April 2023 - Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS] mm: mem_reliable: Use zone_page_state to count free reliable pages
by Yongqiang Liu 28 Apr '23

28 Apr '23

From: Ma Wupeng <mawupeng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6RKHX CVE: NA -------------------------------- commit ee97b61005df ("mm: Count mirrored pages in buddy system") proposes to use vmstat events (PGALLOC/PGFREE) to count free reliable pages. However, this can be achieved by counting NR_FREE_PAGES for all non-movable zones, which will have better compatibility. Therefore, replace it. Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/linux/mem_reliable.h | 7 ------- mm/mem_reliable.c | 27 +++++++++++++-------------- mm/page_alloc.c | 4 ---- 3 files changed, 13 insertions(+), 25 deletions(-) diff --git a/include/linux/mem_reliable.h b/include/linux/mem_reliable.h index aa3fe77c8a72..c0eff851bbe7 100644 --- a/include/linux/mem_reliable.h +++ b/include/linux/mem_reliable.h @@ -111,12 +111,6 @@ static inline void shmem_reliable_page_counter(struct page *page, int nr_page) percpu_counter_add(&reliable_shmem_used_nr_page, nr_page); } -static inline void mem_reliable_buddy_counter(struct page *page, int nr_page) -{ - if (page_reliable(page)) - this_cpu_add(nr_reliable_buddy_pages, nr_page); -} - static inline bool mem_reliable_shmem_limit_check(void) { return percpu_counter_read_positive(&reliable_shmem_used_nr_page) < @@ -168,7 +162,6 @@ static inline void shmem_reliable_page_counter(struct page *page, int nr_page) static inline bool pagecache_reliable_is_enabled(void) { return false; } static inline bool mem_reliable_status(void) { return false; } -static inline void mem_reliable_buddy_counter(struct page *page, int nr_page) {} static inline bool mem_reliable_shmem_limit_check(void) { return true; } static inline void reliable_lru_add(enum lru_list lru, struct page *page, diff --git a/mm/mem_reliable.c b/mm/mem_reliable.c index f8b8543d7933..524d276db72c 100644 --- a/mm/mem_reliable.c +++ b/mm/mem_reliable.c @@ -28,7 +28,6 @@ unsigned long task_reliable_limit = ULONG_MAX; bool reliable_allow_fallback __read_mostly = true; bool shmem_reliable __read_mostly = true; struct percpu_counter reliable_shmem_used_nr_page __read_mostly; -DEFINE_PER_CPU(long, nr_reliable_buddy_pages); long shmem_reliable_nr_page = LONG_MAX; bool pagecache_use_reliable_mem __read_mostly = true; @@ -176,16 +175,21 @@ static unsigned long total_reliable_mem_sz(void) return atomic_long_read(&total_reliable_mem); } -static unsigned long used_reliable_mem_sz(void) +static inline long free_reliable_pages(void) { - unsigned long nr_page = 0; - struct zone *z; + struct zone *zone; + unsigned long cnt = 0; - for_each_populated_zone(z) - if (zone_idx(z) < ZONE_MOVABLE) - nr_page += zone_page_state(z, NR_FREE_PAGES); + for_each_populated_zone(zone) + if (zone_idx(zone) < ZONE_MOVABLE) + cnt += zone_page_state(zone, NR_FREE_PAGES); - return total_reliable_mem_sz() - nr_page * PAGE_SIZE; + return cnt; +} + +static unsigned long used_reliable_mem_sz(void) +{ + return total_reliable_mem_sz() - (free_reliable_pages() << PAGE_SHIFT); } static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) @@ -198,15 +202,10 @@ void reliable_report_meminfo(struct seq_file *m) { s64 nr_pagecache_pages = 0; s64 nr_anon_pages = 0; - long nr_buddy_pages = 0; - int cpu; if (!mem_reliable_is_enabled()) return; - for_each_possible_cpu(cpu) - nr_buddy_pages += per_cpu(nr_reliable_buddy_pages, cpu); - nr_anon_pages = percpu_counter_sum_positive(&anon_reliable_pages); nr_pagecache_pages = percpu_counter_sum_positive(&pagecache_reliable_pages); @@ -215,7 +214,7 @@ void reliable_report_meminfo(struct seq_file *m) show_val_kb(m, "ReliableUsed: ", used_reliable_mem_sz() >> PAGE_SHIFT); show_val_kb(m, "ReliableTaskUsed: ", nr_anon_pages + nr_pagecache_pages); - show_val_kb(m, "ReliableBuddyMem: ", nr_buddy_pages); + show_val_kb(m, "ReliableBuddyMem: ", free_reliable_pages()); if (shmem_reliable_is_enabled()) { show_val_kb(m, "ReliableShmem: ", diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e722d73a3724..2084b912efa8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1340,7 +1340,6 @@ static void __free_pages_ok(struct page *page, unsigned int order, migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - mem_reliable_buddy_counter(page, 1 << order); free_one_page(page_zone(page), page, pfn, order, migratetype, fpi_flags); local_irq_restore(flags); @@ -2920,7 +2919,6 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) migratetype = get_pcppage_migratetype(page); __count_vm_event(PGFREE); - mem_reliable_buddy_counter(page, 1); /* * We only track unmovable, reclaimable and movable on pcp lists. @@ -3174,7 +3172,6 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone, page = __rmqueue_pcplist(zone, migratetype, pcp, list); if (page) { __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - mem_reliable_buddy_counter(page, -(1 << order)); zone_statistics(preferred_zone, zone); } local_irq_restore(flags); @@ -3223,7 +3220,6 @@ struct page *rmqueue(struct zone *preferred_zone, get_pcppage_migratetype(page)); __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); - mem_reliable_buddy_counter(page, -(1 << order)); zone_statistics(preferred_zone, zone); local_irq_restore(flags); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] writeback, cgroup: fix null-ptr-deref write in bdi_split_work_to_wbs
by Yongqiang Liu 28 Apr '23

28 Apr '23

From: Baokun Li <libaokun1(a)huawei.com> mainline inclusion from mainline-v6.3-rc8 commit 1ba1199ec5747f475538c0d25a32804e5ba1dfde category: bugfix bugzilla: 188601, https://gitee.com/openeuler/kernel/issues/I6TNTC CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- KASAN report null-ptr-deref: ================================================================== BUG: KASAN: null-ptr-deref in bdi_split_work_to_wbs+0x5c5/0x7b0 Write of size 8 at addr 0000000000000000 by task sync/943 CPU: 5 PID: 943 Comm: sync Tainted: 6.3.0-rc5-next-20230406-dirty #461 Call Trace: <TASK> dump_stack_lvl+0x7f/0xc0 print_report+0x2ba/0x340 kasan_report+0xc4/0x120 kasan_check_range+0x1b7/0x2e0 __kasan_check_write+0x24/0x40 bdi_split_work_to_wbs+0x5c5/0x7b0 sync_inodes_sb+0x195/0x630 sync_inodes_one_sb+0x3a/0x50 iterate_supers+0x106/0x1b0 ksys_sync+0x98/0x160 [...] ================================================================== The race that causes the above issue is as follows: cpu1 cpu2 -------------------------|------------------------- inode_switch_wbs INIT_WORK(&isw->work, inode_switch_wbs_work_fn) queue_rcu_work(isw_wq, &isw->work) // queue_work async inode_switch_wbs_work_fn wb_put_many(old_wb, nr_switched) percpu_ref_put_many ref->data->release(ref) cgwb_release queue_work(cgwb_release_wq, &wb->release_work) // queue_work async &wb->release_work cgwb_release_workfn ksys_sync iterate_supers sync_inodes_one_sb sync_inodes_sb bdi_split_work_to_wbs kmalloc(sizeof(*work), GFP_ATOMIC) // alloc memory failed percpu_ref_exit ref->data = NULL kfree(data) wb_get(wb) percpu_ref_get(&wb->refcnt) percpu_ref_get_many(ref, 1) atomic_long_add(nr, &ref->data->count) atomic64_add(i, v) // trigger null-ptr-deref bdi_split_work_to_wbs() traverses &bdi->wb_list to split work into all wbs. If the allocation of new work fails, the on-stack fallback will be used and the reference count of the current wb is increased afterwards. If cgroup writeback membership switches occur before getting the reference count and the current wb is released as old_wd, then calling wb_get() or wb_put() will trigger the null pointer dereference above. This issue was introduced in v4.3-rc7 (see fix tag1). Both sync_inodes_sb() and __writeback_inodes_sb_nr() calls to bdi_split_work_to_wbs() can trigger this issue. For scenarios called via sync_inodes_sb(), originally commit 7fc5854f8c6e ("writeback: synchronize sync(2) against cgroup writeback membership switches") reduced the possibility of the issue by adding wb_switch_rwsem, but in v5.14-rc1 (see fix tag2) removed the "inode_io_list_del_locked(inode, old_wb)" from inode_switch_wbs_work_fn() so that wb->state contains WB_has_dirty_io, thus old_wb is not skipped when traversing wbs in bdi_split_work_to_wbs(), and the issue becomes easily reproducible again. To solve this problem, percpu_ref_exit() is called under RCU protection to avoid race between cgwb_release_workfn() and bdi_split_work_to_wbs(). Moreover, replace wb_get() with wb_tryget() in bdi_split_work_to_wbs(), and skip the current wb if wb_tryget() fails because the wb has already been shutdown. Link: https://lkml.kernel.org/r/20230410130826.1492525-1-libaokun1@huawei.com Fixes: b817525a4a80 ("writeback: bdi_writeback iteration must not skip dying ones") Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Acked-by: Tejun Heo <tj(a)kernel.org> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Andreas Dilger <adilger.kernel(a)dilger.ca> Cc: Christian Brauner <brauner(a)kernel.org> Cc: Dennis Zhou <dennis(a)kernel.org> Cc: Hou Tao <houtao1(a)huawei.com> Cc: yangerkun <yangerkun(a)huawei.com> Cc: Zhang Yi <yi.zhang(a)huawei.com> Cc: Jens Axboe <axboe(a)kernel.dk> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Conflicts: mm/backing-dev.c Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/fs-writeback.c | 17 ++++++++++------- mm/backing-dev.c | 12 ++++++++++-- 2 files changed, 20 insertions(+), 9 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 23a632f02839..dd53d00a2583 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -884,6 +884,16 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, continue; } + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; @@ -892,13 +902,6 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, work->done = &fallback_work_done; wb_queue_work(wb, work); - - /* - * Pin @wb so that it stays on @bdi->wb_list. This allows - * continuing iteration from @wb after dropping and - * regrabbing rcu read lock. - */ - wb_get(wb); last_wb = wb; rcu_read_unlock(); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f80d5c2ff420..c5caa7e91935 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -487,6 +487,15 @@ void wb_congested_put(struct bdi_writeback_congested *congested) kfree(congested); } +static void cgwb_free_rcu(struct rcu_head *rcu_head) +{ + struct bdi_writeback *wb = container_of(rcu_head, + struct bdi_writeback, rcu); + + percpu_ref_exit(&wb->refcnt); + kfree(wb); +} + static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, @@ -504,9 +513,8 @@ static void cgwb_release_workfn(struct work_struct *work) blkcg_cgwb_put(blkcg); fprop_local_destroy_percpu(&wb->memcg_completions); - percpu_ref_exit(&wb->refcnt); wb_exit(wb); - kfree_rcu(wb, rcu); + call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/6] vfs: add rcu argument to ->get_acl() callback
by Yongqiang Liu 28 Apr '23

28 Apr '23

From: Miklos Szeredi <mszeredi(a)redhat.com> mainline inclusion from mainline-v5.15-rc1 commit 0cad6246621b5887d5b33fea84219d2a71f2f99a category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/I6ZCW0 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Add a rcu argument to the ->get_acl() callback to allow get_cached_acl_rcu() to call the ->get_acl() method in the next patch. Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> [chengzhihao: rename get_acl to get_acl2 to prevent KABI changes, and only backport(realize) overlayfs] Conflicts: fs/overlayfs/dir.c fs/overlayfs/inode.c fs/overlayfs/overlayfs.h fs/posix_acl.c include/linux/fs.h Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 9 ++++++--- fs/overlayfs/overlayfs.h | 2 +- fs/posix_acl.c | 7 +++++-- include/linux/fs.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8570e755a392..cdbb916aa636 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1292,6 +1292,6 @@ const struct inode_operations ovl_dir_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 3eabe457a5d5..3aa33c18cb80 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -421,12 +421,15 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } -struct posix_acl *ovl_get_acl(struct inode *inode, int type) +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) { struct inode *realinode = ovl_inode_real(inode); const struct cred *old_cred; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; @@ -480,7 +483,7 @@ static const struct inode_operations ovl_file_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, .fiemap = ovl_fiemap, }; @@ -498,7 +501,7 @@ static const struct inode_operations ovl_special_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 76e096ad2ef9..38fada5fa552 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -358,7 +358,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); -struct posix_acl *ovl_get_acl(struct inode *inode, int type); +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu); int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(const char *name); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 2fd0fde16fe1..8e3fe9cbb28c 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -133,11 +133,14 @@ struct posix_acl *get_acl(struct inode *inode, int type) * If the filesystem doesn't have a get_acl() function at all, we'll * just create the negative cache entry. */ - if (!inode->i_op->get_acl) { + if (!inode->i_op->get_acl && !inode->i_op->get_acl2) { set_cached_acl(inode, type, NULL); return NULL; } - acl = inode->i_op->get_acl(inode, type); + if (inode->i_op->get_acl) + acl = inode->i_op->get_acl(inode, type); + else + acl = inode->i_op->get_acl2(inode, type, false); if (IS_ERR(acl)) { /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 6363c0a67af5..bd3e09a3c9a9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1838,6 +1838,7 @@ struct inode_operations { const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl2)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); -- 2.25.1

1 6

[PATCH OLK-5.10 0/1] Modifying SAS Registers
by Yihang Li 28 Apr '23

28 Apr '23

From: xiabing <xiabing12(a)h-partners.com> The register is modified to solve the problem that the link is unstable and the link bit error occurs when the screen is refreshed. Yihang Li (1): scsi: hisi_sas: Configure the initialization registers according to HBA model drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) -- 2.30.0

1 1

[PATCH openEuler-1.0-LTS 1/6] vfs: add rcu argument to ->get_acl() callback
by Yongqiang Liu 28 Apr '23

28 Apr '23

From: Miklos Szeredi <mszeredi(a)redhat.com> mainline inclusion from mainline-v5.15-rc1 commit 0cad6246621b5887d5b33fea84219d2a71f2f99a category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/I6ZCW0 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Add a rcu argument to the ->get_acl() callback to allow get_cached_acl_rcu() to call the ->get_acl() method in the next patch. Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> [chengzhihao: rename get_acl to get_acl2 to prevent KABI changes, and only backport(realize) overlayfs] Conflicts: fs/overlayfs/dir.c fs/overlayfs/inode.c fs/overlayfs/overlayfs.h fs/posix_acl.c include/linux/fs.h Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 9 ++++++--- fs/overlayfs/overlayfs.h | 2 +- fs/posix_acl.c | 7 +++++-- include/linux/fs.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8570e755a392..cdbb916aa636 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1292,6 +1292,6 @@ const struct inode_operations ovl_dir_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 3eabe457a5d5..3aa33c18cb80 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -421,12 +421,15 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } -struct posix_acl *ovl_get_acl(struct inode *inode, int type) +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) { struct inode *realinode = ovl_inode_real(inode); const struct cred *old_cred; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; @@ -480,7 +483,7 @@ static const struct inode_operations ovl_file_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, .fiemap = ovl_fiemap, }; @@ -498,7 +501,7 @@ static const struct inode_operations ovl_special_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 76e096ad2ef9..38fada5fa552 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -358,7 +358,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); -struct posix_acl *ovl_get_acl(struct inode *inode, int type); +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu); int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(const char *name); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 2fd0fde16fe1..8e3fe9cbb28c 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -133,11 +133,14 @@ struct posix_acl *get_acl(struct inode *inode, int type) * If the filesystem doesn't have a get_acl() function at all, we'll * just create the negative cache entry. */ - if (!inode->i_op->get_acl) { + if (!inode->i_op->get_acl && !inode->i_op->get_acl2) { set_cached_acl(inode, type, NULL); return NULL; } - acl = inode->i_op->get_acl(inode, type); + if (inode->i_op->get_acl) + acl = inode->i_op->get_acl(inode, type); + else + acl = inode->i_op->get_acl2(inode, type, false); if (IS_ERR(acl)) { /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 6363c0a67af5..bd3e09a3c9a9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1838,6 +1838,7 @@ struct inode_operations { const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl2)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); -- 2.25.1

1 5

[PATCH OLK-5.10 1/1] scsi: hisi_sas: Configure the initialization registers according to HBA model
by Yihang Li 28 Apr '23

28 Apr '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6ZGK8 CVE: NA ---------------------------------------------------------------------- We use init_reg_v3_hw() to set some registers, for the latest HBA devices, some of these HW registers are set through firmware. Therefore, different HBA models are distinguished through pci_dev->revision. Signed-off-by: Yihang Li <liyihang9(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: xiabing <xiabing12(a)h-partners.com> --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index eeb40ad079c8..6e40c4c06650 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -617,12 +617,12 @@ static void interrupt_enable_v3_hw(struct hisi_hba *hisi_hba) static void init_reg_v3_hw(struct hisi_hba *hisi_hba) { + struct pci_dev *pdev = hisi_hba->pci_dev; int i, j; /* Global registers init */ hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, (u32)((1ULL << hisi_hba->queue_count) - 1)); - hisi_sas_write32(hisi_hba, SAS_AXI_USER3, 0); hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400); hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108); hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1); @@ -642,6 +642,9 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) hisi_sas_write32(hisi_hba, ARQOS_ARCACHE_CFG, 0xf0f0); hisi_sas_write32(hisi_hba, HYPER_STREAM_ID_EN_CFG, 1); + if (pdev->revision < 0x30) + hisi_sas_write32(hisi_hba, SAS_AXI_USER3, 0); + interrupt_enable_v3_hw(hisi_hba); for (i = 0; i < hisi_hba->n_phy; i++) { enum sas_linkrate max; @@ -659,7 +662,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) prog_phy_link_rate |= hisi_sas_get_prog_phy_linkrate_mask(max); hisi_sas_phy_write32(hisi_hba, i, PROG_PHY_LINK_RATE, prog_phy_link_rate); - hisi_sas_phy_write32(hisi_hba, i, SERDES_CFG, 0xffc00); hisi_sas_phy_write32(hisi_hba, i, SAS_RX_TRAIN_TIMER, 0x13e80); hisi_sas_phy_write32(hisi_hba, i, CHL_INT0, 0xffffffff); hisi_sas_phy_write32(hisi_hba, i, CHL_INT1, 0xffffffff); @@ -670,13 +672,18 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1); hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120); hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01); - hisi_sas_phy_write32(hisi_hba, i, SAS_SSP_CON_TIMER_CFG, 0x32); hisi_sas_phy_write32(hisi_hba, i, SAS_EC_INT_COAL_TIME, 0x30f4240); - /* used for 12G negotiate */ - hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e); hisi_sas_phy_write32(hisi_hba, i, AIP_LIMIT, 0x2ffff); + /* set value through firmware for the latest HBA */ + if (pdev->revision < 0x30) { + hisi_sas_phy_write32(hisi_hba, i, SAS_SSP_CON_TIMER_CFG, 0x32); + hisi_sas_phy_write32(hisi_hba, i, SERDES_CFG, 0xffc00); + /* used for 12G negotiate */ + hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e); + } + /* get default FFE configuration for BIST */ for (j = 0; j < FFE_CFG_MAX; j++) { u32 val = hisi_sas_phy_read32(hisi_hba, i, -- 2.30.0

1 0

[PATCH OLK-5.10 0/3] Introduce QOS_SMT_EXPELL priority reversion mechanism
by Hui Tang 28 Apr '23

28 Apr '23

From: Guan Jing <guanjing6(a)huawei.com> Guan Jing (3): sched/fair: Start tracking qos_offline tasks count in cfs_rq sched/fair: Introduce QOS_SMT_EXPELL priority reversion mechanism sched/fair: Add cmdline nosmtexpell kernel/sched/fair.c | 150 +++++++++++++++++++++++++++++++++++++------ kernel/sched/sched.h | 20 ++++++ 2 files changed, 152 insertions(+), 18 deletions(-) -- 2.17.1

1 3

[OLK-5.10 v3 00/16] bugfix for bonding
by Chengchang Tang 27 Apr '23

27 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> This group of patches fix bonding-related errors. Junxian Huang (16): RDMA/hns: Move bond_work from hns_roce_dev to hns_roce_bond_group RDMA/hns: Apply XArray for Bond ID allocation RDMA/hns: Delete a useless assignment to bond_state RDMA/hns: Initial value assignment cleanup for RoCE Bonding variables RDMA/hns: Remove the struct member 'bond_grp' from hns_roce_dev RDMA/hns: Simplify the slave uninit logic of RoCE bonding operations RDMA/hns: Fix the driver uninit order during bond setting RDMA/hns: Fix the counting error of slave number RDMA/hns: Support reset recovery for RoCE bonding RDMA/hns: Rename hns_roce_bond_info_record() to make sense RDMA/hns: Fix the repetitive workqueue mission in RoCE Bonding RDMA/hns: Fix the counting error of bonding with more than 2 slaves RDMA/hns: Get real-time port state of bonding slave RDMA/hns: Set IB port state depending on upper device for RoCE bonding RDMA/hns: Support dispatching IB event for RoCE bonding RDMA/hns: Fix a missing constraint for slave num in RoCE Bonding drivers/infiniband/hw/hns/hns_roce_bond.c | 540 +++++++++++--------- drivers/infiniband/hw/hns/hns_roce_bond.h | 15 +- drivers/infiniband/hw/hns/hns_roce_device.h | 5 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 79 ++- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 10 +- drivers/infiniband/hw/hns/hns_roce_main.c | 58 ++- 6 files changed, 421 insertions(+), 286 deletions(-) -- 2.30.0

1 17

[OLK-5.10 v2 0/2] bugfix for rq inline
by Chengchang Tang 27 Apr '23

27 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Luoyouming (2): RDMA/hns: Fix the inconsistency between the rq inline bit and the community RDMA/hns: Fix the compatibility flag problem drivers/infiniband/hw/hns/hns_roce_device.h | 4 +--- drivers/infiniband/hw/hns/hns_roce_main.c | 6 ++++-- 2 files changed, 5 insertions(+), 5 deletions(-) -- 2.30.0

1 2

[PATCH OLK-5.10 v2] net: hns3: add support handling tx dhcp packets for ROH
by Ke Chen 27 Apr '23

27 Apr '23

driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BSMN ----------------------------------------------------------------------- For ROH distributed scenario, EID is allocated by DHCP mode. Driver needs to convert the origin MAC address to EID format, and updates the destination MAC, chaddr and client id(if exists) when transmit DHCP packets. Meantime, the chaddr field should follow the source mac address, in order to make the dhcp server reply to the right client. For the payload of dhcp packet changed, so the checksum of L4 should be calculated too. Signed-off-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Ke Chen <chenke54(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 174 +++++++++++++++++- .../net/ethernet/hisilicon/hns3/hns3_enet.h | 50 +++++ .../hisilicon/hns3/hns3pf/hclge_main.c | 16 ++ 3 files changed, 235 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf79cd69c..95cd61b1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1165,6 +1165,142 @@ static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring, } } +static struct hns3_dhcp_packet *hns3_get_dhcp_packet(struct sk_buff *skb, + int *dhcp_len) +{ + struct hns3_dhcp_packet *dhcp; + union l4_hdr_info l4; + int l4_payload_len; + + l4.hdr = skb_transport_header(skb); + if (l4.udp->dest != htons(HNS3_DHCP_CLIENT_PORT) || + l4.udp->source != htons(HNS3_DHCP_SERVER_PORT)) + return NULL; + + dhcp = (struct hns3_dhcp_packet *)(l4.hdr + sizeof(struct udphdr)); + l4_payload_len = ntohs(l4.udp->len) - sizeof(struct udphdr); + if (l4_payload_len < offsetof(struct hns3_dhcp_packet, options) || + dhcp->hlen != ETH_ALEN || + dhcp->cookie != htonl(HNS3_DHCP_MAGIC)) + return NULL; + + *dhcp_len = l4_payload_len; + return dhcp; +} + +static u8 *hns3_dhcp_option_scan(struct hns3_dhcp_packet *packet, + struct hns3_dhcp_opt_state *opt_state) +{ + int opt_len; + u8 *cur_opt; + + /* option bytes: [code][len][data0~data[len-1]] */ + while (opt_state->rem > 0) { + switch (opt_state->opt_ptr[DHCP_OPT_CODE]) { + /* option padding and end have no len and data byte. */ + case DHCP_OPT_PADDING: + opt_state->rem--; + opt_state->opt_ptr++; + break; + case DHCP_OPT_END: + if (DHCP_OVERLOAD_USE_FILE(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_FILE_USED; + opt_state->opt_ptr = packet->file; + opt_state->rem = sizeof(packet->file); + break; + } + if (DHCP_OVERLOAD_USE_SNAME(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_SNAME_USED; + opt_state->opt_ptr = packet->sname; + opt_state->rem = sizeof(packet->sname); + break; + } + return NULL; + default: + if (opt_state->rem <= DHCP_OPT_LEN) + return NULL; + /* opt_len includes code, len and data bytes */ + opt_len = opt_state->opt_ptr[DHCP_OPT_LEN] + + DHCP_OPT_DATA; + cur_opt = opt_state->opt_ptr; + if (opt_state->rem < opt_len) + return NULL; + + opt_state->opt_ptr += opt_len; + opt_state->rem -= opt_len; + if (cur_opt[DHCP_OPT_CODE] == DHCP_OPT_OVERLOAD) { + opt_state->overload_flag |= + cur_opt[DHCP_OPT_DATA]; + break; + } + return cur_opt; + } + } + + return NULL; +} + +static void hns3_dhcp_update_option61(struct hns3_nic_priv *priv, + struct hns3_dhcp_packet *packet, + int dhcp_len) +{ + struct hns3_dhcp_opt_state opt_state; + u8 *cur_opt; + + opt_state.opt_ptr = packet->options; + opt_state.rem = dhcp_len - offsetof(struct hns3_dhcp_packet, options); + opt_state.overload_flag = 0; + + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + while (cur_opt) { + if (cur_opt[DHCP_OPT_CODE] != DHCP_OPT_CLIENT_ID) { + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + continue; + } + if (cur_opt[DHCP_OPT_LEN] > ETH_ALEN) + ether_addr_copy(&cur_opt[DHCP_CLIENT_ID_MAC_OFT], + priv->roh_perm_mac); + break; + } +} + +static void hns3_dhcp_cal_l4_csum(struct sk_buff *skb) +{ + union l3_hdr_info l3; + union l4_hdr_info l4; + __wsum csum = 0; + int offset; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + return; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + offset = skb_transport_offset(skb); + l4.udp->check = 0; + csum = csum_partial(l4.udp, ntohs(l4.udp->len), 0); + l4.udp->check = csum_tcpudp_magic(l3.v4->saddr, l3.v4->daddr, + skb->len - offset, IPPROTO_UDP, csum); +} + +static void hns3_dhcp_packet_convert(struct hns3_nic_priv *priv, + struct sk_buff *skb, + struct hns3_dhcp_packet *dhcp, + int dhcp_len) +{ + struct ethhdr *l2hdr = eth_hdr(skb); + + if (!dhcp) + return; + + ether_addr_copy(dhcp->chaddr, l2hdr->h_source); + hns3_dhcp_update_option61(priv, dhcp, dhcp_len); + /* for l4 payload changed, need to re-calculate the csum */ + hns3_dhcp_cal_l4_csum(skb); +} + static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs, u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes) { @@ -1716,7 +1852,20 @@ static int hns3_handle_csum_partial(struct hns3_enet_ring *ring, return 0; } -static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, +static bool hns3_roh_check_udpv4(struct sk_buff *skb) +{ + union l3_hdr_info l3; + + l3.hdr = skb_network_header(skb); + if (skb->protocol != htons(ETH_P_IP) || + l3.v4->version != IP_VERSION_IPV4) + return false; + + return l3.v4->protocol == IPPROTO_UDP; +} + +static int hns3_fill_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc *desc, struct hns3_desc_cb *desc_cb) { @@ -1741,6 +1890,15 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, hnae3_set_field(param.paylen_fdop_ol4cs, HNS3_TXD_FD_OP_M, HNS3_TXD_FD_OP_S, fd_op); + if (hnae3_check_roh_mac_type(priv->ae_handle) && + hns3_roh_check_udpv4(skb)) { + struct hns3_dhcp_packet *dhcp; + int dhcp_len; + + dhcp = hns3_get_dhcp_packet(skb, &dhcp_len); + hns3_dhcp_packet_convert(priv, skb, dhcp, dhcp_len); + } + /* Set txbd */ desc->tx.ol_type_vlan_len_msec = cpu_to_le32(param.ol_type_vlan_len_msec); @@ -2338,15 +2496,16 @@ static int hns3_handle_desc_filling(struct hns3_enet_ring *ring, return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); } -static int hns3_handle_skb_desc(struct hns3_enet_ring *ring, +static int hns3_handle_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc_cb *desc_cb, int next_to_use_head) { int ret; - ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use], - desc_cb); + ret = hns3_fill_skb_desc(priv, ring, skb, + &ring->desc[ring->next_to_use], desc_cb); if (unlikely(ret < 0)) goto fill_err; @@ -2395,7 +2554,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) goto out_err_tx_ok; } - ret = hns3_handle_skb_desc(ring, skb, desc_cb, ring->next_to_use); + ret = hns3_handle_skb_desc(priv, ring, skb, desc_cb, ring->next_to_use); if (unlikely(ret <= 0)) goto out_err_tx_ok; @@ -5226,6 +5385,10 @@ static int hns3_init_mac_addr(struct net_device *netdev) return 0; } + if (hnae3_check_roh_mac_type(h) && + is_zero_ether_addr(priv->roh_perm_mac)) + ether_addr_copy(priv->roh_perm_mac, netdev->dev_addr); + if (h->ae_algo->ops->set_mac_addr) ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); @@ -5377,6 +5540,7 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); + eth_zero_addr(priv->roh_perm_mac); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index ccfd38b00..85c352fff 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -604,6 +604,56 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u8 roh_perm_mac[ETH_ALEN]; +}; + +#define HNS3_DHCP_SERVER_PORT 68 +#define HNS3_DHCP_CLIENT_PORT 67 +#define HNS3_DHCP_MAGIC 0x63825363 +#define DHCP_OPT_CODE 0 +#define DHCP_OPT_LEN 1 +#define DHCP_OPT_DATA 2 +#define DHCP_CLIENT_ID_LEN 7 +#define DHCP_CLIENT_ID_MAC_OFT 3 +#define DHCP_OVERLOAD_FILE 0x1 +#define DHCP_OVERLOAD_SNAME 0x2 +#define DHCP_OVERLOAD_FILE_USED 0x101 +#define DHCP_OVERLOAD_SNAME_USED 0x202 +#define DHCP_OVERLOAD_USE_FILE(x) \ + (((x) & DHCP_OVERLOAD_FILE_USED) == DHCP_OVERLOAD_FILE) +#define DHCP_OVERLOAD_USE_SNAME(x) \ + (((x) & DHCP_OVERLOAD_SNAME_USED) == DHCP_OVERLOAD_SNAME) + +enum DHCP_OPTION_CODES { + DHCP_OPT_PADDING = 0, + DHCP_OPT_OVERLOAD = 52, + DHCP_OPT_CLIENT_ID = 61, + DHCP_OPT_END = 255 +}; + +struct hns3_dhcp_packet { + u8 op; + u8 htype; + u8 hlen; + u8 hops; + u32 xid; + u16 secs; + u16 flags; + u32 ciaddr; + u32 yiaddr; + u32 siaddr_nip; + u32 gateway_nip; + u8 chaddr[16]; /* link-layer client hardware address (MAC) */ + u8 sname[64]; + u8 file[128]; + u32 cookie; /* DHCP magic bytes: 0x63825363 */ + u8 options[312]; +}; + +struct hns3_dhcp_opt_state { + u8 *opt_ptr; /* refer to current option item */ + int rem; /* remain bytes in options */ + u32 overload_flag; /* whether use file and sname field as options */ }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index eea175484..947ffde02 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2866,12 +2866,28 @@ static void hclge_get_fec(struct hnae3_handle *handle, u8 *fec_ability, if (fec_mode) *fec_mode = mac->fec_mode; } + +static void hclge_roh_convert_mac_addr(struct hclge_dev *hdev) +{ +#define HCLGE_ROH_EID_MASK_BYTE 3 + + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_handle *handle = &vport->nic; + + if (hnae3_check_roh_mac_type(handle)) { + if (!is_valid_ether_addr(hdev->hw.mac.mac_addr)) + random_ether_addr(hdev->hw.mac.mac_addr); + memset(hdev->hw.mac.mac_addr, 0, HCLGE_ROH_EID_MASK_BYTE); + } +} + static int hclge_mac_init(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; int ret; hclge_mac_type_init(hdev); + hclge_roh_convert_mac_addr(hdev); hdev->support_sfp_query = true; hdev->hw.mac.duplex = HCLGE_MAC_FULL; -- 2.30.0

1 0