if (ret < 0) + goto out; + } + pme = (struct page_map_entry *)(next_pme(pme)); + } else { + vma = vma->vm_next; + } + } +out: + up_write(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL_GPL(do_mem_remap); + +#if defined(CONFIG_ARM64) +void init_reserve_page_map(unsigned long map_addr, unsigned long map_size) +{ + void *addr; + + if (!map_addr || !map_size) + return; + addr = phys_to_virt(map_addr); + init_page_map_info((unsigned int *)addr); +} +#else +void init_reserve_page_map(unsigned long map_addr, unsigned long map_size) +{ +} +#endif + +/* Clear all pin memory record. */ +void clear_pin_memory_record(void) +{ + if (pin_pid_num_addr) { + *pin_pid_num_addr = 0; + pin_pid_num = 0; + page_map_entry_start = (struct page_map_entry *)__page_map_entry_start; + } + if (kernel_space_reserve_start && kernel_pin_space_size > 0) { + *(unsigned long *)kernel_space_reserve_start = 0; + } +} +EXPORT_SYMBOL_GPL(clear_pin_memory_record); + +vm_fault_t reserve_kernel_space_mem(unsigned long start_addr, unsigned int pages) +{ + unsigned long i; + unsigned long entry_num; + struct page_map_entry *pme, *pme_start; + + + entry_num = *(unsigned long *)kernel_space_reserve_start; + pme_start = (struct page_map_entry *)(kernel_space_reserve_start + sizeof(entry_num)); + pme = pme_start; + spin_lock(&page_map_entry_lock); + for (i = 0; i < entry_num; i++) { + if (start_addr == pme->virt_addr) { + spin_unlock(&page_map_entry_lock); + return 0; + } + pme = pme + 1; + } + if ((unsigned long)(pme_start + entry_num) >= kernel_space_reserve_end) { + spin_unlock(&page_map_entry_lock); + return VM_FAULT_OOM; + } + pme = pme_start + entry_num; + pme->virt_addr = start_addr; + pme->nr_pages = pages; + pme->is_huge_page = false; + *(unsigned long *)kernel_space_reserve_start = entry_num + 1; + spin_unlock(&page_map_entry_lock); + return 0; +} +EXPORT_SYMBOL_GPL(reserve_kernel_space_mem); + +#endif /* CONFIG_PIN_MEMORY */ -- 1.8.3.1

1 0

[PATCH] mmap: fix a compiling error on mips
by Zhengyuan Liu 31 Dec '20

31 Dec '20

hulk inclusion category: bugfix bugzilla: NA CVE: NA MAP_PA32BIT was defined in uapi/asm-generic/mman.h, that was not automatically included by mm/mmap.c when building on mips platform, and result in following compiling error: mm/mmap.c: In function ‘do_mmap’: mm/mmap.c:1450:14: error: ‘MAP_PA32BIT’ undeclared (first use in this function); did you mean ‘MAP_32BIT’? if (flags & MAP_PA32BIT) ^~~~~~~~~~~ MAP_32BIT mm/mmap.c:1450:14: note: each undeclared identifier is reported only once for each function it appears in make[1]: *** [scripts/Makefile.build:303: mm/mmap.o] Error 1 Fixes: e138253f2b82 ("svm: add support for allocing memory which is within 4G physical address in svm_mmap") Signed-off-by: Zhengyuan Liu <liuzhengyuan(a)tj.kylinos.cn> --- arch/mips/include/uapi/asm/mman.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 3035ca499cd8..0247a3c705af 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -51,6 +51,7 @@ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ #define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ +#define MAP_PA32BIT 0x400000 /* * Flags for msync -- 2.17.1

4 4

[PATCH v2 OLK-5.10 00/40] Backprot lts patches from Linux-5.10.3
by Chen Jun 30 Dec '20

30 Dec '20

*** BLURB HERE *** Alexey Kardashevskiy (1): serial_core: Check for port state when tty is in error state Anant Thazhemadam (2): fs: quota: fix array-index-out-of-bounds bug by passing correct argument to vfs_cleanup_quota_inode() nl80211: validate key indexes for cfg80211_registered_device Andi Kleen (1): x86/split-lock: Avoid returning with interrupts enabled Antti Palosaari (1): media: msi2500: assign SPI bus number dynamically Arnd Bergmann (1): scsi: megaraid_sas: Check user-provided offsets Artem Labazov (1): exfat: Avoid allocating upcase table using kcalloc() Chao Yu (1): f2fs: fix to seek incorrect data offset in inline data file Dae R. Jeong (1): md: fix a warning caused by a race between concurrent md_ioctl()s Dan Carpenter (1): usb: mtu3: fix memory corruption in mtu3_debugfs_regset() Eric Biggers (6): fscrypt: remove kernel-internal constants from UAPI header fscrypt: add fscrypt_is_nokey_name() ubifs: prevent creating duplicate encrypted filenames ext4: prevent creating duplicate encrypted filenames f2fs: prevent creating duplicate encrypted filenames crypto: af_alg - avoid undefined behavior accessing salg_name Fabio Estevam (1): usb: chipidea: ci_hdrc_imx: Pass DISABLE_DEVICE_STREAMING flag to imx6ul Jack Pham (1): usb: gadget: f_fs: Re-use SS descriptors for SuperSpeedPlus Jack Qiu (1): f2fs: init dirty_secmap incorrectly Jan Kara (1): quota: Sanity-check quota file headers on load Johan Hovold (1): USB: serial: option: add interface-number sanity check to flag handling Julian Sax (1): HID: i2c-hid: add Vero K147 to descriptor override Krzysztof Kozlowski (3): ARM: dts: exynos: fix roles of USB 3.0 ports on Odroid XU ARM: dts: exynos: fix USB 3.0 VBUS control and over-current pins on Exynos5410 ARM: dts: exynos: fix USB 3.0 pins supply being turned off on Odroid XU Mao Jinlong (1): coresight: tmc-etr: Check if page is valid before dma_map_page() Nicolin Chen (1): soc/tegra: fuse: Fix index bug in get_process_id Peilin Ye (1): Bluetooth: Fix slab-out-of-bounds read in hci_le_direct_adv_report_evt() Sai Prakash Ranjan (3): coresight: tmc-etf: Fix NULL ptr dereference in tmc_enable_etf_sink_perf() coresight: etb10: Fix possible NULL ptr dereference in etb_enable_perf() coresight: etm4x: Skip setting LPOVERRIDE bit for qcom, skip-power-up Suzuki K Poulose (5): coresight: tmc-etr: Fix barrier packet insertion for perf buffer coresight: etm4x: Fix accesses to TRCVMIDCTLR1 coresight: etm4x: Fix accesses to TRCCIDCTLR1 coresight: etm4x: Fix accesses to TRCPROCSELR coresight: etm4x: Handle TRCVIPCSSCTLR accesses Thierry Reding (1): net: ipconfig: Avoid spurious blank lines in boot log Will McVicker (2): USB: gadget: f_midi: setup SuperSpeed Plus descriptors USB: gadget: f_rndis: fix bitrate for SuperSpeed and above taehyun.cho (1): USB: gadget: f_acm: add support for SuperSpeed Plus arch/arm/boot/dts/exynos5410-odroidxu.dts | 6 ++- arch/arm/boot/dts/exynos5410-pinctrl.dtsi | 28 ++++++++++ arch/arm/boot/dts/exynos5410.dtsi | 4 ++ arch/x86/kernel/traps.c | 3 +- crypto/af_alg.c | 10 ++-- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 8 +++ drivers/hwtracing/coresight/coresight-etb10.c | 4 +- .../coresight/coresight-etm4x-core.c | 41 +++++++++------ drivers/hwtracing/coresight/coresight-priv.h | 2 + .../hwtracing/coresight/coresight-tmc-etf.c | 4 +- .../hwtracing/coresight/coresight-tmc-etr.c | 4 +- drivers/md/md.c | 7 ++- drivers/media/usb/msi2500/msi2500.c | 2 +- drivers/scsi/megaraid/megaraid_sas_base.c | 16 ++++-- drivers/soc/tegra/fuse/speedo-tegra210.c | 2 +- drivers/tty/serial/serial_core.c | 4 ++ drivers/usb/chipidea/ci_hdrc_imx.c | 3 +- drivers/usb/gadget/function/f_acm.c | 2 +- drivers/usb/gadget/function/f_fs.c | 5 +- drivers/usb/gadget/function/f_midi.c | 6 +++ drivers/usb/gadget/function/f_rndis.c | 4 +- drivers/usb/mtu3/mtu3_debugfs.c | 2 +- drivers/usb/serial/option.c | 23 ++++++++- fs/crypto/fscrypt_private.h | 9 ++-- fs/crypto/hooks.c | 5 +- fs/crypto/keyring.c | 2 +- fs/crypto/keysetup.c | 4 +- fs/crypto/policy.c | 5 +- fs/exfat/nls.c | 6 +-- fs/ext4/namei.c | 3 ++ fs/f2fs/f2fs.h | 2 + fs/f2fs/file.c | 11 ++-- fs/f2fs/segment.c | 2 +- fs/quota/dquot.c | 2 +- fs/quota/quota_v2.c | 19 +++++++ fs/ubifs/dir.c | 17 +++++-- include/linux/fscrypt.h | 34 +++++++++++++ include/uapi/linux/fscrypt.h | 5 +- include/uapi/linux/if_alg.h | 16 ++++++ net/bluetooth/hci_event.c | 12 ++--- net/ipv4/ipconfig.c | 14 +++-- net/wireless/core.h | 2 + net/wireless/nl80211.c | 7 +-- net/wireless/util.c | 51 ++++++++++++++++--- 44 files changed, 332 insertions(+), 86 deletions(-) -- 2.25.0

2 41

[PATCH OLK-5.10 v2 0/2] some bugfix patches for kdump
by Chen Zhou 30 Dec '20

30 Dec '20

Some bugfix patches for kdump. Hanjun Guo (1): arm64: smp: wait 50 seconds for other CPUs to stop for kexec Yingliang Yang (1): arm64: kdump: fix timer interrupts panic, could not boot capture_kernel arch/arm64/kernel/machine_kexec.c | 16 ++++++++++++++++ arch/arm64/kernel/smp.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) -- 2.20.1

2 3

[PATCH OLK-5.10 v3 0/4] kvm: debugfs: support vcpu_stat debugfs
by Jiajun Chen 29 Dec '20

29 Dec '20

From: chenjiajun <chenjiajun8(a)huawei.com> virt inclusion category: feature bugzilla: 46853 CVE: NA Export kvm vcpu info in debugfs entry /sys/kernel/debug/kvm/vcpu_stat, this entry contains kvm exits and cputime items now. And then, we can get all kvm vcpu info through this debugfs instead of one entry per kvm exits items, which will greatly facilitates the collection of performance status. Currently, only support x86 and aarch64. -- ChangeList: v3: modify kzfree in patches v2: modify architecture-dependent st_max to avoid compile err in other arches v1: kvm: debugfs: support vcpu_stat debugfs chenjiajun (4): kvm: debugfs: Export vcpu stat via debugfs kvm: debugfs: export remaining aarch64 kvm exit reasons to debugfs kvm: debugfs: aarch64 export cpu time related items to debugfs kvm: debugfs: Export x86 kvm exits to vcpu_stat arch/arm64/include/asm/kvm_host.h | 21 ++++ arch/arm64/kvm/arm.c | 23 +++++ arch/arm64/kvm/guest.c | 33 +++++++ arch/arm64/kvm/handle_exit.c | 8 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 1 + arch/arm64/kvm/mmu.c | 1 + arch/arm64/kvm/sys_regs.c | 11 +++ arch/x86/include/asm/kvm_host.h | 13 +++ arch/x86/kvm/vmx/vmx.c | 10 ++ arch/x86/kvm/x86.c | 70 +++++++++++++ include/linux/kvm_host.h | 19 ++++ virt/kvm/kvm_main.c | 125 ++++++++++++++++++++++++ 12 files changed, 335 insertions(+) -- 2.29.GIT

3 6

[PATCH OLK-5.10 00/40] Backprot lts patches from Linux-5.10.3
by Chen Jun 28 Dec '20

28 Dec '20

*** BLURB HERE *** Alexey Kardashevskiy (1): serial_core: Check for port state when tty is in error state Anant Thazhemadam (2): fs: quota: fix array-index-out-of-bounds bug by passing correct argument to vfs_cleanup_quota_inode() nl80211: validate key indexes for cfg80211_registered_device Andi Kleen (1): x86/split-lock: Avoid returning with interrupts enabled Antti Palosaari (1): media: msi2500: assign SPI bus number dynamically Arnd Bergmann (1): scsi: megaraid_sas: Check user-provided offsets Artem Labazov (1): exfat: Avoid allocating upcase table using kcalloc() Chao Yu (1): f2fs: fix to seek incorrect data offset in inline data file Dae R. Jeong (1): md: fix a warning caused by a race between concurrent md_ioctl()s Dan Carpenter (1): usb: mtu3: fix memory corruption in mtu3_debugfs_regset() Eric Biggers (6): fscrypt: remove kernel-internal constants from UAPI header fscrypt: add fscrypt_is_nokey_name() ubifs: prevent creating duplicate encrypted filenames ext4: prevent creating duplicate encrypted filenames f2fs: prevent creating duplicate encrypted filenames crypto: af_alg - avoid undefined behavior accessing salg_name Fabio Estevam (1): usb: chipidea: ci_hdrc_imx: Pass DISABLE_DEVICE_STREAMING flag to imx6ul Jack Pham (1): usb: gadget: f_fs: Re-use SS descriptors for SuperSpeedPlus Jack Qiu (1): f2fs: init dirty_secmap incorrectly Jan Kara (1): quota: Sanity-check quota file headers on load Johan Hovold (1): USB: serial: option: add interface-number sanity check to flag handling Julian Sax (1): HID: i2c-hid: add Vero K147 to descriptor override Krzysztof Kozlowski (3): ARM: dts: exynos: fix roles of USB 3.0 ports on Odroid XU ARM: dts: exynos: fix USB 3.0 VBUS control and over-current pins on Exynos5410 ARM: dts: exynos: fix USB 3.0 pins supply being turned off on Odroid XU Mao Jinlong (1): coresight: tmc-etr: Check if page is valid before dma_map_page() Nicolin Chen (1): soc/tegra: fuse: Fix index bug in get_process_id Peilin Ye (1): Bluetooth: Fix slab-out-of-bounds read in hci_le_direct_adv_report_evt() Sai Prakash Ranjan (3): coresight: tmc-etf: Fix NULL ptr dereference in tmc_enable_etf_sink_perf() coresight: etb10: Fix possible NULL ptr dereference in etb_enable_perf() coresight: etm4x: Skip setting LPOVERRIDE bit for qcom, skip-power-up Suzuki K Poulose (5): coresight: tmc-etr: Fix barrier packet insertion for perf buffer coresight: etm4x: Fix accesses to TRCVMIDCTLR1 coresight: etm4x: Fix accesses to TRCCIDCTLR1 coresight: etm4x: Fix accesses to TRCPROCSELR coresight: etm4x: Handle TRCVIPCSSCTLR accesses Thierry Reding (1): net: ipconfig: Avoid spurious blank lines in boot log Will McVicker (2): USB: gadget: f_midi: setup SuperSpeed Plus descriptors USB: gadget: f_rndis: fix bitrate for SuperSpeed and above taehyun.cho (1): USB: gadget: f_acm: add support for SuperSpeed Plus arch/arm/boot/dts/exynos5410-odroidxu.dts | 6 ++- arch/arm/boot/dts/exynos5410-pinctrl.dtsi | 28 ++++++++++ arch/arm/boot/dts/exynos5410.dtsi | 4 ++ arch/x86/kernel/traps.c | 3 +- crypto/af_alg.c | 10 ++-- drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c | 8 +++ drivers/hwtracing/coresight/coresight-etb10.c | 4 +- .../coresight/coresight-etm4x-core.c | 41 +++++++++------ drivers/hwtracing/coresight/coresight-priv.h | 2 + .../hwtracing/coresight/coresight-tmc-etf.c | 4 +- .../hwtracing/coresight/coresight-tmc-etr.c | 4 +- drivers/md/md.c | 7 ++- drivers/media/usb/msi2500/msi2500.c | 2 +- drivers/scsi/megaraid/megaraid_sas_base.c | 16 ++++-- drivers/soc/tegra/fuse/speedo-tegra210.c | 2 +- drivers/tty/serial/serial_core.c | 4 ++ drivers/usb/chipidea/ci_hdrc_imx.c | 3 +- drivers/usb/gadget/function/f_acm.c | 2 +- drivers/usb/gadget/function/f_fs.c | 5 +- drivers/usb/gadget/function/f_midi.c | 6 +++ drivers/usb/gadget/function/f_rndis.c | 4 +- drivers/usb/mtu3/mtu3_debugfs.c | 2 +- drivers/usb/serial/option.c | 23 ++++++++- fs/crypto/fscrypt_private.h | 9 ++-- fs/crypto/hooks.c | 5 +- fs/crypto/keyring.c | 2 +- fs/crypto/keysetup.c | 4 +- fs/crypto/policy.c | 5 +- fs/exfat/nls.c | 6 +-- fs/ext4/namei.c | 3 ++ fs/f2fs/f2fs.h | 2 + fs/f2fs/file.c | 11 ++-- fs/f2fs/segment.c | 2 +- fs/quota/dquot.c | 2 +- fs/quota/quota_v2.c | 19 +++++++ fs/ubifs/dir.c | 17 +++++-- include/linux/fscrypt.h | 34 +++++++++++++ include/uapi/linux/fscrypt.h | 5 +- include/uapi/linux/if_alg.h | 16 ++++++ net/bluetooth/hci_event.c | 12 ++--- net/ipv4/ipconfig.c | 14 +++-- net/wireless/core.h | 2 + net/wireless/nl80211.c | 7 +-- net/wireless/util.c | 51 ++++++++++++++++--- 44 files changed, 332 insertions(+), 86 deletions(-) -- 2.25.0

2 22

[PATCH OLK-5.10 0/2] some bugfix patches for kdump
by Chen Zhou 28 Dec '20

28 Dec '20

some bugfix patches for kdump. Hanjun Guo (1): [Huawei] arm64: smp: wait 50 seconds for other CPUs to stop for kexec Yingliang Yang (1): [Huawei] arm64: kdump: fix timer interrupts panic, could not boot capture_kernel arch/arm64/kernel/machine_kexec.c | 16 ++++++++++++++++ arch/arm64/kernel/smp.c | 4 ++-- 2 files changed, 18 insertions(+), 2 deletions(-) -- 2.20.1

1 2

[PATCH kernel-4.19 1/4] modpost: add read_text_file() and get_line() helpers
by Yang Yingliang 28 Dec '20

28 Dec '20

From: Masahiro Yamada <masahiroy(a)kernel.org> mainline inclusion from mainline-5.8 commit ac5100f54329676469688d1b5415cd8d6428c909 category: bugfix bugzilla: 46847 CVE: NA ----------------------------------------------- modpost uses grab_file() to open a file, but it is not suitable for a text file because the mmap'ed file is not terminated by null byte. Actually, I see some issues for the use of grab_file(). The new helper, read_text_file() loads the whole file content into a malloc'ed buffer, and appends a null byte. Then, get_line() reads each line. To handle text files, I intend to replace as follows: grab_file() -> read_text_file() get_new_line() -> get_line() Signed-off-by: Masahiro Yamada <masahiroy(a)kernel.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- scripts/mod/modpost.c | 49 +++++++++++++++++++++++++++++++++++++++++++ scripts/mod/modpost.h | 2 ++ 2 files changed, 51 insertions(+) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 91a80036c05d..99334521909b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -118,6 +118,55 @@ void *do_nofail(void *ptr, const char *expr) return ptr; } +char *read_text_file(const char *filename) +{ + struct stat st; + size_t nbytes; + int fd; + char *buf; + + fd = open(filename, O_RDONLY); + if (fd < 0) { + perror(filename); + exit(1); + } + + if (fstat(fd, &st) < 0) { + perror(filename); + exit(1); + } + + buf = NOFAIL(malloc(st.st_size + 1)); + + nbytes = st.st_size; + + while (nbytes) { + ssize_t bytes_read; + + bytes_read = read(fd, buf, nbytes); + if (bytes_read < 0) { + perror(filename); + exit(1); + } + + nbytes -= bytes_read; + } + buf[st.st_size] = '\0'; + + close(fd); + + return buf; +} + +char *get_line(char **stringp) +{ + /* do not return the unwanted extra line at EOF */ + if (*stringp && **stringp == '\0') + return NULL; + + return strsep(stringp, "\n"); +} + /* A list of all modules we processed */ static struct module *modules; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 8453d6ac2f77..ff809119f82b 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -185,6 +185,8 @@ void maybe_frob_rcs_version(const char *modfilename, void get_src_version(const char *modname, char sum[], unsigned sumlen); /* from modpost.c */ +char *read_text_file(const char *filename); +char *get_line(char **stringp); void *grab_file(const char *filename, unsigned long *size); char* get_next_line(unsigned long *pos, void *file, unsigned long size); void release_file(void *file, unsigned long size); -- 2.25.1

1 3

[PATCH OLK-5.10 0/6] Support for printing dirty pages
by Chen Jun 28 Dec '20

28 Dec '20

*** BLURB HERE *** yu kuai (6): fs/dirty_pages: dump the number of dirty pages for each inode fs/dirty_pages: fix index out of bounds and integer overflow fs/dirty_pages: fix wrong 'buff_num' after invalid input fs/dirty_pages: Adjust position of some code to improve the code fs/dirty_pages: fix kernel panic in concurrency mode fs/dirty_pages: remove set but not used variable 'm' fs/Makefile | 1 + fs/dirty_pages.c | 466 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 467 insertions(+) create mode 100644 fs/dirty_pages.c -- 2.25.0

2 7

[PATCH OLK-5.10 00/16] Backport v5.10.2 LTS
by Chen Jun 23 Dec '20

23 Dec '20

*** BLURB HERE *** Alan Stern (1): USB: legotower: fix logical error in recent commit Alexander Sverdlin (1): serial: 8250_omap: Avoid FIFO corruption caused by MDR1 access Bui Quang Minh (1): USB: dummy-hcd: Fix uninitialized array use in init() Hans de Goede (1): xhci-pci: Allow host runtime PM as default for Intel Alpine Ridge LP Li Jun (1): xhci: Give USB2 ports time to enter U3 in bus suspend Mika Westerberg (1): xhci-pci: Allow host runtime PM as default for Intel Maple Ridge xHCI Oliver Neukum (2): USB: add RESET_RESUME quirk for Snapscan 1212 USB: UAS: introduce a quirk to set no_write_same Peilin Ye (1): ptrace: Prevent kernel-infoleak in ptrace_get_syscall_info() Steven Rostedt (VMware) (2): ktest.pl: If size of log is too big to email, email error message ktest.pl: Fix the logic for truncating the size of the log file for email Takashi Iwai (3): ALSA: usb-audio: Fix potential out-of-bounds shift ALSA: usb-audio: Fix control 'access overflow' errors from chmap ALSA: pcm: oss: Fix potential out-of-bounds shift Tejas Joglekar (1): usb: xhci: Set quirk for XHCI_SG_TRB_CACHE_SIZE_QUIRK Thomas Gleixner (1): USB: sisusbvga: Make console support depend on BROKEN .../admin-guide/kernel-parameters.txt | 1 + drivers/tty/serial/8250/8250_omap.c | 5 ----- drivers/usb/core/quirks.c | 3 +++ drivers/usb/gadget/udc/dummy_hcd.c | 2 +- drivers/usb/host/xhci-hub.c | 4 ++++ drivers/usb/host/xhci-pci.c | 6 +++++- drivers/usb/host/xhci-plat.c | 3 +++ drivers/usb/host/xhci.h | 1 + drivers/usb/misc/legousbtower.c | 2 +- drivers/usb/misc/sisusbvga/Kconfig | 2 +- drivers/usb/storage/uas.c | 3 +++ drivers/usb/storage/unusual_uas.h | 7 +++++-- drivers/usb/storage/usb.c | 3 +++ include/linux/usb_usual.h | 2 ++ include/uapi/linux/ptrace.h | 3 ++- sound/core/oss/pcm_oss.c | 6 +++++- sound/usb/format.c | 2 ++ sound/usb/stream.c | 6 +++--- tools/testing/ktest/ktest.pl | 20 +++++++++++-------- 19 files changed, 57 insertions(+), 24 deletions(-) -- 2.25.0

2 17

Re: [PATCH OLK-5.10 0/6] Support for printing dirty pages
by Xiexiuqi 23 Dec '20

23 Dec '20

For this series, Reviewed-by: Xie XiuQi <xiexiuqi(a)huawei.com> -----邮件原件----- 发件人: chenjun (AM) 发送时间: 2020年12月23日 10:03 收件人: kernel(a)openeuler.org 抄送: Xiangrui (Euler) <rui.xiang(a)huawei.com>; Guohanjun (Hanjun Guo) <guohanjun(a)huawei.com>; Xiexiuqi <xiexiuqi(a)huawei.com> 主题: [PATCH OLK-5.10 0/6] Support for printing dirty pages *** BLURB HERE *** yu kuai (6): fs/dirty_pages: dump the number of dirty pages for each inode fs/dirty_pages: fix index out of bounds and integer overflow fs/dirty_pages: fix wrong 'buff_num' after invalid input fs/dirty_pages: Adjust position of some code to improve the code fs/dirty_pages: fix kernel panic in concurrency mode fs/dirty_pages: remove set but not used variable 'm' fs/Makefile | 1 + fs/dirty_pages.c | 466 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 467 insertions(+) create mode 100644 fs/dirty_pages.c -- 2.25.0

1 0

[PATCH kernel-4.19 01/24] net: hns3: modify location of one print information
by Yang Yingliang 23 Dec '20

23 Dec '20

From: Junxin Chen <chenjunxin1(a)huawei.com> driver inclusion category: cleanup bugzilla: NA CVE: NA ---------------------------- This patch modifies location of one print information. Signed-off-by: Junxin Chen <chenjunxin1(a)huawei.com> Signed-off-by: Guangbin Huang <huangguangbin2(a)huawei.com> Reviewed-by: Peng Li <lipeng321(a)huawei.com> Signed-off-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: Yongxin Li <liyongxin1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 082625de7a30..2c1c0efad80e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3454,10 +3454,10 @@ static void hclge_do_reset(struct hclge_dev *hdev) switch (hdev->reset_type) { case HNAE3_GLOBAL_RESET: + dev_info(&pdev->dev, "global reset requested\n"); val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG); hnae3_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1); hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val); - dev_info(&pdev->dev, "global reset requested\n"); break; case HNAE3_FUNC_RESET: dev_info(&pdev->dev, "PF reset requested\n"); -- 2.25.1

1 23

[PATCH kernel-4.19 1/2] Page flags: Add reserved page flags for future extension
by Yang Yingliang 23 Dec '20

23 Dec '20

From: Xiangyou Xie <xiexiangyou(a)huawei.com> euleros inclusion category: feature bugzilla: 46840 CVE: NA ------------------------------------------------- Add reserved page flags for internal extension. For the new page flags which backported from kernel upstream, place them behind the the reserved page flags. Signed-off-by: Xiangyou Xie <xiexiangyou(a)huawei.com> Reviewed-by: Zenghui Yu <yuzenghui(a)huawei.com> Reviewed-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/page-flags.h | 8 ++++++++ include/trace/events/mmflags.h | 4 +++- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 17eeaf76259b..0d395970a988 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -103,6 +103,14 @@ enum pageflags { PG_idle, #endif PG_percpu_ref, + + /* Add reserved page flags for internal extension. For the new page + * flags which backported from kernel upstream, please place them + * behind the the reserved page flags. + */ + PG_reserve_pgflag_0, + PG_reserve_pgflag_1, + __NR_PAGEFLAGS, /* Filesystems */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index 894305dad41e..d8965ccb9c4b 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -106,7 +106,9 @@ IF_HAVE_PG_UNCACHED(PG_uncached, "uncached" ) \ IF_HAVE_PG_HWPOISON(PG_hwpoison, "hwpoison" ) \ IF_HAVE_PG_IDLE(PG_young, "young" ) \ IF_HAVE_PG_IDLE(PG_idle, "idle"), \ - {1UL << PG_percpu_ref, "percpu_ref" } + {1UL << PG_percpu_ref, "percpu_ref" }, \ + {1UL << PG_reserve_pgflag_0, "reserve_pgflag_0"}, \ + {1UL << PG_reserve_pgflag_1, "reserve_pgflag_1"} #define show_page_flags(flags) \ (flags) ? __print_flags(flags, "|", \ -- 2.25.1

1 1

[PATCH 01/10] genirq, sched/isolation: Isolate from handling managed interrupts
by Yang Yingliang 23 Dec '20

23 Dec '20

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-v5.6-rc1 commit 11ea68f553e244851d15793a7fa33a97c46d8271 category: bugfix bugzilla: 45956 CVE: NA -------------------------------- The affinity of managed interrupts is completely handled in the kernel and cannot be changed via the /proc/irq/* interfaces from user space. As the kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent vector exhaustion, it can happen that a managed interrupt whose affinity mask contains both isolated and housekeeping CPUs is routed to an isolated CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts on the isolated CPU. Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding logic in the interrupt affinity selection code. The subparameter indicates to the interrupt affinity selection logic that it should try to avoid the above scenario. This isolation is best effort and only effective if the automatically assigned interrupt mask of a device queue contains isolated and housekeeping CPUs. If housekeeping CPUs are online then such interrupts are directed to the housekeeping CPU so that IO submitted on the housekeeping CPU cannot disturb the isolated CPU. If a queue's affinity mask contains only isolated CPUs then this parameter has no effect on the interrupt routing decision, though interrupts are only happening when tasks running on those isolated CPUs submit IO. IO submitted on housekeeping CPUs has no influence on those queues. If the affinity mask contains both housekeeping and isolated CPUs, but none of the contained housekeeping CPUs is online, then the interrupt is also routed to an isolated CPU. Interrupts are only delivered when one of the isolated CPUs in the affinity mask submits IO. If one of the contained housekeeping CPUs comes online, the CPU hotplug logic migrates the interrupt automatically back to the upcoming housekeeping CPU. Depending on the type of interrupt controller, this can require that at least one interrupt is delivered to the isolated CPU in order to complete the migration. [ tglx: Removed unused parameter, added and edited comments/documentation and rephrased the changelog so it contains more details. ] Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com Signed-off-by: Liu Chao <liuchao173(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../admin-guide/kernel-parameters.txt | 26 +++++++++++- include/linux/sched/isolation.h | 7 ++++ kernel/irq/cpuhotplug.c | 21 +++++++++- kernel/irq/manage.c | 41 ++++++++++++++++++- kernel/sched/isolation.c | 12 ++++++ 5 files changed, 102 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 60c06c7d243d..a0e84095a1a5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1911,9 +1911,31 @@ <cpu number> begins at 0 and the maximum value is "number of CPUs in system - 1". - The format of <cpu-list> is described above. - + managed_irq + + Isolate from being targeted by managed interrupts + which have an interrupt mask containing isolated + CPUs. The affinity of managed interrupts is + handled by the kernel and cannot be changed via + the /proc/irq/* interfaces. + + This isolation is best effort and only effective + if the automatically assigned interrupt mask of a + device queue contains isolated and housekeeping + CPUs. If housekeeping CPUs are online then such + interrupts are directed to the housekeeping CPU + so that IO submitted on the housekeeping CPU + cannot disturb the isolated CPU. + + If a queue's affinity mask contains only isolated + CPUs then this parameter has no effect on the + interrupt routing decision, though interrupts are + only delivered when tasks running on those + isolated CPUs submit IO. IO submitted on + housekeeping CPUs has no influence on those + queues. + The format of <cpu-list> is described above. iucv= [HW,NET] diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 4a6582c27dea..461e1f6ab3eb 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -13,12 +13,14 @@ enum hk_flags { HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), + HK_FLAG_MANAGED_IRQ = (1 << 7), }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); extern int housekeeping_any_cpu(enum hk_flags flags); extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); +extern bool housekeeping_enabled(enum hk_flags flags); extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); extern void __init housekeeping_init(void); @@ -35,6 +37,11 @@ static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) return cpu_possible_mask; } +static inline bool housekeeping_enabled(enum hk_flags flags) +{ + return false; +} + static inline void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { } static inline void housekeeping_init(void) { } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 6c7ca2e983a5..02236b13b359 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/ratelimit.h> #include <linux/irq.h> +#include <linux/sched/isolation.h> #include "internals.h" @@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void) } } +static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) +{ + const struct cpumask *hk_mask; + + if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + return false; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) + return false; + + return cpumask_test_cpu(cpu, hk_mask); +} + static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); @@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) /* * If the interrupt can only be directed to a single target * CPU then it is already assigned to a CPU in the affinity - * mask. No point in trying to move it around. + * mask. No point in trying to move it around unless the + * isolation mechanism requests to move it to an upcoming + * housekeeping CPU. */ - if (!irqd_is_single_target(data)) + if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu)) irq_set_affinity_locked(data, affinity, false); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a8c66acee82a..34eda1e772fa 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> @@ -227,7 +228,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - ret = chip->irq_set_affinity(data, mask, force); + /* + * If this is a managed interrupt and housekeeping is enabled on + * it check whether the requested affinity mask intersects with + * a housekeeping CPU. If so, then remove the isolated CPUs from + * the mask and just keep the housekeeping CPU(s). This prevents + * the affinity setter from routing the interrupt to an isolated + * CPU to avoid that I/O submitted from a housekeeping CPU causes + * interrupts on an isolated one. + * + * If the masks do not intersect or include online CPU(s) then + * keep the requested mask. The isolated target CPUs are only + * receiving interrupts when the I/O operation was submitted + * directly from them. + * + * If all housekeeping CPUs in the affinity mask are offline, the + * interrupt will be migrated by the CPU hotplug code once a + * housekeeping CPU which belongs to the affinity mask comes + * online. + */ + if (irqd_affinity_is_managed(data) && + housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + const struct cpumask *hk_mask, *prog_mask; + + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + + raw_spin_lock(&tmp_mask_lock); + cpumask_and(&tmp_mask, mask, hk_mask); + if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) + prog_mask = mask; + else + prog_mask = &tmp_mask; + ret = chip->irq_set_affinity(data, prog_mask, force); + raw_spin_unlock(&tmp_mask_lock); + } else { + ret = chip->irq_set_affinity(data, mask, force); + } switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index e6802181900f..6e85049d68cf 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -13,6 +13,12 @@ EXPORT_SYMBOL_GPL(housekeeping_overriden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; +bool housekeeping_enabled(enum hk_flags flags) +{ + return !!(housekeeping_flags & flags); +} +EXPORT_SYMBOL_GPL(housekeeping_enabled); + int housekeeping_any_cpu(enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) @@ -140,6 +146,12 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } + if (!strncmp(str, "managed_irq,", 12)) { + str += 12; + flags |= HK_FLAG_MANAGED_IRQ; + continue; + } + pr_warn("isolcpus: Error, unknown flag\n"); return 0; } -- 2.25.1

1 9

[PATCH 01/10] genirq, sched/isolation: Isolate from handling managed interrupts
by Yang Yingliang 23 Dec '20

23 Dec '20

From: Ming Lei <ming.lei(a)redhat.com> mainline inclusion from mainline-v5.6-rc1 commit 11ea68f553e244851d15793a7fa33a97c46d8271 category: bugfix bugzilla: 45956 CVE: NA -------------------------------- The affinity of managed interrupts is completely handled in the kernel and cannot be changed via the /proc/irq/* interfaces from user space. As the kernel tries to spread out interrupts evenly accross CPUs on x86 to prevent vector exhaustion, it can happen that a managed interrupt whose affinity mask contains both isolated and housekeeping CPUs is routed to an isolated CPU. As a consequence IO submitted on a housekeeping CPU causes interrupts on the isolated CPU. Add a new sub-parameter 'managed_irq' for 'isolcpus' and the corresponding logic in the interrupt affinity selection code. The subparameter indicates to the interrupt affinity selection logic that it should try to avoid the above scenario. This isolation is best effort and only effective if the automatically assigned interrupt mask of a device queue contains isolated and housekeeping CPUs. If housekeeping CPUs are online then such interrupts are directed to the housekeeping CPU so that IO submitted on the housekeeping CPU cannot disturb the isolated CPU. If a queue's affinity mask contains only isolated CPUs then this parameter has no effect on the interrupt routing decision, though interrupts are only happening when tasks running on those isolated CPUs submit IO. IO submitted on housekeeping CPUs has no influence on those queues. If the affinity mask contains both housekeeping and isolated CPUs, but none of the contained housekeeping CPUs is online, then the interrupt is also routed to an isolated CPU. Interrupts are only delivered when one of the isolated CPUs in the affinity mask submits IO. If one of the contained housekeeping CPUs comes online, the CPU hotplug logic migrates the interrupt automatically back to the upcoming housekeeping CPU. Depending on the type of interrupt controller, this can require that at least one interrupt is delivered to the isolated CPU in order to complete the migration. [ tglx: Removed unused parameter, added and edited comments/documentation and rephrased the changelog so it contains more details. ] Signed-off-by: Ming Lei <ming.lei(a)redhat.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Link: https://lore.kernel.org/r/20200120091625.17912-1-ming.lei@redhat.com Signed-off-by: Liu Chao <liuchao173(a)huawei.com> Reviewed-by: Jian Cheng <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- .../admin-guide/kernel-parameters.txt | 26 +++++++++++- include/linux/sched/isolation.h | 7 ++++ kernel/irq/cpuhotplug.c | 21 +++++++++- kernel/irq/manage.c | 41 ++++++++++++++++++- kernel/sched/isolation.c | 12 ++++++ 5 files changed, 102 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 60c06c7d243d..a0e84095a1a5 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1911,9 +1911,31 @@ <cpu number> begins at 0 and the maximum value is "number of CPUs in system - 1". - The format of <cpu-list> is described above. - + managed_irq + + Isolate from being targeted by managed interrupts + which have an interrupt mask containing isolated + CPUs. The affinity of managed interrupts is + handled by the kernel and cannot be changed via + the /proc/irq/* interfaces. + + This isolation is best effort and only effective + if the automatically assigned interrupt mask of a + device queue contains isolated and housekeeping + CPUs. If housekeeping CPUs are online then such + interrupts are directed to the housekeeping CPU + so that IO submitted on the housekeeping CPU + cannot disturb the isolated CPU. + + If a queue's affinity mask contains only isolated + CPUs then this parameter has no effect on the + interrupt routing decision, though interrupts are + only delivered when tasks running on those + isolated CPUs submit IO. IO submitted on + housekeeping CPUs has no influence on those + queues. + The format of <cpu-list> is described above. iucv= [HW,NET] diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 4a6582c27dea..461e1f6ab3eb 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -13,12 +13,14 @@ enum hk_flags { HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), + HK_FLAG_MANAGED_IRQ = (1 << 7), }; #ifdef CONFIG_CPU_ISOLATION DECLARE_STATIC_KEY_FALSE(housekeeping_overriden); extern int housekeeping_any_cpu(enum hk_flags flags); extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags); +extern bool housekeeping_enabled(enum hk_flags flags); extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags); extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags); extern void __init housekeeping_init(void); @@ -35,6 +37,11 @@ static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags) return cpu_possible_mask; } +static inline bool housekeeping_enabled(enum hk_flags flags) +{ + return false; +} + static inline void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { } static inline void housekeeping_init(void) { } diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 6c7ca2e983a5..02236b13b359 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/ratelimit.h> #include <linux/irq.h> +#include <linux/sched/isolation.h> #include "internals.h" @@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void) } } +static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) +{ + const struct cpumask *hk_mask; + + if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + return false; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) + return false; + + return cpumask_test_cpu(cpu, hk_mask); +} + static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); @@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) /* * If the interrupt can only be directed to a single target * CPU then it is already assigned to a CPU in the affinity - * mask. No point in trying to move it around. + * mask. No point in trying to move it around unless the + * isolation mechanism requests to move it to an upcoming + * housekeeping CPU. */ - if (!irqd_is_single_target(data)) + if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu)) irq_set_affinity_locked(data, affinity, false); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a8c66acee82a..34eda1e772fa 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> @@ -227,7 +228,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - ret = chip->irq_set_affinity(data, mask, force); + /* + * If this is a managed interrupt and housekeeping is enabled on + * it check whether the requested affinity mask intersects with + * a housekeeping CPU. If so, then remove the isolated CPUs from + * the mask and just keep the housekeeping CPU(s). This prevents + * the affinity setter from routing the interrupt to an isolated + * CPU to avoid that I/O submitted from a housekeeping CPU causes + * interrupts on an isolated one. + * + * If the masks do not intersect or include online CPU(s) then + * keep the requested mask. The isolated target CPUs are only + * receiving interrupts when the I/O operation was submitted + * directly from them. + * + * If all housekeeping CPUs in the affinity mask are offline, the + * interrupt will be migrated by the CPU hotplug code once a + * housekeeping CPU which belongs to the affinity mask comes + * online. + */ + if (irqd_affinity_is_managed(data) && + housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + const struct cpumask *hk_mask, *prog_mask; + + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + + raw_spin_lock(&tmp_mask_lock); + cpumask_and(&tmp_mask, mask, hk_mask); + if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) + prog_mask = mask; + else + prog_mask = &tmp_mask; + ret = chip->irq_set_affinity(data, prog_mask, force); + raw_spin_unlock(&tmp_mask_lock); + } else { + ret = chip->irq_set_affinity(data, mask, force); + } switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index e6802181900f..6e85049d68cf 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -13,6 +13,12 @@ EXPORT_SYMBOL_GPL(housekeeping_overriden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; +bool housekeeping_enabled(enum hk_flags flags) +{ + return !!(housekeeping_flags & flags); +} +EXPORT_SYMBOL_GPL(housekeeping_enabled); + int housekeeping_any_cpu(enum hk_flags flags) { if (static_branch_unlikely(&housekeeping_overriden)) @@ -140,6 +146,12 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } + if (!strncmp(str, "managed_irq,", 12)) { + str += 12; + flags |= HK_FLAG_MANAGED_IRQ; + continue; + } + pr_warn("isolcpus: Error, unknown flag\n"); return 0; } -- 2.25.1

1 2

[PATCH v3 OLK-5.10 00/26] KVM RISC-V Support
by MingWang Li 23 Dec '20

23 Dec '20

From: Mingwang Li <limingwang(a)huawei.com> euleros inclusion category: feature feature: initial KVM RISC-V support bugzilla: 46845 CVE: NA This series adds initial KVM RISC-V support. Currently, we are able to boot Linux on RV64/RV32 Guest with multiple VCPUs. This series can be found in riscv_kvm_v15 branch at: https//github.com/avpatel/linux.git Changes since v2 - fix build error Changes since v1 - follow guileline for submiting patches to openEuler - add the testing result in this issue Reference: https://gitee.com/openeuler/kernel/issues/I26X9V Alistair Francis (1): Revert "riscv: Use latest system call ABI" Anup Patel (19): RISC-V: Add fragmented config for debug options RISC-V: Enable CPU Hotplug in defconfigs RISC-V: Add Microchip PolarFire kconfig option RISC-V: Initial DTS for Microchip ICICLE board RISC-V: Enable drivers for Microchip PolarFire ICICLE board RISC-V: Add hypervisor extension related CSR defines RISC-V: Add initial skeletal KVM support RISC-V: KVM: Implement VCPU create, init and destroy functions RISC-V: KVM: Implement VCPU interrupts and requests handling RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls RISC-V: KVM: Implement VCPU world-switch RISC-V: KVM: Handle MMIO exits for VCPU RISC-V: KVM: Handle WFI exits for VCPU RISC-V: KVM: Implement VMID allocator RISC-V: KVM: Implement stage2 page table programming RISC-V: KVM: Implement MMU notifiers RISC-V: KVM: Document RISC-V specific parts of KVM API RISC-V: KVM: Add MAINTAINERS entry RISC-V: Enable KVM for RV64 and RV32 Atish Patra (4): RISC-V: KVM: Add timer functionality RISC-V: KVM: FP lazy save/restore RISC-V: KVM: Implement ONE REG interface for FP registers RISC-V: KVM: Add SBI v0.1 support Mingwang Li (1): RISCV: KVM: fix bug in migration m34782 (1): Microchip Polarfire SoC Clock Driver Documentation/virt/kvm/api.rst | 193 +++- MAINTAINERS | 11 + arch/riscv/Kconfig | 2 + arch/riscv/Kconfig.socs | 7 + arch/riscv/Makefile | 2 + arch/riscv/boot/dts/Makefile | 1 + arch/riscv/boot/dts/microchip/Makefile | 2 + .../boot/dts/microchip/icicle-kit-es.dts | 307 +++++ arch/riscv/configs/defconfig | 30 +- arch/riscv/configs/extra_debug.config | 21 + arch/riscv/configs/rv32_defconfig | 26 +- arch/riscv/include/asm/csr.h | 89 ++ arch/riscv/include/asm/kvm_host.h | 278 +++++ arch/riscv/include/asm/kvm_types.h | 7 + arch/riscv/include/asm/kvm_vcpu_timer.h | 44 + arch/riscv/include/asm/pgtable-bits.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 128 +++ arch/riscv/include/uapi/asm/unistd.h | 5 +- arch/riscv/kernel/asm-offsets.c | 156 +++ arch/riscv/kvm/Kconfig | 36 + arch/riscv/kvm/Makefile | 15 + arch/riscv/kvm/main.c | 118 ++ arch/riscv/kvm/mmu.c | 860 ++++++++++++++ arch/riscv/kvm/tlb.S | 74 ++ arch/riscv/kvm/vcpu.c | 1012 +++++++++++++++++ arch/riscv/kvm/vcpu_exit.c | 701 ++++++++++++ arch/riscv/kvm/vcpu_sbi.c | 173 +++ arch/riscv/kvm/vcpu_switch.S | 400 +++++++ arch/riscv/kvm/vcpu_timer.c | 225 ++++ arch/riscv/kvm/vm.c | 81 ++ arch/riscv/kvm/vmid.c | 120 ++ drivers/clk/Kconfig | 5 + drivers/clk/Makefile | 1 + drivers/clk/microchip/Makefile | 2 + drivers/clk/microchip/clk-pfsoc.c | 508 +++++++++ drivers/clocksource/timer-riscv.c | 8 + include/clocksource/timer-riscv.h | 16 + include/uapi/linux/kvm.h | 8 + 38 files changed, 5619 insertions(+), 54 deletions(-) create mode 100644 arch/riscv/boot/dts/microchip/Makefile create mode 100644 arch/riscv/boot/dts/microchip/icicle-kit-es.dts create mode 100644 arch/riscv/configs/extra_debug.config create mode 100644 arch/riscv/include/asm/kvm_host.h create mode 100644 arch/riscv/include/asm/kvm_types.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_timer.h create mode 100644 arch/riscv/include/uapi/asm/kvm.h create mode 100644 arch/riscv/kvm/Kconfig create mode 100644 arch/riscv/kvm/Makefile create mode 100644 arch/riscv/kvm/main.c create mode 100644 arch/riscv/kvm/mmu.c create mode 100644 arch/riscv/kvm/tlb.S create mode 100644 arch/riscv/kvm/vcpu.c create mode 100644 arch/riscv/kvm/vcpu_exit.c create mode 100644 arch/riscv/kvm/vcpu_sbi.c create mode 100644 arch/riscv/kvm/vcpu_switch.S create mode 100644 arch/riscv/kvm/vcpu_timer.c create mode 100644 arch/riscv/kvm/vm.c create mode 100644 arch/riscv/kvm/vmid.c create mode 100644 drivers/clk/microchip/clk-pfsoc.c create mode 100644 include/clocksource/timer-riscv.h -- 2.19.1

3 28

[PATCH OLK-5.10 1/1] mm, page_alloc: avoid page_to_pfn() in move_freepages()
by Chen Jun 22 Dec '20

22 Dec '20

From: Kefeng Wang <wangkefeng.wang(a)huawei.com> hulk inclusion category: bugfix bugzilla: 46856 CVE: NA --------------------------- The start_pfn and end_pfn are already available in move_freepages_block(), there is no need to go back and forth between page and pfn in move_freepages and move_freepages_block, and pfn_valid_within() should validate pfn first before touching the page. Signed-off-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> --- mm/page_alloc.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eaa227a479e4..636afce90efa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2361,19 +2361,21 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone, * boundary. If alignment is required, use move_freepages_block() */ static int move_freepages(struct zone *zone, - struct page *start_page, struct page *end_page, + unsigned long start_pfn, unsigned long end_pfn, int migratetype, int *num_movable) { struct page *page; + unsigned long pfn; unsigned int order; int pages_moved = 0; - for (page = start_page; page <= end_page;) { - if (!pfn_valid_within(page_to_pfn(page))) { - page++; + for (pfn = start_pfn; pfn <= end_pfn;) { + if (!pfn_valid_within(pfn)) { + pfn++; continue; } + page = pfn_to_page(pfn); if (!PageBuddy(page)) { /* * We assume that pages that could be isolated for @@ -2383,8 +2385,7 @@ static int move_freepages(struct zone *zone, if (num_movable && (PageLRU(page) || __PageMovable(page))) (*num_movable)++; - - page++; + pfn++; continue; } @@ -2394,7 +2395,7 @@ static int move_freepages(struct zone *zone, order = buddy_order(page); move_to_free_list(page, zone, order, migratetype); - page += 1 << order; + pfn += 1 << order; pages_moved += 1 << order; } @@ -2404,25 +2405,22 @@ static int move_freepages(struct zone *zone, int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable) { - unsigned long start_pfn, end_pfn; - struct page *start_page, *end_page; + unsigned long start_pfn, end_pfn, pfn; if (num_movable) *num_movable = 0; - start_pfn = page_to_pfn(page); - start_pfn = start_pfn & ~(pageblock_nr_pages-1); - start_page = pfn_to_page(start_pfn); - end_page = start_page + pageblock_nr_pages - 1; + pfn = page_to_pfn(page); + start_pfn = pfn & ~(pageblock_nr_pages - 1); end_pfn = start_pfn + pageblock_nr_pages - 1; /* Do not cross zone boundaries */ if (!zone_spans_pfn(zone, start_pfn)) - start_page = page; + start_pfn = pfn; if (!zone_spans_pfn(zone, end_pfn)) return 0; - return move_freepages(zone, start_page, end_page, migratetype, + return move_freepages(zone, start_pfn, end_pfn, migratetype, num_movable); } -- 2.25.0

1 0

[PATCH OLK-5.10 00/24] Support ILP32 for ARM64
by Chen Jun 22 Dec '20

22 Dec '20

*** BLURB HERE *** Andrew Pinski (3): arm64: rename COMPAT to AARCH32_EL0 arm64: uapi: set __BITS_PER_LONG correctly for ILP32 and LP64 arm64:ilp32: add ARM64_ILP32 to Kconfig Dave Martin (1): arm64: signal: Make parse_user_sigframe() independent of rt_sigframe layout James Morse (1): ptrace: Add compat PTRACE_{G,S}ETSIGMASK handlers Philipp Tomsich (1): arm64:ilp32: add vdso-ilp32 and use for signal return Xiongfeng Wang (4): arm64: rename functions that reference compat term arm64: secomp: fix the secure computing mode 1 syscall check for ilp32 ilp32: avoid clearing upper 32 bits of syscall return value for ilp32 ilp32: skip ARM erratum 1418040 for ilp32 application Yury Norov (14): thread: move thread bits accessors to separated file arm64: ilp32: add documentation on the ILP32 ABI for ARM64 arm64: introduce is_a32_compat_{task,thread} for AArch32 compat arm64: ilp32: add is_ilp32_compat_{task,thread} and TIF_32BIT_AARCH64 arm64: introduce AUDIT_ARCH_AARCH64ILP32 for ilp32 arm64: introduce binfmt_elf32.c arm64: change compat_elf_hwcap and compat_elf_hwcap2 prefix to a32 arm64: ilp32: introduce binfmt_ilp32.c arm64: ilp32: share aarch32 syscall handlers arm64: ilp32: introduce syscall table for ILP32 arm64: signal: share lp64 signal structures and routines to ilp32 arm64: signal32: move ilp32 and aarch32 common code to separated file arm64: ilp32: introduce ilp32-specific sigframe and ucontext arm64: ptrace: handle ptrace_request differently for aarch32 and ilp32 Documentation/arm64/ilp32.txt | 52 +++ arch/arm64/Kconfig | 20 +- arch/arm64/Makefile | 3 + arch/arm64/include/asm/arch_timer.h | 4 +- arch/arm64/include/asm/compat.h | 19 +- arch/arm64/include/asm/elf.h | 37 +- arch/arm64/include/asm/fpsimd.h | 2 +- arch/arm64/include/asm/ftrace.h | 2 +- arch/arm64/include/asm/hwcap.h | 8 +- arch/arm64/include/asm/is_compat.h | 78 ++++ arch/arm64/include/asm/processor.h | 15 +- arch/arm64/include/asm/ptrace.h | 10 +- arch/arm64/include/asm/seccomp.h | 32 +- arch/arm64/include/asm/signal32.h | 31 +- arch/arm64/include/asm/signal32_common.h | 13 + arch/arm64/include/asm/signal_common.h | 303 +++++++++++++++ arch/arm64/include/asm/signal_ilp32.h | 23 ++ arch/arm64/include/asm/syscall.h | 17 +- arch/arm64/include/asm/thread_info.h | 4 +- arch/arm64/include/asm/unistd.h | 5 + arch/arm64/include/asm/vdso.h | 6 + arch/arm64/include/uapi/asm/bitsperlong.h | 9 +- arch/arm64/include/uapi/asm/unistd.h | 15 +- arch/arm64/kernel/Makefile | 8 +- arch/arm64/kernel/armv8_deprecated.c | 6 +- arch/arm64/kernel/asm-offsets.c | 13 +- arch/arm64/kernel/binfmt_elf32.c | 34 ++ arch/arm64/kernel/binfmt_ilp32.c | 88 +++++ arch/arm64/kernel/cpufeature.c | 30 +- arch/arm64/kernel/cpuinfo.c | 18 +- arch/arm64/kernel/debug-monitors.c | 4 +- arch/arm64/kernel/entry-common.c | 4 +- arch/arm64/kernel/entry.S | 6 +- arch/arm64/kernel/head.S | 2 +- arch/arm64/kernel/hw_breakpoint.c | 8 +- arch/arm64/kernel/perf_callchain.c | 28 +- arch/arm64/kernel/perf_regs.c | 4 +- arch/arm64/kernel/process.c | 15 +- arch/arm64/kernel/proton-pack.c | 2 +- arch/arm64/kernel/ptrace.c | 38 +- arch/arm64/kernel/signal.c | 348 ++++-------------- arch/arm64/kernel/signal32.c | 97 ++--- arch/arm64/kernel/signal32_common.c | 37 ++ arch/arm64/kernel/signal_ilp32.c | 67 ++++ arch/arm64/kernel/sys32.c | 104 +----- arch/arm64/kernel/sys32_common.c | 106 ++++++ arch/arm64/kernel/sys_compat.c | 12 +- arch/arm64/kernel/sys_ilp32.c | 82 +++++ arch/arm64/kernel/syscall.c | 39 +- arch/arm64/kernel/traps.c | 5 +- arch/arm64/kernel/vdso-ilp32/.gitignore | 2 + arch/arm64/kernel/vdso-ilp32/Makefile | 108 ++++++ arch/arm64/kernel/vdso-ilp32/vdso-ilp32.S | 22 ++ arch/arm64/kernel/vdso-ilp32/vdso-ilp32.lds.S | 88 +++++ arch/arm64/kernel/vdso.c | 50 ++- include/linux/sched.h | 1 + include/linux/thread_bits.h | 87 +++++ include/linux/thread_info.h | 75 +--- include/uapi/linux/audit.h | 1 + kernel/ptrace.c | 52 ++- 60 files changed, 1673 insertions(+), 726 deletions(-) create mode 100644 Documentation/arm64/ilp32.txt create mode 100644 arch/arm64/include/asm/is_compat.h create mode 100644 arch/arm64/include/asm/signal32_common.h create mode 100644 arch/arm64/include/asm/signal_common.h create mode 100644 arch/arm64/include/asm/signal_ilp32.h create mode 100644 arch/arm64/kernel/binfmt_elf32.c create mode 100644 arch/arm64/kernel/binfmt_ilp32.c create mode 100644 arch/arm64/kernel/signal32_common.c create mode 100644 arch/arm64/kernel/signal_ilp32.c create mode 100644 arch/arm64/kernel/sys32_common.c create mode 100644 arch/arm64/kernel/sys_ilp32.c create mode 100644 arch/arm64/kernel/vdso-ilp32/.gitignore create mode 100644 arch/arm64/kernel/vdso-ilp32/Makefile create mode 100644 arch/arm64/kernel/vdso-ilp32/vdso-ilp32.S create mode 100644 arch/arm64/kernel/vdso-ilp32/vdso-ilp32.lds.S create mode 100644 include/linux/thread_bits.h -- 2.25.0

2 25

[PATCH kernel-4.19 01/25] ascend: share_pool: make the function share_k2u_to_spg work
by Yang Yingliang 22 Dec '20

22 Dec '20

From: Ding Tianhong <dingtianhong(a)huawei.com> ascend inclusion category: feature bugzilla: NA CVE: NA ------------------------------------------------- The share_k2u_to_spg was designed to translate the kernel virtual address to user level address and share to the whole group, but tht function use the uncorrect file to mmap the memory region, it was not really work for whole group, and will consume more memory, fix this problem to use the correct hugepage file and make share to the whole group for each task. Signed-off-by: Ding Tianhong <dingtianhong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 117 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 87 insertions(+), 30 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index f8dfbe80968b..a83254200e33 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -267,7 +267,10 @@ static int spa_dec_usage(enum spa_type type, unsigned long size, bool is_dvpp) } static unsigned long sp_mmap(struct mm_struct *mm, struct file *file, - struct sp_area *spa, unsigned long *populate); + struct sp_area *spa, unsigned long *populate); +static void sp_munmap(struct mm_struct *mm, unsigned long addr, unsigned long size); +static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, + struct mm_struct *mm); static void free_sp_group_id(unsigned int spg_id) { @@ -596,6 +599,15 @@ int sp_group_add_task(int pid, int spg_id) atomic_inc(&spa->use_count); spin_unlock(&sp_area_lock); + if (spa->type == SPA_TYPE_K2SPG && spa->kva) { + addr = sp_remap_kva_to_vma(spa->kva, spa, mm); + if (IS_ERR_VALUE(addr)) + pr_warn("share pool: task add group remap k2u failed, ret %ld\n", addr); + + spin_lock(&sp_area_lock); + continue; + } + down_write(&mm->mmap_sem); addr = sp_mmap(mm, file, spa, &populate); if (IS_ERR_VALUE(addr)) { @@ -611,9 +623,11 @@ int sp_group_add_task(int pid, int spg_id) if (populate) { ret = do_mm_populate(mm, spa->va_start, populate, 0); if (ret) { - if (printk_ratelimit()) + if (printk_ratelimit()) { pr_warn("share pool: task add group failed when mm populate " - "failed (potential no enough memory): %d\n", ret); + "failed (potential no enough memory): %d " + "spa flag is %d\n", ret, spa->type); + } sp_munmap_task_areas(mm, spa->link.next); spin_lock(&sp_area_lock); break; @@ -1480,12 +1494,16 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, int hsize_log = MAP_HUGE_2MB >> MAP_HUGE_SHIFT; unsigned long addr, buf, offset; - if (spa->is_hugepage) { - file = hugetlb_file_setup(HUGETLB_ANON_FILE, spa_size(spa), VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE, hsize_log); - if (IS_ERR(file)) { - pr_err("share pool: file setup for k2u hugepage failed %ld\n", PTR_ERR(file)); - return PTR_ERR(file); + if (spg_valid(spa->spg)) { + file = spa_file(spa); + } else { + if (spa->is_hugepage) { + file = hugetlb_file_setup(HUGETLB_ANON_FILE, spa_size(spa), VM_NORESERVE, + &user, HUGETLB_ANONHUGE_INODE, hsize_log); + if (IS_ERR(file)) { + pr_err("share pool: file setup for k2u hugepage failed %ld\n", PTR_ERR(file)); + return PTR_ERR(file); + } } } @@ -1510,7 +1528,8 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, ret = remap_vmalloc_hugepage_range(vma, (void *)kva, 0); if (ret) { do_munmap(mm, ret_addr, spa_size(spa), NULL); - pr_err("share pool: remap vmalloc hugepage failed, ret %d\n", ret); + pr_err("share pool: remap vmalloc hugepage failed, " + "ret %d, kva is %lx\n", ret, kva); ret_addr = ret; goto put_mm; } @@ -1538,7 +1557,7 @@ static unsigned long sp_remap_kva_to_vma(unsigned long kva, struct sp_area *spa, up_write(&mm->mmap_sem); mmput(mm); put_file: - if (file) + if (!spa->spg && file) fput(file); return ret_addr; @@ -1615,6 +1634,35 @@ static void *sp_make_share_kva_to_spg(unsigned long kva, struct sp_area *spa, return p; } +static bool vmalloc_area_set_flag(struct sp_area *spa, unsigned long kva, unsigned long flags) +{ + struct vm_struct *area; + + area = find_vm_area((void *)kva); + if (area) { + area->flags |= flags; + spa->kva = kva; + return true; + } + + return false; +} + +static bool vmalloc_area_clr_flag(struct sp_area *spa, unsigned long kva, unsigned long flags) +{ + struct vm_struct *area; + + spa->kva = 0; + + area = find_vm_area((void *)kva); + if (area) { + area->flags &= ~flags; + return true; + } + + return false; +} + /** * Share kernel memory to a specified process or sp_group * @kva: the VA of shared kernel memory @@ -1638,7 +1686,6 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, unsigned long size_aligned; unsigned int page_size = PAGE_SIZE; int ret; - struct vm_struct *area; if (sp_flags & ~SP_DVPP) { if (printk_ratelimit()) @@ -1679,8 +1726,13 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, PTR_ERR(spa)); return spa; } + + if (!vmalloc_area_set_flag(spa, kva_aligned, VM_SHAREPOOL)) { + pr_err("%s: the kva %ld is not valid\n", __func__, kva_aligned); + goto out; + } + uva = sp_make_share_kva_to_task(kva_aligned, spa, pid); - mutex_unlock(&sp_mutex); } else if (spg_valid(spg)) { /* k2u to group */ if (spg_id != SPG_ID_DEFAULT && spg_id != spg->id) { @@ -1699,26 +1751,31 @@ void *sp_make_share_k2u(unsigned long kva, unsigned long size, return spa; } + if (!vmalloc_area_set_flag(spa, kva_aligned, VM_SHAREPOOL)) { + pr_err("%s: the kva %ld is not valid\n", __func__, kva_aligned); + goto out; + } + uva = sp_make_share_kva_to_spg(kva_aligned, spa, spg); - mutex_unlock(&sp_mutex); } else { mutex_unlock(&sp_mutex); pr_err("share pool: failed to make k2u\n"); return NULL; } - if (!IS_ERR(uva)) + if (!IS_ERR(uva)) { uva = uva + (kva - kva_aligned); + } else { + /* associate vma and spa */ + if (!vmalloc_area_clr_flag(spa, kva_aligned, VM_SHAREPOOL)) + pr_warn("share pool: %s: the kva %ld is not valid \n", + __func__, kva_aligned); + } +out: __sp_area_drop(spa); + mutex_unlock(&sp_mutex); - if (!IS_ERR(uva)) { - /* associate vma and spa */ - area = find_vm_area((void *)kva); - if (area) - area->flags |= VM_SHAREPOOL; - spa->kva = kva; - } sp_dump_stack(); return uva; @@ -1990,7 +2047,6 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp unsigned long uva_aligned; unsigned long size_aligned; unsigned int page_size; - struct vm_struct *area; mutex_lock(&sp_mutex); /* @@ -2061,7 +2117,7 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp if (printk_ratelimit()) pr_info("share pool: no need to unshare uva(to task), " "target process mm is exiting\n"); - goto out_drop_area; + goto out_clr_flag; } if (spa->mm != mm) { @@ -2095,7 +2151,7 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp if (printk_ratelimit()) pr_info("share pool: no need to unshare uva(to group), " "spa doesn't belong to a sp group or group is dead\n"); - goto out_drop_area; + goto out_clr_flag; } /* alway allow kthread and dvpp channel destroy procedure */ @@ -2112,11 +2168,12 @@ static int sp_unshare_uva(unsigned long uva, unsigned long size, int pid, int sp sp_dump_stack(); -out_drop_area: +out_clr_flag: /* deassociate vma and spa */ - area = find_vm_area((void *)spa->kva); - if (area) - area->flags &= ~VM_SHAREPOOL; + if (!vmalloc_area_clr_flag(spa, spa->kva, VM_SHAREPOOL)) + pr_warn("share pool: %s: the spa->kva %ld is not valid\n", __func__, spa->kva); + +out_drop_area: __sp_area_drop(spa); out_unlock: mutex_unlock(&sp_mutex); @@ -2162,7 +2219,7 @@ static int sp_unshare_kva(unsigned long kva, unsigned long size) if (page) put_page(page); else - pr_err("share pool: vmalloc %pK to page/hugepage failed\n", + pr_warn("share pool: vmalloc %pK to page/hugepage failed\n", (void *)addr); } -- 2.25.1

1 24

[PATCH v2 OLK-5.10 00/26] KVM RISC-V Support
by MingWang Li 22 Dec '20

22 Dec '20

From: Mingwang Li <limingwang(a)huawei.com> euleros inclusion category: feature feature: initial KVM RISC-V support bugzilla: 46845 CVE: NA This series adds initial KVM RISC-V support. Currently, we are able to boot Linux on RV64/RV32 Guest with multiple VCPUs. This series can be found in riscv_kvm_v15 branch at: https//github.com/avpatel/linux.git Changes since v1 - follow guileline for submiting patches to openEuler - add the testing result in this issue Reference: https://gitee.com/openeuler/kernel/issues/I26X9V Alistair Francis (1): Revert "riscv: Use latest system call ABI" Anup Patel (19): RISC-V: Add fragmented config for debug options RISC-V: Enable CPU Hotplug in defconfigs RISC-V: Add Microchip PolarFire kconfig option RISC-V: Initial DTS for Microchip ICICLE board RISC-V: Enable drivers for Microchip PolarFire ICICLE board RISC-V: Add hypervisor extension related CSR defines RISC-V: Add initial skeletal KVM support RISC-V: KVM: Implement VCPU create, init and destroy functions RISC-V: KVM: Implement VCPU interrupts and requests handling RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls RISC-V: KVM: Implement VCPU world-switch RISC-V: KVM: Handle MMIO exits for VCPU RISC-V: KVM: Handle WFI exits for VCPU RISC-V: KVM: Implement VMID allocator RISC-V: KVM: Implement stage2 page table programming RISC-V: KVM: Implement MMU notifiers RISC-V: KVM: Document RISC-V specific parts of KVM API RISC-V: KVM: Add MAINTAINERS entry RISC-V: Enable KVM for RV64 and RV32 Atish Patra (4): RISC-V: KVM: Add timer functionality RISC-V: KVM: FP lazy save/restore RISC-V: KVM: Implement ONE REG interface for FP registers RISC-V: KVM: Add SBI v0.1 support Mingwang Li (1): RISCV: KVM: fix bug in migration m34782 (1): Microchip Polarfire SoC Clock Driver Documentation/virt/kvm/api.rst | 193 +++- MAINTAINERS | 11 + arch/riscv/Kconfig | 2 + arch/riscv/Kconfig.socs | 7 + arch/riscv/Makefile | 2 + arch/riscv/boot/dts/Makefile | 1 + arch/riscv/boot/dts/microchip/Makefile | 2 + .../boot/dts/microchip/icicle-kit-es.dts | 307 +++++ arch/riscv/configs/defconfig | 30 +- arch/riscv/configs/extra_debug.config | 21 + arch/riscv/configs/rv32_defconfig | 26 +- arch/riscv/include/asm/csr.h | 89 ++ arch/riscv/include/asm/kvm_host.h | 278 +++++ arch/riscv/include/asm/kvm_types.h | 7 + arch/riscv/include/asm/kvm_vcpu_timer.h | 44 + arch/riscv/include/asm/pgtable-bits.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 128 +++ arch/riscv/include/uapi/asm/unistd.h | 5 +- arch/riscv/kernel/asm-offsets.c | 156 +++ arch/riscv/kvm/Kconfig | 36 + arch/riscv/kvm/Makefile | 15 + arch/riscv/kvm/main.c | 118 ++ arch/riscv/kvm/mmu.c | 860 ++++++++++++++ arch/riscv/kvm/tlb.S | 74 ++ arch/riscv/kvm/vcpu.c | 1012 +++++++++++++++++ arch/riscv/kvm/vcpu_exit.c | 701 ++++++++++++ arch/riscv/kvm/vcpu_sbi.c | 173 +++ arch/riscv/kvm/vcpu_switch.S | 400 +++++++ arch/riscv/kvm/vcpu_timer.c | 225 ++++ arch/riscv/kvm/vm.c | 81 ++ arch/riscv/kvm/vmid.c | 120 ++ drivers/clk/Kconfig | 5 + drivers/clk/Makefile | 1 + drivers/clk/microchip/Makefile | 2 + drivers/clk/microchip/clk-pfsoc.c | 508 +++++++++ drivers/clocksource/timer-riscv.c | 8 + include/clocksource/timer-riscv.h | 16 + include/uapi/linux/kvm.h | 8 + 38 files changed, 5619 insertions(+), 54 deletions(-) create mode 100644 arch/riscv/boot/dts/microchip/Makefile create mode 100644 arch/riscv/boot/dts/microchip/icicle-kit-es.dts create mode 100644 arch/riscv/configs/extra_debug.config create mode 100644 arch/riscv/include/asm/kvm_host.h create mode 100644 arch/riscv/include/asm/kvm_types.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_timer.h create mode 100644 arch/riscv/include/uapi/asm/kvm.h create mode 100644 arch/riscv/kvm/Kconfig create mode 100644 arch/riscv/kvm/Makefile create mode 100644 arch/riscv/kvm/main.c create mode 100644 arch/riscv/kvm/mmu.c create mode 100644 arch/riscv/kvm/tlb.S create mode 100644 arch/riscv/kvm/vcpu.c create mode 100644 arch/riscv/kvm/vcpu_exit.c create mode 100644 arch/riscv/kvm/vcpu_sbi.c create mode 100644 arch/riscv/kvm/vcpu_switch.S create mode 100644 arch/riscv/kvm/vcpu_timer.c create mode 100644 arch/riscv/kvm/vm.c create mode 100644 arch/riscv/kvm/vmid.c create mode 100644 drivers/clk/microchip/clk-pfsoc.c create mode 100644 include/clocksource/timer-riscv.h -- 2.19.1

4 30

[PATCH OLK-5.10 v3 0/4] kvm: debugfs: support vcpu_stat debugfs
by Jiajun Chen 22 Dec '20

22 Dec '20

From: chenjiajun <chenjiajun8(a)huawei.com> virt inclusion category: feature bugzilla: 46853 CVE: NA Export kvm vcpu info in debugfs entry /sys/kernel/debug/kvm/vcpu_stat, this entry contains kvm exits and cputime items now. And then, we can get all kvm vcpu info through this debugfs instead of one entry per kvm exits items, which will greatly facilitates the collection of performance status. Currently, only support x86 and aarch64. -- ChangeList: v3: modify kzfree in patches v2: modify architecture-dependent st_max to avoid compile err in other arches v1: kvm: debugfs: support vcpu_stat debugfs chenjiajun (4): kvm: debugfs: Export vcpu stat via debugfs kvm: debugfs: export remaining aarch64 kvm exit reasons to debugfs kvm: debugfs: aarch64 export cpu time related items to debugfs kvm: debugfs: Export x86 kvm exits to vcpu_stat arch/arm64/include/asm/kvm_host.h | 21 ++++ arch/arm64/kvm/arm.c | 23 +++++ arch/arm64/kvm/guest.c | 33 +++++++ arch/arm64/kvm/handle_exit.c | 8 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 1 + arch/arm64/kvm/mmu.c | 1 + arch/arm64/kvm/sys_regs.c | 11 +++ arch/x86/include/asm/kvm_host.h | 13 +++ arch/x86/kvm/vmx/vmx.c | 10 ++ arch/x86/kvm/x86.c | 70 +++++++++++++ include/linux/kvm_host.h | 19 ++++ virt/kvm/kvm_main.c | 125 ++++++++++++++++++++++++ 12 files changed, 335 insertions(+) -- 2.29.GIT

1 4

[PATCH OLK-5.10 0/4] kvm: debugfs: support vcpu_stat debugfs
by Jiajun Chen 22 Dec '20

22 Dec '20

From: chenjiajun <chenjiajun8(a)huawei.com> virt inclusion category: feature bugzilla: 46853 CVE: NA Export kvm vcpu info in debugfs entry /sys/kernel/debug/kvm/vcpu_stat, this entry contains kvm exits and cputime items now. And then, we can get all kvm vcpu info through this debugfs instead of one entry per kvm exits items, which will greatly facilitates the collection of performance status. Currently, only support x86 and aarch64. -- ChangeList: v3: modify kzfree in patches v2: modify architecture-dependent st_max to avoid compile err in other arches v1: kvm: debugfs: support vcpu_stat debugfs chenjiajun (4): kvm: debugfs: Export vcpu stat via debugfs kvm: debugfs: export remaining aarch64 kvm exit reasons to debugfs kvm: debugfs: aarch64 export cpu time related items to debugfs kvm: debugfs: Export x86 kvm exits to vcpu_stat arch/arm64/include/asm/kvm_host.h | 21 ++++ arch/arm64/kvm/arm.c | 23 +++++ arch/arm64/kvm/guest.c | 33 +++++++ arch/arm64/kvm/handle_exit.c | 8 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 1 + arch/arm64/kvm/mmu.c | 1 + arch/arm64/kvm/sys_regs.c | 11 +++ arch/x86/include/asm/kvm_host.h | 13 +++ arch/x86/kvm/vmx/vmx.c | 10 ++ arch/x86/kvm/x86.c | 70 +++++++++++++ include/linux/kvm_host.h | 19 ++++ virt/kvm/kvm_main.c | 125 ++++++++++++++++++++++++ 12 files changed, 335 insertions(+) -- 2.29.GIT

2 5

[PATCH OLK-5.10 0/3] Support MBIGEN
by Chen Jun 22 Dec '20

22 Dec '20

*** BLURB HERE *** Yang Yingliang (3): irqchip/mbigen: rename register marcros irqchip/mbigen: add support for a MBIGEN generating SPIs dt-bindings/irqchip/mbigen: add example of MBIGEN generate SPIs .../hisilicon,mbigen-v2.txt | 17 +++++++- drivers/irqchip/irq-mbigen.c | 39 +++++++++++++------ 2 files changed, 44 insertions(+), 12 deletions(-) -- 2.25.0

2 4

[PATCH OLK-5.10 0/4] kvm: debugfs: support vcpu_stat debugfs
by Jiajun Chen 22 Dec '20

22 Dec '20

From: chenjiajun <chenjiajun8(a)huawei.com> virt inclusion category: feature bugzilla: 46853 CVE: NA Export kvm vcpu info in debugfs entry /sys/kernel/debug/kvm/vcpu_stat, this entry contains kvm exits and cputime items now. And then, we can get all kvm vcpu info through this debugfs instead of one entry per kvm exits items, which will greatly facilitates the collection of performance status. Currently, only support x86 and aarch64. -- ChangeList: v2: modify architecture-dependent st_max to avoid compile err in other arches v1: kvm: debugfs: support vcpu_stat debugfs chenjiajun (4): kvm: debugfs: Export vcpu stat via debugfs kvm: debugfs: export remaining aarch64 kvm exit reasons to debugfs kvm: debugfs: aarch64 export cpu time related items to debugfs kvm: debugfs: Export x86 kvm exits to vcpu_stat arch/arm64/include/asm/kvm_host.h | 21 ++++ arch/arm64/kvm/arm.c | 23 +++++ arch/arm64/kvm/guest.c | 33 +++++++ arch/arm64/kvm/handle_exit.c | 8 ++ arch/arm64/kvm/hyp/include/hyp/switch.h | 1 + arch/arm64/kvm/mmu.c | 1 + arch/arm64/kvm/sys_regs.c | 11 +++ arch/x86/include/asm/kvm_host.h | 13 +++ arch/x86/kvm/vmx/vmx.c | 10 ++ arch/x86/kvm/x86.c | 70 +++++++++++++ include/linux/kvm_host.h | 19 ++++ virt/kvm/kvm_main.c | 124 ++++++++++++++++++++++++ 12 files changed, 334 insertions(+) -- 2.29.GIT

1 4

[PATCH OLK-5.10 1/1] PCI: Add MCFG quirks for some Hisilicon Chip host controllers
by Chen Jun 22 Dec '20

22 Dec '20

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> euler inclusion category: bugfix bugzilla: 46851 CVE: NA ------------------------------------------------- The PCIe controller in some Hisilicon Chip is not completely ECAM-compliant. Part of its PCIe cores do not support ECAM. Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: yangerkun <yangerkun(a)huawei.com> --- drivers/acpi/pci_mcfg.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c index 95f23acd5b80..3f310cfc9e7d 100644 --- a/drivers/acpi/pci_mcfg.c +++ b/drivers/acpi/pci_mcfg.c @@ -77,6 +77,10 @@ static struct mcfg_fixup mcfg_quirks[] = { HISI_QUAD_DOM("HIP07 ", 4, &hisi_pcie_ops), HISI_QUAD_DOM("HIP07 ", 8, &hisi_pcie_ops), HISI_QUAD_DOM("HIP07 ", 12, &hisi_pcie_ops), + HISI_QUAD_DOM("HIP12 ", 0x20, &hisi_pcie_ops), + HISI_QUAD_DOM("HIP12 ", 0x24, &hisi_pcie_ops), + HISI_QUAD_DOM("HIP12 ", 0x28, &hisi_pcie_ops), + HISI_QUAD_DOM("HIP12 ", 0x2c, &hisi_pcie_ops), #define THUNDER_PEM_RES(addr, node) \ DEFINE_RES_MEM((addr) + ((u64) (node) << 44), 0x39 * SZ_16M) -- 2.25.0

1 0

[PATCH OLK-5.10 0/2] Export some interfaces about cache
by Chen Jun 22 Dec '20

22 Dec '20

*** BLURB HERE *** Hanjun Guo (2): arm64: cache: Add flush_dcache_area() for module use arm64: cache: Export and add cache invalidation and clean ABIs for module use arch/arm64/include/asm/cacheflush.h | 51 +++++++++++++++++++++++++++++ arch/arm64/mm/flush.c | 3 ++ 2 files changed, 54 insertions(+) -- 2.25.0

1 2

[PATCH OLK-5.10 1/1] security: restrict init parameters by configuration
by Chen Jun 22 Dec '20

22 Dec '20

From: Xiangyu Lu <luxiangyu(a)huawei.com> euler inclusion category: bugfix bugzilla: 46850 CVE: NA --------------------------------- Linux kernel allow to specify a single-user mode, or specify the init process by init parameter, which could bypass the login authentication mechanisms, direct access to root identify. Close init kernel boot parameters through CONFIG_SECURITY_BOOT_INIT. Signed-off-by: Xiangyu Lu <luxiangyu(a)huawei.com> Reviewed-by: Wang Kai <morgan.wang(a)huawei.com> Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> [hj: backport from hulk-3.10 for security enhancement] Signed-off-by: Hanjun Guo <hanjun.guo(a)linaro.org> Signed-off-by: gaobo <gaobo794(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> --- init/main.c | 2 ++ security/Kconfig | 6 ++++++ 2 files changed, 8 insertions(+) diff --git a/init/main.c b/init/main.c index 32b2a8affafd..1e3c3371ea5d 100644 --- a/init/main.c +++ b/init/main.c @@ -572,6 +572,7 @@ static int __init unknown_bootoption(char *param, char *val, return 0; } +#ifndef CONFIG_SECURITY_BOOT_INIT static int __init init_setup(char *str) { unsigned int i; @@ -600,6 +601,7 @@ static int __init rdinit_setup(char *str) return 1; } __setup("rdinit=", rdinit_setup); +#endif #ifndef CONFIG_SMP static const unsigned int setup_max_cpus = NR_CPUS; diff --git a/security/Kconfig b/security/Kconfig index 7561f6f99f1d..a178816f61ed 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -291,5 +291,11 @@ config LSM source "security/Kconfig.hardening" +config SECURITY_BOOT_INIT + bool "Disable init & rdinit parameters in cmdline" + default n + help + No support init and rdinit parameters in cmdline + endmenu -- 2.25.0

1 0

[PATCH OLK-5.10 0/2] config: add initial openeuler_defconfig for arm64 & x86
by Xie XiuQi 21 Dec '20

21 Dec '20

Add initial configs for arm64 & x86 platform. Use openEuler-20.03's config as base, re-generate it on 5.10 kernel. The major changes: - use 52 bit VA & PA - enable CONFIG_PSI - support more kunpeng drivers on arm64 Xie XiuQi (2): config: add initial openeuler_defconfig for arm64 config: add initial openeuler_defconfig for x86 arch/arm64/configs/openeuler_defconfig | 7068 ++++++++++++++++++++ arch/x86/configs/openeuler_defconfig | 8271 ++++++++++++++++++++++++ 2 files changed, 15339 insertions(+) create mode 100644 arch/arm64/configs/openeuler_defconfig create mode 100644 arch/x86/configs/openeuler_defconfig -- 2.20.1

1 2

[PATCH OLK-5.10 1/1] ARM: mm: non-LPAE systems HugeTLB support for hulk
by Chen Jun 21 Dec '20

21 Dec '20

From: Linxu Fang <fanglinxu(a)huawei.com> maillist inclusion category: feature bugzilla: 46792 CVE: NA Reference: https://lists.linaro.org/pipermail/linaro-kernel/2013-October/008031.html ---------------------------------------- It's a improved version of Steve Capper's RFC patch, see: https://lists.linaro.org/pipermail/linaro-kernel/2013-October/008031.html Signed-off-by: Linxu Fang <fanglinxu(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> --- arch/arm/Kconfig | 2 +- arch/arm/include/asm/hugetlb-2level.h | 148 +++++++++++++++++++ arch/arm/include/asm/hugetlb.h | 6 +- arch/arm/include/asm/pgtable-2level-hwdef.h | 2 + arch/arm/include/asm/pgtable-2level.h | 154 +++++++++++++++++++- arch/arm/include/asm/pgtable-3level.h | 2 +- arch/arm/include/asm/pgtable.h | 14 ++ arch/arm/kernel/head.S | 4 + arch/arm/mm/fault.c | 26 ++-- arch/arm/mm/fsr-2level.c | 4 +- arch/arm/mm/hugetlbpage.c | 2 +- arch/arm/mm/mmu.c | 25 ++++ 12 files changed, 369 insertions(+), 20 deletions(-) create mode 100644 arch/arm/include/asm/hugetlb-2level.h diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 002e0cf025f5..3efce886d7a0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1545,7 +1545,7 @@ config HW_PERF_EVENTS config SYS_SUPPORTS_HUGETLBFS def_bool y - depends on ARM_LPAE + depends on ARM_LPAE || (!CPU_USE_DOMAINS && !MEMORY_FAILURE && !CPU_SW_DOMAIN_PAN) config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y diff --git a/arch/arm/include/asm/hugetlb-2level.h b/arch/arm/include/asm/hugetlb-2level.h new file mode 100644 index 000000000000..ce746dae2497 --- /dev/null +++ b/arch/arm/include/asm/hugetlb-2level.h @@ -0,0 +1,148 @@ +/* + * arch/arm/include/asm/hugetlb-2level.h + * + * Copyright (C) 2014 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ASM_ARM_HUGETLB_2LEVEL_H +#define _ASM_ARM_HUGETLB_2LEVEL_H + +#define __HAVE_ARCH_HUGE_PTEP_GET +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + pmd_t pmd = *((pmd_t *)ptep); + pte_t retval; + + if (!pmd_val(pmd)) + return __pte(0); + + retval = __pte((pteval_t) (pmd_val(pmd) & HPAGE_MASK) + | arm_hugepteprotval); + + if (pmd_exec(pmd)) + retval = pte_mkexec(retval); + else + retval = pte_mknexec(retval); + + if (pmd_young(pmd)) + retval = pte_mkyoung(retval); + else + retval = pte_mkold(retval); + + if (pmd_dirty(pmd)) + retval = pte_mkdirty(retval); + else + retval = pte_mkclean(retval); + + if (pmd_write(pmd)) + retval = pte_mkwrite(retval); + else + retval = pte_wrprotect(retval); + + if (pmd & PMD_SECT_BUFFERABLE) + retval |= PMD_SECT_BUFFERABLE; + else + retval &= ~PMD_SECT_BUFFERABLE; + + if (pmd & PMD_SECT_CACHEABLE) + retval |= PMD_SECT_CACHEABLE; + else + retval &= ~PMD_SECT_CACHEABLE; + + if (pmd & PMD_SECT_TEX(1)) + retval |= L_PTE_MT_DEV_SHARED; + else + retval &= ~L_PTE_MT_DEV_SHARED; + + if (pmd & PMD_SECT_S) + retval |= L_PTE_SHARED; + else + retval &= ~(L_PTE_SHARED); + + if (pmd_protnone(pmd)) + retval = pte_mkprotnone(retval); + else + retval = pte_rmprotnone(retval); + + return retval; +} + +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + pmdval_t pmdval = (pmdval_t) pte_val(pte); + pmd_t *pmdp = (pmd_t *) ptep; + + /* take the target address bits from the pte only */ + pmdval &= HPAGE_MASK; + + /* + * now use pmd_modify to translate the permission bits from the pte + * and set the memory type information. + */ + pmdval = pmd_val(pmd_modify(__pmd(pmdval), __pgprot(pte_val(pte)))); + + __sync_icache_dcache(pte); + + set_pmd_at(mm, addr, pmdp, __pmd(pmdval)); +} + +static inline pte_t pte_mkhuge(pte_t pte) { return pte; } + +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *)ptep; + + pmd_clear(pmdp); + flush_tlb_range(vma, addr, addr + HPAGE_SIZE); +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *) ptep; + + set_pmd_at(mm, addr, pmdp, pmd_wrprotect(*pmdp)); +} + +#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *)ptep; + pte_t pte = huge_ptep_get(ptep); + + pmd_clear(pmdp); + + return pte; +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + int changed = !pte_same(huge_ptep_get(ptep), pte); + + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_range(vma, addr, addr + HPAGE_SIZE); + } + + return changed; +} + +#endif /* _ASM_ARM_HUGETLB_2LEVEL_H */ diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index d02d6ca88e92..44fd1a5f3a32 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -11,7 +11,11 @@ #define _ASM_ARM_HUGETLB_H #include <asm/page.h> -#include <asm/hugetlb-3level.h> +#ifdef CONFIG_ARM_LPAE + #include <asm/hugetlb-3level.h> +#else +#include <asm/hugetlb-2level.h> +#endif #include <asm-generic/hugetlb.h> static inline void arch_clear_hugepage_flags(struct page *page) diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index 556937e1790e..b3ea5d00b5c7 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -20,7 +20,9 @@ #define PMD_PXNTABLE (_AT(pmdval_t, 1) << 2) /* v7 */ #define PMD_BIT4 (_AT(pmdval_t, 1) << 4) #define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#ifndef PMD_DOMAIN_MASK #define PMD_DOMAIN_MASK PMD_DOMAIN(0x0f) +#endif #define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ /* * - section diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index baf7d0204eb5..000feaf88248 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -7,6 +7,8 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H +#include <asm/tlbflush.h> + #define __PAGETABLE_PMD_FOLDED 1 /* @@ -185,13 +187,27 @@ #define pud_clear(pudp) do { } while (0) #define set_pud(pud,pudp) do { } while (0) +static inline int pmd_large(pmd_t pmd) +{ + if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_FAULT) + return pmd_val(pmd); + + return ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_SECT); +} + +static inline int pte_huge(pte_t pte) +{ + pmd_t pmd = (pmd_t)pte; + + return pmd_large(pmd); +} + static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) { return (pmd_t *)pud; } #define pmd_offset pmd_offset -#define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_leaf(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) #define pmd_present(pmd) (pmd_val(pmd)) @@ -215,6 +231,142 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) +/* + * now follows some of the definitions to allow huge page support, we can't put + * these in the hugetlb source files as they are also required for transparent + * hugepage support. + */ + +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#define HUGE_LINUX_PTE_COUNT (PAGE_OFFSET >> HPAGE_SHIFT) +#define HUGE_LINUX_PTE_SIZE (HUGE_LINUX_PTE_COUNT * sizeof(pte_t *)) +#define HUGE_LINUX_PTE_INDEX(addr) (addr >> HPAGE_SHIFT) + +/* + * We re-purpose the following domain bits in the section descriptor + */ +#ifndef PMD_DOMAIN_MASK +#define PMD_DOMAIN_MASK (_AT(pmdval_t, 0xF) << 5) +#endif +#define PMD_DSECT_PROT_NONE (_AT(pmdval_t, 1) << 5) +#define PMD_DSECT_DIRTY (_AT(pmdval_t, 1) << 6) +#define PMD_DSECT_AF (_AT(pmdval_t, 1) << 7) + +#define PMD_BIT_FUNC(fn, op) \ +static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } + +extern pmdval_t arm_hugepmdprotval; +extern pteval_t arm_hugepteprotval; + +#define pmd_mkhuge(pmd) (__pmd((pmd_val(pmd) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT)) + +PMD_BIT_FUNC(mkold, &= ~PMD_DSECT_AF); +PMD_BIT_FUNC(mkdirty, |= PMD_DSECT_DIRTY); +PMD_BIT_FUNC(mkclean, &= ~PMD_DSECT_DIRTY); +PMD_BIT_FUNC(mkyoung, |= PMD_DSECT_AF); +PMD_BIT_FUNC(mkwrite, |= PMD_SECT_AP_WRITE); +PMD_BIT_FUNC(wrprotect, &= ~PMD_SECT_AP_WRITE); +PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK); +PMD_BIT_FUNC(mkexec, &= ~PMD_SECT_XN); +PMD_BIT_FUNC(mknexec, |= PMD_SECT_XN); +PMD_BIT_FUNC(mkprotnone, |= PMD_DSECT_PROT_NONE); +PMD_BIT_FUNC(rmprotnone, &= ~PMD_DSECT_PROT_NONE); + +#ifdef CONFIG_NUMA_BALANCING +#define pmd_protnone(pmd) (pmd_val(pmd) & PMD_DSECT_PROT_NONE) +#else +static inline int pmd_protnone(pmd_t pmd); +#endif +#define pmd_young(pmd) (pmd_val(pmd) & PMD_DSECT_AF) +#define pmd_write(pmd) (pmd_val(pmd) & PMD_SECT_AP_WRITE) +#define pmd_exec(pmd) (!(pmd_val(pmd) & PMD_SECT_XN)) +#define pmd_dirty(pmd) (pmd_val(pmd) & PMD_DSECT_DIRTY) + +#define __HAVE_ARCH_PMD_WRITE + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + /* + * we can sometimes be passed a pmd pointing to a level 2 descriptor + * from collapse_huge_page. + */ + if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_TABLE) { + pmdp[0] = __pmd(pmd_val(pmd)); + pmdp[1] = __pmd(pmd_val(pmd) + 256 * sizeof(pte_t)); + } else { + if (pmd_protnone(pmd)) + pmd_val(pmd) &= ~PMD_TYPE_MASK; + else + pmd_val(pmd) |= PMD_TYPE_SECT; + + pmdp[0] = __pmd(pmd_val(pmd)); + pmdp[1] = __pmd(pmd_val(pmd) + SECTION_SIZE); + } + + flush_pmd_entry(pmdp); +} + +#define pmd_modify(pmd, prot) \ +({ \ + pmd_t pmdret = __pmd((pmd_val(pmd) \ + & (PMD_MASK | PMD_DOMAIN_MASK)) \ + | arm_hugepmdprotval); \ + pgprot_t inprot = prot; \ + pte_t newprot = __pte(pgprot_val(inprot)); \ + \ + if (pte_dirty(newprot)) \ + pmdret = pmd_mkdirty(pmdret); \ + else \ + pmdret = pmd_mkclean(pmdret); \ + \ + if (pte_exec(newprot)) \ + pmdret = pmd_mkexec(pmdret); \ + else \ + pmdret = pmd_mknexec(pmdret); \ + \ + if (pte_write(newprot)) \ + pmdret = pmd_mkwrite(pmdret); \ + else \ + pmdret = pmd_wrprotect(pmdret); \ + \ + if (pte_young(newprot)) \ + pmdret = pmd_mkyoung(pmdret); \ + else \ + pmdret = pmd_mkold(pmdret); \ + \ + if (pte_protnone(newprot)) \ + pmdret = pmd_mkprotnone(pmdret); \ + else \ + pmdret = pmd_rmprotnone(pmdret); \ + \ + if (pte_val(newprot) & PMD_SECT_BUFFERABLE) \ + pmdret |= PMD_SECT_BUFFERABLE; \ + else \ + pmdret &= ~PMD_SECT_BUFFERABLE; \ + \ + if (pte_val(newprot) & PMD_SECT_CACHEABLE) \ + pmdret |= PMD_SECT_CACHEABLE; \ + else \ + pmdret &= ~PMD_SECT_CACHEABLE; \ + \ + if (pte_val(newprot) & L_PTE_MT_DEV_SHARED) \ + pmdret |= PMD_SECT_TEX(1); \ + else \ + pmdret &= ~(PMD_SECT_TEX(1)); \ + \ + if (pte_val(newprot) & L_PTE_SHARED) \ + pmdret |= PMD_SECT_S; \ + else \ + pmdret &= ~PMD_SECT_S; \ + \ + pmdret; \ +}) + /* * We don't have huge page support for short descriptors, for the moment * define empty stubs for use by pin_page_for_write. diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 2b85d175e999..af53b40d1627 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -55,7 +55,7 @@ * Hugetlb definitions. */ #define HPAGE_SHIFT PMD_SHIFT -#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_SIZE (_AC(1, ULL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index c02f24400369..e3a6ebcfe415 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -196,6 +196,10 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG)) #define pte_exec(pte) (pte_isclear((pte), L_PTE_XN)) +#ifdef CONFIG_NUMA_BALANCING +#define pte_protnone(pte) (pte_val(pte) & L_PTE_NONE) +#endif + #define pte_valid_user(pte) \ (pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte)) @@ -274,6 +278,16 @@ static inline pte_t pte_mknexec(pte_t pte) return set_pte_bit(pte, __pgprot(L_PTE_XN)); } +static inline pte_t pte_mkprotnone(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(L_PTE_NONE)); +} + +static inline pte_t pte_rmprotnone(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(L_PTE_NONE)); +} + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f8904227e7fd..dfc95659bb89 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -460,8 +460,12 @@ __enable_mmu: #endif #ifdef CONFIG_ARM_LPAE mcrr p15, 0, r4, r5, c2 @ load TTBR0 +#else +#ifdef CONFIG_SYS_SUPPORTS_HUGETLBFS + ldr r5, =0x55555555 #else mov r5, #DACR_INIT +#endif mcr p15, 0, r5, c3, c0, 0 @ load domain access register mcr p15, 0, r4, c2, c0, 0 @ load page table pointer #endif diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index efa402025031..9985bab5ee66 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -26,6 +26,10 @@ #ifdef CONFIG_MMU +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) +#include <linux/hugetlb.h> +#endif + /* * This is useful to dump out the page tables associated with * 'addr' in mm 'mm'. @@ -76,6 +80,15 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr) break; if (pmd_bad(*pmd)) { +#if !defined(CONFIG_ARM_LPAE) && defined(CONFIG_HUGETLBFS) + if (pte_huge((pte_t)*pgd)) { + pte_t huge_pte = huge_ptep_get((pte_t *)pgd); + + pr_alert("[%08lx] *ppgd=%08llx", addr, + (long long)pmd_val(huge_pte)); + break; + } +#endif pr_cont("(bad)"); break; } @@ -462,19 +475,6 @@ do_translation_fault(unsigned long addr, unsigned int fsr, } #endif /* CONFIG_MMU */ -/* - * Some section permission faults need to be handled gracefully. - * They can happen due to a __{get,put}_user during an oops. - */ -#ifndef CONFIG_ARM_LPAE -static int -do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) -{ - do_bad_area(addr, fsr, regs); - return 0; -} -#endif /* CONFIG_ARM_LPAE */ - /* * This abort handler always returns "fault". */ diff --git a/arch/arm/mm/fsr-2level.c b/arch/arm/mm/fsr-2level.c index f2be95197265..f22e33ab0dc6 100644 --- a/arch/arm/mm/fsr-2level.c +++ b/arch/arm/mm/fsr-2level.c @@ -17,7 +17,7 @@ static struct fsr_info fsr_info[] = { { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, /* @@ -57,7 +57,7 @@ static struct fsr_info ifsr_info[] = { { do_bad, SIGBUS, 0, "unknown 10" }, { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, { do_bad, SIGBUS, 0, "unknown 16" }, diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index dd7a0277c5c0..5ede7ef5e531 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -30,5 +30,5 @@ int pud_huge(pud_t pud) int pmd_huge(pmd_t pmd) { - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); + return pmd_large(pmd); } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ab69250a86bc..911ce69f04a0 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -402,6 +402,20 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); } +/* + * If the system supports huge pages and we are running with short descriptors, + * then compute the pmd and linux pte prot values for a huge page. + * + * These values are used by both the HugeTLB and THP code. + */ +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) +pmdval_t arm_hugepmdprotval; +EXPORT_SYMBOL(arm_hugepmdprotval); + +pteval_t arm_hugepteprotval; +EXPORT_SYMBOL(arm_hugepteprotval); +#endif + /* * Adjust the PMD section entries according to the CPU in use. */ @@ -667,6 +681,17 @@ static void __init build_mem_type_table(void) if (t->prot_sect) t->prot_sect |= PMD_DOMAIN(t->domain); } + +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) + /* + * we assume all huge pages are user pages and that hardware access + * flag updates are disabled (i.e. SCTLR.AFE == 0b). + */ + arm_hugepteprotval = mem_types[MT_MEMORY_RWX].prot_pte | L_PTE_USER | L_PTE_VALID; + + arm_hugepmdprotval = mem_types[MT_MEMORY_RWX].prot_sect | PMD_SECT_AP_READ + | PMD_SECT_nG; +#endif } #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE -- 2.25.0

2 1

[PATCH OLK-5.10 1/1] ARM: mm: non-LPAE systems HugeTLB support for hulk
by Chen Jun 21 Dec '20

21 Dec '20

From: f00440829 <fanglinxu(a)huawei.com> euler inclusion category: feature bugzilla: 46792 CVE: NA ---------------------------------------- It's a improved version of Steve Capper's RFC patch, see: https://lists.linaro.org/pipermail/linaro-kernel/2013-October/008031.html Signed-off-by: Linxu Fang <fanglinxu(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Jing Xiangfeng <jingxiangfeng(a)huawei.com> Signed-off-by: Chen Jun <chenjun102(a)huawei.com> --- arch/arm/Kconfig | 2 +- arch/arm/include/asm/hugetlb-2level.h | 148 +++++++++++++++++++ arch/arm/include/asm/hugetlb.h | 6 +- arch/arm/include/asm/pgtable-2level-hwdef.h | 2 + arch/arm/include/asm/pgtable-2level.h | 154 +++++++++++++++++++- arch/arm/include/asm/pgtable-3level.h | 2 +- arch/arm/include/asm/pgtable.h | 14 ++ arch/arm/kernel/head.S | 4 + arch/arm/mm/fault.c | 26 ++-- arch/arm/mm/fsr-2level.c | 4 +- arch/arm/mm/hugetlbpage.c | 2 +- arch/arm/mm/mmu.c | 25 ++++ 12 files changed, 369 insertions(+), 20 deletions(-) create mode 100644 arch/arm/include/asm/hugetlb-2level.h diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 002e0cf025f5..3efce886d7a0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1545,7 +1545,7 @@ config HW_PERF_EVENTS config SYS_SUPPORTS_HUGETLBFS def_bool y - depends on ARM_LPAE + depends on ARM_LPAE || (!CPU_USE_DOMAINS && !MEMORY_FAILURE && !CPU_SW_DOMAIN_PAN) config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y diff --git a/arch/arm/include/asm/hugetlb-2level.h b/arch/arm/include/asm/hugetlb-2level.h new file mode 100644 index 000000000000..ce746dae2497 --- /dev/null +++ b/arch/arm/include/asm/hugetlb-2level.h @@ -0,0 +1,148 @@ +/* + * arch/arm/include/asm/hugetlb-2level.h + * + * Copyright (C) 2014 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _ASM_ARM_HUGETLB_2LEVEL_H +#define _ASM_ARM_HUGETLB_2LEVEL_H + +#define __HAVE_ARCH_HUGE_PTEP_GET +static inline pte_t huge_ptep_get(pte_t *ptep) +{ + pmd_t pmd = *((pmd_t *)ptep); + pte_t retval; + + if (!pmd_val(pmd)) + return __pte(0); + + retval = __pte((pteval_t) (pmd_val(pmd) & HPAGE_MASK) + | arm_hugepteprotval); + + if (pmd_exec(pmd)) + retval = pte_mkexec(retval); + else + retval = pte_mknexec(retval); + + if (pmd_young(pmd)) + retval = pte_mkyoung(retval); + else + retval = pte_mkold(retval); + + if (pmd_dirty(pmd)) + retval = pte_mkdirty(retval); + else + retval = pte_mkclean(retval); + + if (pmd_write(pmd)) + retval = pte_mkwrite(retval); + else + retval = pte_wrprotect(retval); + + if (pmd & PMD_SECT_BUFFERABLE) + retval |= PMD_SECT_BUFFERABLE; + else + retval &= ~PMD_SECT_BUFFERABLE; + + if (pmd & PMD_SECT_CACHEABLE) + retval |= PMD_SECT_CACHEABLE; + else + retval &= ~PMD_SECT_CACHEABLE; + + if (pmd & PMD_SECT_TEX(1)) + retval |= L_PTE_MT_DEV_SHARED; + else + retval &= ~L_PTE_MT_DEV_SHARED; + + if (pmd & PMD_SECT_S) + retval |= L_PTE_SHARED; + else + retval &= ~(L_PTE_SHARED); + + if (pmd_protnone(pmd)) + retval = pte_mkprotnone(retval); + else + retval = pte_rmprotnone(retval); + + return retval; +} + +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT +static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + pmdval_t pmdval = (pmdval_t) pte_val(pte); + pmd_t *pmdp = (pmd_t *) ptep; + + /* take the target address bits from the pte only */ + pmdval &= HPAGE_MASK; + + /* + * now use pmd_modify to translate the permission bits from the pte + * and set the memory type information. + */ + pmdval = pmd_val(pmd_modify(__pmd(pmdval), __pgprot(pte_val(pte)))); + + __sync_icache_dcache(pte); + + set_pmd_at(mm, addr, pmdp, __pmd(pmdval)); +} + +static inline pte_t pte_mkhuge(pte_t pte) { return pte; } + +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *)ptep; + + pmd_clear(pmdp); + flush_tlb_range(vma, addr, addr + HPAGE_SIZE); +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *) ptep; + + set_pmd_at(mm, addr, pmdp, pmd_wrprotect(*pmdp)); +} + +#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR +static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *)ptep; + pte_t pte = huge_ptep_get(ptep); + + pmd_clear(pmdp); + + return pte; +} + +#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + int changed = !pte_same(huge_ptep_get(ptep), pte); + + if (changed) { + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + flush_tlb_range(vma, addr, addr + HPAGE_SIZE); + } + + return changed; +} + +#endif /* _ASM_ARM_HUGETLB_2LEVEL_H */ diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h index d02d6ca88e92..44fd1a5f3a32 100644 --- a/arch/arm/include/asm/hugetlb.h +++ b/arch/arm/include/asm/hugetlb.h @@ -11,7 +11,11 @@ #define _ASM_ARM_HUGETLB_H #include <asm/page.h> -#include <asm/hugetlb-3level.h> +#ifdef CONFIG_ARM_LPAE + #include <asm/hugetlb-3level.h> +#else +#include <asm/hugetlb-2level.h> +#endif #include <asm-generic/hugetlb.h> static inline void arch_clear_hugepage_flags(struct page *page) diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h index 556937e1790e..b3ea5d00b5c7 100644 --- a/arch/arm/include/asm/pgtable-2level-hwdef.h +++ b/arch/arm/include/asm/pgtable-2level-hwdef.h @@ -20,7 +20,9 @@ #define PMD_PXNTABLE (_AT(pmdval_t, 1) << 2) /* v7 */ #define PMD_BIT4 (_AT(pmdval_t, 1) << 4) #define PMD_DOMAIN(x) (_AT(pmdval_t, (x)) << 5) +#ifndef PMD_DOMAIN_MASK #define PMD_DOMAIN_MASK PMD_DOMAIN(0x0f) +#endif #define PMD_PROTECTION (_AT(pmdval_t, 1) << 9) /* v5 */ /* * - section diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index baf7d0204eb5..000feaf88248 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -7,6 +7,8 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H +#include <asm/tlbflush.h> + #define __PAGETABLE_PMD_FOLDED 1 /* @@ -185,13 +187,27 @@ #define pud_clear(pudp) do { } while (0) #define set_pud(pud,pudp) do { } while (0) +static inline int pmd_large(pmd_t pmd) +{ + if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_FAULT) + return pmd_val(pmd); + + return ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_SECT); +} + +static inline int pte_huge(pte_t pte) +{ + pmd_t pmd = (pmd_t)pte; + + return pmd_large(pmd); +} + static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) { return (pmd_t *)pud; } #define pmd_offset pmd_offset -#define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_leaf(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) #define pmd_present(pmd) (pmd_val(pmd)) @@ -215,6 +231,142 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext) +/* + * now follows some of the definitions to allow huge page support, we can't put + * these in the hugetlb source files as they are also required for transparent + * hugepage support. + */ + +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#define HUGE_LINUX_PTE_COUNT (PAGE_OFFSET >> HPAGE_SHIFT) +#define HUGE_LINUX_PTE_SIZE (HUGE_LINUX_PTE_COUNT * sizeof(pte_t *)) +#define HUGE_LINUX_PTE_INDEX(addr) (addr >> HPAGE_SHIFT) + +/* + * We re-purpose the following domain bits in the section descriptor + */ +#ifndef PMD_DOMAIN_MASK +#define PMD_DOMAIN_MASK (_AT(pmdval_t, 0xF) << 5) +#endif +#define PMD_DSECT_PROT_NONE (_AT(pmdval_t, 1) << 5) +#define PMD_DSECT_DIRTY (_AT(pmdval_t, 1) << 6) +#define PMD_DSECT_AF (_AT(pmdval_t, 1) << 7) + +#define PMD_BIT_FUNC(fn, op) \ +static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; } + +extern pmdval_t arm_hugepmdprotval; +extern pteval_t arm_hugepteprotval; + +#define pmd_mkhuge(pmd) (__pmd((pmd_val(pmd) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT)) + +PMD_BIT_FUNC(mkold, &= ~PMD_DSECT_AF); +PMD_BIT_FUNC(mkdirty, |= PMD_DSECT_DIRTY); +PMD_BIT_FUNC(mkclean, &= ~PMD_DSECT_DIRTY); +PMD_BIT_FUNC(mkyoung, |= PMD_DSECT_AF); +PMD_BIT_FUNC(mkwrite, |= PMD_SECT_AP_WRITE); +PMD_BIT_FUNC(wrprotect, &= ~PMD_SECT_AP_WRITE); +PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK); +PMD_BIT_FUNC(mkexec, &= ~PMD_SECT_XN); +PMD_BIT_FUNC(mknexec, |= PMD_SECT_XN); +PMD_BIT_FUNC(mkprotnone, |= PMD_DSECT_PROT_NONE); +PMD_BIT_FUNC(rmprotnone, &= ~PMD_DSECT_PROT_NONE); + +#ifdef CONFIG_NUMA_BALANCING +#define pmd_protnone(pmd) (pmd_val(pmd) & PMD_DSECT_PROT_NONE) +#else +static inline int pmd_protnone(pmd_t pmd); +#endif +#define pmd_young(pmd) (pmd_val(pmd) & PMD_DSECT_AF) +#define pmd_write(pmd) (pmd_val(pmd) & PMD_SECT_AP_WRITE) +#define pmd_exec(pmd) (!(pmd_val(pmd) & PMD_SECT_XN)) +#define pmd_dirty(pmd) (pmd_val(pmd) & PMD_DSECT_DIRTY) + +#define __HAVE_ARCH_PMD_WRITE + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + /* + * we can sometimes be passed a pmd pointing to a level 2 descriptor + * from collapse_huge_page. + */ + if ((pmd_val(pmd) & PMD_TYPE_MASK) == PMD_TYPE_TABLE) { + pmdp[0] = __pmd(pmd_val(pmd)); + pmdp[1] = __pmd(pmd_val(pmd) + 256 * sizeof(pte_t)); + } else { + if (pmd_protnone(pmd)) + pmd_val(pmd) &= ~PMD_TYPE_MASK; + else + pmd_val(pmd) |= PMD_TYPE_SECT; + + pmdp[0] = __pmd(pmd_val(pmd)); + pmdp[1] = __pmd(pmd_val(pmd) + SECTION_SIZE); + } + + flush_pmd_entry(pmdp); +} + +#define pmd_modify(pmd, prot) \ +({ \ + pmd_t pmdret = __pmd((pmd_val(pmd) \ + & (PMD_MASK | PMD_DOMAIN_MASK)) \ + | arm_hugepmdprotval); \ + pgprot_t inprot = prot; \ + pte_t newprot = __pte(pgprot_val(inprot)); \ + \ + if (pte_dirty(newprot)) \ + pmdret = pmd_mkdirty(pmdret); \ + else \ + pmdret = pmd_mkclean(pmdret); \ + \ + if (pte_exec(newprot)) \ + pmdret = pmd_mkexec(pmdret); \ + else \ + pmdret = pmd_mknexec(pmdret); \ + \ + if (pte_write(newprot)) \ + pmdret = pmd_mkwrite(pmdret); \ + else \ + pmdret = pmd_wrprotect(pmdret); \ + \ + if (pte_young(newprot)) \ + pmdret = pmd_mkyoung(pmdret); \ + else \ + pmdret = pmd_mkold(pmdret); \ + \ + if (pte_protnone(newprot)) \ + pmdret = pmd_mkprotnone(pmdret); \ + else \ + pmdret = pmd_rmprotnone(pmdret); \ + \ + if (pte_val(newprot) & PMD_SECT_BUFFERABLE) \ + pmdret |= PMD_SECT_BUFFERABLE; \ + else \ + pmdret &= ~PMD_SECT_BUFFERABLE; \ + \ + if (pte_val(newprot) & PMD_SECT_CACHEABLE) \ + pmdret |= PMD_SECT_CACHEABLE; \ + else \ + pmdret &= ~PMD_SECT_CACHEABLE; \ + \ + if (pte_val(newprot) & L_PTE_MT_DEV_SHARED) \ + pmdret |= PMD_SECT_TEX(1); \ + else \ + pmdret &= ~(PMD_SECT_TEX(1)); \ + \ + if (pte_val(newprot) & L_PTE_SHARED) \ + pmdret |= PMD_SECT_S; \ + else \ + pmdret &= ~PMD_SECT_S; \ + \ + pmdret; \ +}) + /* * We don't have huge page support for short descriptors, for the moment * define empty stubs for use by pin_page_for_write. diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 2b85d175e999..af53b40d1627 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -55,7 +55,7 @@ * Hugetlb definitions. */ #define HPAGE_SHIFT PMD_SHIFT -#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_SIZE (_AC(1, ULL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index c02f24400369..e3a6ebcfe415 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -196,6 +196,10 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd) #define pte_young(pte) (pte_isset((pte), L_PTE_YOUNG)) #define pte_exec(pte) (pte_isclear((pte), L_PTE_XN)) +#ifdef CONFIG_NUMA_BALANCING +#define pte_protnone(pte) (pte_val(pte) & L_PTE_NONE) +#endif + #define pte_valid_user(pte) \ (pte_valid(pte) && pte_isset((pte), L_PTE_USER) && pte_young(pte)) @@ -274,6 +278,16 @@ static inline pte_t pte_mknexec(pte_t pte) return set_pte_bit(pte, __pgprot(L_PTE_XN)); } +static inline pte_t pte_mkprotnone(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(L_PTE_NONE)); +} + +static inline pte_t pte_rmprotnone(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(L_PTE_NONE)); +} + static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S index f8904227e7fd..dfc95659bb89 100644 --- a/arch/arm/kernel/head.S +++ b/arch/arm/kernel/head.S @@ -460,8 +460,12 @@ __enable_mmu: #endif #ifdef CONFIG_ARM_LPAE mcrr p15, 0, r4, r5, c2 @ load TTBR0 +#else +#ifdef CONFIG_SYS_SUPPORTS_HUGETLBFS + ldr r5, =0x55555555 #else mov r5, #DACR_INIT +#endif mcr p15, 0, r5, c3, c0, 0 @ load domain access register mcr p15, 0, r4, c2, c0, 0 @ load page table pointer #endif diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index efa402025031..9985bab5ee66 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -26,6 +26,10 @@ #ifdef CONFIG_MMU +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) +#include <linux/hugetlb.h> +#endif + /* * This is useful to dump out the page tables associated with * 'addr' in mm 'mm'. @@ -76,6 +80,15 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr) break; if (pmd_bad(*pmd)) { +#if !defined(CONFIG_ARM_LPAE) && defined(CONFIG_HUGETLBFS) + if (pte_huge((pte_t)*pgd)) { + pte_t huge_pte = huge_ptep_get((pte_t *)pgd); + + pr_alert("[%08lx] *ppgd=%08llx", addr, + (long long)pmd_val(huge_pte)); + break; + } +#endif pr_cont("(bad)"); break; } @@ -462,19 +475,6 @@ do_translation_fault(unsigned long addr, unsigned int fsr, } #endif /* CONFIG_MMU */ -/* - * Some section permission faults need to be handled gracefully. - * They can happen due to a __{get,put}_user during an oops. - */ -#ifndef CONFIG_ARM_LPAE -static int -do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) -{ - do_bad_area(addr, fsr, regs); - return 0; -} -#endif /* CONFIG_ARM_LPAE */ - /* * This abort handler always returns "fault". */ diff --git a/arch/arm/mm/fsr-2level.c b/arch/arm/mm/fsr-2level.c index f2be95197265..f22e33ab0dc6 100644 --- a/arch/arm/mm/fsr-2level.c +++ b/arch/arm/mm/fsr-2level.c @@ -17,7 +17,7 @@ static struct fsr_info fsr_info[] = { { do_bad, SIGBUS, 0, "external abort on non-linefetch" }, { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, /* @@ -57,7 +57,7 @@ static struct fsr_info ifsr_info[] = { { do_bad, SIGBUS, 0, "unknown 10" }, { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, - { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" }, { do_bad, SIGBUS, 0, "external abort on translation" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" }, { do_bad, SIGBUS, 0, "unknown 16" }, diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index dd7a0277c5c0..5ede7ef5e531 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -30,5 +30,5 @@ int pud_huge(pud_t pud) int pmd_huge(pmd_t pmd) { - return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); + return pmd_large(pmd); } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ab69250a86bc..911ce69f04a0 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -402,6 +402,20 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE); } +/* + * If the system supports huge pages and we are running with short descriptors, + * then compute the pmd and linux pte prot values for a huge page. + * + * These values are used by both the HugeTLB and THP code. + */ +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) +pmdval_t arm_hugepmdprotval; +EXPORT_SYMBOL(arm_hugepmdprotval); + +pteval_t arm_hugepteprotval; +EXPORT_SYMBOL(arm_hugepteprotval); +#endif + /* * Adjust the PMD section entries according to the CPU in use. */ @@ -667,6 +681,17 @@ static void __init build_mem_type_table(void) if (t->prot_sect) t->prot_sect |= PMD_DOMAIN(t->domain); } + +#if defined(CONFIG_SYS_SUPPORTS_HUGETLBFS) && !defined(CONFIG_ARM_LPAE) + /* + * we assume all huge pages are user pages and that hardware access + * flag updates are disabled (i.e. SCTLR.AFE == 0b). + */ + arm_hugepteprotval = mem_types[MT_MEMORY_RWX].prot_pte | L_PTE_USER | L_PTE_VALID; + + arm_hugepmdprotval = mem_types[MT_MEMORY_RWX].prot_sect | PMD_SECT_AP_READ + | PMD_SECT_nG; +#endif } #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE -- 2.25.0

1 0

[PATCH v3 OLK-5.10 0/2] Backport 5.10.1 LTS
by Chen Jun 21 Dec '20

21 Dec '20

v2->v3: remove the patch "Linux-5.10.1.patch" v1->v2: modifty the commit message: linux-5.10.1 -> stable-5.10.1 *** BLURB HERE *** Greg Kroah-Hartman (2): Revert "md: change mddev 'chunk_sectors' from int to unsigned" Revert "dm raid: fix discard limits for raid1 and raid10" drivers/md/dm-raid.c | 12 +++++------- drivers/md/md.h | 4 ++-- 2 files changed, 7 insertions(+), 9 deletions(-) -- 2.25.0

1 2

[PATCH openEuler-1.0-LTS] defconfig: update the defconfigs to support NVDIMM
by Xie XiuQi 21 Dec '20

21 Dec '20

From: Hanjun Guo <guohanjun(a)huawei.com> hulk inclusion category: feature feature: ACPI NVDIMM Firmware Interface Table (NFIT) bugzilla: 46783 CVE: NA Reference: https://gitee.com/open_euler/dashboard/issues?id=I26KWQ Backport this patch from kernel-4.19 to openEuler 20.03 LTS SP1. 564e83bbdcae defconfig: update the defconfigs to support NVDIMM --------------------------- openEuler wants NVDIMM support, update the defconfig. Signed-off-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Signed-off-by: Xie XiuQi <xiexiuqi(a)huawei.com> --- arch/arm64/configs/hulk_defconfig | 2 +- arch/arm64/configs/openeuler_defconfig | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/configs/hulk_defconfig b/arch/arm64/configs/hulk_defconfig index 20c7c527dc33..090ff6c93730 100644 --- a/arch/arm64/configs/hulk_defconfig +++ b/arch/arm64/configs/hulk_defconfig @@ -635,7 +635,7 @@ CONFIG_ACPI_HED=y # CONFIG_ACPI_CUSTOM_METHOD is not set # CONFIG_ACPI_BGRT is not set CONFIG_ACPI_REDUCED_HARDWARE_ONLY=y -# CONFIG_ACPI_NFIT is not set +CONFIG_ACPI_NFIT=m CONFIG_HAVE_ACPI_APEI=y CONFIG_ACPI_APEI=y CONFIG_ACPI_APEI_GHES=y diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig index c68f4c9ee65c..5561751ad6eb 100644 --- a/arch/arm64/configs/openeuler_defconfig +++ b/arch/arm64/configs/openeuler_defconfig @@ -627,7 +627,7 @@ CONFIG_ACPI_HED=y # CONFIG_ACPI_CUSTOM_METHOD is not set # CONFIG_ACPI_BGRT is not set CONFIG_ACPI_REDUCED_HARDWARE_ONLY=y -# CONFIG_ACPI_NFIT is not set +CONFIG_ACPI_NFIT=m CONFIG_HAVE_ACPI_APEI=y CONFIG_ACPI_APEI=y CONFIG_ACPI_APEI_GHES=y -- 2.20.1

1 0

TCM(Nationz Tech) on SPI driver for openEuler
by Li ZhiGang 21 Dec '20

21 Dec '20

hi openEuler kernel team: 我是麒麟软件共性支撑部李志刚, 公司安排我将 TCM on SPI 的驱动移植到您的社区源码; 代码我已经核外编译验证过, 下一步请你们指导我将其放入你们社区(请告诉我最好放入哪个目录). 不好意思我没有社区开发经验, 请您告诉我如何开始好吧? 譬如是不需要我注册个账户, 最好有个简介性的文档. TCM 是国民技术公司的类米国 TPM 芯片/产品, 用于安全和可信计算等. 麒麟软件共性支撑部李志刚 2020-12-18

2 2

[PATCH OLK-5.10 00/26] KVM RISC-V Support
by MingWang Li 19 Dec '20

19 Dec '20

From: Mingwang Li <limingwang(a)huawei.com> euleros inclusion category: feature bugzilla: NA CVE: NA This series adds initial KVM RISC-V support. Currently, we are able to boot Linux on RV64/RV32 Guest with multiple VCPUs. This series can be found in riscv_kvm_v15 branch at: https//github.com/avpatel/linux.git Link: https://gitee.com/openeuler/kernel/issues/I26X9V Alistair Francis (1): Revert "riscv: Use latest system call ABI" Anup Patel (19): RISC-V: Add fragmented config for debug options RISC-V: Enable CPU Hotplug in defconfigs RISC-V: Add Microchip PolarFire kconfig option RISC-V: Initial DTS for Microchip ICICLE board RISC-V: Enable drivers for Microchip PolarFire ICICLE board RISC-V: Add hypervisor extension related CSR defines RISC-V: Add initial skeletal KVM support RISC-V: KVM: Implement VCPU create, init and destroy functions RISC-V: KVM: Implement VCPU interrupts and requests handling RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls RISC-V: KVM: Implement VCPU world-switch RISC-V: KVM: Handle MMIO exits for VCPU RISC-V: KVM: Handle WFI exits for VCPU RISC-V: KVM: Implement VMID allocator RISC-V: KVM: Implement stage2 page table programming RISC-V: KVM: Implement MMU notifiers RISC-V: KVM: Document RISC-V specific parts of KVM API RISC-V: KVM: Add MAINTAINERS entry RISC-V: Enable KVM for RV64 and RV32 Atish Patra (4): RISC-V: KVM: Add timer functionality RISC-V: KVM: FP lazy save/restore RISC-V: KVM: Implement ONE REG interface for FP registers RISC-V: KVM: Add SBI v0.1 support Mingwang Li (1): RISCV: KVM: fix bug in migration m34782 (1): Microchip Polarfire SoC Clock Driver Documentation/virt/kvm/api.rst | 193 +++- MAINTAINERS | 11 + arch/riscv/Kconfig | 2 + arch/riscv/Kconfig.socs | 7 + arch/riscv/Makefile | 2 + arch/riscv/boot/dts/Makefile | 1 + arch/riscv/boot/dts/microchip/Makefile | 2 + .../boot/dts/microchip/icicle-kit-es.dts | 307 +++++ arch/riscv/configs/defconfig | 30 +- arch/riscv/configs/extra_debug.config | 21 + arch/riscv/configs/rv32_defconfig | 26 +- arch/riscv/include/asm/csr.h | 89 ++ arch/riscv/include/asm/kvm_host.h | 278 +++++ arch/riscv/include/asm/kvm_types.h | 7 + arch/riscv/include/asm/kvm_vcpu_timer.h | 44 + arch/riscv/include/asm/pgtable-bits.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 128 +++ arch/riscv/include/uapi/asm/unistd.h | 5 +- arch/riscv/kernel/asm-offsets.c | 156 +++ arch/riscv/kvm/Kconfig | 36 + arch/riscv/kvm/Makefile | 15 + arch/riscv/kvm/main.c | 118 ++ arch/riscv/kvm/mmu.c | 860 ++++++++++++++ arch/riscv/kvm/tlb.S | 74 ++ arch/riscv/kvm/vcpu.c | 1012 +++++++++++++++++ arch/riscv/kvm/vcpu_exit.c | 701 ++++++++++++ arch/riscv/kvm/vcpu_sbi.c | 173 +++ arch/riscv/kvm/vcpu_switch.S | 400 +++++++ arch/riscv/kvm/vcpu_timer.c | 225 ++++ arch/riscv/kvm/vm.c | 81 ++ arch/riscv/kvm/vmid.c | 120 ++ drivers/clk/Kconfig | 5 + drivers/clk/Makefile | 1 + drivers/clk/microchip/Makefile | 2 + drivers/clk/microchip/clk-pfsoc.c | 508 +++++++++ drivers/clocksource/timer-riscv.c | 8 + include/clocksource/timer-riscv.h | 16 + include/uapi/linux/kvm.h | 8 + 38 files changed, 5619 insertions(+), 54 deletions(-) create mode 100644 arch/riscv/boot/dts/microchip/Makefile create mode 100644 arch/riscv/boot/dts/microchip/icicle-kit-es.dts create mode 100644 arch/riscv/configs/extra_debug.config create mode 100644 arch/riscv/include/asm/kvm_host.h create mode 100644 arch/riscv/include/asm/kvm_types.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_timer.h create mode 100644 arch/riscv/include/uapi/asm/kvm.h create mode 100644 arch/riscv/kvm/Kconfig create mode 100644 arch/riscv/kvm/Makefile create mode 100644 arch/riscv/kvm/main.c create mode 100644 arch/riscv/kvm/mmu.c create mode 100644 arch/riscv/kvm/tlb.S create mode 100644 arch/riscv/kvm/vcpu.c create mode 100644 arch/riscv/kvm/vcpu_exit.c create mode 100644 arch/riscv/kvm/vcpu_sbi.c create mode 100644 arch/riscv/kvm/vcpu_switch.S create mode 100644 arch/riscv/kvm/vcpu_timer.c create mode 100644 arch/riscv/kvm/vm.c create mode 100644 arch/riscv/kvm/vmid.c create mode 100644 drivers/clk/microchip/clk-pfsoc.c create mode 100644 include/clocksource/timer-riscv.h -- 2.19.1

2 27

[PATCH 1/4] net/hinic: Set default features when probe netdev
by Yang Yingliang 17 Dec '20

17 Dec '20

From: Chiqijun <chiqijun(a)huawei.com> driver inclusion category: bugfix bugzilla: 4472 ----------------------------------------------------------------------- In the x86 system, the hinic device turns off LRO by default, and the LRO state will not be set when the driver is loaded. If the LRO of the chip is turned on before the driver is loaded, it will cause the chip to still turn on LRO after reloading the driver, but the LRO that the user sees is turned off. Therefore, the driver is forced to set the default features of the device when probe. Signed-off-by: Chiqijun <chiqijun(a)huawei.com> Reviewed-by: Wangxiaoyun <cloud.wangxiaoyun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/net/ethernet/huawei/hinic/hinic_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index cf7b6ceef060..26cd2929f60a 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1491,7 +1491,7 @@ static int set_feature_lro(struct hinic_nic_dev *nic_dev, static int set_features(struct hinic_nic_dev *nic_dev, netdev_features_t pre_features, - netdev_features_t features, bool force_change) + netdev_features_t features) { netdev_features_t failed_features = 0; u32 err; @@ -1518,7 +1518,7 @@ static int hinic_set_features(struct net_device *netdev, struct hinic_nic_dev *nic_dev = netdev_priv(netdev); return set_features(nic_dev, nic_dev->netdev->features, - features, false); + features); } static netdev_features_t hinic_fix_features(struct net_device *netdev, @@ -1563,7 +1563,8 @@ static int hinic_set_default_hw_feature(struct hinic_nic_dev *nic_dev) } /* enable all hw features in netdev->features */ - return set_features(nic_dev, 0, nic_dev->netdev->features, true); + return set_features(nic_dev, ~nic_dev->netdev->features, + nic_dev->netdev->features); } static int hinic_setup_tc_mqprio(struct net_device *dev, -- 2.25.1

1 3

[PATCH 1/2] ext4: Protect superblock modifications with a buffer lock
by Yang Yingliang 17 Dec '20

17 Dec '20

From: Jan Kara <jack(a)suse.cz> hulk inclusion category: bugfix bugzilla: 46758 CVE: NA --------------------------- Protect all superblock modifications (including checksum computation) with a superblock buffer lock. That way we are sure computed checksum matches current superblock contents (a mismatch could cause checksum failures in nojournal mode or if an unjournalled superblock update races with a journalled one). Also we avoid modifying superblock contents while it is being written out (which can cause DIF/DIX failures if we are running in nojournal mode). Signed-off-by: Jan Kara <jack(a)suse.cz> [backport the 10th patch: https://www.spinics.net/lists/linux-ext4/msg75423.html drop the other lock_buffer besides operation for orphan] Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/ext4/ext4_jbd2.c | 1 - fs/ext4/file.c | 1 + fs/ext4/inode.c | 1 + fs/ext4/namei.c | 6 ++++++ fs/ext4/resize.c | 4 ++++ fs/ext4/xattr.c | 1 + 6 files changed, 13 insertions(+), 1 deletion(-) diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index a589b7f79558..f9ac7dfd93bf 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -361,7 +361,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; - ext4_superblock_csum_set(sb); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); if (err) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 52d155b4e733..1703871fa2d0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -434,6 +434,7 @@ static int ext4_sample_last_mounted(struct super_block *sb, goto out_journal; strlcpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); + ext4_superblock_csum_set(sb); ext4_handle_dirty_super(handle, sb); out_journal: ext4_journal_stop(handle); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8d7e2cd9ae37..6ee89cd7a408 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5398,6 +5398,7 @@ static int ext4_do_update_inode(handle_t *handle, if (err) goto out_brelse; ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); ext4_handle_sync(handle); err = ext4_handle_dirty_super(handle, sb); } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index ffc3695eb153..762eb6913240 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2889,7 +2889,10 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) (le32_to_cpu(sbi->s_es->s_inodes_count))) { /* Insert this inode at the head of the on-disk orphan list */ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan); + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); dirty = true; } list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan); @@ -2972,7 +2975,10 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); + ext4_superblock_csum_set(inode->i_sb); + unlock_buffer(sbi->s_sbh); mutex_unlock(&sbi->s_orphan_lock); err = ext4_handle_dirty_super(handle, inode->i_sb); } else { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 6a0c5c880354..c2e007d836e4 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -901,6 +901,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, ext4_kvfree_array_rcu(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); + ext4_superblock_csum_set(sb); err = ext4_handle_dirty_super(handle, sb); if (err) ext4_std_error(sb, err); @@ -1423,6 +1424,7 @@ static void ext4_update_super(struct super_block *sb, * active. */ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + reserved_blocks); + ext4_superblock_csum_set(sb); /* Update the free space counts */ percpu_counter_add(&sbi->s_freeclusters_counter, @@ -1721,6 +1723,7 @@ static int ext4_group_extend_no_check(struct super_block *sb, ext4_blocks_count_set(es, o_blocks_count + add); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add); + ext4_superblock_csum_set(sb); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ @@ -1882,6 +1885,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + ext4_superblock_csum_set(sb); err = ext4_handle_dirty_super(handle, sb); if (err) { diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 24cf730ba6b0..ae029dccebc1 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -791,6 +791,7 @@ static void ext4_xattr_update_super_block(handle_t *handle, BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { ext4_set_feature_xattr(sb); + ext4_superblock_csum_set(sb); ext4_handle_dirty_super(handle, sb); } } -- 2.25.1

1 1

[PATCH 01/15] arm64: KVM: Remove some extra semicolon in kvm_target_cpu
by Yang Yingliang 17 Dec '20

17 Dec '20

From: zhong jiang <zhongjiang(a)huawei.com> mainline inclusion from mainline-4.20 commit f0725345e3e127032376e4fcb6b0fc893237fcef category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- There are some extra semicolon in kvm_target_cpu, remove it. Signed-off-by: zhong jiang <zhongjiang(a)huawei.com> Signed-off-by: Marc Zyngier <marc.zyngier(a)arm.com> Signed-off-by: Xiangyou Xie <xiexiangyou(a)huawei.com> Reviewed-by: Ying Fang <fangying1(a)huawei.com> Reviewed-by: Zenghui Yu <yuzenghui(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- arch/arm64/kvm/guest.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index ff9908c5d496..ff00e1c8023a 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -432,15 +432,15 @@ int __attribute_const__ kvm_target_cpu(void) return KVM_ARM_TARGET_CORTEX_A53; case ARM_CPU_PART_CORTEX_A57: return KVM_ARM_TARGET_CORTEX_A57; - }; + } break; case ARM_CPU_IMP_APM: switch (part_number) { case APM_CPU_PART_POTENZA: return KVM_ARM_TARGET_XGENE_POTENZA; - }; + } break; - }; + } /* Return a default generic target */ return KVM_ARM_TARGET_GENERIC_V8; -- 2.25.1

1 14

[PATCH] mm: thp: make the THP mapcount atomic against __split_huge_pmd_locked()
by Yang Yingliang 17 Dec '20

17 Dec '20

From: Andrea Arcangeli <aarcange(a)redhat.com> stable inclusion from linux-4.19.129 commit 453d8a481b127edfa7fb76af1bc7586b7a63bdd2 CVE: CVE-2020-29368 -------------------------------- commit c444eb564fb16645c172d550359cb3d75fe8a040 upstream. Write protect anon page faults require an accurate mapcount to decide if to break the COW or not. This is implemented in the THP path with reuse_swap_page() -> page_trans_huge_map_swapcount()/page_trans_huge_mapcount(). If the COW triggers while the other processes sharing the page are under a huge pmd split, to do an accurate reading, we must ensure the mapcount isn't computed while it's being transferred from the head page to the tail pages. reuse_swap_cache() already runs serialized by the page lock, so it's enough to add the page lock around __split_huge_pmd_locked too, in order to add the missing serialization. Note: the commit in "Fixes" is just to facilitate the backporting, because the code before such commit didn't try to do an accurate THP mapcount calculation and it instead used the page_count() to decide if to COW or not. Both the page_count and the pin_count are THP-wide refcounts, so they're inaccurate if used in reuse_swap_page(). Reverting such commit (besides the unrelated fix to the local anon_vma assignment) would have also opened the window for memory corruption side effects to certain workloads as documented in such commit header. Signed-off-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Jann Horn <jannh(a)google.com> Reported-by: Jann Horn <jannh(a)google.com> Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Fixes: 6d0a07edd17c ("mm: thp: calculate the mapcount correctly for THP pages during WP faults") Cc: stable(a)vger.kernel.org Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/huge_memory.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b60cbf77e902..816a7fd3c6ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2286,6 +2286,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, spinlock_t *ptl; struct mm_struct *mm = vma->vm_mm; unsigned long haddr = address & HPAGE_PMD_MASK; + bool was_locked = false; + pmd_t _pmd; mmu_notifier_invalidate_range_start(mm, haddr, haddr + HPAGE_PMD_SIZE); ptl = pmd_lock(mm, pmd); @@ -2295,11 +2297,32 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong page. */ VM_BUG_ON(freeze && !page); - if (page && page != pmd_page(*pmd)) - goto out; + if (page) { + VM_WARN_ON_ONCE(!PageLocked(page)); + was_locked = true; + if (page != pmd_page(*pmd)) + goto out; + } +repeat: if (pmd_trans_huge(*pmd)) { - page = pmd_page(*pmd); + if (!page) { + page = pmd_page(*pmd); + if (unlikely(!trylock_page(page))) { + get_page(page); + _pmd = *pmd; + spin_unlock(ptl); + lock_page(page); + spin_lock(ptl); + if (unlikely(!pmd_same(*pmd, _pmd))) { + unlock_page(page); + put_page(page); + page = NULL; + goto repeat; + } + put_page(page); + } + } if (PageMlocked(page)) clear_page_mlock(page); } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd))) @@ -2307,6 +2330,8 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, __split_huge_pmd_locked(vma, pmd, haddr, freeze); out: spin_unlock(ptl); + if (!was_locked && page) + unlock_page(page); /* * No need to double call mmu_notifier->invalidate_range() callback. * They are 3 cases to consider inside __split_huge_pmd_locked(): -- 2.25.1

1 0

[PATCH] romfs: fix uninitialized memory leak in romfs_dev_read()
by Yang Yingliang 17 Dec '20

17 Dec '20

From: Jann Horn <jannh(a)google.com> stable inclusion from linux-4.19.142 commit 9660983738399465fd0e3b1977a61bbd29b2e5be CVE: CVE-2020-29371 -------------------------------- commit bcf85fcedfdd17911982a3e3564fcfec7b01eebd upstream. romfs has a superblock field that limits the size of the filesystem; data beyond that limit is never accessed. romfs_dev_read() fetches a caller-supplied number of bytes from the backing device. It returns 0 on success or an error code on failure; therefore, its API can't represent short reads, it's all-or-nothing. However, when romfs_dev_read() detects that the requested operation would cross the filesystem size limit, it currently silently truncates the requested number of bytes. This e.g. means that when the content of a file with size 0x1000 starts one byte before the filesystem size limit, ->readpage() will only fill a single byte of the supplied page while leaving the rest uninitialized, leaking that uninitialized memory to userspace. Fix it by returning an error code instead of truncating the read when the requested read operation would go beyond the end of the filesystem. Fixes: da4458bda237 ("NOMMU: Make it possible for RomFS to use MTD devices directly") Signed-off-by: Jann Horn <jannh(a)google.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: David Howells <dhowells(a)redhat.com> Cc: <stable(a)vger.kernel.org> Link: http://lkml.kernel.org/r/20200818013202.2246365-1-jannh@google.com Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/romfs/storage.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index f86f51f99ace..1dcadd22b440 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -221,10 +221,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos, size_t limit; limit = romfs_maxsize(sb); - if (pos >= limit) + if (pos >= limit || buflen > limit - pos) return -EIO; - if (buflen > limit - pos) - buflen = limit - pos; #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) -- 2.25.1

1 0

[PATCH v2 OLK-5.10 0/3] Backport 5.10.1 LTS
by Chen Jun 17 Dec '20

17 Dec '20

v1->v2 modifty the commit message: linux-5.10.1 -> stable-5.10.1 *** BLURB HERE *** Greg Kroah-Hartman (3): Revert "md: change mddev 'chunk_sectors' from int to unsigned" Revert "dm raid: fix discard limits for raid1 and raid10" Linux 5.10.1 Makefile | 2 +- drivers/md/dm-raid.c | 12 +++++------- drivers/md/md.h | 4 ++-- 3 files changed, 8 insertions(+), 10 deletions(-) -- 2.25.0

2 6

[OLK-5.10 0/3] Backport 5.10.1 LTS
by Chen Jun 16 Dec '20

16 Dec '20

*** BLURB HERE *** Greg Kroah-Hartman (3): Revert "md: change mddev 'chunk_sectors' from int to unsigned" Revert "dm raid: fix discard limits for raid1 and raid10" Linux 5.10.1 Makefile | 2 +- drivers/md/dm-raid.c | 12 +++++------- drivers/md/md.h | 4 ++-- 3 files changed, 8 insertions(+), 10 deletions(-) -- 2.25.0

2 6

为什么你一定要参加 openEuler Summit 的 TC、Maintainer、SIG 组工作会议
by public openEuler 16 Dec '20

16 Dec '20

嗨，各位 openEuler 社区的开发者：很高兴能够向你们汇报 openEuler Summit 的会议进度。对于各位来说，本周最重要的事情是 TC、Maintainer和SIG 组开放工作会议的议程已经上线了。 *为什么你一定要参与 TC、Maintainer、SIG组开放工作会议？* 1. 你可以清楚的了解 openEuler 社区的运作模式 2. 你可以和 TC、Maintainer、SIG 的成员共同探讨openEuler 社区的下一个版本的计划和技术路线 3. 可以跟社区里的技术大佬进行面对面交流。 4. 更好的规划自己在社区中的成长路线 *会议时间和房间号：* TC 开放工作会议 Maintainer 开放工作会议 SIG 组开放工作会议时间 12/24 13:00-14:30 12/24 15:00-17:00 12/25 13:00-15:30 房间号悦府6和悦府7 悦府6和悦府7 大宴会厅B *TC **开放工作会议议程：* 1. 讨论 openEuler 支持 App Stream 机制 2. 申请成立智能运维 SIG 3. 讨论从 Gitee issue 整体切换到bugzilla 4. 讨论2021年 TC 合作的开展方式 5. …… *Maintainer **开放工作会议议程* 1. 开场 & 颁发 Maintainer 纪念徽章 2. openEuler 社区运作分析 3. 我在 openEuler 社区担任 Maintainer 的那些事儿 4. 自由问答 5. 总结 *参与本次 SIG 组开放工作会议的 SIG 组：* 1. sig-DDE 2. sig-UKUI 3. sig-Ha 4. sig-arrch32 5. A-Tune 6. iSulad & Container 7. sig-ai-bitdata 8. sig-security-facility 9. sig-confidential-computing 10. Compiler 11. Doc 12. Infrastructure 13. security-committee 14. sig-Compatibility-Infra 15. sig-QA 16. sig-release-management 17. Kernel 18. Virt *openEuler Summit **专属伴手礼：* [image: image.png] *openEuler **卫衣* [image: image.png] *openEuler Maintainer **纪念徽章* *欢迎通过openEuler 社区开发者专属的报名渠道报名：* https://etherpad.openeuler.org/p/openEuler-Summit-2020 openEuler Summit 官网： https://openeuler.org/zh/interaction/summit-list/

1 0

[PATCH 1/2] arm64: arch_timer: only do cntvct workaround on VDSO path on D05
by Yang Yingliang 16 Dec '20

16 Dec '20

hulk inclusion category: bugfix bugzilla: NA CVE: NA -------------------------------- On other board do do cntvct workaround on VDSO path may cause unexpected error, so we do this only on D05. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Hanjun Guo <guohanjun(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/clocksource/arm_arch_timer.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 443079810300..50030326d27b 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -551,9 +551,14 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa * change both the default value and the vdso itself. */ if (wa->read_cntvct_el0) { - clocksource_counter.archdata.vdso_direct = true; - vdso_default = true; - vdso_fix = true; + if (wa->read_cntvct_el0 == hisi_161010101_read_cntvct_el0) { + clocksource_counter.archdata.vdso_direct = true; + vdso_default = true; + vdso_fix = true; + } else { + clocksource_counter.archdata.vdso_direct = false; + vdso_default = false; + } } } -- 2.25.1

1 1

[PATCH] scsi: libiscsi: Fix cmds hung when sd_shutdown
by Yang Yingliang 15 Dec '20

15 Dec '20

From: Wu Bo <wubo40(a)huawei.com> hulk inclusion category: bugfix bugzilla: NA CVE: NA https://gitee.com/src-openeuler/kernel/issues/I28N9J --------------------------- For some reason, during reboot the system, iscsi.service failed to logout all sessions. kernel will hang forever on its sd_sync_cache() logic, after issuing the SYNCHRONIZE_CACHE cmd to all still existent paths. [ 1044.098991] reboot: Mddev shutdown finished. [ 1044.099311] reboot: Usermodehelper disable finished. [ 1050.611244] connection2:0: ping timeout of 5 secs expired, recv timeout 5, last rx 4295152378, last ping 4295153633, now 4295154944 [ 1348.599676] Call trace: [ 1348.599887] __switch_to+0xe8/0x150 [ 1348.600113] __schedule+0x33c/0xa08 [ 1348.600372] schedule+0x2c/0x88 [ 1348.600567] schedule_timeout+0x184/0x3a8 [ 1348.600820] io_schedule_timeout+0x28/0x48 [ 1348.601089] wait_for_common_io.constprop.2+0x168/0x258 [ 1348.601425] wait_for_completion_io_timeout+0x28/0x38 [ 1348.601762] blk_execute_rq+0x98/0xd8 [ 1348.602006] __scsi_execute+0xe0/0x1e8 [ 1348.602262] sd_sync_cache+0xd0/0x220 [sd_mod] [ 1348.602551] sd_shutdown+0x6c/0xf8 [sd_mod] [ 1348.602826] device_shutdown+0x13c/0x250 [ 1348.603078] kernel_restart_prepare+0x5c/0x68 [ 1348.603400] kernel_restart+0x20/0x98 [ 1348.603683] __se_sys_reboot+0x214/0x260 [ 1348.603987] __arm64_sys_reboot+0x24/0x30 [ 1348.604300] el0_svc_common+0x80/0x1b8 [ 1348.604590] el0_svc_handler+0x78/0xe0 [ 1348.604877] el0_svc+0x10/0x260 d754941225 (scsi: libiscsi: Allow sd_shutdown on bad transport) Once solved this problem. The iscsi_eh_cmd_timed_out() function add system_state judgment, and will return BLK_EH_DONE and mark the result as DID_NO_CONNECT when system_state is not SYSTEM_RUNNING, To tell upper layers that the command was handled during the transport layer error handler helper. The scsi Mid Layer timeout handler function(scsi_times_out) will be abort the cmd if the scsi LLD timeout handler return BLK_EH_DONE. if abort cmd failed, will enter scsi EH logic. Scsi EH will do reset target logic, if reset target failed, Will call iscsi_eh_session_reset() function to drop the session. The iscsi_eh_session_reset function will wait for a relogin, session termination from userspace, or a recovery/replacement timeout. But at this time, the app iscsid has exited, and the session was marked as ISCSI_STATE_FAILED, So the SCSI EH process will never be scheduled back again. PID: 9123 TASK: ffff80020c1b4d80 CPU: 3 COMMAND: "scsi_eh_2" #0 [ffff00008632bb70] __switch_to at ffff000080088738 #1 [ffff00008632bb90] __schedule at ffff000080a00480 #2 [ffff00008632bc20] schedule at ffff000080a00b58 #3 [ffff00008632bc30] iscsi_eh_session_reset at ffff000000d1ab9c [libiscsi] #4 [ffff00008632bcb0] iscsi_eh_recover_target at ffff000000d1d1fc [libiscsi] #5 [ffff00008632bd00] scsi_try_target_reset at ffff0000806f0bac #6 [ffff00008632bd30] scsi_eh_ready_devs at ffff0000806f2724 #7 [ffff00008632bde0] scsi_error_handler at ffff0000806f41d4 #8 [ffff00008632be70] kthread at ffff000080119ae0 Reported-by: Tianxiong Lu <lutianxiong(a)huawei.com> Signed-off-by: Wu Bo <wubo40(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/libiscsi.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index ec356e035c5f..35d603db33bb 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -2441,7 +2441,17 @@ int iscsi_eh_session_reset(struct scsi_cmnd *sc) mutex_lock(&session->eh_mutex); spin_lock_bh(&session->frwd_lock); - if (session->state == ISCSI_STATE_TERMINATE) { + + /* + * During shutdown, if session is prematurely disconnected, recovery + * won't happen and there will be hung cmds. To solve this case, all + * cmds would be enter scsi EH, but the EH path will wait for + * wait_event_interruptible() to complete until the state of the + * session is ISCSI_STATE_TERMINATE, ISCSI_STATE_LOGGED_IN or + * ISCSI_STATE_RECOVERY_FAILED. + */ + if (session->state == ISCSI_STATE_TERMINATE || + unlikely(system_state != SYSTEM_RUNNING)) { failed: ISCSI_DBG_EH(session, "failing session reset: Could not log back into " -- 2.25.1

1 0

[PATCH] scsi: iscsi: Perform connection failure entirely in kernel space
by Yang Yingliang 15 Dec '20

15 Dec '20

From: Bharath Ravi <rbharath(a)google.com> mainline inclusion from mainline-v5.7-rc1 commit 0ab710458da113a71c461c4df27e7f1353d9f864 category: bugfix bugzilla: NA CVE: NA https://gitee.com/src-openeuler/kernel/issues/I28N9J -------------------------------- Connection failure processing depends on a daemon being present to (at least) stop the connection and start recovery. This is a problem on a multipath scenario, where if the daemon failed for whatever reason, the SCSI path is never marked as down, multipath won't perform the failover and IO to the device will be forever waiting for that connection to come back. This patch performs the connection failure entirely inside the kernel. This way, the failover can happen and pending IO can continue even if the daemon is dead. Once the daemon comes alive again, it can execute recovery procedures if applicable. Cc: Mike Christie <mchristi(a)redhat.com> Cc: Lee Duncan <LDuncan(a)suse.com> Cc: Bart Van Assche <bvanassche(a)acm.org> Link: https://lore.kernel.org/r/20200125061925.191601-1-krisman@collabora.com Co-developed-by: Dave Clausen <dclausen(a)google.com> Co-developed-by: Nick Black <nlb(a)google.com> Co-developed-by: Vaibhav Nagarnaik <vnagarnaik(a)google.com> Co-developed-by: Anatol Pomazau <anatol(a)google.com> Co-developed-by: Tahsin Erdogan <tahsin(a)google.com> Co-developed-by: Frank Mayhar <fmayhar(a)google.com> Co-developed-by: Junho Ryu <jayr(a)google.com> Co-developed-by: Khazhismel Kumykov <khazhy(a)google.com> Reviewed-by: Reviewed-by: Khazhismel Kumykov <khazhy(a)google.com> Co-developed-by: Gabriel Krisman Bertazi <krisman(a)collabora.com> Reviewed-by: Lee Duncan <lduncan(a)suse.com> Signed-off-by: Bharath Ravi <rbharath(a)google.com> Signed-off-by: Dave Clausen <dclausen(a)google.com> Signed-off-by: Nick Black <nlb(a)google.com> Signed-off-by: Vaibhav Nagarnaik <vnagarnaik(a)google.com> Signed-off-by: Anatol Pomazau <anatol(a)google.com> Signed-off-by: Tahsin Erdogan <tahsin(a)google.com> Signed-off-by: Frank Mayhar <fmayhar(a)google.com> Signed-off-by: Junho Ryu <jayr(a)google.com> Signed-off-by: Khazhismel Kumykov <khazhy(a)google.com> Signed-off-by: Gabriel Krisman Bertazi <krisman(a)collabora.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/scsi_transport_iscsi.c | 68 +++++++++++++++++++++++++++++ include/scsi/scsi_transport_iscsi.h | 1 + 2 files changed, 69 insertions(+) diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 698347301198..e1ac96b8940b 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -81,6 +81,12 @@ struct iscsi_internal { struct transport_container session_cont; }; +/* Worker to perform connection failure on unresponsive connections + * completely in kernel space. + */ +static void stop_conn_work_fn(struct work_struct *work); +static DECLARE_WORK(stop_conn_work, stop_conn_work_fn); + static atomic_t iscsi_session_nr; /* sysfs session id for next new session */ static struct workqueue_struct *iscsi_eh_timer_workq; @@ -1609,6 +1615,7 @@ static DEFINE_MUTEX(rx_queue_mutex); static LIST_HEAD(sesslist); static DEFINE_SPINLOCK(sesslock); static LIST_HEAD(connlist); +static LIST_HEAD(connlist_err); static DEFINE_SPINLOCK(connlock); static uint32_t iscsi_conn_get_sid(struct iscsi_cls_conn *conn) @@ -2247,6 +2254,7 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid) mutex_init(&conn->ep_mutex); INIT_LIST_HEAD(&conn->conn_list); + INIT_LIST_HEAD(&conn->conn_list_err); conn->transport = transport; conn->cid = cid; @@ -2293,6 +2301,7 @@ int iscsi_destroy_conn(struct iscsi_cls_conn *conn) spin_lock_irqsave(&connlock, flags); list_del(&conn->conn_list); + list_del(&conn->conn_list_err); spin_unlock_irqrestore(&connlock, flags); transport_unregister_device(&conn->dev); @@ -2407,6 +2416,51 @@ int iscsi_offload_mesg(struct Scsi_Host *shost, } EXPORT_SYMBOL_GPL(iscsi_offload_mesg); +static void stop_conn_work_fn(struct work_struct *work) +{ + struct iscsi_cls_conn *conn, *tmp; + unsigned long flags; + LIST_HEAD(recovery_list); + + spin_lock_irqsave(&connlock, flags); + if (list_empty(&connlist_err)) { + spin_unlock_irqrestore(&connlock, flags); + return; + } + list_splice_init(&connlist_err, &recovery_list); + spin_unlock_irqrestore(&connlock, flags); + + list_for_each_entry_safe(conn, tmp, &recovery_list, conn_list_err) { + uint32_t sid = iscsi_conn_get_sid(conn); + struct iscsi_cls_session *session; + + mutex_lock(&rx_queue_mutex); + + session = iscsi_session_lookup(sid); + if (session) { + if (system_state != SYSTEM_RUNNING) { + session->recovery_tmo = 0; + conn->transport->stop_conn(conn, + STOP_CONN_TERM); + } else { + conn->transport->stop_conn(conn, + STOP_CONN_RECOVER); + } + } + + list_del_init(&conn->conn_list_err); + + mutex_unlock(&rx_queue_mutex); + + /* we don't want to hold rx_queue_mutex for too long, + * for instance if many conns failed at the same time, + * since this stall other iscsi maintenance operations. + * Give other users a chance to proceed. + */ + cond_resched(); + } +} + void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error) { struct nlmsghdr *nlh; @@ -2414,6 +2468,12 @@ void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error) struct iscsi_uevent *ev; struct iscsi_internal *priv; int len = nlmsg_total_size(sizeof(*ev)); + unsigned long flags; + + spin_lock_irqsave(&connlock, flags); + list_add(&conn->conn_list_err, &connlist_err); + spin_unlock_irqrestore(&connlock, flags); + queue_work(system_unbound_wq, &stop_conn_work); priv = iscsi_if_transport_lookup(conn->transport); if (!priv) @@ -2743,11 +2803,19 @@ static int iscsi_if_destroy_conn(struct iscsi_transport *transport, struct iscsi_uevent *ev) { struct iscsi_cls_conn *conn; + unsigned long flags; conn = iscsi_conn_lookup(ev->u.d_conn.sid, ev->u.d_conn.cid); if (!conn) return -EINVAL; + spin_lock_irqsave(&connlock, flags); + if (!list_empty(&conn->conn_list_err)) { + spin_unlock_irqrestore(&connlock, flags); + return -EAGAIN; + } + spin_unlock_irqrestore(&connlock, flags); + ISCSI_DBG_TRANS_CONN(conn, "Destroying transport conn\n"); if (transport->destroy_conn) transport->destroy_conn(conn); diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index b266d2a3bcb1..7de0bf6a9b60 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -203,6 +203,7 @@ extern void iscsi_ping_comp_event(uint32_t host_no, struct iscsi_cls_conn { struct list_head conn_list; /* item in connlist */ + struct list_head conn_list_err; /* item in connlist_err */ void *dd_data; /* LLD private data */ struct iscsi_transport *transport; uint32_t cid; /* connection id */ -- 2.25.1

1 0

[PATCH 00/38] backport stable-4.19.163
by Yang Yingliang 14 Dec '20

14 Dec '20

Bjørn Mork (1): USB: serial: option: fix Quectel BG96 matching Bob Peterson (1): gfs2: check for empty rgrp tree in gfs2_ri_update Christian Eggers (3): i2c: imx: Don't generate STOP condition if arbitration has been lost i2c: imx: Fix reset of I2SR_IAL flag i2c: imx: Check for I2SR_IAL after every byte Florian Westphal (1): netfilter: nf_tables: avoid false-postive lockdep splat Giacinto Cifelli (1): USB: serial: option: add support for Thales Cinterion EXS82 Greg Kroah-Hartman (1): Linux 4.19.163 Hans de Goede (2): pinctrl: baytrail: Replace WARN with dev_info_once when setting direct-irq pin to output pinctrl: baytrail: Fix pin being driven low for a while on gpiod_get(..., GPIOD_OUT_HIGH) Jakub Kicinski (1): Revert "geneve: pull IP header before ECN decapsulation" Jan-Niklas Burfeind (1): USB: serial: ch341: add new Product ID for CH341A Jian-Hong Pan (1): ALSA: hda/realtek: Enable headset of ASUS UX482EG & B9400CEA with ALC294 Johan Hovold (2): USB: serial: kl5kusb105: fix memleak on open USB: serial: ch341: sort device-id entries Kailang Yang (1): ALSA: hda/realtek - Add new codec supported for ALC897 Lukas Wunner (3): spi: Introduce device-managed SPI controller allocation spi: bcm-qspi: Fix use-after-free on unbind spi: bcm2835: Fix use-after-free on unbind Luo Meng (1): Input: i8042 - fix error return code in i8042_setup_aux() Masami Hiramatsu (2): x86/uprobes: Do not use prefixes.nbytes when looping over prefixes.bytes x86/insn-eval: Use new for_each_insn_prefix() macro to loop over prefixes bytes Mike Snitzer (2): dm: remove invalid sparse __acquires and __releases annotations dm writecache: remove BUG() and fail gracefully instead Mikulas Patocka (1): dm writecache: fix the maximum number of arguments Naveen N. Rao (1): ftrace: Fix updating FTRACE_FL_TRAMP Paulo Alcantara (1): cifs: fix potential use-after-free in cifs_echo_request() Peter Ujfalusi (1): spi: bcm2835: Release the DMA channel if probe fails after dma_init Qian Cai (1): mm/swapfile: do not sleep with a spin lock held Steven Rostedt (VMware) (1): tracing: Fix userstacktrace option for instances Suganath Prabu S (1): scsi: mpt3sas: Fix ioctl timeout Suravee Suthikulpanit (1): iommu/amd: Set DTE[IntTabLen] to represent 512 IRTEs Takashi Iwai (2): ALSA: hda/realtek: Add mute LED quirk to yet another HP x360 model ALSA: hda/generic: Add option to enforce preferred_dacs pairs Vamsi Krishna Samavedam (1): usb: gadget: f_fs: Use local copy of descriptors for userspace copy Vincent Palatin (1): USB: serial: option: add Fibocom NL668 variants Yang Shi (1): mm: list_lru: set shrinker map bit when child nr_items is not zero Zhihao Cheng (1): i2c: qup: Fix error return code in qup_i2c_bam_schedule_desc() Makefile | 2 +- arch/x86/include/asm/insn.h | 15 +++++ arch/x86/kernel/uprobes.c | 10 ++-- arch/x86/lib/insn-eval.c | 5 +- drivers/i2c/busses/i2c-imx.c | 42 +++++++++++--- drivers/i2c/busses/i2c-qup.c | 3 +- drivers/input/serio/i8042.c | 3 +- drivers/iommu/amd_iommu_types.h | 2 +- drivers/md/dm-writecache.c | 4 +- drivers/md/dm.c | 2 - drivers/net/geneve.c | 20 ++----- drivers/pinctrl/intel/pinctrl-baytrail.c | 67 ++++++++++++++++++----- drivers/scsi/mpt3sas/mpt3sas_ctl.c | 2 +- drivers/spi/spi-bcm-qspi.c | 34 ++++-------- drivers/spi/spi-bcm2835.c | 22 +++----- drivers/spi/spi.c | 58 +++++++++++++++++++- drivers/usb/gadget/function/f_fs.c | 6 +- drivers/usb/serial/ch341.c | 5 +- drivers/usb/serial/kl5kusb105.c | 10 ++-- drivers/usb/serial/option.c | 10 ++-- fs/cifs/connect.c | 2 + fs/gfs2/rgrp.c | 4 ++ include/linux/spi/spi.h | 19 +++++++ kernel/trace/ftrace.c | 22 +++++++- kernel/trace/trace.c | 7 ++- kernel/trace/trace.h | 6 +- mm/list_lru.c | 10 ++-- mm/swapfile.c | 4 +- net/netfilter/nf_tables_api.c | 3 +- sound/pci/hda/hda_generic.c | 12 ++-- sound/pci/hda/hda_generic.h | 1 + sound/pci/hda/patch_realtek.c | 6 ++ tools/objtool/arch/x86/include/asm/insn.h | 15 +++++ tools/perf/util/intel-pt-decoder/insn.h | 15 +++++ 34 files changed, 329 insertions(+), 119 deletions(-) -- 2.25.1

1 38

[PATCH 1/5] scsi: hisi_sas: Delete down() when handle Block-IO
by Yang Yingliang 14 Dec '20

14 Dec '20

From: Yang Xingui <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: NA CVE: NA Call down() at RCU Read-Side Critical Secrion sometimes may caugh a RCU preempt Calltrace. [ 3506.800288] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: [ 3506.806357] rcu: Tasks blocked on level-1 rcu_node (CPUs 0-15): P22895/1:b..l [ 3506.813556] (detected by 108, t=162805 jiffies, g=124209, q=59192378) [ 3506.820056] kworker/0:1H D 0 22895 2 0x00000228 [ 3506.825524] Workqueue: kblockd blk_mq_run_work_fn [ 3506.830207] Call trace: [ 3506.832644] __switch_to+0xf0/0x140 [ 3506.836118] __schedule+0x890/0xdc8 [ 3506.839590] schedule+0x80/0x120 [ 3506.842804] schedule_timeout+0x22c/0x328 [ 3506.846796] __down+0x74/0xc8 [ 3506.849751] down+0x54/0x70 [ 3506.852539] hisi_sas_task_exec.isra.25+0x840/0xf28 [hisi_sas_main] [ 3506.858780] hisi_sas_queue_command+0x40/0x84 [hisi_sas_main] [ 3506.864502] sas_queuecommand+0x144/0x1c8 [libsas] [ 3506.869271] scsi_queue_rq+0x72c/0xa20 [ 3506.873005] blk_mq_dispatch_rq_list+0x110/0x680 [ 3506.877601] blk_mq_do_dispatch_sched+0x108/0x148 [ 3506.882285] __blk_mq_sched_dispatch_requests+0x120/0x1b8 [ 3506.887659] blk_mq_sched_dispatch_requests+0x40/0x78 [ 3506.892688] __blk_mq_run_hw_queue+0xb8/0x138 [ 3506.897026] blk_mq_run_work_fn+0x28/0x38 Actually it's no need for keeping IO stopping here to wait for controller reset complete. We can directly return error code. Signed-off-by: Yang Xingui <yangxingui(a)huawei.com> Reviewed-by: Zhu Xiongxiong <zhuxiongxiong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas_main.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 124aa26fa4b8..0128c547e4c8 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -611,19 +611,9 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags, hisi_hba = dev_to_hisi_hba(device); dev = hisi_hba->dev; - if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) { - /* - * For IOs from upper layer, it may already disable preempt - * in the IO path, if disable preempt again in down(), - * function schedule() will report schedule_bug(), so check - * preemptible() before goto down(). - */ - if (!preemptible()) - return -EINVAL; + if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) + return -EINVAL; - down(&hisi_hba->sem); - up(&hisi_hba->sem); - } /* protect task_prep and start_delivery sequence */ rc = hisi_sas_task_prep(task, is_tmf, tmf, &pass, &dq); -- 2.25.1

1 4

[PATCH v2] arm64/mpam: Avoid compilation error of enable_acpi redefinition
by Wang ShaoBo 11 Dec '20

11 Dec '20

hulk inclusion category: bugfix bugzilla: 46772 CVE: NA Reference: https://gitee.com/openeuler/kernel/issues/I28HIY ------------------------------------------------- enable_acpi is declaration as a enumerated type in mpam, where it's also defined as a static inline function in acpi.h, this following compilation error will be triggered if we use their two like this. In file included from ./include/acpi/acpi_io.h:7:0, from ./include/linux/acpi.h:47, from ./arch/arm64/include/asm/machine_t.h:26, from arch/arm64/kernel/process.c:64: ./arch/arm64/include/asm/acpi.h:82:20: error: ‘enable_acpi’ redeclared as different kind of symbol static inline void enable_acpi(void) ^~~~~~~~~~~ In file included from arch/arm64/kernel/process.c:61:0: ./arch/arm64/include/asm/mpam_sched.h:46:2: note: previous definition of ‘enable_acpi’ was here enable_acpi, We should rename enable_acpi properly for mpam. Reported-by: Zhengyuan Liu <liuzhengyuan(a)tj.kylinos.cn> Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> --- arch/arm64/include/asm/mpam_sched.h | 6 +++--- arch/arm64/kernel/mpam.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/mpam_sched.h b/arch/arm64/include/asm/mpam_sched.h index 350296157087a..ddc7ce3e1a9e1 100644 --- a/arch/arm64/include/asm/mpam_sched.h +++ b/arch/arm64/include/asm/mpam_sched.h @@ -41,9 +41,9 @@ static inline void mpam_sched_in(void) } enum mpam_enable_type { - enable_denied = 0, - enable_default, - enable_acpi, + MPAM_ENABLE_DENIED = 0, + MPAM_ENABLE_DEFAULT, + MPAM_ENABLE_ACPI, }; extern enum mpam_enable_type __read_mostly mpam_enabled; diff --git a/arch/arm64/kernel/mpam.c b/arch/arm64/kernel/mpam.c index 3f89cec8e2fb1..96f4d013a9034 100644 --- a/arch/arm64/kernel/mpam.c +++ b/arch/arm64/kernel/mpam.c @@ -252,7 +252,7 @@ int __init mpam_force_init(void) { int ret; - if (mpam_enabled != enable_default) + if (mpam_enabled != MPAM_ENABLE_DEFAULT) return 0; ret = mpam_nodes_discovery_start(); @@ -1380,9 +1380,9 @@ enum mpam_enable_type __read_mostly mpam_enabled; static int __init mpam_setup(char *str) { if (!strcmp(str, "=acpi")) - mpam_enabled = enable_acpi; + mpam_enabled = MPAM_ENABLE_ACPI; else - mpam_enabled = enable_default; + mpam_enabled = MPAM_ENABLE_DEFAULT; return 1; } __setup("mpam", mpam_setup); -- 2.17.1

1 0

【会议纪要】 Re: openEuler kernel sig meeting
by Xie XiuQi 11 Dec '20

11 Dec '20

会议纪要：与会人：Zheng Zhenpeng, xiexiuqi， dukaitian, myeuler, jiaoff, Liu Yuan, Wenlong.Ding, 潘晨博 1. 网迅万兆网卡驱动合入 openEuler 内核讨论 - 郑振鹏、刘源 > > 网迅万兆网卡是国内具有完全知识产权的万兆网络控制器，相关资料请访问官方网站： > 网卡成品及资料 > https://www.net-swift.com/a/383.html > 网卡芯片 > https://www.net-swift.com/a/275.html > > 之前我们已向EulerOS发布版本提供万兆网卡驱动rpm包，此次希望能加深合作， > 将驱动源码推入openeuler内核。 > 根据开源规则（遵从GPLV2），我厂已在官网上提供源码下载 1）openEuler 欢迎网讯网卡驱动合入社区，使 openEuler 支持更丰富的设备。 2）kernel sig 同意网讯万兆网卡驱动合入 openEuler，后续驱动可以按照开源社区的规范，准备补丁； - 建议合入openEuler 20.03 LTS SP2 （kernel-4.19)，如果时间赶不上的话，与 Release sig 讨论是否可以合入后续 update 版本； - 该驱动代码量约 5w+ 行，首次合入时，不要求把所有开发历史作为补丁发出来，可以按照模块或者功能做适当的补丁拆分； 3）建议加入到兼容性sig 组，兼容性 sig 与网讯网卡确认的认证过程 4）与 Release sig 对齐 Release 节奏 5）另有针对网讯网卡针对 dpdk 的适配，也欢迎参与 openEuler，贡献社区。 On 2020/12/10 9:32, zhenpengzheng(a)net-swift.com wrote: > 收到，我会按时参加。 > > ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ > > **************************************************************** > > 郑振鹏(zheng zhenpeng) > > 北京网迅科技有限公司杭州分公司软件工程师 > > 浙江省杭州市西湖区文三路478号华星时代广场A座507室 310013 > > Beijing WangXun Technology Co., Ltd. Software Engineer. > > Room A507, HuaXing Times Square, No.478 West Wensan Road. > > West Lake District, Hangzhou City, 310013 ZHEJIANG, P.R.CHINA. > > > > Office: +86(0571)89807901-8014 > > Mobile: +86-13656681762 > > E-Mail: z <mailto:jianwang@trustnetic.com>henpengzheng(a)net-swift.com > > **************************************************************** > > > *发件人：* Xie XiuQi <mailto:xiexiuqi@huawei.com> > *发送时间：* 2020-12-09 20:09 > *收件人：* kernel(a)openeuler.org <mailto:kernel@openeuler.org> > *抄送：* tc(a)openeuler.org <mailto:tc@openeuler.org>; dev(a)openeuler.org <mailto:dev@openeuler.org>; release(a)openeuler.org <mailto:release@openeuler.org>; 郑振鹏 <mailto:zhenpengzheng@net-swift.com>; Liuyuan (Compatibility, Cloud Infrastructure Service Product Dept.) <mailto:liuyuan36@huawei.com> > *主题：* Re: [Release] Re: 【议题申报】 openEuler kernel sig meeting > 议题： > > 1）网迅万兆网卡驱动合入 openEuler 内核讨论 - 郑振鹏、刘源 > > 网迅万兆网卡是国内具有完全知识产权的万兆网络控制器，相关资料请访问官方网站： > 网卡成品及资料 > https://www.net-swift.com/a/383.html > 网卡芯片 > https://www.net-swift.com/a/275.html > > 之前我们已向EulerOS发布版本提供万兆网卡驱动rpm包，此次希望能加深合作，将驱动源码推入openeuler内核。 > 根据开源规则（遵从GPLV2），我厂已在官网上提供源码下载 > > > 欢迎继续申报议题 > > On 2020/12/2 19:52, Xie XiuQi wrote: > > > > > > On 2020/12/2 19:26, openEuler conference wrote: > >> 您好！ > >> > >> openEuler Kernel SIG 邀请您参加 2020-12-11 10:00 召开的ZOOM会议 > >> > >> 会议主题：openEuler kernel sig meeting > >> > >> 会议链接：https://zoom.us/j/95008051399?pwd=RVRzNk0zSVUxdmVaaWZjT1d4UEhVQT09 > >> > >> 更多资讯尽在：https://openeuler.org/zh/ > >> > >> > >> > >> Hello! > >> > >> openEuler Kernel SIG invites you to attend the ZOOM conference will be held at 2020-12-11 10:00, > >> > >> The subject of the conference is openEuler kernel sig meeting, > >> > >> You can join the meeting at https://zoom.us/j/95008051399?pwd=RVRzNk0zSVUxdmVaaWZjT1d4UEhVQT09. > >> > >> More information <https://openeuler.org/zh/> > >> > >> > >> _______________________________________________ > >> Release mailing list -- release(a)openeuler.org > >> To unsubscribe send an email to release-leave(a)openeuler.org > >> > > _______________________________________________ > > Release mailing list -- release(a)openeuler.org > > To unsubscribe send an email to release-leave(a)openeuler.org > > > >

1 0

[PATCH] arm64/mpam: Avoid compilation error of enable_acpi redefinition
by Wang ShaoBo 10 Dec '20

10 Dec '20

hulk inclusion category: bugfix bugzilla: 46772 CVE: NA Reference: https://gitee.com/openeuler/kernel/issues/I28HIY ------------------------------------------------- enable_acpi is declaration as a enumerated type in mpam, where it's also defined as a static inline function in acpi.h, this following compilation error will be triggered if we use their two like this. In file included from ./include/acpi/acpi_io.h:7:0, from ./include/linux/acpi.h:47, from ./arch/arm64/include/asm/machine_t.h:26, from arch/arm64/kernel/process.c:64: ./arch/arm64/include/asm/acpi.h:82:20: error: ‘enable_acpi’ redeclared as different kind of symbol static inline void enable_acpi(void) ^~~~~~~~~~~ In file included from arch/arm64/kernel/process.c:61:0: ./arch/arm64/include/asm/mpam_sched.h:46:2: note: previous definition of ‘enable_acpi’ was here enable_acpi, We should rename enable_acpi properly for mpam. Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> --- arch/arm64/include/asm/mpam_sched.h | 6 +++--- arch/arm64/kernel/mpam.c | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/arm64/include/asm/mpam_sched.h b/arch/arm64/include/asm/mpam_sched.h index 350296157087a..ddc7ce3e1a9e1 100644 --- a/arch/arm64/include/asm/mpam_sched.h +++ b/arch/arm64/include/asm/mpam_sched.h @@ -41,9 +41,9 @@ static inline void mpam_sched_in(void) } enum mpam_enable_type { - enable_denied = 0, - enable_default, - enable_acpi, + MPAM_ENABLE_DENIED = 0, + MPAM_ENABLE_DEFAULT, + MPAM_ENABLE_ACPI, }; extern enum mpam_enable_type __read_mostly mpam_enabled; diff --git a/arch/arm64/kernel/mpam.c b/arch/arm64/kernel/mpam.c index 3f89cec8e2fb1..96f4d013a9034 100644 --- a/arch/arm64/kernel/mpam.c +++ b/arch/arm64/kernel/mpam.c @@ -252,7 +252,7 @@ int __init mpam_force_init(void) { int ret; - if (mpam_enabled != enable_default) + if (mpam_enabled != MPAM_ENABLE_DEFAULT) return 0; ret = mpam_nodes_discovery_start(); @@ -1380,9 +1380,9 @@ enum mpam_enable_type __read_mostly mpam_enabled; static int __init mpam_setup(char *str) { if (!strcmp(str, "=acpi")) - mpam_enabled = enable_acpi; + mpam_enabled = MPAM_ENABLE_ACPI; else - mpam_enabled = enable_default; + mpam_enabled = MPAM_ENABLE_DEFAULT; return 1; } __setup("mpam", mpam_setup); -- 2.17.1

2 1

[PATCH 00/32] backport stable-4.19.162
by Yang Yingliang 10 Dec '20

10 Dec '20

Alexander Duyck (1): tcp: Set INET_ECN_xmit configuration in tcp_reinit_congestion_control Anmol Karn (1): rose: Fix Null pointer dereference in rose_send_frame() Antoine Tenart (2): netfilter: bridge: reset skb->pkt_type after NF_INET_POST_ROUTING traversal net: ip6_gre: set dev->hard_header_len when using header_ops Dan Carpenter (2): net/x25: prevent a couple of overflows chelsio/chtls: fix a double free in chtls_setkey() Eran Ben Elisha (1): net/mlx5: Fix wrong address reclaim when command interface is down Eric Dumazet (1): geneve: pull IP header before ECN decapsulation Greg Kroah-Hartman (1): Linux 4.19.162 Guillaume Nault (1): ipv4: Fix tos mask in inet_rtm_getroute() Hector Martin (1): ALSA: usb-audio: US16x08: fix value count for level meters Jamie Iles (1): bonding: wait for sysfs kobject destruction before freeing struct slave Jens Axboe (1): tun: honor IOCB_NOWAIT flag Julian Wiedmann (1): net/af_iucv: set correct sk_protocol for child sockets Krzysztof Kozlowski (1): dt-bindings: net: correct interrupt flags in examples Lijun Pan (1): ibmvnic: fix call_netdevice_notifiers in do_reset Maxim Mikityanskiy (1): net/tls: Protect from calling tls_dev_del for TLS RX twice Po-Hsu Lin (1): Input: i8042 - add ByteSpeed touchpad to noloop table Sanjay Govind (1): Input: xpad - support Ardwiino Controllers Shiraz Saleem (1): RDMA/i40iw: Address an mmap handler exploit in i40iw Sylwester Dziedziuch (1): i40e: Fix removing driver while bare-metal VFs pass traffic Thomas Falcon (2): ibmvnic: Ensure that SCRQ entry reads are correctly ordered ibmvnic: Fix TX completion error handling Vadim Fedorenko (1): net/tls: missing received data after fast remote close Vasily Averin (1): tracing: Remove WARN_ON in start_thread() Vinay Kumar Yadav (1): chelsio/chtls: fix panic during unload reload chtls Wang Hai (2): ipv6: addrlabel: fix possible memory leak in ip6addrlbl_net_init net: mvpp2: Fix error return code in mvpp2_open() Willem de Bruijn (1): sock: set sk_err to ee_errno on dequeue from errq Yves-Alexis Perez (1): usbnet: ipheth: fix connectivity with iOS 14 Zhang Changzhong (2): cxgb3: fix error return code in t3_sge_alloc_qset() net: pasemi: fix error return code in pasemi_mac_open() .../devicetree/bindings/net/nfc/nxp-nci.txt | 2 +- .../devicetree/bindings/net/nfc/pn544.txt | 2 +- Makefile | 2 +- drivers/crypto/chelsio/chtls/chtls_cm.c | 1 + drivers/crypto/chelsio/chtls/chtls_hw.c | 1 + drivers/infiniband/hw/i40iw/i40iw_main.c | 5 -- drivers/infiniband/hw/i40iw/i40iw_verbs.c | 36 +++-------- drivers/input/joystick/xpad.c | 2 + drivers/input/serio/i8042-x86ia64io.h | 4 ++ drivers/net/bonding/bond_main.c | 61 +++++++++++++------ drivers/net/bonding/bond_sysfs_slave.c | 18 +----- drivers/net/ethernet/chelsio/cxgb3/sge.c | 1 + drivers/net/ethernet/ibm/ibmvnic.c | 26 ++++++-- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 22 ++++--- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 26 ++++---- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 1 + .../ethernet/mellanox/mlx5/core/pagealloc.c | 21 ++++++- drivers/net/ethernet/pasemi/pasemi_mac.c | 8 ++- drivers/net/geneve.c | 20 ++++-- drivers/net/tun.c | 14 ++++- drivers/net/usb/ipheth.c | 2 +- include/net/bonding.h | 8 +++ include/net/tls.h | 6 ++ kernel/trace/trace_hwlat.c | 2 +- net/bridge/br_netfilter_hooks.c | 7 ++- net/core/skbuff.c | 2 +- net/ipv4/route.c | 7 ++- net/ipv4/tcp_cong.c | 5 ++ net/ipv6/addrlabel.c | 26 +++++--- net/ipv6/ip6_gre.c | 16 ++++- net/iucv/af_iucv.c | 4 +- net/rose/rose_loopback.c | 17 ++++-- net/tls/tls_device.c | 5 +- net/tls/tls_sw.c | 6 ++ net/x25/af_x25.c | 6 +- sound/usb/mixer_us16x08.c | 2 +- 37 files changed, 260 insertions(+), 135 deletions(-) -- 2.25.1

1 32

[PATCH] fanotify: fix merging marks masks with FAN_ONDIR
by Yang Yingliang 10 Dec '20

10 Dec '20

From: Amir Goldstein <amir73il(a)gmail.com> mainline inclusion from mainline-5.7-rc1 commit 55bf882c7f13dda8bbe624040c6d5b4fbb812d16 category: bugfix bugzilla: 46764 CVE: NA https://gitee.com/openeuler/kernel/issues/I27PTB?from=project-issue --------------------------- Change the logic of FAN_ONDIR in two ways that are similar to the logic of FAN_EVENT_ON_CHILD, that was fixed in commit 54a307ba8d3c ("fanotify: fix logic of events on child"): 1. The flag is meaningless in ignore mask 2. The flag refers only to events in the mask of the mark where it is set This is what the fanotify_mark.2 man page says about FAN_ONDIR: "Without this flag, only events for files are created." It doesn't say anything about setting this flag in ignore mask to stop getting events on directories nor can I think of any setup where this capability would be useful. Currently, when marks masks are merged, the FAN_ONDIR flag set in one mark affects the events that are set in another mark's mask and this behavior causes unexpected results. For example, a user adds a mark on a directory with mask FAN_ATTRIB | FAN_ONDIR and a mount mark with mask FAN_OPEN (without FAN_ONDIR). An opendir() of that directory (which is inside that mount) generates a FAN_OPEN event even though neither of the marks requested to get open events on directories. Link: https://lore.kernel.org/r/20200319151022.31456-10-amir73il@gmail.com Signed-off-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Jan Kara <jack(a)suse.cz> Conflicts: fs/notify/fanotify/fanotify.c Signed-off-by: yangerkun <yangerkun(a)huawei.com> Reviewed-by: zhangyi (F) <yi.zhang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/notify/fanotify/fanotify.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index ca3405f73264..cdf0dc9ddbbb 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -117,6 +117,12 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info, /* Apply ignore mask regardless of ISDIR and ON_CHILD flags */ marks_ignored_mask |= mark->ignored_mask; + /* + * If the event is on dir and this mark doesn't care about + * events on dir, don't send it! + */ + if (d_is_dir(path->dentry) && !(mark->mask & FS_ISDIR)) + continue; /* * If the event is for a child and this mark doesn't care about @@ -130,10 +136,6 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info, marks_mask |= mark->mask; } - if (d_is_dir(path->dentry) && - !(marks_mask & FS_ISDIR & ~marks_ignored_mask)) - return false; - if (event_mask & FAN_ALL_OUTGOING_EVENTS & marks_mask & ~marks_ignored_mask) return true; -- 2.25.1

1 0

openEuler kernel sig meeting
by openEuler conference 09 Dec '20

09 Dec '20

3 3

[PATCH 01/17] share_pool: Fix series of bugs
by Yang Yingliang 08 Dec '20

08 Dec '20

From: Tang Yizhou <tangyizhou(a)huawei.com> ascend inclusion category: bugfix bugzilla: NA CVE: NA ------------------------------------------------- 1. Error handling of sp_free(). 2. When sp_alloc(..., SP_HUGEPAGE, ...) rollbacks to normal page, we need to call vfs_fallocate() otherwise memory leaks until sp group is dead. 3. When sp_alloc(..., SP_HUGEPAGE, ...) rollbacks to normal page, we need to clear SP_HUGEPAGE bit in sp_flags then spa_stat interface will show the spa as a normal page spa correctly. 4. Add the reference count of a spg in find_or_alloc_sp_group() due to closer relationship. Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index d39c2c3d728c..a71f6fb214ce 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -358,7 +358,7 @@ static struct sp_group *find_or_alloc_sp_group(int spg_id) spg->hugepage_failures = 0; spg->dvpp_multi_spaces = false; spg->owner = current->group_leader; - atomic_set(&spg->use_count, 0); + atomic_set(&spg->use_count, 1); INIT_LIST_HEAD(&spg->procs); INIT_LIST_HEAD(&spg->spa_list); @@ -391,6 +391,10 @@ static struct sp_group *find_or_alloc_sp_group(int spg_id) ret = PTR_ERR(spg->file_hugetlb); goto out_fput; } + } else { + if (!spg_valid(spg)) + return ERR_PTR(-ENODEV); + atomic_inc(&spg->use_count); } return spg; @@ -540,12 +544,6 @@ int sp_group_add_task(int pid, int spg_id) goto out_put_task; } - if (!spg_valid(spg)) { - ret = -ENODEV; - goto out_put_task; - } - atomic_inc(&spg->use_count); - /* access control permission check */ if (sysctl_ac_mode == AC_SINGLE_OWNER) { if (spg->owner != current->group_leader) { @@ -1102,6 +1100,7 @@ int sp_free(unsigned long addr) if (printk_ratelimit()) pr_err("share pool: sp free failed, addr %pK is not from sp_alloc\n", (void *)addr); + goto drop_spa; } if (!spg_valid(spa->spg)) @@ -1312,31 +1311,32 @@ void *sp_alloc(unsigned long size, unsigned long sp_flags, int spg_id) __sp_free(spg, sp_addr, size_aligned, list_next_entry(mm, sp_node)); + if (printk_ratelimit()) + pr_warn("share pool: allocation failed due to mm populate failed" + "(potential no enough memory when -12): %d\n", ret); + p = ERR_PTR(ret); + + mode = FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE; + offset = sp_addr - MMAP_SHARE_POOL_START; + + ret = vfs_fallocate(spa_file(spa), mode, offset, spa_size(spa)); + if (ret) + pr_err("share pool: sp alloc normal page fallocate failed %d\n", ret); + if (file == spg->file_hugetlb) { spg->hugepage_failures++; /* fallback to small pages */ if (!(sp_flags & SP_HUGEPAGE_ONLY)) { file = spg->file; - spa->is_hugepage = false; size_aligned = ALIGN(size, PAGE_SIZE); + sp_flags &= ~SP_HUGEPAGE; __sp_area_drop(spa); mmput(mm); goto try_again; } } - if (printk_ratelimit()) - pr_warn("share pool: allocation failed due to mm populate failed" - "(potential no enough memory when -12): %d\n", ret); - p = ERR_PTR(ret); - - mode = FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE; - offset = sp_addr - MMAP_SHARE_POOL_START; - ret = vfs_fallocate(spa_file(spa), mode, offset, spa_size(spa)); - if (ret) - pr_err("share pool: fallocate failed %d\n", ret); - mmput(mm); break; } -- 2.25.1

1 16

[PATCH 1/7] ascend: share_pool: Use sharepool_no_page to alloc hugepage
by Yang Yingliang 08 Dec '20

08 Dec '20

From: Weilong Chen <chenweilong(a)huawei.com> ascend inclusion category: feature bugzilla: NA CVE: NA ------------------------------------------------- Sharepool applies for a dedicated interface for large pages, which optimizes the efficiency of memory application Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/hugetlb.h | 4 ++ include/linux/share_pool.h | 5 +++ mm/hugetlb.c | 22 +++++++--- mm/share_pool.c | 90 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 115 insertions(+), 6 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index bd658f44e133..be649e5ba322 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -645,4 +645,8 @@ static inline spinlock_t *huge_pte_lock(struct hstate *h, return ptl; } +#ifdef CONFIG_ASCEND_SHARE_POOL +pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable); +#endif + #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/share_pool.h b/include/linux/share_pool.h index 2557ef138122..47d8579c23ec 100644 --- a/include/linux/share_pool.h +++ b/include/linux/share_pool.h @@ -220,6 +220,11 @@ static inline void sp_dump_stack(void) dump_stack(); } +vm_fault_t sharepool_no_page(struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, pgoff_t idx, + unsigned long address, pte_t *ptep, unsigned int flags); + #else static inline int sp_group_add_task(int pid, int spg_id) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9d2035632aed..a68e7e1afd82 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3352,8 +3352,13 @@ const struct vm_operations_struct hugetlb_vm_ops = { .pagesize = hugetlb_vm_op_pagesize, }; +#ifdef CONFIG_ASCEND_SHARE_POOL +pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, + int writable) +#else static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, int writable) +#endif { pte_t entry; @@ -3370,6 +3375,9 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, return entry; } +#ifdef CONFIG_ASCEND_SHARE_POOL +EXPORT_SYMBOL(make_huge_pte); +#endif static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) @@ -3962,12 +3970,6 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, } page = alloc_huge_page(vma, haddr, 0); - if (IS_ERR(page) && sp_check_vm_share_pool(vma->vm_flags)) { - page = alloc_huge_page_node(hstate_file(vma->vm_file), - numa_mem_id()); - if (!page) - page = ERR_PTR(-ENOMEM); - } if (IS_ERR(page)) { /* * Returning error will result in faulting task being @@ -4155,7 +4157,15 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, entry = huge_ptep_get(ptep); if (huge_pte_none(entry)) { +#ifdef CONFIG_ASCEND_SHARE_POOL + if (sp_check_vm_share_pool(vma->vm_flags)) { + ret = sharepool_no_page(mm, vma, mapping, idx, address, ptep, flags); + } else { + ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); + } +#else ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags); +#endif goto out_mutex; } diff --git a/mm/share_pool.c b/mm/share_pool.c index 23195a76c2c6..286e74f99360 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -41,6 +41,8 @@ #include <linux/idr.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/rmap.h> +#include <linux/hugetlb.h> /* access control mode macros */ #define AC_NONE 0 @@ -2399,6 +2401,94 @@ static int spa_stat_show(struct seq_file *seq, void *offset) return 0; } +vm_fault_t sharepool_no_page(struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, pgoff_t idx, + unsigned long address, pte_t *ptep, unsigned int flags) +{ + struct hstate *h = hstate_vma(vma); + vm_fault_t ret = VM_FAULT_SIGBUS; + unsigned long size; + struct page *page; + pte_t new_pte; + spinlock_t *ptl; + unsigned long haddr = address & huge_page_mask(h); + bool new_page = false; + int err; + +retry: + page = find_lock_page(mapping, idx); + if (!page) { + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto out; + + page = alloc_huge_page(vma, haddr, 0); + if (IS_ERR(page)) { + page = alloc_huge_page_node(hstate_file(vma->vm_file), + numa_mem_id()); + if (!page) + page = ERR_PTR(-ENOMEM); + } + if (IS_ERR(page)) { + ptl = huge_pte_lock(h, mm, ptep); + if (!huge_pte_none(huge_ptep_get(ptep))) { + ret = 0; + spin_unlock(ptl); + goto out; + } + spin_unlock(ptl); + ret = vmf_error(PTR_ERR(page)); + goto out; + } + __SetPageUptodate(page); + new_page = true; + + /* sharepool pages are all shared */ + err = huge_add_to_page_cache(page, mapping, idx); + if (err) { + put_page(page); + if (err == -EEXIST) + goto retry; + goto out; + } + } + + + ptl = huge_pte_lock(h, mm, ptep); + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto backout; + + ret = 0; + if (!huge_pte_none(huge_ptep_get(ptep))) + goto backout; + + page_dup_rmap(page, true); + new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) + && (vma->vm_flags & VM_SHARED))); + set_huge_pte_at(mm, haddr, ptep, new_pte); + + hugetlb_count_add(pages_per_huge_page(h), mm); + + spin_unlock(ptl); + + if (new_page) { + SetPagePrivate(&page[1]); + } + + unlock_page(page); +out: + return ret; + +backout: + spin_unlock(ptl); + unlock_page(page); + put_page(page); + goto out; +} +EXPORT_SYMBOL(sharepool_no_page); + /* * Called by proc_root_init() to initialize the /proc/sharepool subtree */ -- 2.25.1

1 6

Compilation error on openeuler 2003 LTS
by Zhengyuan Liu 08 Dec '20

08 Dec '20

Building the latest 2003 LTS can trigger following compilation error: In file included from ./include/acpi/acpi_io.h:7:0, from ./include/linux/acpi.h:47, from ./arch/arm64/include/asm/machine_t.h:26, from arch/arm64/kernel/process.c:64: ./arch/arm64/include/asm/acpi.h:82:20: error: ‘enable_acpi’ redeclared as different kind of symbol static inline void enable_acpi(void) ^~~~~~~~~~~ In file included from arch/arm64/kernel/process.c:61:0: ./arch/arm64/include/asm/mpam_sched.h:46:2: note: previous definition of ‘enable_acpi’ was here enable_acpi, The redefinition was introduced by commit 7e66740ad725 ("MPAM / ACPI: Refactoring MPAM init process and set MPAM ACPI as entrance")

2 2

openEuler Summit 报名渠道开启，我们为社区内的开发者准备了很多专属环节
by public openEuler 07 Dec '20

07 Dec '20

各位社区内的开发者： openEuler Summit 所有议程 <https://openeuler.org/zh/interaction/summit-list/> 本周已经全部上线。本次峰会设置了 Linux 操作系统、云与云原生、虚拟化、基础软件、开源基础设施、安全与可信六大专场。一些通过 Call for Speaker 提交的议题已经入选。欢迎大家快来围观有没有你感兴趣的议题。 [image: image.png] 针对社区的开发者，我们准备了很多专属环节： 1. 大会为社区开发者准备了专属报名通道，在现场有专属的签到通道和定制的伴手礼。 2. 大会为Maintainer 准备了一份十分具有荣誉感和纪念意义的徽章。大会现场还准备了惊喜环节：大会主题演讲时会通过报名时你填写的 Gitee ID 和Gitee 后台的数据演示一个非常炫酷的Live Demo。我们诚挚地邀请社区开发者到现场参会。社区开发者专属报名通道：https://etherpad.openeuler.org/p/openEuler-Summit-2020 P.S：通过该链接报名的人员可以参加 Day1和 Day2 两天会议。 openEuler 也将迎来自己的一周岁生日，社区准备了一个“我为 openEuler 代言”的百人视频合集，诚挚地邀请所有热爱openEuler 的人来拍摄一段视频，来纪念openEuler这朝气蓬勃的第一年。 “我为 openEuler 代言”的视频拍摄需求：自拍形式，对着镜头回答以下问题： 1. 我想要的操作系统是****的， 2. 我在**时候参与/认识/加入/知道的openEuler（社区） 3. 我在openEuler贡献了**** 4. 我是***，我为openEuler代言使用场景：您拍摄的视频素材将用于 openEuler Summit 2020 前期的会议宣传和开场视频中。拍摄指导： 1. 背景任您喜欢 2. 人物面对镜头，位于画面中央，取半身构图，横向拍摄16:9 的画面比例 3. 最好选择白炽灯，白色光源 4. 尽量由另一个人辅助，用手机后置摄像头拍摄，不要用前置，拍摄前擦拭摄像头 5. 读口播时，声音越大越好 6. 尽量保证每一句话都是完整通顺的，中间重来的部分可以忽略 7. 视频输出，用电脑将手机视频导出，打压缩包传输即可（不要用微信上传，会压缩画质） 8. 拍摄完毕后请将视频上传到百度网盘，将分享链接期限设置为永久，然后发给 public(a)openeuler.io 9. 视频收集截止日期：2020年12月11日23:59分

1 0

[PATCH 00/58] backport stable-4.19.161
by Yang Yingliang 03 Dec '20

03 Dec '20

Alan Stern (2): USB: core: Change %pK for __user pointers to %px USB: core: Fix regression in Hercules audio card Anand K Mistry (1): x86/speculation: Fix prctl() when spectre_v2_user={seccomp,prctl},ibpb Ard Biesheuvel (1): efivarfs: revert "fix memory leak in efivarfs_create()" Benjamin Berg (1): platform/x86: thinkpad_acpi: Send tablet mode switch at wakeup time Brian Masney (1): x86/xen: don't unbind uninitialized lock_kicker_irq Chris Ye (1): HID: add HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE for Gamevice devices Cong Wang (1): netfilter: clear skb->next in NF_HOOK_LIST() Dexuan Cui (1): video: hyperv_fb: Fix the cache type when mapping the VRAM Filipe Manana (1): btrfs: fix lockdep splat when reading qgroup config on mount Frank Yang (1): HID: cypress: Support Varmilo Keyboards' media hotkeys Greg Kroah-Hartman (1): Linux 4.19.161 Hans de Goede (2): Input: i8042 - allow insmod to succeed on devices without an i8042 controller HID: Add Logitech Dinovo Edge battery quirk Hauke Mehrtens (1): wireless: Use linux/stddef.h instead of stddef.h Igor Lubashev (1): perf event: Check ref_reloc_sym before using it Jens Axboe (1): proc: don't allow async path resolution of /proc/self components Jiri Kosina (1): HID: add support for Sega Saturn Johannes Thumshirn (1): btrfs: don't access possibly stale fs_info data for printing duplicate device Julian Wiedmann (1): s390/qeth: fix tear down of async TX buffers Kai Vehmanen (1): ALSA: hda/hdmi: fix incorrect locking in hdmi_pcm_close Kaixu Xia (1): platform/x86: toshiba_acpi: Fix the wrong variable assignment Krzysztof Kozlowski (1): nfc: s3fwrn5: use signed integer for parsing GPIO numbers Laurent Pinchart (1): xtensa: uaccess: Add missing __user to strncpy_from_user() prototype Lee Duncan (1): scsi: libiscsi: Fix NOP race condition Lijun Pan (2): ibmvnic: fix NULL pointer dereference in reset_sub_crq_queues ibmvnic: fix NULL pointer dereference in ibmvic_reset_crq Lyude Paul (1): drm/atomic_helper: Stop modesets on unregistered connectors harder Marc Ferland (1): dmaengine: xilinx_dma: use readl_poll_timeout_atomic variant Marc Kleine-Budde (3): ARM: dts: dra76x: m_can: fix order of clocks can: gs_usb: fix endianess problem with candleLight firmware can: m_can: fix nominal bitiming tseg2 min for version >= 3.1 Marc Zyngier (1): phy: tegra: xusb: Fix dangling pointer on probe failure Masami Hiramatsu (1): perf probe: Fix to die_entrypc() returns error correctly Michael Chan (1): bnxt_en: Release PCI regions when DMA mask setup fails during probe. Mike Christie (1): scsi: target: iscsi: Fix cmd abort fabric stop race Minwoo Im (1): nvme: free sq/cq dbbuf pointers when dbbuf set fails Pablo Ceballos (1): HID: hid-sensor-hub: Fix issue with devices with no report ID Paolo Bonzini (2): KVM: x86: handle !lapic_in_kernel case in kvm_cpu_*_extint KVM: x86: Fix split-irqchip vs interrupt injection window request Raju Rangoju (1): cxgb4: fix the panic caused by non smac rewrite Rui Miguel Silva (1): optee: add writeback to valid memory type Sami Tolvanen (1): perf/x86: fix sysfs type mismatches Shay Agroskin (1): net: ena: set initial DMA width to avoid intel iommu issue Stanley Chu (1): scsi: ufs: Fix race between shutdown and runtime resume flow Sugar Zhang (1): dmaengine: pl330: _prep_dma_memcpy: Fix wrong burst size Taehee Yoo (1): batman-adv: set .owner to THIS_MODULE Will Deacon (2): arm64: pgtable: Fix pte_accessible() arm64: pgtable: Ensure dirty bit is preserved across pte_wrprotect() Xiaochen Shen (2): x86/resctrl: Remove superfluous kernfs_get() calls to prevent refcount leak x86/resctrl: Add necessary kernfs_put() calls to prevent refcount leak Xiongfeng Wang (1): IB/mthca: fix return value of error branch in mthca_init_cq() Zenghui Yu (1): KVM: arm64: vgic-v3: Drop the reporting of GICR_TYPER.Last for userspace Zhang Changzhong (2): bnxt_en: fix error return code in bnxt_init_one() bnxt_en: fix error return code in bnxt_init_board() Zhang Qilong (2): usb: gadget: f_midi: Fix memleak in f_midi_alloc usb: gadget: Fix memleak in gadgetfs_fill_super penghao (1): USB: quirks: Add USB_QUIRK_DISCONNECT_SUSPEND quirk for Lenovo A630Z TIO built-in usb-audio card Makefile | 2 +- arch/arm/boot/dts/dra76x.dtsi | 4 +- arch/arm64/include/asm/pgtable.h | 34 ++--- arch/x86/events/intel/cstate.c | 6 +- arch/x86/events/intel/rapl.c | 14 +- arch/x86/events/intel/uncore.c | 4 +- arch/x86/events/intel/uncore.h | 12 +- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kernel/cpu/bugs.c | 4 +- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 65 ++++----- arch/x86/kvm/irq.c | 85 +++++------- arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/x86.c | 18 +-- arch/x86/xen/spinlock.c | 12 +- arch/xtensa/include/asm/uaccess.h | 2 +- drivers/dma/pl330.c | 2 +- drivers/dma/xilinx/xilinx_dma.c | 4 +- drivers/gpu/drm/drm_atomic.c | 21 --- drivers/gpu/drm/drm_atomic_helper.c | 21 ++- drivers/gpu/drm/drm_connector.c | 11 +- drivers/gpu/drm/i915/intel_dp_mst.c | 8 +- drivers/hid/hid-cypress.c | 44 +++++- drivers/hid/hid-ids.h | 8 ++ drivers/hid/hid-input.c | 3 + drivers/hid/hid-quirks.c | 5 + drivers/hid/hid-sensor-hub.c | 3 +- drivers/infiniband/hw/mthca/mthca_cq.c | 10 +- drivers/input/serio/i8042.c | 12 +- drivers/net/can/m_can/m_can.c | 2 +- drivers/net/can/usb/gs_usb.c | 131 ++++++++++-------- drivers/net/ethernet/amazon/ena/ena_netdev.c | 17 ++- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 +- .../net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 +- drivers/net/ethernet/ibm/ibmvnic.c | 6 + drivers/nfc/s3fwrn5/i2c.c | 4 +- drivers/nvme/host/pci.c | 15 ++ drivers/phy/tegra/xusb.c | 1 + drivers/platform/x86/thinkpad_acpi.c | 1 + drivers/platform/x86/toshiba_acpi.c | 3 +- drivers/s390/net/qeth_core_main.c | 6 - drivers/scsi/libiscsi.c | 23 +-- drivers/scsi/ufs/ufshcd.c | 6 +- drivers/target/iscsi/iscsi_target.c | 17 ++- drivers/tee/optee/call.c | 3 +- drivers/usb/core/devio.c | 14 +- drivers/usb/core/quirks.c | 10 ++ drivers/usb/gadget/function/f_midi.c | 10 +- drivers/usb/gadget/legacy/inode.c | 3 + drivers/video/fbdev/hyperv_fb.c | 7 +- fs/btrfs/qgroup.c | 2 +- fs/btrfs/volumes.c | 8 +- fs/efivarfs/inode.c | 2 + fs/efivarfs/super.c | 1 - fs/proc/self.c | 7 + include/drm/drm_connector.h | 71 +++++++++- include/linux/netfilter.h | 2 +- include/scsi/libiscsi.h | 3 + include/uapi/linux/wireless.h | 6 +- net/batman-adv/log.c | 1 + sound/pci/hda/patch_hdmi.c | 20 +-- tools/perf/util/dwarf-aux.c | 8 ++ tools/perf/util/event.c | 7 +- virt/kvm/arm/vgic/vgic-mmio-v3.c | 22 ++- 63 files changed, 540 insertions(+), 323 deletions(-) -- 2.25.1

1 49

[PATCH 00/87] backport patches from linux-4.19.y for openEuler-1.0-LTS
by Yang Yingliang 02 Dec '20

02 Dec '20

Al Viro (1): don't dump the threads that had been already exiting when zapped. Aleksandr Nogikh (1): netem: fix zero division in tabledist Andy Shevchenko (2): device property: Keep secondary firmware node secondary by type device property: Don't clear secondary pointer for shared primary firmware node Arjun Roy (1): tcp: Prevent low rmem stalls with SO_RCVLOWAT. Arnaldo Carvalho de Melo (1): perf scripting python: Avoid declaring function pointers with a visibility attribute Boris Protopopov (1): Convert trailing spaces and periods in path components Brian Foster (1): xfs: flush new eof page on truncate to avoid post-eof corruption Chen Zhou (1): selinux: Fix error return code in sel_ib_pkey_sid_slow() Christoph Hellwig (2): nbd: fix a block_device refcount leak in nbd_release xfs: fix a missing unlock on error in xfs_fs_map_blocks Chunyan Zhang (1): tick/common: Touch watchdog in tick_unfreeze() on all CPUs Dan Carpenter (1): futex: Don't enable IRQs unconditionally in put_pi_state() Darrick J. Wong (12): xfs: fix realtime bitmap/summary file truncation when growing rt volume xfs: don't free rt blocks when we're doing a REMAP bunmapi call xfs: set xefi_discard when creating a deferred agfl free log intent item xfs: fix scrub flagging rtinherit even if there is no rt device xfs: fix flags argument to rmap lookup when converting shared file rmaps xfs: set the unwritten bit in rmap lookup flags in xchk_bmap_get_rmapextents xfs: fix rmap key and record comparison functions xfs: fix brainos in the refcount scrubber's rmap fragment processor vfs: remove lockdep bogosity in __sb_start_write xfs: fix the minrecs logic when dealing with inode root child blocks xfs: strengthen rmap record flags checking xfs: revert "xfs: fix rmap key and record comparison functions" Dinghao Liu (1): ext4: fix error handling code in add_new_gdb Dongli Zhang (1): page_frag: Recover from memory pressure Douglas Gilbert (1): sgl_alloc_order: fix memory leak Eddy Wu (1): fork: fix copy_process(CLONE_PARENT) race with the exiting ->real_parent Eric Biggers (1): ext4: fix leaking sysfs kobject after failed mount Gabriel Krisman Bertazi (2): blk-cgroup: Fix memleak on error path blk-cgroup: Pre-allocate tree node on blkg_conf_prep George Spelvin (1): random32: make prandom_u32() output unpredictable Gerald Schaefer (1): mm/userfaultfd: do not access vma->vm_mm after calling handle_userfault() Heiner Kallweit (1): net: bridge: add missing counters to ndo_get_stats64 callback Jan Kara (2): ext4: Detect already used quota file early ext4: fix bogus warning in ext4_update_dx_flag() Jason A. Donenfeld (1): netfilter: use actual socket sk rather than skb sk when routing harder Jiri Olsa (2): perf python scripting: Fix printable strings in python3 scripts perf tools: Add missing swap for ino_generation Jonathan Cameron (1): ACPI: Add out of bounds and numa_off protections to pxm_to_node() Joseph Qi (1): ext4: unlock xattr_sem properly in ext4_inline_data_truncate() Kaixu Xia (1): ext4: correctly report "not supported" for {usr, grp}jquota when !CONFIG_QUOTA Lang Dai (1): uio: free uio id after uio file node is freed Lee Jones (1): Fonts: Replace discarded const qualifier Leo Yan (1): perf lock: Don't free "lock_seq_stat" if read_count isn't zero Luo Meng (2): ext4: fix invalid inode checksum fail_function: Remove a redundant mutex unlock Mao Wenan (1): net: Update window_clamp if SOCK_RCVBUF is set Marc Zyngier (1): arm64: Run ARCH_WORKAROUND_1 enabling code on all CPUs Mateusz Nosek (1): futex: Fix incorrect should_fail_futex() handling Matteo Croce (2): Revert "kernel/reboot.c: convert simple_strtoul to kstrtoint" reboot: fix overflow parsing reboot cpu number Michael Schaller (1): efivarfs: Replace invalid slashes with exclamation marks in dentries. Mike Galbraith (1): futex: Handle transient "ownerless" rtmutex state correctly Miklos Szeredi (1): fuse: fix page dereference after free Ming Lei (1): scsi: core: Don't start concurrent async scan on same host Nicholas Piggin (1): mm: fix exec activate_mm vs TLB shootdown and lazy tlb switching race Oleg Nesterov (1): ptrace: fix task_join_group_stop() for the case when current is traced Oliver Herms (1): IPv6: Set SIT tunnel hard_header_len to zero Peter Zijlstra (2): serial: pl011: Fix lockdep splat when handling magic-sysrq interrupt perf: Fix get_recursion_context() Qiujun Huang (2): ring-buffer: Return 0 on success from ring_buffer_resize() tracing: Fix out of bounds write in get_trace_buf Ronnie Sahlberg (1): cifs: handle -EINTR in cifs_setattr Ryan Sharpelletti (1): tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate Shijie Luo (1): mm: mempolicy: fix potential pte_unmap_unlock pte error Shin'ichiro Kawasaki (1): uio: Fix use-after-free in uio_unregister_device() Stefano Brivio (1): netfilter: ipset: Update byte and packet counters regardless of whether they match Steven Rostedt (VMware) (3): ring-buffer: Fix recursion protection transitions between interrupt context ftrace: Fix recursion check for NMI test ftrace: Handle tracing when switching between context Tyler Hicks (1): tpm: efi: Don't create binary_bios_measurements file for an empty log Valentin Schneider (1): arm64: topology: Stop using MPIDR for topology information Vamshi K Sthambamkadi (1): efivarfs: fix memory leak in efivarfs_create() Wang Hai (2): devlink: Add missing genlmsg_cancel() in devlink_nl_sb_port_pool_fill() inet_diag: Fix error path to cancel the meseage in inet_req_diag_fill() Wengang Wang (1): ocfs2: initialize ip_next_orphan Will Deacon (1): arm64: psci: Avoid printing in cpu_psci_cpu_die() Xiubo Li (1): nbd: make the config put is called before the notifying the waiter Yi-Hung Wei (1): ip_tunnels: Set tunnel option flag when tunnel metadata is present Yicong Yang (1): libfs: fix error cast of negative value in simple_attr_write() Yunsheng Lin (1): net: sch_generic: fix the missing new qdisc assignment bug Zeng Tao (1): time: Prevent undefined behaviour in timespec64_to_ns() Zhengyuan Liu (1): arm64/mm: return cpu_all_mask when node is NUMA_NO_NODE Zqiang (1): kthread_worker: prevent queuing delayed work from timer_fn when it is being canceled zhuoliang zhang (1): net: xfrm: fix a race condition during allocing spi arch/Kconfig | 7 + arch/arm64/include/asm/numa.h | 3 + arch/arm64/kernel/cpu_errata.c | 8 + arch/arm64/kernel/psci.c | 5 +- arch/arm64/kernel/topology.c | 43 +- arch/arm64/mm/numa.c | 6 +- block/blk-cgroup.c | 15 +- drivers/acpi/numa.c | 2 +- drivers/base/core.c | 4 +- drivers/block/nbd.c | 3 +- drivers/char/random.c | 1 - drivers/char/tpm/eventlog/efi.c | 5 + drivers/net/geneve.c | 3 +- drivers/scsi/scsi_scan.c | 7 +- drivers/tty/serial/amba-pl011.c | 11 +- drivers/uio/uio.c | 12 +- fs/cifs/cifs_unicode.c | 8 +- fs/cifs/inode.c | 13 +- fs/efivarfs/super.c | 4 + fs/exec.c | 15 +- fs/ext4/ext4.h | 3 +- fs/ext4/inline.c | 1 + fs/ext4/inode.c | 11 +- fs/ext4/resize.c | 4 +- fs/ext4/super.c | 10 +- fs/fuse/dev.c | 28 +- fs/libfs.c | 6 +- fs/ocfs2/super.c | 1 + fs/super.c | 33 +- fs/xfs/libxfs/xfs_alloc.c | 1 + fs/xfs/libxfs/xfs_bmap.c | 19 +- fs/xfs/libxfs/xfs_bmap.h | 2 +- fs/xfs/libxfs/xfs_rmap.c | 2 +- fs/xfs/scrub/bmap.c | 10 +- fs/xfs/scrub/btree.c | 45 +- fs/xfs/scrub/inode.c | 3 +- fs/xfs/scrub/refcount.c | 8 +- fs/xfs/xfs_iops.c | 10 + fs/xfs/xfs_pnfs.c | 2 +- fs/xfs/xfs_rtalloc.c | 10 +- include/linux/netfilter_ipv4.h | 2 +- include/linux/netfilter_ipv6.h | 2 +- include/linux/prandom.h | 36 +- include/linux/time64.h | 4 + include/net/ip_tunnels.h | 7 +- kernel/events/internal.h | 2 +- kernel/exit.c | 5 +- kernel/fail_function.c | 5 +- kernel/fork.c | 10 +- kernel/futex.c | 25 +- kernel/kthread.c | 3 +- kernel/reboot.c | 28 +- kernel/signal.c | 19 +- kernel/time/itimer.c | 4 - kernel/time/tick-common.c | 2 + kernel/time/timer.c | 7 - kernel/trace/ring_buffer.c | 66 ++- kernel/trace/trace.c | 2 +- kernel/trace/trace.h | 26 +- kernel/trace/trace_selftest.c | 9 +- lib/fonts/font_10x18.c | 2 +- lib/fonts/font_6x10.c | 2 +- lib/fonts/font_6x11.c | 2 +- lib/fonts/font_7x14.c | 2 +- lib/fonts/font_8x16.c | 2 +- lib/fonts/font_8x8.c | 2 +- lib/fonts/font_acorn_8x8.c | 2 +- lib/fonts/font_mini_4x6.c | 2 +- lib/fonts/font_pearl_8x8.c | 2 +- lib/fonts/font_sun12x22.c | 2 +- lib/fonts/font_sun8x16.c | 2 +- lib/random32.c | 462 +++++++++++------- lib/scatterlist.c | 2 +- mm/huge_memory.c | 9 +- mm/mempolicy.c | 6 +- mm/page_alloc.c | 5 + net/bridge/br_device.c | 1 + net/core/devlink.c | 6 +- net/ipv4/inet_diag.c | 4 +- net/ipv4/netfilter.c | 12 +- net/ipv4/netfilter/ipt_SYNPROXY.c | 2 +- net/ipv4/netfilter/iptable_mangle.c | 2 +- net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 2 +- net/ipv4/netfilter/nft_chain_route_ipv4.c | 2 +- net/ipv4/syncookies.c | 9 +- net/ipv4/tcp.c | 2 + net/ipv4/tcp_bbr.c | 2 +- net/ipv4/tcp_input.c | 3 +- net/ipv6/netfilter.c | 6 +- net/ipv6/netfilter/ip6table_mangle.c | 2 +- net/ipv6/netfilter/nf_nat_l3proto_ipv6.c | 2 +- net/ipv6/netfilter/nft_chain_route_ipv6.c | 2 +- net/ipv6/sit.c | 2 - net/ipv6/syncookies.c | 10 +- net/netfilter/ipset/ip_set_core.c | 3 +- net/netfilter/ipvs/ip_vs_core.c | 4 +- net/sched/sch_generic.c | 3 + net/sched/sch_netem.c | 9 +- net/xfrm/xfrm_state.c | 8 +- security/selinux/ibpkey.c | 4 +- tools/perf/builtin-lock.c | 2 +- tools/perf/util/print_binary.c | 2 +- .../scripting-engines/trace-event-python.c | 7 +- tools/perf/util/session.c | 1 + 105 files changed, 809 insertions(+), 461 deletions(-) -- 2.25.1

1 87

Re: openeuler patch tag咨询
by Xie XiuQi 02 Dec '20

02 Dec '20

Hi, On 2020/12/2 11:12, Zhengyuan Liu wrote: > > > On 2020/12/2 上午10:59, Yang Yingliang wrote: >> >> On 2020/12/2 10:47, Zhengyuan Liu wrote: >>> Hi, Xiuqi >>> >>> 最近在　backport OpenEuler内核补丁时对于补丁来源有个疑问，每个Patch　来源类别都在 >>> commit log　里面标注了，如 mainline inclusion, stable inclusion, 这两个比较好理解．但是像： >>> hulk >>> ascend >>> driver >>> euleros >>> 这几个我查阅openeuler开发文档也没找到说明，　所以想请问下你们这几个是怎么做区分的． >>> 这个开发者在向openeuler社区提补丁时也用得到，方便的话麻烦你们更新到文档里去．　这个确实是存在一些问题，这个 tag 的划分，既没有覆盖全，划分的标准也不完全一致。当前是给的比较主观的一些 tag，既有按领域的，也有按来源的,也有按子系统的。总之目的是为了方便识别和统计。下面表格是我准备发到社区讨论的，也请大家帮忙看看。 | 补丁 tag | 说明 | | ------------------- | ----------------------------------- | | mainline inclusion | 主线 backport | | stable inclusion | 上游 stable 分支的补丁 | | maillist inclusion | 发到社区，但是还没进主线的补丁 | | hulk inclusion | openEuler kernel 团队开发的补丁 | | virt inclusion | 虚拟化相关的补丁 | | ascend inclusion | 昇腾相关的补丁或特性 | | kunpeng inclusion | 鲲鹏相关的补丁或特性 | | dist inclusion | 从其他发行版移植的补丁 | | openEuler inclusion | 其他发送到openEuler社区的非上游补丁 | >> >> 非主线的补丁会用到上面的分类，只要补丁是来自主线的统一用mainline >> >> ascend是支持昇腾芯片的一些特有补丁 >> >> driver是驱动补丁 >> >> euleros和hulk是一类，主要是一些未进主线的或者待进主线的通用补丁 > > 感谢回复． > > driver相当于从hulk一类单独挑出来的是吧．从现有的分类来看，好像也没有严格的区分． > > >> >> >>> >>> 谢谢． >>> _______________________________________________ >>> Kernel mailing list -- kernel(a)openeuler.org >>> To unsubscribe send an email to kernel-leave(a)openeuler.org >> > >

1 0

openeuler patch tag咨询
by Zhengyuan Liu 02 Dec '20

02 Dec '20

Hi, Xiuqi 最近在　backport OpenEuler内核补丁时对于补丁来源有个疑问，每个Patch　来源类别都在 commit log　里面标注了，如 mainline inclusion, stable inclusion, 这两个比较好理解．但是像： hulk ascend driver euleros 这几个我查阅openeuler开发文档也没找到说明，　所以想请问下你们这几个是怎么做区分的．这个开发者在向openeuler社区提补丁时也用得到，方便的话麻烦你们更新到文档里去．　谢谢．

3 3

bonding: add an option to specify a delay between peer notifications
by liaichun 02 Dec '20

02 Dec '20

From: Vincent Bernat <vincent(a)bernat.ch> mainline inclusion from mainline-5.5-rc5 commit 07a4ddec3ce9b0a533b5f90f582f1057390d5e63 category: bugfix issue: I27SUX bugzilla: NA ------------------------------ Currently, gratuitous ARP/ND packets are sent every `miimon' milliseconds. This commit allows a user to specify a custom delay through a new option, `peer_notif_delay'. Like for `updelay' and `downdelay', this delay should be a multiple of `miimon' to avoid managing an additional work queue. The configuration logic is copied from `updelay' and `downdelay'. However, the default value cannot be set using a module parameter: Netlink or sysfs should be used to configure this feature. When setting `miimon' to 100 and `peer_notif_delay' to 500, we can observe the 500 ms delay is respected: 20:30:19.354693 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:19.874892 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:20.394919 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 20:30:20.914963 ARP, Request who-has 203.0.113.10 tell 203.0.113.10, length 28 In bond_mii_monitor(), I have tried to keep the lock logic readable. The change is due to the fact we cannot rely on a notification to lower the value of `bond->send_peer_notif' as `NETDEV_NOTIFY_PEERS' is only triggered once every N times, while we need to decrement the counter each time. iproute2 also needs to be updated to be able to specify this new attribute through `ip link'. Signed-off-by: Vincent Bernat <vincent(a)bernat.ch> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: wangli <wangli221(a)huawei.com> Signed-off-by: Aichun Li <liaichun(a)huawei.com> --- drivers/net/bonding/bond_main.c | 31 +-- drivers/net/bonding/bond_netlink.c | 14 ++ drivers/net/bonding/bond_options.c | 75 +++++--- drivers/net/bonding/bond_procfs.c | 3 +- drivers/net/bonding/bond_sysfs.c | 13 ++ include/net/bond_options.h | 1 + include/net/bonding.h | 3 +- include/uapi/linux/if_link.h | 1 + tools/include/uapi/linux/if_link.h | 1 + 9 files changed, 102 insertions(+), 40 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index a59333b..b1f3520 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -786,6 +786,8 @@ static bool bond_should_notify_peers(struct bonding *bond) slave ? slave->dev->name : "NULL"); if (!slave || !bond->send_peer_notif || + (bond->send_peer_notif % + max(1, bond->params.peer_notif_delay) != 0) || !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; @@ -878,15 +880,18 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (netif_running(bond->dev)) { bond->send_peer_notif = - bond->params.num_peer_notif; + bond->params.num_peer_notif * + max(1, bond->params.peer_notif_delay); should_notify_peers = bond_should_notify_peers(bond); } call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); - if (should_notify_peers) + if (should_notify_peers) { + bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); + } } } @@ -2290,6 +2295,7 @@ static void bond_mii_monitor(struct work_struct *work) struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; + bool commit; unsigned long delay; struct slave *slave; struct list_head *iter; @@ -2302,10 +2308,18 @@ static void bond_mii_monitor(struct work_struct *work) rcu_read_lock(); should_notify_peers = bond_should_notify_peers(bond); - - if (bond_miimon_inspect(bond)) { + commit = !!bond_miimon_inspect(bond); + if (bond->send_peer_notif) { + rcu_read_unlock(); + if (rtnl_trylock()) { + bond->send_peer_notif--; + rtnl_unlock(); + } + } else { rcu_read_unlock(); + } + if (commit) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; @@ -2319,9 +2333,7 @@ static void bond_mii_monitor(struct work_struct *work) bond_miimon_commit(bond); rtnl_unlock(); /* might sleep, hold no other locks */ - } else - rcu_read_unlock(); - + } re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); @@ -3093,10 +3105,6 @@ static int bond_master_netdev_event(unsigned long event, case NETDEV_REGISTER: bond_create_proc_entry(event_bond); break; - case NETDEV_NOTIFY_PEERS: - if (event_bond->send_peer_notif) - event_bond->send_peer_notif--; - break; default: break; } @@ -4743,6 +4751,7 @@ static int bond_check_params(struct bond_params *params) params->arp_all_targets = arp_all_targets_value; params->updelay = updelay; params->downdelay = downdelay; + params->peer_notif_delay = 0; params->use_carrier = use_carrier; params->lacp_fast = lacp_fast; params->primary[0] = 0; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index fbcd8a7..ae8e4e4 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -112,6 +112,7 @@ static int bond_fill_slave_info(struct sk_buff *skb, [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, + [IFLA_BOND_PEER_NOTIF_DELAY] = { .type = NLA_U32 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { @@ -219,6 +220,14 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], if (err) return err; } + if (data[IFLA_BOND_PEER_NOTIF_DELAY]) { + int delay = nla_get_u32(data[IFLA_BOND_PEER_NOTIF_DELAY]); + + bond_opt_initval(&newval, delay); + err = __bond_opt_set(bond, BOND_OPT_PEER_NOTIF_DELAY, &newval); + if (err) + return err; + } if (data[IFLA_BOND_USE_CARRIER]) { int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]); @@ -497,6 +506,7 @@ static size_t bond_get_size(const struct net_device *bond_dev) nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_USER_PORT_KEY */ nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ + nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ 0; } @@ -539,6 +549,10 @@ static int bond_fill_info(struct sk_buff *skb, bond->params.downdelay * bond->params.miimon)) goto nla_put_failure; + if (nla_put_u32(skb, IFLA_BOND_PEER_NOTIF_DELAY, + bond->params.peer_notif_delay * bond->params.miimon)) + goto nla_put_failure; + if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, bond->params.use_carrier)) goto nla_put_failure; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 80867bd..ceae69c 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -28,6 +28,8 @@ static int bond_option_updelay_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_downdelay_set(struct bonding *bond, const struct bond_opt_value *newval); +static int bond_option_peer_notif_delay_set(struct bonding *bond, + const struct bond_opt_value *newval); static int bond_option_use_carrier_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_arp_interval_set(struct bonding *bond, @@ -78,7 +80,10 @@ static int bond_option_ad_actor_system_set(struct bonding *bond, const struct bond_opt_value *newval); static int bond_option_ad_user_port_key_set(struct bonding *bond, const struct bond_opt_value *newval); - +static int _bond_option_delay_set(struct bonding *bond, + const struct bond_opt_value *newval, + const char *name, + int *target); static const struct bond_opt_value bond_mode_tbl[] = { { "balance-rr", BOND_MODE_ROUNDROBIN, BOND_VALFLAG_DEFAULT}, @@ -428,6 +433,13 @@ static int bond_option_ad_user_port_key_set(struct bonding *bond, .desc = "Number of peer notifications to send on failover event", .values = bond_num_peer_notif_tbl, .set = bond_option_num_peer_notif_set + }, + [BOND_OPT_PEER_NOTIF_DELAY] = { + .id = BOND_OPT_PEER_NOTIF_DELAY, + .name = "peer_notif_delay", + .desc = "Delay between each peer notification on failover event, in milliseconds", + .values = bond_intmax_tbl, + .set = bond_option_peer_notif_delay_set } }; @@ -850,6 +862,9 @@ static int bond_option_miimon_set(struct bonding *bond, if (bond->params.downdelay) netdev_dbg(bond->dev, "Note: Updating downdelay (to %d) since it is a multiple of the miimon value\n", bond->params.downdelay * bond->params.miimon); + if (bond->params.peer_notif_delay) + netdev_dbg(bond->dev, "Note: Updating peer_notif_delay (to %d) since it is a multiple of the miimon value\n", + bond->params.peer_notif_delay * bond->params.miimon); if (newval->value && bond->params.arp_interval) { netdev_dbg(bond->dev, "MII monitoring cannot be used with ARP monitoring - disabling ARP monitoring...\n"); bond->params.arp_interval = 0; @@ -873,52 +888,58 @@ static int bond_option_miimon_set(struct bonding *bond, return 0; } -/* Set up and down delays. These must be multiples of the - * MII monitoring value, and are stored internally as the multiplier. - * Thus, we must translate to MS for the real world. +/* Set up, down and peer notification delays. These must be multiples + * of the MII monitoring value, and are stored internally as the + * multiplier.Thus, we must translate to MS for the real world. */ -static int bond_option_updelay_set(struct bonding *bond, - const struct bond_opt_value *newval) +static int _bond_option_delay_set(struct bonding *bond, + const struct bond_opt_value *newval, + const char *name, + int *target) { int value = newval->value; if (!bond->params.miimon) { - netdev_err(bond->dev, "Unable to set up delay as MII monitoring is disabled\n"); + netdev_err(bond->dev, "Unable to set %s as MII monitoring is disabled\n", + name); return -EPERM; } if ((value % bond->params.miimon) != 0) { - netdev_warn(bond->dev, "up delay (%d) is not a multiple of miimon (%d), updelay rounded to %d ms\n", + netdev_warn(bond->dev, + "%s (%d) is not a multiple of miimon (%d), value rounded to %d ms\n", + name, value, bond->params.miimon, (value / bond->params.miimon) * bond->params.miimon); } - bond->params.updelay = value / bond->params.miimon; - netdev_dbg(bond->dev, "Setting up delay to %d\n", - bond->params.updelay * bond->params.miimon); + *target = value / bond->params.miimon; + netdev_dbg(bond->dev, "Setting %s to %d\n", + name, + *target * bond->params.miimon); return 0; } +static int bond_option_updelay_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + return _bond_option_delay_set(bond, newval, "up delay", + &bond->params.updelay); +} + static int bond_option_downdelay_set(struct bonding *bond, const struct bond_opt_value *newval) { - int value = newval->value; - - if (!bond->params.miimon) { - netdev_err(bond->dev, "Unable to set down delay as MII monitoring is disabled\n"); - return -EPERM; - } - if ((value % bond->params.miimon) != 0) { - netdev_warn(bond->dev, "down delay (%d) is not a multiple of miimon (%d), delay rounded to %d ms\n", - value, bond->params.miimon, - (value / bond->params.miimon) * - bond->params.miimon); - } - bond->params.downdelay = value / bond->params.miimon; - netdev_dbg(bond->dev, "Setting down delay to %d\n", - bond->params.downdelay * bond->params.miimon); + return _bond_option_delay_set(bond, newval, "down delay", + &bond->params.downdelay); +} - return 0; +static int bond_option_peer_notif_delay_set(struct bonding *bond, + const struct bond_opt_value *newval) +{ + return _bond_option_delay_set(bond, newval, + "peer notification delay", + &bond->params.peer_notif_delay); } static int bond_option_use_carrier_set(struct bonding *bond, diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 9f7d83e..850dde4 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -104,7 +104,8 @@ static void bond_info_show_master(struct seq_file *seq) bond->params.updelay * bond->params.miimon); seq_printf(seq, "Down Delay (ms): %d\n", bond->params.downdelay * bond->params.miimon); - + seq_printf(seq, "Peer Notification Delay (ms): %d\n", + bond->params.peer_notif_delay * bond->params.miimon); /* ARP information */ if (bond->params.arp_interval > 0) { diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 3584725..0ecafe1 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -343,6 +343,18 @@ static ssize_t bonding_show_updelay(struct device *d, static DEVICE_ATTR(updelay, 0644, bonding_show_updelay, bonding_sysfs_store_option); +static ssize_t bonding_show_peer_notif_delay(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", + bond->params.peer_notif_delay * bond->params.miimon); +} +static DEVICE_ATTR(peer_notif_delay, 0644, + bonding_show_peer_notif_delay, bonding_sysfs_store_option); + /* Show the LACP interval. */ static ssize_t bonding_show_lacp(struct device *d, struct device_attribute *attr, @@ -734,6 +746,7 @@ static DEVICE_ATTR(ad_user_port_key, 0644, &dev_attr_arp_ip_target.attr, &dev_attr_downdelay.attr, &dev_attr_updelay.attr, + &dev_attr_peer_notif_delay.attr, &dev_attr_lacp_rate.attr, &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, diff --git a/include/net/bond_options.h b/include/net/bond_options.h index d79d28f..6889a04 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -67,6 +67,7 @@ enum { BOND_OPT_AD_ACTOR_SYSTEM, BOND_OPT_AD_USER_PORT_KEY, BOND_OPT_NUM_PEER_NOTIF_ALIAS, + BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 81166488..c241010 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -114,6 +114,7 @@ struct bond_params { int fail_over_mac; int updelay; int downdelay; + int peer_notif_delay; int lacp_fast; unsigned int min_links; int ad_select; @@ -205,7 +206,7 @@ struct bonding { */ spinlock_t mode_lock; spinlock_t stats_lock; - u8 send_peer_notif; + u64 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9d8eac5..f9a0359 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -615,6 +615,7 @@ enum { IFLA_BOND_AD_USER_PORT_KEY, IFLA_BOND_AD_ACTOR_SYSTEM, IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, __IFLA_BOND_MAX, }; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 43391e2..f57af58 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -614,6 +614,7 @@ enum { IFLA_BOND_AD_USER_PORT_KEY, IFLA_BOND_AD_ACTOR_SYSTEM, IFLA_BOND_TLB_DYNAMIC_LB, + IFLA_BOND_PEER_NOTIF_DELAY, __IFLA_BOND_MAX, }; -- 1.8.3.1

1 0

[PATCH 1/6] share_pool: Add sp_area cache
by Yang Yingliang 02 Dec '20

02 Dec '20

From: Tang Yizhou <tangyizhou(a)huawei.com> ascend inclusion category: feature bugzilla: NA CVE: NA ------------------------------------------------- Provide a free area cache for the share pool VA allocator, based on the algorithm used by linux mainline commit 89699605fe7c. This reduces the number of rbtree operations and linear traversals over the share pool extents in order to find a free area, by starting off at the last point that a free area was found. The free area cache is reset if areas are freed behind it, or if we are searching for an another area (such as DVPP 16G area) than last time. So allocation patterns are not changed. After this patch, the search will start from where it left off, giving closer to an amortized O(1). Test environment: Huawei 1951 DC (8 CPU cores) with 21G memory, no load. Test method: A single thread process first call sp_alloc() to allocate a specified number of 2M hugepages, then we calculate the allocation time when sp_alloc() another 2M hugepage. The results are in microsecond. test 1, first sp_alloc() 256 2M-hugepage, total 512M test 2, first sp_alloc() 512 2M-hugepage, total 1G test 3, first sp_alloc() 1024 2M-hugepage, total 2G test 4, first sp_alloc() 1536 2M-hugepage, total 3G test 5, first sp_alloc() 2048 2M-hugepage, total 4G test 6, first sp_alloc() 4096 2M-hugepage, total 8G test 7, first sp_alloc() 6072 2M-hugepage, total 12G test 8, first sp_alloc() 8192 2M-hugepage, total 16G test1 test2 test3 test4 231 238 240 252 279 253 315 268 242 238 247 253 282 255 326 265 233 234 250 243 272 251 314 258 239 224 245 246 273 261 324 262 234 233 252 257 277 262 326 265 225 231 243 243 279 249 325 264 236 261 246 248 265 262 323 266 233 238 247 246 281 259 331 265 239 222 243 241 270 248 325 263 241 231 239 241 335 246 321 268 avg: 235.3 235 245.2 247 281.3 254.6 323 264.4 res: - - 9.49% 18.14% test5 test6 test7 test8 371 280 720 458 1001 629 1547 909 369 283 691 465 1005 718 1533 903 374 279 954 470 1003 680 1371 908 363 279 697 457 1004 923 1375 930 369 286 711 464 1016 683 1395 1083 382 280 967 491 1029 695 1413 1096 378 284 688 823 1008 689 1419 905 376 360 921 469 1285 696 1554 1085 374 287 896 485 1030 682 1381 902 380 276 706 545 1286 717 1606 1097 avg: 373.6 289.4 791.5 512.7 1066.7 717.5 1459.4 981.8 res: 22.54% 35.52% 32.74% 32.73% Suggested-by: Zefan Li <lizefan(a)huawei.com> Signed-off-by: Tang Yizhou <tangyizhou(a)huawei.com> Reviewed-by: Ding Tianhong <dingtianhong(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- mm/share_pool.c | 104 ++++++++++++++++++++++++++++++++++-------------- 1 file changed, 75 insertions(+), 29 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 24c5dd680451..b9d30d36b7c2 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -730,6 +730,11 @@ static void __insert_sp_area(struct sp_area *spa) rb_insert_color(&spa->rb_node, &sp_area_root); } +/* The sp_area cache globals are protected by sp_area_lock */ +static struct rb_node *free_sp_area_cache; +static unsigned long cached_hole_size; +static unsigned long cached_vstart; /* affected by SP_DVPP and sp_config_dvpp_range() */ + /* * Allocate a region of VA from the share pool. * @size - the size of VA to allocate @@ -741,7 +746,7 @@ static void __insert_sp_area(struct sp_area *spa) static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, struct sp_group *spg, enum spa_type type) { - struct sp_area *spa, *err; + struct sp_area *spa, *first, *err; struct rb_node *n; unsigned long vstart = MMAP_SHARE_POOL_START; unsigned long vend = MMAP_SHARE_POOL_16G_START; @@ -763,8 +768,6 @@ static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, } } - addr = vstart; - spa = kmalloc(sizeof(struct sp_area), GFP_KERNEL); if (unlikely(!spa)) { if (printk_ratelimit()) @@ -774,45 +777,75 @@ static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, spin_lock(&sp_area_lock); - n = sp_area_root.rb_node; - if (n) { - struct sp_area *first = NULL; + /* + * Invalidate cache if we have more permissive parameters. + * cached_hole_size notes the largest hole noticed _below_ + * the sp_area cached in free_sp_area_cache: if size fits + * into that hole, we want to scan from vstart to reuse + * the hole instead of allocating above free_sp_area_cache. + * Note that sp_free_area may update free_sp_area_cache + * without updating cached_hole_size. + */ + if (!free_sp_area_cache || size_align < cached_hole_size || + vstart != cached_vstart) { + cached_hole_size = 0; + free_sp_area_cache = NULL; + } + + /* record if we encounter less permissive parameters */ + cached_vstart = vstart; + + /* find starting point for our search */ + if (free_sp_area_cache) { + first = rb_entry(free_sp_area_cache, struct sp_area, rb_node); + addr = first->va_end; + if (addr + size_align < addr) { + err = ERR_PTR(-EOVERFLOW); + goto error; + } + } else { + addr = vstart; + if (addr + size_align < addr) { + err = ERR_PTR(-EOVERFLOW); + goto error; + } + + n = sp_area_root.rb_node; + first = NULL; - do { + while (n) { struct sp_area *tmp; tmp = rb_entry(n, struct sp_area, rb_node); if (tmp->va_end >= addr) { - if (!first && tmp->va_start < addr + size_align) - first = tmp; - n = n->rb_left; - } else { first = tmp; + if (tmp->va_start <= addr) + break; + n = n->rb_left; + } else n = n->rb_right; - } - } while (n); + } if (!first) goto found; + } - if (first->va_end < addr) { - n = rb_next(&first->rb_node); - if (n) - first = rb_entry(n, struct sp_area, rb_node); - else - goto found; + /* from the starting point, traverse areas until a suitable hole is found */ + while (addr + size_align > first->va_start && addr + size_align <= vend) { + if (addr + cached_hole_size < first->va_start) + cached_hole_size = first->va_start - addr; + addr = first->va_end; + if (addr + size_align < addr) { + err = ERR_PTR(-EOVERFLOW); + goto error; } - while (addr + size_align >= first->va_start && - addr + size_align <= vend) { - addr = first->va_end; - - n = rb_next(&first->rb_node); - if (n) - first = rb_entry(n, struct sp_area, rb_node); - else - goto found; - } + n = rb_next(&first->rb_node); + if (n) + first = rb_entry(n, struct sp_area, rb_node); + else + goto found; } + found: if (addr + size_align > vend) { err = ERR_PTR(-EOVERFLOW); @@ -833,6 +866,7 @@ static struct sp_area *sp_alloc_area(unsigned long size, unsigned long flags, } __insert_sp_area(spa); + free_sp_area_cache = &spa->rb_node; if (spa->spg) { atomic_inc(&spg->spa_num); atomic64_add(size, &spg->size); @@ -889,6 +923,18 @@ static void sp_free_area(struct sp_area *spa) { lockdep_assert_held(&sp_area_lock); + if (free_sp_area_cache) { + struct sp_area *cache; + cache = rb_entry(free_sp_area_cache, struct sp_area, rb_node); + if (spa->va_start <= cache->va_start) { + free_sp_area_cache = rb_prev(&spa->rb_node); + /* + * We don't try to update cached_hole_size, + * but it won't go very wrong. + */ + } + } + spa_dec_usage(spa->type, spa->real_size); /* won't fail */ if (spa->spg) { atomic_dec(&spa->spg->spa_num); -- 2.25.1

1 5

[PATCH 1/2] nvme: fix nvme_stop_queues cost long time error
by Yang Yingliang 02 Dec '20

02 Dec '20

From: Di Wang <wangdi44(a)huawei.com> driver inclusion category: bugfix bugzilla: NA Link: https://gitee.com/openeuler/kernel/issues/I1WGZE -------------------------------- It will cost a lot of time when synchronize_rcu() is called for every namspace in nvme_stop_queues(). Reviewed-by: Chao Leng <lengchao(a)huawei.com> Reviewed-by: Jike Cheng <chengjike.cheng(a)huawei.com> Signed-off-by: Di Wang <wangdi44(a)huawei.com> Signed-off-by: Lijie <lijie34(a)huawei.com> Acked-by: Hanjun Guo <guohanjun(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-mq.c | 18 ++++++++++++++++++ drivers/nvme/host/core.c | 6 +++++- include/linux/blk-mq.h | 1 + 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 7096f23b18da..41e92dbff821 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -242,6 +242,24 @@ void blk_mq_quiesce_queue(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); +bool blk_mq_quiesce_queue_without_rcu(struct request_queue *q) +{ + struct blk_mq_hw_ctx *hctx; + unsigned int i; + bool rcu = false; + + blk_mq_quiesce_queue_nowait(q); + + queue_for_each_hw_ctx(q, hctx, i) { + if (hctx->flags & BLK_MQ_F_BLOCKING) + synchronize_srcu(hctx->srcu); + else + rcu = true; + } + return rcu; +} +EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_without_rcu); + /* * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue() * @q: request queue. diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 8443c6c5c5af..c9faa824de26 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3904,11 +3904,15 @@ EXPORT_SYMBOL_GPL(nvme_start_freeze); void nvme_stop_queues(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; + bool rcu = false; down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) - blk_mq_quiesce_queue(ns->queue); + rcu = (blk_mq_quiesce_queue_without_rcu(ns->queue) || rcu); up_read(&ctrl->namespaces_rwsem); + + if (rcu) + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nvme_stop_queues); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d26edab21d5c..730de600075b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -309,6 +309,7 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); +bool blk_mq_quiesce_queue_without_rcu(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); -- 2.25.1

1 1

Re: [Release] openEuler 20.03 LTS SP1 内核版本咨询
by Xie XiuQi 02 Dec '20

02 Dec '20

Hi 亚芬， On 2020/12/1 16:47, 方亚芬 wrote: > 内核组的老师们，大家好。我是 openEuler 社区树莓派 SIG 组的 maintainer 方亚芬。 > > > 针对即将发布的 openEuler 20.03 LTS SP1，有个问题想咨询一下。 > > 当前 openEuler 4.19 内核源码最新版本为 4.19.90-2011.6.0（https://gitee.com/openeuler/kernel/tree/4.19.90-2011.6.0/）… src-openeuler/kernel（https://gitee.com/src-openeuler/kernel）下三个分支更新版本不同，分别为： > 1. openEuler 20.03 LTS Next：4.19.90-2010.2.0 > 2. openEuler 20.03 LTS SP1：4.19.90-2011.4.0 > 3. openEuler 20.03 LTS：4.19.90-2011.6.0 > > > 针对该情况有以下两个问题： > 1. 之前树莓派镜像的内核版本一直根据 src-openeuler/kernel 下内核版本做更新，即将发布的 openEuler 20.03 LTS SP1 > 树莓派镜像采用内核版本要与 src-openeuler/kernel 的 openEuler 20.03 LTS SP1 分支内核版本一致？还是需要采用 openEuler 4.19 内核源码的最新版本（https://gitee.com/openeuler/kernel/tree/openEuler-1.0-LTS/，当前为 4.19.90-2011.6.0）？ 20.03 LTS SP1 和 20.03 LTS 的kernel同源，使用相同的内核分支，4.19.90-2011.4.0 和 4.19.90-2011.6.0 只是合入节奏的问题，实际上是同一个分支。对应的源码分支都是 openEuler-1.0-LTS. > > 2. openEuler 20.03 LTS SP1 正式发布前，内核会一直不定期更新，还是会有个具体的截止时间停止更新呢？ > SP1 包括之前的 20.03 LTS 都会陆续有少量的 cve 或 bugfix 补丁，SP1 正式发布之后，也会有陆续的更新，会持续到 SP1、SP0 生命周期结束。我理解你的诉求，你关心树莓派的内核 rebase 到openEuler具体哪个版本。我觉得这个影响应该不大，近期到 SP1 release，合入的补丁应该会很少。这个 SP1 的 release 计划， https://gitee.com/openeuler/release-management/blob/master/openEuler-20.03-… > ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ > 祝工作顺利，生活愉快。 > > ------------------------------------------ > 方亚芬 > 中国科学院软件研究所智能软件研究中心 > 邮箱：yafen(a)iscas.ac.cn <mailto:jiran@iscas.ac.cn> > 地址：北京市海淀区中关村南四街4号5楼 > > _______________________________________________ > Release mailing list -- release(a)openeuler.org > To unsubscribe send an email to release-leave(a)openeuler.org >

2 1

openEuler Summit 社区内报名通道开启，欢迎报名，诚挚的欢迎您为 openEuler 代言
by public＠openeuler.io 30 Nov '20

30 Nov '20

亲爱的 openEuler 社区开发者： openEuler Summit 是由 openEuler 社区举办的开发者交流会，首届线下 openEuler Summit 2020 将于 12 月 24-25 日在北京・望京凯悦酒店举办。openEuler 是一个面向未来的开源操作系统，依托于最具活力的 openEuler 社区，它的未来将不止于操作系统！ openEuler Summit 2020 将聚焦于软硬件协同、云边端协同的技术趋势，万物互联的多算力场景，挖掘技术创新与社区生态的价值。开发者、用户、社区贡献者、软件爱好者在 openEuler Summit 上汇聚成海，连接行业上下游，让全产业链共享操作系统创新价值。目前各大 Session 议题已经评审完毕，今日将会上线部分议程，大会报名通道开启，TC、Maintainer、SIG 工作组会议也在有条不紊地推进中。我们也将持续向大家同步会议进程，以便于社区成员了解 openEuler Summit 最新进展。 openEuler Summit 社区内开发者报名专属通道：https://etherpad.openeuler.org/p/openEuler-Summit-2020 在 openEuler 一周年之际，大会准备了一个 100个社区开发者为openEuler 代言的视频，诚挚地邀请您按照下方的要求拍摄一段视频，将 openEuler 操作系统推荐给更多的人。拍摄需求：自拍形式，对着镜头回答以下问题： 1. 我想要的操作系统是****的， 2. 我在**时候参与/认识/加入/知道的openEuler（社区） 3. 我在openEuler贡献了**** 4. 我是***，我为openEuler代言使用场景：您拍摄的视频素材将用于 openEuler Summit 2020 前期的会议宣传和开场视频中。拍摄指导： 1. 背景任您喜欢 2. 人物面对镜头，取半身构图，横向拍摄16:9 的画面比例 3. 最好选择白炽灯，白色光源 4. 尽量由另一个人辅助，用手机后置摄像头拍摄，不要用前置，拍摄前擦拭摄像头 5. 读口播时，声音越大越好 6. 尽量保证每一句话都是完整通顺的，中间重来的部分可以忽略 7. 视频输出，用电脑将手机视频导出，打压缩包传输即可（不要用微信上传，会压缩画质） 8. 拍摄完毕后请将视频上传到百度网盘，将分享链接期限设置为永久，然后发给 public(a)openeuler.io 9. 样片在附件，请您参考

1 0

[PATCH 1/3] Revert "refcount_t: Add ACQUIRE ordering on success for dec(sub)_and_test() variants"
by Yang Yingliang 28 Nov '20

28 Nov '20

hulk inclusion category: bugfix bugzilla: NA CVE: NA ---------------------------------------- This reverts commit 99294378e022ec2785f88247a7373767fd090e3a. 288e4521f0f6 ("x86/asm: 'Simplify' GEN_*_RMWcc() macros") need be apply before this commit to avoid compile error. Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- Documentation/core-api/refcount-vs-atomic.rst | 24 +++---------------- arch/x86/include/asm/refcount.h | 18 ++------------ lib/refcount.c | 18 ++++---------- 3 files changed, 10 insertions(+), 50 deletions(-) diff --git a/Documentation/core-api/refcount-vs-atomic.rst b/Documentation/core-api/refcount-vs-atomic.rst index 976e85adffe8..322851bada16 100644 --- a/Documentation/core-api/refcount-vs-atomic.rst +++ b/Documentation/core-api/refcount-vs-atomic.rst @@ -54,13 +54,6 @@ must propagate to all other CPUs before the release operation (A-cumulative property). This is implemented using :c:func:`smp_store_release`. -An ACQUIRE memory ordering guarantees that all post loads and -stores (all po-later instructions) on the same CPU are -completed after the acquire operation. It also guarantees that all -po-later stores on the same CPU must propagate to all other CPUs -after the acquire operation executes. This is implemented using -:c:func:`smp_acquire__after_ctrl_dep`. - A control dependency (on success) for refcounters guarantees that if a reference for an object was successfully obtained (reference counter increment or addition happened, function returned true), @@ -126,24 +119,13 @@ Memory ordering guarantees changes: result of obtaining pointer to the object! -case 5) - generic dec/sub decrement-based RMW ops that return a value ---------------------------------------------------------------------- +case 5) - decrement-based RMW ops that return a value +----------------------------------------------------- Function changes: * :c:func:`atomic_dec_and_test` --> :c:func:`refcount_dec_and_test` * :c:func:`atomic_sub_and_test` --> :c:func:`refcount_sub_and_test` - -Memory ordering guarantees changes: - - * fully ordered --> RELEASE ordering + ACQUIRE ordering on success - - -case 6) other decrement-based RMW ops that return a value ---------------------------------------------------------- - -Function changes: - * no atomic counterpart --> :c:func:`refcount_dec_if_one` * ``atomic_add_unless(&var, -1, 1)`` --> ``refcount_dec_not_one(&var)`` @@ -154,7 +136,7 @@ Memory ordering guarantees changes: .. note:: :c:func:`atomic_add_unless` only provides full order on success. -case 7) - lock-based RMW +case 6) - lock-based RMW ------------------------ Function changes: diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 88061df7add6..19b90521954c 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -67,28 +67,14 @@ static __always_inline void refcount_dec(refcount_t *r) static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { - bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, + GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, r->refs.counter, "er", i, "%0", e, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { - bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, + GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, r->refs.counter, "%0", e, "cx"); - - if (ret) { - smp_acquire__after_ctrl_dep(); - return true; - } - - return false; } static __always_inline __must_check diff --git a/lib/refcount.c b/lib/refcount.c index 6e904af0fb3e..ebcf8cd49e05 100644 --- a/lib/refcount.c +++ b/lib/refcount.c @@ -33,9 +33,6 @@ * Note that the allocator is responsible for ordering things between free() * and alloc(). * - * The decrements dec_and_test() and sub_and_test() also provide acquire - * ordering on success. - * */ #include <linux/mutex.h> @@ -167,8 +164,8 @@ EXPORT_SYMBOL(refcount_inc_checked); * at UINT_MAX. * * Provides release memory ordering, such that prior loads and stores are done - * before, and provides an acquire ordering on success such that free() - * must come after. + * before, and provides a control dependency such that free() must come after. + * See the comment on top. * * Use of this function is not recommended for the normal reference counting * use case in which references are taken and released one at a time. In these @@ -193,12 +190,7 @@ bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r) } while (!atomic_try_cmpxchg_release(&r->refs, &val, new)); - if (!new) { - smp_acquire__after_ctrl_dep(); - return true; - } - return false; - + return !new; } EXPORT_SYMBOL(refcount_sub_and_test_checked); @@ -210,8 +202,8 @@ EXPORT_SYMBOL(refcount_sub_and_test_checked); * decrement when saturated at UINT_MAX. * * Provides release memory ordering, such that prior loads and stores are done - * before, and provides an acquire ordering on success such that free() - * must come after. + * before, and provides a control dependency such that free() must come after. + * See the comment on top. * * Return: true if the resulting refcount is 0, false otherwise */ -- 2.25.1

1 2

[PATCH 01/11] mm: move nr_deactivate accounting to shrink_active_list()
by Yang Yingliang 28 Nov '20

28 Nov '20

From: Kirill Tkhai <ktkhai(a)virtuozzo.com> mainline inclusion from mainline-v5.2-rc1 commit 9851ac13592df77958ae7bac6ba39e71420c38ec category: bugfix bugzilla: 36232 CVE: NA ------------------------------------------------- We know which LRU is not active. [chris(a)chrisdown.name: fix build on !CONFIG_MEMCG] Link: http://lkml.kernel.org/r/20190322150513.GA22021@chrisdown.name Link: http://lkml.kernel.org/r/155290128498.31489.18250485448913338607.stgit@loca… Signed-off-by: Kirill Tkhai <ktkhai(a)virtuozzo.com> Signed-off-by: Chris Down <chris(a)chrisdown.name> Reviewed-by: Daniel Jordan <daniel.m.jordan(a)oracle.com> Cc: Michal Hocko <mhocko(a)kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- include/linux/memcontrol.h | 6 ++++++ mm/vmscan.c | 10 ++++------ 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f6f51b14a332..029b4848ab6f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1109,6 +1109,12 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, { } +static inline void __count_memcg_events(struct mem_cgroup *memcg, + enum vm_event_item idx, + unsigned long count) +{ +} + static inline void count_memcg_page_event(struct page *page, int idx) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 38fcda38bf7b..92f2489efda8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2077,12 +2077,6 @@ static unsigned move_active_pages_to_lru(struct lruvec *lruvec, } } - if (!is_active_lru(lru)) { - __count_vm_events(PGDEACTIVATE, nr_moved); - count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, - nr_moved); - } - return nr_moved; } @@ -2178,6 +2172,10 @@ static void shrink_active_list(unsigned long nr_to_scan, nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru); nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE); + + __count_vm_events(PGDEACTIVATE, nr_deactivate); + __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate); + __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); spin_unlock_irq(&pgdat->lru_lock); -- 2.25.1

1 10

[PATCH 01/13] bpf: remove duplicated include from syscall.c
by Yang Yingliang 28 Nov '20

28 Nov '20

From: YueHaibing <yuehaibing(a)huawei.com> mainline inclusion from mainline-v4.20-rc1 commit efbaec89c642cd1d4977fc6df9923697e1598d4e category: other bugzilla: 43460 CVE: NA --------------------------------------- Remove duplicated include. Signed-off-by: YueHaibing <yuehaibing(a)huawei.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Signed-off-by: liuxin <liuxin264(a)huawei.com> Reviewed-by: Cheng Jian <cj.chengjian(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- kernel/bpf/syscall.c | 1 - 1 file changed, 1 deletion(-) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb473159a55c..3e9ff9897c7c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -30,7 +30,6 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> -#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ -- 2.25.1

1 12

[PATCH 00/91] backport stable-4.19.160
by Yang Yingliang 28 Nov '20

28 Nov '20

Aaron Lewis (1): selftests: kvm: Fix the segment descriptor layout to match the actual layout Alejandro Concepcion Rodriguez (1): can: dev: can_restart(): post buffer from the right context Anant Thazhemadam (2): can: af_can: prevent potential access of uninitialized member in can_rcv() can: af_can: prevent potential access of uninitialized member in canfd_rcv() Arvind Sankar (1): efi/x86: Free efi_pgd with free_pages() Aya Levin (1): net/mlx4_core: Fix init_hca fields offset Brian O'Keefe (1): staging: rtl8723bs: Add 024c:0627 to the list of SDIO device-ids Can Guo (1): scsi: ufs: Fix unbalanced scsi_block_reqs_cnt caused by ufshcd_hold() Chen Yu (1): x86/microcode/intel: Check patch signature before saving microcode for early loading Chen-Yu Tsai (4): Revert "arm: sun8i: orangepi-pc-plus: Set EMAC activity LEDs to active high" ARM: dts: sun8i: h3: orangepi-plus2e: Enable RGMII RX/TX delay on Ethernet PHY ARM: dts: sun8i: a83t: Enable both RGMII RX/TX delay on Ethernet PHY arm64: dts: allwinner: a64: bananapi-m64: Enable RGMII RX/TX delay on PHY Colin Ian King (1): can: peak_usb: fix potential integer overflow on shift of a int Dan Carpenter (2): Input: adxl34x - clean up a data type in adxl34x_probe() ALSA: firewire: Clean up a locking issue in copy_resp_to_buf() Darrick J. Wong (4): vfs: remove lockdep bogosity in __sb_start_write xfs: fix the minrecs logic when dealing with inode root child blocks xfs: strengthen rmap record flags checking xfs: revert "xfs: fix rmap key and record comparison functions" Dongli Zhang (1): page_frag: Recover from memory pressure Edwin Peer (1): bnxt_en: read EEPROM A2h address using page 0 Fabio Estevam (1): ARM: dts: imx50-evk: Fix the chip select 1 IOMUX Felix Fietkau (2): mac80211: minstrel: remove deferred sampling code mac80211: minstrel: fix tx status processing corner case Filip Moc (1): net: usb: qmi_wwan: Set DTR quirk for MR400 Florian Fainelli (1): net: Have netpoll bring-up DSA management interface Fugang Duan (1): tty: serial: imx: keep console clocks always on Gerald Schaefer (1): mm/userfaultfd: do not access vma->vm_mm after calling handle_userfault() Greg Kroah-Hartman (1): Linux 4.19.160 Hans de Goede (3): ACPI: button: Add DMI quirk for Medion Akoya E2228T iio: accel: kxcjk1013: Replace is_smo8500_device with an acpi_type enum iio: accel: kxcjk1013: Add support for KIOX010A ACPI DSM for setting tablet-mode Heiner Kallweit (1): net: bridge: add missing counters to ndo_get_stats64 callback Ido Schimmel (1): mlxsw: core: Use variable timeout for EMAD retries Jan Kara (1): ext4: fix bogus warning in ext4_update_dx_flag() Jernej Skrabec (3): arm64: dts: allwinner: a64: Pine64 Plus: Fix ethernet node arm64: dts: allwinner: h5: OrangePi PC2: Fix ethernet node ARM: dts: sun8i: r40: bananapi-m2-ultra: Fix ethernet node Jianqun Xu (1): pinctrl: rockchip: enable gpio pclk for rockchip_gpio_to_irq Jimmy Assarsson (1): can: kvaser_usb: kvaser_usb_hydra: Fix KCAN bittiming limits Joakim Tjernlund (1): ALSA: usb-audio: Add delay quirk for all Logitech USB devices Joel Stanley (2): net/ncsi: Fix netlink registration net: ftgmac100: Fix crash when removing driver Johannes Berg (1): mac80211: free sta in sta_info_insert_finish() on errors Leo Yan (1): perf lock: Don't free "lock_seq_stat" if read_count isn't zero Luo Meng (1): fail_function: Remove a redundant mutex unlock Marc Kleine-Budde (1): can: mcba_usb: mcba_usb_start_xmit(): first fill skb, then pass to can_put_echo_skb() Max Filippov (1): xtensa: disable preemption around cache alias management calls Michał Mirosław (3): regulator: fix memory leak with repeated set_machine_constraints() regulator: avoid resolve_supply() infinite recursion regulator: workaround self-referent regulators Mickaël Salaün (2): ptrace: Set PF_SUPERPRIV when checking capability seccomp: Set PF_SUPERPRIV when checking capability Necip Fazil Yildiran (1): Input: resistive-adc-touch - fix kconfig dependency on IIO_BUFFER Nenad Peric (1): arm64: dts: allwinner: h5: OrangePi Prime: Fix ethernet node Nishanth Menon (1): regulator: ti-abb: Fix array out of bound read access on the first transition Paul Moore (2): netlabel: fix our progress tracking in netlbl_unlabel_staticlist() netlabel: fix an uninitialized warning in netlbl_unlabel_staticlist() PeiSen Hou (1): ALSA: hda/realtek: Add some Clove SSID in the ALC293(ALC1220) Randy Dunlap (1): MIPS: export has_transparent_hugepage() for modules Ryan Sharpelletti (1): tcp: only postpone PROBE_RTT if RTT is < current min_rtt estimate Sean Nyekjaer (1): regulator: pfuze100: limit pfuze-support-disable-sw to pfuze{100,200} Sebastian Andrzej Siewior (1): atm: nicstar: Unmap DMA on send error Sergey Matyukevich (1): arm: dts: imx6qdl-udoo: fix rgmii phy-mode for ksz9031 phy Srinivasa Rao Mandadapu (1): ASoC: qcom: lpass-platform: Fix memory leak Stefan Haberland (1): s390/dasd: fix null pointer dereference for ERP requests Subash Abhinov Kasiviswanathan (1): net: qualcomm: rmnet: Fix incorrect receive packet handling during cleanup Sven Van Asbroeck (2): lan743x: fix issue causing intermittent kernel log warnings lan743x: prevent entire kernel HANG on open, for some platforms Takashi Iwai (1): ALSA: mixart: Fix mutex deadlock Takashi Sakamoto (1): ALSA: ctl: fix error path at adding user-defined element set Thomas Richter (1): s390/cpum_sf.c: fix file permission for cpum_sfb_size Tobias Waldekranz (1): net: dsa: mv88e6xxx: Avoid VTU corruption on 6097 Vamshi K Sthambamkadi (1): efivarfs: fix memory leak in efivarfs_create() Vladyslav Tarasiuk (1): net/mlx5: Disable QoS when min_rates on all VFs are zero Wang Hai (2): devlink: Add missing genlmsg_cancel() in devlink_nl_sb_port_pool_fill() inet_diag: Fix error path to cancel the meseage in inet_req_diag_fill() Will Deacon (1): arm64: psci: Avoid printing in cpu_psci_cpu_die() Wu Bo (1): can: m_can: m_can_handle_state_change(): fix state change Xie He (1): net: x25: Increase refcnt of "struct x25_neigh" in x25_rx_call_request Xin Long (1): sctp: change to hold/put transport for proto_unreach_timer Xiongfeng Wang (1): drm/sun4i: dw-hdmi: fix error return code in sun8i_dw_hdmi_bind() Yi-Hung Wei (1): ip_tunnels: Set tunnel option flag when tunnel metadata is present Yicong Yang (1): libfs: fix error cast of negative value in simple_attr_write() Zhang Changzhong (4): ah6: fix error return code in ah6_input() net: b44: fix error return code in b44_init_one() qed: fix error return code in qed_iwarp_ll2_start() qlcnic: fix error return code in qlcnic_83xx_restart_hw() Zhang Qilong (2): can: ti_hecc: Fix memleak in ti_hecc_probe MIPS: Alchemy: Fix memleak in alchemy_clk_setup_cpu Makefile | 2 +- arch/arm/boot/dts/imx50-evk.dts | 2 +- arch/arm/boot/dts/imx6qdl-udoo.dtsi | 2 +- arch/arm/boot/dts/sun8i-a83t-bananapi-m3.dts | 2 +- .../boot/dts/sun8i-a83t-cubietruck-plus.dts | 2 +- .../boot/dts/sun8i-h3-orangepi-pc-plus.dts | 5 -- .../arm/boot/dts/sun8i-h3-orangepi-plus2e.dts | 2 +- .../boot/dts/sun8i-r40-bananapi-m2-ultra.dts | 2 +- .../dts/allwinner/sun50i-a64-bananapi-m64.dts | 2 +- .../dts/allwinner/sun50i-a64-pine64-plus.dts | 2 +- .../dts/allwinner/sun50i-h5-orangepi-pc2.dts | 2 +- .../allwinner/sun50i-h5-orangepi-prime.dts | 2 +- arch/arm64/kernel/psci.c | 5 +- arch/mips/alchemy/common/clock.c | 9 ++- arch/mips/mm/tlb-r4k.c | 1 + arch/s390/kernel/perf_cpum_sf.c | 2 +- arch/x86/kernel/cpu/microcode/intel.c | 63 +++---------------- arch/x86/platform/efi/efi_64.c | 24 +++---- arch/xtensa/mm/cache.c | 14 +++++ drivers/acpi/button.c | 13 +++- drivers/atm/nicstar.c | 2 + drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 1 + drivers/iio/accel/kxcjk-1013.c | 51 +++++++++++++-- drivers/input/misc/adxl34x.c | 2 +- drivers/input/touchscreen/Kconfig | 1 + drivers/net/can/dev.c | 2 +- drivers/net/can/m_can/m_can.c | 4 +- drivers/net/can/ti_hecc.c | 13 ++-- .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 +- drivers/net/can/usb/mcba_usb.c | 4 +- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 4 +- drivers/net/dsa/mv88e6xxx/global1_vtu.c | 59 ++++++++++++++--- drivers/net/ethernet/broadcom/b44.c | 3 +- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 2 +- drivers/net/ethernet/faraday/ftgmac100.c | 4 ++ drivers/net/ethernet/mellanox/mlx4/fw.c | 6 +- drivers/net/ethernet/mellanox/mlx4/fw.h | 4 +- .../net/ethernet/mellanox/mlx5/core/eswitch.c | 15 ++--- drivers/net/ethernet/mellanox/mlxsw/core.c | 3 +- drivers/net/ethernet/microchip/lan743x_main.c | 13 ++-- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 12 +++- .../ethernet/qlogic/qlcnic/qlcnic_83xx_init.c | 3 +- .../ethernet/qualcomm/rmnet/rmnet_handlers.c | 5 ++ drivers/net/geneve.c | 3 +- drivers/net/usb/qmi_wwan.c | 2 +- drivers/pinctrl/pinctrl-rockchip.c | 2 + drivers/regulator/core.c | 38 ++++++----- drivers/regulator/pfuze100-regulator.c | 13 ++-- drivers/regulator/ti-abb-regulator.c | 12 +++- drivers/s390/block/dasd.c | 6 ++ drivers/scsi/ufs/ufshcd.c | 6 +- drivers/staging/rtl8723bs/os_dep/sdio_intf.c | 1 + drivers/tty/serial/imx.c | 20 +----- fs/efivarfs/super.c | 1 + fs/ext4/ext4.h | 3 +- fs/libfs.c | 6 +- fs/super.c | 33 ++-------- fs/xfs/libxfs/xfs_rmap_btree.c | 16 ++--- fs/xfs/scrub/bmap.c | 8 +-- fs/xfs/scrub/btree.c | 45 +++++++------ include/net/ip_tunnels.h | 7 ++- kernel/fail_function.c | 5 +- kernel/ptrace.c | 16 ++--- kernel/seccomp.c | 5 +- mm/huge_memory.c | 9 ++- mm/page_alloc.c | 5 ++ net/bridge/br_device.c | 1 + net/can/af_can.c | 38 ++++++++--- net/core/devlink.c | 6 +- net/core/netpoll.c | 22 +++++-- net/ipv4/inet_diag.c | 4 +- net/ipv4/tcp_bbr.c | 2 +- net/ipv6/ah6.c | 3 +- net/mac80211/rc80211_minstrel.c | 27 ++------ net/mac80211/rc80211_minstrel.h | 1 - net/mac80211/sta_info.c | 14 ++--- net/ncsi/ncsi-manage.c | 5 -- net/ncsi/ncsi-netlink.c | 22 +------ net/ncsi/ncsi-netlink.h | 3 - net/netlabel/netlabel_unlabeled.c | 17 +++-- net/sctp/input.c | 4 +- net/sctp/sm_sideeffect.c | 4 +- net/sctp/transport.c | 2 +- net/x25/af_x25.c | 1 + sound/core/control.c | 2 +- .../fireworks/fireworks_transaction.c | 4 +- sound/pci/hda/patch_realtek.c | 50 ++++++++++++++- sound/pci/mixart/mixart_core.c | 5 +- sound/soc/qcom/lpass-platform.c | 5 +- sound/usb/quirks.c | 10 +-- tools/perf/builtin-lock.c | 2 +- tools/testing/selftests/kvm/include/x86.h | 2 +- tools/testing/selftests/kvm/lib/x86.c | 3 +- 93 files changed, 517 insertions(+), 377 deletions(-) -- 2.25.1

1 91

[PATCH 01/14] blk-cgroup: prevent rcu_sched detected stalls warnings in blkg_destroy_all()
by Yang Yingliang 28 Nov '20

28 Nov '20

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: 46357 CVE: NA --------------------------- test procedures: a. create 20000 cgroups, and echo "8:0 10000" to blkio.throttle.write_bps_device b. echo 1 > /sys/blocd/sda/device/delete test result: rcu: INFO: rcu_sched detected stalls on CPUs/tasks: [5/1143] rcu: 0-...0: (0 ticks this GP) idle=0f2/1/0x4000000000000000 softirq=15507/15507 fq rcu: (detected by 6, t=60012 jiffies, g=119977, q=27153) NMI backtrace for cpu 0 CPU: 0 PID: 443 Comm: bash Not tainted 4.19.95-00061-g0bcc83b30eec #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-p4 RIP: 0010:blk_throtl_update_limit_valid.isra.0+0x116/0x2a0 Code: 01 00 00 e8 7c dd 74 ff 48 83 bb 78 01 00 00 00 0f 85 54 01 00 00 48 8d bb 88 01 1 RSP: 0018:ffff8881030bf9f0 EFLAGS: 00000046 RAX: 0000000000000000 RBX: ffff8880b4f37080 RCX: ffffffff95da0afe RDX: dffffc0000000000 RSI: ffff888100373980 RDI: ffff8880b4f37208 RBP: ffff888100deca00 R08: ffffffff9528f951 R09: 0000000000000001 R10: ffffed10159dbf56 R11: ffff8880acedfab3 R12: ffff8880b9fda498 R13: ffff8880b9fda4f4 R14: 0000000000000050 R15: ffffffff98b622c0 FS: 00007feb51c51700(0000) GS:ffff888106200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000561619547080 CR3: 0000000102bc9000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: throtl_pd_offline+0x98/0x100 blkg_destroy+0x133/0x630 ? blkcg_deactivate_policy+0x2c0/0x2c0 ? lock_timer_base+0x65/0x110 blkg_destroy_all+0x7f/0x100 blkcg_exit_queue+0x3f/0xa5 blk_exit_queue+0x69/0xa0 blk_cleanup_queue+0x226/0x360 __scsi_remove_device+0xb4/0x3c0 scsi_remove_device+0x38/0x60 sdev_store_delete+0x74/0x100 ? dev_driver_string+0xb0/0xb0 dev_attr_store+0x41/0x70 sysfs_kf_write+0x89/0xc0 kernfs_fop_write+0x1b6/0x2e0 ? sysfs_kf_bin_read+0x130/0x130 __vfs_write+0xca/0x420 ? kernel_read+0xc0/0xc0 ? __alloc_fd+0x16f/0x2d0 ? __fd_install+0x95/0x1a0 ? handle_mm_fault+0x3e0/0x560 vfs_write+0x11a/0x2f0 ksys_write+0xb9/0x1e0 ? __x64_sys_read+0x60/0x60 ? kasan_check_write+0x20/0x30 ? filp_close+0xb5/0xf0 __x64_sys_write+0x46/0x60 do_syscall_64+0xd9/0x1f0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The usage of so many blkg is very rare, however, such problem do exist in theory. In order to avoid such warnings, release 'q->queue_lock' for a while when a batch of blkg were destroyed. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Tao Hou <houtao1(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- block/blk-cgroup.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index e592167449aa..c64f0afa27dc 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -364,16 +364,31 @@ static void blkg_destroy(struct blkcg_gq *blkg) */ static void blkg_destroy_all(struct request_queue *q) { +#define BLKG_DESTROY_BATCH 4096 struct blkcg_gq *blkg, *n; + int count; lockdep_assert_held(q->queue_lock); +again: + count = BLKG_DESTROY_BATCH; list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); blkg_destroy(blkg); spin_unlock(&blkcg->lock); + /* + * If the list is too long, the loop can took a long time, + * thus relese the lock for a while when a batch of blkg + * were destroyed. + */ + if (!--count) { + spin_unlock_irq(q->queue_lock); + cond_resched(); + spin_lock_irq(q->queue_lock); + goto again; + } } q->root_blkg = NULL; -- 2.25.1

1 13

kernel sig meeting
by openEuler conference 26 Nov '20

26 Nov '20

2 1

[PATCH 00/26] KVM RISC-V Support
by MingWang Li 25 Nov '20

25 Nov '20

From: Mingwang Li <limingwang(a)huawei.com> euleros inclusion category: feature bugzilla: NA CVE: NA This series adds initial KVM RISC-V support. Currently, we are able to boot Linux on RV64/RV32 Guest with multiple VCPUs. This series can be found in riscv_kvm_v15 branch at: https//github.com/avpatel/linux.git Link: https://gitee.com/openeuler/kernel/issues/I26X9V Alistair Francis (1): Revert "riscv: Use latest system call ABI" Anup Patel (20): RISC-V: Add fragmented config for debug options RISC-V: Enable CPU Hotplug in defconfigs RISC-V: Add Microchip PolarFire kconfig option RISC-V: Initial DTS for Microchip ICICLE board RISC-V: Enable drivers for Microchip PolarFire ICICLE board RISC-V: Add missing jump label initialization RISC-V: Add hypervisor extension related CSR defines RISC-V: Add initial skeletal KVM support RISC-V: KVM: Implement VCPU create, init and destroy functions RISC-V: KVM: Implement VCPU interrupts and requests handling RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls RISC-V: KVM: Implement VCPU world-switch RISC-V: KVM: Handle MMIO exits for VCPU RISC-V: KVM: Handle WFI exits for VCPU RISC-V: KVM: Implement VMID allocator RISC-V: KVM: Implement stage2 page table programming RISC-V: KVM: Implement MMU notifiers RISC-V: KVM: Document RISC-V specific parts of KVM API RISC-V: KVM: Add MAINTAINERS entry RISC-V: Enable KVM for RV64 and RV32 Atish Patra (4): RISC-V: KVM: Add timer functionality RISC-V: KVM: FP lazy save/restore RISC-V: KVM: Implement ONE REG interface for FP registers RISC-V: KVM: Add SBI v0.1 support m34782 (1): Microchip Polarfire SoC Clock Driver Documentation/virt/kvm/api.rst | 193 +++- MAINTAINERS | 11 + arch/riscv/Kconfig | 2 + arch/riscv/Kconfig.socs | 7 + arch/riscv/Makefile | 2 + arch/riscv/boot/dts/Makefile | 1 + arch/riscv/boot/dts/microchip/Makefile | 2 + .../boot/dts/microchip/icicle-kit-es.dts | 307 +++++ arch/riscv/configs/defconfig | 30 +- arch/riscv/configs/extra_debug.config | 21 + arch/riscv/configs/rv32_defconfig | 26 +- arch/riscv/include/asm/csr.h | 89 ++ arch/riscv/include/asm/kvm_host.h | 279 +++++ arch/riscv/include/asm/kvm_types.h | 7 + arch/riscv/include/asm/kvm_vcpu_timer.h | 44 + arch/riscv/include/asm/pgtable-bits.h | 1 + arch/riscv/include/uapi/asm/kvm.h | 128 +++ arch/riscv/include/uapi/asm/unistd.h | 5 +- arch/riscv/kernel/asm-offsets.c | 156 +++ arch/riscv/kernel/setup.c | 1 + arch/riscv/kvm/Kconfig | 36 + arch/riscv/kvm/Makefile | 15 + arch/riscv/kvm/main.c | 118 ++ arch/riscv/kvm/mmu.c | 860 ++++++++++++++ arch/riscv/kvm/tlb.S | 74 ++ arch/riscv/kvm/vcpu.c | 1012 +++++++++++++++++ arch/riscv/kvm/vcpu_exit.c | 701 ++++++++++++ arch/riscv/kvm/vcpu_sbi.c | 173 +++ arch/riscv/kvm/vcpu_switch.S | 400 +++++++ arch/riscv/kvm/vcpu_timer.c | 225 ++++ arch/riscv/kvm/vm.c | 81 ++ arch/riscv/kvm/vmid.c | 120 ++ drivers/clk/Kconfig | 5 + drivers/clk/Makefile | 1 + drivers/clk/microchip/Makefile | 2 + drivers/clk/microchip/clk-pfsoc.c | 508 +++++++++ drivers/clocksource/timer-riscv.c | 8 + include/clocksource/timer-riscv.h | 16 + include/uapi/linux/kvm.h | 8 + 39 files changed, 5621 insertions(+), 54 deletions(-) create mode 100644 arch/riscv/boot/dts/microchip/Makefile create mode 100644 arch/riscv/boot/dts/microchip/icicle-kit-es.dts create mode 100644 arch/riscv/configs/extra_debug.config create mode 100644 arch/riscv/include/asm/kvm_host.h create mode 100644 arch/riscv/include/asm/kvm_types.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_timer.h create mode 100644 arch/riscv/include/uapi/asm/kvm.h create mode 100644 arch/riscv/kvm/Kconfig create mode 100644 arch/riscv/kvm/Makefile create mode 100644 arch/riscv/kvm/main.c create mode 100644 arch/riscv/kvm/mmu.c create mode 100644 arch/riscv/kvm/tlb.S create mode 100644 arch/riscv/kvm/vcpu.c create mode 100644 arch/riscv/kvm/vcpu_exit.c create mode 100644 arch/riscv/kvm/vcpu_sbi.c create mode 100644 arch/riscv/kvm/vcpu_switch.S create mode 100644 arch/riscv/kvm/vcpu_timer.c create mode 100644 arch/riscv/kvm/vm.c create mode 100644 arch/riscv/kvm/vmid.c create mode 100644 drivers/clk/microchip/clk-pfsoc.c create mode 100644 include/clocksource/timer-riscv.h -- 2.19.1

1 26

[PATCH 0/7] fixes CVE-2020-4788
by Yang Yingliang 24 Nov '20

24 Nov '20

Andrew Donnellan (1): powerpc: Fix __clear_user() with KUAP enabled Christophe Leroy (2): powerpc: Add a framework for user access tracking powerpc: Implement user_access_begin and friends Daniel Axtens (1): powerpc/64s: move some exception handlers out of line Nicholas Piggin (3): powerpc/64s: flush L1D on kernel entry powerpc/uaccess: Evaluate macro arguments once, before user access is allowed powerpc/64s: flush L1D after user accesses .../admin-guide/kernel-parameters.txt | 7 + .../powerpc/include/asm/book3s/64/kup-radix.h | 22 +++ arch/powerpc/include/asm/exception-64s.h | 9 +- arch/powerpc/include/asm/feature-fixups.h | 19 +++ arch/powerpc/include/asm/futex.h | 4 + arch/powerpc/include/asm/kup.h | 40 +++++ arch/powerpc/include/asm/security_features.h | 7 + arch/powerpc/include/asm/setup.h | 4 + arch/powerpc/include/asm/uaccess.h | 147 ++++++++++++++---- arch/powerpc/kernel/exceptions-64s.S | 96 +++++++----- arch/powerpc/kernel/setup_64.c | 122 ++++++++++++++- arch/powerpc/kernel/vmlinux.lds.S | 14 ++ arch/powerpc/lib/checksum_wrappers.c | 4 + arch/powerpc/lib/feature-fixups.c | 104 +++++++++++++ arch/powerpc/lib/string_32.S | 4 +- arch/powerpc/lib/string_64.S | 6 +- arch/powerpc/platforms/powernv/setup.c | 17 ++ arch/powerpc/platforms/pseries/setup.c | 8 + 18 files changed, 553 insertions(+), 81 deletions(-) create mode 100644 arch/powerpc/include/asm/book3s/64/kup-radix.h create mode 100644 arch/powerpc/include/asm/kup.h -- 2.25.1

1 7

[PATCH 00/14] backport stable-4.19.159
by Yang Yingliang 23 Nov '20

23 Nov '20

Andrew Donnellan (1): powerpc: Fix __clear_user() with KUAP enabled Christophe Leroy (3): powerpc: Add a framework for user access tracking powerpc: Implement user_access_begin and friends powerpc/8xx: Always fault when _PAGE_ACCESSED is not set Daniel Axtens (1): powerpc/64s: move some exception handlers out of line David Edmondson (1): KVM: x86: clflushopt should be treated as a no-op by emulation Greg Kroah-Hartman (1): Linux 4.19.159 Johannes Berg (1): mac80211: always wind down STA state Nicholas Piggin (3): powerpc/64s: flush L1D on kernel entry powerpc/uaccess: Evaluate macro arguments once, before user access is allowed powerpc/64s: flush L1D after user accesses Nick Desaulniers (1): ACPI: GED: fix -Wformat Salvatore Bonaccorso (1): Revert "perf cs-etm: Move definition of 'traceid_list' global variable from header file" Zhang Changzhong (1): can: proc: can_remove_proc(): silence remove_proc_entry warning .../admin-guide/kernel-parameters.txt | 7 + Makefile | 2 +- .../powerpc/include/asm/book3s/64/kup-radix.h | 22 +++ arch/powerpc/include/asm/exception-64s.h | 9 +- arch/powerpc/include/asm/feature-fixups.h | 19 +++ arch/powerpc/include/asm/futex.h | 4 + arch/powerpc/include/asm/kup.h | 40 +++++ arch/powerpc/include/asm/security_features.h | 7 + arch/powerpc/include/asm/setup.h | 4 + arch/powerpc/include/asm/uaccess.h | 147 ++++++++++++++---- arch/powerpc/kernel/exceptions-64s.S | 96 +++++++----- arch/powerpc/kernel/head_8xx.S | 8 +- arch/powerpc/kernel/setup_64.c | 122 ++++++++++++++- arch/powerpc/kernel/vmlinux.lds.S | 14 ++ arch/powerpc/lib/checksum_wrappers.c | 4 + arch/powerpc/lib/feature-fixups.c | 104 +++++++++++++ arch/powerpc/lib/string_32.S | 4 +- arch/powerpc/lib/string_64.S | 6 +- arch/powerpc/platforms/powernv/setup.c | 17 ++ arch/powerpc/platforms/pseries/setup.c | 8 + arch/x86/kvm/emulate.c | 8 +- drivers/acpi/evged.c | 2 +- net/can/proc.c | 6 +- net/mac80211/sta_info.c | 18 +++ tools/perf/util/cs-etm.c | 3 - tools/perf/util/cs-etm.h | 3 + 26 files changed, 589 insertions(+), 95 deletions(-) create mode 100644 arch/powerpc/include/asm/book3s/64/kup-radix.h create mode 100644 arch/powerpc/include/asm/kup.h -- 2.25.1

1 14

[PATCH] vt: Disable KD_FONT_OP_COPY
by Yang Yingliang 23 Nov '20

23 Nov '20

From: Daniel Vetter <daniel.vetter(a)ffwll.ch> stable inclusion from linux-4.19.156 commit 6612b754ac0c85ca8b1181b5d3ea4461a8c1bbcb CVE: CVE-2020-28974 -------------------------------- commit 3c4e0dff2095c579b142d5a0693257f1c58b4804 upstream. It's buggy: On Fri, Nov 06, 2020 at 10:30:08PM +0800, Minh Yuan wrote: > We recently discovered a slab-out-of-bounds read in fbcon in the latest > kernel ( v5.10-rc2 for now ). The root cause of this vulnerability is that > "fbcon_do_set_font" did not handle "vc->vc_font.data" and > "vc->vc_font.height" correctly, and the patch > <https://lkml.org/lkml/2020/9/27/223> for VT_RESIZEX can't handle this > issue. > > Specifically, we use KD_FONT_OP_SET to set a small font.data for tty6, and > use KD_FONT_OP_SET again to set a large font.height for tty1. After that, > we use KD_FONT_OP_COPY to assign tty6's vc_font.data to tty1's vc_font.data > in "fbcon_do_set_font", while tty1 retains the original larger > height. Obviously, this will cause an out-of-bounds read, because we can > access a smaller vc_font.data with a larger vc_font.height. Further there was only one user ever. - Android's loadfont, busybox and console-tools only ever use OP_GET and OP_SET - fbset documentation only mentions the kernel cmdline font: option, not anything else. - systemd used OP_COPY before release 232 published in Nov 2016 Now unfortunately the crucial report seems to have gone down with gmane, and the commit message doesn't say much. But the pull request hints at OP_COPY being broken https://github.com/systemd/systemd/pull/3651 So in other words, this never worked, and the only project which foolishly every tried to use it, realized that rather quickly too. Instead of trying to fix security issues here on dead code by adding missing checks, fix the entire thing by removing the functionality. Note that systemd code using the OP_COPY function ignored the return value, so it doesn't matter what we're doing here really - just in case a lone server somewhere happens to be extremely unlucky and running an affected old version of systemd. The relevant code from font_copy_to_all_vcs() in systemd was: /* copy font from active VT, where the font was uploaded to */ cfo.op = KD_FONT_OP_COPY; cfo.height = vcs.v_active-1; /* tty1 == index 0 */ (void) ioctl(vcfd, KDFONTOP, &cfo); Note this just disables the ioctl, garbage collecting the now unused callbacks is left for -next. v2: Tetsuo found the old mail, which allowed me to find it on another archive. Add the link too. Acked-by: Peilin Ye <yepeilin.cs(a)gmail.com> Reported-by: Minh Yuan <yuanmingbuaa(a)gmail.com> References: https://lists.freedesktop.org/archives/systemd-devel/2016-June/036935.html References: https://github.com/systemd/systemd/pull/3651 Cc: Greg KH <greg(a)kroah.com> Cc: Peilin Ye <yepeilin.cs(a)gmail.com> Cc: Tetsuo Handa <penguin-kernel(a)i-love.sakura.ne.jp> Signed-off-by: Daniel Vetter <daniel.vetter(a)intel.com> Link: https://lore.kernel.org/r/20201108153806.3140315-1-daniel.vetter@ffwll.ch Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/tty/vt/vt.c | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 758f522f331e..13ea0579f104 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -4574,27 +4574,6 @@ static int con_font_default(struct vc_data *vc, struct console_font_op *op) return rc; } -static int con_font_copy(struct vc_data *vc, struct console_font_op *op) -{ - int con = op->height; - int rc; - - - console_lock(); - if (vc->vc_mode != KD_TEXT) - rc = -EINVAL; - else if (!vc->vc_sw->con_font_copy) - rc = -ENOSYS; - else if (con < 0 || !vc_cons_allocated(con)) - rc = -ENOTTY; - else if (con == vc->vc_num) /* nothing to do */ - rc = 0; - else - rc = vc->vc_sw->con_font_copy(vc, con); - console_unlock(); - return rc; -} - int con_font_op(struct vc_data *vc, struct console_font_op *op) { switch (op->op) { @@ -4605,7 +4584,8 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op) case KD_FONT_OP_SET_DEFAULT: return con_font_default(vc, op); case KD_FONT_OP_COPY: - return con_font_copy(vc, op); + /* was buggy and never really used */ + return -EINVAL; } return -ENOSYS; } -- 2.25.1

1 0

[PATCH 1/3] fbdev, newport_con: Move FONT_EXTRA_WORDS macros into linux/font.h
by Yang Yingliang 23 Nov '20

23 Nov '20

From: Peilin Ye <yepeilin.cs(a)gmail.com> stable inclusion from linux-4.19.151 commit 7b9eaa7241ea2cfa580b854d461be72107a4b35c CVE: CVE-2020-28915 It's prepare for fixing CVE-2020-28915. -------------------------------- commit bb0890b4cd7f8203e3aa99c6d0f062d6acdaad27 upstream. drivers/video/console/newport_con.c is borrowing FONT_EXTRA_WORDS macros from drivers/video/fbdev/core/fbcon.h. To keep things simple, move all definitions into <linux/font.h>. Since newport_con now uses four extra words, initialize the fourth word in newport_set_font() properly. Cc: stable(a)vger.kernel.org Signed-off-by: Peilin Ye <yepeilin.cs(a)gmail.com> Reviewed-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/7fb8bc9b0abc676ada6b7ac0e0bd4… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Reviewed-by: Jason Yan <yanaijie(a)huawei.com> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- drivers/video/console/newport_con.c | 7 +------ drivers/video/fbdev/core/fbcon.h | 7 ------- drivers/video/fbdev/core/fbcon_rotate.c | 1 + drivers/video/fbdev/core/tileblit.c | 1 + include/linux/font.h | 8 ++++++++ 5 files changed, 11 insertions(+), 13 deletions(-) diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 7f2526b43b33..46a6e6568994 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -33,12 +33,6 @@ #define FONT_DATA ((unsigned char *)font_vga_8x16.data) -/* borrowed from fbcon.c */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FONT_EXTRA_WORDS 3 - static unsigned char *font_data[MAX_NR_CONSOLES]; static struct newport_regs *npregs; @@ -519,6 +513,7 @@ static int newport_set_font(int unit, struct console_font *op) FNTSIZE(new_data) = size; FNTCHARCNT(new_data) = op->charcount; REFCOUNT(new_data) = 0; /* usage counter */ + FNTSUM(new_data) = 0; p = new_data; for (i = 0; i < op->charcount; i++) { diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index ac11200fd2d5..609280281a47 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -152,13 +152,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) -/* Font */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FNTSUM(fd) (((int *)(fd))[-4]) -#define FONT_EXTRA_WORDS 4 - /* * Scroll Method */ diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c index c0d445294aa7..ac72d4f85f7d 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.c +++ b/drivers/video/fbdev/core/fbcon_rotate.c @@ -14,6 +14,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" #include "fbcon_rotate.h" diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index eb664dbf96f6..adff8d6ffe6f 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -13,6 +13,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" diff --git a/include/linux/font.h b/include/linux/font.h index d6821769dd1e..0a3639a00b3a 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -57,4 +57,12 @@ extern const struct font_desc *get_default_font(int xres, int yres, /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 +/* Extra word getters */ +#define REFCOUNT(fd) (((int *)(fd))[-1]) +#define FNTSIZE(fd) (((int *)(fd))[-2]) +#define FNTCHARCNT(fd) (((int *)(fd))[-3]) +#define FNTSUM(fd) (((int *)(fd))[-4]) + +#define FONT_EXTRA_WORDS 4 + #endif /* _VIDEO_FONT_H */ -- 2.25.1

1 2